super.c 40.0 KB
Newer Older
D
David Howells 已提交
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
/*
 *  linux/fs/nfs/super.c
 *
 *  Copyright (C) 1992  Rick Sladkey
 *
 *  nfs superblock handling functions
 *
 *  Modularised by Alan Cox <Alan.Cox@linux.org>, while hacking some
 *  experimental NFS changes. Modularisation taken straight from SYS5 fs.
 *
 *  Change to nfs_read_super() to permit NFS mounts to multi-homed hosts.
 *  J.S.Peatfield@damtp.cam.ac.uk
 *
 *  Split from inode.c by David Howells <dhowells@redhat.com>
 *
 */

#include <linux/config.h>
#include <linux/module.h>
#include <linux/init.h>

#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/errno.h>
#include <linux/unistd.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/metrics.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/nfs4_mount.h>
#include <linux/lockd/bind.h>
#include <linux/smp_lock.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/nfs_idmap.h>
#include <linux/vfs.h>
#include <linux/inet.h>
#include <linux/nfs_xdr.h>

#include <asm/system.h>
#include <asm/uaccess.h>

#include "nfs4_fs.h"
#include "callback.h"
#include "delegation.h"
#include "iostat.h"
#include "internal.h"

#define NFSDBG_FACILITY		NFSDBG_VFS

/* Maximum number of readahead requests
 * FIXME: this should really be a sysctl so that users may tune it to suit
 *        their needs. People that do NFS over a slow network, might for
 *        instance want to reduce it to something closer to 1 for improved
 *        interactive response.
 */
#define NFS_MAX_READAHEAD	(RPC_DEF_SLOT_TABLE - 1)

/*
 * RPC cruft for NFS
 */
static struct rpc_version * nfs_version[] = {
	NULL,
	NULL,
	&nfs_version2,
#if defined(CONFIG_NFS_V3)
	&nfs_version3,
#elif defined(CONFIG_NFS_V4)
	NULL,
#endif
#if defined(CONFIG_NFS_V4)
	&nfs_version4,
#endif
};

static struct rpc_program nfs_program = {
	.name			= "nfs",
	.number			= NFS_PROGRAM,
	.nrvers			= ARRAY_SIZE(nfs_version),
	.version		= nfs_version,
	.stats			= &nfs_rpcstat,
	.pipe_dir_name		= "/nfs",
};

struct rpc_stat nfs_rpcstat = {
	.program		= &nfs_program
};


#ifdef CONFIG_NFS_V3_ACL
static struct rpc_stat		nfsacl_rpcstat = { &nfsacl_program };
static struct rpc_version *	nfsacl_version[] = {
	[3]			= &nfsacl_version3,
};

struct rpc_program		nfsacl_program = {
	.name =			"nfsacl",
	.number =		NFS_ACL_PROGRAM,
	.nrvers =		ARRAY_SIZE(nfsacl_version),
	.version =		nfsacl_version,
	.stats =		&nfsacl_rpcstat,
};
#endif  /* CONFIG_NFS_V3_ACL */

static void nfs_umount_begin(struct vfsmount *, int);
110
static int  nfs_statfs(struct dentry *, struct kstatfs *);
D
David Howells 已提交
111 112
static int  nfs_show_options(struct seq_file *, struct vfsmount *);
static int  nfs_show_stats(struct seq_file *, struct vfsmount *);
113 114 115
static int nfs_get_sb(struct file_system_type *, int, const char *, void *, struct vfsmount *);
static int nfs_clone_nfs_sb(struct file_system_type *fs_type,
		int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
D
David Howells 已提交
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
static void nfs_kill_super(struct super_block *);

static struct file_system_type nfs_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "nfs",
	.get_sb		= nfs_get_sb,
	.kill_sb	= nfs_kill_super,
	.fs_flags	= FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
};

struct file_system_type clone_nfs_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "nfs",
	.get_sb		= nfs_clone_nfs_sb,
	.kill_sb	= nfs_kill_super,
	.fs_flags	= FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
};

static struct super_operations nfs_sops = {
	.alloc_inode	= nfs_alloc_inode,
	.destroy_inode	= nfs_destroy_inode,
	.write_inode	= nfs_write_inode,
	.statfs		= nfs_statfs,
	.clear_inode	= nfs_clear_inode,
	.umount_begin	= nfs_umount_begin,
	.show_options	= nfs_show_options,
	.show_stats	= nfs_show_stats,
};

#ifdef CONFIG_NFS_V4
146 147 148 149 150 151
static int nfs4_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
static int nfs_clone_nfs4_sb(struct file_system_type *fs_type,
		int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
static int nfs_referral_nfs4_sb(struct file_system_type *fs_type,
		int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
D
David Howells 已提交
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
static void nfs4_kill_super(struct super_block *sb);

static struct file_system_type nfs4_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "nfs4",
	.get_sb		= nfs4_get_sb,
	.kill_sb	= nfs4_kill_super,
	.fs_flags	= FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
};

struct file_system_type clone_nfs4_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "nfs4",
	.get_sb		= nfs_clone_nfs4_sb,
	.kill_sb	= nfs4_kill_super,
	.fs_flags	= FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
};

struct file_system_type nfs_referral_nfs4_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "nfs4",
	.get_sb		= nfs_referral_nfs4_sb,
	.kill_sb	= nfs4_kill_super,
	.fs_flags	= FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
};

static struct super_operations nfs4_sops = {
	.alloc_inode	= nfs_alloc_inode,
	.destroy_inode	= nfs_destroy_inode,
	.write_inode	= nfs_write_inode,
	.statfs		= nfs_statfs,
	.clear_inode	= nfs4_clear_inode,
	.umount_begin	= nfs_umount_begin,
	.show_options	= nfs_show_options,
	.show_stats	= nfs_show_stats,
};
#endif

A
Andrew Morton 已提交
190
#ifdef CONFIG_NFS_V4
D
David Howells 已提交
191 192 193 194 195 196 197 198 199 200 201 202 203 204 205
static const int nfs_set_port_min = 0;
static const int nfs_set_port_max = 65535;

static int param_set_port(const char *val, struct kernel_param *kp)
{
	char *endp;
	int num = simple_strtol(val, &endp, 0);
	if (endp == val || *endp || num < nfs_set_port_min || num > nfs_set_port_max)
		return -EINVAL;
	*((int *)kp->arg) = num;
	return 0;
}

module_param_call(callback_tcpport, param_set_port, param_get_int,
		 &nfs_callback_set_tcpport, 0644);
A
Andrew Morton 已提交
206
#endif
D
David Howells 已提交
207

A
Andrew Morton 已提交
208
#ifdef CONFIG_NFS_V4
D
David Howells 已提交
209 210 211 212 213 214 215 216 217 218 219 220 221
static int param_set_idmap_timeout(const char *val, struct kernel_param *kp)
{
	char *endp;
	int num = simple_strtol(val, &endp, 0);
	int jif = num * HZ;
	if (endp == val || *endp || num < 0 || jif < num)
		return -EINVAL;
	*((int *)kp->arg) = jif;
	return 0;
}

module_param_call(idmap_cache_timeout, param_set_idmap_timeout, param_get_int,
		 &nfs_idmap_cache_timeout, 0644);
A
Andrew Morton 已提交
222
#endif
D
David Howells 已提交
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

/*
 * Register the NFS filesystems
 */
int __init register_nfs_fs(void)
{
	int ret;

        ret = register_filesystem(&nfs_fs_type);
	if (ret < 0)
		goto error_0;

#ifdef CONFIG_NFS_V4
	ret = nfs_register_sysctl();
	if (ret < 0)
		goto error_1;
	ret = register_filesystem(&nfs4_fs_type);
	if (ret < 0)
		goto error_2;
#endif
	return 0;

#ifdef CONFIG_NFS_V4
error_2:
	nfs_unregister_sysctl();
error_1:
	unregister_filesystem(&nfs_fs_type);
#endif
error_0:
	return ret;
}

/*
 * Unregister the NFS filesystems
 */
void __exit unregister_nfs_fs(void)
{
#ifdef CONFIG_NFS_V4
	unregister_filesystem(&nfs4_fs_type);
	nfs_unregister_sysctl();
#endif
	unregister_filesystem(&nfs_fs_type);
}

/*
 * Deliver file system statistics to userspace
 */
270
static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
D
David Howells 已提交
271
{
272
	struct super_block *sb = dentry->d_sb;
D
David Howells 已提交
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
	struct nfs_server *server = NFS_SB(sb);
	unsigned char blockbits;
	unsigned long blockres;
	struct nfs_fh *rootfh = NFS_FH(sb->s_root->d_inode);
	struct nfs_fattr fattr;
	struct nfs_fsstat res = {
			.fattr = &fattr,
	};
	int error;

	lock_kernel();

	error = server->rpc_ops->statfs(server, rootfh, &res);
	buf->f_type = NFS_SUPER_MAGIC;
	if (error < 0)
		goto out_err;

	/*
	 * Current versions of glibc do not correctly handle the
	 * case where f_frsize != f_bsize.  Eventually we want to
	 * report the value of wtmult in this field.
	 */
	buf->f_frsize = sb->s_blocksize;

	/*
	 * On most *nix systems, f_blocks, f_bfree, and f_bavail
	 * are reported in units of f_frsize.  Linux hasn't had
	 * an f_frsize field in its statfs struct until recently,
	 * thus historically Linux's sys_statfs reports these
	 * fields in units of f_bsize.
	 */
	buf->f_bsize = sb->s_blocksize;
	blockbits = sb->s_blocksize_bits;
	blockres = (1 << blockbits) - 1;
	buf->f_blocks = (res.tbytes + blockres) >> blockbits;
	buf->f_bfree = (res.fbytes + blockres) >> blockbits;
	buf->f_bavail = (res.abytes + blockres) >> blockbits;

	buf->f_files = res.tfiles;
	buf->f_ffree = res.afiles;

	buf->f_namelen = server->namelen;
 out:
	unlock_kernel();
	return 0;

 out_err:
	dprintk("%s: statfs error = %d\n", __FUNCTION__, -error);
	buf->f_bsize = buf->f_blocks = buf->f_bfree = buf->f_bavail = -1;
	goto out;

}

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
static const char *nfs_pseudoflavour_to_name(rpc_authflavor_t flavour)
{
	static struct {
		rpc_authflavor_t flavour;
		const char *str;
	} sec_flavours[] = {
		{ RPC_AUTH_NULL, "null" },
		{ RPC_AUTH_UNIX, "sys" },
		{ RPC_AUTH_GSS_KRB5, "krb5" },
		{ RPC_AUTH_GSS_KRB5I, "krb5i" },
		{ RPC_AUTH_GSS_KRB5P, "krb5p" },
		{ RPC_AUTH_GSS_LKEY, "lkey" },
		{ RPC_AUTH_GSS_LKEYI, "lkeyi" },
		{ RPC_AUTH_GSS_LKEYP, "lkeyp" },
		{ RPC_AUTH_GSS_SPKM, "spkm" },
		{ RPC_AUTH_GSS_SPKMI, "spkmi" },
		{ RPC_AUTH_GSS_SPKMP, "spkmp" },
		{ -1, "unknown" }
	};
	int i;

	for (i=0; sec_flavours[i].flavour != -1; i++) {
		if (sec_flavours[i].flavour == flavour)
			break;
	}
	return sec_flavours[i].str;
}

D
David Howells 已提交
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
/*
 * Describe the mount options in force on this server representation
 */
static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, int showdefaults)
{
	static struct proc_nfs_info {
		int flag;
		char *str;
		char *nostr;
	} nfs_info[] = {
		{ NFS_MOUNT_SOFT, ",soft", ",hard" },
		{ NFS_MOUNT_INTR, ",intr", "" },
		{ NFS_MOUNT_NOCTO, ",nocto", "" },
		{ NFS_MOUNT_NOAC, ",noac", "" },
		{ NFS_MOUNT_NONLM, ",nolock", "" },
		{ NFS_MOUNT_NOACL, ",noacl", "" },
		{ 0, NULL, NULL }
	};
	struct proc_nfs_info *nfs_infop;
	char buf[12];
	char *proto;

	seq_printf(m, ",vers=%d", nfss->rpc_ops->version);
	seq_printf(m, ",rsize=%d", nfss->rsize);
	seq_printf(m, ",wsize=%d", nfss->wsize);
	if (nfss->acregmin != 3*HZ || showdefaults)
		seq_printf(m, ",acregmin=%d", nfss->acregmin/HZ);
	if (nfss->acregmax != 60*HZ || showdefaults)
		seq_printf(m, ",acregmax=%d", nfss->acregmax/HZ);
	if (nfss->acdirmin != 30*HZ || showdefaults)
		seq_printf(m, ",acdirmin=%d", nfss->acdirmin/HZ);
	if (nfss->acdirmax != 60*HZ || showdefaults)
		seq_printf(m, ",acdirmax=%d", nfss->acdirmax/HZ);
	for (nfs_infop = nfs_info; nfs_infop->flag; nfs_infop++) {
		if (nfss->flags & nfs_infop->flag)
			seq_puts(m, nfs_infop->str);
		else
			seq_puts(m, nfs_infop->nostr);
	}
	switch (nfss->client->cl_xprt->prot) {
		case IPPROTO_TCP:
			proto = "tcp";
			break;
		case IPPROTO_UDP:
			proto = "udp";
			break;
		default:
			snprintf(buf, sizeof(buf), "%u", nfss->client->cl_xprt->prot);
			proto = buf;
	}
	seq_printf(m, ",proto=%s", proto);
	seq_printf(m, ",timeo=%lu", 10U * nfss->retrans_timeo / HZ);
	seq_printf(m, ",retrans=%u", nfss->retrans_count);
407
	seq_printf(m, ",sec=%s", nfs_pseudoflavour_to_name(nfss->client->cl_auth->au_flavor));
D
David Howells 已提交
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
}

/*
 * Describe the mount options on this VFS mountpoint
 */
static int nfs_show_options(struct seq_file *m, struct vfsmount *mnt)
{
	struct nfs_server *nfss = NFS_SB(mnt->mnt_sb);

	nfs_show_mount_options(m, nfss, 0);

	seq_puts(m, ",addr=");
	seq_escape(m, nfss->hostname, " \t\n\\");

	return 0;
}

/*
 * Present statistical information for this VFS mountpoint
 */
static int nfs_show_stats(struct seq_file *m, struct vfsmount *mnt)
{
	int i, cpu;
	struct nfs_server *nfss = NFS_SB(mnt->mnt_sb);
	struct rpc_auth *auth = nfss->client->cl_auth;
	struct nfs_iostats totals = { };

	seq_printf(m, "statvers=%s", NFS_IOSTAT_VERS);

	/*
	 * Display all mount option settings
	 */
	seq_printf(m, "\n\topts:\t");
	seq_puts(m, mnt->mnt_sb->s_flags & MS_RDONLY ? "ro" : "rw");
	seq_puts(m, mnt->mnt_sb->s_flags & MS_SYNCHRONOUS ? ",sync" : "");
	seq_puts(m, mnt->mnt_sb->s_flags & MS_NOATIME ? ",noatime" : "");
	seq_puts(m, mnt->mnt_sb->s_flags & MS_NODIRATIME ? ",nodiratime" : "");
	nfs_show_mount_options(m, nfss, 1);

	seq_printf(m, "\n\tage:\t%lu", (jiffies - nfss->mount_time) / HZ);

	seq_printf(m, "\n\tcaps:\t");
	seq_printf(m, "caps=0x%x", nfss->caps);
	seq_printf(m, ",wtmult=%d", nfss->wtmult);
	seq_printf(m, ",dtsize=%d", nfss->dtsize);
	seq_printf(m, ",bsize=%d", nfss->bsize);
	seq_printf(m, ",namelen=%d", nfss->namelen);

#ifdef CONFIG_NFS_V4
	if (nfss->rpc_ops->version == 4) {
		seq_printf(m, "\n\tnfsv4:\t");
		seq_printf(m, "bm0=0x%x", nfss->attr_bitmask[0]);
		seq_printf(m, ",bm1=0x%x", nfss->attr_bitmask[1]);
		seq_printf(m, ",acl=0x%x", nfss->acl_bitmask);
	}
#endif

	/*
	 * Display security flavor in effect for this mount
	 */
	seq_printf(m, "\n\tsec:\tflavor=%d", auth->au_ops->au_flavor);
	if (auth->au_flavor)
		seq_printf(m, ",pseudoflavor=%d", auth->au_flavor);

	/*
	 * Display superblock I/O counters
	 */
	for_each_possible_cpu(cpu) {
		struct nfs_iostats *stats;

		preempt_disable();
		stats = per_cpu_ptr(nfss->io_stats, cpu);

		for (i = 0; i < __NFSIOS_COUNTSMAX; i++)
			totals.events[i] += stats->events[i];
		for (i = 0; i < __NFSIOS_BYTESMAX; i++)
			totals.bytes[i] += stats->bytes[i];

		preempt_enable();
	}

	seq_printf(m, "\n\tevents:\t");
	for (i = 0; i < __NFSIOS_COUNTSMAX; i++)
		seq_printf(m, "%lu ", totals.events[i]);
	seq_printf(m, "\n\tbytes:\t");
	for (i = 0; i < __NFSIOS_BYTESMAX; i++)
		seq_printf(m, "%Lu ", totals.bytes[i]);
	seq_printf(m, "\n");

	rpc_print_iostats(m, nfss->client);

	return 0;
}

/*
 * Begin unmount by attempting to remove all automounted mountpoints we added
 * in response to traversals
 */
static void nfs_umount_begin(struct vfsmount *vfsmnt, int flags)
{
	struct nfs_server *server;
	struct rpc_clnt	*rpc;

	shrink_submounts(vfsmnt, &nfs_automount_list);
	if (!(flags & MNT_FORCE))
		return;
	/* -EIO all pending I/O */
	server = NFS_SB(vfsmnt->mnt_sb);
	rpc = server->client;
	if (!IS_ERR(rpc))
		rpc_killall_tasks(rpc);
	rpc = server->client_acl;
	if (!IS_ERR(rpc))
		rpc_killall_tasks(rpc);
}

/*
 * Obtain the root inode of the file system.
 */
static struct inode *
nfs_get_root(struct super_block *sb, struct nfs_fh *rootfh, struct nfs_fsinfo *fsinfo)
{
	struct nfs_server	*server = NFS_SB(sb);
	int			error;

	error = server->rpc_ops->getroot(server, rootfh, fsinfo);
	if (error < 0) {
		dprintk("nfs_get_root: getattr error = %d\n", -error);
		return ERR_PTR(error);
	}

	server->fsid = fsinfo->fattr->fsid;
	return nfs_fhget(sb, rootfh, fsinfo->fattr);
}

/*
 * Do NFS version-independent mount processing, and sanity checking
 */
static int
nfs_sb_init(struct super_block *sb, rpc_authflavor_t authflavor)
{
	struct nfs_server	*server;
	struct inode		*root_inode;
	struct nfs_fattr	fattr;
	struct nfs_fsinfo	fsinfo = {
					.fattr = &fattr,
				};
	struct nfs_pathconf pathinfo = {
			.fattr = &fattr,
	};
	int no_root_error = 0;
	unsigned long max_rpc_payload;

	/* We probably want something more informative here */
	snprintf(sb->s_id, sizeof(sb->s_id), "%x:%x", MAJOR(sb->s_dev), MINOR(sb->s_dev));

	server = NFS_SB(sb);

	sb->s_magic      = NFS_SUPER_MAGIC;

	server->io_stats = nfs_alloc_iostats();
	if (server->io_stats == NULL)
		return -ENOMEM;

	root_inode = nfs_get_root(sb, &server->fh, &fsinfo);
	/* Did getting the root inode fail? */
	if (IS_ERR(root_inode)) {
		no_root_error = PTR_ERR(root_inode);
		goto out_no_root;
	}
	sb->s_root = d_alloc_root(root_inode);
	if (!sb->s_root) {
		no_root_error = -ENOMEM;
		goto out_no_root;
	}
	sb->s_root->d_op = server->rpc_ops->dentry_ops;

	/* mount time stamp, in seconds */
	server->mount_time = jiffies;

	/* Get some general file system info */
	if (server->namelen == 0 &&
	    server->rpc_ops->pathconf(server, &server->fh, &pathinfo) >= 0)
		server->namelen = pathinfo.max_namelen;
	/* Work out a lot of parameters */
	if (server->rsize == 0)
		server->rsize = nfs_block_size(fsinfo.rtpref, NULL);
	if (server->wsize == 0)
		server->wsize = nfs_block_size(fsinfo.wtpref, NULL);

	if (fsinfo.rtmax >= 512 && server->rsize > fsinfo.rtmax)
		server->rsize = nfs_block_size(fsinfo.rtmax, NULL);
	if (fsinfo.wtmax >= 512 && server->wsize > fsinfo.wtmax)
		server->wsize = nfs_block_size(fsinfo.wtmax, NULL);

	max_rpc_payload = nfs_block_size(rpc_max_payload(server->client), NULL);
	if (server->rsize > max_rpc_payload)
		server->rsize = max_rpc_payload;
	if (server->rsize > NFS_MAX_FILE_IO_SIZE)
		server->rsize = NFS_MAX_FILE_IO_SIZE;
	server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;

	if (server->wsize > max_rpc_payload)
		server->wsize = max_rpc_payload;
	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
		server->wsize = NFS_MAX_FILE_IO_SIZE;
	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;

	if (sb->s_blocksize == 0)
		sb->s_blocksize = nfs_block_bits(server->wsize,
							 &sb->s_blocksize_bits);
	server->wtmult = nfs_block_bits(fsinfo.wtmult, NULL);

	server->dtsize = nfs_block_size(fsinfo.dtpref, NULL);
	if (server->dtsize > PAGE_CACHE_SIZE)
		server->dtsize = PAGE_CACHE_SIZE;
	if (server->dtsize > server->rsize)
		server->dtsize = server->rsize;

	if (server->flags & NFS_MOUNT_NOAC) {
		server->acregmin = server->acregmax = 0;
		server->acdirmin = server->acdirmax = 0;
		sb->s_flags |= MS_SYNCHRONOUS;
	}
	server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;

	nfs_super_set_maxbytes(sb, fsinfo.maxfilesize);

	server->client->cl_intr = (server->flags & NFS_MOUNT_INTR) ? 1 : 0;
	server->client->cl_softrtry = (server->flags & NFS_MOUNT_SOFT) ? 1 : 0;

	/* We're airborne Set socket buffersize */
	rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100);
	return 0;
	/* Yargs. It didn't work out. */
out_no_root:
	dprintk("nfs_sb_init: get root inode failed: errno %d\n", -no_root_error);
	if (!IS_ERR(root_inode))
		iput(root_inode);
	return no_root_error;
}

/*
 * Initialise the timeout values for a connection
 */
static void nfs_init_timeout_values(struct rpc_timeout *to, int proto, unsigned int timeo, unsigned int retrans)
{
	to->to_initval = timeo * HZ / 10;
	to->to_retries = retrans;
	if (!to->to_retries)
		to->to_retries = 2;

	switch (proto) {
	case IPPROTO_TCP:
		if (!to->to_initval)
			to->to_initval = 60 * HZ;
		if (to->to_initval > NFS_MAX_TCP_TIMEOUT)
			to->to_initval = NFS_MAX_TCP_TIMEOUT;
		to->to_increment = to->to_initval;
		to->to_maxval = to->to_initval + (to->to_increment * to->to_retries);
		to->to_exponential = 0;
		break;
	case IPPROTO_UDP:
	default:
		if (!to->to_initval)
			to->to_initval = 11 * HZ / 10;
		if (to->to_initval > NFS_MAX_UDP_TIMEOUT)
			to->to_initval = NFS_MAX_UDP_TIMEOUT;
		to->to_maxval = NFS_MAX_UDP_TIMEOUT;
		to->to_exponential = 1;
		break;
	}
}

/*
 * Create an RPC client handle.
 */
static struct rpc_clnt *
nfs_create_client(struct nfs_server *server, const struct nfs_mount_data *data)
{
	struct rpc_timeout	timeparms;
	struct rpc_xprt		*xprt = NULL;
	struct rpc_clnt		*clnt = NULL;
	int			proto = (data->flags & NFS_MOUNT_TCP) ? IPPROTO_TCP : IPPROTO_UDP;

	nfs_init_timeout_values(&timeparms, proto, data->timeo, data->retrans);

	server->retrans_timeo = timeparms.to_initval;
	server->retrans_count = timeparms.to_retries;

	/* create transport and client */
	xprt = xprt_create_proto(proto, &server->addr, &timeparms);
	if (IS_ERR(xprt)) {
		dprintk("%s: cannot create RPC transport. Error = %ld\n",
				__FUNCTION__, PTR_ERR(xprt));
		return (struct rpc_clnt *)xprt;
	}
	clnt = rpc_create_client(xprt, server->hostname, &nfs_program,
				 server->rpc_ops->version, data->pseudoflavor);
	if (IS_ERR(clnt)) {
		dprintk("%s: cannot create RPC client. Error = %ld\n",
				__FUNCTION__, PTR_ERR(xprt));
		goto out_fail;
	}

	clnt->cl_intr     = 1;
	clnt->cl_softrtry = 1;

	return clnt;

out_fail:
	return clnt;
}

/*
 * Clone a server record
 */
static struct nfs_server *nfs_clone_server(struct super_block *sb, struct nfs_clone_mount *data)
{
	struct nfs_server *server = NFS_SB(sb);
	struct nfs_server *parent = NFS_SB(data->sb);
	struct inode *root_inode;
	struct nfs_fsinfo fsinfo;
	void *err = ERR_PTR(-ENOMEM);

	sb->s_op = data->sb->s_op;
	sb->s_blocksize = data->sb->s_blocksize;
	sb->s_blocksize_bits = data->sb->s_blocksize_bits;
	sb->s_maxbytes = data->sb->s_maxbytes;

	server->client_sys = server->client_acl = ERR_PTR(-EINVAL);
	server->io_stats = nfs_alloc_iostats();
	if (server->io_stats == NULL)
		goto out;

	server->client = rpc_clone_client(parent->client);
	if (IS_ERR((err = server->client)))
		goto out;

	if (!IS_ERR(parent->client_sys)) {
		server->client_sys = rpc_clone_client(parent->client_sys);
		if (IS_ERR((err = server->client_sys)))
			goto out;
	}
	if (!IS_ERR(parent->client_acl)) {
		server->client_acl = rpc_clone_client(parent->client_acl);
		if (IS_ERR((err = server->client_acl)))
			goto out;
	}
	root_inode = nfs_fhget(sb, data->fh, data->fattr);
	if (!root_inode)
		goto out;
	sb->s_root = d_alloc_root(root_inode);
	if (!sb->s_root)
		goto out_put_root;
	fsinfo.fattr = data->fattr;
	if (NFS_PROTO(root_inode)->fsinfo(server, data->fh, &fsinfo) == 0)
		nfs_super_set_maxbytes(sb, fsinfo.maxfilesize);
	sb->s_root->d_op = server->rpc_ops->dentry_ops;
	sb->s_flags |= MS_ACTIVE;
	return server;
out_put_root:
	iput(root_inode);
out:
	return err;
}

/*
 * Copy an existing superblock and attach revised data
 */
778
static int nfs_clone_generic_sb(struct nfs_clone_mount *data,
D
David Howells 已提交
779
		struct super_block *(*fill_sb)(struct nfs_server *, struct nfs_clone_mount *),
780 781
		struct nfs_server *(*fill_server)(struct super_block *, struct nfs_clone_mount *),
		struct vfsmount *mnt)
D
David Howells 已提交
782 783 784 785 786
{
	struct nfs_server *server;
	struct nfs_server *parent = NFS_SB(data->sb);
	struct super_block *sb = ERR_PTR(-EINVAL);
	char *hostname;
787
	int error = -ENOMEM;
D
David Howells 已提交
788 789 790 791 792 793 794 795 796 797 798 799
	int len;

	server = kmalloc(sizeof(struct nfs_server), GFP_KERNEL);
	if (server == NULL)
		goto out_err;
	memcpy(server, parent, sizeof(*server));
	hostname = (data->hostname != NULL) ? data->hostname : parent->hostname;
	len = strlen(hostname) + 1;
	server->hostname = kmalloc(len, GFP_KERNEL);
	if (server->hostname == NULL)
		goto free_server;
	memcpy(server->hostname, hostname, len);
800 801
	error = rpciod_up();
	if (error != 0)
D
David Howells 已提交
802 803 804
		goto free_hostname;

	sb = fill_sb(server, data);
805 806
	if (IS_ERR(sb)) {
		error = PTR_ERR(sb);
D
David Howells 已提交
807
		goto kill_rpciod;
808 809 810 811
	}
		
	if (sb->s_root)
		goto out_rpciod_down;
D
David Howells 已提交
812 813

	server = fill_server(sb, data);
814 815
	if (IS_ERR(server)) {
		error = PTR_ERR(server);
D
David Howells 已提交
816
		goto out_deactivate;
817 818
	}
	return simple_set_mnt(mnt, sb);
D
David Howells 已提交
819 820 821
out_deactivate:
	up_write(&sb->s_umount);
	deactivate_super(sb);
822 823 824 825 826 827
	return error;
out_rpciod_down:
	rpciod_down();
	kfree(server->hostname);
	kfree(server);
	return simple_set_mnt(mnt, sb);
D
David Howells 已提交
828 829 830 831 832 833 834
kill_rpciod:
	rpciod_down();
free_hostname:
	kfree(server->hostname);
free_server:
	kfree(server);
out_err:
835
	return error;
D
David Howells 已提交
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
}

/*
 * Set up an NFS2/3 superblock
 *
 * The way this works is that the mount process passes a structure
 * in the data argument which contains the server's IP address
 * and the root file handle obtained from the server's mount
 * daemon. We stash these away in the private superblock fields.
 */
static int
nfs_fill_super(struct super_block *sb, struct nfs_mount_data *data, int silent)
{
	struct nfs_server	*server;
	rpc_authflavor_t	authflavor;

	server           = NFS_SB(sb);
	sb->s_blocksize_bits = 0;
	sb->s_blocksize = 0;
	if (data->bsize)
		sb->s_blocksize = nfs_block_size(data->bsize, &sb->s_blocksize_bits);
	if (data->rsize)
		server->rsize = nfs_block_size(data->rsize, NULL);
	if (data->wsize)
		server->wsize = nfs_block_size(data->wsize, NULL);
	server->flags    = data->flags & NFS_MOUNT_FLAGMASK;

	server->acregmin = data->acregmin*HZ;
	server->acregmax = data->acregmax*HZ;
	server->acdirmin = data->acdirmin*HZ;
	server->acdirmax = data->acdirmax*HZ;

	/* Start lockd here, before we might error out */
	if (!(server->flags & NFS_MOUNT_NONLM))
		lockd_up();

	server->namelen  = data->namlen;
	server->hostname = kmalloc(strlen(data->hostname) + 1, GFP_KERNEL);
	if (!server->hostname)
		return -ENOMEM;
	strcpy(server->hostname, data->hostname);

	/* Check NFS protocol revision and initialize RPC op vector
	 * and file handle pool. */
#ifdef CONFIG_NFS_V3
	if (server->flags & NFS_MOUNT_VER3) {
		server->rpc_ops = &nfs_v3_clientops;
		server->caps |= NFS_CAP_READDIRPLUS;
	} else {
		server->rpc_ops = &nfs_v2_clientops;
	}
#else
	server->rpc_ops = &nfs_v2_clientops;
#endif

	/* Fill in pseudoflavor for mount version < 5 */
	if (!(data->flags & NFS_MOUNT_SECFLAVOUR))
		data->pseudoflavor = RPC_AUTH_UNIX;
	authflavor = data->pseudoflavor;	/* save for sb_init() */
	/* XXX maybe we want to add a server->pseudoflavor field */

	/* Create RPC client handles */
	server->client = nfs_create_client(server, data);
	if (IS_ERR(server->client))
		return PTR_ERR(server->client);
	/* RFC 2623, sec 2.3.2 */
	if (authflavor != RPC_AUTH_UNIX) {
		struct rpc_auth *auth;

		server->client_sys = rpc_clone_client(server->client);
		if (IS_ERR(server->client_sys))
			return PTR_ERR(server->client_sys);
		auth = rpcauth_create(RPC_AUTH_UNIX, server->client_sys);
		if (IS_ERR(auth))
			return PTR_ERR(auth);
	} else {
		atomic_inc(&server->client->cl_count);
		server->client_sys = server->client;
	}
	if (server->flags & NFS_MOUNT_VER3) {
#ifdef CONFIG_NFS_V3_ACL
		if (!(server->flags & NFS_MOUNT_NOACL)) {
			server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3);
			/* No errors! Assume that Sun nfsacls are supported */
			if (!IS_ERR(server->client_acl))
				server->caps |= NFS_CAP_ACLS;
		}
#else
		server->flags &= ~NFS_MOUNT_NOACL;
#endif /* CONFIG_NFS_V3_ACL */
		/*
		 * The VFS shouldn't apply the umask to mode bits. We will
		 * do so ourselves when necessary.
		 */
		sb->s_flags |= MS_POSIXACL;
		if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN)
			server->namelen = NFS3_MAXNAMLEN;
		sb->s_time_gran = 1;
	} else {
		if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
			server->namelen = NFS2_MAXNAMLEN;
	}

	sb->s_op = &nfs_sops;
	return nfs_sb_init(sb, authflavor);
}

static int nfs_set_super(struct super_block *s, void *data)
{
	s->s_fs_info = data;
	return set_anon_super(s, data);
}

static int nfs_compare_super(struct super_block *sb, void *data)
{
	struct nfs_server *server = data;
	struct nfs_server *old = NFS_SB(sb);

	if (old->addr.sin_addr.s_addr != server->addr.sin_addr.s_addr)
		return 0;
	if (old->addr.sin_port != server->addr.sin_port)
		return 0;
	return !nfs_compare_fh(&old->fh, &server->fh);
}

961 962
static int nfs_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
D
David Howells 已提交
963 964 965 966 967 968 969
{
	int error;
	struct nfs_server *server = NULL;
	struct super_block *s;
	struct nfs_fh *root;
	struct nfs_mount_data *data = raw_data;

970
	error = -EINVAL;
D
David Howells 已提交
971 972
	if (data == NULL) {
		dprintk("%s: missing data argument\n", __FUNCTION__);
973
		goto out_err_noserver;
D
David Howells 已提交
974 975 976
	}
	if (data->version <= 0 || data->version > NFS_MOUNT_VERSION) {
		dprintk("%s: bad mount version\n", __FUNCTION__);
977
		goto out_err_noserver;
D
David Howells 已提交
978 979 980 981 982 983 984 985 986 987 988
	}
	switch (data->version) {
		case 1:
			data->namlen = 0;
		case 2:
			data->bsize  = 0;
		case 3:
			if (data->flags & NFS_MOUNT_VER3) {
				dprintk("%s: mount structure version %d does not support NFSv3\n",
						__FUNCTION__,
						data->version);
989
				goto out_err_noserver;
D
David Howells 已提交
990 991 992 993 994 995 996 997
			}
			data->root.size = NFS2_FHSIZE;
			memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE);
		case 4:
			if (data->flags & NFS_MOUNT_SECFLAVOUR) {
				dprintk("%s: mount structure version %d does not support strong security\n",
						__FUNCTION__,
						data->version);
998
				goto out_err_noserver;
D
David Howells 已提交
999 1000 1001 1002 1003 1004
			}
		case 5:
			memset(data->context, 0, sizeof(data->context));
	}
#ifndef CONFIG_NFS_V3
	/* If NFSv3 is not compiled in, return -EPROTONOSUPPORT */
1005
	error = -EPROTONOSUPPORT;
D
David Howells 已提交
1006 1007
	if (data->flags & NFS_MOUNT_VER3) {
		dprintk("%s: NFSv3 not compiled into kernel\n", __FUNCTION__);
1008
		goto out_err_noserver;
D
David Howells 已提交
1009 1010 1011
	}
#endif /* CONFIG_NFS_V3 */

1012
	error = -ENOMEM;
D
David Howells 已提交
1013 1014
	server = kzalloc(sizeof(struct nfs_server), GFP_KERNEL);
	if (!server)
1015
		goto out_err_noserver;
D
David Howells 已提交
1016 1017 1018 1019 1020 1021 1022 1023 1024
	/* Zero out the NFS state stuff */
	init_nfsv4_state(server);
	server->client = server->client_sys = server->client_acl = ERR_PTR(-EINVAL);

	root = &server->fh;
	if (data->flags & NFS_MOUNT_VER3)
		root->size = data->root.size;
	else
		root->size = NFS2_FHSIZE;
1025
	error = -EINVAL;
D
David Howells 已提交
1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040
	if (root->size > sizeof(root->data)) {
		dprintk("%s: invalid root filehandle\n", __FUNCTION__);
		goto out_err;
	}
	memcpy(root->data, data->root.data, root->size);

	/* We now require that the mount process passes the remote address */
	memcpy(&server->addr, &data->addr, sizeof(server->addr));
	if (server->addr.sin_addr.s_addr == INADDR_ANY) {
		dprintk("%s: mount program didn't pass remote address!\n",
				__FUNCTION__);
		goto out_err;
	}

	/* Fire up rpciod if not yet running */
1041 1042 1043 1044
	error = rpciod_up();
	if (error < 0) {
		dprintk("%s: couldn't start rpciod! Error = %d\n",
				__FUNCTION__, error);
D
David Howells 已提交
1045 1046 1047 1048
		goto out_err;
	}

	s = sget(fs_type, nfs_compare_super, nfs_set_super, server);
1049 1050 1051 1052 1053 1054
	if (IS_ERR(s)) {
		error = PTR_ERR(s);
		goto out_err_rpciod;
	}

	if (s->s_root)
D
David Howells 已提交
1055 1056 1057 1058 1059 1060 1061 1062
		goto out_rpciod_down;

	s->s_flags = flags;

	error = nfs_fill_super(s, data, flags & MS_SILENT ? 1 : 0);
	if (error) {
		up_write(&s->s_umount);
		deactivate_super(s);
1063
		return error;
D
David Howells 已提交
1064 1065
	}
	s->s_flags |= MS_ACTIVE;
1066 1067
	return simple_set_mnt(mnt, s);

D
David Howells 已提交
1068 1069
out_rpciod_down:
	rpciod_down();
1070 1071 1072 1073 1074
	kfree(server);
	return simple_set_mnt(mnt, s);

out_err_rpciod:
	rpciod_down();
D
David Howells 已提交
1075 1076
out_err:
	kfree(server);
1077 1078
out_err_noserver:
	return error;
D
David Howells 已提交
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
}

static void nfs_kill_super(struct super_block *s)
{
	struct nfs_server *server = NFS_SB(s);

	kill_anon_super(s);

	if (!IS_ERR(server->client))
		rpc_shutdown_client(server->client);
	if (!IS_ERR(server->client_sys))
		rpc_shutdown_client(server->client_sys);
	if (!IS_ERR(server->client_acl))
		rpc_shutdown_client(server->client_acl);

	if (!(server->flags & NFS_MOUNT_NONLM))
		lockd_down();	/* release rpc.lockd */

	rpciod_down();		/* release rpciod */

	nfs_free_iostats(server->io_stats);
	kfree(server->hostname);
	kfree(server);
	nfs_release_automount_timer();
}

static struct super_block *nfs_clone_sb(struct nfs_server *server, struct nfs_clone_mount *data)
{
	struct super_block *sb;

	server->fsid = data->fattr->fsid;
	nfs_copy_fh(&server->fh, data->fh);
	sb = sget(&nfs_fs_type, nfs_compare_super, nfs_set_super, server);
	if (!IS_ERR(sb) && sb->s_root == NULL && !(server->flags & NFS_MOUNT_NONLM))
		lockd_up();
	return sb;
}

1117 1118
static int nfs_clone_nfs_sb(struct file_system_type *fs_type,
		int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
D
David Howells 已提交
1119 1120
{
	struct nfs_clone_mount *data = raw_data;
1121
	return nfs_clone_generic_sb(data, nfs_clone_sb, nfs_clone_server, mnt);
D
David Howells 已提交
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 1292 1293 1294 1295 1296 1297 1298 1299
}

#ifdef CONFIG_NFS_V4
static struct rpc_clnt *nfs4_create_client(struct nfs_server *server,
	struct rpc_timeout *timeparms, int proto, rpc_authflavor_t flavor)
{
	struct nfs4_client *clp;
	struct rpc_xprt *xprt = NULL;
	struct rpc_clnt *clnt = NULL;
	int err = -EIO;

	clp = nfs4_get_client(&server->addr.sin_addr);
	if (!clp) {
		dprintk("%s: failed to create NFS4 client.\n", __FUNCTION__);
		return ERR_PTR(err);
	}

	/* Now create transport and client */
	down_write(&clp->cl_sem);
	if (IS_ERR(clp->cl_rpcclient)) {
		xprt = xprt_create_proto(proto, &server->addr, timeparms);
		if (IS_ERR(xprt)) {
			up_write(&clp->cl_sem);
			err = PTR_ERR(xprt);
			dprintk("%s: cannot create RPC transport. Error = %d\n",
					__FUNCTION__, err);
			goto out_fail;
		}
		/* Bind to a reserved port! */
		xprt->resvport = 1;
		clnt = rpc_create_client(xprt, server->hostname, &nfs_program,
				server->rpc_ops->version, flavor);
		if (IS_ERR(clnt)) {
			up_write(&clp->cl_sem);
			err = PTR_ERR(clnt);
			dprintk("%s: cannot create RPC client. Error = %d\n",
					__FUNCTION__, err);
			goto out_fail;
		}
		clnt->cl_intr     = 1;
		clnt->cl_softrtry = 1;
		clp->cl_rpcclient = clnt;
		memcpy(clp->cl_ipaddr, server->ip_addr, sizeof(clp->cl_ipaddr));
		nfs_idmap_new(clp);
	}
	list_add_tail(&server->nfs4_siblings, &clp->cl_superblocks);
	clnt = rpc_clone_client(clp->cl_rpcclient);
	if (!IS_ERR(clnt))
		server->nfs4_state = clp;
	up_write(&clp->cl_sem);
	clp = NULL;

	if (IS_ERR(clnt)) {
		dprintk("%s: cannot create RPC client. Error = %d\n",
				__FUNCTION__, err);
		return clnt;
	}

	if (server->nfs4_state->cl_idmap == NULL) {
		dprintk("%s: failed to create idmapper.\n", __FUNCTION__);
		return ERR_PTR(-ENOMEM);
	}

	if (clnt->cl_auth->au_flavor != flavor) {
		struct rpc_auth *auth;

		auth = rpcauth_create(flavor, clnt);
		if (IS_ERR(auth)) {
			dprintk("%s: couldn't create credcache!\n", __FUNCTION__);
			return (struct rpc_clnt *)auth;
		}
	}
	return clnt;

 out_fail:
	if (clp)
		nfs4_put_client(clp);
	return ERR_PTR(err);
}

/*
 * Set up an NFS4 superblock
 */
static int nfs4_fill_super(struct super_block *sb, struct nfs4_mount_data *data, int silent)
{
	struct nfs_server *server;
	struct rpc_timeout timeparms;
	rpc_authflavor_t authflavour;
	int err = -EIO;

	sb->s_blocksize_bits = 0;
	sb->s_blocksize = 0;
	server = NFS_SB(sb);
	if (data->rsize != 0)
		server->rsize = nfs_block_size(data->rsize, NULL);
	if (data->wsize != 0)
		server->wsize = nfs_block_size(data->wsize, NULL);
	server->flags = data->flags & NFS_MOUNT_FLAGMASK;
	server->caps = NFS_CAP_ATOMIC_OPEN;

	server->acregmin = data->acregmin*HZ;
	server->acregmax = data->acregmax*HZ;
	server->acdirmin = data->acdirmin*HZ;
	server->acdirmax = data->acdirmax*HZ;

	server->rpc_ops = &nfs_v4_clientops;

	nfs_init_timeout_values(&timeparms, data->proto, data->timeo, data->retrans);

	server->retrans_timeo = timeparms.to_initval;
	server->retrans_count = timeparms.to_retries;

	/* Now create transport and client */
	authflavour = RPC_AUTH_UNIX;
	if (data->auth_flavourlen != 0) {
		if (data->auth_flavourlen != 1) {
			dprintk("%s: Invalid number of RPC auth flavours %d.\n",
					__FUNCTION__, data->auth_flavourlen);
			err = -EINVAL;
			goto out_fail;
		}
		if (copy_from_user(&authflavour, data->auth_flavours, sizeof(authflavour))) {
			err = -EFAULT;
			goto out_fail;
		}
	}

	server->client = nfs4_create_client(server, &timeparms, data->proto, authflavour);
	if (IS_ERR(server->client)) {
		err = PTR_ERR(server->client);
			dprintk("%s: cannot create RPC client. Error = %d\n",
					__FUNCTION__, err);
			goto out_fail;
	}

	sb->s_time_gran = 1;

	sb->s_op = &nfs4_sops;
	err = nfs_sb_init(sb, authflavour);

 out_fail:
	return err;
}

static int nfs4_compare_super(struct super_block *sb, void *data)
{
	struct nfs_server *server = data;
	struct nfs_server *old = NFS_SB(sb);

	if (strcmp(server->hostname, old->hostname) != 0)
		return 0;
	if (strcmp(server->mnt_path, old->mnt_path) != 0)
		return 0;
	return 1;
}

static void *
nfs_copy_user_string(char *dst, struct nfs_string *src, int maxlen)
{
	void *p = NULL;

	if (!src->len)
		return ERR_PTR(-EINVAL);
	if (src->len < maxlen)
		maxlen = src->len;
	if (dst == NULL) {
		p = dst = kmalloc(maxlen + 1, GFP_KERNEL);
		if (p == NULL)
			return ERR_PTR(-ENOMEM);
	}
	if (copy_from_user(dst, src->data, maxlen)) {
		kfree(p);
		return ERR_PTR(-EFAULT);
	}
	dst[maxlen] = '\0';
	return dst;
}

1300 1301
static int nfs4_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
D
David Howells 已提交
1302 1303 1304 1305 1306 1307 1308 1309 1310
{
	int error;
	struct nfs_server *server;
	struct super_block *s;
	struct nfs4_mount_data *data = raw_data;
	void *p;

	if (data == NULL) {
		dprintk("%s: missing data argument\n", __FUNCTION__);
1311
		return -EINVAL;
D
David Howells 已提交
1312 1313 1314
	}
	if (data->version <= 0 || data->version > NFS4_MOUNT_VERSION) {
		dprintk("%s: bad mount version\n", __FUNCTION__);
1315
		return -EINVAL;
D
David Howells 已提交
1316 1317 1318 1319
	}

	server = kzalloc(sizeof(struct nfs_server), GFP_KERNEL);
	if (!server)
1320
		return -ENOMEM;
D
David Howells 已提交
1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341
	/* Zero out the NFS state stuff */
	init_nfsv4_state(server);
	server->client = server->client_sys = server->client_acl = ERR_PTR(-EINVAL);

	p = nfs_copy_user_string(NULL, &data->hostname, 256);
	if (IS_ERR(p))
		goto out_err;
	server->hostname = p;

	p = nfs_copy_user_string(NULL, &data->mnt_path, 1024);
	if (IS_ERR(p))
		goto out_err;
	server->mnt_path = p;

	p = nfs_copy_user_string(server->ip_addr, &data->client_addr,
			sizeof(server->ip_addr) - 1);
	if (IS_ERR(p))
		goto out_err;

	/* We now require that the mount process passes the remote address */
	if (data->host_addrlen != sizeof(server->addr)) {
1342
		error = -EINVAL;
D
David Howells 已提交
1343 1344 1345
		goto out_free;
	}
	if (copy_from_user(&server->addr, data->host_addr, sizeof(server->addr))) {
1346
		error = -EFAULT;
D
David Howells 已提交
1347 1348 1349 1350 1351 1352
		goto out_free;
	}
	if (server->addr.sin_family != AF_INET ||
	    server->addr.sin_addr.s_addr == INADDR_ANY) {
		dprintk("%s: mount program didn't pass remote IP address!\n",
				__FUNCTION__);
1353
		error = -EINVAL;
D
David Howells 已提交
1354 1355 1356 1357
		goto out_free;
	}

	/* Fire up rpciod if not yet running */
1358 1359 1360 1361
	error = rpciod_up();
	if (error < 0) {
		dprintk("%s: couldn't start rpciod! Error = %d\n",
				__FUNCTION__, error);
D
David Howells 已提交
1362 1363 1364 1365 1366
		goto out_free;
	}

	s = sget(fs_type, nfs4_compare_super, nfs_set_super, server);

1367 1368
	if (IS_ERR(s)) {
		error = PTR_ERR(s);
D
David Howells 已提交
1369
		goto out_free;
1370 1371 1372 1373 1374 1375 1376 1377
	}

	if (s->s_root) {
		kfree(server->mnt_path);
		kfree(server->hostname);
		kfree(server);
		return simple_set_mnt(mnt, s);
	}
D
David Howells 已提交
1378 1379 1380 1381 1382 1383 1384

	s->s_flags = flags;

	error = nfs4_fill_super(s, data, flags & MS_SILENT ? 1 : 0);
	if (error) {
		up_write(&s->s_umount);
		deactivate_super(s);
1385
		return error;
D
David Howells 已提交
1386 1387
	}
	s->s_flags |= MS_ACTIVE;
1388
	return simple_set_mnt(mnt, s);
D
David Howells 已提交
1389
out_err:
1390
	error = PTR_ERR(p);
D
David Howells 已提交
1391 1392 1393 1394
out_free:
	kfree(server->mnt_path);
	kfree(server->hostname);
	kfree(server);
1395
	return error;
D
David Howells 已提交
1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472
}

static void nfs4_kill_super(struct super_block *sb)
{
	struct nfs_server *server = NFS_SB(sb);

	nfs_return_all_delegations(sb);
	kill_anon_super(sb);

	nfs4_renewd_prepare_shutdown(server);

	if (server->client != NULL && !IS_ERR(server->client))
		rpc_shutdown_client(server->client);

	destroy_nfsv4_state(server);

	rpciod_down();

	nfs_free_iostats(server->io_stats);
	kfree(server->hostname);
	kfree(server);
	nfs_release_automount_timer();
}

/*
 * Constructs the SERVER-side path
 */
static inline char *nfs4_dup_path(const struct dentry *dentry)
{
	char *page = (char *) __get_free_page(GFP_USER);
	char *path;

	path = nfs4_path(dentry, page, PAGE_SIZE);
	if (!IS_ERR(path)) {
		int len = PAGE_SIZE + page - path;
		char *tmp = path;

		path = kmalloc(len, GFP_KERNEL);
		if (path)
			memcpy(path, tmp, len);
		else
			path = ERR_PTR(-ENOMEM);
	}
	free_page((unsigned long)page);
	return path;
}

static struct super_block *nfs4_clone_sb(struct nfs_server *server, struct nfs_clone_mount *data)
{
	const struct dentry *dentry = data->dentry;
	struct nfs4_client *clp = server->nfs4_state;
	struct super_block *sb;

	server->fsid = data->fattr->fsid;
	nfs_copy_fh(&server->fh, data->fh);
	server->mnt_path = nfs4_dup_path(dentry);
	if (IS_ERR(server->mnt_path)) {
		sb = (struct super_block *)server->mnt_path;
		goto err;
	}
	sb = sget(&nfs4_fs_type, nfs4_compare_super, nfs_set_super, server);
	if (IS_ERR(sb) || sb->s_root)
		goto free_path;
	nfs4_server_capabilities(server, &server->fh);

	down_write(&clp->cl_sem);
	atomic_inc(&clp->cl_count);
	list_add_tail(&server->nfs4_siblings, &clp->cl_superblocks);
	up_write(&clp->cl_sem);
	return sb;
free_path:
	kfree(server->mnt_path);
err:
	server->mnt_path = NULL;
	return sb;
}

1473 1474
static int nfs_clone_nfs4_sb(struct file_system_type *fs_type,
		int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
D
David Howells 已提交
1475 1476
{
	struct nfs_clone_mount *data = raw_data;
1477
	return nfs_clone_generic_sb(data, nfs4_clone_sb, nfs_clone_server, mnt);
D
David Howells 已提交
1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529
}

static struct super_block *nfs4_referral_sb(struct nfs_server *server, struct nfs_clone_mount *data)
{
	struct super_block *sb = ERR_PTR(-ENOMEM);
	int len;

	len = strlen(data->mnt_path) + 1;
	server->mnt_path = kmalloc(len, GFP_KERNEL);
	if (server->mnt_path == NULL)
		goto err;
	memcpy(server->mnt_path, data->mnt_path, len);
	memcpy(&server->addr, data->addr, sizeof(struct sockaddr_in));

	sb = sget(&nfs4_fs_type, nfs4_compare_super, nfs_set_super, server);
	if (IS_ERR(sb) || sb->s_root)
		goto free_path;
	return sb;
free_path:
	kfree(server->mnt_path);
err:
	server->mnt_path = NULL;
	return sb;
}

static struct nfs_server *nfs4_referral_server(struct super_block *sb, struct nfs_clone_mount *data)
{
	struct nfs_server *server = NFS_SB(sb);
	struct rpc_timeout timeparms;
	int proto, timeo, retrans;
	void *err;

	proto = IPPROTO_TCP;
	/* Since we are following a referral and there may be alternatives,
	   set the timeouts and retries to low values */
	timeo = 2;
	retrans = 1;
	nfs_init_timeout_values(&timeparms, proto, timeo, retrans);

	server->client = nfs4_create_client(server, &timeparms, proto, data->authflavor);
	if (IS_ERR((err = server->client)))
		goto out_err;

	sb->s_time_gran = 1;
	sb->s_op = &nfs4_sops;
	err = ERR_PTR(nfs_sb_init(sb, data->authflavor));
	if (!IS_ERR(err))
		return server;
out_err:
	return (struct nfs_server *)err;
}

1530 1531
static int nfs_referral_nfs4_sb(struct file_system_type *fs_type,
		int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
D
David Howells 已提交
1532 1533
{
	struct nfs_clone_mount *data = raw_data;
1534
	return nfs_clone_generic_sb(data, nfs4_referral_sb, nfs4_referral_server, mnt);
D
David Howells 已提交
1535 1536 1537
}

#endif