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()

5 files changed, 31 insertions, 2 deletions

diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index a16dbeced152..eec3b7c40811 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -27,6 +27,8 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */
 
 #define FANOTIFY_FID_BITS	(FAN_REPORT_FID | FAN_REPORT_DFID_NAME)
 
+#define FANOTIFY_INFO_MODES	(FANOTIFY_FID_BITS | FAN_REPORT_PIDFD)
+
 /*
  * fanotify_init() flags that require CAP_SYS_ADMIN.
  * We do not allow unprivileged groups to request permission events.
@@ -35,6 +37,7 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */
  */
 #define FANOTIFY_ADMIN_INIT_FLAGS	(FANOTIFY_PERM_CLASSES | \
 					 FAN_REPORT_TID | \
+					 FAN_REPORT_PIDFD | \
 					 FAN_UNLIMITED_QUEUE | \
 					 FAN_UNLIMITED_MARKS)
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 640574294216..bea8ec5c726c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1507,8 +1507,11 @@ struct super_block {
 	/* Number of inodes with nlink == 0 but still referenced */
 	atomic_long_t s_remove_count;
 
-	/* Pending fsnotify inode refs */
-	atomic_long_t s_fsnotify_inode_refs;
+	/*
+	 * Number of inode/mount/sb objects that are being watched, note that
+	 * inodes objects are currently double-accounted.
+	 */
+	atomic_long_t s_fsnotify_connectors;
 
 	/* Being remounted read-only */
 	int s_readonly_remount;
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index f8acddcf54fb..12d3a7d308ab 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -30,6 +30,9 @@ static inline void fsnotify_name(struct inode *dir, __u32 mask,
 				 struct inode *child,
 				 const struct qstr *name, u32 cookie)
 {
+	if (atomic_long_read(&dir->i_sb->s_fsnotify_connectors) == 0)
+		return;
+
 	fsnotify(mask, child, FSNOTIFY_EVENT_INODE, dir, name, NULL, cookie);
 }
 
@@ -41,6 +44,9 @@ static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry,
 
 static inline void fsnotify_inode(struct inode *inode, __u32 mask)
 {
+	if (atomic_long_read(&inode->i_sb->s_fsnotify_connectors) == 0)
+		return;
+
 	if (S_ISDIR(inode->i_mode))
 		mask |= FS_ISDIR;
 
@@ -53,6 +59,9 @@ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask,
 {
 	struct inode *inode = d_inode(dentry);
 
+	if (atomic_long_read(&inode->i_sb->s_fsnotify_connectors) == 0)
+		return 0;
+
 	if (S_ISDIR(inode->i_mode)) {
 		mask |= FS_ISDIR;
 
diff --git a/include/linux/pid.h b/include/linux/pid.h
index fa10acb8d6a4..af308e15f174 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -78,6 +78,7 @@ struct file;
 
 extern struct pid *pidfd_pid(const struct file *file);
 struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags);
+int pidfd_create(struct pid *pid, unsigned int flags);
 
 static inline struct pid *get_pid(struct pid *pid)
 {
diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h
index fbf9c5c7dd59..64553df9d735 100644
--- a/include/uapi/linux/fanotify.h
+++ b/include/uapi/linux/fanotify.h
@@ -51,6 +51,7 @@
 #define FAN_ENABLE_AUDIT	0x00000040
 
 /* Flags to determine fanotify event format */
+#define FAN_REPORT_PIDFD	0x00000080	/* Report pidfd for event->pid */
 #define FAN_REPORT_TID		0x00000100	/* event->pid is thread id */
 #define FAN_REPORT_FID		0x00000200	/* Report unique file id */
 #define FAN_REPORT_DIR_FID	0x00000400	/* Report unique directory id */
@@ -123,6 +124,7 @@ struct fanotify_event_metadata {
 #define FAN_EVENT_INFO_TYPE_FID		1
 #define FAN_EVENT_INFO_TYPE_DFID_NAME	2
 #define FAN_EVENT_INFO_TYPE_DFID	3
+#define FAN_EVENT_INFO_TYPE_PIDFD	4
 
 /* Variable length info record following event metadata */
 struct fanotify_event_info_header {
@@ -148,6 +150,15 @@ struct fanotify_event_info_fid {
 	unsigned char handle[0];
 };
 
+/*
+ * This structure is used for info records of type FAN_EVENT_INFO_TYPE_PIDFD.
+ * It holds a pidfd for the pid that was responsible for generating an event.
+ */
+struct fanotify_event_info_pidfd {
+	struct fanotify_event_info_header hdr;
+	__s32 pidfd;
+};
+
 struct fanotify_response {
 	__s32 fd;
 	__u32 response;
@@ -160,6 +171,8 @@ struct fanotify_response {
 
 /* No fd set in event */
 #define FAN_NOFD	-1
+#define FAN_NOPIDFD	FAN_NOFD
+#define FAN_EPIDFD	-2
 
 /* Helper functions to deal with fanotify_event_metadata buffers */
 #define FAN_EVENT_METADATA_LEN (sizeof(struct fanotify_event_metadata))