delegation.c 29.2 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
/*
 * linux/fs/nfs/delegation.c
 *
 * Copyright (C) 2004 Trond Myklebust
 *
 * NFS file delegation management
 *
 */
#include <linux/completion.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>

#include <linux/nfs4.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_xdr.h>

#include "nfs4_fs.h"
#include "delegation.h"
#include "internal.h"
#include "nfs4trace.h"

static void nfs_free_delegation(struct nfs_delegation *delegation)
{
	if (delegation->cred) {
		put_rpccred(delegation->cred);
		delegation->cred = NULL;
	}
	kfree_rcu(delegation, rcu);
}

/**
 * nfs_mark_delegation_referenced - set delegation's REFERENCED flag
 * @delegation: delegation to process
 *
 */
void nfs_mark_delegation_referenced(struct nfs_delegation *delegation)
{
	set_bit(NFS_DELEGATION_REFERENCED, &delegation->flags);
}

static bool
nfs4_is_valid_delegation(const struct nfs_delegation *delegation,
		fmode_t flags)
{
	if (delegation != NULL && (delegation->type & flags) == flags &&
	    !test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) &&
	    !test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
		return true;
	return false;
}

static int
nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark)
{
	struct nfs_delegation *delegation;
	int ret = 0;

	flags &= FMODE_READ|FMODE_WRITE;
	rcu_read_lock();
	delegation = rcu_dereference(NFS_I(inode)->delegation);
	if (nfs4_is_valid_delegation(delegation, flags)) {
		if (mark)
			nfs_mark_delegation_referenced(delegation);
		ret = 1;
	}
	rcu_read_unlock();
	return ret;
}
/**
 * nfs_have_delegation - check if inode has a delegation, mark it
 * NFS_DELEGATION_REFERENCED if there is one.
 * @inode: inode to check
 * @flags: delegation types to check for
 *
 * Returns one if inode has the indicated delegation, otherwise zero.
 */
int nfs4_have_delegation(struct inode *inode, fmode_t flags)
{
	return nfs4_do_check_delegation(inode, flags, true);
}

/*
 * nfs4_check_delegation - check if inode has a delegation, do not mark
 * NFS_DELEGATION_REFERENCED if it has one.
 */
int nfs4_check_delegation(struct inode *inode, fmode_t flags)
{
	return nfs4_do_check_delegation(inode, flags, false);
}

static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid)
{
	struct inode *inode = state->inode;
	struct file_lock *fl;
	struct file_lock_context *flctx = inode->i_flctx;
	struct list_head *list;
	int status = 0;

	if (flctx == NULL)
		goto out;

	list = &flctx->flc_posix;
	spin_lock(&flctx->flc_lock);
restart:
	list_for_each_entry(fl, list, fl_list) {
		if (nfs_file_open_context(fl->fl_file) != ctx)
			continue;
		spin_unlock(&flctx->flc_lock);
		status = nfs4_lock_delegation_recall(fl, state, stateid);
		if (status < 0)
			goto out;
		spin_lock(&flctx->flc_lock);
	}
	if (list == &flctx->flc_posix) {
		list = &flctx->flc_flock;
		goto restart;
	}
	spin_unlock(&flctx->flc_lock);
out:
	return status;
}

static int nfs_delegation_claim_opens(struct inode *inode,
		const nfs4_stateid *stateid, fmode_t type)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_open_context *ctx;
	struct nfs4_state_owner *sp;
	struct nfs4_state *state;
	unsigned int seq;
	int err;

again:
	spin_lock(&inode->i_lock);
	list_for_each_entry(ctx, &nfsi->open_files, list) {
		state = ctx->state;
		if (state == NULL)
			continue;
		if (!test_bit(NFS_DELEGATED_STATE, &state->flags))
			continue;
		if (!nfs4_valid_open_stateid(state))
			continue;
		if (!nfs4_stateid_match(&state->stateid, stateid))
			continue;
		get_nfs_open_context(ctx);
		spin_unlock(&inode->i_lock);
		sp = state->owner;
		/* Block nfs4_proc_unlck */
		mutex_lock(&sp->so_delegreturn_mutex);
		seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
		err = nfs4_open_delegation_recall(ctx, state, stateid, type);
		if (!err)
			err = nfs_delegation_claim_locks(ctx, state, stateid);
		if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
			err = -EAGAIN;
		mutex_unlock(&sp->so_delegreturn_mutex);
		put_nfs_open_context(ctx);
		if (err != 0)
			return err;
		goto again;
	}
	spin_unlock(&inode->i_lock);
	return 0;
}

/**
 * nfs_inode_reclaim_delegation - process a delegation reclaim request
 * @inode: inode to process
 * @cred: credential to use for request
 * @res: new delegation state from server
 *
 */
void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred,
				  struct nfs_openres *res)
{
	struct nfs_delegation *delegation;
	struct rpc_cred *oldcred = NULL;

	rcu_read_lock();
	delegation = rcu_dereference(NFS_I(inode)->delegation);
	if (delegation != NULL) {
		spin_lock(&delegation->lock);
		if (delegation->inode != NULL) {
			nfs4_stateid_copy(&delegation->stateid, &res->delegation);
			delegation->type = res->delegation_type;
			delegation->pagemod_limit = res->pagemod_limit;
			oldcred = delegation->cred;
			delegation->cred = get_rpccred(cred);
			clear_bit(NFS_DELEGATION_NEED_RECLAIM,
				  &delegation->flags);
			spin_unlock(&delegation->lock);
			rcu_read_unlock();
			put_rpccred(oldcred);
			trace_nfs4_reclaim_delegation(inode, res->delegation_type);
			return;
		}
		/* We appear to have raced with a delegation return. */
		spin_unlock(&delegation->lock);
	}
	rcu_read_unlock();
	nfs_inode_set_delegation(inode, cred, res);
}

static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync)
{
	int res = 0;

	if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
		res = nfs4_proc_delegreturn(inode,
				delegation->cred,
				&delegation->stateid,
				issync);
	nfs_free_delegation(delegation);
	return res;
}

static struct inode *nfs_delegation_grab_inode(struct nfs_delegation *delegation)
{
	struct inode *inode = NULL;

	spin_lock(&delegation->lock);
	if (delegation->inode != NULL)
		inode = igrab(delegation->inode);
	spin_unlock(&delegation->lock);
	return inode;
}

static struct nfs_delegation *
nfs_start_delegation_return_locked(struct nfs_inode *nfsi)
{
	struct nfs_delegation *ret = NULL;
	struct nfs_delegation *delegation = rcu_dereference(nfsi->delegation);

	if (delegation == NULL)
		goto out;
	spin_lock(&delegation->lock);
	if (!test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
		ret = delegation;
	spin_unlock(&delegation->lock);
out:
	return ret;
}

static struct nfs_delegation *
nfs_start_delegation_return(struct nfs_inode *nfsi)
{
	struct nfs_delegation *delegation;

	rcu_read_lock();
	delegation = nfs_start_delegation_return_locked(nfsi);
	rcu_read_unlock();
	return delegation;
}

static void
nfs_abort_delegation_return(struct nfs_delegation *delegation,
		struct nfs_client *clp)
{

	spin_lock(&delegation->lock);
	clear_bit(NFS_DELEGATION_RETURNING, &delegation->flags);
	set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
	spin_unlock(&delegation->lock);
	set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state);
}

static struct nfs_delegation *
nfs_detach_delegation_locked(struct nfs_inode *nfsi,
		struct nfs_delegation *delegation,
		struct nfs_client *clp)
{
	struct nfs_delegation *deleg_cur =
		rcu_dereference_protected(nfsi->delegation,
				lockdep_is_held(&clp->cl_lock));

	if (deleg_cur == NULL || delegation != deleg_cur)
		return NULL;

	spin_lock(&delegation->lock);
	set_bit(NFS_DELEGATION_RETURNING, &delegation->flags);
	list_del_rcu(&delegation->super_list);
	delegation->inode = NULL;
	rcu_assign_pointer(nfsi->delegation, NULL);
	spin_unlock(&delegation->lock);
	return delegation;
}

static struct nfs_delegation *nfs_detach_delegation(struct nfs_inode *nfsi,
		struct nfs_delegation *delegation,
		struct nfs_server *server)
{
	struct nfs_client *clp = server->nfs_client;

	spin_lock(&clp->cl_lock);
	delegation = nfs_detach_delegation_locked(nfsi, delegation, clp);
	spin_unlock(&clp->cl_lock);
	return delegation;
}

static struct nfs_delegation *
nfs_inode_detach_delegation(struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_server *server = NFS_SERVER(inode);
	struct nfs_delegation *delegation;

	delegation = nfs_start_delegation_return(nfsi);
	if (delegation == NULL)
		return NULL;
	return nfs_detach_delegation(nfsi, delegation, server);
}

static void
nfs_update_inplace_delegation(struct nfs_delegation *delegation,
		const struct nfs_delegation *update)
{
	if (nfs4_stateid_is_newer(&update->stateid, &delegation->stateid)) {
		delegation->stateid.seqid = update->stateid.seqid;
		smp_wmb();
		delegation->type = update->type;
	}
}

/**
 * nfs_inode_set_delegation - set up a delegation on an inode
 * @inode: inode to which delegation applies
 * @cred: cred to use for subsequent delegation processing
 * @res: new delegation state from server
 *
 * Returns zero on success, or a negative errno value.
 */
int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res)
{
	struct nfs_server *server = NFS_SERVER(inode);
	struct nfs_client *clp = server->nfs_client;
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_delegation *delegation, *old_delegation;
	struct nfs_delegation *freeme = NULL;
	int status = 0;

	delegation = kmalloc(sizeof(*delegation), GFP_NOFS);
	if (delegation == NULL)
		return -ENOMEM;
	nfs4_stateid_copy(&delegation->stateid, &res->delegation);
	delegation->type = res->delegation_type;
	delegation->pagemod_limit = res->pagemod_limit;
	delegation->change_attr = inode->i_version;
	delegation->cred = get_rpccred(cred);
	delegation->inode = inode;
	delegation->flags = 1<<NFS_DELEGATION_REFERENCED;
	spin_lock_init(&delegation->lock);

	spin_lock(&clp->cl_lock);
	old_delegation = rcu_dereference_protected(nfsi->delegation,
					lockdep_is_held(&clp->cl_lock));
	if (old_delegation != NULL) {
		/* Is this an update of the existing delegation? */
		if (nfs4_stateid_match_other(&old_delegation->stateid,
					&delegation->stateid)) {
			nfs_update_inplace_delegation(old_delegation,
					delegation);
			goto out;
		}
		/*
		 * Deal with broken servers that hand out two
		 * delegations for the same file.
		 * Allow for upgrades to a WRITE delegation, but
		 * nothing else.
		 */
		dfprintk(FILE, "%s: server %s handed out "
				"a duplicate delegation!\n",
				__func__, clp->cl_hostname);
		if (delegation->type == old_delegation->type ||
		    !(delegation->type & FMODE_WRITE)) {
			freeme = delegation;
			delegation = NULL;
			goto out;
		}
		if (test_and_set_bit(NFS_DELEGATION_RETURNING,
					&old_delegation->flags))
			goto out;
		freeme = nfs_detach_delegation_locked(nfsi,
				old_delegation, clp);
		if (freeme == NULL)
			goto out;
	}
	list_add_tail_rcu(&delegation->super_list, &server->delegations);
	rcu_assign_pointer(nfsi->delegation, delegation);
	delegation = NULL;

	/* Ensure we revalidate the attributes and page cache! */
	spin_lock(&inode->i_lock);
	nfsi->cache_validity |= NFS_INO_REVAL_FORCED;
	spin_unlock(&inode->i_lock);
	trace_nfs4_set_delegation(inode, res->delegation_type);

out:
	spin_unlock(&clp->cl_lock);
	if (delegation != NULL)
		nfs_free_delegation(delegation);
	if (freeme != NULL)
		nfs_do_return_delegation(inode, freeme, 0);
	return status;
}

/*
 * Basic procedure for returning a delegation to the server
 */
static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation *delegation, int issync)
{
	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
	struct nfs_inode *nfsi = NFS_I(inode);
	int err = 0;

	if (delegation == NULL)
		return 0;
	do {
		if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
			break;
		err = nfs_delegation_claim_opens(inode, &delegation->stateid,
				delegation->type);
		if (!issync || err != -EAGAIN)
			break;
		/*
		 * Guard against state recovery
		 */
		err = nfs4_wait_clnt_recover(clp);
	} while (err == 0);

	if (err) {
		nfs_abort_delegation_return(delegation, clp);
		goto out;
	}
	if (!nfs_detach_delegation(nfsi, delegation, NFS_SERVER(inode)))
		goto out;

	err = nfs_do_return_delegation(inode, delegation, issync);
out:
	return err;
}

static bool nfs_delegation_need_return(struct nfs_delegation *delegation)
{
	bool ret = false;

	if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
		goto out;
	if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags))
		ret = true;
	if (test_and_clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags) && !ret) {
		struct inode *inode;

		spin_lock(&delegation->lock);
		inode = delegation->inode;
		if (inode && list_empty(&NFS_I(inode)->open_files))
			ret = true;
		spin_unlock(&delegation->lock);
	}
out:
	return ret;
}

/**
 * nfs_client_return_marked_delegations - return previously marked delegations
 * @clp: nfs_client to process
 *
 * Note that this function is designed to be called by the state
 * manager thread. For this reason, it cannot flush the dirty data,
 * since that could deadlock in case of a state recovery error.
 *
 * Returns zero on success, or a negative errno value.
 */
int nfs_client_return_marked_delegations(struct nfs_client *clp)
{
	struct nfs_delegation *delegation;
	struct nfs_server *server;
	struct inode *inode;
	int err = 0;

restart:
	rcu_read_lock();
	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
		list_for_each_entry_rcu(delegation, &server->delegations,
								super_list) {
			if (!nfs_delegation_need_return(delegation))
				continue;
			if (!nfs_sb_active(server->super))
				continue;
			inode = nfs_delegation_grab_inode(delegation);
			if (inode == NULL) {
				rcu_read_unlock();
				nfs_sb_deactive(server->super);
				goto restart;
			}
			delegation = nfs_start_delegation_return_locked(NFS_I(inode));
			rcu_read_unlock();

			err = nfs_end_delegation_return(inode, delegation, 0);
			iput(inode);
			nfs_sb_deactive(server->super);
			if (!err)
				goto restart;
			set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state);
			return err;
		}
	}
	rcu_read_unlock();
	return 0;
}

/**
 * nfs_inode_return_delegation_noreclaim - return delegation, don't reclaim opens
 * @inode: inode to process
 *
 * Does not protect against delegation reclaims, therefore really only safe
 * to be called from nfs4_clear_inode().
 */
void nfs_inode_return_delegation_noreclaim(struct inode *inode)
{
	struct nfs_delegation *delegation;

	delegation = nfs_inode_detach_delegation(inode);
	if (delegation != NULL)
		nfs_do_return_delegation(inode, delegation, 1);
}

/**
 * nfs_inode_return_delegation - synchronously return a delegation
 * @inode: inode to process
 *
 * This routine will always flush any dirty data to disk on the
 * assumption that if we need to return the delegation, then
 * we should stop caching.
 *
 * Returns zero on success, or a negative errno value.
 */
int nfs4_inode_return_delegation(struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_delegation *delegation;
	int err = 0;

	nfs_wb_all(inode);
	delegation = nfs_start_delegation_return(nfsi);
	if (delegation != NULL)
		err = nfs_end_delegation_return(inode, delegation, 1);
	return err;
}

static void nfs_mark_return_if_closed_delegation(struct nfs_server *server,
		struct nfs_delegation *delegation)
{
	set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
	set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
}

static void nfs_mark_return_delegation(struct nfs_server *server,
		struct nfs_delegation *delegation)
{
	set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
	set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
}

static bool nfs_server_mark_return_all_delegations(struct nfs_server *server)
{
	struct nfs_delegation *delegation;
	bool ret = false;

	list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
		nfs_mark_return_delegation(server, delegation);
		ret = true;
	}
	return ret;
}

static void nfs_client_mark_return_all_delegations(struct nfs_client *clp)
{
	struct nfs_server *server;

	rcu_read_lock();
	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
		nfs_server_mark_return_all_delegations(server);
	rcu_read_unlock();
}

static void nfs_delegation_run_state_manager(struct nfs_client *clp)
{
	if (test_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state))
		nfs4_schedule_state_manager(clp);
}

/**
 * nfs_expire_all_delegations
 * @clp: client to process
 *
 */
void nfs_expire_all_delegations(struct nfs_client *clp)
{
	nfs_client_mark_return_all_delegations(clp);
	nfs_delegation_run_state_manager(clp);
}

/**
 * nfs_super_return_all_delegations - return delegations for one superblock
 * @sb: sb to process
 *
 */
void nfs_server_return_all_delegations(struct nfs_server *server)
{
	struct nfs_client *clp = server->nfs_client;
	bool need_wait;

	if (clp == NULL)
		return;

	rcu_read_lock();
	need_wait = nfs_server_mark_return_all_delegations(server);
	rcu_read_unlock();

	if (need_wait) {
		nfs4_schedule_state_manager(clp);
		nfs4_wait_clnt_recover(clp);
	}
}

static void nfs_mark_return_unused_delegation_types(struct nfs_server *server,
						 fmode_t flags)
{
	struct nfs_delegation *delegation;

	list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
		if ((delegation->type == (FMODE_READ|FMODE_WRITE)) && !(flags & FMODE_WRITE))
			continue;
		if (delegation->type & flags)
			nfs_mark_return_if_closed_delegation(server, delegation);
	}
}

static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *clp,
							fmode_t flags)
{
	struct nfs_server *server;

	rcu_read_lock();
	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
		nfs_mark_return_unused_delegation_types(server, flags);
	rcu_read_unlock();
}

static void nfs_mark_delegation_revoked(struct nfs_server *server,
		struct nfs_delegation *delegation)
{
	set_bit(NFS_DELEGATION_REVOKED, &delegation->flags);
	delegation->stateid.type = NFS4_INVALID_STATEID_TYPE;
	nfs_mark_return_delegation(server, delegation);
}

static bool nfs_revoke_delegation(struct inode *inode,
		const nfs4_stateid *stateid)
{
	struct nfs_delegation *delegation;
	nfs4_stateid tmp;
	bool ret = false;

	rcu_read_lock();
	delegation = rcu_dereference(NFS_I(inode)->delegation);
	if (delegation == NULL)
		goto out;
	if (stateid == NULL) {
		nfs4_stateid_copy(&tmp, &delegation->stateid);
		stateid = &tmp;
	} else if (!nfs4_stateid_match(stateid, &delegation->stateid))
		goto out;
	nfs_mark_delegation_revoked(NFS_SERVER(inode), delegation);
	ret = true;
out:
	rcu_read_unlock();
	if (ret)
		nfs_inode_find_state_and_recover(inode, stateid);
	return ret;
}

void nfs_remove_bad_delegation(struct inode *inode,
		const nfs4_stateid *stateid)
{
	struct nfs_delegation *delegation;

	if (!nfs_revoke_delegation(inode, stateid))
		return;
	delegation = nfs_inode_detach_delegation(inode);
	if (delegation)
		nfs_free_delegation(delegation);
}
EXPORT_SYMBOL_GPL(nfs_remove_bad_delegation);

/**
 * nfs_expire_unused_delegation_types
 * @clp: client to process
 * @flags: delegation types to expire
 *
 */
void nfs_expire_unused_delegation_types(struct nfs_client *clp, fmode_t flags)
{
	nfs_client_mark_return_unused_delegation_types(clp, flags);
	nfs_delegation_run_state_manager(clp);
}

static void nfs_mark_return_unreferenced_delegations(struct nfs_server *server)
{
	struct nfs_delegation *delegation;

	list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
		if (test_and_clear_bit(NFS_DELEGATION_REFERENCED, &delegation->flags))
			continue;
		nfs_mark_return_if_closed_delegation(server, delegation);
	}
}

/**
 * nfs_expire_unreferenced_delegations - Eliminate unused delegations
 * @clp: nfs_client to process
 *
 */
void nfs_expire_unreferenced_delegations(struct nfs_client *clp)
{
	struct nfs_server *server;

	rcu_read_lock();
	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
		nfs_mark_return_unreferenced_delegations(server);
	rcu_read_unlock();

	nfs_delegation_run_state_manager(clp);
}

/**
 * nfs_async_inode_return_delegation - asynchronously return a delegation
 * @inode: inode to process
 * @stateid: state ID information
 *
 * Returns zero on success, or a negative errno value.
 */
int nfs_async_inode_return_delegation(struct inode *inode,
				      const nfs4_stateid *stateid)
{
	struct nfs_server *server = NFS_SERVER(inode);
	struct nfs_client *clp = server->nfs_client;
	struct nfs_delegation *delegation;

	rcu_read_lock();
	delegation = rcu_dereference(NFS_I(inode)->delegation);
	if (delegation == NULL)
		goto out_enoent;
	if (stateid != NULL &&
	    !clp->cl_mvops->match_stateid(&delegation->stateid, stateid))
		goto out_enoent;
	nfs_mark_return_delegation(server, delegation);
	rcu_read_unlock();

	nfs_delegation_run_state_manager(clp);
	return 0;
out_enoent:
	rcu_read_unlock();
	return -ENOENT;
}

static struct inode *
nfs_delegation_find_inode_server(struct nfs_server *server,
				 const struct nfs_fh *fhandle)
{
	struct nfs_delegation *delegation;
	struct inode *res = NULL;

	list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
		spin_lock(&delegation->lock);
		if (delegation->inode != NULL &&
		    nfs_compare_fh(fhandle, &NFS_I(delegation->inode)->fh) == 0) {
			res = igrab(delegation->inode);
		}
		spin_unlock(&delegation->lock);
		if (res != NULL)
			break;
	}
	return res;
}

/**
 * nfs_delegation_find_inode - retrieve the inode associated with a delegation
 * @clp: client state handle
 * @fhandle: filehandle from a delegation recall
 *
 * Returns pointer to inode matching "fhandle," or NULL if a matching inode
 * cannot be found.
 */
struct inode *nfs_delegation_find_inode(struct nfs_client *clp,
					const struct nfs_fh *fhandle)
{
	struct nfs_server *server;
	struct inode *res = NULL;

	rcu_read_lock();
	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
		res = nfs_delegation_find_inode_server(server, fhandle);
		if (res != NULL)
			break;
	}
	rcu_read_unlock();
	return res;
}

static void nfs_delegation_mark_reclaim_server(struct nfs_server *server)
{
	struct nfs_delegation *delegation;

	list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
		/*
		 * If the delegation may have been admin revoked, then we
		 * cannot reclaim it.
		 */
		if (test_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags))
			continue;
		set_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
	}
}

/**
 * nfs_delegation_mark_reclaim - mark all delegations as needing to be reclaimed
 * @clp: nfs_client to process
 *
 */
void nfs_delegation_mark_reclaim(struct nfs_client *clp)
{
	struct nfs_server *server;

	rcu_read_lock();
	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
		nfs_delegation_mark_reclaim_server(server);
	rcu_read_unlock();
}

/**
 * nfs_delegation_reap_unclaimed - reap unclaimed delegations after reboot recovery is done
 * @clp: nfs_client to process
 *
 */
void nfs_delegation_reap_unclaimed(struct nfs_client *clp)
{
	struct nfs_delegation *delegation;
	struct nfs_server *server;
	struct inode *inode;

restart:
	rcu_read_lock();
	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
		list_for_each_entry_rcu(delegation, &server->delegations,
								super_list) {
			if (test_bit(NFS_DELEGATION_RETURNING,
						&delegation->flags))
				continue;
			if (test_bit(NFS_DELEGATION_NEED_RECLAIM,
						&delegation->flags) == 0)
				continue;
			if (!nfs_sb_active(server->super))
				continue;
			inode = nfs_delegation_grab_inode(delegation);
			if (inode == NULL) {
				rcu_read_unlock();
				nfs_sb_deactive(server->super);
				goto restart;
			}
			delegation = nfs_start_delegation_return_locked(NFS_I(inode));
			rcu_read_unlock();
			if (delegation != NULL) {
				delegation = nfs_detach_delegation(NFS_I(inode),
					delegation, server);
				if (delegation != NULL)
					nfs_free_delegation(delegation);
			}
			iput(inode);
			nfs_sb_deactive(server->super);
			goto restart;
		}
	}
	rcu_read_unlock();
}

static inline bool nfs4_server_rebooted(const struct nfs_client *clp)
{
	return (clp->cl_state & (BIT(NFS4CLNT_CHECK_LEASE) |
				BIT(NFS4CLNT_LEASE_EXPIRED) |
				BIT(NFS4CLNT_SESSION_RESET))) != 0;
}

static void nfs_mark_test_expired_delegation(struct nfs_server *server,
	    struct nfs_delegation *delegation)
{
	if (delegation->stateid.type == NFS4_INVALID_STATEID_TYPE)
		return;
	clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
	set_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags);
	set_bit(NFS4CLNT_DELEGATION_EXPIRED, &server->nfs_client->cl_state);
}

static void nfs_inode_mark_test_expired_delegation(struct nfs_server *server,
		struct inode *inode)
{
	struct nfs_delegation *delegation;

	rcu_read_lock();
	delegation = rcu_dereference(NFS_I(inode)->delegation);
	if (delegation)
		nfs_mark_test_expired_delegation(server, delegation);
	rcu_read_unlock();

}

static void nfs_delegation_mark_test_expired_server(struct nfs_server *server)
{
	struct nfs_delegation *delegation;

	list_for_each_entry_rcu(delegation, &server->delegations, super_list)
		nfs_mark_test_expired_delegation(server, delegation);
}

/**
 * nfs_mark_test_expired_all_delegations - mark all delegations for testing
 * @clp: nfs_client to process
 *
 * Iterates through all the delegations associated with this server and
 * marks them as needing to be checked for validity.
 */
void nfs_mark_test_expired_all_delegations(struct nfs_client *clp)
{
	struct nfs_server *server;

	rcu_read_lock();
	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
		nfs_delegation_mark_test_expired_server(server);
	rcu_read_unlock();
}

/**
 * nfs_reap_expired_delegations - reap expired delegations
 * @clp: nfs_client to process
 *
 * Iterates through all the delegations associated with this server and
 * checks if they have may have been revoked. This function is usually
 * expected to be called in cases where the server may have lost its
 * lease.
 */
void nfs_reap_expired_delegations(struct nfs_client *clp)
{
	const struct nfs4_minor_version_ops *ops = clp->cl_mvops;
	struct nfs_delegation *delegation;
	struct nfs_server *server;
	struct inode *inode;
	struct rpc_cred *cred;
	nfs4_stateid stateid;

restart:
	rcu_read_lock();
	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
		list_for_each_entry_rcu(delegation, &server->delegations,
								super_list) {
			if (test_bit(NFS_DELEGATION_RETURNING,
						&delegation->flags))
				continue;
			if (test_bit(NFS_DELEGATION_TEST_EXPIRED,
						&delegation->flags) == 0)
				continue;
			if (!nfs_sb_active(server->super))
				continue;
			inode = nfs_delegation_grab_inode(delegation);
			if (inode == NULL) {
				rcu_read_unlock();
				nfs_sb_deactive(server->super);
				goto restart;
			}
			cred = get_rpccred_rcu(delegation->cred);
			nfs4_stateid_copy(&stateid, &delegation->stateid);
			clear_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags);
			rcu_read_unlock();
			if (cred != NULL &&
			    ops->test_and_free_expired(server, &stateid, cred) < 0) {
				nfs_revoke_delegation(inode, &stateid);
				nfs_inode_find_state_and_recover(inode, &stateid);
			}
			put_rpccred(cred);
			if (nfs4_server_rebooted(clp)) {
				nfs_inode_mark_test_expired_delegation(server,inode);
				iput(inode);
				nfs_sb_deactive(server->super);
				return;
			}
			iput(inode);
			nfs_sb_deactive(server->super);
			goto restart;
		}
	}
	rcu_read_unlock();
}

void nfs_inode_find_delegation_state_and_recover(struct inode *inode,
		const nfs4_stateid *stateid)
{
	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
	struct nfs_delegation *delegation;
	bool found = false;

	rcu_read_lock();
	delegation = rcu_dereference(NFS_I(inode)->delegation);
	if (delegation &&
	    nfs4_stateid_match_other(&delegation->stateid, stateid)) {
		nfs_mark_test_expired_delegation(NFS_SERVER(inode), delegation);
		found = true;
	}
	rcu_read_unlock();
	if (found)
		nfs4_schedule_state_manager(clp);
}

/**
 * nfs_delegations_present - check for existence of delegations
 * @clp: client state handle
 *
 * Returns one if there are any nfs_delegation structures attached
 * to this nfs_client.
 */
int nfs_delegations_present(struct nfs_client *clp)
{
	struct nfs_server *server;
	int ret = 0;

	rcu_read_lock();
	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
		if (!list_empty(&server->delegations)) {
			ret = 1;
			break;
		}
	rcu_read_unlock();
	return ret;
}

/**
 * nfs4_copy_delegation_stateid - Copy inode's state ID information
 * @inode: inode to check
 * @flags: delegation type requirement
 * @dst: stateid data structure to fill in
 * @cred: optional argument to retrieve credential
 *
 * Returns "true" and fills in "dst->data" * if inode had a delegation,
 * otherwise "false" is returned.
 */
bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags,
		nfs4_stateid *dst, struct rpc_cred **cred)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_delegation *delegation;
	bool ret;

	flags &= FMODE_READ|FMODE_WRITE;
	rcu_read_lock();
	delegation = rcu_dereference(nfsi->delegation);
	ret = nfs4_is_valid_delegation(delegation, flags);
	if (ret) {
		nfs4_stateid_copy(dst, &delegation->stateid);
		nfs_mark_delegation_referenced(delegation);
		if (cred)
			*cred = get_rpccred(delegation->cred);
	}
	rcu_read_unlock();
	return ret;
}

/**
 * nfs4_delegation_flush_on_close - Check if we must flush file on close
 * @inode: inode to check
 *
 * This function checks the number of outstanding writes to the file
 * against the delegation 'space_limit' field to see if
 * the spec requires us to flush the file on close.
 */
bool nfs4_delegation_flush_on_close(const struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_delegation *delegation;
	bool ret = true;

	rcu_read_lock();
	delegation = rcu_dereference(nfsi->delegation);
	if (delegation == NULL || !(delegation->type & FMODE_WRITE))
		goto out;
	if (nfsi->nrequests < delegation->pagemod_limit)
		ret = false;
out:
	rcu_read_unlock();
	return ret;
}