Message-ID: <adaeis53d2m.fsf_-_@cisco.com>
Date:	Fri, 24 Jul 2009 15:56:17 -0700
From:	Roland Dreier <rdreier@...co.com>
To:	Andrew Morton <akpm@...ux-foundation.org>
Cc:	linux-kernel@...r.kernel.org, jsquyres@...co.com,
	Steven Rostedt <rostedt@...dmis.org>
Subject: [PATCH v2] ummunotify: Userspace support for MMU notifications

As discussed in <http://article.gmane.org/gmane.linux.drivers.openib/61925>
and follow-up messages, libraries using RDMA would like to track
precisely when application code changes memory mapping via free(),
munmap(), etc.  Current pure-userspace solutions using malloc hooks
and other tricks are not robust, and the feeling among experts is that
the issue is unfixable without kernel help.

We solve this not by implementing the full API proposed in the email
linked above but rather with a simpler and more generic interface,
which may be useful in other contexts.  Specifically, we implement a
new character device driver, ummunotify, that creates a /dev/ummunotify
node.  A userspace process can open this node read-only and use the fd
as follows:

 1. ioctl() to register/unregister an address range to watch in the
    kernel (cf struct ummunotify_register_ioctl in <linux/ummunotify.h>).

 2. read() to retrieve events generated when a mapping in a watched
    address range is invalidated (cf struct ummunotify_event in
    <linux/ummunotify.h>).  select()/poll()/epoll() and SIGIO are
    handled for this IO.

 3. mmap() one page at offset 0 to map a kernel page that contains a
    generation counter that is incremented each time an event is
    generated.  This allows userspace to have a fast path that checks
    that no events have occurred without a system call.

Thanks to Jason Gunthorpe <jgunthorpe@...idianresearch.com> for
suggestions on the interface design.  Also thanks to Jeff Squyres
<jsquyres@...co.com> for prototyping support for this in Open MPI, which
helped find several bugs during development.

Signed-off-by: Roland Dreier <rolandd@...co.com>
---
Hi Andrew,

since last time I've
 - agreed (I think) with Steve that this doesn't really fit in with
   (current) ftrace code.
 - s/ummunot/ummunotify/
 - documented the main datastructures
 - clarified a few other names (inval -> invalidate, dirty -> invalid)
 - used min_t to handle taking min of size_t and PAGE_SIZE
which I think covers everything you mentioned last time.

What else do you think needs to happen to move this upstream?

Thanks,
  Roland


 drivers/char/Kconfig       |   12 +
 drivers/char/Makefile      |    1 +
 drivers/char/ummunotify.c  |  554 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/ummunotify.h |  121 ++++++++++
 4 files changed, 688 insertions(+), 0 deletions(-)
 create mode 100644 drivers/char/ummunotify.c
 create mode 100644 include/linux/ummunotify.h

diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index 6a06913..b8368e2 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -1108,6 +1108,18 @@ config DEVPORT
 	depends on ISA || PCI
 	default y
 
+config UMMUNOTIFY
+       tristate "Userspace MMU notifications"
+       select MMU_NOTIFIER
+       help
+         The ummunotify (userspace MMU notification) driver creates a
+         character device that can be used by userspace libraries to
+         get notifications when an application's memory mapping
+         changed.  This is used, for example, by RDMA libraries to
+         improve the reliability of memory registration caching, since
+         the kernel's MMU notifications can be used to know precisely
+         when to shoot down a cached registration.
+
 source "drivers/s390/char/Kconfig"
 
 endmenu
diff --git a/drivers/char/Makefile b/drivers/char/Makefile
index 66f779a..3547020 100644
--- a/drivers/char/Makefile
+++ b/drivers/char/Makefile
@@ -97,6 +97,7 @@ obj-$(CONFIG_NSC_GPIO)		+= nsc_gpio.o
 obj-$(CONFIG_CS5535_GPIO)	+= cs5535_gpio.o
 obj-$(CONFIG_GPIO_TB0219)	+= tb0219.o
 obj-$(CONFIG_TELCLOCK)		+= tlclk.o
+obj-$(CONFIG_UMMUNOTIFY)	+= ummunotify.o
 
 obj-$(CONFIG_MWAVE)		+= mwave/
 obj-$(CONFIG_AGP)		+= agp/
diff --git a/drivers/char/ummunotify.c b/drivers/char/ummunotify.c
new file mode 100644
index 0000000..1150623
--- /dev/null
+++ b/drivers/char/ummunotify.c
@@ -0,0 +1,554 @@
+/*
+ * Copyright (c) 2009 Cisco Systems.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/mmu_notifier.h>
+#include <linux/module.h>
+#include <linux/poll.h>
+#include <linux/rbtree.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/uaccess.h>
+#include <linux/ummunotify.h>
+
+#include <asm/cacheflush.h>
+
+MODULE_AUTHOR("Roland Dreier");
+MODULE_DESCRIPTION("Userspace MMU notifiers");
+MODULE_LICENSE("GPL v2");
+
+/*
+ * Information about an address range userspace has asked us to watch.
+ *
+ * user_cookie: Opaque cookie given to us when userspace registers the
+ *   address range.
+ *
+ * start, end: Address range; start is inclusive, end is exclusive.
+ *
+ * hint_start, hint_end: If a single MMU notification event
+ *   invalidates the address range, we hold the actual range of
+ *   addresses that were invalidated (and set UMMUNOTIFY_FLAG_HINT).
+ *   If another event hits this range before userspace reads the
+ *   event, we give up and don't try to keep track of which subsets
+ *   got invalidated.
+ *
+ * flags: Holds the INVALID flag for ranges that are on the invalid
+ *   list and/or the HINT flag for ranges where the hint range holds
+ *   good information.
+ *
+ * node: Used to put the range into an rbtree we use to be able to
+ *   scan address ranges in order.
+ *
+ * list: Used to put the range on the invalid list when an MMU
+ *   notification event hits the range.
+ */
+enum {
+	UMMUNOTIFY_FLAG_INVALID	= 1,
+	UMMUNOTIFY_FLAG_HINT	= 2,
+};
+
+struct ummunotify_reg {
+	u64			user_cookie;
+	unsigned long		start;
+	unsigned long		end;
+	unsigned long		hint_start;
+	unsigned long		hint_end;
+	unsigned long		flags;
+	struct rb_node		node;
+	struct list_head	list;
+};
+
+/*
+ * Context attached to each file that userspace opens.
+ *
+ * mmu_notifier: MMU notifier registered for this context.
+ *
+ * mm: mm_struct for process that created the context; we use this to
+ *   hold a reference to the mm to make sure it doesn't go away until
+ *   we're done with it.
+ *
+ * reg_tree: RB tree of address ranges being watched, sorted by start
+ *   address.
+ *
+ * invalid_list: List of address ranges that have been invalidated by
+ *   MMU notification events; as userspace reads events, the address
+ *   range corresponding to the event is removed from the list.
+ *
+ * counter: Page that can be mapped read-only by userspace, which
+ *   holds a generation count that is incremented each time an event
+ *   occurs.
+ *
+ * lock: Spinlock used to protect all context.
+ *
+ * read_wait: Wait queue used to wait for data to become available in
+ *   blocking read()s.
+ *
+ * async_queue: Used to implement fasync().
+ *
+ * need_empty: Set when userspace reads an invalidation event, so that
+ *   read() knows it must generate an "empty" event when userspace
+ *   drains the invalid_list.
+ *
+ * used: Set after userspace does anything with the file, so that the
+ *   "exchange flags" ioctl() knows it's too late to change anything.
+ */
+struct ummunotify_file {
+	struct mmu_notifier	mmu_notifier;
+	struct mm_struct       *mm;
+	struct rb_root		reg_tree;
+	struct list_head	invalid_list;
+	u64		       *counter;
+	spinlock_t		lock;
+	wait_queue_head_t	read_wait;
+	struct fasync_struct   *async_queue;
+	int			need_empty;
+	int			used;
+};
+
+static void ummunotify_handle_notify(struct mmu_notifier *mn,
+				     unsigned long start, unsigned long end)
+{
+	struct ummunotify_file *priv =
+		container_of(mn, struct ummunotify_file, mmu_notifier);
+	struct rb_node *n;
+	struct ummunotify_reg *reg;
+	unsigned long flags;
+	int hit = 0;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	for (n = rb_first(&priv->reg_tree); n; n = rb_next(n)) {
+		reg = rb_entry(n, struct ummunotify_reg, node);
+
+		if (reg->start >= end)
+			break;
+
+		/*
+		 * Ranges overlap if they're not disjoint; and they're
+		 * disjoint if the end of one is before the start of
+		 * the other one.
+		 */
+		if (!(reg->end <= start || end <= reg->start)) {
+			hit = 1;
+
+			if (!test_and_set_bit(UMMUNOTIFY_FLAG_INVALID, &reg->flags))
+				list_add_tail(&reg->list, &priv->invalid_list);
+
+			if (test_bit(UMMUNOTIFY_FLAG_HINT, &reg->flags)) {
+				clear_bit(UMMUNOTIFY_FLAG_HINT, &reg->flags);
+			} else {
+				set_bit(UMMUNOTIFY_FLAG_HINT, &reg->flags);
+				reg->hint_start = start;
+				reg->hint_end   = end;
+			}
+		}
+	}
+
+	if (hit) {
+		++(*priv->counter);
+		flush_dcache_page(virt_to_page(priv->counter));
+		wake_up_interruptible(&priv->read_wait);
+		kill_fasync(&priv->async_queue, SIGIO, POLL_IN);
+	}
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static void ummunotify_invalidate_page(struct mmu_notifier *mn,
+				       struct mm_struct *mm,
+				       unsigned long addr)
+{
+	ummunotify_handle_notify(mn, addr, addr + PAGE_SIZE);
+}
+
+static void ummunotify_invalidate_range_start(struct mmu_notifier *mn,
+					      struct mm_struct *mm,
+					      unsigned long start,
+					      unsigned long end)
+{
+	ummunotify_handle_notify(mn, start, end);
+}
+
+static const struct mmu_notifier_ops ummunotify_mmu_notifier_ops = {
+	.invalidate_page	= ummunotify_invalidate_page,
+	.invalidate_range_start	= ummunotify_invalidate_range_start,
+};
+
+static int ummunotify_open(struct inode *inode, struct file *filp)
+{
+	struct ummunotify_file *priv;
+	int ret;
+
+	if (filp->f_mode & FMODE_WRITE)
+		return -EINVAL;
+
+	priv = kmalloc(sizeof *priv, GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->counter = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!priv->counter) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	priv->reg_tree = RB_ROOT;
+	INIT_LIST_HEAD(&priv->invalid_list);
+	spin_lock_init(&priv->lock);
+	init_waitqueue_head(&priv->read_wait);
+	priv->async_queue = NULL;
+	priv->need_empty  = 0;
+	priv->used	  = 0;
+
+	priv->mmu_notifier.ops = &ummunotify_mmu_notifier_ops;
+	/*
+	 * Register notifier last, since notifications can occur as
+	 * soon as we register....
+	 */
+	ret = mmu_notifier_register(&priv->mmu_notifier, current->mm);
+	if (ret)
+		goto err_page;
+
+	priv->mm = current->mm;
+	atomic_inc(&priv->mm->mm_count);
+
+	filp->private_data = priv;
+
+	return 0;
+
+err_page:
+	free_page((unsigned long) priv->counter);
+
+err:
+	kfree(priv);
+	return ret;
+}
+
+static int ummunotify_close(struct inode *inode, struct file *filp)
+{
+	struct ummunotify_file *priv = filp->private_data;
+	struct rb_node *n;
+	struct ummunotify_reg *reg;
+
+	mmu_notifier_unregister(&priv->mmu_notifier, priv->mm);
+	mmdrop(priv->mm);
+	free_page((unsigned long) priv->counter);
+
+	for (n = rb_first(&priv->reg_tree); n; n = rb_next(n)) {
+		reg = rb_entry(n, struct ummunotify_reg, node);
+		kfree(reg);
+	}
+
+	kfree(priv);
+
+	return 0;
+}
+
+static bool ummunotify_readable(struct ummunotify_file *priv)
+{
+	return priv->need_empty || !list_empty(&priv->invalid_list);
+}
+
+static ssize_t ummunotify_read(struct file *filp, char __user *buf,
+			       size_t count, loff_t *pos)
+{
+	struct ummunotify_file *priv = filp->private_data;
+	struct ummunotify_reg *reg;
+	ssize_t ret;
+	struct ummunotify_event *events;
+	int max;
+	int n;
+
+	priv->used = 1;
+
+	events = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!events) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	spin_lock_irq(&priv->lock);
+
+	while (!ummunotify_readable(priv)) {
+		spin_unlock_irq(&priv->lock);
+
+		if (filp->f_flags & O_NONBLOCK) {
+			ret = -EAGAIN;
+			goto out;
+		}
+
+		if (wait_event_interruptible(priv->read_wait,
+					     ummunotify_readable(priv))) {
+			ret = -ERESTARTSYS;
+			goto out;
+		}
+
+		spin_lock_irq(&priv->lock);
+	}
+
+	max = min_t(size_t, PAGE_SIZE, count) / sizeof *events;
+
+	for (n = 0; n < max; ++n) {
+		if (list_empty(&priv->invalid_list)) {
+			events[n].type		      = UMMUNOTIFY_EVENT_TYPE_LAST;
+			events[n].user_cookie_counter = *priv->counter;
+			++n;
+			priv->need_empty = 0;
+			break;
+		}
+
+		reg = list_first_entry(&priv->invalid_list, struct ummunotify_reg,
+				       list);
+
+		events[n].type = UMMUNOTIFY_EVENT_TYPE_INVAL;
+		if (test_bit(UMMUNOTIFY_FLAG_HINT, &reg->flags)) {
+			events[n].flags		= UMMUNOTIFY_EVENT_FLAG_HINT;
+			events[n].hint_start	= max(reg->start, reg->hint_start);
+			events[n].hint_end	= min(reg->end, reg->hint_end);
+		} else {
+			events[n].hint_start	= reg->start;
+			events[n].hint_end	= reg->end;
+		}
+		events[n].user_cookie_counter = reg->user_cookie;
+
+		list_del(&reg->list);
+		reg->flags = 0;
+		priv->need_empty = 1;
+	}
+
+	spin_unlock_irq(&priv->lock);
+
+	if (copy_to_user(buf, events, n * sizeof *events))
+		ret = -EFAULT;
+	else
+		ret = n * sizeof *events;
+
+out:
+	free_page((unsigned long) events);
+	return ret;
+}
+
+static unsigned int ummunotify_poll(struct file *filp, struct poll_table_struct *wait)
+{
+	struct ummunotify_file *priv = filp->private_data;
+
+	poll_wait(filp, &priv->read_wait, wait);
+
+	return ummunotify_readable(priv) ? (POLLIN | POLLRDNORM) : 0;
+}
+
+static long ummunotify_exchange_features(struct ummunotify_file *priv,
+					 __u32 __user *arg)
+{
+	u32 feature_mask;
+
+	if (priv->used)
+		return -EINVAL;
+
+	priv->used = 1;
+
+	if (get_user(feature_mask, arg))
+		return -EFAULT;
+
+	/* No extensions defined at present. */
+	feature_mask = 0;
+
+	if (put_user(feature_mask, arg))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long ummunotify_register_region(struct ummunotify_file *priv,
+				       struct ummunotify_register_ioctl __user *arg)
+{
+	struct ummunotify_register_ioctl parm;
+	struct ummunotify_reg *reg, *treg;
+	struct rb_node **n = &priv->reg_tree.rb_node;
+	struct rb_node *pn;
+	int ret = 0;
+
+	if (copy_from_user(&parm, arg, sizeof parm))
+		return -EFAULT;
+
+	priv->used = 1;
+
+	reg = kmalloc(sizeof *reg, GFP_KERNEL);
+	if (!reg)
+		return -ENOMEM;
+
+	reg->user_cookie	= parm.user_cookie;
+	reg->start		= parm.start;
+	reg->end		= parm.end;
+	reg->flags		= 0;
+
+	spin_lock_irq(&priv->lock);
+
+	for (pn = rb_first(&priv->reg_tree); pn; pn = rb_next(pn)) {
+		treg = rb_entry(pn, struct ummunotify_reg, node);
+
+		if (treg->user_cookie == parm.user_cookie) {
+			kfree(reg);
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	pn = NULL;
+	while (*n) {
+		pn = *n;
+		treg = rb_entry(pn, struct ummunotify_reg, node);
+
+		if (reg->start <= treg->start)
+			n = &pn->rb_left;
+		else
+			n = &pn->rb_right;
+	}
+
+	rb_link_node(&reg->node, pn, n);
+	rb_insert_color(&reg->node, &priv->reg_tree);
+
+out:
+	spin_unlock_irq(&priv->lock);
+
+	return ret;
+}
+
+static long ummunotify_unregister_region(struct ummunotify_file *priv,
+					 __u64 __user *arg)
+{
+	u64 user_cookie;
+	struct rb_node *n;
+	struct ummunotify_reg *reg;
+	int ret = -EINVAL;
+
+	if (get_user(user_cookie, arg))
+		return -EFAULT;
+
+	spin_lock_irq(&priv->lock);
+
+	for (n = rb_first(&priv->reg_tree); n; n = rb_next(n)) {
+		reg = rb_entry(n, struct ummunotify_reg, node);
+
+		if (reg->user_cookie == user_cookie) {
+			rb_erase(n, &priv->reg_tree);
+			if (test_bit(UMMUNOTIFY_FLAG_INVALID, &reg->flags))
+				list_del(&reg->list);
+			kfree(reg);
+			ret = 0;
+			break;
+		}
+	}
+
+	spin_unlock_irq(&priv->lock);
+
+	return ret;
+}
+
+static long ummunotify_ioctl(struct file *filp, unsigned int cmd,
+			     unsigned long arg)
+{
+	struct ummunotify_file *priv = filp->private_data;
+	void __user *argp = (void __user *) arg;
+
+	switch (cmd) {
+	case UMMUNOTIFY_EXCHANGE_FEATURES:
+		return ummunotify_exchange_features(priv, argp);
+	case UMMUNOTIFY_REGISTER_REGION:
+		return ummunotify_register_region(priv, argp);
+	case UMMUNOTIFY_UNREGISTER_REGION:
+		return ummunotify_unregister_region(priv, argp);
+	default:
+		return -ENOIOCTLCMD;
+	}
+}
+
+static int ummunotify_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct ummunotify_file *priv = vma->vm_private_data;
+
+	if (vmf->pgoff != 0)
+		return VM_FAULT_SIGBUS;
+
+	vmf->page = virt_to_page(priv->counter);
+	get_page(vmf->page);
+
+	return 0;
+
+}
+
+static struct vm_operations_struct ummunotify_vm_ops = {
+	.fault		= ummunotify_fault,
+};
+
+static int ummunotify_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct ummunotify_file *priv = filp->private_data;
+
+	if (vma->vm_end - vma->vm_start != PAGE_SIZE ||
+	    vma->vm_pgoff != 0)
+		return -EINVAL;
+
+	vma->vm_ops		= &ummunotify_vm_ops;
+	vma->vm_private_data	= priv;
+
+	return 0;
+}
+
+static int ummunotify_fasync(int fd, struct file *filp, int on)
+{
+	struct ummunotify_file *priv = filp->private_data;
+
+	return fasync_helper(fd, filp, on, &priv->async_queue);
+}
+
+static const struct file_operations ummunotify_fops = {
+	.owner		= THIS_MODULE,
+	.open		= ummunotify_open,
+	.release	= ummunotify_close,
+	.read		= ummunotify_read,
+	.poll		= ummunotify_poll,
+	.unlocked_ioctl	= ummunotify_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ummunotify_ioctl,
+#endif
+	.mmap		= ummunotify_mmap,
+	.fasync		= ummunotify_fasync,
+};
+
+static struct miscdevice ummunotify_misc = {
+	.minor	= MISC_DYNAMIC_MINOR,
+	.name	= "ummunotify",
+	.fops	= &ummunotify_fops,
+};
+
+static int __init ummunotify_init(void)
+{
+	return misc_register(&ummunotify_misc);
+}
+
+static void __exit ummunotify_cleanup(void)
+{
+	misc_deregister(&ummunotify_misc);
+}
+
+module_init(ummunotify_init);
+module_exit(ummunotify_cleanup);
diff --git a/include/linux/ummunotify.h b/include/linux/ummunotify.h
new file mode 100644
index 0000000..9e4620e
--- /dev/null
+++ b/include/linux/ummunotify.h
@@ -0,0 +1,121 @@
+/*
+ * Copyright (c) 2009 Cisco Systems.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _LINUX_UMMUNOTIFY_H
+#define _LINUX_UMMUNOTIFY_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/*
+ * Ummunotify relays MMU notifier events to userspace.  A userspace
+ * process uses it by opening /dev/ummunotify, which returns a file
+ * descriptor.  Interest in address ranges is registered using ioctl()
+ * and MMU notifier events are retrieved using read(), as described in
+ * more detail below.
+ *
+ * Userspace can also mmap() a single read-only page at offset 0 on
+ * this file descriptor.  This page contains (at offest 0) a single
+ * 64-bit generation counter that the kernel increments each time an
+ * MMU notifier event occurs.  Userspace can use this to very quickly
+ * check if there are any events to retrieve without needing to do a
+ * system call.
+ */
+
+/*
+ * struct ummunotify_register_ioctl describes an address range from
+ * start to end (including start but not including end) to be
+ * monitored.  user_cookie is an opaque handle that userspace assigns,
+ * and which is used to unregister.  flags and reserved are currently
+ * unused and should be set to 0 for forward compatibility.
+ */
+struct ummunotify_register_ioctl {
+	__u64	start;		/* in */
+	__u64	end;		/* in */
+	__u64	user_cookie;	/* in */
+	__u32	flags;		/* in */
+	__u32	reserved;	/* in */
+};
+
+#define UMMUNOTIFY_MAGIC		'U'
+
+/*
+ * Forward compatibility: Userspace passes in a 32-bit feature mask
+ * with feature flags set indicating which extensions it wishes to
+ * use.  The kernel will return a feature mask with the bits of
+ * userspace's mask that the kernel implements; from that point on
+ * both userspace and the kernel should behave as described by the
+ * kernel's feature mask.
+ *
+ * If userspace does not perform a UMMUNOTIFY_EXCHANGE_FEATURES ioctl,
+ * then the kernel will use a feature mask of 0.
+ *
+ * No feature flags are currently defined, so the kernel will always
+ * return a feature mask of 0 at present.
+ */
+#define UMMUNOTIFY_EXCHANGE_FEATURES	_IOWR(UMMUNOTIFY_MAGIC, 1, __u32)
+
+/*
+ * Register interest in an address range; userspace should pass in a
+ * struct ummunotify_register_ioctl describing the region.
+ */
+#define UMMUNOTIFY_REGISTER_REGION	_IOW(UMMUNOTIFY_MAGIC, 2, \
+					     struct ummunotify_register_ioctl)
+/*
+ * Unregister interest in an address range; userspace should pass in
+ * the user_cookie value that was used to register the address range.
+ * No events for the address range will be reported once it is
+ * unregistered.
+ */
+#define UMMUNOTIFY_UNREGISTER_REGION	_IOW(UMMUNOTIFY_MAGIC, 3, __u64)
+
+/*
+ * Invalidation events are returned whenever the kernel changes the
+ * mapping for a monitored address.  These events are retrieved by
+ * read() on the ummunotify file descriptor, which will fill the
+ * read() buffer with struct ummunotify_event.
+ *
+ * If type field is INVAL, then user_cookie_counter holds the
+ * user_cookie for the region being reported; if the HINT flag is set
+ * then hint_start/hint_end hold the start and end of the mapping that
+ * was invalidated.  (If HINT is not set, then multiple events
+ * invalidated parts of the registered range and hint_start/hint_end
+ * and set to the start/end of the whole registered range)
+ *
+ * If type is LAST, then the read operation has emptied the list of
+ * invalidated regions, and user_cookie_counter holds the value of the
+ * kernel's generation counter when the empty list occurred.  The
+ * other fields are not filled in for this event.
+ */
+enum {
+	UMMUNOTIFY_EVENT_TYPE_INVAL	= 0,
+	UMMUNOTIFY_EVENT_TYPE_LAST	= 1,
+};
+
+enum {
+	UMMUNOTIFY_EVENT_FLAG_HINT	= 1 << 0,
+};
+
+struct ummunotify_event {
+	__u32	type;
+	__u32	flags;
+	__u64	hint_start;
+	__u64	hint_end;
+	__u64	user_cookie_counter;
+};
+
+#endif /* _LINUX_UMMUNOTIFY_H */
-- 
1.6.3.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists