Merge tag 'fsnotify_for_v5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull fsnotify updates from Jan Kara:
 "fsnotify speedups when notification actually isn't used and support
  for identifying processes which caused fanotify events through pidfd
  instead of normal pid"

* tag 'fsnotify_for_v5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
  fsnotify: optimize the case of no marks of any type
  fsnotify: count all objects with attached connectors
  fsnotify: count s_fsnotify_inode_refs for attached connectors
  fsnotify: replace igrab() with ihold() on attach connector
  fanotify: add pidfd support to the fanotify API
  fanotify: introduce a generic info record copying helper
  fanotify: minor cosmetic adjustments to fid labels
  kernel/pid.c: implement additional checks upon pidfd_create() parameters
  kernel/pid.c: remove static qualifier from pidfd_create()

4 files changed, 235 insertions, 89 deletions

diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 28b67cb9458d..6facdf476255 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/fanotify.h>
 #include <linux/fcntl.h>
+#include <linux/fdtable.h>
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/anon_inodes.h>
@@ -109,8 +110,10 @@ 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 \
+#define FANOTIFY_FID_INFO_HDR_LEN \
 	(sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle))
+#define FANOTIFY_PIDFD_INFO_HDR_LEN \
+	sizeof(struct fanotify_event_info_pidfd)
 
 static int fanotify_fid_info_len(int fh_len, int name_len)
 {
@@ -119,10 +122,11 @@ static int fanotify_fid_info_len(int fh_len, int name_len)
 	if (name_len)
 		info_len += name_len + 1;
 
-	return roundup(FANOTIFY_INFO_HDR_LEN + info_len, FANOTIFY_EVENT_ALIGN);
+	return roundup(FANOTIFY_FID_INFO_HDR_LEN + info_len,
+		       FANOTIFY_EVENT_ALIGN);
 }
 
-static int fanotify_event_info_len(unsigned int fid_mode,
+static int fanotify_event_info_len(unsigned int info_mode,
 				   struct fanotify_event *event)
 {
 	struct fanotify_info *info = fanotify_event_info(event);
@@ -133,7 +137,8 @@ static int fanotify_event_info_len(unsigned int fid_mode,
 
 	if (dir_fh_len) {
 		info_len += fanotify_fid_info_len(dir_fh_len, info->name_len);
-	} else if ((fid_mode & FAN_REPORT_NAME) && (event->mask & FAN_ONDIR)) {
+	} else if ((info_mode & FAN_REPORT_NAME) &&
+		   (event->mask & FAN_ONDIR)) {
 		/*
 		 * With group flag FAN_REPORT_NAME, if name was not recorded in
 		 * event on a directory, we will report the name ".".
@@ -141,6 +146,9 @@ static int fanotify_event_info_len(unsigned int fid_mode,
 		dot_len = 1;
 	}
 
+	if (info_mode & FAN_REPORT_PIDFD)
+		info_len += FANOTIFY_PIDFD_INFO_HDR_LEN;
+
 	if (fh_len)
 		info_len += fanotify_fid_info_len(fh_len, dot_len);
 
@@ -176,7 +184,7 @@ static struct fanotify_event *get_one_event(struct fsnotify_group *group,
 	size_t event_size = FAN_EVENT_METADATA_LEN;
 	struct fanotify_event *event = NULL;
 	struct fsnotify_event *fsn_event;
-	unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
+	unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES);
 
 	pr_debug("%s: group=%p count=%zd\n", __func__, group, count);
 
@@ -186,8 +194,8 @@ static struct fanotify_event *get_one_event(struct fsnotify_group *group,
 		goto out;
 
 	event = FANOTIFY_E(fsn_event);
-	if (fid_mode)
-		event_size += fanotify_event_info_len(fid_mode, event);
+	if (info_mode)
+		event_size += fanotify_event_info_len(info_mode, event);
 
 	if (event_size > count) {
 		event = ERR_PTR(-EINVAL);
@@ -308,9 +316,10 @@ static int process_access_response(struct fsnotify_group *group,
 	return -ENOENT;
 }
 
-static int copy_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
-			     int info_type, const char *name, size_t name_len,
-			     char __user *buf, size_t count)
+static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
+				 int info_type, const char *name,
+				 size_t name_len,
+				 char __user *buf, size_t count)
 {
 	struct fanotify_event_info_fid info = { };
 	struct file_handle handle = { };
@@ -403,6 +412,117 @@ static int copy_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
 	return info_len;
 }
 
+static int copy_pidfd_info_to_user(int pidfd,
+				   char __user *buf,
+				   size_t count)
+{
+	struct fanotify_event_info_pidfd info = { };
+	size_t info_len = FANOTIFY_PIDFD_INFO_HDR_LEN;
+
+	if (WARN_ON_ONCE(info_len > count))
+		return -EFAULT;
+
+	info.hdr.info_type = FAN_EVENT_INFO_TYPE_PIDFD;
+	info.hdr.len = info_len;
+	info.pidfd = pidfd;
+
+	if (copy_to_user(buf, &info, info_len))
+		return -EFAULT;
+
+	return info_len;
+}
+
+static int copy_info_records_to_user(struct fanotify_event *event,
+				     struct fanotify_info *info,
+				     unsigned int info_mode, int pidfd,
+				     char __user *buf, size_t count)
+{
+	int ret, total_bytes = 0, info_type = 0;
+	unsigned int fid_mode = info_mode & FANOTIFY_FID_BITS;
+	unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD;
+
+	/*
+	 * Event info records order is as follows: dir fid + name, child fid.
+	 */
+	if (fanotify_event_dir_fh_len(event)) {
+		info_type = info->name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME :
+					     FAN_EVENT_INFO_TYPE_DFID;
+		ret = copy_fid_info_to_user(fanotify_event_fsid(event),
+					    fanotify_info_dir_fh(info),
+					    info_type,
+					    fanotify_info_name(info),
+					    info->name_len, buf, count);
+		if (ret < 0)
+			return ret;
+
+		buf += ret;
+		count -= ret;
+		total_bytes += ret;
+	}
+
+	if (fanotify_event_object_fh_len(event)) {
+		const char *dot = NULL;
+		int dot_len = 0;
+
+		if (fid_mode == FAN_REPORT_FID || info_type) {
+			/*
+			 * With only group flag FAN_REPORT_FID only type FID is
+			 * reported. Second info record type is always FID.
+			 */
+			info_type = FAN_EVENT_INFO_TYPE_FID;
+		} else if ((fid_mode & FAN_REPORT_NAME) &&
+			   (event->mask & FAN_ONDIR)) {
+			/*
+			 * With group flag FAN_REPORT_NAME, if name was not
+			 * recorded in an event on a directory, report the name
+			 * "." with info type DFID_NAME.
+			 */
+			info_type = FAN_EVENT_INFO_TYPE_DFID_NAME;
+			dot = ".";
+			dot_len = 1;
+		} else if ((event->mask & ALL_FSNOTIFY_DIRENT_EVENTS) ||
+			   (event->mask & FAN_ONDIR)) {
+			/*
+			 * With group flag FAN_REPORT_DIR_FID, a single info
+			 * record has type DFID for directory entry modification
+			 * event and for event on a directory.
+			 */
+			info_type = FAN_EVENT_INFO_TYPE_DFID;
+		} else {
+			/*
+			 * With group flags FAN_REPORT_DIR_FID|FAN_REPORT_FID,
+			 * a single info record has type FID for event on a
+			 * non-directory, when there is no directory to report.
+			 * For example, on FAN_DELETE_SELF event.
+			 */
+			info_type = FAN_EVENT_INFO_TYPE_FID;
+		}
+
+		ret = copy_fid_info_to_user(fanotify_event_fsid(event),
+					    fanotify_event_object_fh(event),
+					    info_type, dot, dot_len,
+					    buf, count);
+		if (ret < 0)
+			return ret;
+
+		buf += ret;
+		count -= ret;
+		total_bytes += ret;
+	}
+
+	if (pidfd_mode) {
+		ret = copy_pidfd_info_to_user(pidfd, buf, count);
+		if (ret < 0)
+			return ret;
+
+		buf += ret;
+		count -= ret;
+		total_bytes += ret;
+	}
+
+	return total_bytes;
+}
+
 static ssize_t copy_event_to_user(struct fsnotify_group *group,
 				  struct fanotify_event *event,
 				  char __user *buf, size_t count)
@@ -410,15 +530,15 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 	struct fanotify_event_metadata metadata;
 	struct path *path = fanotify_event_path(event);
 	struct fanotify_info *info = fanotify_event_info(event);
-	unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
+	unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES);
+	unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD;
 	struct file *f = NULL;
-	int ret, fd = FAN_NOFD;
-	int info_type = 0;
+	int ret, pidfd = FAN_NOPIDFD, fd = FAN_NOFD;
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
 	metadata.event_len = FAN_EVENT_METADATA_LEN +
-				fanotify_event_info_len(fid_mode, event);
+				fanotify_event_info_len(info_mode, event);
 	metadata.metadata_len = FAN_EVENT_METADATA_LEN;
 	metadata.vers = FANOTIFY_METADATA_VERSION;
 	metadata.reserved = 0;
@@ -447,6 +567,33 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 	}
 	metadata.fd = fd;
 
+	if (pidfd_mode) {
+		/*
+		 * Complain if the FAN_REPORT_PIDFD and FAN_REPORT_TID mutual
+		 * exclusion is ever lifted. At the time of incoporating pidfd
+		 * support within fanotify, the pidfd API only supported the
+		 * creation of pidfds for thread-group leaders.
+		 */
+		WARN_ON_ONCE(FAN_GROUP_FLAG(group, FAN_REPORT_TID));
+
+		/*
+		 * The PIDTYPE_TGID check for an event->pid is performed
+		 * preemptively in an attempt to catch out cases where the event
+		 * listener reads events after the event generating process has
+		 * already terminated. Report FAN_NOPIDFD to the event listener
+		 * in those cases, with all other pidfd creation errors being
+		 * reported as FAN_EPIDFD.
+		 */
+		if (metadata.pid == 0 ||
+		    !pid_has_task(event->pid, PIDTYPE_TGID)) {
+			pidfd = FAN_NOPIDFD;
+		} else {
+			pidfd = pidfd_create(event->pid, 0);
+			if (pidfd < 0)
+				pidfd = FAN_EPIDFD;
+		}
+	}
+
 	ret = -EFAULT;
 	/*
 	 * Sanity check copy size in case get_one_event() and
@@ -467,67 +614,11 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 	if (f)
 		fd_install(fd, f);
 
-	/* Event info records order is: dir fid + name, child fid */
-	if (fanotify_event_dir_fh_len(event)) {
-		info_type = info->name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME :
-					     FAN_EVENT_INFO_TYPE_DFID;
-		ret = copy_info_to_user(fanotify_event_fsid(event),
-					fanotify_info_dir_fh(info),
-					info_type, fanotify_info_name(info),
-					info->name_len, buf, count);
+	if (info_mode) {
+		ret = copy_info_records_to_user(event, info, info_mode, pidfd,
+						buf, count);
 		if (ret < 0)
 			goto out_close_fd;
-
-		buf += ret;
-		count -= ret;
-	}
-
-	if (fanotify_event_object_fh_len(event)) {
-		const char *dot = NULL;
-		int dot_len = 0;
-
-		if (fid_mode == FAN_REPORT_FID || info_type) {
-			/*
-			 * With only group flag FAN_REPORT_FID only type FID is
-			 * reported. Second info record type is always FID.
-			 */
-			info_type = FAN_EVENT_INFO_TYPE_FID;
-		} else if ((fid_mode & FAN_REPORT_NAME) &&
-			   (event->mask & FAN_ONDIR)) {
-			/*
-			 * With group flag FAN_REPORT_NAME, if name was not
-			 * recorded in an event on a directory, report the
-			 * name "." with info type DFID_NAME.
-			 */
-			info_type = FAN_EVENT_INFO_TYPE_DFID_NAME;
-			dot = ".";
-			dot_len = 1;
-		} else if ((event->mask & ALL_FSNOTIFY_DIRENT_EVENTS) ||
-			   (event->mask & FAN_ONDIR)) {
-			/*
-			 * With group flag FAN_REPORT_DIR_FID, a single info
-			 * record has type DFID for directory entry modification
-			 * event and for event on a directory.
-			 */
-			info_type = FAN_EVENT_INFO_TYPE_DFID;
-		} else {
-			/*
-			 * With group flags FAN_REPORT_DIR_FID|FAN_REPORT_FID,
-			 * a single info record has type FID for event on a
-			 * non-directory, when there is no directory to report.
-			 * For example, on FAN_DELETE_SELF event.
-			 */
-			info_type = FAN_EVENT_INFO_TYPE_FID;
-		}
-
-		ret = copy_info_to_user(fanotify_event_fsid(event),
-					fanotify_event_object_fh(event),
-					info_type, dot, dot_len, buf, count);
-		if (ret < 0)
-			goto out_close_fd;
-
-		buf += ret;
-		count -= ret;
 	}
 
 	return metadata.event_len;
@@ -537,6 +628,10 @@ out_close_fd:
 		put_unused_fd(fd);
 		fput(f);
 	}
+
+	if (pidfd >= 0)
+		close_fd(pidfd);
+
 	return ret;
 }
 
@@ -1082,6 +1177,14 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 #endif
 		return -EINVAL;
 
+	/*
+	 * A pidfd can only be returned for a thread-group leader; thus
+	 * FAN_REPORT_PIDFD and FAN_REPORT_TID need to remain mutually
+	 * exclusive.
+	 */
+	if ((flags & FAN_REPORT_PIDFD) && (flags & FAN_REPORT_TID))
+		return -EINVAL;
+
 	if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS)
 		return -EINVAL;
 
@@ -1483,7 +1586,7 @@ static int __init fanotify_user_setup(void)
 				     FANOTIFY_DEFAULT_MAX_USER_MARKS);
 
 	BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS);
-	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 10);
+	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 11);
 	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9);
 
 	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 30d422b8c0fc..963e6ce75b96 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -87,15 +87,15 @@ static void fsnotify_unmount_inodes(struct super_block *sb)
 
 	if (iput_inode)
 		iput(iput_inode);
-	/* Wait for outstanding inode references from connectors */
-	wait_var_event(&sb->s_fsnotify_inode_refs,
-		       !atomic_long_read(&sb->s_fsnotify_inode_refs));
 }
 
 void fsnotify_sb_delete(struct super_block *sb)
 {
 	fsnotify_unmount_inodes(sb);
 	fsnotify_clear_marks_by_sb(sb);
+	/* Wait for outstanding object references from connectors */
+	wait_var_event(&sb->s_fsnotify_connectors,
+		       !atomic_long_read(&sb->s_fsnotify_connectors));
 }
 
 /*
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index ff2063ec6b0f..87d8a50ee803 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -27,6 +27,21 @@ static inline struct super_block *fsnotify_conn_sb(
 	return container_of(conn->obj, struct super_block, s_fsnotify_marks);
 }
 
+static inline struct super_block *fsnotify_connector_sb(
+				struct fsnotify_mark_connector *conn)
+{
+	switch (conn->type) {
+	case FSNOTIFY_OBJ_TYPE_INODE:
+		return fsnotify_conn_inode(conn)->i_sb;
+	case FSNOTIFY_OBJ_TYPE_VFSMOUNT:
+		return fsnotify_conn_mount(conn)->mnt.mnt_sb;
+	case FSNOTIFY_OBJ_TYPE_SB:
+		return fsnotify_conn_sb(conn);
+	default:
+		return NULL;
+	}
+}
+
 /* destroy all events sitting in this groups notification queue */
 extern void fsnotify_flush_notify(struct fsnotify_group *group);
 
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index d32ab349db74..95006d1d29ab 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -169,6 +169,37 @@ static void fsnotify_connector_destroy_workfn(struct work_struct *work)
 	}
 }
 
+static void fsnotify_get_inode_ref(struct inode *inode)
+{
+	ihold(inode);
+	atomic_long_inc(&inode->i_sb->s_fsnotify_connectors);
+}
+
+static void fsnotify_put_inode_ref(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+
+	iput(inode);
+	if (atomic_long_dec_and_test(&sb->s_fsnotify_connectors))
+		wake_up_var(&sb->s_fsnotify_connectors);
+}
+
+static void fsnotify_get_sb_connectors(struct fsnotify_mark_connector *conn)
+{
+	struct super_block *sb = fsnotify_connector_sb(conn);
+
+	if (sb)
+		atomic_long_inc(&sb->s_fsnotify_connectors);
+}
+
+static void fsnotify_put_sb_connectors(struct fsnotify_mark_connector *conn)
+{
+	struct super_block *sb = fsnotify_connector_sb(conn);
+
+	if (sb && atomic_long_dec_and_test(&sb->s_fsnotify_connectors))
+		wake_up_var(&sb->s_fsnotify_connectors);
+}
+
 static void *fsnotify_detach_connector_from_object(
 					struct fsnotify_mark_connector *conn,
 					unsigned int *type)
@@ -182,13 +213,13 @@ static void *fsnotify_detach_connector_from_object(
 	if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) {
 		inode = fsnotify_conn_inode(conn);
 		inode->i_fsnotify_mask = 0;
-		atomic_long_inc(&inode->i_sb->s_fsnotify_inode_refs);
 	} else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
 		fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0;
 	} else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) {
 		fsnotify_conn_sb(conn)->s_fsnotify_mask = 0;
 	}
 
+	fsnotify_put_sb_connectors(conn);
 	rcu_assign_pointer(*(conn->obj), NULL);
 	conn->obj = NULL;
 	conn->type = FSNOTIFY_OBJ_TYPE_DETACHED;
@@ -209,19 +240,12 @@ static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark)
 /* Drop object reference originally held by a connector */
 static void fsnotify_drop_object(unsigned int type, void *objp)
 {
-	struct inode *inode;
-	struct super_block *sb;
-
 	if (!objp)
 		return;
 	/* Currently only inode references are passed to be dropped */
 	if (WARN_ON_ONCE(type != FSNOTIFY_OBJ_TYPE_INODE))
 		return;
-	inode = objp;
-	sb = inode->i_sb;
-	iput(inode);
-	if (atomic_long_dec_and_test(&sb->s_fsnotify_inode_refs))
-		wake_up_var(&sb->s_fsnotify_inode_refs);
+	fsnotify_put_inode_ref(objp);
 }
 
 void fsnotify_put_mark(struct fsnotify_mark *mark)
@@ -493,8 +517,12 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp,
 		conn->fsid.val[0] = conn->fsid.val[1] = 0;
 		conn->flags = 0;
 	}
-	if (conn->type == FSNOTIFY_OBJ_TYPE_INODE)
-		inode = igrab(fsnotify_conn_inode(conn));
+	if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) {
+		inode = fsnotify_conn_inode(conn);
+		fsnotify_get_inode_ref(inode);
+	}
+	fsnotify_get_sb_connectors(conn);
+
 	/*
 	 * cmpxchg() provides the barrier so that readers of *connp can see
 	 * only initialized structure
@@ -502,7 +530,7 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp,
 	if (cmpxchg(connp, NULL, conn)) {
 		/* Someone else created list structure for us */
 		if (inode)
-			iput(inode);
+			fsnotify_put_inode_ref(inode);
 		kmem_cache_free(fsnotify_mark_connector_cachep, conn);
 	}