gntdev.c 21 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867
/******************************************************************************
 * gntdev.c
 *
 * Device for accessing (in user-space) pages that have been granted by other
 * domains.
 *
 * Copyright (c) 2006-2007, D G Murray.
 *           (c) 2009 Gerd Hoffmann <kraxel@redhat.com>
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */

#undef DEBUG

#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/miscdevice.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/mmu_notifier.h>
#include <linux/types.h>
#include <linux/uaccess.h>
#include <linux/sched.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/highmem.h>

#include <xen/xen.h>
#include <xen/grant_table.h>
#include <xen/balloon.h>
#include <xen/gntdev.h>
#include <xen/events.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/page.h>

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Derek G. Murray <Derek.Murray@cl.cam.ac.uk>, "
	      "Gerd Hoffmann <kraxel@redhat.com>");
MODULE_DESCRIPTION("User-space granted page access driver");

static int limit = 1024*1024;
module_param(limit, int, 0644);
MODULE_PARM_DESC(limit, "Maximum number of grants that may be mapped by "
		"the gntdev device");

static atomic_t pages_mapped = ATOMIC_INIT(0);

static int use_ptemod;
#define populate_freeable_maps use_ptemod

struct gntdev_priv {
	/* maps with visible offsets in the file descriptor */
	struct list_head maps;
	/* maps that are not visible; will be freed on munmap.
	 * Only populated if populate_freeable_maps == 1 */
	struct list_head freeable_maps;
	/* lock protects maps and freeable_maps */
	spinlock_t lock;
	struct mm_struct *mm;
	struct mmu_notifier mn;
};

struct unmap_notify {
	int flags;
	/* Address relative to the start of the grant_map */
	int addr;
	int event;
};

struct grant_map {
	struct list_head next;
	struct vm_area_struct *vma;
	int index;
	int count;
	int flags;
	atomic_t users;
	struct unmap_notify notify;
	struct ioctl_gntdev_grant_ref *grants;
	struct gnttab_map_grant_ref   *map_ops;
	struct gnttab_unmap_grant_ref *unmap_ops;
	struct gnttab_map_grant_ref   *kmap_ops;
	struct page **pages;
};

static int unmap_grant_pages(struct grant_map *map, int offset, int pages);

/* ------------------------------------------------------------------ */

static void gntdev_print_maps(struct gntdev_priv *priv,
			      char *text, int text_index)
{
#ifdef DEBUG
	struct grant_map *map;

	pr_debug("%s: maps list (priv %p)\n", __func__, priv);
	list_for_each_entry(map, &priv->maps, next)
		pr_debug("  index %2d, count %2d %s\n",
		       map->index, map->count,
		       map->index == text_index && text ? text : "");
#endif
}

static void gntdev_free_map(struct grant_map *map)
{
	if (map == NULL)
		return;

	if (map->pages)
		free_xenballooned_pages(map->count, map->pages);
	kfree(map->pages);
	kfree(map->grants);
	kfree(map->map_ops);
	kfree(map->unmap_ops);
	kfree(map->kmap_ops);
	kfree(map);
}

static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
{
	struct grant_map *add;
	int i;

	add = kzalloc(sizeof(struct grant_map), GFP_KERNEL);
	if (NULL == add)
		return NULL;

	add->grants    = kcalloc(count, sizeof(add->grants[0]), GFP_KERNEL);
	add->map_ops   = kcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL);
	add->unmap_ops = kcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL);
	add->kmap_ops  = kcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL);
	add->pages     = kcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
	if (NULL == add->grants    ||
	    NULL == add->map_ops   ||
	    NULL == add->unmap_ops ||
	    NULL == add->kmap_ops  ||
	    NULL == add->pages)
		goto err;

	if (alloc_xenballooned_pages(count, add->pages, false /* lowmem */))
		goto err;

	for (i = 0; i < count; i++) {
		add->map_ops[i].handle = -1;
		add->unmap_ops[i].handle = -1;
		add->kmap_ops[i].handle = -1;
	}

	add->index = 0;
	add->count = count;
	atomic_set(&add->users, 1);

	return add;

err:
	gntdev_free_map(add);
	return NULL;
}

static void gntdev_add_map(struct gntdev_priv *priv, struct grant_map *add)
{
	struct grant_map *map;

	list_for_each_entry(map, &priv->maps, next) {
		if (add->index + add->count < map->index) {
			list_add_tail(&add->next, &map->next);
			goto done;
		}
		add->index = map->index + map->count;
	}
	list_add_tail(&add->next, &priv->maps);

done:
	gntdev_print_maps(priv, "[new]", add->index);
}

static struct grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
		int index, int count)
{
	struct grant_map *map;

	list_for_each_entry(map, &priv->maps, next) {
		if (map->index != index)
			continue;
		if (count && map->count != count)
			continue;
		return map;
	}
	return NULL;
}

static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map)
{
	if (!map)
		return;

	if (!atomic_dec_and_test(&map->users))
		return;

	atomic_sub(map->count, &pages_mapped);

	if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) {
		notify_remote_via_evtchn(map->notify.event);
		evtchn_put(map->notify.event);
	}

	if (populate_freeable_maps && priv) {
		spin_lock(&priv->lock);
		list_del(&map->next);
		spin_unlock(&priv->lock);
	}

	if (map->pages && !use_ptemod)
		unmap_grant_pages(map, 0, map->count);
	gntdev_free_map(map);
}

/* ------------------------------------------------------------------ */

static int find_grant_ptes(pte_t *pte, pgtable_t token,
		unsigned long addr, void *data)
{
	struct grant_map *map = data;
	unsigned int pgnr = (addr - map->vma->vm_start) >> PAGE_SHIFT;
	int flags = map->flags | GNTMAP_application_map | GNTMAP_contains_pte;
	u64 pte_maddr;

	BUG_ON(pgnr >= map->count);
	pte_maddr = arbitrary_virt_to_machine(pte).maddr;

	gnttab_set_map_op(&map->map_ops[pgnr], pte_maddr, flags,
			  map->grants[pgnr].ref,
			  map->grants[pgnr].domid);
	gnttab_set_unmap_op(&map->unmap_ops[pgnr], pte_maddr, flags,
			    -1 /* handle */);
	return 0;
}

static int map_grant_pages(struct grant_map *map)
{
	int i, err = 0;

	if (!use_ptemod) {
		/* Note: it could already be mapped */
		if (map->map_ops[0].handle != -1)
			return 0;
		for (i = 0; i < map->count; i++) {
			unsigned long addr = (unsigned long)
				pfn_to_kaddr(page_to_pfn(map->pages[i]));
			gnttab_set_map_op(&map->map_ops[i], addr, map->flags,
				map->grants[i].ref,
				map->grants[i].domid);
			gnttab_set_unmap_op(&map->unmap_ops[i], addr,
				map->flags, -1 /* handle */);
		}
	} else {
		/*
		 * Setup the map_ops corresponding to the pte entries pointing
		 * to the kernel linear addresses of the struct pages.
		 * These ptes are completely different from the user ptes dealt
		 * with find_grant_ptes.
		 */
		for (i = 0; i < map->count; i++) {
			unsigned long address = (unsigned long)
				pfn_to_kaddr(page_to_pfn(map->pages[i]));
			BUG_ON(PageHighMem(map->pages[i]));

			gnttab_set_map_op(&map->kmap_ops[i], address,
				map->flags | GNTMAP_host_map,
				map->grants[i].ref,
				map->grants[i].domid);
		}
	}

	pr_debug("map %d+%d\n", map->index, map->count);
	err = gnttab_map_refs(map->map_ops, use_ptemod ? map->kmap_ops : NULL,
			map->pages, map->count);
	if (err)
		return err;

	for (i = 0; i < map->count; i++) {
		if (map->map_ops[i].status)
			err = -EINVAL;
		else {
			BUG_ON(map->map_ops[i].handle == -1);
			map->unmap_ops[i].handle = map->map_ops[i].handle;
			pr_debug("map handle=%d\n", map->map_ops[i].handle);
		}
	}
	return err;
}

static int __unmap_grant_pages(struct grant_map *map, int offset, int pages)
{
	int i, err = 0;

	if (map->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) {
		int pgno = (map->notify.addr >> PAGE_SHIFT);
		if (pgno >= offset && pgno < offset + pages) {
			/* No need for kmap, pages are in lowmem */
			uint8_t *tmp = pfn_to_kaddr(page_to_pfn(map->pages[pgno]));
			tmp[map->notify.addr & (PAGE_SIZE-1)] = 0;
			map->notify.flags &= ~UNMAP_NOTIFY_CLEAR_BYTE;
		}
	}

	err = gnttab_unmap_refs(map->unmap_ops + offset,
			use_ptemod ? map->kmap_ops + offset : NULL, map->pages + offset,
			pages);
	if (err)
		return err;

	for (i = 0; i < pages; i++) {
		if (map->unmap_ops[offset+i].status)
			err = -EINVAL;
		pr_debug("unmap handle=%d st=%d\n",
			map->unmap_ops[offset+i].handle,
			map->unmap_ops[offset+i].status);
		map->unmap_ops[offset+i].handle = -1;
	}
	return err;
}

static int unmap_grant_pages(struct grant_map *map, int offset, int pages)
{
	int range, err = 0;

	pr_debug("unmap %d+%d [%d+%d]\n", map->index, map->count, offset, pages);

	/* It is possible the requested range will have a "hole" where we
	 * already unmapped some of the grants. Only unmap valid ranges.
	 */
	while (pages && !err) {
		while (pages && map->unmap_ops[offset].handle == -1) {
			offset++;
			pages--;
		}
		range = 0;
		while (range < pages) {
			if (map->unmap_ops[offset+range].handle == -1) {
				range--;
				break;
			}
			range++;
		}
		err = __unmap_grant_pages(map, offset, range);
		offset += range;
		pages -= range;
	}

	return err;
}

/* ------------------------------------------------------------------ */

static void gntdev_vma_open(struct vm_area_struct *vma)
{
	struct grant_map *map = vma->vm_private_data;

	pr_debug("gntdev_vma_open %p\n", vma);
	atomic_inc(&map->users);
}

static void gntdev_vma_close(struct vm_area_struct *vma)
{
	struct grant_map *map = vma->vm_private_data;
	struct file *file = vma->vm_file;
	struct gntdev_priv *priv = file->private_data;

	pr_debug("gntdev_vma_close %p\n", vma);
	if (use_ptemod) {
		/* It is possible that an mmu notifier could be running
		 * concurrently, so take priv->lock to ensure that the vma won't
		 * vanishing during the unmap_grant_pages call, since we will
		 * spin here until that completes. Such a concurrent call will
		 * not do any unmapping, since that has been done prior to
		 * closing the vma, but it may still iterate the unmap_ops list.
		 */
		spin_lock(&priv->lock);
		map->vma = NULL;
		spin_unlock(&priv->lock);
	}
	vma->vm_private_data = NULL;
	gntdev_put_map(priv, map);
}

static struct vm_operations_struct gntdev_vmops = {
	.open = gntdev_vma_open,
	.close = gntdev_vma_close,
};

/* ------------------------------------------------------------------ */

static void unmap_if_in_range(struct grant_map *map,
			      unsigned long start, unsigned long end)
{
	unsigned long mstart, mend;
	int err;

	if (!map->vma)
		return;
	if (map->vma->vm_start >= end)
		return;
	if (map->vma->vm_end <= start)
		return;
	mstart = max(start, map->vma->vm_start);
	mend   = min(end,   map->vma->vm_end);
	pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n",
			map->index, map->count,
			map->vma->vm_start, map->vma->vm_end,
			start, end, mstart, mend);
	err = unmap_grant_pages(map,
				(mstart - map->vma->vm_start) >> PAGE_SHIFT,
				(mend - mstart) >> PAGE_SHIFT);
	WARN_ON(err);
}

static void mn_invl_range_start(struct mmu_notifier *mn,
				struct mm_struct *mm,
				unsigned long start, unsigned long end)
{
	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
	struct grant_map *map;

	spin_lock(&priv->lock);
	list_for_each_entry(map, &priv->maps, next) {
		unmap_if_in_range(map, start, end);
	}
	list_for_each_entry(map, &priv->freeable_maps, next) {
		unmap_if_in_range(map, start, end);
	}
	spin_unlock(&priv->lock);
}

static void mn_invl_page(struct mmu_notifier *mn,
			 struct mm_struct *mm,
			 unsigned long address)
{
	mn_invl_range_start(mn, mm, address, address + PAGE_SIZE);
}

static void mn_release(struct mmu_notifier *mn,
		       struct mm_struct *mm)
{
	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
	struct grant_map *map;
	int err;

	spin_lock(&priv->lock);
	list_for_each_entry(map, &priv->maps, next) {
		if (!map->vma)
			continue;
		pr_debug("map %d+%d (%lx %lx)\n",
				map->index, map->count,
				map->vma->vm_start, map->vma->vm_end);
		err = unmap_grant_pages(map, /* offset */ 0, map->count);
		WARN_ON(err);
	}
	list_for_each_entry(map, &priv->freeable_maps, next) {
		if (!map->vma)
			continue;
		pr_debug("map %d+%d (%lx %lx)\n",
				map->index, map->count,
				map->vma->vm_start, map->vma->vm_end);
		err = unmap_grant_pages(map, /* offset */ 0, map->count);
		WARN_ON(err);
	}
	spin_unlock(&priv->lock);
}

static struct mmu_notifier_ops gntdev_mmu_ops = {
	.release                = mn_release,
	.invalidate_page        = mn_invl_page,
	.invalidate_range_start = mn_invl_range_start,
};

/* ------------------------------------------------------------------ */

static int gntdev_open(struct inode *inode, struct file *flip)
{
	struct gntdev_priv *priv;
	int ret = 0;

	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
	if (!priv)
		return -ENOMEM;

	INIT_LIST_HEAD(&priv->maps);
	INIT_LIST_HEAD(&priv->freeable_maps);
	spin_lock_init(&priv->lock);

	if (use_ptemod) {
		priv->mm = get_task_mm(current);
		if (!priv->mm) {
			kfree(priv);
			return -ENOMEM;
		}
		priv->mn.ops = &gntdev_mmu_ops;
		ret = mmu_notifier_register(&priv->mn, priv->mm);
		mmput(priv->mm);
	}

	if (ret) {
		kfree(priv);
		return ret;
	}

	flip->private_data = priv;
	pr_debug("priv %p\n", priv);

	return 0;
}

static int gntdev_release(struct inode *inode, struct file *flip)
{
	struct gntdev_priv *priv = flip->private_data;
	struct grant_map *map;

	pr_debug("priv %p\n", priv);

	while (!list_empty(&priv->maps)) {
		map = list_entry(priv->maps.next, struct grant_map, next);
		list_del(&map->next);
		gntdev_put_map(NULL /* already removed */, map);
	}
	WARN_ON(!list_empty(&priv->freeable_maps));

	if (use_ptemod)
		mmu_notifier_unregister(&priv->mn, priv->mm);
	kfree(priv);
	return 0;
}

static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
				       struct ioctl_gntdev_map_grant_ref __user *u)
{
	struct ioctl_gntdev_map_grant_ref op;
	struct grant_map *map;
	int err;

	if (copy_from_user(&op, u, sizeof(op)) != 0)
		return -EFAULT;
	pr_debug("priv %p, add %d\n", priv, op.count);
	if (unlikely(op.count <= 0))
		return -EINVAL;

	err = -ENOMEM;
	map = gntdev_alloc_map(priv, op.count);
	if (!map)
		return err;

	if (unlikely(atomic_add_return(op.count, &pages_mapped) > limit)) {
		pr_debug("can't map: over limit\n");
		gntdev_put_map(NULL, map);
		return err;
	}

	if (copy_from_user(map->grants, &u->refs,
			   sizeof(map->grants[0]) * op.count) != 0) {
		gntdev_put_map(NULL, map);
		return -EFAULT;
	}

	spin_lock(&priv->lock);
	gntdev_add_map(priv, map);
	op.index = map->index << PAGE_SHIFT;
	spin_unlock(&priv->lock);

	if (copy_to_user(u, &op, sizeof(op)) != 0)
		return -EFAULT;

	return 0;
}

static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv,
					 struct ioctl_gntdev_unmap_grant_ref __user *u)
{
	struct ioctl_gntdev_unmap_grant_ref op;
	struct grant_map *map;
	int err = -ENOENT;

	if (copy_from_user(&op, u, sizeof(op)) != 0)
		return -EFAULT;
	pr_debug("priv %p, del %d+%d\n", priv, (int)op.index, (int)op.count);

	spin_lock(&priv->lock);
	map = gntdev_find_map_index(priv, op.index >> PAGE_SHIFT, op.count);
	if (map) {
		list_del(&map->next);
		if (populate_freeable_maps)
			list_add_tail(&map->next, &priv->freeable_maps);
		err = 0;
	}
	spin_unlock(&priv->lock);
	if (map)
		gntdev_put_map(priv, map);
	return err;
}

static long gntdev_ioctl_get_offset_for_vaddr(struct gntdev_priv *priv,
					      struct ioctl_gntdev_get_offset_for_vaddr __user *u)
{
	struct ioctl_gntdev_get_offset_for_vaddr op;
	struct vm_area_struct *vma;
	struct grant_map *map;
	int rv = -EINVAL;

	if (copy_from_user(&op, u, sizeof(op)) != 0)
		return -EFAULT;
	pr_debug("priv %p, offset for vaddr %lx\n", priv, (unsigned long)op.vaddr);

	down_read(&current->mm->mmap_sem);
	vma = find_vma(current->mm, op.vaddr);
	if (!vma || vma->vm_ops != &gntdev_vmops)
		goto out_unlock;

	map = vma->vm_private_data;
	if (!map)
		goto out_unlock;

	op.offset = map->index << PAGE_SHIFT;
	op.count = map->count;
	rv = 0;

 out_unlock:
	up_read(&current->mm->mmap_sem);

	if (rv == 0 && copy_to_user(u, &op, sizeof(op)) != 0)
		return -EFAULT;
	return rv;
}

static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u)
{
	struct ioctl_gntdev_unmap_notify op;
	struct grant_map *map;
	int rc;
	int out_flags;
	unsigned int out_event;

	if (copy_from_user(&op, u, sizeof(op)))
		return -EFAULT;

	if (op.action & ~(UNMAP_NOTIFY_CLEAR_BYTE|UNMAP_NOTIFY_SEND_EVENT))
		return -EINVAL;

	/* We need to grab a reference to the event channel we are going to use
	 * to send the notify before releasing the reference we may already have
	 * (if someone has called this ioctl twice). This is required so that
	 * it is possible to change the clear_byte part of the notification
	 * without disturbing the event channel part, which may now be the last
	 * reference to that event channel.
	 */
	if (op.action & UNMAP_NOTIFY_SEND_EVENT) {
		if (evtchn_get(op.event_channel_port))
			return -EINVAL;
	}

	out_flags = op.action;
	out_event = op.event_channel_port;

	spin_lock(&priv->lock);

	list_for_each_entry(map, &priv->maps, next) {
		uint64_t begin = map->index << PAGE_SHIFT;
		uint64_t end = (map->index + map->count) << PAGE_SHIFT;
		if (op.index >= begin && op.index < end)
			goto found;
	}
	rc = -ENOENT;
	goto unlock_out;

 found:
	if ((op.action & UNMAP_NOTIFY_CLEAR_BYTE) &&
			(map->flags & GNTMAP_readonly)) {
		rc = -EINVAL;
		goto unlock_out;
	}

	out_flags = map->notify.flags;
	out_event = map->notify.event;

	map->notify.flags = op.action;
	map->notify.addr = op.index - (map->index << PAGE_SHIFT);
	map->notify.event = op.event_channel_port;

	rc = 0;

 unlock_out:
	spin_unlock(&priv->lock);

	/* Drop the reference to the event channel we did not save in the map */
	if (out_flags & UNMAP_NOTIFY_SEND_EVENT)
		evtchn_put(out_event);

	return rc;
}

static long gntdev_ioctl(struct file *flip,
			 unsigned int cmd, unsigned long arg)
{
	struct gntdev_priv *priv = flip->private_data;
	void __user *ptr = (void __user *)arg;

	switch (cmd) {
	case IOCTL_GNTDEV_MAP_GRANT_REF:
		return gntdev_ioctl_map_grant_ref(priv, ptr);

	case IOCTL_GNTDEV_UNMAP_GRANT_REF:
		return gntdev_ioctl_unmap_grant_ref(priv, ptr);

	case IOCTL_GNTDEV_GET_OFFSET_FOR_VADDR:
		return gntdev_ioctl_get_offset_for_vaddr(priv, ptr);

	case IOCTL_GNTDEV_SET_UNMAP_NOTIFY:
		return gntdev_ioctl_notify(priv, ptr);

	default:
		pr_debug("priv %p, unknown cmd %x\n", priv, cmd);
		return -ENOIOCTLCMD;
	}

	return 0;
}

static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
{
	struct gntdev_priv *priv = flip->private_data;
	int index = vma->vm_pgoff;
	int count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
	struct grant_map *map;
	int i, err = -EINVAL;

	if ((vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_SHARED))
		return -EINVAL;

	pr_debug("map %d+%d at %lx (pgoff %lx)\n",
			index, count, vma->vm_start, vma->vm_pgoff);

	spin_lock(&priv->lock);
	map = gntdev_find_map_index(priv, index, count);
	if (!map)
		goto unlock_out;
	if (use_ptemod && map->vma)
		goto unlock_out;
	if (use_ptemod && priv->mm != vma->vm_mm) {
		pr_warn("Huh? Other mm?\n");
		goto unlock_out;
	}

	atomic_inc(&map->users);

	vma->vm_ops = &gntdev_vmops;

	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;

	if (use_ptemod)
		vma->vm_flags |= VM_DONTCOPY;

	vma->vm_private_data = map;

	if (use_ptemod)
		map->vma = vma;

	if (map->flags) {
		if ((vma->vm_flags & VM_WRITE) &&
				(map->flags & GNTMAP_readonly))
			goto out_unlock_put;
	} else {
		map->flags = GNTMAP_host_map;
		if (!(vma->vm_flags & VM_WRITE))
			map->flags |= GNTMAP_readonly;
	}

	spin_unlock(&priv->lock);

	if (use_ptemod) {
		err = apply_to_page_range(vma->vm_mm, vma->vm_start,
					  vma->vm_end - vma->vm_start,
					  find_grant_ptes, map);
		if (err) {
			pr_warn("find_grant_ptes() failure.\n");
			goto out_put_map;
		}
	}

	err = map_grant_pages(map);
	if (err)
		goto out_put_map;

	if (!use_ptemod) {
		for (i = 0; i < count; i++) {
			err = vm_insert_page(vma, vma->vm_start + i*PAGE_SIZE,
				map->pages[i]);
			if (err)
				goto out_put_map;
		}
	}

	return 0;

unlock_out:
	spin_unlock(&priv->lock);
	return err;

out_unlock_put:
	spin_unlock(&priv->lock);
out_put_map:
	if (use_ptemod)
		map->vma = NULL;
	gntdev_put_map(priv, map);
	return err;
}

static const struct file_operations gntdev_fops = {
	.owner = THIS_MODULE,
	.open = gntdev_open,
	.release = gntdev_release,
	.mmap = gntdev_mmap,
	.unlocked_ioctl = gntdev_ioctl
};

static struct miscdevice gntdev_miscdev = {
	.minor        = MISC_DYNAMIC_MINOR,
	.name         = "xen/gntdev",
	.fops         = &gntdev_fops,
};

/* ------------------------------------------------------------------ */

static int __init gntdev_init(void)
{
	int err;

	if (!xen_domain())
		return -ENODEV;

	use_ptemod = !xen_feature(XENFEAT_auto_translated_physmap);

	err = misc_register(&gntdev_miscdev);
	if (err != 0) {
		pr_err("Could not register gntdev device\n");
		return err;
	}
	return 0;
}

static void __exit gntdev_exit(void)
{
	misc_deregister(&gntdev_miscdev);
}

module_init(gntdev_init);
module_exit(gntdev_exit);

/* ------------------------------------------------------------------ */