@@ -445,3 +445,4 @@
438 i386 pidfd_getfd sys_pidfd_getfd
439 i386 faccessat2 sys_faccessat2
440 i386 process_madvise sys_process_madvise
+441 i386 watch_sb sys_watch_sb
@@ -362,6 +362,7 @@
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
440 common process_madvise sys_process_madvise
+441 common watch_sb sys_watch_sb
#
# Due to a historical design error, certain syscalls are numbered differently
@@ -117,6 +117,18 @@ source "fs/verity/Kconfig"
source "fs/notify/Kconfig"
+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 watch_queue API 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"
@@ -330,6 +332,10 @@ 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);
@@ -969,6 +975,8 @@ 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
@@ -1867,3 +1875,122 @@ int thaw_super(struct super_block *sb)
return thaw_super_locked(sb);
}
EXPORT_SYMBOL(thaw_super);
+
+#ifdef CONFIG_SB_NOTIFICATIONS
+/*
+ * Post superblock notifications.
+ */
+
+void post_sb_notification(struct super_block *s, struct superblock_notification *n,
+ const char *fmt, va_list *args)
+{
+ post_watch_notification_string(s->s_watchers, &n->watch, current_cred(),
+ s->s_unique_id, fmt, args);
+}
+
+/**
+ * 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;
+ 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 (!s->s_watchers) {
+ wlist = kzalloc(sizeof(*wlist), GFP_KERNEL);
+ if (!wlist)
+ goto err_wqueue;
+ init_watch_list(wlist, NULL);
+ }
+
+ 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(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;
+ }
+
+ ret = add_watch_to_object(watch, s->s_watchers);
+ if (ret == 0) {
+ spin_lock(&sb_lock);
+ s->s_count++;
+ spin_unlock(&sb_lock);
+ watch = NULL;
+ }
+ }
+ up_write(&s->s_umount);
+ } else {
+ ret = -EBADSLT;
+ if (READ_ONCE(s->s_watchers)) {
+ 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
@@ -39,6 +39,7 @@
#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>
@@ -1547,6 +1548,13 @@ struct super_block {
spinlock_t s_inode_wblist_lock;
struct list_head s_inodes_wb; /* writeback inodes */
+
+ /* Superblock event notifications */
+ u64 s_unique_id;
+
+#ifdef CONFIG_SB_NOTIFICATIONS
+ struct watch_list *s_watchers;
+#endif
} __randomize_layout;
/* Helper functions so that in most cases filesystems will
@@ -3460,4 +3468,83 @@ static inline int inode_drain_writes(struct inode *inode)
return filemap_write_and_wait(inode->i_mapping);
}
+extern void post_sb_notification(struct super_block *, struct superblock_notification *,
+ const char *fmt, va_list *args);
+/**
+ * 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
+ if (unlikely(s->s_watchers)) {
+ 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, NULL, NULL);
+ }
+
+#endif
+}
+
+/**
+ * notify_sb_error: Post superblock error notification.
+ * @s: The superblock the notification is about.
+ * @error: The error number to be recorded.
+ * @inode: The inode the error refers to (if available, 0 otherwise)
+ * @block: The block the error refers to (if available, 0 otherwise)
+ * @fmt: Formating string for extra information appended to the notification
+ * @args: arguments for extra information string appended to the notification
+ */
+static inline int notify_sb_error(struct super_block *s, int error, u64 inode,
+ u64 block, const char *fmt, va_list *args)
+{
+#ifdef CONFIG_SB_NOTIFICATIONS
+ if (unlikely(s->s_watchers)) {
+ 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,
+ .inode = inode,
+ .block = block,
+ };
+
+ post_sb_notification(s, &n.s, fmt, args);
+ }
+#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
+ if (unlikely(s->s_watchers)) {
+ 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, NULL, NULL);
+ }
+#endif
+ return -EDQUOT;
+}
+
#endif /* _LINUX_FS_H */
@@ -1008,6 +1008,8 @@ asmlinkage long sys_pidfd_send_signal(int pidfd, int sig,
siginfo_t __user *info,
unsigned int flags);
asmlinkage long sys_pidfd_getfd(int pidfd, int fd, unsigned int flags);
+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
@@ -859,9 +859,11 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
__SYSCALL(__NR_faccessat2, sys_faccessat2)
#define __NR_process_madvise 440
__SYSCALL(__NR_process_madvise, sys_process_madvise)
+#define __NR_watch_sb 441
+__SYSCALL(__NR_watch_sb, sys_watch_sb)
#undef __NR_syscalls
-#define __NR_syscalls 441
+#define __NR_syscalls 442
/*
* 32 bit systems traditionally used different
@@ -14,7 +14,8 @@
enum watch_notification_type {
WATCH_TYPE_META = 0, /* Special record */
WATCH_TYPE_KEY_NOTIFY = 1, /* Key change event notification */
- WATCH_TYPE__NR = 2
+ WATCH_TYPE_SB_NOTIFY = 2,
+ WATCH_TYPE__NR = 3
};
enum watch_meta_notification_subtype {
@@ -101,4 +102,35 @@ struct key_notification {
__u32 aux; /* Per-type auxiliary data */
};
+/*
+ * 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 [fsinfo_ids::f_sb_id] */
+};
+
+struct superblock_error_notification {
+ struct superblock_notification s; /* subtype = notify_superblock_error */
+ __u32 error_number;
+ __u32 error_cookie;
+ __u64 inode;
+ __u64 block;
+ char desc[0];
+};
+
#endif /* _UAPI_LINUX_WATCH_QUEUE_H */
@@ -51,6 +51,9 @@ COND_SYSCALL_COMPAT(io_pgetevents);
COND_SYSCALL(io_uring_setup);
COND_SYSCALL(io_uring_enter);
COND_SYSCALL(io_uring_register);
+COND_SYSCALL(fsinfo);
+COND_SYSCALL(watch_mount);
+COND_SYSCALL(watch_sb);
/* fs/xattr.c */