[PATCH 00/17] pipe: Keyrings, mount and superblock notifications [ver #5]

@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_WATCH_QUEUE_H
+#define _UAPI_LINUX_WATCH_QUEUE_H
+
+#include <linux/types.h>
+
+enum watch_notification_type {
+	WATCH_TYPE_META		= 0,	/* Special record */
+	WATCH_TYPE__NR		= 1
+};
+
+enum watch_meta_notification_subtype {
+	WATCH_META_REMOVAL_NOTIFICATION	= 0,	/* Watched object was removed */
+	WATCH_META_LOSS_NOTIFICATION	= 1,	/* Data loss occurred */
+};
+
+/*
+ * Notification record header.  This is aligned to 64-bits so that subclasses
+ * can contain __u64 fields.
+ */
+struct watch_notification {
+	__u32			type:24;	/* enum watch_notification_type */
+	__u32			subtype:8;	/* Type-specific subtype (filterable) */
+	__u32			info;
+#define WATCH_INFO_LENGTH	0x0000007f	/* Length of record */
+#define WATCH_INFO_LENGTH__SHIFT 0
+#define WATCH_INFO_ID		0x0000ff00	/* ID of watchpoint */
+#define WATCH_INFO_ID__SHIFT	8
+#define WATCH_INFO_TYPE_INFO	0xffff0000	/* Type-specific info */
+#define WATCH_INFO_TYPE_INFO__SHIFT 16
+#define WATCH_INFO_FLAG_0	0x00010000	/* Type-specific info, flag bit 0 */
+#define WATCH_INFO_FLAG_1	0x00020000	/* ... */
+#define WATCH_INFO_FLAG_2	0x00040000
+#define WATCH_INFO_FLAG_3	0x00080000
+#define WATCH_INFO_FLAG_4	0x00100000
+#define WATCH_INFO_FLAG_5	0x00200000
+#define WATCH_INFO_FLAG_6	0x00400000
+#define WATCH_INFO_FLAG_7	0x00800000
+};
+
+
+/*
+ * Extended watch removal notification.  This is used optionally if the type
+ * wants to indicate an identifier for the object being watched, if there is
+ * such.  This can be distinguished by the length.
+ *
+ * type -> WATCH_TYPE_META
+ * subtype -> WATCH_META_REMOVAL_NOTIFICATION
+ */
+struct watch_notification_removal {
+	struct watch_notification watch;
+	__u64	id;		/* Type-dependent identifier */
+};
+
+#endif /* _UAPI_LINUX_WATCH_QUEUE_H */

@@ -1416,6 +1416,18 @@
  *	@ctx is a pointer in which to place the allocated security context.
  *	@ctxlen points to the place to put the length of @ctx.
  *
+ * Security hooks for the general notification queue:
+ *
+ * @watch_key:
+ *	Check to see if a process is allowed to watch for event notifications
+ *	from a key or keyring.
+ *	@key: The key to watch.
+ *
+ * @watch_devices:
+ *	Check to see if a process is allowed to watch for event notifications
+ *	from devices (as a global set).
+ *
+ *
  * Security hooks for using the eBPF maps and programs functionalities through
  * eBPF syscalls.
  *

@@ -1698,6 +1710,12 @@ union security_list_options {
 	int (*inode_notifysecctx)(struct inode *inode, void *ctx, u32 ctxlen);
 	int (*inode_setsecctx)(struct dentry *dentry, void *ctx, u32 ctxlen);
 	int (*inode_getsecctx)(struct inode *inode, void **ctx, u32 *ctxlen);
+#ifdef CONFIG_KEY_NOTIFICATIONS
+	int (*watch_key)(struct key *key);
+#endif
+#ifdef CONFIG_DEVICE_NOTIFICATIONS
+	int (*watch_devices)(void);
+#endif
 
 #ifdef CONFIG_SECURITY_NETWORK
 	int (*unix_stream_connect)(struct sock *sock, struct sock *other,

@@ -1985,6 +2003,12 @@ struct security_hook_heads {
 	struct hlist_head inode_notifysecctx;
 	struct hlist_head inode_setsecctx;
 	struct hlist_head inode_getsecctx;
+#ifdef CONFIG_KEY_NOTIFICATIONS
+	struct hlist_head watch_key;
+#endif
+#ifdef CONFIG_DEVICE_NOTIFICATIONS
+	struct hlist_head watch_devices;
+#endif
 #ifdef CONFIG_SECURITY_NETWORK
 	struct hlist_head unix_stream_connect;
 	struct hlist_head unix_may_send;

@@ -1276,6 +1276,23 @@ static inline int security_locked_down(enum lockdown_reason what)
 }
 #endif	/* CONFIG_SECURITY */
 
+#if defined(CONFIG_SECURITY) && defined(CONFIG_KEY_NOTIFICATIONS)
+int security_watch_key(struct key *key);
+#else
+static inline int security_watch_key(struct key *key)
+{
+	return 0;
+}
+#endif
+#if defined(CONFIG_SECURITY) && defined(CONFIG_DEVICE_NOTIFICATIONS)
+int security_watch_devices(void);
+#else
+static inline int security_watch_devices(void)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_SECURITY_NETWORK
 
 int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk);

@@ -1988,6 +1988,20 @@ int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen)
 }
 EXPORT_SYMBOL(security_inode_getsecctx);
 
+#ifdef CONFIG_KEY_NOTIFICATIONS
+int security_watch_key(struct key *key)
+{
+	return call_int_hook(watch_key, 0, key);
+}
+#endif
+
+#ifdef CONFIG_DEVICE_NOTIFICATIONS
+int security_watch_devices(void)
+{
+	return call_int_hook(watch_devices, 0);
+}
+#endif
+
 #ifdef CONFIG_SECURITY_NETWORK
 
 int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk)

@@ -1427,6 +1427,12 @@
  *	Check to see if a process is allowed to watch for event notifications
  *	from devices (as a global set).
  *
+ * @post_notification:
+ *	Check to see if a watch notification can be posted to a particular
+ *	queue.
+ *	@w_cred: The credentials of the whoever set the watch.
+ *	@cred: The event-triggerer's credentials
+ *	@n: The notification being posted
  *
  * Security hooks for using the eBPF maps and programs functionalities through
  * eBPF syscalls.

@@ -1716,6 +1722,11 @@ union security_list_options {
 #ifdef CONFIG_DEVICE_NOTIFICATIONS
 	int (*watch_devices)(void);
 #endif
+#ifdef CONFIG_WATCH_QUEUE
+	int (*post_notification)(const struct cred *w_cred,
+				 const struct cred *cred,
+				 struct watch_notification *n);
+#endif
 
 #ifdef CONFIG_SECURITY_NETWORK
 	int (*unix_stream_connect)(struct sock *sock, struct sock *other,

@@ -2009,6 +2020,9 @@ struct security_hook_heads {
 #ifdef CONFIG_DEVICE_NOTIFICATIONS
 	struct hlist_head watch_devices;
 #endif
+#ifdef CONFIG_WATCH_QUEUE
+	struct hlist_head post_notification;
+#endif /* CONFIG_WATCH_QUEUE */
 #ifdef CONFIG_SECURITY_NETWORK
 	struct hlist_head unix_stream_connect;
 	struct hlist_head unix_may_send;

@@ -57,6 +57,8 @@ struct mm_struct;
 struct fs_context;
 struct fs_parameter;
 enum fs_value_type;
+struct watch;
+struct watch_notification;
 
 /* Default (no) options for the capable function */
 #define CAP_OPT_NONE 0x0

@@ -1292,6 +1294,18 @@ static inline int security_watch_devices(void)
 	return 0;
 }
 #endif
+#if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE)
+int security_post_notification(const struct cred *w_cred,
+			       const struct cred *cred,
+			       struct watch_notification *n);
+#else
+static inline int security_post_notification(const struct cred *w_cred,
+					     const struct cred *cred,
+					     struct watch_notification *n)
+{
+	return 0;
+}
+#endif
 
 #ifdef CONFIG_SECURITY_NETWORK
 

@@ -1988,6 +1988,15 @@ int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen)
 }
 EXPORT_SYMBOL(security_inode_getsecctx);
 
+#ifdef CONFIG_WATCH_QUEUE
+int security_post_notification(const struct cred *w_cred,
+			       const struct cred *cred,
+			       struct watch_notification *n)
+{
+	return call_int_hook(post_notification, 0, w_cred, cred, n);
+}
+#endif /* CONFIG_WATCH_QUEUE */
+
 #ifdef CONFIG_KEY_NOTIFICATIONS
 int security_watch_key(struct key *key)
 {

@@ -3,6 +3,9 @@
 #define _UAPI_LINUX_WATCH_QUEUE_H
 
 #include <linux/types.h>
+#include <linux/fcntl.h>
+
+#define O_NOTIFICATION_PIPE	O_EXCL	/* Parameter to pipe2() selecting notification pipe */
 
 enum watch_notification_type {
 	WATCH_TYPE_META		= 0,	/* Special record */

@@ -201,6 +201,7 @@ Code  Seq#    Include File                                           Comments
 'W'   00-1F  linux/wanrouter.h                                       conflict! (pre 3.9)
 'W'   00-3F  sound/asound.h                                          conflict!
 'W'   40-5F  drivers/pci/switch/switchtec.c
+'W'   60-61  linux/watch_queue.h
 'X'   all    fs/xfs/xfs_fs.h,                                        conflict!
              fs/xfs/linux-2.6/xfs_ioctl32.h,
              include/linux/falloc.h,

@@ -0,0 +1,339 @@
+==============================
+General notification mechanism
+==============================
+
+The general notification mechanism is built on top of the standard pipe driver
+whereby it effectively splices notification messages from the kernel into pipes
+opened by userspace.  This can be used in conjunction with::
+
+  * Key/keyring notifications
+
+
+The notifications buffers can be enabled by:
+
+	"General setup"/"General notification queue"
+	(CONFIG_WATCH_QUEUE)
+
+This document has the following sections:
+
+.. contents:: :local:
+
+
+Overview
+========
+
+This facility appears as a pipe that is opened in a special mode.  The pipe's
+internal ring buffer is used to hold messages that are generated by the kernel.
+These messages are then read out by read().  Splice and similar are disabled on
+such pipes due to them wanting to, under some circumstances, revert their
+additions to the ring - which might end up interleaved with notification
+messages.
+
+The owner of the pipe has to tell the kernel which sources it would like to
+watch through that pipe.  Only sources that have been connected to a pipe will
+insert messages into it.  Note that a source may be bound to multiple pipes and
+insert messages into all of them simultaneously.
+
+Filters may also be emplaced on a pipe so that certain source types and
+subevents can be ignored if they're not of interest.
+
+A message will be discarded if there isn't a slot available in the ring or if
+no preallocated message buffer is available.  In both of these cases, read()
+will insert a WATCH_META_LOSS_NOTIFICATION message into the output buffer after
+the last message currently in the buffer has been read.
+
+Note that when producing a notification, the kernel does not wait for the
+consumers to collect it, but rather just continues on.  This means that
+notifications can be generated whilst spinlocks are held and also protects the
+kernel from being held up indefinitely by a userspace malfunction.
+
+
+Message Structure
+=================
+
+Notification messages begin with a short header::
+
+	struct watch_notification {
+		__u32	type:24;
+		__u32	subtype:8;
+		__u32	info;
+	};
+
+"type" indicates the source of the notification record and "subtype" indicates
+the type of record from that source (see the Watch Sources section below).  The
+type may also be "WATCH_TYPE_META".  This is a special record type generated
+internally by the watch queue itself.  There are two subtypes:
+
+  * WATCH_META_REMOVAL_NOTIFICATION
+  * WATCH_META_LOSS_NOTIFICATION
+
+The first indicates that an object on which a watch was installed was removed
+or destroyed and the second indicates that some messages have been lost.
+
+"info" indicates a bunch of things, including:
+
+  * The length of the message in bytes, including the header (mask with
+    WATCH_INFO_LENGTH and shift by WATCH_INFO_LENGTH__SHIFT).  This indicates
+    the size of the record, which may be between 8 and 127 bytes.
+
+  * The watch ID (mask with WATCH_INFO_ID and shift by WATCH_INFO_ID__SHIFT).
+    This indicates that caller's ID of the watch, which may be between 0
+    and 255.  Multiple watches may share a queue, and this provides a means to
+    distinguish them.
+
+  * A type-specific field (WATCH_INFO_TYPE_INFO).  This is set by the
+    notification producer to indicate some meaning specific to the type and
+    subtype.
+
+Everything in info apart from the length can be used for filtering.
+
+The header can be followed by supplementary information.  The format of this is
+at the discretion is defined by the type and subtype.
+
+
+Watch List (Notification Source) API
+====================================
+
+A "watch list" is a list of watchers that are subscribed to a source of
+notifications.  A list may be attached to an object (say a key or a superblock)
+or may be global (say for device events).  From a userspace perspective, a
+non-global watch list is typically referred to by reference to the object it
+belongs to (such as using KEYCTL_NOTIFY and giving it a key serial number to
+watch that specific key).
+
+To manage a watch list, the following functions are provided:
+
+  * ``void init_watch_list(struct watch_list *wlist,
+			   void (*release_watch)(struct watch *wlist));``
+
+    Initialise a watch list.  If ``release_watch`` is not NULL, then this
+    indicates a function that should be called when the watch_list object is
+    destroyed to discard any references the watch list holds on the watched
+    object.
+
+  * ``void remove_watch_list(struct watch_list *wlist);``
+
+    This removes all of the watches subscribed to a watch_list and frees them
+    and then destroys the watch_list object itself.
+
+
+Watch Queue (Notification Output) API
+=====================================
+
+A "watch queue" is the buffer allocated by an application that notification
+records will be written into.  The workings of this are hidden entirely inside
+of the pipe device driver, but it is necessary to gain a reference to it to set
+a watch.  These can be managed with:
+
+  * ``struct watch_queue *get_watch_queue(int fd);``
+
+    Since watch queues are indicated to the kernel by the fd of the pipe that
+    implements the buffer, userspace must hand that fd through a system call.
+    This can be used to look up an opaque pointer to the watch queue from the
+    system call.
+
+  * ``void put_watch_queue(struct watch_queue *wqueue);``
+
+    This discards the reference obtained from ``get_watch_queue()``.
+
+
+Watch Subscription API
+======================
+
+A "watch" is a subscription on a watch list, indicating the watch queue, and
+thus the buffer, into which notification records should be written.  The watch
+queue object may also carry filtering rules for that object, as set by
+userspace.  Some parts of the watch struct can be set by the driver::
+
+	struct watch {
+		union {
+			u32		info_id;	/* ID to be OR'd in to info field */
+			...
+		};
+		void			*private;	/* Private data for the watched object */
+		u64			id;		/* Internal identifier */
+		...
+	};
+
+The ``info_id`` value should be an 8-bit number obtained from userspace and
+shifted by WATCH_INFO_ID__SHIFT.  This is OR'd into the WATCH_INFO_ID field of
+struct watch_notification::info when and if the notification is written into
+the associated watch queue buffer.
+
+The ``private`` field is the driver's data associated with the watch_list and
+is cleaned up by the ``watch_list::release_watch()`` method.
+
+The ``id`` field is the source's ID.  Notifications that are posted with a
+different ID are ignored.
+
+The following functions are provided to manage watches:
+
+  * ``void init_watch(struct watch *watch, struct watch_queue *wqueue);``
+
+    Initialise a watch object, setting its pointer to the watch queue, using
+    appropriate barriering to avoid lockdep complaints.
+
+  * ``int add_watch_to_object(struct watch *watch, struct watch_list *wlist);``
+
+    Subscribe a watch to a watch list (notification source).  The
+    driver-settable fields in the watch struct must have been set before this
+    is called.
+
+  * ``int remove_watch_from_object(struct watch_list *wlist,
+				   struct watch_queue *wqueue,
+				   u64 id, false);``
+
+    Remove a watch from a watch list, where the watch must match the specified
+    watch queue (``wqueue``) and object identifier (``id``).  A notification
+    (``WATCH_META_REMOVAL_NOTIFICATION``) is sent to the watch queue to
+    indicate that the watch got removed.
+
+  * ``int remove_watch_from_object(struct watch_list *wlist, NULL, 0, true);``
+
+    Remove all the watches from a watch list.  It is expected that this will be
+    called preparatory to destruction and that the watch list will be
+    inaccessible to new watches by this point.  A notification
+    (``WATCH_META_REMOVAL_NOTIFICATION``) is sent to the watch queue of each
+    subscribed watch to indicate that the watch got removed.
+
+
+Notification Posting API
+========================
+
+To post a notification to watch list so that the subscribed watches can see it,
+the following function should be used::
+
+	void post_watch_notification(struct watch_list *wlist,
+				     struct watch_notification *n,
+				     const struct cred *cred,
+				     u64 id);
+
+The notification should be preformatted and a pointer to the header (``n``)
+should be passed in.  The notification may be larger than this and the size in
+units of buffer slots is noted in ``n->info & WATCH_INFO_LENGTH``.
+
+The ``cred`` struct indicates the credentials of the source (subject) and is
+passed to the LSMs, such as SELinux, to allow or suppress the recording of the
+note in each individual queue according to the credentials of that queue
+(object).
+
+The ``id`` is the ID of the source object (such as the serial number on a key).
+Only watches that have the same ID set in them will see this notification.
+
+
+Watch Sources
+=============
+
+Any particular buffer can be fed from multiple sources.  Sources include:
+
+  * WATCH_TYPE_KEY_NOTIFY
+
+    Notifications of this type indicate changes to keys and keyrings, including
+    the changes of keyring contents or the attributes of keys.
+
+    See Documentation/security/keys/core.rst for more information.
+
+
+Event Filtering
+===============
+
+Once a watch queue has been created, a set of filters can be applied to limit
+the events that are received using::
+
+	struct watch_notification_filter filter = {
+		...
+	};
+	ioctl(fd, IOC_WATCH_QUEUE_SET_FILTER, &filter)
+
+The filter description is a variable of type::
+
+	struct watch_notification_filter {
+		__u32	nr_filters;
+		__u32	__reserved;
+		struct watch_notification_type_filter filters[];
+	};
+
+Where "nr_filters" is the number of filters in filters[] and "__reserved"
+should be 0.  The "filters" array has elements of the following type::
+
+	struct watch_notification_type_filter {
+		__u32	type;
+		__u32	info_filter;
+		__u32	info_mask;
+		__u32	subtype_filter[8];
+	};
+
+Where:
+
+  * ``type`` is the event type to filter for and should be something like
+    "WATCH_TYPE_KEY_NOTIFY"
+
+  * ``info_filter`` and ``info_mask`` act as a filter on the info field of the
+    notification record.  The notification is only written into the buffer if::
+
+	(watch.info & info_mask) == info_filter
+
+    This could be used, for example, to ignore events that are not exactly on
+    the watched point in a mount tree.
+
+  * ``subtype_filter`` is a bitmask indicating the subtypes that are of
+    interest.  Bit 0 of subtype_filter[0] corresponds to subtype 0, bit 1 to
+    subtype 1, and so on.
+
+If the argument to the ioctl() is NULL, then the filters will be removed and
+all events from the watched sources will come through.
+
+
+Userspace Code Example
+======================
+
+A buffer is created with something like the following::
+
+	pipe2(fds, O_TMPFILE);
+	ioctl(fds[1], IOC_WATCH_QUEUE_SET_SIZE, 256);
+
+It can then be set to receive keyring change notifications::
+
+	keyctl(KEYCTL_WATCH_KEY, KEY_SPEC_SESSION_KEYRING, fds[1], 0x01);
+
+The notifications can then be consumed by something like the following::
+
+	static void consumer(int rfd, struct watch_queue_buffer *buf)
+	{
+		unsigned char buffer[128];
+		ssize_t buf_len;
+
+		while (buf_len = read(rfd, buffer, sizeof(buffer)),
+		       buf_len > 0
+		       ) {
+			void *p = buffer;
+			void *end = buffer + buf_len;
+			while (p < end) {
+				union {
+					struct watch_notification n;
+					unsigned char buf1[128];
+				} n;
+				size_t largest, len;
+
+				largest = end - p;
+				if (largest > 128)
+					largest = 128;
+				memcpy(&n, p, largest);
+
+				len = (n->info & WATCH_INFO_LENGTH) >>
+					WATCH_INFO_LENGTH__SHIFT;
+				if (len == 0 || len > largest)
+					return;
+
+				switch (n.n.type) {
+				case WATCH_TYPE_META:
+					got_meta(&n.n);
+				case WATCH_TYPE_KEY_NOTIFY:
+					saw_key_change(&n.n);
+					break;
+				}
+
+				p += len;
+			}
+		}
+	}

@@ -24,6 +24,7 @@
 #include <linux/syscalls.h>
 #include <linux/fcntl.h>
 #include <linux/memcontrol.h>
+#include <linux/watch_queue.h>
 
 #include <linux/uaccess.h>
 #include <asm/ioctls.h>

@@ -459,6 +460,13 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 		goto out;
 	}
 
+#ifdef CONFIG_WATCH_QUEUE
+	if (pipe->watch_queue) {
+		ret = -EXDEV;
+		goto out;
+	}
+#endif
+
 	/*
 	 * Only wake up if the pipe started out empty, since
 	 * otherwise there should be no readers waiting.

@@ -628,22 +636,37 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	int count, head, tail, mask;
 
 	switch (cmd) {
-		case FIONREAD:
-			__pipe_lock(pipe);
-			count = 0;
-			head = pipe->head;
-			tail = pipe->tail;
-			mask = pipe->ring_size - 1;
+	case FIONREAD:
+		__pipe_lock(pipe);
+		count = 0;
+		head = pipe->head;
+		tail = pipe->tail;
+		mask = pipe->ring_size - 1;
 
-			while (tail != head) {
-				count += pipe->bufs[tail & mask].len;
-				tail++;
-			}
-			__pipe_unlock(pipe);
+		while (tail != head) {
+			count += pipe->bufs[tail & mask].len;
+			tail++;
+		}
+		__pipe_unlock(pipe);
 
-			return put_user(count, (int __user *)arg);
-		default:
-			return -ENOIOCTLCMD;
+		return put_user(count, (int __user *)arg);
+
+#ifdef CONFIG_WATCH_QUEUE
+	case IOC_WATCH_QUEUE_SET_SIZE: {
+		int ret;
+		__pipe_lock(pipe);
+		ret = watch_queue_set_size(pipe, arg);
+		__pipe_unlock(pipe);
+		return ret;
+	}
+
+	case IOC_WATCH_QUEUE_SET_FILTER:
+		return watch_queue_set_filter(
+			pipe, (struct watch_notification_filter __user *)arg);
+#endif
+
+	default:
+		return -ENOIOCTLCMD;
 	}
 }
 

@@ -754,27 +777,27 @@ pipe_fasync(int fd, struct file *filp, int on)
 	return retval;
 }
 
-static unsigned long account_pipe_buffers(struct user_struct *user,
-                                 unsigned long old, unsigned long new)
+unsigned long account_pipe_buffers(struct user_struct *user,
+				   unsigned long old, unsigned long new)
 {
 	return atomic_long_add_return(new - old, &user->pipe_bufs);
 }
 
-static bool too_many_pipe_buffers_soft(unsigned long user_bufs)
+bool too_many_pipe_buffers_soft(unsigned long user_bufs)
 {
 	unsigned long soft_limit = READ_ONCE(pipe_user_pages_soft);
 
 	return soft_limit && user_bufs > soft_limit;
 }
 
-static bool too_many_pipe_buffers_hard(unsigned long user_bufs)
+bool too_many_pipe_buffers_hard(unsigned long user_bufs)
 {
 	unsigned long hard_limit = READ_ONCE(pipe_user_pages_hard);
 
 	return hard_limit && user_bufs > hard_limit;
 }
 
-static bool is_unprivileged_user(void)
+bool pipe_is_unprivileged_user(void)
 {
 	return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
 }

@@ -796,12 +819,12 @@ struct pipe_inode_info *alloc_pipe_info(void)
 
 	user_bufs = account_pipe_buffers(user, 0, pipe_bufs);
 
-	if (too_many_pipe_buffers_soft(user_bufs) && is_unprivileged_user()) {
+	if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) {
 		user_bufs = account_pipe_buffers(user, pipe_bufs, 1);
 		pipe_bufs = 1;
 	}
 
-	if (too_many_pipe_buffers_hard(user_bufs) && is_unprivileged_user())
+	if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user())
 		goto out_revert_acct;
 
 	pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer),

@@ -813,6 +836,7 @@ struct pipe_inode_info *alloc_pipe_info(void)
 		pipe->r_counter = pipe->w_counter = 1;
 		pipe->max_usage = pipe_bufs;
 		pipe->ring_size = pipe_bufs;
+		pipe->nr_accounted = pipe_bufs;
 		pipe->user = user;
 		mutex_init(&pipe->mutex);
 		return pipe;

@@ -830,7 +854,14 @@ void free_pipe_info(struct pipe_inode_info *pipe)
 {
 	int i;
 
-	(void) account_pipe_buffers(pipe->user, pipe->ring_size, 0);
+#ifdef CONFIG_WATCH_QUEUE
+	if (pipe->watch_queue) {
+		watch_queue_clear(pipe->watch_queue);
+		put_watch_queue(pipe->watch_queue);
+	}
+#endif
+
+	(void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0);
 	free_uid(pipe->user);
 	for (i = 0; i < pipe->ring_size; i++) {
 		struct pipe_buffer *buf = pipe->bufs + i;

@@ -906,6 +937,17 @@ int create_pipe_files(struct file **res, int flags)
 	if (!inode)
 		return -ENFILE;
 
+	if (flags & O_NOTIFICATION_PIPE) {
+#ifdef CONFIG_WATCH_QUEUE
+		if (watch_queue_init(inode->i_pipe) < 0) {
+			iput(inode);
+			return -ENOMEM;
+		}
+#else
+		return -ENOPKG;
+#endif
+	}
+
 	f = alloc_file_pseudo(inode, pipe_mnt, "",
 				O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)),
 				&pipefifo_fops);

@@ -936,7 +978,7 @@ static int __do_pipe_flags(int *fd, struct file **files, int flags)
 	int error;
 	int fdw, fdr;
 
-	if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT))
+	if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT | O_NOTIFICATION_PIPE))
 		return -EINVAL;
 
 	error = create_pipe_files(files, flags);

@@ -1184,42 +1226,12 @@ unsigned int round_pipe_size(unsigned long size)
 }
 
 /*
- * Allocate a new array of pipe buffers and copy the info over. Returns the
- * pipe size if successful, or return -ERROR on error.
+ * Resize the pipe ring to a number of slots.
  */
-static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
+int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots)
 {
 	struct pipe_buffer *bufs;
-	unsigned int size, nr_slots, head, tail, mask, n;
-	unsigned long user_bufs;
-	long ret = 0;
-
-	size = round_pipe_size(arg);
-	nr_slots = size >> PAGE_SHIFT;
-
-	if (!nr_slots)
-		return -EINVAL;
-
-	/*
-	 * If trying to increase the pipe capacity, check that an
-	 * unprivileged user is not trying to exceed various limits
-	 * (soft limit check here, hard limit check just below).
-	 * Decreasing the pipe capacity is always permitted, even
-	 * if the user is currently over a limit.
-	 */
-	if (nr_slots > pipe->ring_size &&
-			size > pipe_max_size && !capable(CAP_SYS_RESOURCE))
-		return -EPERM;
-
-	user_bufs = account_pipe_buffers(pipe->user, pipe->ring_size, nr_slots);
-
-	if (nr_slots > pipe->ring_size &&
-			(too_many_pipe_buffers_hard(user_bufs) ||
-			 too_many_pipe_buffers_soft(user_bufs)) &&
-			is_unprivileged_user()) {
-		ret = -EPERM;
-		goto out_revert_acct;
-	}
+	unsigned int head, tail, mask, n;
 
 	/*
 	 * We can shrink the pipe, if arg is greater than the ring occupancy.

@@ -1231,17 +1243,13 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
 	head = pipe->head;
 	tail = pipe->tail;
 	n = pipe_occupancy(pipe->head, pipe->tail);
-	if (nr_slots < n) {
-		ret = -EBUSY;
-		goto out_revert_acct;
-	}
+	if (nr_slots < n)
+		return -EBUSY;
 
 	bufs = kcalloc(nr_slots, sizeof(*bufs),
 		       GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
-	if (unlikely(!bufs)) {
-		ret = -ENOMEM;
-		goto out_revert_acct;
-	}
+	if (unlikely(!bufs))
+		return -ENOMEM;
 
 	/*
 	 * The pipe array wraps around, so just start the new one at zero

@@ -1269,16 +1277,68 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
 	kfree(pipe->bufs);
 	pipe->bufs = bufs;
 	pipe->ring_size = nr_slots;
-	pipe->max_usage = nr_slots;
+	if (pipe->max_usage > nr_slots)
+		pipe->max_usage = nr_slots;
 	pipe->tail = tail;
 	pipe->head = head;
 
 	/* This might have made more room for writers */
 	wake_up_interruptible(&pipe->wr_wait);
+	return 0;
+}
+
+/*
+ * Allocate a new array of pipe buffers and copy the info over. Returns the
+ * pipe size if successful, or return -ERROR on error.
+ */
+static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
+{
+	unsigned long user_bufs;
+	unsigned int nr_slots, size;
+	long ret = 0;
+
+#ifdef CONFIG_WATCH_QUEUE
+	if (pipe->watch_queue)
+		return -EBUSY;
+#endif
+
+	size = round_pipe_size(arg);
+	nr_slots = size >> PAGE_SHIFT;
+
+	if (!nr_slots)
+		return -EINVAL;
+
+	/*
+	 * If trying to increase the pipe capacity, check that an
+	 * unprivileged user is not trying to exceed various limits
+	 * (soft limit check here, hard limit check just below).
+	 * Decreasing the pipe capacity is always permitted, even
+	 * if the user is currently over a limit.
+	 */
+	if (nr_slots > pipe->max_usage &&
+			size > pipe_max_size && !capable(CAP_SYS_RESOURCE))
+		return -EPERM;
+
+	user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_slots);
+
+	if (nr_slots > pipe->max_usage &&
+			(too_many_pipe_buffers_hard(user_bufs) ||
+			 too_many_pipe_buffers_soft(user_bufs)) &&
+			pipe_is_unprivileged_user()) {
+		ret = -EPERM;
+		goto out_revert_acct;
+	}
+
+	ret = pipe_resize_ring(pipe, nr_slots);
+	if (ret < 0)
+		goto out_revert_acct;
+
+	pipe->max_usage = nr_slots;
+	pipe->nr_accounted = nr_slots;
 	return pipe->max_usage * PAGE_SIZE;
 
 out_revert_acct:
-	(void) account_pipe_buffers(pipe->user, nr_slots, pipe->ring_size);
+	(void) account_pipe_buffers(pipe->user, nr_slots, pipe->nr_accounted);
 	return ret;
 }
 

@@ -1287,9 +1347,17 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
  * location, so checking ->i_pipe is not enough to verify that this is a
  * pipe.
  */
-struct pipe_inode_info *get_pipe_info(struct file *file)
+struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice)
 {
-	return file->f_op == &pipefifo_fops ? file->private_data : NULL;
+	struct pipe_inode_info *pipe = file->private_data;
+
+	if (file->f_op != &pipefifo_fops || !pipe)
+		return NULL;
+#ifdef CONFIG_WATCH_QUEUE
+	if (for_splice && pipe->watch_queue)
+		return NULL;
+#endif
+	return pipe;
 }
 
 long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)

@@ -1297,7 +1365,7 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 	struct pipe_inode_info *pipe;
 	long ret;
 
-	pipe = get_pipe_info(file);
+	pipe = get_pipe_info(file, false);
 	if (!pipe)
 		return -EBADF;
 

@@ -1118,8 +1118,8 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 	loff_t offset;
 	long ret;
 
-	ipipe = get_pipe_info(in);
-	opipe = get_pipe_info(out);
+	ipipe = get_pipe_info(in, true);
+	opipe = get_pipe_info(out, true);
 
 	if (ipipe && opipe) {
 		if (off_in || off_out)

@@ -1278,7 +1278,7 @@ static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 static long vmsplice_to_user(struct file *file, struct iov_iter *iter,
 			     unsigned int flags)
 {
-	struct pipe_inode_info *pipe = get_pipe_info(file);
+	struct pipe_inode_info *pipe = get_pipe_info(file, true);
 	struct splice_desc sd = {
 		.total_len = iov_iter_count(iter),
 		.flags = flags,

@@ -1313,7 +1313,7 @@ static long vmsplice_to_pipe(struct file *file, struct iov_iter *iter,
 	if (flags & SPLICE_F_GIFT)
 		buf_flag = PIPE_BUF_FLAG_GIFT;
 
-	pipe = get_pipe_info(file);
+	pipe = get_pipe_info(file, true);
 	if (!pipe)
 		return -EBADF;
 

@@ -1766,8 +1766,8 @@ static int link_pipe(struct pipe_inode_info *ipipe,
 static long do_tee(struct file *in, struct file *out, size_t len,
 		   unsigned int flags)
 {
-	struct pipe_inode_info *ipipe = get_pipe_info(in);
-	struct pipe_inode_info *opipe = get_pipe_info(out);
+	struct pipe_inode_info *ipipe = get_pipe_info(in, true);
+	struct pipe_inode_info *opipe = get_pipe_info(out, true);
 	int ret = -EINVAL;
 
 	/*

@@ -35,6 +35,7 @@ struct pipe_buffer {
  *	@tail: The point of buffer consumption
  *	@max_usage: The maximum number of slots that may be used in the ring
  *	@ring_size: total number of buffers (should be a power of 2)
+ *	@nr_accounted: The amount this pipe accounts for in user->pipe_bufs
  *	@tmp_page: cached released page
  *	@readers: number of current readers of this pipe
  *	@writers: number of current writers of this pipe

@@ -45,6 +46,7 @@ struct pipe_buffer {
  *	@fasync_writers: writer side fasync
  *	@bufs: the circular array of pipe buffers
  *	@user: the user who created this pipe
+ *	@watch_queue: If this pipe is a watch_queue, this is the stuff for that
  **/
 struct pipe_inode_info {
 	struct mutex mutex;

@@ -53,6 +55,7 @@ struct pipe_inode_info {
 	unsigned int tail;
 	unsigned int max_usage;
 	unsigned int ring_size;
+	unsigned int nr_accounted;
 	unsigned int readers;
 	unsigned int writers;
 	unsigned int files;

@@ -63,6 +66,9 @@ struct pipe_inode_info {
 	struct fasync_struct *fasync_writers;
 	struct pipe_buffer *bufs;
 	struct user_struct *user;
+#ifdef CONFIG_WATCH_QUEUE
+	struct watch_queue *watch_queue;
+#endif
 };
 
 /*

@@ -237,9 +243,20 @@ void pipe_buf_mark_unmergeable(struct pipe_buffer *buf);
 
 extern const struct pipe_buf_operations nosteal_pipe_buf_ops;
 
+#ifdef CONFIG_WATCH_QUEUE
+unsigned long account_pipe_buffers(struct user_struct *user,
+				   unsigned long old, unsigned long new);
+bool too_many_pipe_buffers_soft(unsigned long user_bufs);
+bool too_many_pipe_buffers_hard(unsigned long user_bufs);
+bool pipe_is_unprivileged_user(void);
+#endif
+
 /* for F_SETPIPE_SZ and F_GETPIPE_SZ */
+#ifdef CONFIG_WATCH_QUEUE
+int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots);
+#endif
 long pipe_fcntl(struct file *, unsigned int, unsigned long arg);
-struct pipe_inode_info *get_pipe_info(struct file *file);
+struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice);
 
 int create_pipe_files(struct file **, int);
 unsigned int round_pipe_size(unsigned long size);

@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0
+/* User-mappable watch queue
+ *
+ * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * See Documentation/watch_queue.rst
+ */
+
+#ifndef _LINUX_WATCH_QUEUE_H
+#define _LINUX_WATCH_QUEUE_H
+
+#include <uapi/linux/watch_queue.h>
+#include <linux/kref.h>
+#include <linux/rcupdate.h>
+
+#ifdef CONFIG_WATCH_QUEUE
+
+struct cred;
+
+struct watch_type_filter {
+	enum watch_notification_type type;
+	__u32		subtype_filter[1];	/* Bitmask of subtypes to filter on */
+	__u32		info_filter;		/* Filter on watch_notification::info */
+	__u32		info_mask;		/* Mask of relevant bits in info_filter */
+};
+
+struct watch_filter {
+	union {
+		struct rcu_head	rcu;
+		unsigned long	type_filter[2];	/* Bitmask of accepted types */
+	};
+	u32			nr_filters;	/* Number of filters */
+	struct watch_type_filter filters[];
+};
+
+struct watch_queue {
+	struct rcu_head		rcu;
+	struct watch_filter __rcu *filter;
+	struct pipe_inode_info	*pipe;		/* The pipe we're using as a buffer */
+	struct hlist_head	watches;	/* Contributory watches */
+	struct page		**notes;	/* Preallocated notifications */
+	unsigned long		*notes_bitmap;	/* Allocation bitmap for notes */
+	struct kref		usage;		/* Object usage count */
+	spinlock_t		lock;
+	unsigned int		nr_notes;	/* Number of notes */
+	unsigned int		nr_pages;	/* Number of pages in notes[] */
+	bool			defunct;	/* T when queues closed */
+};
+
+/*
+ * Representation of a watch on an object.
+ */
+struct watch {
+	union {
+		struct rcu_head	rcu;
+		u32		info_id;	/* ID to be OR'd in to info field */
+	};
+	struct watch_queue __rcu *queue;	/* Queue to post events to */
+	struct hlist_node	queue_node;	/* Link in queue->watches */
+	struct watch_list __rcu	*watch_list;
+	struct hlist_node	list_node;	/* Link in watch_list->watchers */
+	const struct cred	*cred;		/* Creds of the owner of the watch */
+	void			*private;	/* Private data for the watched object */
+	u64			id;		/* Internal identifier */
+	struct kref		usage;		/* Object usage count */
+};
+
+/*
+ * List of watches on an object.
+ */
+struct watch_list {
+	struct rcu_head		rcu;
+	struct hlist_head	watchers;
+	void (*release_watch)(struct watch *);
+	spinlock_t		lock;
+};
+
+extern void __post_watch_notification(struct watch_list *,
+				      struct watch_notification *,
+				      const struct cred *,
+				      u64);
+extern struct watch_queue *get_watch_queue(int);
+extern void put_watch_queue(struct watch_queue *);
+extern void init_watch(struct watch *, struct watch_queue *);
+extern int add_watch_to_object(struct watch *, struct watch_list *);
+extern int remove_watch_from_object(struct watch_list *, struct watch_queue *, u64, bool);
+extern long watch_queue_set_size(struct pipe_inode_info *, unsigned int);
+extern long watch_queue_set_filter(struct pipe_inode_info *,
+				   struct watch_notification_filter __user *);
+extern int watch_queue_init(struct pipe_inode_info *);
+extern void watch_queue_clear(struct watch_queue *);
+
+static inline void init_watch_list(struct watch_list *wlist,
+				   void (*release_watch)(struct watch *))
+{
+	INIT_HLIST_HEAD(&wlist->watchers);
+	spin_lock_init(&wlist->lock);
+	wlist->release_watch = release_watch;
+}
+
+static inline void post_watch_notification(struct watch_list *wlist,
+					   struct watch_notification *n,
+					   const struct cred *cred,
+					   u64 id)
+{
+	if (unlikely(wlist))
+		__post_watch_notification(wlist, n, cred, id);
+}
+
+static inline void remove_watch_list(struct watch_list *wlist, u64 id)
+{
+	if (wlist) {
+		remove_watch_from_object(wlist, NULL, id, true);
+		kfree_rcu(wlist, rcu);
+	}
+}
+
+/**
+ * watch_sizeof - Calculate the information part of the size of a watch record,
+ * given the structure size.
+ */
+#define watch_sizeof(STRUCT) (sizeof(STRUCT) << WATCH_INFO_LENGTH__SHIFT)
+
+#endif
+
+#endif /* _LINUX_WATCH_QUEUE_H */

@@ -4,9 +4,13 @@
 
 #include <linux/types.h>
 #include <linux/fcntl.h>
+#include <linux/ioctl.h>
 
 #define O_NOTIFICATION_PIPE	O_EXCL	/* Parameter to pipe2() selecting notification pipe */
 
+#define IOC_WATCH_QUEUE_SET_SIZE	_IO('W', 0x60)	/* Set the size in pages */
+#define IOC_WATCH_QUEUE_SET_FILTER	_IO('W', 0x61)	/* Set the filter */
+
 enum watch_notification_type {
 	WATCH_TYPE_META		= 0,	/* Special record */
 	WATCH_TYPE__NR		= 1

@@ -41,6 +45,22 @@ struct watch_notification {
 #define WATCH_INFO_FLAG_7	0x00800000
 };
 
+/*
+ * Notification filtering rules (IOC_WATCH_QUEUE_SET_FILTER).
+ */
+struct watch_notification_type_filter {
+	__u32	type;			/* Type to apply filter to */
+	__u32	info_filter;		/* Filter on watch_notification::info */
+	__u32	info_mask;		/* Mask of relevant bits in info_filter */
+	__u32	subtype_filter[8];	/* Bitmask of subtypes to filter on */
+};
+
+struct watch_notification_filter {
+	__u32	nr_filters;		/* Number of filters */
+	__u32	__reserved;		/* Must be 0 */
+	struct watch_notification_type_filter filters[];
+};
+
 
 /*
  * Extended watch removal notification.  This is used optionally if the type