pvcalls-front.c 31.9 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * (c) 2017 Stefano Stabellini <stefano@aporeto.com>
 */

#include <linux/module.h>
#include <linux/net.h>
#include <linux/socket.h>

#include <net/sock.h>

#include <xen/events.h>
#include <xen/grant_table.h>
#include <xen/xen.h>
#include <xen/xenbus.h>
#include <xen/interface/io/pvcalls.h>

#include "pvcalls-front.h"

#define PVCALLS_INVALID_ID UINT_MAX
#define PVCALLS_RING_ORDER XENBUS_MAX_RING_GRANT_ORDER
#define PVCALLS_NR_RSP_PER_RING __CONST_RING_SIZE(xen_pvcalls, XEN_PAGE_SIZE)
#define PVCALLS_FRONT_MAX_SPIN 5000

static struct proto pvcalls_proto = {
	.name	= "PVCalls",
	.owner	= THIS_MODULE,
	.obj_size = sizeof(struct sock),
};

struct pvcalls_bedata {
	struct xen_pvcalls_front_ring ring;
	grant_ref_t ref;
	int irq;

	struct list_head socket_mappings;
	spinlock_t socket_lock;

	wait_queue_head_t inflight_req;
	struct xen_pvcalls_response rsp[PVCALLS_NR_RSP_PER_RING];
};
/* Only one front/back connection supported. */
static struct xenbus_device *pvcalls_front_dev;
static atomic_t pvcalls_refcount;

/* first increment refcount, then proceed */
#define pvcalls_enter() {               \
	atomic_inc(&pvcalls_refcount);      \
}

/* first complete other operations, then decrement refcount */
#define pvcalls_exit() {                \
	atomic_dec(&pvcalls_refcount);      \
}

struct sock_mapping {
	bool active_socket;
	struct list_head list;
	struct socket *sock;
	atomic_t refcount;
	union {
		struct {
			int irq;
			grant_ref_t ref;
			struct pvcalls_data_intf *ring;
			struct pvcalls_data data;
			struct mutex in_mutex;
			struct mutex out_mutex;

			wait_queue_head_t inflight_conn_req;
		} active;
		struct {
		/*
		 * Socket status, needs to be 64-bit aligned due to the
		 * test_and_* functions which have this requirement on arm64.
		 */
#define PVCALLS_STATUS_UNINITALIZED  0
#define PVCALLS_STATUS_BIND          1
#define PVCALLS_STATUS_LISTEN        2
			uint8_t status __attribute__((aligned(8)));
		/*
		 * Internal state-machine flags.
		 * Only one accept operation can be inflight for a socket.
		 * Only one poll operation can be inflight for a given socket.
		 * flags needs to be 64-bit aligned due to the test_and_*
		 * functions which have this requirement on arm64.
		 */
#define PVCALLS_FLAG_ACCEPT_INFLIGHT 0
#define PVCALLS_FLAG_POLL_INFLIGHT   1
#define PVCALLS_FLAG_POLL_RET        2
			uint8_t flags __attribute__((aligned(8)));
			uint32_t inflight_req_id;
			struct sock_mapping *accept_map;
			wait_queue_head_t inflight_accept_req;
		} passive;
	};
};

static inline struct sock_mapping *pvcalls_enter_sock(struct socket *sock)
{
	struct sock_mapping *map;

	if (!pvcalls_front_dev ||
		dev_get_drvdata(&pvcalls_front_dev->dev) == NULL)
		return ERR_PTR(-ENOTCONN);

	map = (struct sock_mapping *)sock->sk->sk_send_head;
	if (map == NULL)
		return ERR_PTR(-ENOTSOCK);

	pvcalls_enter();
	atomic_inc(&map->refcount);
	return map;
}

static inline void pvcalls_exit_sock(struct socket *sock)
{
	struct sock_mapping *map;

	map = (struct sock_mapping *)sock->sk->sk_send_head;
	atomic_dec(&map->refcount);
	pvcalls_exit();
}

static inline int get_request(struct pvcalls_bedata *bedata, int *req_id)
{
	*req_id = bedata->ring.req_prod_pvt & (RING_SIZE(&bedata->ring) - 1);
	if (RING_FULL(&bedata->ring) ||
	    bedata->rsp[*req_id].req_id != PVCALLS_INVALID_ID)
		return -EAGAIN;
	return 0;
}

static bool pvcalls_front_write_todo(struct sock_mapping *map)
{
	struct pvcalls_data_intf *intf = map->active.ring;
	RING_IDX cons, prod, size = XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER);
	int32_t error;

	error = intf->out_error;
	if (error == -ENOTCONN)
		return false;
	if (error != 0)
		return true;

	cons = intf->out_cons;
	prod = intf->out_prod;
	return !!(size - pvcalls_queued(prod, cons, size));
}

static bool pvcalls_front_read_todo(struct sock_mapping *map)
{
	struct pvcalls_data_intf *intf = map->active.ring;
	RING_IDX cons, prod;
	int32_t error;

	cons = intf->in_cons;
	prod = intf->in_prod;
	error = intf->in_error;
	return (error != 0 ||
		pvcalls_queued(prod, cons,
			       XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER)) != 0);
}

static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
{
	struct xenbus_device *dev = dev_id;
	struct pvcalls_bedata *bedata;
	struct xen_pvcalls_response *rsp;
	uint8_t *src, *dst;
	int req_id = 0, more = 0, done = 0;

	if (dev == NULL)
		return IRQ_HANDLED;

	pvcalls_enter();
	bedata = dev_get_drvdata(&dev->dev);
	if (bedata == NULL) {
		pvcalls_exit();
		return IRQ_HANDLED;
	}

again:
	while (RING_HAS_UNCONSUMED_RESPONSES(&bedata->ring)) {
		rsp = RING_GET_RESPONSE(&bedata->ring, bedata->ring.rsp_cons);

		req_id = rsp->req_id;
		if (rsp->cmd == PVCALLS_POLL) {
			struct sock_mapping *map = (struct sock_mapping *)(uintptr_t)
						   rsp->u.poll.id;

			clear_bit(PVCALLS_FLAG_POLL_INFLIGHT,
				  (void *)&map->passive.flags);
			/*
			 * clear INFLIGHT, then set RET. It pairs with
			 * the checks at the beginning of
			 * pvcalls_front_poll_passive.
			 */
			smp_wmb();
			set_bit(PVCALLS_FLAG_POLL_RET,
				(void *)&map->passive.flags);
		} else {
			dst = (uint8_t *)&bedata->rsp[req_id] +
			      sizeof(rsp->req_id);
			src = (uint8_t *)rsp + sizeof(rsp->req_id);
			memcpy(dst, src, sizeof(*rsp) - sizeof(rsp->req_id));
			/*
			 * First copy the rest of the data, then req_id. It is
			 * paired with the barrier when accessing bedata->rsp.
			 */
			smp_wmb();
			bedata->rsp[req_id].req_id = req_id;
		}

		done = 1;
		bedata->ring.rsp_cons++;
	}

	RING_FINAL_CHECK_FOR_RESPONSES(&bedata->ring, more);
	if (more)
		goto again;
	if (done)
		wake_up(&bedata->inflight_req);
	pvcalls_exit();
	return IRQ_HANDLED;
}

static void pvcalls_front_free_map(struct pvcalls_bedata *bedata,
				   struct sock_mapping *map)
{
	int i;

	unbind_from_irqhandler(map->active.irq, map);

	spin_lock(&bedata->socket_lock);
	if (!list_empty(&map->list))
		list_del_init(&map->list);
	spin_unlock(&bedata->socket_lock);

	for (i = 0; i < (1 << PVCALLS_RING_ORDER); i++)
		gnttab_end_foreign_access(map->active.ring->ref[i], 0, 0);
	gnttab_end_foreign_access(map->active.ref, 0, 0);
	free_page((unsigned long)map->active.ring);

	kfree(map);
}

static irqreturn_t pvcalls_front_conn_handler(int irq, void *sock_map)
{
	struct sock_mapping *map = sock_map;

	if (map == NULL)
		return IRQ_HANDLED;

	wake_up_interruptible(&map->active.inflight_conn_req);

	return IRQ_HANDLED;
}

int pvcalls_front_socket(struct socket *sock)
{
	struct pvcalls_bedata *bedata;
	struct sock_mapping *map = NULL;
	struct xen_pvcalls_request *req;
	int notify, req_id, ret;

	/*
	 * PVCalls only supports domain AF_INET,
	 * type SOCK_STREAM and protocol 0 sockets for now.
	 *
	 * Check socket type here, AF_INET and protocol checks are done
	 * by the caller.
	 */
	if (sock->type != SOCK_STREAM)
		return -EOPNOTSUPP;

	pvcalls_enter();
	if (!pvcalls_front_dev) {
		pvcalls_exit();
		return -EACCES;
	}
	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);

	map = kzalloc(sizeof(*map), GFP_KERNEL);
	if (map == NULL) {
		pvcalls_exit();
		return -ENOMEM;
	}

	spin_lock(&bedata->socket_lock);

	ret = get_request(bedata, &req_id);
	if (ret < 0) {
		kfree(map);
		spin_unlock(&bedata->socket_lock);
		pvcalls_exit();
		return ret;
	}

	/*
	 * sock->sk->sk_send_head is not used for ip sockets: reuse the
	 * field to store a pointer to the struct sock_mapping
	 * corresponding to the socket. This way, we can easily get the
	 * struct sock_mapping from the struct socket.
	 */
	sock->sk->sk_send_head = (void *)map;
	list_add_tail(&map->list, &bedata->socket_mappings);

	req = RING_GET_REQUEST(&bedata->ring, req_id);
	req->req_id = req_id;
	req->cmd = PVCALLS_SOCKET;
	req->u.socket.id = (uintptr_t) map;
	req->u.socket.domain = AF_INET;
	req->u.socket.type = SOCK_STREAM;
	req->u.socket.protocol = IPPROTO_IP;

	bedata->ring.req_prod_pvt++;
	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
	spin_unlock(&bedata->socket_lock);
	if (notify)
		notify_remote_via_irq(bedata->irq);

	wait_event(bedata->inflight_req,
		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);

	/* read req_id, then the content */
	smp_rmb();
	ret = bedata->rsp[req_id].ret;
	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;

	pvcalls_exit();
	return ret;
}

static void free_active_ring(struct sock_mapping *map)
{
	if (!map->active.ring)
		return;

	free_pages((unsigned long)map->active.data.in,
			map->active.ring->ring_order);
	free_page((unsigned long)map->active.ring);
}

static int alloc_active_ring(struct sock_mapping *map)
{
	void *bytes;

	map->active.ring = (struct pvcalls_data_intf *)
		get_zeroed_page(GFP_KERNEL);
	if (!map->active.ring)
		goto out;

	map->active.ring->ring_order = PVCALLS_RING_ORDER;
	bytes = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
					PVCALLS_RING_ORDER);
	if (!bytes)
		goto out;

	map->active.data.in = bytes;
	map->active.data.out = bytes +
		XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER);

	return 0;

out:
	free_active_ring(map);
	return -ENOMEM;
}

static int create_active(struct sock_mapping *map, int *evtchn)
{
	void *bytes;
	int ret = -ENOMEM, irq = -1, i;

	*evtchn = -1;
	init_waitqueue_head(&map->active.inflight_conn_req);

	bytes = map->active.data.in;
	for (i = 0; i < (1 << PVCALLS_RING_ORDER); i++)
		map->active.ring->ref[i] = gnttab_grant_foreign_access(
			pvcalls_front_dev->otherend_id,
			pfn_to_gfn(virt_to_pfn(bytes) + i), 0);

	map->active.ref = gnttab_grant_foreign_access(
		pvcalls_front_dev->otherend_id,
		pfn_to_gfn(virt_to_pfn((void *)map->active.ring)), 0);

	ret = xenbus_alloc_evtchn(pvcalls_front_dev, evtchn);
	if (ret)
		goto out_error;
	irq = bind_evtchn_to_irqhandler(*evtchn, pvcalls_front_conn_handler,
					0, "pvcalls-frontend", map);
	if (irq < 0) {
		ret = irq;
		goto out_error;
	}

	map->active.irq = irq;
	map->active_socket = true;
	mutex_init(&map->active.in_mutex);
	mutex_init(&map->active.out_mutex);

	return 0;

out_error:
	if (*evtchn >= 0)
		xenbus_free_evtchn(pvcalls_front_dev, *evtchn);
	return ret;
}

int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
				int addr_len, int flags)
{
	struct pvcalls_bedata *bedata;
	struct sock_mapping *map = NULL;
	struct xen_pvcalls_request *req;
	int notify, req_id, ret, evtchn;

	if (addr->sa_family != AF_INET || sock->type != SOCK_STREAM)
		return -EOPNOTSUPP;

	map = pvcalls_enter_sock(sock);
	if (IS_ERR(map))
		return PTR_ERR(map);

	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
	ret = alloc_active_ring(map);
	if (ret < 0) {
		pvcalls_exit_sock(sock);
		return ret;
	}

	spin_lock(&bedata->socket_lock);
	ret = get_request(bedata, &req_id);
	if (ret < 0) {
		spin_unlock(&bedata->socket_lock);
		free_active_ring(map);
		pvcalls_exit_sock(sock);
		return ret;
	}
	ret = create_active(map, &evtchn);
	if (ret < 0) {
		spin_unlock(&bedata->socket_lock);
		free_active_ring(map);
		pvcalls_exit_sock(sock);
		return ret;
	}

	req = RING_GET_REQUEST(&bedata->ring, req_id);
	req->req_id = req_id;
	req->cmd = PVCALLS_CONNECT;
	req->u.connect.id = (uintptr_t)map;
	req->u.connect.len = addr_len;
	req->u.connect.flags = flags;
	req->u.connect.ref = map->active.ref;
	req->u.connect.evtchn = evtchn;
	memcpy(req->u.connect.addr, addr, sizeof(*addr));

	map->sock = sock;

	bedata->ring.req_prod_pvt++;
	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
	spin_unlock(&bedata->socket_lock);

	if (notify)
		notify_remote_via_irq(bedata->irq);

	wait_event(bedata->inflight_req,
		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);

	/* read req_id, then the content */
	smp_rmb();
	ret = bedata->rsp[req_id].ret;
	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
	pvcalls_exit_sock(sock);
	return ret;
}

static int __write_ring(struct pvcalls_data_intf *intf,
			struct pvcalls_data *data,
			struct iov_iter *msg_iter,
			int len)
{
	RING_IDX cons, prod, size, masked_prod, masked_cons;
	RING_IDX array_size = XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER);
	int32_t error;

	error = intf->out_error;
	if (error < 0)
		return error;
	cons = intf->out_cons;
	prod = intf->out_prod;
	/* read indexes before continuing */
	virt_mb();

	size = pvcalls_queued(prod, cons, array_size);
	if (size > array_size)
		return -EINVAL;
	if (size == array_size)
		return 0;
	if (len > array_size - size)
		len = array_size - size;

	masked_prod = pvcalls_mask(prod, array_size);
	masked_cons = pvcalls_mask(cons, array_size);

	if (masked_prod < masked_cons) {
		len = copy_from_iter(data->out + masked_prod, len, msg_iter);
	} else {
		if (len > array_size - masked_prod) {
			int ret = copy_from_iter(data->out + masked_prod,
				       array_size - masked_prod, msg_iter);
			if (ret != array_size - masked_prod) {
				len = ret;
				goto out;
			}
			len = ret + copy_from_iter(data->out, len - ret, msg_iter);
		} else {
			len = copy_from_iter(data->out + masked_prod, len, msg_iter);
		}
	}
out:
	/* write to ring before updating pointer */
	virt_wmb();
	intf->out_prod += len;

	return len;
}

int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg,
			  size_t len)
{
	struct sock_mapping *map;
	int sent, tot_sent = 0;
	int count = 0, flags;

	flags = msg->msg_flags;
	if (flags & (MSG_CONFIRM|MSG_DONTROUTE|MSG_EOR|MSG_OOB))
		return -EOPNOTSUPP;

	map = pvcalls_enter_sock(sock);
	if (IS_ERR(map))
		return PTR_ERR(map);

	mutex_lock(&map->active.out_mutex);
	if ((flags & MSG_DONTWAIT) && !pvcalls_front_write_todo(map)) {
		mutex_unlock(&map->active.out_mutex);
		pvcalls_exit_sock(sock);
		return -EAGAIN;
	}
	if (len > INT_MAX)
		len = INT_MAX;

again:
	count++;
	sent = __write_ring(map->active.ring,
			    &map->active.data, &msg->msg_iter,
			    len);
	if (sent > 0) {
		len -= sent;
		tot_sent += sent;
		notify_remote_via_irq(map->active.irq);
	}
	if (sent >= 0 && len > 0 && count < PVCALLS_FRONT_MAX_SPIN)
		goto again;
	if (sent < 0)
		tot_sent = sent;

	mutex_unlock(&map->active.out_mutex);
	pvcalls_exit_sock(sock);
	return tot_sent;
}

static int __read_ring(struct pvcalls_data_intf *intf,
		       struct pvcalls_data *data,
		       struct iov_iter *msg_iter,
		       size_t len, int flags)
{
	RING_IDX cons, prod, size, masked_prod, masked_cons;
	RING_IDX array_size = XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER);
	int32_t error;

	cons = intf->in_cons;
	prod = intf->in_prod;
	error = intf->in_error;
	/* get pointers before reading from the ring */
	virt_rmb();

	size = pvcalls_queued(prod, cons, array_size);
	masked_prod = pvcalls_mask(prod, array_size);
	masked_cons = pvcalls_mask(cons, array_size);

	if (size == 0)
		return error ?: size;

	if (len > size)
		len = size;

	if (masked_prod > masked_cons) {
		len = copy_to_iter(data->in + masked_cons, len, msg_iter);
	} else {
		if (len > (array_size - masked_cons)) {
			int ret = copy_to_iter(data->in + masked_cons,
				     array_size - masked_cons, msg_iter);
			if (ret != array_size - masked_cons) {
				len = ret;
				goto out;
			}
			len = ret + copy_to_iter(data->in, len - ret, msg_iter);
		} else {
			len = copy_to_iter(data->in + masked_cons, len, msg_iter);
		}
	}
out:
	/* read data from the ring before increasing the index */
	virt_mb();
	if (!(flags & MSG_PEEK))
		intf->in_cons += len;

	return len;
}

int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
		     int flags)
{
	int ret;
	struct sock_mapping *map;

	if (flags & (MSG_CMSG_CLOEXEC|MSG_ERRQUEUE|MSG_OOB|MSG_TRUNC))
		return -EOPNOTSUPP;

	map = pvcalls_enter_sock(sock);
	if (IS_ERR(map))
		return PTR_ERR(map);

	mutex_lock(&map->active.in_mutex);
	if (len > XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER))
		len = XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER);

	while (!(flags & MSG_DONTWAIT) && !pvcalls_front_read_todo(map)) {
		wait_event_interruptible(map->active.inflight_conn_req,
					 pvcalls_front_read_todo(map));
	}
	ret = __read_ring(map->active.ring, &map->active.data,
			  &msg->msg_iter, len, flags);

	if (ret > 0)
		notify_remote_via_irq(map->active.irq);
	if (ret == 0)
		ret = (flags & MSG_DONTWAIT) ? -EAGAIN : 0;
	if (ret == -ENOTCONN)
		ret = 0;

	mutex_unlock(&map->active.in_mutex);
	pvcalls_exit_sock(sock);
	return ret;
}

int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
{
	struct pvcalls_bedata *bedata;
	struct sock_mapping *map = NULL;
	struct xen_pvcalls_request *req;
	int notify, req_id, ret;

	if (addr->sa_family != AF_INET || sock->type != SOCK_STREAM)
		return -EOPNOTSUPP;

	map = pvcalls_enter_sock(sock);
	if (IS_ERR(map))
		return PTR_ERR(map);
	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);

	spin_lock(&bedata->socket_lock);
	ret = get_request(bedata, &req_id);
	if (ret < 0) {
		spin_unlock(&bedata->socket_lock);
		pvcalls_exit_sock(sock);
		return ret;
	}
	req = RING_GET_REQUEST(&bedata->ring, req_id);
	req->req_id = req_id;
	map->sock = sock;
	req->cmd = PVCALLS_BIND;
	req->u.bind.id = (uintptr_t)map;
	memcpy(req->u.bind.addr, addr, sizeof(*addr));
	req->u.bind.len = addr_len;

	init_waitqueue_head(&map->passive.inflight_accept_req);

	map->active_socket = false;

	bedata->ring.req_prod_pvt++;
	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
	spin_unlock(&bedata->socket_lock);
	if (notify)
		notify_remote_via_irq(bedata->irq);

	wait_event(bedata->inflight_req,
		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);

	/* read req_id, then the content */
	smp_rmb();
	ret = bedata->rsp[req_id].ret;
	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;

	map->passive.status = PVCALLS_STATUS_BIND;
	pvcalls_exit_sock(sock);
	return 0;
}

int pvcalls_front_listen(struct socket *sock, int backlog)
{
	struct pvcalls_bedata *bedata;
	struct sock_mapping *map;
	struct xen_pvcalls_request *req;
	int notify, req_id, ret;

	map = pvcalls_enter_sock(sock);
	if (IS_ERR(map))
		return PTR_ERR(map);
	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);

	if (map->passive.status != PVCALLS_STATUS_BIND) {
		pvcalls_exit_sock(sock);
		return -EOPNOTSUPP;
	}

	spin_lock(&bedata->socket_lock);
	ret = get_request(bedata, &req_id);
	if (ret < 0) {
		spin_unlock(&bedata->socket_lock);
		pvcalls_exit_sock(sock);
		return ret;
	}
	req = RING_GET_REQUEST(&bedata->ring, req_id);
	req->req_id = req_id;
	req->cmd = PVCALLS_LISTEN;
	req->u.listen.id = (uintptr_t) map;
	req->u.listen.backlog = backlog;

	bedata->ring.req_prod_pvt++;
	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
	spin_unlock(&bedata->socket_lock);
	if (notify)
		notify_remote_via_irq(bedata->irq);

	wait_event(bedata->inflight_req,
		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);

	/* read req_id, then the content */
	smp_rmb();
	ret = bedata->rsp[req_id].ret;
	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;

	map->passive.status = PVCALLS_STATUS_LISTEN;
	pvcalls_exit_sock(sock);
	return ret;
}

int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
{
	struct pvcalls_bedata *bedata;
	struct sock_mapping *map;
	struct sock_mapping *map2 = NULL;
	struct xen_pvcalls_request *req;
	int notify, req_id, ret, evtchn, nonblock;

	map = pvcalls_enter_sock(sock);
	if (IS_ERR(map))
		return PTR_ERR(map);
	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);

	if (map->passive.status != PVCALLS_STATUS_LISTEN) {
		pvcalls_exit_sock(sock);
		return -EINVAL;
	}

	nonblock = flags & SOCK_NONBLOCK;
	/*
	 * Backend only supports 1 inflight accept request, will return
	 * errors for the others
	 */
	if (test_and_set_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
			     (void *)&map->passive.flags)) {
		req_id = READ_ONCE(map->passive.inflight_req_id);
		if (req_id != PVCALLS_INVALID_ID &&
		    READ_ONCE(bedata->rsp[req_id].req_id) == req_id) {
			map2 = map->passive.accept_map;
			goto received;
		}
		if (nonblock) {
			pvcalls_exit_sock(sock);
			return -EAGAIN;
		}
		if (wait_event_interruptible(map->passive.inflight_accept_req,
			!test_and_set_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
					  (void *)&map->passive.flags))) {
			pvcalls_exit_sock(sock);
			return -EINTR;
		}
	}

	map2 = kzalloc(sizeof(*map2), GFP_KERNEL);
	if (map2 == NULL) {
		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
			  (void *)&map->passive.flags);
		pvcalls_exit_sock(sock);
		return -ENOMEM;
	}
	ret = alloc_active_ring(map2);
	if (ret < 0) {
		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
				(void *)&map->passive.flags);
		kfree(map2);
		pvcalls_exit_sock(sock);
		return ret;
	}
	spin_lock(&bedata->socket_lock);
	ret = get_request(bedata, &req_id);
	if (ret < 0) {
		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
			  (void *)&map->passive.flags);
		spin_unlock(&bedata->socket_lock);
		free_active_ring(map2);
		kfree(map2);
		pvcalls_exit_sock(sock);
		return ret;
	}

	ret = create_active(map2, &evtchn);
	if (ret < 0) {
		free_active_ring(map2);
		kfree(map2);
		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
			  (void *)&map->passive.flags);
		spin_unlock(&bedata->socket_lock);
		pvcalls_exit_sock(sock);
		return ret;
	}
	list_add_tail(&map2->list, &bedata->socket_mappings);

	req = RING_GET_REQUEST(&bedata->ring, req_id);
	req->req_id = req_id;
	req->cmd = PVCALLS_ACCEPT;
	req->u.accept.id = (uintptr_t) map;
	req->u.accept.ref = map2->active.ref;
	req->u.accept.id_new = (uintptr_t) map2;
	req->u.accept.evtchn = evtchn;
	map->passive.accept_map = map2;

	bedata->ring.req_prod_pvt++;
	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
	spin_unlock(&bedata->socket_lock);
	if (notify)
		notify_remote_via_irq(bedata->irq);
	/* We could check if we have received a response before returning. */
	if (nonblock) {
		WRITE_ONCE(map->passive.inflight_req_id, req_id);
		pvcalls_exit_sock(sock);
		return -EAGAIN;
	}

	if (wait_event_interruptible(bedata->inflight_req,
		READ_ONCE(bedata->rsp[req_id].req_id) == req_id)) {
		pvcalls_exit_sock(sock);
		return -EINTR;
	}
	/* read req_id, then the content */
	smp_rmb();

received:
	map2->sock = newsock;
	newsock->sk = sk_alloc(sock_net(sock->sk), PF_INET, GFP_KERNEL, &pvcalls_proto, false);
	if (!newsock->sk) {
		bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
		map->passive.inflight_req_id = PVCALLS_INVALID_ID;
		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
			  (void *)&map->passive.flags);
		pvcalls_front_free_map(bedata, map2);
		pvcalls_exit_sock(sock);
		return -ENOMEM;
	}
	newsock->sk->sk_send_head = (void *)map2;

	ret = bedata->rsp[req_id].ret;
	bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID;
	map->passive.inflight_req_id = PVCALLS_INVALID_ID;

	clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags);
	wake_up(&map->passive.inflight_accept_req);

	pvcalls_exit_sock(sock);
	return ret;
}

static __poll_t pvcalls_front_poll_passive(struct file *file,
					       struct pvcalls_bedata *bedata,
					       struct sock_mapping *map,
					       poll_table *wait)
{
	int notify, req_id, ret;
	struct xen_pvcalls_request *req;

	if (test_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
		     (void *)&map->passive.flags)) {
		uint32_t req_id = READ_ONCE(map->passive.inflight_req_id);

		if (req_id != PVCALLS_INVALID_ID &&
		    READ_ONCE(bedata->rsp[req_id].req_id) == req_id)
			return EPOLLIN | EPOLLRDNORM;

		poll_wait(file, &map->passive.inflight_accept_req, wait);
		return 0;
	}

	if (test_and_clear_bit(PVCALLS_FLAG_POLL_RET,
			       (void *)&map->passive.flags))
		return EPOLLIN | EPOLLRDNORM;

	/*
	 * First check RET, then INFLIGHT. No barriers necessary to
	 * ensure execution ordering because of the conditional
	 * instructions creating control dependencies.
	 */

	if (test_and_set_bit(PVCALLS_FLAG_POLL_INFLIGHT,
			     (void *)&map->passive.flags)) {
		poll_wait(file, &bedata->inflight_req, wait);
		return 0;
	}

	spin_lock(&bedata->socket_lock);
	ret = get_request(bedata, &req_id);
	if (ret < 0) {
		spin_unlock(&bedata->socket_lock);
		return ret;
	}
	req = RING_GET_REQUEST(&bedata->ring, req_id);
	req->req_id = req_id;
	req->cmd = PVCALLS_POLL;
	req->u.poll.id = (uintptr_t) map;

	bedata->ring.req_prod_pvt++;
	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
	spin_unlock(&bedata->socket_lock);
	if (notify)
		notify_remote_via_irq(bedata->irq);

	poll_wait(file, &bedata->inflight_req, wait);
	return 0;
}

static __poll_t pvcalls_front_poll_active(struct file *file,
					      struct pvcalls_bedata *bedata,
					      struct sock_mapping *map,
					      poll_table *wait)
{
	__poll_t mask = 0;
	int32_t in_error, out_error;
	struct pvcalls_data_intf *intf = map->active.ring;

	out_error = intf->out_error;
	in_error = intf->in_error;

	poll_wait(file, &map->active.inflight_conn_req, wait);
	if (pvcalls_front_write_todo(map))
		mask |= EPOLLOUT | EPOLLWRNORM;
	if (pvcalls_front_read_todo(map))
		mask |= EPOLLIN | EPOLLRDNORM;
	if (in_error != 0 || out_error != 0)
		mask |= EPOLLERR;

	return mask;
}

__poll_t pvcalls_front_poll(struct file *file, struct socket *sock,
			       poll_table *wait)
{
	struct pvcalls_bedata *bedata;
	struct sock_mapping *map;
	__poll_t ret;

	map = pvcalls_enter_sock(sock);
	if (IS_ERR(map))
		return EPOLLNVAL;
	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);

	if (map->active_socket)
		ret = pvcalls_front_poll_active(file, bedata, map, wait);
	else
		ret = pvcalls_front_poll_passive(file, bedata, map, wait);
	pvcalls_exit_sock(sock);
	return ret;
}

int pvcalls_front_release(struct socket *sock)
{
	struct pvcalls_bedata *bedata;
	struct sock_mapping *map;
	int req_id, notify, ret;
	struct xen_pvcalls_request *req;

	if (sock->sk == NULL)
		return 0;

	map = pvcalls_enter_sock(sock);
	if (IS_ERR(map)) {
		if (PTR_ERR(map) == -ENOTCONN)
			return -EIO;
		else
			return 0;
	}
	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);

	spin_lock(&bedata->socket_lock);
	ret = get_request(bedata, &req_id);
	if (ret < 0) {
		spin_unlock(&bedata->socket_lock);
		pvcalls_exit_sock(sock);
		return ret;
	}
	sock->sk->sk_send_head = NULL;

	req = RING_GET_REQUEST(&bedata->ring, req_id);
	req->req_id = req_id;
	req->cmd = PVCALLS_RELEASE;
	req->u.release.id = (uintptr_t)map;

	bedata->ring.req_prod_pvt++;
	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
	spin_unlock(&bedata->socket_lock);
	if (notify)
		notify_remote_via_irq(bedata->irq);

	wait_event(bedata->inflight_req,
		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);

	if (map->active_socket) {
		/*
		 * Set in_error and wake up inflight_conn_req to force
		 * recvmsg waiters to exit.
		 */
		map->active.ring->in_error = -EBADF;
		wake_up_interruptible(&map->active.inflight_conn_req);

		/*
		 * We need to make sure that sendmsg/recvmsg on this socket have
		 * not started before we've cleared sk_send_head here. The
		 * easiest way to guarantee this is to see that no pvcalls
		 * (other than us) is in progress on this socket.
		 */
		while (atomic_read(&map->refcount) > 1)
			cpu_relax();

		pvcalls_front_free_map(bedata, map);
	} else {
		wake_up(&bedata->inflight_req);
		wake_up(&map->passive.inflight_accept_req);

		while (atomic_read(&map->refcount) > 1)
			cpu_relax();

		spin_lock(&bedata->socket_lock);
		list_del(&map->list);
		spin_unlock(&bedata->socket_lock);
		if (READ_ONCE(map->passive.inflight_req_id) != PVCALLS_INVALID_ID &&
			READ_ONCE(map->passive.inflight_req_id) != 0) {
			pvcalls_front_free_map(bedata,
					       map->passive.accept_map);
		}
		kfree(map);
	}
	WRITE_ONCE(bedata->rsp[req_id].req_id, PVCALLS_INVALID_ID);

	pvcalls_exit();
	return 0;
}

static const struct xenbus_device_id pvcalls_front_ids[] = {
	{ "pvcalls" },
	{ "" }
};

static int pvcalls_front_remove(struct xenbus_device *dev)
{
	struct pvcalls_bedata *bedata;
	struct sock_mapping *map = NULL, *n;

	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
	dev_set_drvdata(&dev->dev, NULL);
	pvcalls_front_dev = NULL;
	if (bedata->irq >= 0)
		unbind_from_irqhandler(bedata->irq, dev);

	list_for_each_entry_safe(map, n, &bedata->socket_mappings, list) {
		map->sock->sk->sk_send_head = NULL;
		if (map->active_socket) {
			map->active.ring->in_error = -EBADF;
			wake_up_interruptible(&map->active.inflight_conn_req);
		}
	}

	smp_mb();
	while (atomic_read(&pvcalls_refcount) > 0)
		cpu_relax();
	list_for_each_entry_safe(map, n, &bedata->socket_mappings, list) {
		if (map->active_socket) {
			/* No need to lock, refcount is 0 */
			pvcalls_front_free_map(bedata, map);
		} else {
			list_del(&map->list);
			kfree(map);
		}
	}
	if (bedata->ref != -1)
		gnttab_end_foreign_access(bedata->ref, 0, 0);
	kfree(bedata->ring.sring);
	kfree(bedata);
	xenbus_switch_state(dev, XenbusStateClosed);
	return 0;
}

static int pvcalls_front_probe(struct xenbus_device *dev,
			  const struct xenbus_device_id *id)
{
	int ret = -ENOMEM, evtchn, i;
	unsigned int max_page_order, function_calls, len;
	char *versions;
	grant_ref_t gref_head = 0;
	struct xenbus_transaction xbt;
	struct pvcalls_bedata *bedata = NULL;
	struct xen_pvcalls_sring *sring;

	if (pvcalls_front_dev != NULL) {
		dev_err(&dev->dev, "only one PV Calls connection supported\n");
		return -EINVAL;
	}

	versions = xenbus_read(XBT_NIL, dev->otherend, "versions", &len);
	if (IS_ERR(versions))
		return PTR_ERR(versions);
	if (!len)
		return -EINVAL;
	if (strcmp(versions, "1")) {
		kfree(versions);
		return -EINVAL;
	}
	kfree(versions);
	max_page_order = xenbus_read_unsigned(dev->otherend,
					      "max-page-order", 0);
	if (max_page_order < PVCALLS_RING_ORDER)
		return -ENODEV;
	function_calls = xenbus_read_unsigned(dev->otherend,
					      "function-calls", 0);
	/* See XENBUS_FUNCTIONS_CALLS in pvcalls.h */
	if (function_calls != 1)
		return -ENODEV;
	pr_info("%s max-page-order is %u\n", __func__, max_page_order);

	bedata = kzalloc(sizeof(struct pvcalls_bedata), GFP_KERNEL);
	if (!bedata)
		return -ENOMEM;

	dev_set_drvdata(&dev->dev, bedata);
	pvcalls_front_dev = dev;
	init_waitqueue_head(&bedata->inflight_req);
	INIT_LIST_HEAD(&bedata->socket_mappings);
	spin_lock_init(&bedata->socket_lock);
	bedata->irq = -1;
	bedata->ref = -1;

	for (i = 0; i < PVCALLS_NR_RSP_PER_RING; i++)
		bedata->rsp[i].req_id = PVCALLS_INVALID_ID;

	sring = (struct xen_pvcalls_sring *) __get_free_page(GFP_KERNEL |
							     __GFP_ZERO);
	if (!sring)
		goto error;
	SHARED_RING_INIT(sring);
	FRONT_RING_INIT(&bedata->ring, sring, XEN_PAGE_SIZE);

	ret = xenbus_alloc_evtchn(dev, &evtchn);
	if (ret)
		goto error;

	bedata->irq = bind_evtchn_to_irqhandler(evtchn,
						pvcalls_front_event_handler,
						0, "pvcalls-frontend", dev);
	if (bedata->irq < 0) {
		ret = bedata->irq;
		goto error;
	}

	ret = gnttab_alloc_grant_references(1, &gref_head);
	if (ret < 0)
		goto error;
	ret = gnttab_claim_grant_reference(&gref_head);
	if (ret < 0)
		goto error;
	bedata->ref = ret;
	gnttab_grant_foreign_access_ref(bedata->ref, dev->otherend_id,
					virt_to_gfn((void *)sring), 0);

 again:
	ret = xenbus_transaction_start(&xbt);
	if (ret) {
		xenbus_dev_fatal(dev, ret, "starting transaction");
		goto error;
	}
	ret = xenbus_printf(xbt, dev->nodename, "version", "%u", 1);
	if (ret)
		goto error_xenbus;
	ret = xenbus_printf(xbt, dev->nodename, "ring-ref", "%d", bedata->ref);
	if (ret)
		goto error_xenbus;
	ret = xenbus_printf(xbt, dev->nodename, "port", "%u",
			    evtchn);
	if (ret)
		goto error_xenbus;
	ret = xenbus_transaction_end(xbt, 0);
	if (ret) {
		if (ret == -EAGAIN)
			goto again;
		xenbus_dev_fatal(dev, ret, "completing transaction");
		goto error;
	}
	xenbus_switch_state(dev, XenbusStateInitialised);

	return 0;

 error_xenbus:
	xenbus_transaction_end(xbt, 1);
	xenbus_dev_fatal(dev, ret, "writing xenstore");
 error:
	pvcalls_front_remove(dev);
	return ret;
}

static void pvcalls_front_changed(struct xenbus_device *dev,
			    enum xenbus_state backend_state)
{
	switch (backend_state) {
	case XenbusStateReconfiguring:
	case XenbusStateReconfigured:
	case XenbusStateInitialising:
	case XenbusStateInitialised:
	case XenbusStateUnknown:
		break;

	case XenbusStateInitWait:
		break;

	case XenbusStateConnected:
		xenbus_switch_state(dev, XenbusStateConnected);
		break;

	case XenbusStateClosed:
		if (dev->state == XenbusStateClosed)
			break;
		/* Missed the backend's CLOSING state */
		/* fall through */
	case XenbusStateClosing:
		xenbus_frontend_closed(dev);
		break;
	}
}

static struct xenbus_driver pvcalls_front_driver = {
	.ids = pvcalls_front_ids,
	.probe = pvcalls_front_probe,
	.remove = pvcalls_front_remove,
	.otherend_changed = pvcalls_front_changed,
};

static int __init pvcalls_frontend_init(void)
{
	if (!xen_domain())
		return -ENODEV;

	pr_info("Initialising Xen pvcalls frontend driver\n");

	return xenbus_register_frontend(&pvcalls_front_driver);
}

module_init(pvcalls_frontend_init);

MODULE_DESCRIPTION("Xen PV Calls frontend driver");
MODULE_AUTHOR("Stefano Stabellini <sstabellini@kernel.org>");
MODULE_LICENSE("GPL");