fanotify: configurable limits via sysfs

fanotify has some hardcoded limits. The only APIs to escape those limits
are FAN_UNLIMITED_QUEUE and FAN_UNLIMITED_MARKS.

Allow finer grained tuning of the system limits via sysfs tunables under
/proc/sys/fs/fanotify, similar to tunables under /proc/sys/fs/inotify,
with some minor differences.

- max_queued_events - global system tunable for group queue size limit.
  Like the inotify tunable with the same name, it defaults to 16384 and
  applies on initialization of a new group.

- max_user_marks - user ns tunable for marks limit per user.
  Like the inotify tunable named max_user_watches, on a machine with
  sufficient RAM and it defaults to 1048576 in init userns and can be
  further limited per containing user ns.

- max_user_groups - user ns tunable for number of groups per user.
  Like the inotify tunable named max_user_instances, it defaults to 128
  in init userns and can be further limited per containing user ns.

The slightly different tunable names used for fanotify are derived from
the "group" and "mark" terminology used in the fanotify man pages and
throughout the code.

Considering the fact that the default value for max_user_instances was
increased in kernel v5.10 from 8192 to 1048576, leaving the legacy
fanotify limit of 8192 marks per group in addition to the max_user_marks
limit makes little sense, so the per group marks limit has been removed.

Note that when a group is initialized with FAN_UNLIMITED_MARKS, its own
marks are not accounted in the per user marks account, so in effect the
limit of max_user_marks is only for the collection of groups that are
not initialized with FAN_UNLIMITED_MARKS.

Link: https://lore.kernel.org/r/20210304112921.3996419-2-amir73il@gmail.com
Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>

4 files changed, 8 insertions, 8 deletions

diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index 3e9c56ee651f..031a97d8369a 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -2,8 +2,11 @@
 #ifndef _LINUX_FANOTIFY_H
 #define _LINUX_FANOTIFY_H
 
+#include <linux/sysctl.h>
 #include <uapi/linux/fanotify.h>
 
+extern struct ctl_table fanotify_table[]; /* for sysctl */
+
 #define FAN_GROUP_FLAG(group, flag) \
 	((group)->fanotify_data.flags & (flag))
 
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 63fb766f0f3e..1ce66748a2d2 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -206,9 +206,6 @@ struct fsnotify_group {
 
 	/* stores all fastpath marks assoc with this group so they can be cleaned on unregister */
 	struct mutex mark_mutex;	/* protect marks_list */
-	atomic_t num_marks;		/* 1 for each mark and 1 for not being
-					 * past the point of no return when freeing
-					 * a group */
 	atomic_t user_waits;		/* Number of tasks waiting for user
 					 * response */
 	struct list_head marks_list;	/* all inode marks for this group */
@@ -240,8 +237,7 @@ struct fsnotify_group {
 			wait_queue_head_t access_waitq;
 			int flags;           /* flags from fanotify_init() */
 			int f_flags; /* event_f_flags from fanotify_init() */
-			unsigned int max_marks;
-			struct user_struct *user;
+			struct ucounts *ucounts;
 		} fanotify_data;
 #endif /* CONFIG_FANOTIFY */
 	};
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index a8ec3b6093fc..3632c5d6ec55 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -14,9 +14,6 @@ struct user_struct {
 	refcount_t __count;	/* reference count */
 	atomic_t processes;	/* How many processes does this user have? */
 	atomic_t sigpending;	/* How many pending signals does this user have? */
-#ifdef CONFIG_FANOTIFY
-	atomic_t fanotify_listeners;
-#endif
 #ifdef CONFIG_EPOLL
 	atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
 #endif
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 64cf8ebdc4ec..f0d961a15fba 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -50,6 +50,10 @@ enum ucount_type {
 	UCOUNT_INOTIFY_INSTANCES,
 	UCOUNT_INOTIFY_WATCHES,
 #endif
+#ifdef CONFIG_FANOTIFY
+	UCOUNT_FANOTIFY_GROUPS,
+	UCOUNT_FANOTIFY_MARKS,
+#endif
 	UCOUNT_COUNTS,
 };