xattr.c 20.2 KB
Newer Older
S
Sage Weil 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
#include "ceph_debug.h"
#include "super.h"
#include "decode.h"

#include <linux/xattr.h>

static bool ceph_is_valid_xattr(const char *name)
{
	return !strncmp(name, XATTR_SECURITY_PREFIX,
			XATTR_SECURITY_PREFIX_LEN) ||
	       !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
	       !strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN);
}

/*
 * These define virtual xattrs exposing the recursive directory
 * statistics and layout metadata.
 */
struct ceph_vxattr_cb {
	bool readonly;
	char *name;
	size_t (*getxattr_cb)(struct ceph_inode_info *ci, char *val,
			      size_t size);
};

/* directories */

static size_t ceph_vxattrcb_entries(struct ceph_inode_info *ci, char *val,
					size_t size)
{
	return snprintf(val, size, "%lld", ci->i_files + ci->i_subdirs);
}

static size_t ceph_vxattrcb_files(struct ceph_inode_info *ci, char *val,
				      size_t size)
{
	return snprintf(val, size, "%lld", ci->i_files);
}

static size_t ceph_vxattrcb_subdirs(struct ceph_inode_info *ci, char *val,
					size_t size)
{
	return snprintf(val, size, "%lld", ci->i_subdirs);
}

static size_t ceph_vxattrcb_rentries(struct ceph_inode_info *ci, char *val,
					 size_t size)
{
	return snprintf(val, size, "%lld", ci->i_rfiles + ci->i_rsubdirs);
}

static size_t ceph_vxattrcb_rfiles(struct ceph_inode_info *ci, char *val,
				       size_t size)
{
	return snprintf(val, size, "%lld", ci->i_rfiles);
}

static size_t ceph_vxattrcb_rsubdirs(struct ceph_inode_info *ci, char *val,
					 size_t size)
{
	return snprintf(val, size, "%lld", ci->i_rsubdirs);
}

static size_t ceph_vxattrcb_rbytes(struct ceph_inode_info *ci, char *val,
				       size_t size)
{
	return snprintf(val, size, "%lld", ci->i_rbytes);
}

static size_t ceph_vxattrcb_rctime(struct ceph_inode_info *ci, char *val,
				       size_t size)
{
	return snprintf(val, size, "%ld.%ld", (long)ci->i_rctime.tv_sec,
			(long)ci->i_rctime.tv_nsec);
}

static struct ceph_vxattr_cb ceph_dir_vxattrs[] = {
	{ true, "user.ceph.dir.entries", ceph_vxattrcb_entries},
	{ true, "user.ceph.dir.files", ceph_vxattrcb_files},
	{ true, "user.ceph.dir.subdirs", ceph_vxattrcb_subdirs},
	{ true, "user.ceph.dir.rentries", ceph_vxattrcb_rentries},
	{ true, "user.ceph.dir.rfiles", ceph_vxattrcb_rfiles},
	{ true, "user.ceph.dir.rsubdirs", ceph_vxattrcb_rsubdirs},
	{ true, "user.ceph.dir.rbytes", ceph_vxattrcb_rbytes},
	{ true, "user.ceph.dir.rctime", ceph_vxattrcb_rctime},
	{ true, NULL, NULL }
};

/* files */

static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
				   size_t size)
{
94 95 96
	int ret;

	ret = snprintf(val, size,
S
Sage Weil 已提交
97 98 99 100
		"chunk_bytes=%lld\nstripe_count=%lld\nobject_size=%lld\n",
		(unsigned long long)ceph_file_layout_su(ci->i_layout),
		(unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
		(unsigned long long)ceph_file_layout_object_size(ci->i_layout));
101 102 103 104 105
	if (ceph_file_layout_pg_preferred(ci->i_layout))
		ret += snprintf(val + ret, size, "preferred_osd=%lld\n",
			    (unsigned long long)ceph_file_layout_pg_preferred(
				    ci->i_layout));
	return ret;
S
Sage Weil 已提交
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
}

static struct ceph_vxattr_cb ceph_file_vxattrs[] = {
	{ true, "user.ceph.layout", ceph_vxattrcb_layout},
	{ NULL, NULL }
};

static struct ceph_vxattr_cb *ceph_inode_vxattrs(struct inode *inode)
{
	if (S_ISDIR(inode->i_mode))
		return ceph_dir_vxattrs;
	else if (S_ISREG(inode->i_mode))
		return ceph_file_vxattrs;
	return NULL;
}

static struct ceph_vxattr_cb *ceph_match_vxattr(struct ceph_vxattr_cb *vxattr,
						const char *name)
{
	do {
		if (strcmp(vxattr->name, name) == 0)
			return vxattr;
		vxattr++;
	} while (vxattr->name);
	return NULL;
}

static int __set_xattr(struct ceph_inode_info *ci,
			   const char *name, int name_len,
			   const char *val, int val_len,
			   int dirty,
			   int should_free_name, int should_free_val,
			   struct ceph_inode_xattr **newxattr)
{
	struct rb_node **p;
	struct rb_node *parent = NULL;
	struct ceph_inode_xattr *xattr = NULL;
	int c;
	int new = 0;

	p = &ci->i_xattrs.index.rb_node;
	while (*p) {
		parent = *p;
		xattr = rb_entry(parent, struct ceph_inode_xattr, node);
		c = strncmp(name, xattr->name, min(name_len, xattr->name_len));
		if (c < 0)
			p = &(*p)->rb_left;
		else if (c > 0)
			p = &(*p)->rb_right;
		else {
			if (name_len == xattr->name_len)
				break;
			else if (name_len < xattr->name_len)
				p = &(*p)->rb_left;
			else
				p = &(*p)->rb_right;
		}
		xattr = NULL;
	}

	if (!xattr) {
		new = 1;
		xattr = *newxattr;
		xattr->name = name;
		xattr->name_len = name_len;
		xattr->should_free_name = should_free_name;

		ci->i_xattrs.count++;
		dout("__set_xattr count=%d\n", ci->i_xattrs.count);
	} else {
		kfree(*newxattr);
		*newxattr = NULL;
		if (xattr->should_free_val)
			kfree((void *)xattr->val);

		if (should_free_name) {
			kfree((void *)name);
			name = xattr->name;
		}
		ci->i_xattrs.names_size -= xattr->name_len;
		ci->i_xattrs.vals_size -= xattr->val_len;
	}
	if (!xattr) {
		pr_err("__set_xattr ENOMEM on %p %llx.%llx xattr %s=%s\n",
		       &ci->vfs_inode, ceph_vinop(&ci->vfs_inode), name,
		       xattr->val);
		return -ENOMEM;
	}
	ci->i_xattrs.names_size += name_len;
	ci->i_xattrs.vals_size += val_len;
	if (val)
		xattr->val = val;
	else
		xattr->val = "";

	xattr->val_len = val_len;
	xattr->dirty = dirty;
	xattr->should_free_val = (val && should_free_val);

	if (new) {
		rb_link_node(&xattr->node, parent, p);
		rb_insert_color(&xattr->node, &ci->i_xattrs.index);
		dout("__set_xattr_val p=%p\n", p);
	}

	dout("__set_xattr_val added %llx.%llx xattr %p %s=%.*s\n",
	     ceph_vinop(&ci->vfs_inode), xattr, name, val_len, val);

	return 0;
}

static struct ceph_inode_xattr *__get_xattr(struct ceph_inode_info *ci,
			   const char *name)
{
	struct rb_node **p;
	struct rb_node *parent = NULL;
	struct ceph_inode_xattr *xattr = NULL;
	int c;

	p = &ci->i_xattrs.index.rb_node;
	while (*p) {
		parent = *p;
		xattr = rb_entry(parent, struct ceph_inode_xattr, node);
		c = strncmp(name, xattr->name, xattr->name_len);
		if (c < 0)
			p = &(*p)->rb_left;
		else if (c > 0)
			p = &(*p)->rb_right;
		else {
			dout("__get_xattr %s: found %.*s\n", name,
			     xattr->val_len, xattr->val);
			return xattr;
		}
	}

	dout("__get_xattr %s: not found\n", name);

	return NULL;
}

static void __free_xattr(struct ceph_inode_xattr *xattr)
{
	BUG_ON(!xattr);

	if (xattr->should_free_name)
		kfree((void *)xattr->name);
	if (xattr->should_free_val)
		kfree((void *)xattr->val);

	kfree(xattr);
}

static int __remove_xattr(struct ceph_inode_info *ci,
			  struct ceph_inode_xattr *xattr)
{
	if (!xattr)
		return -EOPNOTSUPP;

	rb_erase(&xattr->node, &ci->i_xattrs.index);

	if (xattr->should_free_name)
		kfree((void *)xattr->name);
	if (xattr->should_free_val)
		kfree((void *)xattr->val);

	ci->i_xattrs.names_size -= xattr->name_len;
	ci->i_xattrs.vals_size -= xattr->val_len;
	ci->i_xattrs.count--;
	kfree(xattr);

	return 0;
}

static int __remove_xattr_by_name(struct ceph_inode_info *ci,
			   const char *name)
{
	struct rb_node **p;
	struct ceph_inode_xattr *xattr;
	int err;

	p = &ci->i_xattrs.index.rb_node;
	xattr = __get_xattr(ci, name);
	err = __remove_xattr(ci, xattr);
	return err;
}

static char *__copy_xattr_names(struct ceph_inode_info *ci,
				char *dest)
{
	struct rb_node *p;
	struct ceph_inode_xattr *xattr = NULL;

	p = rb_first(&ci->i_xattrs.index);
	dout("__copy_xattr_names count=%d\n", ci->i_xattrs.count);

	while (p) {
		xattr = rb_entry(p, struct ceph_inode_xattr, node);
		memcpy(dest, xattr->name, xattr->name_len);
		dest[xattr->name_len] = '\0';

		dout("dest=%s %p (%s) (%d/%d)\n", dest, xattr, xattr->name,
		     xattr->name_len, ci->i_xattrs.names_size);

		dest += xattr->name_len + 1;
		p = rb_next(p);
	}

	return dest;
}

void __ceph_destroy_xattrs(struct ceph_inode_info *ci)
{
	struct rb_node *p, *tmp;
	struct ceph_inode_xattr *xattr = NULL;

	p = rb_first(&ci->i_xattrs.index);

	dout("__ceph_destroy_xattrs p=%p\n", p);

	while (p) {
		xattr = rb_entry(p, struct ceph_inode_xattr, node);
		tmp = p;
		p = rb_next(tmp);
		dout("__ceph_destroy_xattrs next p=%p (%.*s)\n", p,
		     xattr->name_len, xattr->name);
		rb_erase(tmp, &ci->i_xattrs.index);

		__free_xattr(xattr);
	}

	ci->i_xattrs.names_size = 0;
	ci->i_xattrs.vals_size = 0;
	ci->i_xattrs.index_version = 0;
	ci->i_xattrs.count = 0;
	ci->i_xattrs.index = RB_ROOT;
}

static int __build_xattrs(struct inode *inode)
{
	u32 namelen;
	u32 numattr = 0;
	void *p, *end;
	u32 len;
	const char *name, *val;
	struct ceph_inode_info *ci = ceph_inode(inode);
	int xattr_version;
	struct ceph_inode_xattr **xattrs = NULL;
	int err;
	int i;

	dout("__build_xattrs() len=%d\n",
	     ci->i_xattrs.blob ? (int)ci->i_xattrs.blob->vec.iov_len : 0);

	if (ci->i_xattrs.index_version >= ci->i_xattrs.version)
		return 0; /* already built */

	__ceph_destroy_xattrs(ci);

start:
	/* updated internal xattr rb tree */
	if (ci->i_xattrs.blob && ci->i_xattrs.blob->vec.iov_len > 4) {
		p = ci->i_xattrs.blob->vec.iov_base;
		end = p + ci->i_xattrs.blob->vec.iov_len;
		ceph_decode_32_safe(&p, end, numattr, bad);
		xattr_version = ci->i_xattrs.version;
		spin_unlock(&inode->i_lock);

		xattrs = kcalloc(numattr, sizeof(struct ceph_xattr *),
				 GFP_NOFS);
		err = -ENOMEM;
		if (!xattrs)
			goto bad_lock;
		memset(xattrs, 0, numattr*sizeof(struct ceph_xattr *));
		for (i = 0; i < numattr; i++) {
			xattrs[i] = kmalloc(sizeof(struct ceph_inode_xattr),
					    GFP_NOFS);
			if (!xattrs[i])
				goto bad_lock;
		}

		spin_lock(&inode->i_lock);
		if (ci->i_xattrs.version != xattr_version) {
			/* lost a race, retry */
			for (i = 0; i < numattr; i++)
				kfree(xattrs[i]);
			kfree(xattrs);
			goto start;
		}
		err = -EIO;
		while (numattr--) {
			ceph_decode_32_safe(&p, end, len, bad);
			namelen = len;
			name = p;
			p += len;
			ceph_decode_32_safe(&p, end, len, bad);
			val = p;
			p += len;

			err = __set_xattr(ci, name, namelen, val, len,
					  0, 0, 0, &xattrs[numattr]);

			if (err < 0)
				goto bad;
		}
		kfree(xattrs);
	}
	ci->i_xattrs.index_version = ci->i_xattrs.version;
	ci->i_xattrs.dirty = false;

	return err;
bad_lock:
	spin_lock(&inode->i_lock);
bad:
	if (xattrs) {
		for (i = 0; i < numattr; i++)
			kfree(xattrs[i]);
		kfree(xattrs);
	}
	ci->i_xattrs.names_size = 0;
	return err;
}

static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size,
				    int val_size)
{
	/*
	 * 4 bytes for the length, and additional 4 bytes per each xattr name,
	 * 4 bytes per each value
	 */
	int size = 4 + ci->i_xattrs.count*(4 + 4) +
			     ci->i_xattrs.names_size +
			     ci->i_xattrs.vals_size;
	dout("__get_required_blob_size c=%d names.size=%d vals.size=%d\n",
	     ci->i_xattrs.count, ci->i_xattrs.names_size,
	     ci->i_xattrs.vals_size);

	if (name_size)
		size += 4 + 4 + name_size + val_size;

	return size;
}

/*
 * If there are dirty xattrs, reencode xattrs into the prealloc_blob
 * and swap into place.
 */
void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
{
	struct rb_node *p;
	struct ceph_inode_xattr *xattr = NULL;
	void *dest;

	dout("__build_xattrs_blob %p\n", &ci->vfs_inode);
	if (ci->i_xattrs.dirty) {
		int need = __get_required_blob_size(ci, 0, 0);

		BUG_ON(need > ci->i_xattrs.prealloc_blob->alloc_len);

		p = rb_first(&ci->i_xattrs.index);
		dest = ci->i_xattrs.prealloc_blob->vec.iov_base;

		ceph_encode_32(&dest, ci->i_xattrs.count);
		while (p) {
			xattr = rb_entry(p, struct ceph_inode_xattr, node);

			ceph_encode_32(&dest, xattr->name_len);
			memcpy(dest, xattr->name, xattr->name_len);
			dest += xattr->name_len;
			ceph_encode_32(&dest, xattr->val_len);
			memcpy(dest, xattr->val, xattr->val_len);
			dest += xattr->val_len;

			p = rb_next(p);
		}

		/* adjust buffer len; it may be larger than we need */
		ci->i_xattrs.prealloc_blob->vec.iov_len =
			dest - ci->i_xattrs.prealloc_blob->vec.iov_base;

		ceph_buffer_put(ci->i_xattrs.blob);
		ci->i_xattrs.blob = ci->i_xattrs.prealloc_blob;
		ci->i_xattrs.prealloc_blob = NULL;
		ci->i_xattrs.dirty = false;
	}
}

ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value,
		      size_t size)
{
	struct inode *inode = dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
	int err;
	struct ceph_inode_xattr *xattr;
	struct ceph_vxattr_cb *vxattr = NULL;

	if (!ceph_is_valid_xattr(name))
		return -ENODATA;

	/* let's see if a virtual xattr was requested */
	if (vxattrs)
		vxattr = ceph_match_vxattr(vxattrs, name);

	spin_lock(&inode->i_lock);
	dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
	     ci->i_xattrs.version, ci->i_xattrs.index_version);

	if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1) &&
	    (ci->i_xattrs.index_version >= ci->i_xattrs.version)) {
		goto get_xattr;
	} else {
		spin_unlock(&inode->i_lock);
		/* get xattrs from mds (if we don't already have them) */
		err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR);
		if (err)
			return err;
	}

	spin_lock(&inode->i_lock);

	if (vxattr && vxattr->readonly) {
		err = vxattr->getxattr_cb(ci, value, size);
		goto out;
	}

	err = __build_xattrs(inode);
	if (err < 0)
		goto out;

get_xattr:
	err = -ENODATA;  /* == ENOATTR */
	xattr = __get_xattr(ci, name);
	if (!xattr) {
		if (vxattr)
			err = vxattr->getxattr_cb(ci, value, size);
		goto out;
	}

	err = -ERANGE;
	if (size && size < xattr->val_len)
		goto out;

	err = xattr->val_len;
	if (size == 0)
		goto out;

	memcpy(value, xattr->val, xattr->val_len);

out:
	spin_unlock(&inode->i_lock);
	return err;
}

ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
{
	struct inode *inode = dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
	u32 vir_namelen = 0;
	u32 namelen;
	int err;
	u32 len;
	int i;

	spin_lock(&inode->i_lock);
	dout("listxattr %p ver=%lld index_ver=%lld\n", inode,
	     ci->i_xattrs.version, ci->i_xattrs.index_version);

	if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1) &&
	    (ci->i_xattrs.index_version > ci->i_xattrs.version)) {
		goto list_xattr;
	} else {
		spin_unlock(&inode->i_lock);
		err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR);
		if (err)
			return err;
	}

	spin_lock(&inode->i_lock);

	err = __build_xattrs(inode);
	if (err < 0)
		goto out;

list_xattr:
	vir_namelen = 0;
	/* include virtual dir xattrs */
	if (vxattrs)
		for (i = 0; vxattrs[i].name; i++)
			vir_namelen += strlen(vxattrs[i].name) + 1;
	/* adding 1 byte per each variable due to the null termination */
	namelen = vir_namelen + ci->i_xattrs.names_size + ci->i_xattrs.count;
	err = -ERANGE;
	if (size && namelen > size)
		goto out;

	err = namelen;
	if (size == 0)
		goto out;

	names = __copy_xattr_names(ci, names);

	/* virtual xattr names, too */
	if (vxattrs)
		for (i = 0; vxattrs[i].name; i++) {
			len = sprintf(names, "%s", vxattrs[i].name);
			names += len + 1;
		}

out:
	spin_unlock(&inode->i_lock);
	return err;
}

static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
			      const char *value, size_t size, int flags)
{
	struct ceph_client *client = ceph_client(dentry->d_sb);
	struct inode *inode = dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct inode *parent_inode = dentry->d_parent->d_inode;
	struct ceph_mds_request *req;
	struct ceph_mds_client *mdsc = &client->mdsc;
	int err;
	int i, nr_pages;
	struct page **pages = NULL;
	void *kaddr;

	/* copy value into some pages */
	nr_pages = calc_pages_for(0, size);
	if (nr_pages) {
		pages = kmalloc(sizeof(pages[0])*nr_pages, GFP_NOFS);
		if (!pages)
			return -ENOMEM;
		err = -ENOMEM;
		for (i = 0; i < nr_pages; i++) {
			pages[i] = alloc_page(GFP_NOFS);
			if (!pages[i]) {
				nr_pages = i;
				goto out;
			}
			kaddr = kmap(pages[i]);
			memcpy(kaddr, value + i*PAGE_CACHE_SIZE,
			       min(PAGE_CACHE_SIZE, size-i*PAGE_CACHE_SIZE));
		}
	}

	dout("setxattr value=%.*s\n", (int)size, value);

	/* do request */
	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETXATTR,
				       USE_AUTH_MDS);
	if (IS_ERR(req))
		return PTR_ERR(req);
	req->r_inode = igrab(inode);
	req->r_inode_drop = CEPH_CAP_XATTR_SHARED;
	req->r_num_caps = 1;
	req->r_args.setxattr.flags = cpu_to_le32(flags);
	req->r_path2 = kstrdup(name, GFP_NOFS);

	req->r_pages = pages;
	req->r_num_pages = nr_pages;
	req->r_data_len = size;

	dout("xattr.ver (before): %lld\n", ci->i_xattrs.version);
	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
	ceph_mdsc_put_request(req);
	dout("xattr.ver (after): %lld\n", ci->i_xattrs.version);

out:
	if (pages) {
		for (i = 0; i < nr_pages; i++)
			__free_page(pages[i]);
		kfree(pages);
	}
	return err;
}

int ceph_setxattr(struct dentry *dentry, const char *name,
		  const void *value, size_t size, int flags)
{
	struct inode *inode = dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
	int err;
	int name_len = strlen(name);
	int val_len = size;
	char *newname = NULL;
	char *newval = NULL;
	struct ceph_inode_xattr *xattr = NULL;
	int issued;
	int required_blob_size;

	if (ceph_snap(inode) != CEPH_NOSNAP)
		return -EROFS;

	if (!ceph_is_valid_xattr(name))
		return -EOPNOTSUPP;

	if (vxattrs) {
		struct ceph_vxattr_cb *vxattr =
			ceph_match_vxattr(vxattrs, name);
		if (vxattr && vxattr->readonly)
			return -EOPNOTSUPP;
	}

	/* preallocate memory for xattr name, value, index node */
	err = -ENOMEM;
	newname = kmalloc(name_len + 1, GFP_NOFS);
	if (!newname)
		goto out;
	memcpy(newname, name, name_len + 1);

	if (val_len) {
		newval = kmalloc(val_len + 1, GFP_NOFS);
		if (!newval)
			goto out;
		memcpy(newval, value, val_len);
		newval[val_len] = '\0';
	}

	xattr = kmalloc(sizeof(struct ceph_inode_xattr), GFP_NOFS);
	if (!xattr)
		goto out;

	spin_lock(&inode->i_lock);
retry:
	issued = __ceph_caps_issued(ci, NULL);
	if (!(issued & CEPH_CAP_XATTR_EXCL))
		goto do_sync;
	__build_xattrs(inode);

	required_blob_size = __get_required_blob_size(ci, name_len, val_len);

	if (!ci->i_xattrs.prealloc_blob ||
	    required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) {
		struct ceph_buffer *blob = NULL;

		spin_unlock(&inode->i_lock);
		dout(" preaallocating new blob size=%d\n", required_blob_size);
		blob = ceph_buffer_new_alloc(required_blob_size, GFP_NOFS);
		if (!blob)
			goto out;
		spin_lock(&inode->i_lock);
		ceph_buffer_put(ci->i_xattrs.prealloc_blob);
		ci->i_xattrs.prealloc_blob = blob;
		goto retry;
	}

	dout("setxattr %p issued %s\n", inode, ceph_cap_string(issued));
	err = __set_xattr(ci, newname, name_len, newval,
			  val_len, 1, 1, 1, &xattr);
	__ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
	ci->i_xattrs.dirty = true;
	inode->i_ctime = CURRENT_TIME;
	spin_unlock(&inode->i_lock);

	return err;

do_sync:
	spin_unlock(&inode->i_lock);
	err = ceph_sync_setxattr(dentry, name, value, size, flags);
out:
	kfree(newname);
	kfree(newval);
	kfree(xattr);
	return err;
}

static int ceph_send_removexattr(struct dentry *dentry, const char *name)
{
	struct ceph_client *client = ceph_client(dentry->d_sb);
	struct ceph_mds_client *mdsc = &client->mdsc;
	struct inode *inode = dentry->d_inode;
	struct inode *parent_inode = dentry->d_parent->d_inode;
	struct ceph_mds_request *req;
	int err;

	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_RMXATTR,
				       USE_AUTH_MDS);
	if (IS_ERR(req))
		return PTR_ERR(req);
	req->r_inode = igrab(inode);
	req->r_inode_drop = CEPH_CAP_XATTR_SHARED;
	req->r_num_caps = 1;
	req->r_path2 = kstrdup(name, GFP_NOFS);

	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
	ceph_mdsc_put_request(req);
	return err;
}

int ceph_removexattr(struct dentry *dentry, const char *name)
{
	struct inode *inode = dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
	int issued;
	int err;

	if (ceph_snap(inode) != CEPH_NOSNAP)
		return -EROFS;

	if (!ceph_is_valid_xattr(name))
		return -EOPNOTSUPP;

	if (vxattrs) {
		struct ceph_vxattr_cb *vxattr =
			ceph_match_vxattr(vxattrs, name);
		if (vxattr && vxattr->readonly)
			return -EOPNOTSUPP;
	}

	spin_lock(&inode->i_lock);
	__build_xattrs(inode);
	issued = __ceph_caps_issued(ci, NULL);
	dout("removexattr %p issued %s\n", inode, ceph_cap_string(issued));

	if (!(issued & CEPH_CAP_XATTR_EXCL))
		goto do_sync;

	err = __remove_xattr_by_name(ceph_inode(inode), name);
	__ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
	ci->i_xattrs.dirty = true;
	inode->i_ctime = CURRENT_TIME;

	spin_unlock(&inode->i_lock);

	return err;
do_sync:
	spin_unlock(&inode->i_lock);
	err = ceph_send_removexattr(dentry, name);
	return err;
}