vmci_context.c 30.7 KB
Newer Older
George Zhang's avatar
George Zhang committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21
/*
 * VMware VMCI Driver
 *
 * Copyright (C) 2012 VMware, Inc. 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 as published by the
 * Free Software Foundation version 2 and no later version.
 *
 * 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.
 */

#include <linux/vmw_vmci_defs.h>
#include <linux/vmw_vmci_api.h>
#include <linux/highmem.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
22
#include <linux/cred.h>
George Zhang's avatar
George Zhang committed
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
#include <linux/slab.h>

#include "vmci_queue_pair.h"
#include "vmci_datagram.h"
#include "vmci_doorbell.h"
#include "vmci_context.h"
#include "vmci_driver.h"
#include "vmci_event.h"

/*
 * List of current VMCI contexts.  Contexts can be added by
 * vmci_ctx_create() and removed via vmci_ctx_destroy().
 * These, along with context lookup, are protected by the
 * list structure's lock.
 */
static struct {
	struct list_head head;
	spinlock_t lock; /* Spinlock for context list operations */
} ctx_list = {
	.head = LIST_HEAD_INIT(ctx_list.head),
	.lock = __SPIN_LOCK_UNLOCKED(ctx_list.lock),
};

/* Used by contexts that did not set up notify flag pointers */
static bool ctx_dummy_notify;

static void ctx_signal_notify(struct vmci_ctx *context)
{
	*context->notify = true;
}

static void ctx_clear_notify(struct vmci_ctx *context)
{
	*context->notify = false;
}

/*
 * If nothing requires the attention of the guest, clears both
 * notify flag and call.
 */
static void ctx_clear_notify_call(struct vmci_ctx *context)
{
	if (context->pending_datagrams == 0 &&
	    vmci_handle_arr_get_size(context->pending_doorbell_array) == 0)
		ctx_clear_notify(context);
}

/*
 * Sets the context's notify flag iff datagrams are pending for this
 * context.  Called from vmci_setup_notify().
 */
void vmci_ctx_check_signal_notify(struct vmci_ctx *context)
{
	spin_lock(&context->lock);
	if (context->pending_datagrams)
		ctx_signal_notify(context);
	spin_unlock(&context->lock);
}

/*
 * Allocates and initializes a VMCI context.
 */
struct vmci_ctx *vmci_ctx_create(u32 cid, u32 priv_flags,
				 uintptr_t event_hnd,
				 int user_version,
				 const struct cred *cred)
{
	struct vmci_ctx *context;
	int error;

	if (cid == VMCI_INVALID_ID) {
		pr_devel("Invalid context ID for VMCI context\n");
		error = -EINVAL;
		goto err_out;
	}

	if (priv_flags & ~VMCI_PRIVILEGE_ALL_FLAGS) {
		pr_devel("Invalid flag (flags=0x%x) for VMCI context\n",
			 priv_flags);
		error = -EINVAL;
		goto err_out;
	}

	if (user_version == 0) {
		pr_devel("Invalid suer_version %d\n", user_version);
		error = -EINVAL;
		goto err_out;
	}

	context = kzalloc(sizeof(*context), GFP_KERNEL);
	if (!context) {
		pr_warn("Failed to allocate memory for VMCI context\n");
		error = -EINVAL;
		goto err_out;
	}

	kref_init(&context->kref);
	spin_lock_init(&context->lock);
	INIT_LIST_HEAD(&context->list_item);
	INIT_LIST_HEAD(&context->datagram_queue);
	INIT_LIST_HEAD(&context->notifier_list);

	/* Initialize host-specific VMCI context. */
	init_waitqueue_head(&context->host_context.wait_queue);

	context->queue_pair_array = vmci_handle_arr_create(0);
	if (!context->queue_pair_array) {
		error = -ENOMEM;
		goto err_free_ctx;
	}

	context->doorbell_array = vmci_handle_arr_create(0);
	if (!context->doorbell_array) {
		error = -ENOMEM;
		goto err_free_qp_array;
	}

	context->pending_doorbell_array = vmci_handle_arr_create(0);
	if (!context->pending_doorbell_array) {
		error = -ENOMEM;
		goto err_free_db_array;
	}

	context->user_version = user_version;

	context->priv_flags = priv_flags;

	if (cred)
		context->cred = get_cred(cred);

	context->notify = &ctx_dummy_notify;
	context->notify_page = NULL;

	/*
	 * If we collide with an existing context we generate a new
	 * and use it instead. The VMX will determine if regeneration
	 * is okay. Since there isn't 4B - 16 VMs running on a given
	 * host, the below loop will terminate.
	 */
	spin_lock(&ctx_list.lock);

	while (vmci_ctx_exists(cid)) {
		/* We reserve the lowest 16 ids for fixed contexts. */
		cid = max(cid, VMCI_RESERVED_CID_LIMIT - 1) + 1;
		if (cid == VMCI_INVALID_ID)
			cid = VMCI_RESERVED_CID_LIMIT;
	}
	context->cid = cid;

	list_add_tail_rcu(&context->list_item, &ctx_list.head);
	spin_unlock(&ctx_list.lock);

	return context;

 err_free_db_array:
	vmci_handle_arr_destroy(context->doorbell_array);
 err_free_qp_array:
	vmci_handle_arr_destroy(context->queue_pair_array);
 err_free_ctx:
	kfree(context);
 err_out:
	return ERR_PTR(error);
}

/*
 * Destroy VMCI context.
 */
void vmci_ctx_destroy(struct vmci_ctx *context)
{
	spin_lock(&ctx_list.lock);
	list_del_rcu(&context->list_item);
	spin_unlock(&ctx_list.lock);
	synchronize_rcu();

	vmci_ctx_put(context);
}

/*
 * Fire notification for all contexts interested in given cid.
 */
static int ctx_fire_notification(u32 context_id, u32 priv_flags)
{
	u32 i, array_size;
	struct vmci_ctx *sub_ctx;
	struct vmci_handle_arr *subscriber_array;
	struct vmci_handle context_handle =
		vmci_make_handle(context_id, VMCI_EVENT_HANDLER);

	/*
	 * We create an array to hold the subscribers we find when
	 * scanning through all contexts.
	 */
	subscriber_array = vmci_handle_arr_create(0);
	if (subscriber_array == NULL)
		return VMCI_ERROR_NO_MEM;

	/*
	 * Scan all contexts to find who is interested in being
	 * notified about given contextID.
	 */
	rcu_read_lock();
	list_for_each_entry_rcu(sub_ctx, &ctx_list.head, list_item) {
		struct vmci_handle_list *node;

		/*
		 * We only deliver notifications of the removal of
		 * contexts, if the two contexts are allowed to
		 * interact.
		 */
		if (vmci_deny_interaction(priv_flags, sub_ctx->priv_flags))
			continue;

		list_for_each_entry_rcu(node, &sub_ctx->notifier_list, node) {
			if (!vmci_handle_is_equal(node->handle, context_handle))
				continue;

			vmci_handle_arr_append_entry(&subscriber_array,
					vmci_make_handle(sub_ctx->cid,
							 VMCI_EVENT_HANDLER));
		}
	}
	rcu_read_unlock();

	/* Fire event to all subscribers. */
	array_size = vmci_handle_arr_get_size(subscriber_array);
	for (i = 0; i < array_size; i++) {
		int result;
		struct vmci_event_ctx ev;

		ev.msg.hdr.dst = vmci_handle_arr_get_entry(subscriber_array, i);
		ev.msg.hdr.src = vmci_make_handle(VMCI_HYPERVISOR_CONTEXT_ID,
						  VMCI_CONTEXT_RESOURCE_ID);
		ev.msg.hdr.payload_size = sizeof(ev) - sizeof(ev.msg.hdr);
		ev.msg.event_data.event = VMCI_EVENT_CTX_REMOVED;
		ev.payload.context_id = context_id;

		result = vmci_datagram_dispatch(VMCI_HYPERVISOR_CONTEXT_ID,
						&ev.msg.hdr, false);
		if (result < VMCI_SUCCESS) {
			pr_devel("Failed to enqueue event datagram (type=%d) for context (ID=0x%x)\n",
				 ev.msg.event_data.event,
				 ev.msg.hdr.dst.context);
			/* We continue to enqueue on next subscriber. */
		}
	}
	vmci_handle_arr_destroy(subscriber_array);

	return VMCI_SUCCESS;
}

/*
 * Returns the current number of pending datagrams. The call may
 * also serve as a synchronization point for the datagram queue,
 * as no enqueue operations can occur concurrently.
 */
int vmci_ctx_pending_datagrams(u32 cid, u32 *pending)
{
	struct vmci_ctx *context;

	context = vmci_ctx_get(cid);
	if (context == NULL)
		return VMCI_ERROR_INVALID_ARGS;

	spin_lock(&context->lock);
	if (pending)
		*pending = context->pending_datagrams;
	spin_unlock(&context->lock);
	vmci_ctx_put(context);

	return VMCI_SUCCESS;
}

/*
 * Queues a VMCI datagram for the appropriate target VM context.
 */
int vmci_ctx_enqueue_datagram(u32 cid, struct vmci_datagram *dg)
{
	struct vmci_datagram_queue_entry *dq_entry;
	struct vmci_ctx *context;
	struct vmci_handle dg_src;
	size_t vmci_dg_size;

	vmci_dg_size = VMCI_DG_SIZE(dg);
	if (vmci_dg_size > VMCI_MAX_DG_SIZE) {
307
		pr_devel("Datagram too large (bytes=%zu)\n", vmci_dg_size);
George Zhang's avatar
George Zhang committed
308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215
		return VMCI_ERROR_INVALID_ARGS;
	}

	/* Get the target VM's VMCI context. */
	context = vmci_ctx_get(cid);
	if (!context) {
		pr_devel("Invalid context (ID=0x%x)\n", cid);
		return VMCI_ERROR_INVALID_ARGS;
	}

	/* Allocate guest call entry and add it to the target VM's queue. */
	dq_entry = kmalloc(sizeof(*dq_entry), GFP_KERNEL);
	if (dq_entry == NULL) {
		pr_warn("Failed to allocate memory for datagram\n");
		vmci_ctx_put(context);
		return VMCI_ERROR_NO_MEM;
	}
	dq_entry->dg = dg;
	dq_entry->dg_size = vmci_dg_size;
	dg_src = dg->src;
	INIT_LIST_HEAD(&dq_entry->list_item);

	spin_lock(&context->lock);

	/*
	 * We put a higher limit on datagrams from the hypervisor.  If
	 * the pending datagram is not from hypervisor, then we check
	 * if enqueueing it would exceed the
	 * VMCI_MAX_DATAGRAM_QUEUE_SIZE limit on the destination.  If
	 * the pending datagram is from hypervisor, we allow it to be
	 * queued at the destination side provided we don't reach the
	 * VMCI_MAX_DATAGRAM_AND_EVENT_QUEUE_SIZE limit.
	 */
	if (context->datagram_queue_size + vmci_dg_size >=
	    VMCI_MAX_DATAGRAM_QUEUE_SIZE &&
	    (!vmci_handle_is_equal(dg_src,
				vmci_make_handle
				(VMCI_HYPERVISOR_CONTEXT_ID,
				 VMCI_CONTEXT_RESOURCE_ID)) ||
	     context->datagram_queue_size + vmci_dg_size >=
	     VMCI_MAX_DATAGRAM_AND_EVENT_QUEUE_SIZE)) {
		spin_unlock(&context->lock);
		vmci_ctx_put(context);
		kfree(dq_entry);
		pr_devel("Context (ID=0x%x) receive queue is full\n", cid);
		return VMCI_ERROR_NO_RESOURCES;
	}

	list_add(&dq_entry->list_item, &context->datagram_queue);
	context->pending_datagrams++;
	context->datagram_queue_size += vmci_dg_size;
	ctx_signal_notify(context);
	wake_up(&context->host_context.wait_queue);
	spin_unlock(&context->lock);
	vmci_ctx_put(context);

	return vmci_dg_size;
}

/*
 * Verifies whether a context with the specified context ID exists.
 * FIXME: utility is dubious as no decisions can be reliably made
 * using this data as context can appear and disappear at any time.
 */
bool vmci_ctx_exists(u32 cid)
{
	struct vmci_ctx *context;
	bool exists = false;

	rcu_read_lock();

	list_for_each_entry_rcu(context, &ctx_list.head, list_item) {
		if (context->cid == cid) {
			exists = true;
			break;
		}
	}

	rcu_read_unlock();
	return exists;
}

/*
 * Retrieves VMCI context corresponding to the given cid.
 */
struct vmci_ctx *vmci_ctx_get(u32 cid)
{
	struct vmci_ctx *c, *context = NULL;

	if (cid == VMCI_INVALID_ID)
		return NULL;

	rcu_read_lock();
	list_for_each_entry_rcu(c, &ctx_list.head, list_item) {
		if (c->cid == cid) {
			/*
			 * The context owner drops its own reference to the
			 * context only after removing it from the list and
			 * waiting for RCU grace period to expire. This
			 * means that we are not about to increase the
			 * reference count of something that is in the
			 * process of being destroyed.
			 */
			context = c;
			kref_get(&context->kref);
			break;
		}
	}
	rcu_read_unlock();

	return context;
}

/*
 * Deallocates all parts of a context data structure. This
 * function doesn't lock the context, because it assumes that
 * the caller was holding the last reference to context.
 */
static void ctx_free_ctx(struct kref *kref)
{
	struct vmci_ctx *context = container_of(kref, struct vmci_ctx, kref);
	struct vmci_datagram_queue_entry *dq_entry, *dq_entry_tmp;
	struct vmci_handle temp_handle;
	struct vmci_handle_list *notifier, *tmp;

	/*
	 * Fire event to all contexts interested in knowing this
	 * context is dying.
	 */
	ctx_fire_notification(context->cid, context->priv_flags);

	/*
	 * Cleanup all queue pair resources attached to context.  If
	 * the VM dies without cleaning up, this code will make sure
	 * that no resources are leaked.
	 */
	temp_handle = vmci_handle_arr_get_entry(context->queue_pair_array, 0);
	while (!vmci_handle_is_equal(temp_handle, VMCI_INVALID_HANDLE)) {
		if (vmci_qp_broker_detach(temp_handle,
					  context) < VMCI_SUCCESS) {
			/*
			 * When vmci_qp_broker_detach() succeeds it
			 * removes the handle from the array.  If
			 * detach fails, we must remove the handle
			 * ourselves.
			 */
			vmci_handle_arr_remove_entry(context->queue_pair_array,
						     temp_handle);
		}
		temp_handle =
		    vmci_handle_arr_get_entry(context->queue_pair_array, 0);
	}

	/*
	 * It is fine to destroy this without locking the callQueue, as
	 * this is the only thread having a reference to the context.
	 */
	list_for_each_entry_safe(dq_entry, dq_entry_tmp,
				 &context->datagram_queue, list_item) {
		WARN_ON(dq_entry->dg_size != VMCI_DG_SIZE(dq_entry->dg));
		list_del(&dq_entry->list_item);
		kfree(dq_entry->dg);
		kfree(dq_entry);
	}

	list_for_each_entry_safe(notifier, tmp,
				 &context->notifier_list, node) {
		list_del(&notifier->node);
		kfree(notifier);
	}

	vmci_handle_arr_destroy(context->queue_pair_array);
	vmci_handle_arr_destroy(context->doorbell_array);
	vmci_handle_arr_destroy(context->pending_doorbell_array);
	vmci_ctx_unset_notify(context);
	if (context->cred)
		put_cred(context->cred);
	kfree(context);
}

/*
 * Drops reference to VMCI context. If this is the last reference to
 * the context it will be deallocated. A context is created with
 * a reference count of one, and on destroy, it is removed from
 * the context list before its reference count is decremented. Thus,
 * if we reach zero, we are sure that nobody else are about to increment
 * it (they need the entry in the context list for that), and so there
 * is no need for locking.
 */
void vmci_ctx_put(struct vmci_ctx *context)
{
	kref_put(&context->kref, ctx_free_ctx);
}

/*
 * Dequeues the next datagram and returns it to caller.
 * The caller passes in a pointer to the max size datagram
 * it can handle and the datagram is only unqueued if the
 * size is less than max_size. If larger max_size is set to
 * the size of the datagram to give the caller a chance to
 * set up a larger buffer for the guestcall.
 */
int vmci_ctx_dequeue_datagram(struct vmci_ctx *context,
			      size_t *max_size,
			      struct vmci_datagram **dg)
{
	struct vmci_datagram_queue_entry *dq_entry;
	struct list_head *list_item;
	int rv;

	/* Dequeue the next datagram entry. */
	spin_lock(&context->lock);
	if (context->pending_datagrams == 0) {
		ctx_clear_notify_call(context);
		spin_unlock(&context->lock);
		pr_devel("No datagrams pending\n");
		return VMCI_ERROR_NO_MORE_DATAGRAMS;
	}

	list_item = context->datagram_queue.next;

	dq_entry =
	    list_entry(list_item, struct vmci_datagram_queue_entry, list_item);

	/* Check size of caller's buffer. */
	if (*max_size < dq_entry->dg_size) {
		*max_size = dq_entry->dg_size;
		spin_unlock(&context->lock);
		pr_devel("Caller's buffer should be at least (size=%u bytes)\n",
			 (u32) *max_size);
		return VMCI_ERROR_NO_MEM;
	}

	list_del(list_item);
	context->pending_datagrams--;
	context->datagram_queue_size -= dq_entry->dg_size;
	if (context->pending_datagrams == 0) {
		ctx_clear_notify_call(context);
		rv = VMCI_SUCCESS;
	} else {
		/*
		 * Return the size of the next datagram.
		 */
		struct vmci_datagram_queue_entry *next_entry;

		list_item = context->datagram_queue.next;
		next_entry =
		    list_entry(list_item, struct vmci_datagram_queue_entry,
			       list_item);

		/*
		 * The following size_t -> int truncation is fine as
		 * the maximum size of a (routable) datagram is 68KB.
		 */
		rv = (int)next_entry->dg_size;
	}
	spin_unlock(&context->lock);

	/* Caller must free datagram. */
	*dg = dq_entry->dg;
	dq_entry->dg = NULL;
	kfree(dq_entry);

	return rv;
}

/*
 * Reverts actions set up by vmci_setup_notify().  Unmaps and unlocks the
 * page mapped/locked by vmci_setup_notify().
 */
void vmci_ctx_unset_notify(struct vmci_ctx *context)
{
	struct page *notify_page;

	spin_lock(&context->lock);

	notify_page = context->notify_page;
	context->notify = &ctx_dummy_notify;
	context->notify_page = NULL;

	spin_unlock(&context->lock);

	if (notify_page) {
		kunmap(notify_page);
		put_page(notify_page);
	}
}

/*
 * Add remote_cid to list of contexts current contexts wants
 * notifications from/about.
 */
int vmci_ctx_add_notification(u32 context_id, u32 remote_cid)
{
	struct vmci_ctx *context;
	struct vmci_handle_list *notifier, *n;
	int result;
	bool exists = false;

	context = vmci_ctx_get(context_id);
	if (!context)
		return VMCI_ERROR_NOT_FOUND;

	if (VMCI_CONTEXT_IS_VM(context_id) && VMCI_CONTEXT_IS_VM(remote_cid)) {
		pr_devel("Context removed notifications for other VMs not supported (src=0x%x, remote=0x%x)\n",
			 context_id, remote_cid);
		result = VMCI_ERROR_DST_UNREACHABLE;
		goto out;
	}

	if (context->priv_flags & VMCI_PRIVILEGE_FLAG_RESTRICTED) {
		result = VMCI_ERROR_NO_ACCESS;
		goto out;
	}

	notifier = kmalloc(sizeof(struct vmci_handle_list), GFP_KERNEL);
	if (!notifier) {
		result = VMCI_ERROR_NO_MEM;
		goto out;
	}

	INIT_LIST_HEAD(&notifier->node);
	notifier->handle = vmci_make_handle(remote_cid, VMCI_EVENT_HANDLER);

	spin_lock(&context->lock);

	list_for_each_entry(n, &context->notifier_list, node) {
		if (vmci_handle_is_equal(n->handle, notifier->handle)) {
			exists = true;
			break;
		}
	}

	if (exists) {
		kfree(notifier);
		result = VMCI_ERROR_ALREADY_EXISTS;
	} else {
		list_add_tail_rcu(&notifier->node, &context->notifier_list);
		context->n_notifiers++;
		result = VMCI_SUCCESS;
	}

	spin_unlock(&context->lock);

 out:
	vmci_ctx_put(context);
	return result;
}

/*
 * Remove remote_cid from current context's list of contexts it is
 * interested in getting notifications from/about.
 */
int vmci_ctx_remove_notification(u32 context_id, u32 remote_cid)
{
	struct vmci_ctx *context;
	struct vmci_handle_list *notifier, *tmp;
	struct vmci_handle handle;
	bool found = false;

	context = vmci_ctx_get(context_id);
	if (!context)
		return VMCI_ERROR_NOT_FOUND;

	handle = vmci_make_handle(remote_cid, VMCI_EVENT_HANDLER);

	spin_lock(&context->lock);
	list_for_each_entry_safe(notifier, tmp,
				 &context->notifier_list, node) {
		if (vmci_handle_is_equal(notifier->handle, handle)) {
			list_del_rcu(&notifier->node);
			context->n_notifiers--;
			found = true;
			break;
		}
	}
	spin_unlock(&context->lock);

	if (found) {
		synchronize_rcu();
		kfree(notifier);
	}

	vmci_ctx_put(context);

	return found ? VMCI_SUCCESS : VMCI_ERROR_NOT_FOUND;
}

static int vmci_ctx_get_chkpt_notifiers(struct vmci_ctx *context,
					u32 *buf_size, void **pbuf)
{
	u32 *notifiers;
	size_t data_size;
	struct vmci_handle_list *entry;
	int i = 0;

	if (context->n_notifiers == 0) {
		*buf_size = 0;
		*pbuf = NULL;
		return VMCI_SUCCESS;
	}

	data_size = context->n_notifiers * sizeof(*notifiers);
	if (*buf_size < data_size) {
		*buf_size = data_size;
		return VMCI_ERROR_MORE_DATA;
	}

	notifiers = kmalloc(data_size, GFP_ATOMIC); /* FIXME: want GFP_KERNEL */
	if (!notifiers)
		return VMCI_ERROR_NO_MEM;

	list_for_each_entry(entry, &context->notifier_list, node)
		notifiers[i++] = entry->handle.context;

	*buf_size = data_size;
	*pbuf = notifiers;
	return VMCI_SUCCESS;
}

static int vmci_ctx_get_chkpt_doorbells(struct vmci_ctx *context,
					u32 *buf_size, void **pbuf)
{
	struct dbell_cpt_state *dbells;
	size_t n_doorbells;
	int i;

	n_doorbells = vmci_handle_arr_get_size(context->doorbell_array);
	if (n_doorbells > 0) {
		size_t data_size = n_doorbells * sizeof(*dbells);
		if (*buf_size < data_size) {
			*buf_size = data_size;
			return VMCI_ERROR_MORE_DATA;
		}

		dbells = kmalloc(data_size, GFP_ATOMIC);
		if (!dbells)
			return VMCI_ERROR_NO_MEM;

		for (i = 0; i < n_doorbells; i++)
			dbells[i].handle = vmci_handle_arr_get_entry(
						context->doorbell_array, i);

		*buf_size = data_size;
		*pbuf = dbells;
	} else {
		*buf_size = 0;
		*pbuf = NULL;
	}

	return VMCI_SUCCESS;
}

/*
 * Get current context's checkpoint state of given type.
 */
int vmci_ctx_get_chkpt_state(u32 context_id,
			     u32 cpt_type,
			     u32 *buf_size,
			     void **pbuf)
{
	struct vmci_ctx *context;
	int result;

	context = vmci_ctx_get(context_id);
	if (!context)
		return VMCI_ERROR_NOT_FOUND;

	spin_lock(&context->lock);

	switch (cpt_type) {
	case VMCI_NOTIFICATION_CPT_STATE:
		result = vmci_ctx_get_chkpt_notifiers(context, buf_size, pbuf);
		break;

	case VMCI_WELLKNOWN_CPT_STATE:
		/*
		 * For compatibility with VMX'en with VM to VM communication, we
		 * always return zero wellknown handles.
		 */

		*buf_size = 0;
		*pbuf = NULL;
		result = VMCI_SUCCESS;
		break;

	case VMCI_DOORBELL_CPT_STATE:
		result = vmci_ctx_get_chkpt_doorbells(context, buf_size, pbuf);
		break;

	default:
		pr_devel("Invalid cpt state (type=%d)\n", cpt_type);
		result = VMCI_ERROR_INVALID_ARGS;
		break;
	}

	spin_unlock(&context->lock);
	vmci_ctx_put(context);

	return result;
}

/*
 * Set current context's checkpoint state of given type.
 */
int vmci_ctx_set_chkpt_state(u32 context_id,
			     u32 cpt_type,
			     u32 buf_size,
			     void *cpt_buf)
{
	u32 i;
	u32 current_id;
	int result = VMCI_SUCCESS;
	u32 num_ids = buf_size / sizeof(u32);

	if (cpt_type == VMCI_WELLKNOWN_CPT_STATE && num_ids > 0) {
		/*
		 * We would end up here if VMX with VM to VM communication
		 * attempts to restore a checkpoint with wellknown handles.
		 */
		pr_warn("Attempt to restore checkpoint with obsolete wellknown handles\n");
		return VMCI_ERROR_OBSOLETE;
	}

	if (cpt_type != VMCI_NOTIFICATION_CPT_STATE) {
		pr_devel("Invalid cpt state (type=%d)\n", cpt_type);
		return VMCI_ERROR_INVALID_ARGS;
	}

	for (i = 0; i < num_ids && result == VMCI_SUCCESS; i++) {
		current_id = ((u32 *)cpt_buf)[i];
		result = vmci_ctx_add_notification(context_id, current_id);
		if (result != VMCI_SUCCESS)
			break;
	}
	if (result != VMCI_SUCCESS)
		pr_devel("Failed to set cpt state (type=%d) (error=%d)\n",
			 cpt_type, result);

	return result;
}

/*
 * Retrieves the specified context's pending notifications in the
 * form of a handle array. The handle arrays returned are the
 * actual data - not a copy and should not be modified by the
 * caller. They must be released using
 * vmci_ctx_rcv_notifications_release.
 */
int vmci_ctx_rcv_notifications_get(u32 context_id,
				   struct vmci_handle_arr **db_handle_array,
				   struct vmci_handle_arr **qp_handle_array)
{
	struct vmci_ctx *context;
	int result = VMCI_SUCCESS;

	context = vmci_ctx_get(context_id);
	if (context == NULL)
		return VMCI_ERROR_NOT_FOUND;

	spin_lock(&context->lock);

	*db_handle_array = context->pending_doorbell_array;
	context->pending_doorbell_array = vmci_handle_arr_create(0);
	if (!context->pending_doorbell_array) {
		context->pending_doorbell_array = *db_handle_array;
		*db_handle_array = NULL;
		result = VMCI_ERROR_NO_MEM;
	}
	*qp_handle_array = NULL;

	spin_unlock(&context->lock);
	vmci_ctx_put(context);

	return result;
}

/*
 * Releases handle arrays with pending notifications previously
 * retrieved using vmci_ctx_rcv_notifications_get. If the
 * notifications were not successfully handed over to the guest,
 * success must be false.
 */
void vmci_ctx_rcv_notifications_release(u32 context_id,
					struct vmci_handle_arr *db_handle_array,
					struct vmci_handle_arr *qp_handle_array,
					bool success)
{
	struct vmci_ctx *context = vmci_ctx_get(context_id);

	spin_lock(&context->lock);
	if (!success) {
		struct vmci_handle handle;

		/*
		 * New notifications may have been added while we were not
		 * holding the context lock, so we transfer any new pending
		 * doorbell notifications to the old array, and reinstate the
		 * old array.
		 */

		handle = vmci_handle_arr_remove_tail(
					context->pending_doorbell_array);
		while (!vmci_handle_is_invalid(handle)) {
			if (!vmci_handle_arr_has_entry(db_handle_array,
						       handle)) {
				vmci_handle_arr_append_entry(
						&db_handle_array, handle);
			}
			handle = vmci_handle_arr_remove_tail(
					context->pending_doorbell_array);
		}
		vmci_handle_arr_destroy(context->pending_doorbell_array);
		context->pending_doorbell_array = db_handle_array;
		db_handle_array = NULL;
	} else {
		ctx_clear_notify_call(context);
	}
	spin_unlock(&context->lock);
	vmci_ctx_put(context);

	if (db_handle_array)
		vmci_handle_arr_destroy(db_handle_array);

	if (qp_handle_array)
		vmci_handle_arr_destroy(qp_handle_array);
}

/*
 * Registers that a new doorbell handle has been allocated by the
 * context. Only doorbell handles registered can be notified.
 */
int vmci_ctx_dbell_create(u32 context_id, struct vmci_handle handle)
{
	struct vmci_ctx *context;
	int result;

	if (context_id == VMCI_INVALID_ID || vmci_handle_is_invalid(handle))
		return VMCI_ERROR_INVALID_ARGS;

	context = vmci_ctx_get(context_id);
	if (context == NULL)
		return VMCI_ERROR_NOT_FOUND;

	spin_lock(&context->lock);
	if (!vmci_handle_arr_has_entry(context->doorbell_array, handle)) {
		vmci_handle_arr_append_entry(&context->doorbell_array, handle);
		result = VMCI_SUCCESS;
	} else {
		result = VMCI_ERROR_DUPLICATE_ENTRY;
	}

	spin_unlock(&context->lock);
	vmci_ctx_put(context);

	return result;
}

/*
 * Unregisters a doorbell handle that was previously registered
 * with vmci_ctx_dbell_create.
 */
int vmci_ctx_dbell_destroy(u32 context_id, struct vmci_handle handle)
{
	struct vmci_ctx *context;
	struct vmci_handle removed_handle;

	if (context_id == VMCI_INVALID_ID || vmci_handle_is_invalid(handle))
		return VMCI_ERROR_INVALID_ARGS;

	context = vmci_ctx_get(context_id);
	if (context == NULL)
		return VMCI_ERROR_NOT_FOUND;

	spin_lock(&context->lock);
	removed_handle =
	    vmci_handle_arr_remove_entry(context->doorbell_array, handle);
	vmci_handle_arr_remove_entry(context->pending_doorbell_array, handle);
	spin_unlock(&context->lock);

	vmci_ctx_put(context);

	return vmci_handle_is_invalid(removed_handle) ?
	    VMCI_ERROR_NOT_FOUND : VMCI_SUCCESS;
}

/*
 * Unregisters all doorbell handles that were previously
 * registered with vmci_ctx_dbell_create.
 */
int vmci_ctx_dbell_destroy_all(u32 context_id)
{
	struct vmci_ctx *context;
	struct vmci_handle handle;

	if (context_id == VMCI_INVALID_ID)
		return VMCI_ERROR_INVALID_ARGS;

	context = vmci_ctx_get(context_id);
	if (context == NULL)
		return VMCI_ERROR_NOT_FOUND;

	spin_lock(&context->lock);
	do {
		struct vmci_handle_arr *arr = context->doorbell_array;
		handle = vmci_handle_arr_remove_tail(arr);
	} while (!vmci_handle_is_invalid(handle));
	do {
		struct vmci_handle_arr *arr = context->pending_doorbell_array;
		handle = vmci_handle_arr_remove_tail(arr);
	} while (!vmci_handle_is_invalid(handle));
	spin_unlock(&context->lock);

	vmci_ctx_put(context);

	return VMCI_SUCCESS;
}

/*
 * Registers a notification of a doorbell handle initiated by the
 * specified source context. The notification of doorbells are
 * subject to the same isolation rules as datagram delivery. To
 * allow host side senders of notifications a finer granularity
 * of sender rights than those assigned to the sending context
 * itself, the host context is required to specify a different
 * set of privilege flags that will override the privileges of
 * the source context.
 */
int vmci_ctx_notify_dbell(u32 src_cid,
			  struct vmci_handle handle,
			  u32 src_priv_flags)
{
	struct vmci_ctx *dst_context;
	int result;

	if (vmci_handle_is_invalid(handle))
		return VMCI_ERROR_INVALID_ARGS;

	/* Get the target VM's VMCI context. */
	dst_context = vmci_ctx_get(handle.context);
	if (!dst_context) {
		pr_devel("Invalid context (ID=0x%x)\n", handle.context);
		return VMCI_ERROR_NOT_FOUND;
	}

	if (src_cid != handle.context) {
		u32 dst_priv_flags;

		if (VMCI_CONTEXT_IS_VM(src_cid) &&
		    VMCI_CONTEXT_IS_VM(handle.context)) {
			pr_devel("Doorbell notification from VM to VM not supported (src=0x%x, dst=0x%x)\n",
				 src_cid, handle.context);
			result = VMCI_ERROR_DST_UNREACHABLE;
			goto out;
		}

		result = vmci_dbell_get_priv_flags(handle, &dst_priv_flags);
		if (result < VMCI_SUCCESS) {
			pr_warn("Failed to get privilege flags for destination (handle=0x%x:0x%x)\n",
				handle.context, handle.resource);
			goto out;
		}

		if (src_cid != VMCI_HOST_CONTEXT_ID ||
		    src_priv_flags == VMCI_NO_PRIVILEGE_FLAGS) {
			src_priv_flags = vmci_context_get_priv_flags(src_cid);
		}

		if (vmci_deny_interaction(src_priv_flags, dst_priv_flags)) {
			result = VMCI_ERROR_NO_ACCESS;
			goto out;
		}
	}

	if (handle.context == VMCI_HOST_CONTEXT_ID) {
		result = vmci_dbell_host_context_notify(src_cid, handle);
	} else {
		spin_lock(&dst_context->lock);

		if (!vmci_handle_arr_has_entry(dst_context->doorbell_array,
					       handle)) {
			result = VMCI_ERROR_NOT_FOUND;
		} else {
			if (!vmci_handle_arr_has_entry(
					dst_context->pending_doorbell_array,
					handle)) {
				vmci_handle_arr_append_entry(
					&dst_context->pending_doorbell_array,
					handle);

				ctx_signal_notify(dst_context);
				wake_up(&dst_context->host_context.wait_queue);

			}
			result = VMCI_SUCCESS;
		}
		spin_unlock(&dst_context->lock);
	}

 out:
	vmci_ctx_put(dst_context);

	return result;
}

bool vmci_ctx_supports_host_qp(struct vmci_ctx *context)
{
	return context && context->user_version >= VMCI_VERSION_HOSTQP;
}

/*
 * Registers that a new queue pair handle has been allocated by
 * the context.
 */
int vmci_ctx_qp_create(struct vmci_ctx *context, struct vmci_handle handle)
{
	int result;

	if (context == NULL || vmci_handle_is_invalid(handle))
		return VMCI_ERROR_INVALID_ARGS;

	if (!vmci_handle_arr_has_entry(context->queue_pair_array, handle)) {
		vmci_handle_arr_append_entry(&context->queue_pair_array,
					     handle);
		result = VMCI_SUCCESS;
	} else {
		result = VMCI_ERROR_DUPLICATE_ENTRY;
	}

	return result;
}

/*
 * Unregisters a queue pair handle that was previously registered
 * with vmci_ctx_qp_create.
 */
int vmci_ctx_qp_destroy(struct vmci_ctx *context, struct vmci_handle handle)
{
	struct vmci_handle hndl;

	if (context == NULL || vmci_handle_is_invalid(handle))
		return VMCI_ERROR_INVALID_ARGS;

	hndl = vmci_handle_arr_remove_entry(context->queue_pair_array, handle);

	return vmci_handle_is_invalid(hndl) ?
		VMCI_ERROR_NOT_FOUND : VMCI_SUCCESS;
}

/*
 * Determines whether a given queue pair handle is registered
 * with the given context.
 */
bool vmci_ctx_qp_exists(struct vmci_ctx *context, struct vmci_handle handle)
{
	if (context == NULL || vmci_handle_is_invalid(handle))
		return false;

	return vmci_handle_arr_has_entry(context->queue_pair_array, handle);
}

/*
 * vmci_context_get_priv_flags() - Retrieve privilege flags.
 * @context_id: The context ID of the VMCI context.
 *
 * Retrieves privilege flags of the given VMCI context ID.
 */
u32 vmci_context_get_priv_flags(u32 context_id)
{
	if (vmci_host_code_active()) {
		u32 flags;
		struct vmci_ctx *context;

		context = vmci_ctx_get(context_id);
		if (!context)
			return VMCI_LEAST_PRIVILEGE_FLAGS;

		flags = context->priv_flags;
		vmci_ctx_put(context);
		return flags;
	}
	return VMCI_NO_PRIVILEGE_FLAGS;
}
EXPORT_SYMBOL_GPL(vmci_context_get_priv_flags);

/*
 * vmci_is_context_owner() - Determimnes if user is the context owner
 * @context_id: The context ID of the VMCI context.
 * @uid:        The host user id (real kernel value).
 *
 * Determines whether a given UID is the owner of given VMCI context.
 */
bool vmci_is_context_owner(u32 context_id, kuid_t uid)
{
	bool is_owner = false;

	if (vmci_host_code_active()) {
		struct vmci_ctx *context = vmci_ctx_get(context_id);
		if (context) {
			if (context->cred)
				is_owner = uid_eq(context->cred->uid, uid);
			vmci_ctx_put(context);
		}
	}

	return is_owner;
}
EXPORT_SYMBOL_GPL(vmci_is_context_owner);