[PATCH 16/17] watch_queue: Add superblock notifications [ver #5]

@@ -10,6 +10,8 @@ opened by userspace.  This can be used in conjunction with::
 
   * Mount notifications.
 
+  * Superblock notifications.
+
 The notifications buffers can be enabled by:
 
 	"General setup"/"General notification queue"

@@ -239,6 +241,12 @@ Any particular buffer can be fed from multiple sources.  Sources include:
     Notifications of this type indicate changes to mount attributes and the
     mount topology within the subtree at the indicated point.
 
+  * WATCH_TYPE_SB_NOTIFY
+
+    Notifications of this type indicate changes to superblock attributes and
+    configuration and events generated within a superblock such as I/O errors,
+    network status changes and out-of-space/out-of-quota errors.
+
 
 Event Filtering
 ===============

@@ -302,6 +310,7 @@ It can then be set to receive notifications::
 
 	keyctl(KEYCTL_WATCH_KEY, KEY_SPEC_SESSION_KEYRING, fds[1], 0x01);
 	watch_mount(AT_FDCWD, "/", 0, fds[1], 0x02);
+	watch_sb(AT_FDCWD, "/", 0, fds[1], 0x03);
 
 The notifications can then be consumed by something like the following::
 

@@ -341,6 +350,9 @@ The notifications can then be consumed by something like the following::
 				case WATCH_TYPE_MOUNT_NOTIFY:
 					saw_mount_change(&n.n);
 					break;
+				case WATCH_TYPE_SB_NOTIFY:
+					saw_sb_event(&n.n);
+					break;
 				}
 
 				p += len;

@@ -478,3 +478,4 @@
 547	common	openat2				sys_openat2
 548	common	pidfd_getfd			sys_pidfd_getfd
 549	common	watch_mount			sys_watch_mount
+550	common	watch_sb			sys_watch_sb

@@ -452,3 +452,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	watch_mount			sys_watch_mount
+440	common	watch_sb			sys_watch_sb

@@ -38,7 +38,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		440
+#define __NR_compat_syscalls		441
 #endif
 
 #define __ARCH_WANT_SYS_CLONE

@@ -885,6 +885,8 @@ __SYSCALL(__NR_openat2, sys_openat2)
 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
 #define __NR_watch_mount 439
 __SYSCALL(__NR_watch_mount, sys_watch_mount)
+#define __NR_watch_sb 440
+__SYSCALL(__NR_watch_sb, sys_watch_sb)
 
 /*
  * Please add new compat syscalls above this comment and update

@@ -359,3 +359,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	watch_mount			sys_watch_mount
+440	common	watch_sb			sys_watch_sb

@@ -438,3 +438,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	watch_mount			sys_watch_mount
+440	common	watch_sb			sys_watch_sb

@@ -444,3 +444,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	watch_mount			sys_watch_mount
+440	common	watch_sb			sys_watch_sb

@@ -377,3 +377,4 @@
 437	n32	openat2				sys_openat2
 438	n32	pidfd_getfd			sys_pidfd_getfd
 439	n32	watch_mount			sys_watch_mount
+440	n32	watch_sb			sys_watch_sb

@@ -353,3 +353,4 @@
 437	n64	openat2				sys_openat2
 438	n64	pidfd_getfd			sys_pidfd_getfd
 439	n64	watch_mount			sys_watch_mount
+440	n64	watch_sb			sys_watch_sb

@@ -426,3 +426,4 @@
 437	o32	openat2				sys_openat2
 438	o32	pidfd_getfd			sys_pidfd_getfd
 439	o32	watch_mount			sys_watch_mount
+440	o32	watch_sb			sys_watch_sb

@@ -436,3 +436,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	watch_mount			sys_watch_mount
+440	common	watch_sb			sys_watch_sb

@@ -520,3 +520,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	watch_mount			sys_watch_mount
+440	common	watch_sb			sys_watch_sb

@@ -441,3 +441,4 @@
 437  common	openat2			sys_openat2			sys_openat2
 438  common	pidfd_getfd		sys_pidfd_getfd			sys_pidfd_getfd
 439	common	watch_mount		sys_watch_mount			sys_watch_mount
+440	common	watch_sb		sys_watch_sb			sys_watch_sb

@@ -441,3 +441,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	watch_mount			sys_watch_mount
+440	common	watch_sb			sys_watch_sb

@@ -484,3 +484,4 @@
 437	common	openat2			sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	watch_mount			sys_watch_mount
+440	common	watch_sb			sys_watch_sb

@@ -443,3 +443,4 @@
 437	i386	openat2			sys_openat2			__ia32_sys_openat2
 438	i386	pidfd_getfd		sys_pidfd_getfd			__ia32_sys_pidfd_getfd
 439	i386	watch_mount		sys_watch_mount			__ia32_sys_watch_mount
+440	i386	watch_sb		sys_watch_sb			__ia32_sys_watch_sb

@@ -360,6 +360,7 @@
 437	common	openat2			__x64_sys_openat2
 438	common	pidfd_getfd		__x64_sys_pidfd_getfd
 439	common	watch_mount		__x64_sys_watch_mount
+440	common	watch_sb		__x64_sys_watch_sb
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

@@ -409,3 +409,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	watch_mount			sys_watch_mount
+440	common	watch_sb			sys_watch_sb

@@ -126,6 +126,18 @@ config MOUNT_NOTIFICATIONS
 	  device to handle the notification buffer and provides the
 	  mount_notify() system call to enable/disable watchpoints.
 
+config SB_NOTIFICATIONS
+	bool "Superblock event notifications"
+	select WATCH_QUEUE
+	help
+	  This option provides support for receiving superblock event
+	  notifications.  This makes use of the /dev/watch_queue misc device to
+	  handle the notification buffer and provides the sb_notify() system
+	  call to enable/disable watches.
+
+	  Events can include things like changing between R/W and R/O, EIO
+	  generation, ENOSPC generation and EDQUOT generation.
+
 source "fs/quota/Kconfig"
 
 source "fs/autofs/Kconfig"

@@ -37,6 +37,8 @@
 #include <linux/lockdep.h>
 #include <linux/user_namespace.h>
 #include <linux/fs_context.h>
+#include <linux/syscalls.h>
+#include <linux/namei.h>
 #include <uapi/linux/mount.h>
 #include "internal.h"
 

@@ -333,6 +335,10 @@ void deactivate_locked_super(struct super_block *s)
 {
 	struct file_system_type *fs = s->s_type;
 	if (atomic_dec_and_test(&s->s_active)) {
+#ifdef CONFIG_SB_NOTIFICATIONS
+		if (s->s_watchers)
+			remove_watch_list(s->s_watchers, s->s_unique_id);
+#endif
 		cleancache_invalidate_fs(s);
 		unregister_shrinker(&s->s_shrink);
 		fs->kill_sb(s);

@@ -972,6 +978,8 @@ int reconfigure_super(struct fs_context *fc)
 	/* Needs to be ordered wrt mnt_is_readonly() */
 	smp_wmb();
 	sb->s_readonly_remount = 0;
+	notify_sb(sb, NOTIFY_SUPERBLOCK_READONLY,
+		  remount_ro ? NOTIFY_SUPERBLOCK_IS_NOW_RO : 0);
 
 	/*
 	 * Some filesystems modify their metadata via some other path than the

@@ -1891,3 +1899,176 @@ void vfs_generate_unique_id(u64 *_id)
 
 	*_id = id;
 }
+
+#ifdef CONFIG_SB_NOTIFICATIONS
+/*
+ * Post superblock notifications.
+ */
+static void post_sb_notification(struct super_block *s, struct superblock_notification *n)
+{
+	post_watch_notification(s->s_watchers, &n->watch, current_cred(),
+				s->s_unique_id);
+}
+
+/*
+ * Post simple superblock notification.
+ */
+void __notify_sb(struct super_block *s,
+		 enum superblock_notification_type subtype,
+		 u32 info)
+{
+	struct superblock_notification n = {
+		.watch.type	= WATCH_TYPE_SB_NOTIFY,
+		.watch.subtype	= subtype,
+		.watch.info	= watch_sizeof(n) | info,
+		.sb_id		= s->s_unique_id,
+	};
+
+	post_sb_notification(s, &n);
+}
+
+/*
+ * Post superblock error notification.
+ */
+void __notify_sb_error(struct super_block *s, int error)
+{
+	struct superblock_error_notification n = {
+		.s.watch.type	= WATCH_TYPE_SB_NOTIFY,
+		.s.watch.subtype = NOTIFY_SUPERBLOCK_ERROR,
+		.s.watch.info	= watch_sizeof(n),
+		.s.sb_id	= s->s_unique_id,
+		.error_number	= error,
+		.error_cookie	= 0,
+	};
+
+	post_sb_notification(s, &n.s);
+}
+
+/*
+ * Post superblock quota overrun notification.
+ */
+void __notify_sb_EQDUOT(struct super_block *s)
+{
+	struct superblock_notification n = {
+		.watch.type	= WATCH_TYPE_SB_NOTIFY,
+		.watch.subtype	= NOTIFY_SUPERBLOCK_EDQUOT,
+		.watch.info	= watch_sizeof(n),
+		.sb_id		= s->s_unique_id,
+	};
+
+	post_sb_notification(s, &n);
+}
+
+static void sb_release_watch(struct watch *watch)
+{
+	put_super(watch->private);
+}
+
+/**
+ * sys_watch_sb - Watch for superblock events.
+ * @dfd: Base directory to pathwalk from or fd referring to superblock.
+ * @filename: Path to superblock to place the watch upon
+ * @at_flags: Pathwalk control flags
+ * @watch_fd: The watch queue to send notifications to.
+ * @watch_id: The watch ID to be placed in the notification (-1 to remove watch)
+ */
+SYSCALL_DEFINE5(watch_sb,
+		int, dfd,
+		const char __user *, filename,
+		unsigned int, at_flags,
+		int, watch_fd,
+		int, watch_id)
+{
+	struct watch_queue *wqueue;
+	struct super_block *s;
+	struct watch_list *wlist = NULL;
+	struct watch *watch = NULL;
+	struct path path;
+	unsigned int lookup_flags =
+		LOOKUP_DIRECTORY | LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
+	bool drop_s_count = false;
+	int ret;
+
+	if (watch_id < -1 || watch_id > 0xff)
+		return -EINVAL;
+	if ((at_flags & ~(AT_NO_AUTOMOUNT | AT_EMPTY_PATH)) != 0)
+		return -EINVAL;
+	if (at_flags & AT_NO_AUTOMOUNT)
+		lookup_flags &= ~LOOKUP_AUTOMOUNT;
+	if (at_flags & AT_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
+
+	ret = user_path_at(dfd, filename, at_flags, &path);
+	if (ret)
+		return ret;
+
+	ret = inode_permission(path.dentry->d_inode, MAY_EXEC);
+	if (ret)
+		goto err_path;
+
+	wqueue = get_watch_queue(watch_fd);
+	if (IS_ERR(wqueue))
+		goto err_path;
+
+	s = path.dentry->d_sb;
+	if (watch_id >= 0) {
+		ret = -ENOMEM;
+		if (!READ_ONCE(s->s_watchers)) {
+			wlist = kzalloc(sizeof(*wlist), GFP_KERNEL);
+			if (!wlist)
+				goto err_wqueue;
+			init_watch_list(wlist, sb_release_watch);
+		}
+
+		watch = kzalloc(sizeof(*watch), GFP_KERNEL);
+		if (!watch)
+			goto err_wlist;
+
+		init_watch(watch, wqueue);
+		watch->id		= s->s_unique_id;
+		watch->private		= s;
+		watch->info_id		= (u32)watch_id << 24;
+
+		ret = security_watch_sb(watch, s);
+		if (ret < 0)
+			goto err_watch;
+
+		down_write(&s->s_umount);
+		ret = -EIO;
+		if (atomic_read(&s->s_active)) {
+			if (!s->s_watchers) {
+				s->s_watchers = wlist;
+				wlist = NULL;
+			}
+
+			spin_lock(&sb_lock);
+			s->s_count++;
+			spin_unlock(&sb_lock);
+			ret = add_watch_to_object(watch, s->s_watchers);
+			if (ret == 0)
+				watch = NULL; /* It worked */
+			else
+				drop_s_count = true;
+		}
+		up_write(&s->s_umount);
+		if (drop_s_count)
+			put_super(s);
+	} else {
+		ret = -EBADSLT;
+		down_write(&s->s_umount);
+		ret = remove_watch_from_object(s->s_watchers, wqueue,
+					       s->s_unique_id, false);
+		up_write(&s->s_umount);
+	}
+
+err_watch:
+	kfree(watch);
+err_wlist:
+	kfree(wlist);
+err_wqueue:
+	put_watch_queue(wqueue);
+err_path:
+	path_put(&path);
+	return ret;
+}
+#endif

@@ -40,6 +40,7 @@
 #include <linux/fs_types.h>
 #include <linux/build_bug.h>
 #include <linux/stddef.h>
+#include <linux/watch_queue.h>
 
 #include <asm/byteorder.h>
 #include <uapi/linux/fs.h>

@@ -1551,6 +1552,12 @@ struct super_block {
 
 	/* Superblock event notifications */
 	u64			s_unique_id;
+
+#ifdef CONFIG_SB_NOTIFICATIONS
+	struct watch_list	*s_watchers;
+#endif
+	atomic_t		s_change_counter;	/* Count of config change notifications */
+	atomic_t		s_notify_counter;	/* Count of other notifications */
 } __randomize_layout;
 
 /* Helper functions so that in most cases filesystems will

@@ -3654,4 +3661,56 @@ static inline int inode_drain_writes(struct inode *inode)
 	return filemap_write_and_wait(inode->i_mapping);
 }
 
+extern void __notify_sb(struct super_block *s,
+			enum superblock_notification_type subtype,
+			u32 info);
+extern void __notify_sb_error(struct super_block *s, int error);
+extern void __notify_sb_EQDUOT(struct super_block *s);
+
+/**
+ * notify_sb: Post simple superblock notification.
+ * @s: The superblock the notification is about.
+ * @subtype: The type of notification.
+ * @info: WATCH_INFO_FLAG_* flags to be set in the record.
+ */
+static inline void notify_sb(struct super_block *s,
+			     enum superblock_notification_type subtype,
+			     u32 info)
+{
+#ifdef CONFIG_SB_NOTIFICATIONS
+	atomic_inc(&s->s_change_counter);
+	if (unlikely(READ_ONCE(s->s_watchers)))
+		__notify_sb(s, subtype, info);
+#endif
+}
+
+/**
+ * notify_sb_error: Post superblock error notification.
+ * @s: The superblock the notification is about.
+ * @error: The error number to be recorded.
+ */
+static inline int notify_sb_error(struct super_block *s, int error)
+{
+#ifdef CONFIG_SB_NOTIFICATIONS
+	atomic_inc(&s->s_notify_counter);
+	if (unlikely(READ_ONCE(s->s_watchers)))
+		__notify_sb_error(s, error);
+#endif
+	return error;
+}
+
+/**
+ * notify_sb_EDQUOT: Post superblock quota overrun notification.
+ * @s: The superblock the notification is about.
+ */
+static inline int notify_sb_EQDUOT(struct super_block *s)
+{
+#ifdef CONFIG_SB_NOTIFICATIONS
+	atomic_inc(&s->s_notify_counter);
+	if (unlikely(READ_ONCE(s->s_watchers)))
+		__notify_sb_EQDUOT(s);
+#endif
+	return -EDQUOT;
+}
+
 #endif /* _LINUX_FS_H */

@@ -1005,6 +1005,8 @@ asmlinkage long sys_pidfd_send_signal(int pidfd, int sig,
 asmlinkage long sys_pidfd_getfd(int pidfd, int fd, unsigned int flags);
 asmlinkage long sys_watch_mount(int dfd, const char __user *path,
 				unsigned int at_flags, int watch_fd, int watch_id);
+asmlinkage long sys_watch_sb(int dfd, const char __user *path,
+			     unsigned int at_flags, int watch_fd, int watch_id);
 
 /*
  * Architecture-specific system calls

@@ -857,9 +857,11 @@ __SYSCALL(__NR_openat2, sys_openat2)
 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
 #define __NR_watch_mount 439
 __SYSCALL(__NR_watch_mount, sys_watch_mount)
+#define __NR_watch_sb 440
+__SYSCALL(__NR_watch_sb, sys_watch_sb)
 
 #undef __NR_syscalls
-#define __NR_syscalls 440
+#define __NR_syscalls 441
 
 /*
  * 32 bit systems traditionally used different

@@ -15,7 +15,8 @@ enum watch_notification_type {
 	WATCH_TYPE_META		= 0,	/* Special record */
 	WATCH_TYPE_KEY_NOTIFY	= 1,	/* Key change event notification */
 	WATCH_TYPE_MOUNT_NOTIFY	= 2,	/* Mount topology change notification */
-	WATCH_TYPE___NR		= 3
+	WATCH_TYPE_SB_NOTIFY	= 3,	/* Superblock event notification */
+	WATCH_TYPE___NR		= 4
 };
 
 enum watch_meta_notification_subtype {

@@ -135,4 +136,32 @@ struct mount_notification {
 	__u32	__padding;
 };
 
+/*
+ * Type of superblock notification.
+ */
+enum superblock_notification_type {
+	NOTIFY_SUPERBLOCK_READONLY	= 0, /* Filesystem toggled between R/O and R/W */
+	NOTIFY_SUPERBLOCK_ERROR		= 1, /* Error in filesystem or blockdev */
+	NOTIFY_SUPERBLOCK_EDQUOT	= 2, /* EDQUOT notification */
+	NOTIFY_SUPERBLOCK_NETWORK	= 3, /* Network status change */
+};
+
+#define NOTIFY_SUPERBLOCK_IS_NOW_RO	WATCH_INFO_FLAG_0 /* Superblock changed to R/O */
+
+/*
+ * Superblock notification record.
+ * - watch.type = WATCH_TYPE_MOUNT_NOTIFY
+ * - watch.subtype = enum superblock_notification_subtype
+ */
+struct superblock_notification {
+	struct watch_notification watch; /* WATCH_TYPE_SB_NOTIFY */
+	__u64	sb_id;			/* 64-bit superblock ID */
+};
+
+struct superblock_error_notification {
+	struct superblock_notification s; /* subtype = notify_superblock_error */
+	__u32	error_number;
+	__u32	error_cookie;
+};
+
 #endif /* _UAPI_LINUX_WATCH_QUEUE_H */

@@ -119,6 +119,9 @@ COND_SYSCALL_COMPAT(signalfd4);
 
 /* fs/sync.c */
 
+/* fs/super.c */
+COND_SYSCALL(watch_sb);
+
 /* fs/timerfd.c */
 COND_SYSCALL(timerfd_create);
 COND_SYSCALL(timerfd_settime);