[RFC][PATCH 0/8] Mount, FS, Block and Keyrings notifications [ver #2]

@@ -46,6 +46,7 @@ static void file_free_rcu(struct rcu_head *head)
 	struct file *f = container_of(head, struct file, f_u.fu_rcuhead);
 
 	put_cred(f->f_cred);
+	put_cred(f->f_fput_cred);
 	kmem_cache_free(filp_cachep, f);
 }
 

@@ -252,6 +253,7 @@ struct file *alloc_file_clone(struct file *base, int flags,
  */
 static void __fput(struct file *file)
 {
+	const struct cred *saved_cred;
 	struct dentry *dentry = file->f_path.dentry;
 	struct vfsmount *mnt = file->f_path.mnt;
 	struct inode *inode = file->f_inode;

@@ -262,6 +264,12 @@ static void __fput(struct file *file)
 
 	might_sleep();
 
+	/* Set the creds of whoever triggered the last fput for the LSM.  Note
+	 * that this has to be made available to further fputs, say on fds
+	 * trapped in a unix socket.
+	 */
+	saved_cred = override_creds(file->f_fput_cred);
+
 	fsnotify_close(file);
 	/*
 	 * The function eventpoll_release() should be the first called

@@ -293,6 +301,8 @@ static void __fput(struct file *file)
 	if (unlikely(mode & FMODE_NEED_UNMOUNT))
 		dissolve_on_fput(mnt);
 	mntput(mnt);
+
+	revert_creds(saved_cred);
 out:
 	file_free(file);
 }

@@ -334,6 +344,7 @@ void fput_many(struct file *file, unsigned int refs)
 	if (atomic_long_sub_and_test(refs, &file->f_count)) {
 		struct task_struct *task = current;
 
+		file->f_fput_cred = get_current_cred();
 		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
 			init_task_work(&file->f_u.fu_rcuhead, ____fput);
 			if (!task_work_add(task, &file->f_u.fu_rcuhead, true))

@@ -368,6 +379,7 @@ void __fput_sync(struct file *file)
 	if (atomic_long_dec_and_test(&file->f_count)) {
 		struct task_struct *task = current;
 		BUG_ON(!(task->flags & PF_KTHREAD));
+		file->f_fput_cred = get_current_cred();
 		__fput(file);
 	}
 }

@@ -943,6 +943,7 @@ struct file {
 	loff_t			f_pos;
 	struct fown_struct	f_owner;
 	const struct cred	*f_cred;
+	const struct cred	*f_fput_cred;	/* Who did the last fput() (for LSM) */
 	struct file_ra_state	f_ra;
 
 	u64			f_version;

@@ -0,0 +1,328 @@
+============================
+Mappable notifications queue
+============================
+
+This is a misc device that acts as a mapped ring buffer by which userspace can
+receive notifications from the kernel.  This can be used in conjunction with::
+
+  * Key/keyring notifications
+
+  * Mount topology change notifications
+
+  * Superblock event notifications
+
+  * Block layer event notifications
+
+
+The notifications buffers can be enabled by:
+
+	"Device Drivers"/"Misc devices"/"Mappable notification queue"
+	(CONFIG_WATCH_QUEUE)
+
+This document has the following sections:
+
+.. contents:: :local:
+
+
+Overview
+========
+
+This facility appears as a misc device file that is opened and then mapped and
+polled.  Each time it is opened, it creates a new buffer specific to the
+returned file descriptor.  Then, when the opening process sets watches, it
+indicates the particular buffer it wants notifications from that watch to be
+written into.  Note that there are no read() and write() methods (except for
+debugging).  The user is expected to access the ring directly and to use poll
+to wait for new data.
+
+If a watch is in place, notifications are only written into the buffer if the
+filter criteria are passed and if there's sufficient space available in the
+ring.  If neither of those is so, a notification will be discarded.  In the
+latter case, an overrun indicator will also be set.
+
+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.
+
+As far as the ring goes, the head index belongs to the kernel and the tail
+index belongs to userspace.  The kernel will refuse to write anything if the
+tail index becomes invalid.  Userspace *must* use appropriate memory barriers
+between reading or updating the tail index and reading the ring.
+
+
+Record Structure
+================
+
+Notification records in the ring may occupy a variable number of slots within
+the buffer, beginning with a 1-slot 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 driver itself.  There are two subtypes, one of
+which indicates records that should be just skipped (padding or metadata):
+
+  * WATCH_META_SKIP_NOTIFICATION
+  * WATCH_META_REMOVAL_NOTIFICATION
+
+The former indicates a record that should just be skipped and the latter
+indicates that an object on which a watchpoint was installed was removed or
+destroyed.
+
+"info" indicates a bunch of things, including:
+
+  * The length of the record (mask with WATCH_INFO_LENGTH).  This indicates the
+    size of the record, which may be between 1 and 63 slots.  Note that this is
+    placed appropriately within the info value so that no shifting is required
+    to convert number of occupied slots to byte length.
+
+  * The watchpoint ID (mask with WATCH_INFO_ID).  This indicates that caller's
+    ID of the watchpoint, which may be between 0 and 255.  Multiple watchpoints
+    may share a queue, and this provides a means to distinguish them.
+
+  * A buffer overrun flag (WATCH_INFO_OVERRUN flag).  If this is set in a
+    notification record, some of the preceding records were discarded.
+
+  * An ENOMEM-loss flag (WATCH_INFO_ENOMEM flag).  This is set to indicate that
+    an event was lost to ENOMEM.
+
+  * A recursive-change flag (WATCH_INFO_RECURSIVE flag).  This is set to
+    indicate that the change that happened was recursive - for instance
+    changing the attributes on an entire mount subtree.
+
+  * An exact-match flag (WATCH_INFO_IN_SUBTREE flag).  This is set if the event
+    didn't happen exactly at the watchpoint, but rather somewhere in the
+    subtree thereunder.
+
+  * Some type-specific flags (WATCH_INFO_TYPE_FLAGS).  These are 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.
+
+
+Ring Structure
+==============
+
+The ring is divided into 8-byte slots.  The caller uses an ioctl() to set the
+size of the ring after opening and this must be a power-of-2 multiple of the
+system page size (so that the mask can be used with AND).
+
+The head and tail indices are stored in the first two slots in the ring, which
+are marked out as a skippable entry::
+
+	struct watch_queue_buffer {
+		union {
+			struct {
+				struct watch_notification watch;
+				volatile __u32	head;
+				volatile __u32	tail;
+				__u32		mask;
+			} meta;
+			struct watch_notification slots[0];
+		};
+	};
+
+In "meta.watch", type will be set to WATCH_TYPE_META and subtype to
+WATCH_META_SKIP_NOTIFICATION so that anyone processing the buffer will just
+skip this record.  Also, because this record is here, records cannot wrap round
+the end of the buffer, so a skippable padding element will be inserted at the
+end of the buffer if needed.  Thus the contents of a notification record in the
+buffer are always contiguous.
+
+"meta.mask" is an AND'able mask to turn the index counters into slots array
+indices.
+
+The buffer is empty if "meta.head" == "meta.tail".
+
+[!] NOTE that the ring indices "meta.head" and "meta.tail" are indices into
+"slots[]" not byte offsets into the buffer.
+
+[!] NOTE that userspace must never change the head pointer.  This belongs to
+the kernel and will be updated by that.  The kernel will never change the tail
+pointer.
+
+[!] NOTE that userspace must never AND-off the tail pointer before updating it,
+but should just keep adding to it and letting it wrap naturally.  The value
+*should* be masked off when used as an index into slots[].
+
+[!] NOTE that if the distance between head and tail becomes too great, the
+kernel will assume the buffer is full and write no more until the issue is
+resolved.
+
+
+Watch Sources
+=============
+
+Any particular buffer can be fed from multiple sources.  Sources include:
+
+  * WATCH_TYPE_MOUNT_NOTIFY
+
+    Notifications of this type indicate mount tree topology changes and mount
+    attribute changes.  A watchpoint can be set on a particular file or
+    directory and notifications from the path subtree rooted at that point will
+    be intercepted.
+
+  * WATCH_TYPE_SB_NOTIFY
+
+    Notifications of this type indicate superblock events, such as quota limits
+    being hit, I/O errors being produced or network server loss/reconnection.
+    Watchpoints of this type are set directly on superblocks.
+
+  * 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.
+
+  * WATCH_TYPE_BLOCK_NOTIFY
+
+    Notifications of this type indicate block layer events, such as I/O errors
+    or temporary link loss.  Watchpoints of this type are set on a global
+    queue.
+
+
+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_MOUNT_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 can be used, for example, to ignore events that are not exactly on the
+    watched point in a mount tree by specifying WATCH_INFO_IN_SUBTREE must
+    be 0.
+
+  * ``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.
+
+
+Polling
+=======
+
+The file descriptor that holds the buffer may be used with poll() and similar.
+POLLIN and POLLRDNORM are set if the buffer indices differ.  POLLERR is set if
+the buffer indices are further apart than the size of the buffer.  Wake-up
+events are only generated if the buffer is transitioned from an empty state.
+
+
+Example
+=======
+
+A buffer is created with something like the following::
+
+	fd = open("/dev/watch_queue", O_RDWR);
+
+	#define BUF_SIZE 4
+	ioctl(fd, IOC_WATCH_QUEUE_SET_SIZE, BUF_SIZE);
+
+	page_size = sysconf(_SC_PAGESIZE);
+	buf = mmap(NULL, BUF_SIZE * page_size,
+		   PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+
+It can then be set to receive mount topology change notifications, keyring
+change notifications and superblock notifications::
+
+	memset(&filter, 0, sizeof(filter));
+	filter.subtype_filter[0] = ~0ULL;
+	filter.info_mask	 = WATCH_INFO_IN_SUBTREE;
+	filter.info_filter	 = 0;
+	filter.info_id		 = 0x01000000;
+
+	keyctl(KEYCTL_WATCH_KEY, KEY_SPEC_SESSION_KEYRING, fd, &filter);
+
+	mount_notify(AT_FDCWD, "/", 0, fd, &filter);
+
+	sb_notify(AT_FDCWD, "/", 0, fd, &filter);
+
+The notifications can then be consumed by something like the following::
+
+	extern void saw_mount_change(struct watch_notification *n);
+	extern void saw_key_change(struct watch_notification *n);
+
+	static int consumer(int fd, struct watch_queue_buffer *buf)
+	{
+		struct watch_notification *n;
+		struct pollfd p[1];
+		unsigned int head, tail, mask = buf->meta.mask;
+
+		for (;;) {
+			p[0].fd = fd;
+			p[0].events = POLLIN | POLLERR;
+			p[0].revents = 0;
+
+			if (poll(p, 1, -1) == -1 || p[0].revents & POLLERR)
+				goto went_wrong;
+
+			while (head = _atomic_load_acquire(buf->meta.head),
+			       tail = buf->meta.tail,
+			       tail != head
+			       ) {
+				n = &buf->slots[tail & mask];
+				if ((n->info & WATCH_INFO_LENGTH) == 0)
+					goto went_wrong;
+
+				switch (n->type) {
+				case WATCH_TYPE_MOUNT_NOTIFY:
+					saw_mount_change(n);
+					break;
+				case WATCH_TYPE_KEY_NOTIFY:
+					saw_key_change(n);
+					break;
+				}
+
+				tail += (n->info & WATCH_INFO_LENGTH) >> WATCH_LENGTH_SHIFT;
+				_atomic_store_release(buf->meta.tail, tail);
+			}
+		}
+
+	went_wrong:
+		return 0;
+	}
+
+Note the memory barriers when loading the head pointer and storing the tail
+pointer!

@@ -4,6 +4,19 @@
 
 menu "Misc devices"
 
+config WATCH_QUEUE
+	bool "Mappable notification queue"
+	default n
+	depends on MMU
+	help
+	  This is a general notification queue for the kernel to pass events to
+	  userspace through a mmap()'able ring buffer.  It can be used in
+	  conjunction with watches for mount topology change notifications,
+	  superblock change notifications and key/keyring change notifications.
+
+	  Note that in theory this should work fine with NOMMU, but I'm not
+	  sure how to make that work.
+
 config SENSORS_LIS3LV02D
 	tristate
 	depends on INPUT

@@ -3,6 +3,7 @@
 # Makefile for misc devices that really don't fit anywhere else.
 #
 
+obj-$(CONFIG_WATCH_QUEUE)	+= watch_queue.o
 obj-$(CONFIG_IBM_ASM)		+= ibmasm/
 obj-$(CONFIG_IBMVMC)		+= ibmvmc.o
 obj-$(CONFIG_AD525X_DPOT)	+= ad525x_dpot.o

@@ -0,0 +1,895 @@
+/* User-mappable watch queue
+ *
+ * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ *
+ * See Documentation/watch_queue.rst
+ */
+
+#define pr_fmt(fmt) "watchq: " fmt
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/printk.h>
+#include <linux/miscdevice.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/poll.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/file.h>
+#include <linux/security.h>
+#include <linux/cred.h>
+#include <linux/watch_queue.h>
+
+#undef DEBUG_WITH_WRITE /* Allow use of write() to record notifications */
+
+MODULE_DESCRIPTION("Watch queue");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+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 address_space	mapping;
+	const struct cred	*cred;		/* Creds of the owner of the queue */
+	struct watch_filter __rcu *filter;
+	wait_queue_head_t	waiters;
+	struct hlist_head	watches;	/* Contributory watches */
+	struct kref		usage;		/* Object usage count */
+	spinlock_t		lock;
+	bool			defunct;	/* T when queues closed */
+	u8			nr_pages;	/* Size of pages[] */
+	u8			flag_next;	/* Flag to apply to next item */
+#ifdef DEBUG_WITH_WRITE
+	u8			debug;
+#endif
+	u32			size;
+	struct watch_queue_buffer *buffer;	/* Pointer to first record */
+
+	/* The mappable pages.  The zeroth page holds the ring pointers. */
+	struct page		**pages;
+};
+
+/**
+ * post_one_notification - Post an event notification to one queue
+ * @wqueue: The watch queue to add the event to.
+ * @n: The notification record to post.
+ * @cred: The credentials to use in security checks.
+ *
+ * Post a notification of an event into an mmap'd queue and let the user know.
+ * Returns true if successful and false on failure (eg. buffer overrun or
+ * userspace mucked up the ring indices).
+ *
+ *
+ * The size of the notification should be set in n->flags & WATCH_LENGTH and
+ * should be in units of sizeof(*n).
+ */
+static bool post_one_notification(struct watch_queue *wqueue,
+				  struct watch_notification *n,
+				  const struct cred *cred)
+{
+	struct watch_queue_buffer *buf = wqueue->buffer;
+	unsigned int metalen = sizeof(buf->meta) / sizeof(buf->slots[0]);
+	unsigned int size = wqueue->size, mask = size - 1;
+	unsigned int len;
+	unsigned int ring_tail, tail, head, used, segment, h;
+
+	if (!buf)
+		return false;
+
+	len = (n->info & WATCH_INFO_LENGTH) >> WATCH_LENGTH_SHIFT;
+	if (len == 0)
+		return false;
+
+	spin_lock_bh(&wqueue->lock); /* Protect head pointer */
+
+	if (wqueue->defunct ||
+	    security_post_notification(wqueue->cred, cred, n) < 0)
+		goto out;
+
+	ring_tail = READ_ONCE(buf->meta.tail);
+	head = READ_ONCE(buf->meta.head);
+	used = head - ring_tail;
+
+	/* Check to see if userspace mucked up the pointers */
+	if (used >= size)
+		goto overrun;
+	tail = ring_tail & mask;
+	if (tail > 0 && tail < metalen)
+		goto overrun;
+
+	h = head & mask;
+	if (h >= tail) {
+		/* Head is at or after tail in the buffer.  There may then be
+		 * two segments: one to the end of buffer and one at the
+		 * beginning of the buffer between the metadata block and the
+		 * tail pointer.
+		 */
+		segment = size - h;
+		if (len > segment) {
+			/* Not enough space in the post-head segment; we need
+			 * to wrap.  When wrapping, we will have to skip the
+			 * metadata at the beginning of the buffer.
+			 */
+			if (len > tail - metalen)
+				goto overrun;
+
+			/* Fill the space at the end of the page */
+			buf->slots[h].type	= WATCH_TYPE_META;
+			buf->slots[h].subtype	= WATCH_META_SKIP_NOTIFICATION;
+			buf->slots[h].info	= segment << WATCH_LENGTH_SHIFT;
+			head += segment;
+			h = 0;
+			if (h >= tail)
+				goto overrun;
+		}
+	}
+
+	if (h == 0) {
+		/* Reset and skip the header metadata */
+		buf->meta.watch.type = WATCH_TYPE_META;
+		buf->meta.watch.subtype = WATCH_META_SKIP_NOTIFICATION;
+		buf->meta.watch.info = metalen << WATCH_LENGTH_SHIFT;
+		head += metalen;
+		h = metalen;
+		if (h >= tail)
+			goto overrun;
+	}
+
+	if (h < tail) {
+		/* Head is before tail in the buffer.  There may be one segment
+		 * between the two, but we may need to skip the metadata block.
+		 */
+		segment = tail - h;
+		if (len > segment)
+			goto overrun;
+	}
+
+	n->info |= wqueue->flag_next;
+	wqueue->flag_next = 0;
+	memcpy(buf->slots + h, n, len * sizeof(buf->slots[0]));
+	head += len;
+
+	smp_store_release(&buf->meta.head, head);
+	spin_unlock_bh(&wqueue->lock);
+	if (used == 0)
+		wake_up(&wqueue->waiters);
+	return true;
+
+overrun:
+	wqueue->flag_next = WATCH_INFO_OVERRUN;
+out:
+	spin_unlock_bh(&wqueue->lock);
+	return false;
+}
+
+/*
+ * Apply filter rules to a notification.
+ */
+static bool filter_watch_notification(const struct watch_filter *wf,
+				      const struct watch_notification *n)
+{
+	const struct watch_type_filter *wt;
+	int i;
+
+	if (!test_bit(n->type, wf->type_filter))
+		return false;
+
+	for (i = 0; i < wf->nr_filters; i++) {
+		wt = &wf->filters[i];
+		if (n->type == wt->type &&
+		    ((1U << n->subtype) & wt->subtype_filter[0]) &&
+		    (n->info & wt->info_mask) == wt->info_filter)
+			return true;
+	}
+
+	return false; /* If there is a filter, the default is to reject. */
+}
+
+/**
+ * __post_watch_notification - Post an event notification
+ * @wlist: The watch list to post the event to.
+ * @n: The notification record to post.
+ * @cred: The creds of the process that triggered the notification.
+ * @id: The ID to match on the watch.
+ *
+ * Post a notification of an event into a set of watch queues and let the users
+ * know.
+ *
+ * If @n is NULL then WATCH_INFO_LENGTH will be set on the next event posted.
+ *
+ * The size of the notification should be set in n->info & WATCH_INFO_LENGTH and
+ * should be in units of sizeof(*n).
+ */
+void __post_watch_notification(struct watch_list *wlist,
+			       struct watch_notification *n,
+			       const struct cred *cred,
+			       u64 id)
+{
+	const struct watch_filter *wf;
+	struct watch_queue *wqueue;
+	struct watch *watch;
+
+	rcu_read_lock();
+
+	hlist_for_each_entry_rcu(watch, &wlist->watchers, list_node) {
+		if (watch->id != id)
+			continue;
+		n->info &= ~(WATCH_INFO_ID | WATCH_INFO_OVERRUN);
+		n->info |= watch->info_id;
+
+		wqueue = rcu_dereference(watch->queue);
+		wf = rcu_dereference(wqueue->filter);
+		if (wf && !filter_watch_notification(wf, n))
+			continue;
+
+		post_one_notification(wqueue, n, cred);
+	}
+
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(__post_watch_notification);
+
+/*
+ * Allow the queue to be polled.
+ */
+static __poll_t watch_queue_poll(struct file *file, poll_table *wait)
+{
+	struct watch_queue *wqueue = file->private_data;
+	struct watch_queue_buffer *buf = wqueue->buffer;
+	unsigned int head, tail;
+	__poll_t mask = 0;
+
+	poll_wait(file, &wqueue->waiters, wait);
+
+	head = READ_ONCE(buf->meta.head);
+	tail = READ_ONCE(buf->meta.tail);
+	if (head != tail)
+		mask |= EPOLLIN | EPOLLRDNORM;
+	if (head - tail > wqueue->size)
+		mask |= EPOLLERR;
+	return mask;
+}
+
+static int watch_queue_set_page_dirty(struct page *page)
+{
+	SetPageDirty(page);
+	return 0;
+}
+
+static const struct address_space_operations watch_queue_aops = {
+	.set_page_dirty	= watch_queue_set_page_dirty,
+};
+
+static vm_fault_t watch_queue_fault(struct vm_fault *vmf)
+{
+	struct watch_queue *wqueue = vmf->vma->vm_file->private_data;
+	struct page *page;
+
+	page = wqueue->pages[vmf->pgoff];
+	get_page(page);
+	if (!lock_page_or_retry(page, vmf->vma->vm_mm, vmf->flags)) {
+		put_page(page);
+		return VM_FAULT_RETRY;
+	}
+	vmf->page = page;
+	return VM_FAULT_LOCKED;
+}
+
+static void watch_queue_map_pages(struct vm_fault *vmf,
+				  pgoff_t start_pgoff, pgoff_t end_pgoff)
+{
+	struct watch_queue *wqueue = vmf->vma->vm_file->private_data;
+	struct page *page;
+
+	rcu_read_lock();
+
+	do {
+		page = wqueue->pages[start_pgoff];
+		if (trylock_page(page)) {
+			vm_fault_t ret;
+			get_page(page);
+			ret = alloc_set_pte(vmf, NULL, page);
+			if (ret != 0)
+				put_page(page);
+
+			unlock_page(page);
+		}
+	} while (++start_pgoff < end_pgoff);
+
+	rcu_read_unlock();
+}
+
+static const struct vm_operations_struct watch_queue_vm_ops = {
+	.fault		= watch_queue_fault,
+	.map_pages	= watch_queue_map_pages,
+};
+
+/*
+ * Map the buffer.
+ */
+static int watch_queue_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct watch_queue *wqueue = file->private_data;
+	struct inode *inode = file_inode(file);
+	u8 nr_pages;
+
+	inode_lock(inode);
+	nr_pages = wqueue->nr_pages;
+	inode_unlock(inode);
+
+	if (nr_pages == 0 ||
+	    vma->vm_pgoff != 0 ||
+	    vma->vm_end - vma->vm_start > nr_pages * PAGE_SIZE ||
+	    !(pgprot_val(vma->vm_page_prot) & pgprot_val(PAGE_SHARED)))
+		return -EINVAL;
+
+	vma->vm_flags |= VM_DONTEXPAND;
+	vma->vm_ops = &watch_queue_vm_ops;
+
+	vma_interval_tree_insert(vma, &wqueue->mapping.i_mmap);
+	return 0;
+}
+
+/*
+ * Allocate the required number of pages.
+ */
+static long watch_queue_set_size(struct watch_queue *wqueue, unsigned long nr_pages)
+{
+	struct watch_queue_buffer *buf;
+	u32 len;
+	int i;
+
+	if (wqueue->buffer)
+		return -EBUSY;
+
+	if (nr_pages == 0 ||
+	    nr_pages > 16 || /* TODO: choose a better hard limit */
+	    !is_power_of_2(nr_pages))
+		return -EINVAL;
+
+	wqueue->pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
+	if (!wqueue->pages)
+		goto err;
+
+	for (i = 0; i < nr_pages; i++) {
+		wqueue->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!wqueue->pages[i])
+			goto err_some_pages;
+		wqueue->pages[i]->mapping = &wqueue->mapping;
+		SetPageUptodate(wqueue->pages[i]);
+	}
+
+	buf = vmap(wqueue->pages, nr_pages, VM_MAP, PAGE_SHARED);
+	if (!buf)
+		goto err_some_pages;
+
+	wqueue->buffer = buf;
+	wqueue->nr_pages = nr_pages;
+	wqueue->size = ((nr_pages * PAGE_SIZE) / sizeof(struct watch_notification));
+
+	/* The first four slots in the buffer contain metadata about the ring,
+	 * including the head and tail indices and mask.
+	 */
+	len = sizeof(buf->meta) / sizeof(buf->slots[0]);
+	buf->meta.watch.info	= len << WATCH_LENGTH_SHIFT;
+	buf->meta.watch.type	= WATCH_TYPE_META;
+	buf->meta.watch.subtype	= WATCH_META_SKIP_NOTIFICATION;
+	buf->meta.mask		= wqueue->size - 1;
+	buf->meta.head		= len;
+	buf->meta.tail		= len;
+	return 0;
+
+err_some_pages:
+	for (i--; i >= 0; i--) {
+		ClearPageUptodate(wqueue->pages[i]);
+		wqueue->pages[i]->mapping = NULL;
+		put_page(wqueue->pages[i]);
+	}
+
+	kfree(wqueue->pages);
+	wqueue->pages = NULL;
+err:
+	return -ENOMEM;
+}
+
+/*
+ * Set the filter on a watch queue.
+ */
+static long watch_queue_set_filter(struct inode *inode,
+				   struct watch_queue *wqueue,
+				   struct watch_notification_filter __user *_filter)
+{
+	struct watch_notification_type_filter *tf;
+	struct watch_notification_filter filter;
+	struct watch_type_filter *q;
+	struct watch_filter *wfilter;
+	int ret, nr_filter = 0, i;
+
+	if (!_filter) {
+		/* Remove the old filter */
+		wfilter = NULL;
+		goto set;
+	}
+
+	/* Grab the user's filter specification */
+	if (copy_from_user(&filter, _filter, sizeof(filter)) != 0)
+		return -EFAULT;
+	if (filter.nr_filters == 0 ||
+	    filter.nr_filters > 16 ||
+	    filter.__reserved != 0)
+		return -EINVAL;
+
+	tf = memdup_user(_filter->filters, filter.nr_filters * sizeof(*tf));
+	if (IS_ERR(tf))
+		return PTR_ERR(tf);
+
+	ret = -EINVAL;
+	for (i = 0; i < filter.nr_filters; i++) {
+		if ((tf[i].info_filter & ~tf[i].info_mask) ||
+		    tf[i].info_mask & WATCH_INFO_LENGTH)
+			goto err_filter;
+		/* Ignore any unknown types */
+		if (tf[i].type >= sizeof(wfilter->type_filter) * 8)
+			continue;
+		nr_filter++;
+	}
+
+	/* Now we need to build the internal filter from only the relevant
+	 * user-specified filters.
+	 */
+	ret = -ENOMEM;
+	wfilter = kzalloc(struct_size(wfilter, filters, nr_filter), GFP_KERNEL);
+	if (!wfilter)
+		goto err_filter;
+	wfilter->nr_filters = nr_filter;
+
+	q = wfilter->filters;
+	for (i = 0; i < filter.nr_filters; i++) {
+		if (tf[i].type >= sizeof(wfilter->type_filter) * BITS_PER_LONG)
+			continue;
+
+		q->type			= tf[i].type;
+		q->info_filter		= tf[i].info_filter;
+		q->info_mask		= tf[i].info_mask;
+		q->subtype_filter[0]	= tf[i].subtype_filter[0];
+		__set_bit(q->type, wfilter->type_filter);
+		q++;
+	}
+
+	kfree(tf);
+set:
+	inode_lock(inode);
+	rcu_swap_protected(wqueue->filter, wfilter,
+			   lockdep_is_held(&inode->i_rwsem));
+	inode_unlock(inode);
+	if (wfilter)
+		kfree_rcu(wfilter, rcu);
+	return 0;
+
+err_filter:
+	kfree(tf);
+	return ret;
+}
+
+/*
+ * Set parameters.
+ */
+static long watch_queue_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct watch_queue *wqueue = file->private_data;
+	struct inode *inode = file_inode(file);
+	long ret;
+
+	switch (cmd) {
+	case IOC_WATCH_QUEUE_SET_SIZE:
+		inode_lock(inode);
+		ret = watch_queue_set_size(wqueue, arg);
+		inode_unlock(inode);
+		return ret;
+
+	case IOC_WATCH_QUEUE_SET_FILTER:
+		ret = watch_queue_set_filter(
+			inode, wqueue,
+			(struct watch_notification_filter __user *)arg);
+		return ret;
+
+	default:
+		return -ENOTTY;
+	}
+}
+
+/*
+ * Open the file.
+ */
+static int watch_queue_open(struct inode *inode, struct file *file)
+{
+	struct watch_queue *wqueue;
+
+	wqueue = kzalloc(sizeof(*wqueue), GFP_KERNEL);
+	if (!wqueue)
+		return -ENOMEM;
+
+	wqueue->mapping.a_ops = &watch_queue_aops;
+	wqueue->mapping.i_mmap = RB_ROOT_CACHED;
+	init_rwsem(&wqueue->mapping.i_mmap_rwsem);
+	spin_lock_init(&wqueue->mapping.private_lock);
+
+	kref_init(&wqueue->usage);
+	spin_lock_init(&wqueue->lock);
+	init_waitqueue_head(&wqueue->waiters);
+	wqueue->cred = get_cred(file->f_cred);
+
+	file->private_data = wqueue;
+	return 0;
+}
+
+static void __put_watch_queue(struct kref *kref)
+{
+	struct watch_queue *wqueue =
+		container_of(kref, struct watch_queue, usage);
+
+	kfree_rcu(wqueue, rcu);
+}
+
+/**
+ * put_watch_queue - Dispose of a ref on a watchqueue.
+ * @wqueue: The watch queue to unref.
+ */
+void put_watch_queue(struct watch_queue *wqueue)
+{
+	kref_put(&wqueue->usage, __put_watch_queue);
+}
+EXPORT_SYMBOL(put_watch_queue);
+
+static void free_watch(struct rcu_head *rcu)
+{
+	struct watch *watch = container_of(rcu, struct watch, rcu);
+
+	put_watch_queue(rcu_access_pointer(watch->queue));
+}
+
+static void __put_watch(struct kref *kref)
+{
+	struct watch *watch = container_of(kref, struct watch, usage);
+
+	call_rcu(&watch->rcu, free_watch);
+}
+
+/*
+ * Discard a watch.
+ */
+static void put_watch(struct watch *watch)
+{
+	kref_put(&watch->usage, __put_watch);
+}
+
+/**
+ * init_watch_queue - Initialise a watch
+ * @watch: The watch to initialise.
+ * @wqueue: The queue to assign.
+ *
+ * Initialise a watch and set the watch queue.
+ */
+void init_watch(struct watch *watch, struct watch_queue *wqueue)
+{
+	kref_init(&watch->usage);
+	INIT_HLIST_NODE(&watch->list_node);
+	INIT_HLIST_NODE(&watch->queue_node);
+	rcu_assign_pointer(watch->queue, wqueue);
+}
+
+/**
+ * add_watch_to_object - Add a watch on an object to a watch list
+ * @watch: The watch to add
+ * @wlist: The watch list to add to
+ *
+ * @watch->queue must have been set to point to the queue to post notifications
+ * to and the watch list of the object to be watched.
+ *
+ * The caller must pin the queue and the list both and must hold the list
+ * locked against racing watch additions/removals.
+ */
+int add_watch_to_object(struct watch *watch, struct watch_list *wlist)
+{
+	struct watch_queue *wqueue = rcu_access_pointer(watch->queue);
+	struct watch *w;
+
+	hlist_for_each_entry(w, &wlist->watchers, list_node) {
+		if (watch->id == w->id)
+			return -EBUSY;
+	}
+
+	rcu_assign_pointer(watch->watch_list, wlist);
+
+	spin_lock_bh(&wqueue->lock);
+	kref_get(&wqueue->usage);
+	hlist_add_head(&watch->queue_node, &wqueue->watches);
+	spin_unlock_bh(&wqueue->lock);
+
+	hlist_add_head(&watch->list_node, &wlist->watchers);
+	return 0;
+}
+EXPORT_SYMBOL(add_watch_to_object);
+
+/**
+ * remove_watch_from_object - Remove a watch or all watches from an object.
+ * @wlist: The watch list to remove from
+ * @wq: The watch queue of interest (ignored if @all is true)
+ * @id: The ID of the watch to remove (ignored if @all is true)
+ * @all: True to remove all objects
+ *
+ * Remove a specific watch or all watches from an object.  A notification is
+ * sent to the watcher to tell them that this happened.
+ */
+int remove_watch_from_object(struct watch_list *wlist, struct watch_queue *wq,
+			     u64 id, bool all)
+{
+	struct watch_notification n;
+	struct watch_queue *wqueue;
+	struct watch *watch;
+	int ret = -EBADSLT;
+
+	rcu_read_lock();
+
+again:
+	spin_lock(&wlist->lock);
+	hlist_for_each_entry(watch, &wlist->watchers, list_node) {
+		if (all ||
+		    (watch->id == id && rcu_access_pointer(watch->queue) == wq))
+			goto found;
+	}
+	spin_unlock(&wlist->lock);
+	goto out;
+
+found:
+	ret = 0;
+	hlist_del_init_rcu(&watch->list_node);
+	rcu_assign_pointer(watch->watch_list, NULL);
+	spin_unlock(&wlist->lock);
+
+	/* We now own the reference on watch that used to belong to wlist. */
+
+	n.type = WATCH_TYPE_META;
+	n.subtype = WATCH_META_REMOVAL_NOTIFICATION;
+	n.info = watch->info_id | sizeof(n);
+
+	wqueue = rcu_dereference(watch->queue);
+
+	/* We don't need the watch list lock for the next bit as RCU is
+	 * protecting *wqueue from deallocation.
+	 */
+	if (wqueue) {
+		post_one_notification(wqueue, &n, wq ? wq->cred : NULL);
+
+		spin_lock_bh(&wqueue->lock);
+
+		if (!hlist_unhashed(&watch->queue_node)) {
+			hlist_del_init_rcu(&watch->queue_node);
+			put_watch(watch);
+		}
+
+		spin_unlock_bh(&wqueue->lock);
+	}
+
+	if (wlist->release_watch) {
+		void (*release_watch)(struct watch *);
+
+		release_watch = wlist->release_watch;
+		rcu_read_unlock();
+		(*release_watch)(watch);
+		rcu_read_lock();
+	}
+	put_watch(watch);
+
+	if (all && !hlist_empty(&wlist->watchers))
+		goto again;
+out:
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL(remove_watch_from_object);
+
+/*
+ * Remove all the watches that are contributory to a queue.  This has the
+ * potential to race with removal of the watches by the destruction of the
+ * objects being watched or with the distribution of notifications.
+ */
+static void watch_queue_clear(struct watch_queue *wqueue)
+{
+	struct watch_list *wlist;
+	struct watch *watch;
+	bool release;
+
+	rcu_read_lock();
+	spin_lock_bh(&wqueue->lock);
+
+	/* Prevent new additions and prevent notifications from happening */
+	wqueue->defunct = true;
+
+	while (!hlist_empty(&wqueue->watches)) {
+		watch = hlist_entry(wqueue->watches.first, struct watch, queue_node);
+		hlist_del_init_rcu(&watch->queue_node);
+		/* We now own a ref on the watch. */
+		spin_unlock_bh(&wqueue->lock);
+
+		/* We can't do the next bit under the queue lock as we need to
+		 * get the list lock - which would cause a deadlock if someone
+		 * was removing from the opposite direction at the same time or
+		 * posting a notification.
+		 */
+		wlist = rcu_dereference(watch->watch_list);
+		if (wlist) {
+			void (*release_watch)(struct watch *);
+
+			spin_lock(&wlist->lock);
+
+			release = !hlist_unhashed(&watch->list_node);
+			if (release) {
+				hlist_del_init_rcu(&watch->list_node);
+				rcu_assign_pointer(watch->watch_list, NULL);
+
+				/* We now own a second ref on the watch. */
+			}
+
+			release_watch = wlist->release_watch;
+			spin_unlock(&wlist->lock);
+
+			if (release) {
+				if (release_watch) {
+					rcu_read_unlock();
+					/* This might need to call dput(), so
+					 * we have to drop all the locks.
+					 */
+					(*release_watch)(watch);
+					rcu_read_lock();
+				}
+				put_watch(watch);
+			}
+		}
+
+		put_watch(watch);
+		spin_lock_bh(&wqueue->lock);
+	}
+
+	spin_unlock_bh(&wqueue->lock);
+	rcu_read_unlock();
+}
+
+/*
+ * Release the file.
+ */
+static int watch_queue_release(struct inode *inode, struct file *file)
+{
+	struct watch_filter *wfilter;
+	struct watch_queue *wqueue = file->private_data;
+	int i, pgref;
+
+	watch_queue_clear(wqueue);
+
+	if (wqueue->pages && wqueue->pages[0])
+		WARN_ON(page_ref_count(wqueue->pages[0]) != 1);
+
+	if (wqueue->buffer)
+		vfree(wqueue->buffer);
+	for (i = 0; i < wqueue->nr_pages; i++) {
+		ClearPageUptodate(wqueue->pages[i]);
+		wqueue->pages[i]->mapping = NULL;
+		pgref = page_ref_count(wqueue->pages[i]);
+		WARN(pgref != 1,
+		     "FREE PAGE[%d] refcount %d\n", i, page_ref_count(wqueue->pages[i]));
+		__free_page(wqueue->pages[i]);
+	}
+
+	wfilter = rcu_dereference_protected(wqueue->filter, true);
+	if (wfilter)
+		kfree_rcu(wfilter, rcu);
+	kfree(wqueue->pages);
+	put_cred(wqueue->cred);
+	put_watch_queue(wqueue);
+	return 0;
+}
+
+#ifdef DEBUG_WITH_WRITE
+static ssize_t watch_queue_write(struct file *file,
+				 const char __user *_buf, size_t len, loff_t *pos)
+{
+	struct watch_notification *n;
+	struct watch_queue *wqueue = file->private_data;
+	ssize_t ret;
+
+	if (!wqueue->buffer)
+		return -ENOBUFS;
+
+	if (len & ~WATCH_INFO_LENGTH || len == 0 || !_buf)
+		return -EINVAL;
+
+	n = memdup_user(_buf, len);
+	if (IS_ERR(n))
+		return PTR_ERR(n);
+
+	ret = -EINVAL;
+	if ((n->info & WATCH_INFO_LENGTH) != len)
+		goto error;
+	n->info &= (WATCH_INFO_LENGTH | WATCH_INFO_TYPE_FLAGS | WATCH_INFO_ID);
+
+	if (post_one_notification(wqueue, n, file->f_cred))
+		wqueue->debug = 0;
+	else
+		wqueue->debug++;
+	ret = len;
+	if (wqueue->debug > 20)
+		ret = -EIO;
+
+error:
+	kfree(n);
+	return ret;
+}
+#endif
+
+static const struct file_operations watch_queue_fops = {
+	.owner		= THIS_MODULE,
+	.open		= watch_queue_open,
+	.release	= watch_queue_release,
+	.unlocked_ioctl	= watch_queue_ioctl,
+	.poll		= watch_queue_poll,
+	.mmap		= watch_queue_mmap,
+#ifdef DEBUG_WITH_WRITE
+	.write		= watch_queue_write,
+#endif
+	.llseek		= no_llseek,
+};
+
+/**
+ * get_watch_queue - Get a watch queue from its file descriptor.
+ * @fd: The fd to query.
+ */
+struct watch_queue *get_watch_queue(int fd)
+{
+	struct watch_queue *wqueue = ERR_PTR(-EBADF);
+	struct fd f;
+
+	f = fdget(fd);
+	if (f.file) {
+		wqueue = ERR_PTR(-EINVAL);
+		if (f.file->f_op == &watch_queue_fops) {
+			wqueue = f.file->private_data;
+			kref_get(&wqueue->usage);
+		}
+		fdput(f);
+	}
+
+	return wqueue;
+}
+EXPORT_SYMBOL(get_watch_queue);
+
+static struct miscdevice watch_queue_dev = {
+	.minor	= MISC_DYNAMIC_MINOR,
+	.name	= "watch_queue",
+	.fops	= &watch_queue_fops,
+	.mode	= 0666,
+};
+builtin_misc_device(watch_queue_dev);