vio.c 41.5 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3
/*
 * IBM PowerPC Virtual I/O Infrastructure Support.
 *
4
 *    Copyright (c) 2003,2008 IBM Corp.
L
Linus Torvalds 已提交
5 6 7
 *     Dave Engebretsen engebret@us.ibm.com
 *     Santiago Leon santil@us.ibm.com
 *     Hollis Blanchard <hollisb@us.ibm.com>
8
 *     Stephen Rothwell
9
 *     Robert Jennings <rcjenn@us.ibm.com>
L
Linus Torvalds 已提交
10 11 12 13 14 15 16
 *
 *      This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 */

17 18
#include <linux/types.h>
#include <linux/device.h>
L
Linus Torvalds 已提交
19 20 21 22 23
#include <linux/init.h>
#include <linux/console.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/dma-mapping.h>
24 25
#include <linux/kobject.h>

L
Linus Torvalds 已提交
26 27 28
#include <asm/iommu.h>
#include <asm/dma.h>
#include <asm/vio.h>
29
#include <asm/prom.h>
30
#include <asm/firmware.h>
31 32 33 34 35 36 37 38 39 40
#include <asm/tce.h>
#include <asm/abs_addr.h>
#include <asm/page.h>
#include <asm/hvcall.h>
#include <asm/iseries/vio.h>
#include <asm/iseries/hv_types.h>
#include <asm/iseries/hv_lp_config.h>
#include <asm/iseries/hv_call_xm.h>
#include <asm/iseries/iommu.h>

41 42
static struct bus_type vio_bus_type;

43
static struct vio_dev vio_bus_device  = { /* fake "parent" device */
44 45 46 47
	.name = vio_bus_device.dev.bus_id,
	.type = "",
	.dev.bus_id = "vio",
	.dev.bus = &vio_bus_type,
L
Linus Torvalds 已提交
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
#ifdef CONFIG_PPC_SMLPAR
/**
 * vio_cmo_pool - A pool of IO memory for CMO use
 *
 * @size: The size of the pool in bytes
 * @free: The amount of free memory in the pool
 */
struct vio_cmo_pool {
	size_t size;
	size_t free;
};

/* How many ms to delay queued balance work */
#define VIO_CMO_BALANCE_DELAY 100

/* Portion out IO memory to CMO devices by this chunk size */
#define VIO_CMO_BALANCE_CHUNK 131072

/**
 * vio_cmo_dev_entry - A device that is CMO-enabled and requires entitlement
 *
 * @vio_dev: struct vio_dev pointer
 * @list: pointer to other devices on bus that are being tracked
 */
struct vio_cmo_dev_entry {
	struct vio_dev *viodev;
	struct list_head list;
};

/**
 * vio_cmo - VIO bus accounting structure for CMO entitlement
 *
 * @lock: spinlock for entire structure
 * @balance_q: work queue for balancing system entitlement
 * @device_list: list of CMO-enabled devices requiring entitlement
 * @entitled: total system entitlement in bytes
 * @reserve: pool of memory from which devices reserve entitlement, incl. spare
 * @excess: pool of excess entitlement not needed for device reserves or spare
 * @spare: IO memory for device hotplug functionality
 * @min: minimum necessary for system operation
 * @desired: desired memory for system operation
 * @curr: bytes currently allocated
 * @high: high water mark for IO data usage
 */
struct vio_cmo {
	spinlock_t lock;
	struct delayed_work balance_q;
	struct list_head device_list;
	size_t entitled;
	struct vio_cmo_pool reserve;
	struct vio_cmo_pool excess;
	size_t spare;
	size_t min;
	size_t desired;
	size_t curr;
	size_t high;
} vio_cmo;

/**
 * vio_cmo_OF_devices - Count the number of OF devices that have DMA windows
 */
static int vio_cmo_num_OF_devs(void)
{
	struct device_node *node_vroot;
	int count = 0;

	/*
	 * Count the number of vdevice entries with an
	 * ibm,my-dma-window OF property
	 */
	node_vroot = of_find_node_by_name(NULL, "vdevice");
	if (node_vroot) {
		struct device_node *of_node;
		struct property *prop;

		for_each_child_of_node(node_vroot, of_node) {
			prop = of_find_property(of_node, "ibm,my-dma-window",
			                       NULL);
			if (prop)
				count++;
		}
	}
	of_node_put(node_vroot);
	return count;
}

/**
 * vio_cmo_alloc - allocate IO memory for CMO-enable devices
 *
 * @viodev: VIO device requesting IO memory
 * @size: size of allocation requested
 *
 * Allocations come from memory reserved for the devices and any excess
 * IO memory available to all devices.  The spare pool used to service
 * hotplug must be equal to %VIO_CMO_MIN_ENT for the excess pool to be
 * made available.
 *
 * Return codes:
 *  0 for successful allocation and -ENOMEM for a failure
 */
static inline int vio_cmo_alloc(struct vio_dev *viodev, size_t size)
{
	unsigned long flags;
	size_t reserve_free = 0;
	size_t excess_free = 0;
	int ret = -ENOMEM;

	spin_lock_irqsave(&vio_cmo.lock, flags);

	/* Determine the amount of free entitlement available in reserve */
	if (viodev->cmo.entitled > viodev->cmo.allocated)
		reserve_free = viodev->cmo.entitled - viodev->cmo.allocated;

	/* If spare is not fulfilled, the excess pool can not be used. */
	if (vio_cmo.spare >= VIO_CMO_MIN_ENT)
		excess_free = vio_cmo.excess.free;

	/* The request can be satisfied */
	if ((reserve_free + excess_free) >= size) {
		vio_cmo.curr += size;
		if (vio_cmo.curr > vio_cmo.high)
			vio_cmo.high = vio_cmo.curr;
		viodev->cmo.allocated += size;
		size -= min(reserve_free, size);
		vio_cmo.excess.free -= size;
		ret = 0;
	}

	spin_unlock_irqrestore(&vio_cmo.lock, flags);
	return ret;
}

/**
 * vio_cmo_dealloc - deallocate IO memory from CMO-enable devices
 * @viodev: VIO device freeing IO memory
 * @size: size of deallocation
 *
 * IO memory is freed by the device back to the correct memory pools.
 * The spare pool is replenished first from either memory pool, then
 * the reserve pool is used to reduce device entitlement, the excess
 * pool is used to increase the reserve pool toward the desired entitlement
 * target, and then the remaining memory is returned to the pools.
 *
 */
static inline void vio_cmo_dealloc(struct vio_dev *viodev, size_t size)
{
	unsigned long flags;
	size_t spare_needed = 0;
	size_t excess_freed = 0;
	size_t reserve_freed = size;
	size_t tmp;
	int balance = 0;

	spin_lock_irqsave(&vio_cmo.lock, flags);
	vio_cmo.curr -= size;

	/* Amount of memory freed from the excess pool */
	if (viodev->cmo.allocated > viodev->cmo.entitled) {
		excess_freed = min(reserve_freed, (viodev->cmo.allocated -
		                                   viodev->cmo.entitled));
		reserve_freed -= excess_freed;
	}

	/* Remove allocation from device */
	viodev->cmo.allocated -= (reserve_freed + excess_freed);

	/* Spare is a subset of the reserve pool, replenish it first. */
	spare_needed = VIO_CMO_MIN_ENT - vio_cmo.spare;

	/*
	 * Replenish the spare in the reserve pool from the excess pool.
	 * This moves entitlement into the reserve pool.
	 */
	if (spare_needed && excess_freed) {
		tmp = min(excess_freed, spare_needed);
		vio_cmo.excess.size -= tmp;
		vio_cmo.reserve.size += tmp;
		vio_cmo.spare += tmp;
		excess_freed -= tmp;
		spare_needed -= tmp;
		balance = 1;
	}

	/*
	 * Replenish the spare in the reserve pool from the reserve pool.
	 * This removes entitlement from the device down to VIO_CMO_MIN_ENT,
	 * if needed, and gives it to the spare pool. The amount of used
	 * memory in this pool does not change.
	 */
	if (spare_needed && reserve_freed) {
		tmp = min(spare_needed, min(reserve_freed,
		                            (viodev->cmo.entitled -
		                             VIO_CMO_MIN_ENT)));

		vio_cmo.spare += tmp;
		viodev->cmo.entitled -= tmp;
		reserve_freed -= tmp;
		spare_needed -= tmp;
		balance = 1;
	}

	/*
	 * Increase the reserve pool until the desired allocation is met.
	 * Move an allocation freed from the excess pool into the reserve
	 * pool and schedule a balance operation.
	 */
	if (excess_freed && (vio_cmo.desired > vio_cmo.reserve.size)) {
		tmp = min(excess_freed, (vio_cmo.desired - vio_cmo.reserve.size));

		vio_cmo.excess.size -= tmp;
		vio_cmo.reserve.size += tmp;
		excess_freed -= tmp;
		balance = 1;
	}

	/* Return memory from the excess pool to that pool */
	if (excess_freed)
		vio_cmo.excess.free += excess_freed;

	if (balance)
		schedule_delayed_work(&vio_cmo.balance_q, VIO_CMO_BALANCE_DELAY);
	spin_unlock_irqrestore(&vio_cmo.lock, flags);
}

/**
 * vio_cmo_entitlement_update - Manage system entitlement changes
 *
 * @new_entitlement: new system entitlement to attempt to accommodate
 *
 * Increases in entitlement will be used to fulfill the spare entitlement
 * and the rest is given to the excess pool.  Decreases, if they are
 * possible, come from the excess pool and from unused device entitlement
 *
 * Returns: 0 on success, -ENOMEM when change can not be made
 */
int vio_cmo_entitlement_update(size_t new_entitlement)
{
	struct vio_dev *viodev;
	struct vio_cmo_dev_entry *dev_ent;
	unsigned long flags;
	size_t avail, delta, tmp;

	spin_lock_irqsave(&vio_cmo.lock, flags);

	/* Entitlement increases */
	if (new_entitlement > vio_cmo.entitled) {
		delta = new_entitlement - vio_cmo.entitled;

		/* Fulfill spare allocation */
		if (vio_cmo.spare < VIO_CMO_MIN_ENT) {
			tmp = min(delta, (VIO_CMO_MIN_ENT - vio_cmo.spare));
			vio_cmo.spare += tmp;
			vio_cmo.reserve.size += tmp;
			delta -= tmp;
		}

		/* Remaining new allocation goes to the excess pool */
		vio_cmo.entitled += delta;
		vio_cmo.excess.size += delta;
		vio_cmo.excess.free += delta;

		goto out;
	}

	/* Entitlement decreases */
	delta = vio_cmo.entitled - new_entitlement;
	avail = vio_cmo.excess.free;

	/*
	 * Need to check how much unused entitlement each device can
	 * sacrifice to fulfill entitlement change.
	 */
	list_for_each_entry(dev_ent, &vio_cmo.device_list, list) {
		if (avail >= delta)
			break;

		viodev = dev_ent->viodev;
		if ((viodev->cmo.entitled > viodev->cmo.allocated) &&
		    (viodev->cmo.entitled > VIO_CMO_MIN_ENT))
				avail += viodev->cmo.entitled -
				         max_t(size_t, viodev->cmo.allocated,
				               VIO_CMO_MIN_ENT);
	}

	if (delta <= avail) {
		vio_cmo.entitled -= delta;

		/* Take entitlement from the excess pool first */
		tmp = min(vio_cmo.excess.free, delta);
		vio_cmo.excess.size -= tmp;
		vio_cmo.excess.free -= tmp;
		delta -= tmp;

		/*
		 * Remove all but VIO_CMO_MIN_ENT bytes from devices
		 * until entitlement change is served
		 */
		list_for_each_entry(dev_ent, &vio_cmo.device_list, list) {
			if (!delta)
				break;

			viodev = dev_ent->viodev;
			tmp = 0;
			if ((viodev->cmo.entitled > viodev->cmo.allocated) &&
			    (viodev->cmo.entitled > VIO_CMO_MIN_ENT))
				tmp = viodev->cmo.entitled -
				      max_t(size_t, viodev->cmo.allocated,
				            VIO_CMO_MIN_ENT);
			viodev->cmo.entitled -= min(tmp, delta);
			delta -= min(tmp, delta);
		}
	} else {
		spin_unlock_irqrestore(&vio_cmo.lock, flags);
		return -ENOMEM;
	}

out:
	schedule_delayed_work(&vio_cmo.balance_q, 0);
	spin_unlock_irqrestore(&vio_cmo.lock, flags);
	return 0;
}

/**
 * vio_cmo_balance - Balance entitlement among devices
 *
 * @work: work queue structure for this operation
 *
 * Any system entitlement above the minimum needed for devices, or
 * already allocated to devices, can be distributed to the devices.
 * The list of devices is iterated through to recalculate the desired
 * entitlement level and to determine how much entitlement above the
 * minimum entitlement is allocated to devices.
 *
 * Small chunks of the available entitlement are given to devices until
 * their requirements are fulfilled or there is no entitlement left to give.
 * Upon completion sizes of the reserve and excess pools are calculated.
 *
 * The system minimum entitlement level is also recalculated here.
 * Entitlement will be reserved for devices even after vio_bus_remove to
 * accommodate reloading the driver.  The OF tree is walked to count the
 * number of devices present and this will remove entitlement for devices
 * that have actually left the system after having vio_bus_remove called.
 */
static void vio_cmo_balance(struct work_struct *work)
{
	struct vio_cmo *cmo;
	struct vio_dev *viodev;
	struct vio_cmo_dev_entry *dev_ent;
	unsigned long flags;
	size_t avail = 0, level, chunk, need;
	int devcount = 0, fulfilled;

	cmo = container_of(work, struct vio_cmo, balance_q.work);

	spin_lock_irqsave(&vio_cmo.lock, flags);

	/* Calculate minimum entitlement and fulfill spare */
	cmo->min = vio_cmo_num_OF_devs() * VIO_CMO_MIN_ENT;
	BUG_ON(cmo->min > cmo->entitled);
	cmo->spare = min_t(size_t, VIO_CMO_MIN_ENT, (cmo->entitled - cmo->min));
	cmo->min += cmo->spare;
	cmo->desired = cmo->min;

	/*
	 * Determine how much entitlement is available and reset device
	 * entitlements
	 */
	avail = cmo->entitled - cmo->spare;
	list_for_each_entry(dev_ent, &vio_cmo.device_list, list) {
		viodev = dev_ent->viodev;
		devcount++;
		viodev->cmo.entitled = VIO_CMO_MIN_ENT;
		cmo->desired += (viodev->cmo.desired - VIO_CMO_MIN_ENT);
		avail -= max_t(size_t, viodev->cmo.allocated, VIO_CMO_MIN_ENT);
	}

	/*
	 * Having provided each device with the minimum entitlement, loop
	 * over the devices portioning out the remaining entitlement
	 * until there is nothing left.
	 */
	level = VIO_CMO_MIN_ENT;
	while (avail) {
		fulfilled = 0;
		list_for_each_entry(dev_ent, &vio_cmo.device_list, list) {
			viodev = dev_ent->viodev;

			if (viodev->cmo.desired <= level) {
				fulfilled++;
				continue;
			}

			/*
			 * Give the device up to VIO_CMO_BALANCE_CHUNK
			 * bytes of entitlement, but do not exceed the
			 * desired level of entitlement for the device.
			 */
			chunk = min_t(size_t, avail, VIO_CMO_BALANCE_CHUNK);
			chunk = min(chunk, (viodev->cmo.desired -
			                    viodev->cmo.entitled));
			viodev->cmo.entitled += chunk;

			/*
			 * If the memory for this entitlement increase was
			 * already allocated to the device it does not come
			 * from the available pool being portioned out.
			 */
			need = max(viodev->cmo.allocated, viodev->cmo.entitled)-
			       max(viodev->cmo.allocated, level);
			avail -= need;

		}
		if (fulfilled == devcount)
			break;
		level += VIO_CMO_BALANCE_CHUNK;
	}

	/* Calculate new reserve and excess pool sizes */
	cmo->reserve.size = cmo->min;
	cmo->excess.free = 0;
	cmo->excess.size = 0;
	need = 0;
	list_for_each_entry(dev_ent, &vio_cmo.device_list, list) {
		viodev = dev_ent->viodev;
		/* Calculated reserve size above the minimum entitlement */
		if (viodev->cmo.entitled)
			cmo->reserve.size += (viodev->cmo.entitled -
			                      VIO_CMO_MIN_ENT);
		/* Calculated used excess entitlement */
		if (viodev->cmo.allocated > viodev->cmo.entitled)
			need += viodev->cmo.allocated - viodev->cmo.entitled;
	}
	cmo->excess.size = cmo->entitled - cmo->reserve.size;
	cmo->excess.free = cmo->excess.size - need;

	cancel_delayed_work(container_of(work, struct delayed_work, work));
	spin_unlock_irqrestore(&vio_cmo.lock, flags);
}

static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size,
                                          dma_addr_t *dma_handle, gfp_t flag)
{
	struct vio_dev *viodev = to_vio_dev(dev);
	void *ret;

	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE))) {
		atomic_inc(&viodev->cmo.allocs_failed);
		return NULL;
	}

	ret = dma_iommu_ops.alloc_coherent(dev, size, dma_handle, flag);
	if (unlikely(ret == NULL)) {
		vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE));
		atomic_inc(&viodev->cmo.allocs_failed);
	}

	return ret;
}

static void vio_dma_iommu_free_coherent(struct device *dev, size_t size,
                                        void *vaddr, dma_addr_t dma_handle)
{
	struct vio_dev *viodev = to_vio_dev(dev);

	dma_iommu_ops.free_coherent(dev, size, vaddr, dma_handle);

	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE));
}

static dma_addr_t vio_dma_iommu_map_single(struct device *dev, void *vaddr,
                                           size_t size,
                                           enum dma_data_direction direction,
                                           struct dma_attrs *attrs)
{
	struct vio_dev *viodev = to_vio_dev(dev);
	dma_addr_t ret = DMA_ERROR_CODE;

	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE))) {
		atomic_inc(&viodev->cmo.allocs_failed);
		return ret;
	}

	ret = dma_iommu_ops.map_single(dev, vaddr, size, direction, attrs);
533
	if (unlikely(dma_mapping_error(dev, ret))) {
534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033
		vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE));
		atomic_inc(&viodev->cmo.allocs_failed);
	}

	return ret;
}

static void vio_dma_iommu_unmap_single(struct device *dev,
		dma_addr_t dma_handle, size_t size,
		enum dma_data_direction direction,
		struct dma_attrs *attrs)
{
	struct vio_dev *viodev = to_vio_dev(dev);

	dma_iommu_ops.unmap_single(dev, dma_handle, size, direction, attrs);

	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE));
}

static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
                                int nelems, enum dma_data_direction direction,
                                struct dma_attrs *attrs)
{
	struct vio_dev *viodev = to_vio_dev(dev);
	struct scatterlist *sgl;
	int ret, count = 0;
	size_t alloc_size = 0;

	for (sgl = sglist; count < nelems; count++, sgl++)
		alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE);

	if (vio_cmo_alloc(viodev, alloc_size)) {
		atomic_inc(&viodev->cmo.allocs_failed);
		return 0;
	}

	ret = dma_iommu_ops.map_sg(dev, sglist, nelems, direction, attrs);

	if (unlikely(!ret)) {
		vio_cmo_dealloc(viodev, alloc_size);
		atomic_inc(&viodev->cmo.allocs_failed);
	}

	for (sgl = sglist, count = 0; count < ret; count++, sgl++)
		alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE);
	if (alloc_size)
		vio_cmo_dealloc(viodev, alloc_size);

	return ret;
}

static void vio_dma_iommu_unmap_sg(struct device *dev,
		struct scatterlist *sglist, int nelems,
		enum dma_data_direction direction,
		struct dma_attrs *attrs)
{
	struct vio_dev *viodev = to_vio_dev(dev);
	struct scatterlist *sgl;
	size_t alloc_size = 0;
	int count = 0;

	for (sgl = sglist; count < nelems; count++, sgl++)
		alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE);

	dma_iommu_ops.unmap_sg(dev, sglist, nelems, direction, attrs);

	vio_cmo_dealloc(viodev, alloc_size);
}

struct dma_mapping_ops vio_dma_mapping_ops = {
	.alloc_coherent = vio_dma_iommu_alloc_coherent,
	.free_coherent  = vio_dma_iommu_free_coherent,
	.map_single     = vio_dma_iommu_map_single,
	.unmap_single   = vio_dma_iommu_unmap_single,
	.map_sg         = vio_dma_iommu_map_sg,
	.unmap_sg       = vio_dma_iommu_unmap_sg,
};

/**
 * vio_cmo_set_dev_desired - Set desired entitlement for a device
 *
 * @viodev: struct vio_dev for device to alter
 * @new_desired: new desired entitlement level in bytes
 *
 * For use by devices to request a change to their entitlement at runtime or
 * through sysfs.  The desired entitlement level is changed and a balancing
 * of system resources is scheduled to run in the future.
 */
void vio_cmo_set_dev_desired(struct vio_dev *viodev, size_t desired)
{
	unsigned long flags;
	struct vio_cmo_dev_entry *dev_ent;
	int found = 0;

	if (!firmware_has_feature(FW_FEATURE_CMO))
		return;

	spin_lock_irqsave(&vio_cmo.lock, flags);
	if (desired < VIO_CMO_MIN_ENT)
		desired = VIO_CMO_MIN_ENT;

	/*
	 * Changes will not be made for devices not in the device list.
	 * If it is not in the device list, then no driver is loaded
	 * for the device and it can not receive entitlement.
	 */
	list_for_each_entry(dev_ent, &vio_cmo.device_list, list)
		if (viodev == dev_ent->viodev) {
			found = 1;
			break;
		}
	if (!found)
		return;

	/* Increase/decrease in desired device entitlement */
	if (desired >= viodev->cmo.desired) {
		/* Just bump the bus and device values prior to a balance*/
		vio_cmo.desired += desired - viodev->cmo.desired;
		viodev->cmo.desired = desired;
	} else {
		/* Decrease bus and device values for desired entitlement */
		vio_cmo.desired -= viodev->cmo.desired - desired;
		viodev->cmo.desired = desired;
		/*
		 * If less entitlement is desired than current entitlement, move
		 * any reserve memory in the change region to the excess pool.
		 */
		if (viodev->cmo.entitled > desired) {
			vio_cmo.reserve.size -= viodev->cmo.entitled - desired;
			vio_cmo.excess.size += viodev->cmo.entitled - desired;
			/*
			 * If entitlement moving from the reserve pool to the
			 * excess pool is currently unused, add to the excess
			 * free counter.
			 */
			if (viodev->cmo.allocated < viodev->cmo.entitled)
				vio_cmo.excess.free += viodev->cmo.entitled -
				                       max(viodev->cmo.allocated, desired);
			viodev->cmo.entitled = desired;
		}
	}
	schedule_delayed_work(&vio_cmo.balance_q, 0);
	spin_unlock_irqrestore(&vio_cmo.lock, flags);
}

/**
 * vio_cmo_bus_probe - Handle CMO specific bus probe activities
 *
 * @viodev - Pointer to struct vio_dev for device
 *
 * Determine the devices IO memory entitlement needs, attempting
 * to satisfy the system minimum entitlement at first and scheduling
 * a balance operation to take care of the rest at a later time.
 *
 * Returns: 0 on success, -EINVAL when device doesn't support CMO, and
 *          -ENOMEM when entitlement is not available for device or
 *          device entry.
 *
 */
static int vio_cmo_bus_probe(struct vio_dev *viodev)
{
	struct vio_cmo_dev_entry *dev_ent;
	struct device *dev = &viodev->dev;
	struct vio_driver *viodrv = to_vio_driver(dev->driver);
	unsigned long flags;
	size_t size;

	/*
	 * Check to see that device has a DMA window and configure
	 * entitlement for the device.
	 */
	if (of_get_property(viodev->dev.archdata.of_node,
	                    "ibm,my-dma-window", NULL)) {
		/* Check that the driver is CMO enabled and get desired DMA */
		if (!viodrv->get_desired_dma) {
			dev_err(dev, "%s: device driver does not support CMO\n",
			        __func__);
			return -EINVAL;
		}

		viodev->cmo.desired = IOMMU_PAGE_ALIGN(viodrv->get_desired_dma(viodev));
		if (viodev->cmo.desired < VIO_CMO_MIN_ENT)
			viodev->cmo.desired = VIO_CMO_MIN_ENT;
		size = VIO_CMO_MIN_ENT;

		dev_ent = kmalloc(sizeof(struct vio_cmo_dev_entry),
		                  GFP_KERNEL);
		if (!dev_ent)
			return -ENOMEM;

		dev_ent->viodev = viodev;
		spin_lock_irqsave(&vio_cmo.lock, flags);
		list_add(&dev_ent->list, &vio_cmo.device_list);
	} else {
		viodev->cmo.desired = 0;
		size = 0;
		spin_lock_irqsave(&vio_cmo.lock, flags);
	}

	/*
	 * If the needs for vio_cmo.min have not changed since they
	 * were last set, the number of devices in the OF tree has
	 * been constant and the IO memory for this is already in
	 * the reserve pool.
	 */
	if (vio_cmo.min == ((vio_cmo_num_OF_devs() + 1) *
	                    VIO_CMO_MIN_ENT)) {
		/* Updated desired entitlement if device requires it */
		if (size)
			vio_cmo.desired += (viodev->cmo.desired -
		                        VIO_CMO_MIN_ENT);
	} else {
		size_t tmp;

		tmp = vio_cmo.spare + vio_cmo.excess.free;
		if (tmp < size) {
			dev_err(dev, "%s: insufficient free "
			        "entitlement to add device. "
			        "Need %lu, have %lu\n", __func__,
				size, (vio_cmo.spare + tmp));
			spin_unlock_irqrestore(&vio_cmo.lock, flags);
			return -ENOMEM;
		}

		/* Use excess pool first to fulfill request */
		tmp = min(size, vio_cmo.excess.free);
		vio_cmo.excess.free -= tmp;
		vio_cmo.excess.size -= tmp;
		vio_cmo.reserve.size += tmp;

		/* Use spare if excess pool was insufficient */
		vio_cmo.spare -= size - tmp;

		/* Update bus accounting */
		vio_cmo.min += size;
		vio_cmo.desired += viodev->cmo.desired;
	}
	spin_unlock_irqrestore(&vio_cmo.lock, flags);
	return 0;
}

/**
 * vio_cmo_bus_remove - Handle CMO specific bus removal activities
 *
 * @viodev - Pointer to struct vio_dev for device
 *
 * Remove the device from the cmo device list.  The minimum entitlement
 * will be reserved for the device as long as it is in the system.  The
 * rest of the entitlement the device had been allocated will be returned
 * to the system.
 */
static void vio_cmo_bus_remove(struct vio_dev *viodev)
{
	struct vio_cmo_dev_entry *dev_ent;
	unsigned long flags;
	size_t tmp;

	spin_lock_irqsave(&vio_cmo.lock, flags);
	if (viodev->cmo.allocated) {
		dev_err(&viodev->dev, "%s: device had %lu bytes of IO "
		        "allocated after remove operation.\n",
		        __func__, viodev->cmo.allocated);
		BUG();
	}

	/*
	 * Remove the device from the device list being maintained for
	 * CMO enabled devices.
	 */
	list_for_each_entry(dev_ent, &vio_cmo.device_list, list)
		if (viodev == dev_ent->viodev) {
			list_del(&dev_ent->list);
			kfree(dev_ent);
			break;
		}

	/*
	 * Devices may not require any entitlement and they do not need
	 * to be processed.  Otherwise, return the device's entitlement
	 * back to the pools.
	 */
	if (viodev->cmo.entitled) {
		/*
		 * This device has not yet left the OF tree, it's
		 * minimum entitlement remains in vio_cmo.min and
		 * vio_cmo.desired
		 */
		vio_cmo.desired -= (viodev->cmo.desired - VIO_CMO_MIN_ENT);

		/*
		 * Save min allocation for device in reserve as long
		 * as it exists in OF tree as determined by later
		 * balance operation
		 */
		viodev->cmo.entitled -= VIO_CMO_MIN_ENT;

		/* Replenish spare from freed reserve pool */
		if (viodev->cmo.entitled && (vio_cmo.spare < VIO_CMO_MIN_ENT)) {
			tmp = min(viodev->cmo.entitled, (VIO_CMO_MIN_ENT -
			                                 vio_cmo.spare));
			vio_cmo.spare += tmp;
			viodev->cmo.entitled -= tmp;
		}

		/* Remaining reserve goes to excess pool */
		vio_cmo.excess.size += viodev->cmo.entitled;
		vio_cmo.excess.free += viodev->cmo.entitled;
		vio_cmo.reserve.size -= viodev->cmo.entitled;

		/*
		 * Until the device is removed it will keep a
		 * minimum entitlement; this will guarantee that
		 * a module unload/load will result in a success.
		 */
		viodev->cmo.entitled = VIO_CMO_MIN_ENT;
		viodev->cmo.desired = VIO_CMO_MIN_ENT;
		atomic_set(&viodev->cmo.allocs_failed, 0);
	}

	spin_unlock_irqrestore(&vio_cmo.lock, flags);
}

static void vio_cmo_set_dma_ops(struct vio_dev *viodev)
{
	vio_dma_mapping_ops.dma_supported = dma_iommu_ops.dma_supported;
	viodev->dev.archdata.dma_ops = &vio_dma_mapping_ops;
}

/**
 * vio_cmo_bus_init - CMO entitlement initialization at bus init time
 *
 * Set up the reserve and excess entitlement pools based on available
 * system entitlement and the number of devices in the OF tree that
 * require entitlement in the reserve pool.
 */
static void vio_cmo_bus_init(void)
{
	struct hvcall_mpp_data mpp_data;
	int err;

	memset(&vio_cmo, 0, sizeof(struct vio_cmo));
	spin_lock_init(&vio_cmo.lock);
	INIT_LIST_HEAD(&vio_cmo.device_list);
	INIT_DELAYED_WORK(&vio_cmo.balance_q, vio_cmo_balance);

	/* Get current system entitlement */
	err = h_get_mpp(&mpp_data);

	/*
	 * On failure, continue with entitlement set to 0, will panic()
	 * later when spare is reserved.
	 */
	if (err != H_SUCCESS) {
		printk(KERN_ERR "%s: unable to determine system IO "\
		       "entitlement. (%d)\n", __func__, err);
		vio_cmo.entitled = 0;
	} else {
		vio_cmo.entitled = mpp_data.entitled_mem;
	}

	/* Set reservation and check against entitlement */
	vio_cmo.spare = VIO_CMO_MIN_ENT;
	vio_cmo.reserve.size = vio_cmo.spare;
	vio_cmo.reserve.size += (vio_cmo_num_OF_devs() *
	                         VIO_CMO_MIN_ENT);
	if (vio_cmo.reserve.size > vio_cmo.entitled) {
		printk(KERN_ERR "%s: insufficient system entitlement\n",
		       __func__);
		panic("%s: Insufficient system entitlement", __func__);
	}

	/* Set the remaining accounting variables */
	vio_cmo.excess.size = vio_cmo.entitled - vio_cmo.reserve.size;
	vio_cmo.excess.free = vio_cmo.excess.size;
	vio_cmo.min = vio_cmo.reserve.size;
	vio_cmo.desired = vio_cmo.reserve.size;
}

/* sysfs device functions and data structures for CMO */

#define viodev_cmo_rd_attr(name)                                        \
static ssize_t viodev_cmo_##name##_show(struct device *dev,             \
                                        struct device_attribute *attr,  \
                                         char *buf)                     \
{                                                                       \
	return sprintf(buf, "%lu\n", to_vio_dev(dev)->cmo.name);        \
}

static ssize_t viodev_cmo_allocs_failed_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct vio_dev *viodev = to_vio_dev(dev);
	return sprintf(buf, "%d\n", atomic_read(&viodev->cmo.allocs_failed));
}

static ssize_t viodev_cmo_allocs_failed_reset(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t count)
{
	struct vio_dev *viodev = to_vio_dev(dev);
	atomic_set(&viodev->cmo.allocs_failed, 0);
	return count;
}

static ssize_t viodev_cmo_desired_set(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t count)
{
	struct vio_dev *viodev = to_vio_dev(dev);
	size_t new_desired;
	int ret;

	ret = strict_strtoul(buf, 10, &new_desired);
	if (ret)
		return ret;

	vio_cmo_set_dev_desired(viodev, new_desired);
	return count;
}

viodev_cmo_rd_attr(desired);
viodev_cmo_rd_attr(entitled);
viodev_cmo_rd_attr(allocated);

static ssize_t name_show(struct device *, struct device_attribute *, char *);
static ssize_t devspec_show(struct device *, struct device_attribute *, char *);
static struct device_attribute vio_cmo_dev_attrs[] = {
	__ATTR_RO(name),
	__ATTR_RO(devspec),
	__ATTR(cmo_desired,       S_IWUSR|S_IRUSR|S_IWGRP|S_IRGRP|S_IROTH,
	       viodev_cmo_desired_show, viodev_cmo_desired_set),
	__ATTR(cmo_entitled,      S_IRUGO, viodev_cmo_entitled_show,      NULL),
	__ATTR(cmo_allocated,     S_IRUGO, viodev_cmo_allocated_show,     NULL),
	__ATTR(cmo_allocs_failed, S_IWUSR|S_IRUSR|S_IWGRP|S_IRGRP|S_IROTH,
	       viodev_cmo_allocs_failed_show, viodev_cmo_allocs_failed_reset),
	__ATTR_NULL
};

/* sysfs bus functions and data structures for CMO */

#define viobus_cmo_rd_attr(name)                                        \
static ssize_t                                                          \
viobus_cmo_##name##_show(struct bus_type *bt, char *buf)                \
{                                                                       \
	return sprintf(buf, "%lu\n", vio_cmo.name);                     \
}

#define viobus_cmo_pool_rd_attr(name, var)                              \
static ssize_t                                                          \
viobus_cmo_##name##_pool_show_##var(struct bus_type *bt, char *buf)     \
{                                                                       \
	return sprintf(buf, "%lu\n", vio_cmo.name.var);                 \
}

static ssize_t viobus_cmo_high_reset(struct bus_type *bt, const char *buf,
                                     size_t count)
{
	unsigned long flags;

	spin_lock_irqsave(&vio_cmo.lock, flags);
	vio_cmo.high = vio_cmo.curr;
	spin_unlock_irqrestore(&vio_cmo.lock, flags);

	return count;
}

viobus_cmo_rd_attr(entitled);
viobus_cmo_pool_rd_attr(reserve, size);
viobus_cmo_pool_rd_attr(excess, size);
viobus_cmo_pool_rd_attr(excess, free);
viobus_cmo_rd_attr(spare);
viobus_cmo_rd_attr(min);
viobus_cmo_rd_attr(desired);
viobus_cmo_rd_attr(curr);
viobus_cmo_rd_attr(high);

static struct bus_attribute vio_cmo_bus_attrs[] = {
	__ATTR(cmo_entitled, S_IRUGO, viobus_cmo_entitled_show, NULL),
	__ATTR(cmo_reserve_size, S_IRUGO, viobus_cmo_reserve_pool_show_size, NULL),
	__ATTR(cmo_excess_size, S_IRUGO, viobus_cmo_excess_pool_show_size, NULL),
	__ATTR(cmo_excess_free, S_IRUGO, viobus_cmo_excess_pool_show_free, NULL),
	__ATTR(cmo_spare,   S_IRUGO, viobus_cmo_spare_show,   NULL),
	__ATTR(cmo_min,     S_IRUGO, viobus_cmo_min_show,     NULL),
	__ATTR(cmo_desired, S_IRUGO, viobus_cmo_desired_show, NULL),
	__ATTR(cmo_curr,    S_IRUGO, viobus_cmo_curr_show,    NULL),
	__ATTR(cmo_high,    S_IWUSR|S_IRUSR|S_IWGRP|S_IRGRP|S_IROTH,
	       viobus_cmo_high_show, viobus_cmo_high_reset),
	__ATTR_NULL
};

static void vio_cmo_sysfs_init(void)
{
	vio_bus_type.dev_attrs = vio_cmo_dev_attrs;
	vio_bus_type.bus_attrs = vio_cmo_bus_attrs;
}
#else /* CONFIG_PPC_SMLPAR */
/* Dummy functions for iSeries platform */
int vio_cmo_entitlement_update(size_t new_entitlement) { return 0; }
void vio_cmo_set_dev_desired(struct vio_dev *viodev, size_t desired) {}
static int vio_cmo_bus_probe(struct vio_dev *viodev) { return 0; }
static void vio_cmo_bus_remove(struct vio_dev *viodev) {}
static void vio_cmo_set_dma_ops(struct vio_dev *viodev) {}
N
Nathan Lynch 已提交
1034 1035
static void vio_cmo_bus_init(void) {}
static void vio_cmo_sysfs_init(void) { }
1036 1037 1038 1039
#endif /* CONFIG_PPC_SMLPAR */
EXPORT_SYMBOL(vio_cmo_entitlement_update);
EXPORT_SYMBOL(vio_cmo_set_dev_desired);

1040 1041
static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
{
1042 1043 1044 1045 1046 1047
	const unsigned char *dma_window;
	struct iommu_table *tbl;
	unsigned long offset, size;

	if (firmware_has_feature(FW_FEATURE_ISERIES))
		return vio_build_iommu_table_iseries(dev);
1048

1049 1050 1051 1052
	dma_window = of_get_property(dev->dev.archdata.of_node,
				  "ibm,my-dma-window", NULL);
	if (!dma_window)
		return NULL;
1053

1054
	tbl = kmalloc(sizeof(*tbl), GFP_KERNEL);
1055

1056 1057
	of_parse_dma_window(dev->dev.archdata.of_node, dma_window,
			    &tbl->it_index, &offset, &size);
1058

1059 1060 1061 1062 1063 1064
	/* TCE table size - measured in tce entries */
	tbl->it_size = size >> IOMMU_PAGE_SHIFT;
	/* offset for VIO should always be 0 */
	tbl->it_offset = offset >> IOMMU_PAGE_SHIFT;
	tbl->it_busno = 0;
	tbl->it_type = TCE_VB;
1065

1066
	return iommu_init_table(tbl, -1);
1067
}
L
Linus Torvalds 已提交
1068

1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082
/**
 * vio_match_device: - Tell if a VIO device has a matching
 *			VIO device id structure.
 * @ids:	array of VIO device id structures to search in
 * @dev:	the VIO device structure to match against
 *
 * Used by a driver to check whether a VIO device present in the
 * system is in its list of supported devices. Returns the matching
 * vio_device_id structure or NULL if there is no match.
 */
static const struct vio_device_id *vio_match_device(
		const struct vio_device_id *ids, const struct vio_dev *dev)
{
	while (ids->type[0] != '\0') {
1083
		if ((strncmp(dev->type, ids->type, strlen(ids->type)) == 0) &&
1084
		    of_device_is_compatible(dev->dev.archdata.of_node,
1085
					 ids->compat))
1086 1087 1088 1089 1090 1091
			return ids;
		ids++;
	}
	return NULL;
}

1092 1093
/*
 * Convert from struct device to struct vio_dev and pass to driver.
L
Linus Torvalds 已提交
1094
 * dev->driver has already been set by generic code because vio_bus_match
1095 1096
 * succeeded.
 */
L
Linus Torvalds 已提交
1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107
static int vio_bus_probe(struct device *dev)
{
	struct vio_dev *viodev = to_vio_dev(dev);
	struct vio_driver *viodrv = to_vio_driver(dev->driver);
	const struct vio_device_id *id;
	int error = -ENODEV;

	if (!viodrv->probe)
		return error;

	id = vio_match_device(viodrv->id_table, viodev);
1108 1109 1110 1111 1112 1113 1114
	if (id) {
		memset(&viodev->cmo, 0, sizeof(viodev->cmo));
		if (firmware_has_feature(FW_FEATURE_CMO)) {
			error = vio_cmo_bus_probe(viodev);
			if (error)
				return error;
		}
L
Linus Torvalds 已提交
1115
		error = viodrv->probe(viodev, id);
1116 1117 1118
		if (error)
			vio_cmo_bus_remove(viodev);
	}
L
Linus Torvalds 已提交
1119 1120 1121 1122 1123 1124 1125 1126 1127

	return error;
}

/* convert from struct device to struct vio_dev and pass to driver. */
static int vio_bus_remove(struct device *dev)
{
	struct vio_dev *viodev = to_vio_dev(dev);
	struct vio_driver *viodrv = to_vio_driver(dev->driver);
1128 1129 1130 1131 1132 1133 1134 1135
	struct device *devptr;
	int ret = 1;

	/*
	 * Hold a reference to the device after the remove function is called
	 * to allow for CMO accounting cleanup for the device.
	 */
	devptr = get_device(dev);
L
Linus Torvalds 已提交
1136

1137
	if (viodrv->remove)
1138
		ret = viodrv->remove(viodev);
L
Linus Torvalds 已提交
1139

1140 1141 1142 1143 1144
	if (!ret && firmware_has_feature(FW_FEATURE_CMO))
		vio_cmo_bus_remove(viodev);

	put_device(devptr);
	return ret;
L
Linus Torvalds 已提交
1145 1146 1147 1148 1149 1150 1151 1152
}

/**
 * vio_register_driver: - Register a new vio driver
 * @drv:	The vio_driver structure to be registered.
 */
int vio_register_driver(struct vio_driver *viodrv)
{
1153
	printk(KERN_DEBUG "%s: driver %s registering\n", __func__,
1154
		viodrv->driver.name);
L
Linus Torvalds 已提交
1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172

	/* fill in 'struct driver' fields */
	viodrv->driver.bus = &vio_bus_type;

	return driver_register(&viodrv->driver);
}
EXPORT_SYMBOL(vio_register_driver);

/**
 * vio_unregister_driver - Remove registration of vio driver.
 * @driver:	The vio_driver struct to be removed form registration
 */
void vio_unregister_driver(struct vio_driver *viodrv)
{
	driver_unregister(&viodrv->driver);
}
EXPORT_SYMBOL(vio_unregister_driver);

1173 1174 1175
/* vio_dev refcount hit 0 */
static void __devinit vio_dev_release(struct device *dev)
{
1176 1177
	/* XXX should free TCE table */
	of_node_put(dev->archdata.of_node);
1178 1179 1180
	kfree(to_vio_dev(dev));
}

L
Linus Torvalds 已提交
1181
/**
1182 1183
 * vio_register_device_node: - Register a new vio device.
 * @of_node:	The OF node for this device.
L
Linus Torvalds 已提交
1184
 *
1185
 * Creates and initializes a vio_dev structure from the data in
1186
 * of_node and adds it to the list of virtual devices.
1187 1188
 * Returns a pointer to the created vio_dev or NULL if node has
 * NULL device_type or compatible fields.
L
Linus Torvalds 已提交
1189
 */
1190
struct vio_dev *vio_register_device_node(struct device_node *of_node)
L
Linus Torvalds 已提交
1191
{
1192
	struct vio_dev *viodev;
1193
	const unsigned int *unit_address;
1194 1195 1196 1197

	/* we need the 'device_type' property, in order to match with drivers */
	if (of_node->type == NULL) {
		printk(KERN_WARNING "%s: node %s missing 'device_type'\n",
1198
				__func__,
1199 1200
				of_node->name ? of_node->name : "<unknown>");
		return NULL;
L
Linus Torvalds 已提交
1201
	}
1202

1203
	unit_address = of_get_property(of_node, "reg", NULL);
1204 1205
	if (unit_address == NULL) {
		printk(KERN_WARNING "%s: node %s missing 'reg'\n",
1206
				__func__,
1207 1208 1209 1210 1211 1212 1213 1214 1215
				of_node->name ? of_node->name : "<unknown>");
		return NULL;
	}

	/* allocate a vio_dev for this node */
	viodev = kzalloc(sizeof(struct vio_dev), GFP_KERNEL);
	if (viodev == NULL)
		return NULL;

1216
	viodev->irq = irq_of_parse_and_map(of_node, 0);
1217 1218 1219 1220 1221 1222

	snprintf(viodev->dev.bus_id, BUS_ID_SIZE, "%x", *unit_address);
	viodev->name = of_node->name;
	viodev->type = of_node->type;
	viodev->unit_address = *unit_address;
	if (firmware_has_feature(FW_FEATURE_ISERIES)) {
1223
		unit_address = of_get_property(of_node,
1224 1225 1226 1227
				"linux,unit_address", NULL);
		if (unit_address != NULL)
			viodev->unit_address = *unit_address;
	}
1228
	viodev->dev.archdata.of_node = of_node_get(of_node);
1229 1230 1231 1232 1233

	if (firmware_has_feature(FW_FEATURE_CMO))
		vio_cmo_set_dma_ops(viodev);
	else
		viodev->dev.archdata.dma_ops = &dma_iommu_ops;
1234 1235
	viodev->dev.archdata.dma_data = vio_build_iommu_table(viodev);
	viodev->dev.archdata.numa_node = of_node_to_nid(of_node);
1236 1237 1238 1239 1240

	/* init generic 'struct device' fields: */
	viodev->dev.parent = &vio_bus_device.dev;
	viodev->dev.bus = &vio_bus_type;
	viodev->dev.release = vio_dev_release;
1241 1242

	/* register with generic device framework */
1243 1244
	if (device_register(&viodev->dev)) {
		printk(KERN_ERR "%s: failed to register device %s\n",
1245
				__func__, viodev->dev.bus_id);
1246 1247 1248 1249 1250 1251
		/* XXX free TCE table */
		kfree(viodev);
		return NULL;
	}

	return viodev;
L
Linus Torvalds 已提交
1252
}
1253
EXPORT_SYMBOL(vio_register_device_node);
L
Linus Torvalds 已提交
1254 1255 1256 1257

/**
 * vio_bus_init: - Initialize the virtual IO bus
 */
1258
static int __init vio_bus_init(void)
L
Linus Torvalds 已提交
1259 1260
{
	int err;
1261
	struct device_node *node_vroot;
L
Linus Torvalds 已提交
1262

1263 1264 1265
	if (firmware_has_feature(FW_FEATURE_CMO))
		vio_cmo_sysfs_init();

L
Linus Torvalds 已提交
1266 1267 1268 1269 1270 1271
	err = bus_register(&vio_bus_type);
	if (err) {
		printk(KERN_ERR "failed to register VIO bus\n");
		return err;
	}

1272 1273
	/*
	 * The fake parent of all vio devices, just to give us
1274 1275
	 * a nice directory
	 */
1276
	err = device_register(&vio_bus_device.dev);
L
Linus Torvalds 已提交
1277
	if (err) {
1278
		printk(KERN_WARNING "%s: device_register returned %i\n",
1279
				__func__, err);
L
Linus Torvalds 已提交
1280 1281 1282
		return err;
	}

1283 1284 1285
	if (firmware_has_feature(FW_FEATURE_CMO))
		vio_cmo_bus_init();

1286
	node_vroot = of_find_node_by_name(NULL, "vdevice");
1287 1288 1289 1290 1291 1292 1293 1294
	if (node_vroot) {
		struct device_node *of_node;

		/*
		 * Create struct vio_devices for each virtual device in
		 * the device tree. Drivers will associate with them later.
		 */
		for (of_node = node_vroot->child; of_node != NULL;
1295
				of_node = of_node->sibling)
1296
			vio_register_device_node(of_node);
1297
		of_node_put(node_vroot);
1298 1299
	}

1300 1301
	return 0;
}
1302
__initcall(vio_bus_init);
L
Linus Torvalds 已提交
1303

1304
static ssize_t name_show(struct device *dev,
1305
		struct device_attribute *attr, char *buf)
L
Linus Torvalds 已提交
1306 1307 1308
{
	return sprintf(buf, "%s\n", to_vio_dev(dev)->name);
}
1309 1310 1311 1312

static ssize_t devspec_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
1313
	struct device_node *of_node = dev->archdata.of_node;
1314 1315 1316 1317 1318 1319 1320 1321 1322

	return sprintf(buf, "%s\n", of_node ? of_node->full_name : "none");
}

static struct device_attribute vio_dev_attrs[] = {
	__ATTR_RO(name),
	__ATTR_RO(devspec),
	__ATTR_NULL
};
L
Linus Torvalds 已提交
1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335

void __devinit vio_unregister_device(struct vio_dev *viodev)
{
	device_unregister(&viodev->dev);
}
EXPORT_SYMBOL(vio_unregister_device);

static int vio_bus_match(struct device *dev, struct device_driver *drv)
{
	const struct vio_dev *vio_dev = to_vio_dev(dev);
	struct vio_driver *vio_drv = to_vio_driver(drv);
	const struct vio_device_id *ids = vio_drv->id_table;

1336
	return (ids != NULL) && (vio_match_device(ids, vio_dev) != NULL);
L
Linus Torvalds 已提交
1337 1338
}

1339
static int vio_hotplug(struct device *dev, struct kobj_uevent_env *env)
1340 1341
{
	const struct vio_dev *vio_dev = to_vio_dev(dev);
1342
	struct device_node *dn;
1343
	const char *cp;
1344

1345
	dn = dev->archdata.of_node;
1346
	if (!dn)
1347
		return -ENODEV;
1348
	cp = of_get_property(dn, "compatible", NULL);
1349 1350 1351
	if (!cp)
		return -ENODEV;

1352
	add_uevent_var(env, "MODALIAS=vio:T%sS%s", vio_dev->type, cp);
1353 1354 1355
	return 0;
}

1356
static struct bus_type vio_bus_type = {
L
Linus Torvalds 已提交
1357
	.name = "vio",
1358
	.dev_attrs = vio_dev_attrs,
1359
	.uevent = vio_hotplug,
L
Linus Torvalds 已提交
1360
	.match = vio_bus_match,
1361 1362
	.probe = vio_bus_probe,
	.remove = vio_bus_remove,
L
Linus Torvalds 已提交
1363
};
1364 1365 1366 1367 1368 1369 1370

/**
 * vio_get_attribute: - get attribute for virtual device
 * @vdev:	The vio device to get property.
 * @which:	The property/attribute to be extracted.
 * @length:	Pointer to length of returned data size (unused if NULL).
 *
1371
 * Calls prom.c's of_get_property() to return the value of the
1372 1373 1374 1375
 * attribute specified by @which
*/
const void *vio_get_attribute(struct vio_dev *vdev, char *which, int *length)
{
1376
	return of_get_property(vdev->dev.archdata.of_node, which, length);
1377 1378
}
EXPORT_SYMBOL(vio_get_attribute);
1379 1380 1381 1382 1383

#ifdef CONFIG_PPC_PSERIES
/* vio_find_name() - internal because only vio.c knows how we formatted the
 * kobject name
 */
1384
static struct vio_dev *vio_find_name(const char *name)
1385
{
1386
	struct device *found;
1387

1388
	found = bus_find_device_by_name(&vio_bus_type, NULL, name);
1389 1390 1391
	if (!found)
		return NULL;

1392
	return to_vio_dev(found);
1393 1394 1395 1396 1397 1398 1399 1400
}

/**
 * vio_find_node - find an already-registered vio_dev
 * @vnode: device_node of the virtual device we're looking for
 */
struct vio_dev *vio_find_node(struct device_node *vnode)
{
1401
	const uint32_t *unit_address;
1402 1403 1404
	char kobj_name[BUS_ID_SIZE];

	/* construct the kobject name from the device node */
1405
	unit_address = of_get_property(vnode, "reg", NULL);
1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431
	if (!unit_address)
		return NULL;
	snprintf(kobj_name, BUS_ID_SIZE, "%x", *unit_address);

	return vio_find_name(kobj_name);
}
EXPORT_SYMBOL(vio_find_node);

int vio_enable_interrupts(struct vio_dev *dev)
{
	int rc = h_vio_signal(dev->unit_address, VIO_IRQ_ENABLE);
	if (rc != H_SUCCESS)
		printk(KERN_ERR "vio: Error 0x%x enabling interrupts\n", rc);
	return rc;
}
EXPORT_SYMBOL(vio_enable_interrupts);

int vio_disable_interrupts(struct vio_dev *dev)
{
	int rc = h_vio_signal(dev->unit_address, VIO_IRQ_DISABLE);
	if (rc != H_SUCCESS)
		printk(KERN_ERR "vio: Error 0x%x disabling interrupts\n", rc);
	return rc;
}
EXPORT_SYMBOL(vio_disable_interrupts);
#endif /* CONFIG_PPC_PSERIES */