aboutsummaryrefslogtreecommitdiffstats
path: root/block/blk-throttle.c
Commit message (Expand)AuthorAge
* block: Rename queue dead flagBart Van Assche2012-12-06
* workqueue: use mod_delayed_work() instead of __cancel + queueTejun Heo2012-08-21
* workqueue: deprecate system_nrt[_freezable]_wqTejun Heo2012-08-20
* block: allocate io_context upfrontTejun Heo2012-06-25
* blkcg: tg_stats_alloc_lock is an irq lockTejun Heo2012-05-23
* Merge tag 'v3.4-rc5' into for-3.5/coreJens Axboe2012-05-01
|\
| * block: use lockdep_assert_held for queue lockingAndi Kleen2012-03-30
* | blkcg: collapse blkcg_policy_ops into blkcg_policyTejun Heo2012-04-20
* | blkcg: embed struct blkg_policy_data in policy specific dataTejun Heo2012-04-20
* | blkcg: mass rename of blkcg APITejun Heo2012-04-20
* | blkcg: remove blkio_group->path[]Tejun Heo2012-04-20
* | blkcg: drop stuff unused after per-queue policy activation updateTejun Heo2012-04-20
* | blkcg: implement per-queue policy activationTejun Heo2012-04-20
* | blkcg: add request_queue->root_blkgTejun Heo2012-04-20
* | blkcg: make blkg_conf_prep() take @pol and return with queue lock heldTejun Heo2012-04-20
* | blkcg: remove static policy ID enumsTejun Heo2012-04-20
* | blkcg: use @pol instead of @plid in update_root_blkg_pd() and blkcg_print_blk...Tejun Heo2012-04-20
* | blkcg: drop BLKCG_STAT_{PRIV|POL|OFF} macrosTejun Heo2012-04-01
* | blkcg: pass around pd->pdata instead of pd itself in prfill functionsTejun Heo2012-04-01
* | blkcg: move blkio_group_conf->iops and ->bps to blk-throttleTejun Heo2012-04-01
* | blkcg: move blkio_group_stats_cpu and friends to blk-throttle.cTejun Heo2012-04-01
* | blkcg: cfq doesn't need per-cpu dispatch statsTejun Heo2012-04-01
* | blkcg: move statistics update code to policiesTejun Heo2012-04-01
* | blkcg: move conf/stat file handling code to policiesTejun Heo2012-04-01
* | blkcg: remove unused @pol and @plid parametersTejun Heo2012-04-01
* | block: make blk-throttle preserve the issuing task on delayed biosTejun Heo2012-03-06
* | block: make block cgroup policies follow bio task associationTejun Heo2012-03-06
* | blkcg: drop unnecessary RCU lockingTejun Heo2012-03-06
* | blkcg: unify blkg's for blkcg policiesTejun Heo2012-03-06
* | blkcg: let blkcg core manage per-queue blkg list and counterTejun Heo2012-03-06
* | blkcg: move per-queue blkg list heads and counters to queue and blkgTejun Heo2012-03-06
* | blkcg: don't use blkg->plid in stat related functionsTejun Heo2012-03-06
* | blkcg: move refcnt to blkcg coreTejun Heo2012-03-06
* | blkcg: let blkcg core handle policy private data allocationTejun Heo2012-03-06
* | blkcg: add blkcg_{init|drain|exit}_queue()Tejun Heo2012-03-06
* | blkcg: let blkio_group point to blkio_cgroup directlyTejun Heo2012-03-06
* | blkcg: kill the mind-bending blkg->devTejun Heo2012-03-06
* | blkcg: don't allow or retain configuration of missing devicesTejun Heo2012-03-06
* | blkcg: factor out blkio_group creationTejun Heo2012-03-06
* | blkcg: use the usual get blkg path for root blkio_groupTejun Heo2012-03-06
* | blkcg: use q and plid instead of opaque void * for blkio_group associationTejun Heo2012-03-06
* | blkcg: update blkg get functions take blkio_cgroup as parameterTejun Heo2012-03-06
* | blkcg: move rcu_read_lock() outside of blkio_group get functionsTejun Heo2012-03-06
* | blkcg: shoot down blkio_groups on elevator switchTejun Heo2012-03-06
* | block: extend queue bypassing to cover blkcg policiesTejun Heo2012-03-06
|/
* block: add blk_queue_dead()Tejun Heo2011-12-13
* blk-throttle: use queue_is_locked() instead of lockdep_is_held()Jens Axboe2011-10-25
* block: fix request_queue lifetime handling by making blk_queue_cleanup() prop...Tejun Heo2011-10-19
* block: reorganize throtl_get_tg() and blk_throtl_bio()Tejun Heo2011-10-19
* block: drop unnecessary blk_get/put_queue() in scsi_cmd_ioctl() and blk_get_tg()Tejun Heo2011-10-19
/a> 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
/*
 * linux/net/sunrpc/xdr.c
 *
 * Generic XDR support.
 *
 * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
 */

#include <linux/module.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/pagemap.h>
#include <linux/errno.h>
#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/msg_prot.h>

/*
 * XDR functions for basic NFS types
 */
__be32 *
xdr_encode_netobj(__be32 *p, const struct xdr_netobj *obj)
{
	unsigned int	quadlen = XDR_QUADLEN(obj->len);

	p[quadlen] = 0;		/* zero trailing bytes */
	*p++ = cpu_to_be32(obj->len);
	memcpy(p, obj->data, obj->len);
	return p + XDR_QUADLEN(obj->len);
}
EXPORT_SYMBOL_GPL(xdr_encode_netobj);

__be32 *
xdr_decode_netobj(__be32 *p, struct xdr_netobj *obj)
{
	unsigned int	len;

	if ((len = be32_to_cpu(*p++)) > XDR_MAX_NETOBJ)
		return NULL;
	obj->len  = len;
	obj->data = (u8 *) p;
	return p + XDR_QUADLEN(len);
}
EXPORT_SYMBOL_GPL(xdr_decode_netobj);

/**
 * xdr_encode_opaque_fixed - Encode fixed length opaque data
 * @p: pointer to current position in XDR buffer.
 * @ptr: pointer to data to encode (or NULL)
 * @nbytes: size of data.
 *
 * Copy the array of data of length nbytes at ptr to the XDR buffer
 * at position p, then align to the next 32-bit boundary by padding
 * with zero bytes (see RFC1832).
 * Note: if ptr is NULL, only the padding is performed.
 *
 * Returns the updated current XDR buffer position
 *
 */
__be32 *xdr_encode_opaque_fixed(__be32 *p, const void *ptr, unsigned int nbytes)
{
	if (likely(nbytes != 0)) {
		unsigned int quadlen = XDR_QUADLEN(nbytes);
		unsigned int padding = (quadlen << 2) - nbytes;

		if (ptr != NULL)
			memcpy(p, ptr, nbytes);
		if (padding != 0)
			memset((char *)p + nbytes, 0, padding);
		p += quadlen;
	}
	return p;
}
EXPORT_SYMBOL_GPL(xdr_encode_opaque_fixed);

/**
 * xdr_encode_opaque - Encode variable length opaque data
 * @p: pointer to current position in XDR buffer.
 * @ptr: pointer to data to encode (or NULL)
 * @nbytes: size of data.
 *
 * Returns the updated current XDR buffer position
 */
__be32 *xdr_encode_opaque(__be32 *p, const void *ptr, unsigned int nbytes)
{
	*p++ = cpu_to_be32(nbytes);
	return xdr_encode_opaque_fixed(p, ptr, nbytes);
}
EXPORT_SYMBOL_GPL(xdr_encode_opaque);

__be32 *
xdr_encode_string(__be32 *p, const char *string)
{
	return xdr_encode_array(p, string, strlen(string));
}
EXPORT_SYMBOL_GPL(xdr_encode_string);

__be32 *
xdr_decode_string_inplace(__be32 *p, char **sp,
			  unsigned int *lenp, unsigned int maxlen)
{
	u32 len;

	len = be32_to_cpu(*p++);
	if (len > maxlen)
		return NULL;
	*lenp = len;
	*sp = (char *) p;
	return p + XDR_QUADLEN(len);
}
EXPORT_SYMBOL_GPL(xdr_decode_string_inplace);

/**
 * xdr_terminate_string - '\0'-terminate a string residing in an xdr_buf
 * @buf: XDR buffer where string resides
 * @len: length of string, in bytes
 *
 */
void
xdr_terminate_string(struct xdr_buf *buf, const u32 len)
{
	char *kaddr;

	kaddr = kmap_atomic(buf->pages[0], KM_USER0);
	kaddr[buf->page_base + len] = '\0';
	kunmap_atomic(kaddr, KM_USER0);
}
EXPORT_SYMBOL(xdr_terminate_string);

void
xdr_encode_pages(struct xdr_buf *xdr, struct page **pages, unsigned int base,
		 unsigned int len)
{
	struct kvec *tail = xdr->tail;
	u32 *p;

	xdr->pages = pages;
	xdr->page_base = base;
	xdr->page_len = len;

	p = (u32 *)xdr->head[0].iov_base + XDR_QUADLEN(xdr->head[0].iov_len);
	tail->iov_base = p;
	tail->iov_len = 0;

	if (len & 3) {
		unsigned int pad = 4 - (len & 3);

		*p = 0;
		tail->iov_base = (char *)p + (len & 3);
		tail->iov_len  = pad;
		len += pad;
	}
	xdr->buflen += len;
	xdr->len += len;
}
EXPORT_SYMBOL_GPL(xdr_encode_pages);

void
xdr_inline_pages(struct xdr_buf *xdr, unsigned int offset,
		 struct page **pages, unsigned int base, unsigned int len)
{
	struct kvec *head = xdr->head;
	struct kvec *tail = xdr->tail;
	char *buf = (char *)head->iov_base;
	unsigned int buflen = head->iov_len;

	head->iov_len  = offset;

	xdr->pages = pages;
	xdr->page_base = base;
	xdr->page_len = len;

	tail->iov_base = buf + offset;
	tail->iov_len = buflen - offset;

	xdr->buflen += len;
}
EXPORT_SYMBOL_GPL(xdr_inline_pages);

/*
 * Helper routines for doing 'memmove' like operations on a struct xdr_buf
 *
 * _shift_data_right_pages
 * @pages: vector of pages containing both the source and dest memory area.
 * @pgto_base: page vector address of destination
 * @pgfrom_base: page vector address of source
 * @len: number of bytes to copy
 *
 * Note: the addresses pgto_base and pgfrom_base are both calculated in
 *       the same way:
 *            if a memory area starts at byte 'base' in page 'pages[i]',
 *            then its address is given as (i << PAGE_CACHE_SHIFT) + base
 * Also note: pgfrom_base must be < pgto_base, but the memory areas
 * 	they point to may overlap.
 */
static void
_shift_data_right_pages(struct page **pages, size_t pgto_base,
		size_t pgfrom_base, size_t len)
{
	struct page **pgfrom, **pgto;
	char *vfrom, *vto;
	size_t copy;

	BUG_ON(pgto_base <= pgfrom_base);

	pgto_base += len;
	pgfrom_base += len;

	pgto = pages + (pgto_base >> PAGE_CACHE_SHIFT);
	pgfrom = pages + (pgfrom_base >> PAGE_CACHE_SHIFT);

	pgto_base &= ~PAGE_CACHE_MASK;
	pgfrom_base &= ~PAGE_CACHE_MASK;

	do {
		/* Are any pointers crossing a page boundary? */
		if (pgto_base == 0) {
			pgto_base = PAGE_CACHE_SIZE;
			pgto--;
		}
		if (pgfrom_base == 0) {
			pgfrom_base = PAGE_CACHE_SIZE;
			pgfrom--;
		}

		copy = len;
		if (copy > pgto_base)
			copy = pgto_base;
		if (copy > pgfrom_base)
			copy = pgfrom_base;
		pgto_base -= copy;
		pgfrom_base -= copy;

		vto = kmap_atomic(*pgto, KM_USER0);
		vfrom = kmap_atomic(*pgfrom, KM_USER1);
		memmove(vto + pgto_base, vfrom + pgfrom_base, copy);
		flush_dcache_page(*pgto);
		kunmap_atomic(vfrom, KM_USER1);
		kunmap_atomic(vto, KM_USER0);

	} while ((len -= copy) != 0);
}

/*
 * _copy_to_pages
 * @pages: array of pages
 * @pgbase: page vector address of destination
 * @p: pointer to source data
 * @len: length
 *
 * Copies data from an arbitrary memory location into an array of pages
 * The copy is assumed to be non-overlapping.
 */
static void
_copy_to_pages(struct page **pages, size_t pgbase, const char *p, size_t len)
{
	struct page **pgto;
	char *vto;
	size_t copy;

	pgto = pages + (pgbase >> PAGE_CACHE_SHIFT);
	pgbase &= ~PAGE_CACHE_MASK;

	for (;;) {
		copy = PAGE_CACHE_SIZE - pgbase;
		if (copy > len)
			copy = len;

		vto = kmap_atomic(*pgto, KM_USER0);
		memcpy(vto + pgbase, p, copy);
		kunmap_atomic(vto, KM_USER0);

		len -= copy;
		if (len == 0)
			break;

		pgbase += copy;
		if (pgbase == PAGE_CACHE_SIZE) {
			flush_dcache_page(*pgto);
			pgbase = 0;
			pgto++;
		}
		p += copy;
	}
	flush_dcache_page(*pgto);
}

/*
 * _copy_from_pages
 * @p: pointer to destination
 * @pages: array of pages
 * @pgbase: offset of source data
 * @len: length
 *
 * Copies data into an arbitrary memory location from an array of pages
 * The copy is assumed to be non-overlapping.
 */
static void
_copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len)
{
	struct page **pgfrom;
	char *vfrom;
	size_t copy;

	pgfrom = pages + (pgbase >> PAGE_CACHE_SHIFT);
	pgbase &= ~PAGE_CACHE_MASK;

	do {
		copy = PAGE_CACHE_SIZE - pgbase;
		if (copy > len)
			copy = len;

		vfrom = kmap_atomic(*pgfrom, KM_USER0);
		memcpy(p, vfrom + pgbase, copy);
		kunmap_atomic(vfrom, KM_USER0);

		pgbase += copy;
		if (pgbase == PAGE_CACHE_SIZE) {
			pgbase = 0;
			pgfrom++;
		}
		p += copy;

	} while ((len -= copy) != 0);
}

/*
 * xdr_shrink_bufhead
 * @buf: xdr_buf
 * @len: bytes to remove from buf->head[0]
 *
 * Shrinks XDR buffer's header kvec buf->head[0] by
 * 'len' bytes. The extra data is not lost, but is instead
 * moved into the inlined pages and/or the tail.
 */
static void
xdr_shrink_bufhead(struct xdr_buf *buf, size_t len)
{
	struct kvec *head, *tail;
	size_t copy, offs;
	unsigned int pglen = buf->page_len;

	tail = buf->tail;
	head = buf->head;
	BUG_ON (len > head->iov_len);

	/* Shift the tail first */
	if (tail->iov_len != 0) {
		if (tail->iov_len > len) {
			copy = tail->iov_len - len;
			memmove((char *)tail->iov_base + len,
					tail->iov_base, copy);
		}
		/* Copy from the inlined pages into the tail */
		copy = len;
		if (copy > pglen)
			copy = pglen;
		offs = len - copy;
		if (offs >= tail->iov_len)
			copy = 0;
		else if (copy > tail->iov_len - offs)
			copy = tail->iov_len - offs;
		if (copy != 0)
			_copy_from_pages((char *)tail->iov_base + offs,
					buf->pages,
					buf->page_base + pglen + offs - len,
					copy);
		/* Do we also need to copy data from the head into the tail ? */
		if (len > pglen) {
			offs = copy = len - pglen;
			if (copy > tail->iov_len)
				copy = tail->iov_len;
			memcpy(tail->iov_base,
					(char *)head->iov_base +
					head->iov_len - offs,
					copy);
		}
	}
	/* Now handle pages */
	if (pglen != 0) {
		if (pglen > len)
			_shift_data_right_pages(buf->pages,
					buf->page_base + len,
					buf->page_base,
					pglen - len);
		copy = len;
		if (len > pglen)
			copy = pglen;
		_copy_to_pages(buf->pages, buf->page_base,
				(char *)head->iov_base + head->iov_len - len,
				copy);
	}
	head->iov_len -= len;
	buf->buflen -= len;
	/* Have we truncated the message? */
	if (buf->len > buf->buflen)
		buf->len = buf->buflen;
}

/*
 * xdr_shrink_pagelen
 * @buf: xdr_buf
 * @len: bytes to remove from buf->pages
 *
 * Shrinks XDR buffer's page array buf->pages by
 * 'len' bytes. The extra data is not lost, but is instead
 * moved into the tail.
 */
static void
xdr_shrink_pagelen(struct xdr_buf *buf, size_t len)
{
	struct kvec *tail;
	size_t copy;
	unsigned int pglen = buf->page_len;
	unsigned int tailbuf_len;

	tail = buf->tail;
	BUG_ON (len > pglen);

	tailbuf_len = buf->buflen - buf->head->iov_len - buf->page_len;

	/* Shift the tail first */
	if (tailbuf_len != 0) {
		unsigned int free_space = tailbuf_len - tail->iov_len;

		if (len < free_space)
			free_space = len;
		tail->iov_len += free_space;

		copy = len;
		if (tail->iov_len > len) {
			char *p = (char *)tail->iov_base + len;
			memmove(p, tail->iov_base, tail->iov_len - len);
		} else
			copy = tail->iov_len;
		/* Copy from the inlined pages into the tail */
		_copy_from_pages((char *)tail->iov_base,
				buf->pages, buf->page_base + pglen - len,
				copy);
	}
	buf->page_len -= len;
	buf->buflen -= len;
	/* Have we truncated the message? */
	if (buf->len > buf->buflen)
		buf->len = buf->buflen;
}

void
xdr_shift_buf(struct xdr_buf *buf, size_t len)
{
	xdr_shrink_bufhead(buf, len);
}
EXPORT_SYMBOL_GPL(xdr_shift_buf);

/**
 * xdr_init_encode - Initialize a struct xdr_stream for sending data.
 * @xdr: pointer to xdr_stream struct
 * @buf: pointer to XDR buffer in which to encode data
 * @p: current pointer inside XDR buffer
 *
 * Note: at the moment the RPC client only passes the length of our
 *	 scratch buffer in the xdr_buf's header kvec. Previously this
 *	 meant we needed to call xdr_adjust_iovec() after encoding the
 *	 data. With the new scheme, the xdr_stream manages the details
 *	 of the buffer length, and takes care of adjusting the kvec
 *	 length for us.
 */
void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p)
{
	struct kvec *iov = buf->head;
	int scratch_len = buf->buflen - buf->page_len - buf->tail[0].iov_len;

	BUG_ON(scratch_len < 0);
	xdr->buf = buf;
	xdr->iov = iov;
	xdr->p = (__be32 *)((char *)iov->iov_base + iov->iov_len);
	xdr->end = (__be32 *)((char *)iov->iov_base + scratch_len);
	BUG_ON(iov->iov_len > scratch_len);

	if (p != xdr->p && p != NULL) {
		size_t len;

		BUG_ON(p < xdr->p || p > xdr->end);
		len = (char *)p - (char *)xdr->p;
		xdr->p = p;
		buf->len += len;
		iov->iov_len += len;
	}
}
EXPORT_SYMBOL_GPL(xdr_init_encode);

/**
 * xdr_reserve_space - Reserve buffer space for sending
 * @xdr: pointer to xdr_stream
 * @nbytes: number of bytes to reserve
 *
 * Checks that we have enough buffer space to encode 'nbytes' more
 * bytes of data. If so, update the total xdr_buf length, and
 * adjust the length of the current kvec.
 */
__be32 * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes)
{
	__be32 *p = xdr->p;
	__be32 *q;

	/* align nbytes on the next 32-bit boundary */
	nbytes += 3;
	nbytes &= ~3;
	q = p + (nbytes >> 2);
	if (unlikely(q > xdr->end || q < p))
		return NULL;
	xdr->p = q;
	xdr->iov->iov_len += nbytes;
	xdr->buf->len += nbytes;
	return p;
}
EXPORT_SYMBOL_GPL(xdr_reserve_space);

/**
 * xdr_write_pages - Insert a list of pages into an XDR buffer for sending
 * @xdr: pointer to xdr_stream
 * @pages: list of pages
 * @base: offset of first byte
 * @len: length of data in bytes
 *
 */
void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int base,
		 unsigned int len)
{
	struct xdr_buf *buf = xdr->buf;
	struct kvec *iov = buf->tail;
	buf->pages = pages;
	buf->page_base = base;
	buf->page_len = len;

	iov->iov_base = (char *)xdr->p;
	iov->iov_len  = 0;
	xdr->iov = iov;

	if (len & 3) {
		unsigned int pad = 4 - (len & 3);

		BUG_ON(xdr->p >= xdr->end);
		iov->iov_base = (char *)xdr->p + (len & 3);
		iov->iov_len  += pad;
		len += pad;
		*xdr->p++ = 0;
	}
	buf->buflen += len;
	buf->len += len;
}
EXPORT_SYMBOL_GPL(xdr_write_pages);

static void xdr_set_iov(struct xdr_stream *xdr, struct kvec *iov,
		__be32 *p, unsigned int len)
{
	if (len > iov->iov_len)
		len = iov->iov_len;
	if (p == NULL)
		p = (__be32*)iov->iov_base;
	xdr->p = p;
	xdr->end = (__be32*)(iov->iov_base + len);
	xdr->iov = iov;
	xdr->page_ptr = NULL;
}

static int xdr_set_page_base(struct xdr_stream *xdr,
		unsigned int base, unsigned int len)
{
	unsigned int pgnr;
	unsigned int maxlen;
	unsigned int pgoff;
	unsigned int pgend;
	void *kaddr;

	maxlen = xdr->buf->page_len;
	if (base >= maxlen)
		return -EINVAL;
	maxlen -= base;
	if (len > maxlen)
		len = maxlen;

	base += xdr->buf->page_base;

	pgnr = base >> PAGE_SHIFT;
	xdr->page_ptr = &xdr->buf->pages[pgnr];
	kaddr = page_address(*xdr->page_ptr);

	pgoff = base & ~PAGE_MASK;
	xdr->p = (__be32*)(kaddr + pgoff);

	pgend = pgoff + len;
	if (pgend > PAGE_SIZE)
		pgend = PAGE_SIZE;
	xdr->end = (__be32*)(kaddr + pgend);
	xdr->iov = NULL;
	return 0;
}

static void xdr_set_next_page(struct xdr_stream *xdr)
{
	unsigned int newbase;

	newbase = (1 + xdr->page_ptr - xdr->buf->pages) << PAGE_SHIFT;
	newbase -= xdr->buf->page_base;

	if (xdr_set_page_base(xdr, newbase, PAGE_SIZE) < 0)
		xdr_set_iov(xdr, xdr->buf->tail, NULL, xdr->buf->len);
}

static bool xdr_set_next_buffer(struct xdr_stream *xdr)
{
	if (xdr->page_ptr != NULL)
		xdr_set_next_page(xdr);
	else if (xdr->iov == xdr->buf->head) {
		if (xdr_set_page_base(xdr, 0, PAGE_SIZE) < 0)
			xdr_set_iov(xdr, xdr->buf->tail, NULL, xdr->buf->len);
	}
	return xdr->p != xdr->end;
}

/**
 * xdr_init_decode - Initialize an xdr_stream for decoding data.
 * @xdr: pointer to xdr_stream struct
 * @buf: pointer to XDR buffer from which to decode data
 * @p: current pointer inside XDR buffer
 */
void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p)
{
	xdr->buf = buf;
	xdr->scratch.iov_base = NULL;
	xdr->scratch.iov_len = 0;
	if (buf->head[0].iov_len != 0)
		xdr_set_iov(xdr, buf->head, p, buf->len);
	else if (buf->page_len != 0)
		xdr_set_page_base(xdr, 0, buf->len);
}
EXPORT_SYMBOL_GPL(xdr_init_decode);

/**
 * xdr_init_decode - Initialize an xdr_stream for decoding data.
 * @xdr: pointer to xdr_stream struct
 * @buf: pointer to XDR buffer from which to decode data
 * @pages: list of pages to decode into
 * @len: length in bytes of buffer in pages
 */
void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
			   struct page **pages, unsigned int len)
{
	memset(buf, 0, sizeof(*buf));
	buf->pages =  pages;
	buf->page_len =  len;
	buf->buflen =  len;
	buf->len = len;
	xdr_init_decode(xdr, buf, NULL);
}
EXPORT_SYMBOL_GPL(xdr_init_decode_pages);

static __be32 * __xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes)
{
	__be32 *p = xdr->p;
	__be32 *q = p + XDR_QUADLEN(nbytes);

	if (unlikely(q > xdr->end || q < p))
		return NULL;
	xdr->p = q;
	return p;
}

/**
 * xdr_set_scratch_buffer - Attach a scratch buffer for decoding data.
 * @xdr: pointer to xdr_stream struct
 * @buf: pointer to an empty buffer
 * @buflen: size of 'buf'
 *
 * The scratch buffer is used when decoding from an array of pages.
 * If an xdr_inline_decode() call spans across page boundaries, then
 * we copy the data into the scratch buffer in order to allow linear
 * access.
 */
void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen)
{
	xdr->scratch.iov_base = buf;
	xdr->scratch.iov_len = buflen;
}
EXPORT_SYMBOL_GPL(xdr_set_scratch_buffer);

static __be32 *xdr_copy_to_scratch(struct xdr_stream *xdr, size_t nbytes)
{
	__be32 *p;
	void *cpdest = xdr->scratch.iov_base;
	size_t cplen = (char *)xdr->end - (char *)xdr->p;

	if (nbytes > xdr->scratch.iov_len)
		return NULL;
	memcpy(cpdest, xdr->p, cplen);
	cpdest += cplen;
	nbytes -= cplen;
	if (!xdr_set_next_buffer(xdr))
		return NULL;
	p = __xdr_inline_decode(xdr, nbytes);
	if (p == NULL)
		return NULL;
	memcpy(cpdest, p, nbytes);
	return xdr->scratch.iov_base;
}

/**
 * xdr_inline_decode - Retrieve XDR data to decode
 * @xdr: pointer to xdr_stream struct
 * @nbytes: number of bytes of data to decode
 *
 * Check if the input buffer is long enough to enable us to decode
 * 'nbytes' more bytes of data starting at the current position.
 * If so return the current pointer, then update the current
 * pointer position.
 */
__be32 * xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes)
{
	__be32 *p;

	if (nbytes == 0)
		return xdr->p;
	if (xdr->p == xdr->end && !xdr_set_next_buffer(xdr))
		return NULL;
	p = __xdr_inline_decode(xdr, nbytes);
	if (p != NULL)
		return p;
	return xdr_copy_to_scratch(xdr, nbytes);
}
EXPORT_SYMBOL_GPL(xdr_inline_decode);

/**
 * xdr_read_pages - Ensure page-based XDR data to decode is aligned at current pointer position
 * @xdr: pointer to xdr_stream struct
 * @len: number of bytes of page data
 *
 * Moves data beyond the current pointer position from the XDR head[] buffer
 * into the page list. Any data that lies beyond current position + "len"
 * bytes is moved into the XDR tail[].
 */
void xdr_read_pages(struct xdr_stream *xdr, unsigned int len)
{
	struct xdr_buf *buf = xdr->buf;
	struct kvec *iov;
	ssize_t shift;
	unsigned int end;
	int padding;

	/* Realign pages to current pointer position */
	iov  = buf->head;
	shift = iov->iov_len + (char *)iov->iov_base - (char *)xdr->p;
	if (shift > 0)
		xdr_shrink_bufhead(buf, shift);

	/* Truncate page data and move it into the tail */
	if (buf->page_len > len)
		xdr_shrink_pagelen(buf, buf->page_len - len);
	padding = (XDR_QUADLEN(len) << 2) - len;
	xdr->iov = iov = buf->tail;
	/* Compute remaining message length.  */
	end = iov->iov_len;
	shift = buf->buflen - buf->len;
	if (shift < end)
		end -= shift;
	else if (shift > 0)
		end = 0;
	/*
	 * Position current pointer at beginning of tail, and
	 * set remaining message length.
	 */
	xdr->p = (__be32 *)((char *)iov->iov_base + padding);
	xdr->end = (__be32 *)((char *)iov->iov_base + end);
}
EXPORT_SYMBOL_GPL(xdr_read_pages);

/**
 * xdr_enter_page - decode data from the XDR page
 * @xdr: pointer to xdr_stream struct
 * @len: number of bytes of page data
 *
 * Moves data beyond the current pointer position from the XDR head[] buffer
 * into the page list. Any data that lies beyond current position + "len"
 * bytes is moved into the XDR tail[]. The current pointer is then
 * repositioned at the beginning of the first XDR page.
 */
void xdr_enter_page(struct xdr_stream *xdr, unsigned int len)
{
	xdr_read_pages(xdr, len);
	/*
	 * Position current pointer at beginning of tail, and
	 * set remaining message length.
	 */
	xdr_set_page_base(xdr, 0, len);
}
EXPORT_SYMBOL_GPL(xdr_enter_page);

static struct kvec empty_iov = {.iov_base = NULL, .iov_len = 0};

void
xdr_buf_from_iov(struct kvec *iov, struct xdr_buf *buf)
{
	buf->head[0] = *iov;
	buf->tail[0] = empty_iov;
	buf->page_len = 0;
	buf->buflen = buf->len = iov->iov_len;
}
EXPORT_SYMBOL_GPL(xdr_buf_from_iov);

/* Sets subbuf to the portion of buf of length len beginning base bytes
 * from the start of buf. Returns -1 if base of length are out of bounds. */
int
xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
			unsigned int base, unsigned int len)
{
	subbuf->buflen = subbuf->len = len;
	if (base < buf->head[0].iov_len) {
		subbuf->head[0].iov_base = buf->head[0].iov_base + base;
		subbuf->head[0].iov_len = min_t(unsigned int, len,
						buf->head[0].iov_len - base);
		len -= subbuf->head[0].iov_len;
		base = 0;
	} else {
		subbuf->head[0].iov_base = NULL;
		subbuf->head[0].iov_len = 0;
		base -= buf->head[0].iov_len;
	}

	if (base < buf->page_len) {
		subbuf->page_len = min(buf->page_len - base, len);
		base += buf->page_base;
		subbuf->page_base = base & ~PAGE_CACHE_MASK;
		subbuf->pages = &buf->pages[base >> PAGE_CACHE_SHIFT];
		len -= subbuf->page_len;
		base = 0;
	} else {
		base -= buf->page_len;
		subbuf->page_len = 0;
	}

	if (base < buf->tail[0].iov_len) {
		subbuf->tail[0].iov_base = buf->tail[0].iov_base + base;
		subbuf->tail[0].iov_len = min_t(unsigned int, len,
						buf->tail[0].iov_len - base);
		len -= subbuf->tail[0].iov_len;
		base = 0;
	} else {
		subbuf->tail[0].iov_base = NULL;
		subbuf->tail[0].iov_len = 0;
		base -= buf->tail[0].iov_len;
	}

	if (base || len)
		return -1;
	return 0;
}
EXPORT_SYMBOL_GPL(xdr_buf_subsegment);

static void __read_bytes_from_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned int len)
{
	unsigned int this_len;

	this_len = min_t(unsigned int, len, subbuf->head[0].iov_len);
	memcpy(obj, subbuf->head[0].iov_base, this_len);
	len -= this_len;
	obj += this_len;
	this_len = min_t(unsigned int, len, subbuf->page_len);
	if (this_len)
		_copy_from_pages(obj, subbuf->pages, subbuf->page_base, this_len);
	len -= this_len;
	obj += this_len;
	this_len = min_t(unsigned int, len, subbuf->tail[0].iov_len);
	memcpy(obj, subbuf->tail[0].iov_base, this_len);
}

/* obj is assumed to point to allocated memory of size at least len: */
int read_bytes_from_xdr_buf(struct xdr_buf *buf, unsigned int base, void *obj, unsigned int len)
{
	struct xdr_buf subbuf;
	int status;

	status = xdr_buf_subsegment(buf, &subbuf, base, len);
	if (status != 0)
		return status;
	__read_bytes_from_xdr_buf(&subbuf, obj, len);
	return 0;
}
EXPORT_SYMBOL_GPL(read_bytes_from_xdr_buf);

static void __write_bytes_to_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned int len)
{
	unsigned int this_len;

	this_len = min_t(unsigned int, len, subbuf->head[0].iov_len);
	memcpy(subbuf->head[0].iov_base, obj, this_len);
	len -= this_len;
	obj += this_len;
	this_len = min_t(unsigned int, len, subbuf->page_len);
	if (this_len)
		_copy_to_pages(subbuf->pages, subbuf->page_base, obj, this_len);
	len -= this_len;
	obj += this_len;
	this_len = min_t(unsigned int, len, subbuf->tail[0].iov_len);
	memcpy(subbuf->tail[0].iov_base, obj, this_len);
}

/* obj is assumed to point to allocated memory of size at least len: */
int write_bytes_to_xdr_buf(struct xdr_buf *buf, unsigned int base, void *obj, unsigned int len)
{
	struct xdr_buf subbuf;
	int status;

	status = xdr_buf_subsegment(buf, &subbuf, base, len);
	if (status != 0)
		return status;
	__write_bytes_to_xdr_buf(&subbuf, obj, len);
	return 0;
}
EXPORT_SYMBOL_GPL(write_bytes_to_xdr_buf);

int
xdr_decode_word(struct xdr_buf *buf, unsigned int base, u32 *obj)
{
	__be32	raw;
	int	status;

	status = read_bytes_from_xdr_buf(buf, base, &raw, sizeof(*obj));
	if (status)
		return status;
	*obj = be32_to_cpu(raw);
	return 0;
}
EXPORT_SYMBOL_GPL(xdr_decode_word);

int
xdr_encode_word(struct xdr_buf *buf, unsigned int base, u32 obj)
{
	__be32	raw = cpu_to_be32(obj);

	return write_bytes_to_xdr_buf(buf, base, &raw, sizeof(obj));
}
EXPORT_SYMBOL_GPL(xdr_encode_word);

/* If the netobj starting offset bytes from the start of xdr_buf is contained
 * entirely in the head or the tail, set object to point to it; otherwise
 * try to find space for it at the end of the tail, copy it there, and
 * set obj to point to it. */
int xdr_buf_read_netobj(struct xdr_buf *buf, struct xdr_netobj *obj, unsigned int offset)
{
	struct xdr_buf subbuf;

	if (xdr_decode_word(buf, offset, &obj->len))
		return -EFAULT;
	if (xdr_buf_subsegment(buf, &subbuf, offset + 4, obj->len))
		return -EFAULT;

	/* Is the obj contained entirely in the head? */
	obj->data = subbuf.head[0].iov_base;
	if (subbuf.head[0].iov_len == obj->len)
		return 0;
	/* ..or is the obj contained entirely in the tail? */
	obj->data = subbuf.tail[0].iov_base;
	if (subbuf.tail[0].iov_len == obj->len)
		return 0;

	/* use end of tail as storage for obj:
	 * (We don't copy to the beginning because then we'd have
	 * to worry about doing a potentially overlapping copy.
	 * This assumes the object is at most half the length of the
	 * tail.) */
	if (obj->len > buf->buflen - buf->len)
		return -ENOMEM;
	if (buf->tail[0].iov_len != 0)
		obj->data = buf->tail[0].iov_base + buf->tail[0].iov_len;
	else
		obj->data = buf->head[0].iov_base + buf->head[0].iov_len;
	__read_bytes_from_xdr_buf(&subbuf, obj->data, obj->len);
	return 0;
}
EXPORT_SYMBOL_GPL(xdr_buf_read_netobj);

/* Returns 0 on success, or else a negative error code. */
static int
xdr_xcode_array2(struct xdr_buf *buf, unsigned int base,
		 struct xdr_array2_desc *desc, int encode)
{
	char *elem = NULL, *c;
	unsigned int copied = 0, todo, avail_here;
	struct page **ppages = NULL;
	int err;

	if (encode) {
		if (xdr_encode_word(buf, base, desc->array_len) != 0)
			return -EINVAL;
	} else {
		if (xdr_decode_word(buf, base, &desc->array_len) != 0 ||
		    desc->array_len > desc->array_maxlen ||
		    (unsigned long) base + 4 + desc->array_len *
				    desc->elem_size > buf->len)
			return -EINVAL;
	}
	base += 4;

	if (!desc->xcode)
		return 0;

	todo = desc->array_len * desc->elem_size;

	/* process head */
	if (todo && base < buf->head->iov_len) {
		c = buf->head->iov_base + base;
		avail_here = min_t(unsigned int, todo,
				   buf->head->iov_len - base);
		todo -= avail_here;

		while (avail_here >= desc->elem_size) {
			err = desc->xcode(desc, c);
			if (err)
				goto out;
			c += desc->elem_size;
			avail_here -= desc->elem_size;
		}
		if (avail_here) {
			if (!elem) {
				elem = kmalloc(desc->elem_size, GFP_KERNEL);
				err = -ENOMEM;
				if (!elem)
					goto out;
			}
			if (encode) {
				err = desc->xcode(desc, elem);
				if (err)
					goto out;
				memcpy(c, elem, avail_here);
			} else
				memcpy(elem, c, avail_here);
			copied = avail_here;
		}
		base = buf->head->iov_len;  /* align to start of pages */
	}

	/* process pages array */
	base -= buf->head->iov_len;
	if (todo && base < buf->page_len) {
		unsigned int avail_page;

		avail_here = min(todo, buf->page_len - base);
		todo -= avail_here;

		base += buf->page_base;
		ppages = buf->pages + (base >> PAGE_CACHE_SHIFT);
		base &= ~PAGE_CACHE_MASK;
		avail_page = min_t(unsigned int, PAGE_CACHE_SIZE - base,
					avail_here);
		c = kmap(*ppages) + base;

		while (avail_here) {
			avail_here -= avail_page;
			if (copied || avail_page < desc->elem_size) {
				unsigned int l = min(avail_page,
					desc->elem_size - copied);
				if (!elem) {
					elem = kmalloc(desc->elem_size,
						       GFP_KERNEL);
					err = -ENOMEM;
					if (!elem)
						goto out;
				}
				if (encode) {
					if (!copied) {
						err = desc->xcode(desc, elem);
						if (err)
							goto out;
					}
					memcpy(c, elem + copied, l);
					copied += l;
					if (copied == desc->elem_size)
						copied = 0;
				} else {
					memcpy(elem + copied, c, l);
					copied += l;
					if (copied == desc->elem_size) {
						err = desc->xcode(desc, elem);
						if (err)
							goto out;
						copied = 0;
					}
				}
				avail_page -= l;
				c += l;
			}
			while (avail_page >= desc->elem_size) {
				err = desc->xcode(desc, c);
				if (err)
					goto out;
				c += desc->elem_size;
				avail_page -= desc->elem_size;
			}
			if (avail_page) {
				unsigned int l = min(avail_page,
					    desc->elem_size - copied);
				if (!elem) {
					elem = kmalloc(desc->elem_size,
						       GFP_KERNEL);
					err = -ENOMEM;
					if (!elem)
						goto out;
				}
				if (encode) {
					if (!copied) {
						err = desc->xcode(desc, elem);
						if (err)
							goto out;
					}
					memcpy(c, elem + copied, l);
					copied += l;
					if (copied == desc->elem_size)
						copied = 0;
				} else {
					memcpy(elem + copied, c, l);
					copied += l;
					if (copied == desc->elem_size) {
						err = desc->xcode(desc, elem);
						if (err)
							goto out;
						copied = 0;
					}
				}
			}
			if (avail_here) {
				kunmap(*ppages);
				ppages++;
				c = kmap(*ppages);
			}

			avail_page = min(avail_here,
				 (unsigned int) PAGE_CACHE_SIZE);
		}
		base = buf->page_len;  /* align to start of tail */
	}

	/* process tail */
	base -= buf->page_len;
	if (todo) {
		c = buf->tail->iov_base + base;
		if (copied) {
			unsigned int l = desc->elem_size - copied;

			if (encode)
				memcpy(c, elem + copied, l);
			else {
				memcpy(elem + copied, c, l);
				err = desc->xcode(desc, elem);
				if (err)
					goto out;
			}
			todo -= l;
			c += l;
		}
		while (todo) {
			err = desc->xcode(desc, c);
			if (err)
				goto out;
			c += desc->elem_size;
			todo -= desc->elem_size;
		}
	}
	err = 0;

out:
	kfree(elem);
	if (ppages)
		kunmap(*ppages);
	return err;
}

int
xdr_decode_array2(struct xdr_buf *buf, unsigned int base,
		  struct xdr_array2_desc *desc)
{
	if (base >= buf->len)
		return -EINVAL;

	return xdr_xcode_array2(buf, base, desc, 0);
}
EXPORT_SYMBOL_GPL(xdr_decode_array2);

int
xdr_encode_array2(struct xdr_buf *buf, unsigned int base,
		  struct xdr_array2_desc *desc)
{
	if ((unsigned long) base + 4 + desc->array_len * desc->elem_size >
	    buf->head->iov_len + buf->page_len + buf->tail->iov_len)
		return -EINVAL;

	return xdr_xcode_array2(buf, base, desc, 1);
}
EXPORT_SYMBOL_GPL(xdr_encode_array2);

int
xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len,
		int (*actor)(struct scatterlist *, void *), void *data)
{
	int i, ret = 0;
	unsigned page_len, thislen, page_offset;
	struct scatterlist      sg[1];

	sg_init_table(sg, 1);

	if (offset >= buf->head[0].iov_len) {
		offset -= buf->head[0].iov_len;
	} else {
		thislen = buf->head[0].iov_len - offset;
		if (thislen > len)
			thislen = len;
		sg_set_buf(sg, buf->head[0].iov_base + offset, thislen);
		ret = actor(sg, data);
		if (ret)
			goto out;
		offset = 0;
		len -= thislen;
	}
	if (len == 0)
		goto out;

	if (offset >= buf->page_len) {
		offset -= buf->page_len;
	} else {
		page_len = buf->page_len - offset;
		if (page_len > len)
			page_len = len;
		len -= page_len;
		page_offset = (offset + buf->page_base) & (PAGE_CACHE_SIZE - 1);
		i = (offset + buf->page_base) >> PAGE_CACHE_SHIFT;
		thislen = PAGE_CACHE_SIZE - page_offset;
		do {
			if (thislen > page_len)
				thislen = page_len;
			sg_set_page(sg, buf->pages[i], thislen, page_offset);
			ret = actor(sg, data);
			if (ret)
				goto out;
			page_len -= thislen;
			i++;
			page_offset = 0;
			thislen = PAGE_CACHE_SIZE;
		} while (page_len != 0);
		offset = 0;
	}
	if (len == 0)
		goto out;
	if (offset < buf->tail[0].iov_len) {
		thislen = buf->tail[0].iov_len - offset;
		if (thislen > len)
			thislen = len;
		sg_set_buf(sg, buf->tail[0].iov_base + offset, thislen);
		ret = actor(sg, data);
		len -= thislen;
	}
	if (len != 0)
		ret = -EINVAL;
out:
	return ret;
}
EXPORT_SYMBOL_GPL(xdr_process_buf);