inode.c 51.6 KB
Newer Older
1
#include <linux/ceph/ceph_debug.h>
S
Sage Weil 已提交
2 3 4 5 6 7 8 9 10 11 12 13

#include <linux/module.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/uaccess.h>
#include <linux/kernel.h>
#include <linux/namei.h>
#include <linux/writeback.h>
#include <linux/vmalloc.h>

#include "super.h"
14
#include "mds_client.h"
15
#include "cache.h"
16
#include <linux/ceph/decode.h>
S
Sage Weil 已提交
17 18 19 20 21 22 23 24 25 26 27 28 29 30 31

/*
 * Ceph inode operations
 *
 * Implement basic inode helpers (get, alloc) and inode ops (getattr,
 * setattr, etc.), xattr helpers, and helpers for assimilating
 * metadata returned by the MDS into our cache.
 *
 * Also define helpers for doing asynchronous writeback, invalidation,
 * and truncation for the benefit of those who can't afford to block
 * (typically because they are in the message handler path).
 */

static const struct inode_operations ceph_symlink_iops;

32 33 34
static void ceph_invalidate_work(struct work_struct *work);
static void ceph_writeback_work(struct work_struct *work);
static void ceph_vmtruncate_work(struct work_struct *work);
S
Sage Weil 已提交
35 36 37 38

/*
 * find or create an inode, given the ceph ino number
 */
Y
Yehuda Sadeh 已提交
39 40 41 42 43 44 45
static int ceph_set_ino_cb(struct inode *inode, void *data)
{
	ceph_inode(inode)->i_vino = *(struct ceph_vino *)data;
	inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data);
	return 0;
}

S
Sage Weil 已提交
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
struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino)
{
	struct inode *inode;
	ino_t t = ceph_vino_to_ino(vino);

	inode = iget5_locked(sb, t, ceph_ino_compare, ceph_set_ino_cb, &vino);
	if (inode == NULL)
		return ERR_PTR(-ENOMEM);
	if (inode->i_state & I_NEW) {
		dout("get_inode created new inode %p %llx.%llx ino %llx\n",
		     inode, ceph_vinop(inode), (u64)inode->i_ino);
		unlock_new_inode(inode);
	}

	dout("get_inode on %lu=%llx.%llx got %p\n", inode->i_ino, vino.ino,
	     vino.snap, inode);
	return inode;
}

/*
 * get/constuct snapdir inode for a given directory
 */
struct inode *ceph_get_snapdir(struct inode *parent)
{
	struct ceph_vino vino = {
		.ino = ceph_ino(parent),
		.snap = CEPH_SNAPDIR,
	};
	struct inode *inode = ceph_get_inode(parent->i_sb, vino);
75
	struct ceph_inode_info *ci = ceph_inode(inode);
S
Sage Weil 已提交
76 77 78

	BUG_ON(!S_ISDIR(parent->i_mode));
	if (IS_ERR(inode))
J
Julia Lawall 已提交
79
		return inode;
S
Sage Weil 已提交
80 81 82 83 84
	inode->i_mode = parent->i_mode;
	inode->i_uid = parent->i_uid;
	inode->i_gid = parent->i_gid;
	inode->i_op = &ceph_dir_iops;
	inode->i_fop = &ceph_dir_fops;
85 86
	ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */
	ci->i_rbytes = 0;
S
Sage Weil 已提交
87 88 89 90 91 92 93 94 95 96 97
	return inode;
}

const struct inode_operations ceph_file_iops = {
	.permission = ceph_permission,
	.setattr = ceph_setattr,
	.getattr = ceph_getattr,
	.setxattr = ceph_setxattr,
	.getxattr = ceph_getxattr,
	.listxattr = ceph_listxattr,
	.removexattr = ceph_removexattr,
G
Guangliang Zhao 已提交
98
	.get_acl = ceph_get_acl,
S
Sage Weil 已提交
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
};


/*
 * We use a 'frag tree' to keep track of the MDS's directory fragments
 * for a given inode (usually there is just a single fragment).  We
 * need to know when a child frag is delegated to a new MDS, or when
 * it is flagged as replicated, so we can direct our requests
 * accordingly.
 */

/*
 * find/create a frag in the tree
 */
static struct ceph_inode_frag *__get_or_create_frag(struct ceph_inode_info *ci,
						    u32 f)
{
	struct rb_node **p;
	struct rb_node *parent = NULL;
	struct ceph_inode_frag *frag;
	int c;

	p = &ci->i_fragtree.rb_node;
	while (*p) {
		parent = *p;
		frag = rb_entry(parent, struct ceph_inode_frag, node);
		c = ceph_frag_compare(f, frag->frag);
		if (c < 0)
			p = &(*p)->rb_left;
		else if (c > 0)
			p = &(*p)->rb_right;
		else
			return frag;
	}

	frag = kmalloc(sizeof(*frag), GFP_NOFS);
	if (!frag) {
		pr_err("__get_or_create_frag ENOMEM on %p %llx.%llx "
		       "frag %x\n", &ci->vfs_inode,
		       ceph_vinop(&ci->vfs_inode), f);
		return ERR_PTR(-ENOMEM);
	}
	frag->frag = f;
	frag->split_by = 0;
	frag->mds = -1;
	frag->ndist = 0;

	rb_link_node(&frag->node, parent, p);
	rb_insert_color(&frag->node, &ci->i_fragtree);

	dout("get_or_create_frag added %llx.%llx frag %x\n",
	     ceph_vinop(&ci->vfs_inode), f);
	return frag;
}

/*
 * find a specific frag @f
 */
struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci, u32 f)
{
	struct rb_node *n = ci->i_fragtree.rb_node;

	while (n) {
		struct ceph_inode_frag *frag =
			rb_entry(n, struct ceph_inode_frag, node);
		int c = ceph_frag_compare(f, frag->frag);
		if (c < 0)
			n = n->rb_left;
		else if (c > 0)
			n = n->rb_right;
		else
			return frag;
	}
	return NULL;
}

/*
 * Choose frag containing the given value @v.  If @pfrag is
 * specified, copy the frag delegation info to the caller if
 * it is present.
 */
u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
		     struct ceph_inode_frag *pfrag,
		     int *found)
{
	u32 t = ceph_frag_make(0, 0);
	struct ceph_inode_frag *frag;
	unsigned nway, i;
	u32 n;

	if (found)
		*found = 0;

	mutex_lock(&ci->i_fragtree_mutex);
	while (1) {
		WARN_ON(!ceph_frag_contains_value(t, v));
		frag = __ceph_find_frag(ci, t);
		if (!frag)
			break; /* t is a leaf */
		if (frag->split_by == 0) {
			if (pfrag)
				memcpy(pfrag, frag, sizeof(*pfrag));
			if (found)
				*found = 1;
			break;
		}

		/* choose child */
		nway = 1 << frag->split_by;
		dout("choose_frag(%x) %x splits by %d (%d ways)\n", v, t,
		     frag->split_by, nway);
		for (i = 0; i < nway; i++) {
			n = ceph_frag_make_child(t, frag->split_by, i);
			if (ceph_frag_contains_value(n, v)) {
				t = n;
				break;
			}
		}
		BUG_ON(i == nway);
	}
	dout("choose_frag(%x) = %x\n", v, t);

	mutex_unlock(&ci->i_fragtree_mutex);
	return t;
}

/*
 * Process dirfrag (delegation) info from the mds.  Include leaf
 * fragment in tree ONLY if ndist > 0.  Otherwise, only
 * branches/splits are included in i_fragtree)
 */
static int ceph_fill_dirfrag(struct inode *inode,
			     struct ceph_mds_reply_dirfrag *dirinfo)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_inode_frag *frag;
	u32 id = le32_to_cpu(dirinfo->frag);
	int mds = le32_to_cpu(dirinfo->auth);
	int ndist = le32_to_cpu(dirinfo->ndist);
	int i;
	int err = 0;

	mutex_lock(&ci->i_fragtree_mutex);
	if (ndist == 0) {
		/* no delegation info needed. */
		frag = __ceph_find_frag(ci, id);
		if (!frag)
			goto out;
		if (frag->split_by == 0) {
			/* tree leaf, remove */
			dout("fill_dirfrag removed %llx.%llx frag %x"
			     " (no ref)\n", ceph_vinop(inode), id);
			rb_erase(&frag->node, &ci->i_fragtree);
			kfree(frag);
		} else {
			/* tree branch, keep and clear */
			dout("fill_dirfrag cleared %llx.%llx frag %x"
			     " referral\n", ceph_vinop(inode), id);
			frag->mds = -1;
			frag->ndist = 0;
		}
		goto out;
	}


	/* find/add this frag to store mds delegation info */
	frag = __get_or_create_frag(ci, id);
	if (IS_ERR(frag)) {
		/* this is not the end of the world; we can continue
		   with bad/inaccurate delegation info */
		pr_err("fill_dirfrag ENOMEM on mds ref %llx.%llx fg %x\n",
		       ceph_vinop(inode), le32_to_cpu(dirinfo->frag));
		err = -ENOMEM;
		goto out;
	}

	frag->mds = mds;
	frag->ndist = min_t(u32, ndist, CEPH_MAX_DIRFRAG_REP);
	for (i = 0; i < frag->ndist; i++)
		frag->dist[i] = le32_to_cpu(dirinfo->dist[i]);
	dout("fill_dirfrag %llx.%llx frag %x ndist=%d\n",
	     ceph_vinop(inode), frag->frag, frag->ndist);

out:
	mutex_unlock(&ci->i_fragtree_mutex);
	return err;
}


/*
 * initialize a newly allocated inode.
 */
struct inode *ceph_alloc_inode(struct super_block *sb)
{
	struct ceph_inode_info *ci;
	int i;

	ci = kmem_cache_alloc(ceph_inode_cachep, GFP_NOFS);
	if (!ci)
		return NULL;

	dout("alloc_inode %p\n", &ci->vfs_inode);

302 303
	spin_lock_init(&ci->i_ceph_lock);

S
Sage Weil 已提交
304 305 306
	ci->i_version = 0;
	ci->i_time_warp_seq = 0;
	ci->i_ceph_flags = 0;
307 308
	atomic_set(&ci->i_release_count, 1);
	atomic_set(&ci->i_complete_count, 0);
S
Sage Weil 已提交
309 310
	ci->i_symlink = NULL;

S
Sage Weil 已提交
311 312
	memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout));

S
Sage Weil 已提交
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
	ci->i_fragtree = RB_ROOT;
	mutex_init(&ci->i_fragtree_mutex);

	ci->i_xattrs.blob = NULL;
	ci->i_xattrs.prealloc_blob = NULL;
	ci->i_xattrs.dirty = false;
	ci->i_xattrs.index = RB_ROOT;
	ci->i_xattrs.count = 0;
	ci->i_xattrs.names_size = 0;
	ci->i_xattrs.vals_size = 0;
	ci->i_xattrs.version = 0;
	ci->i_xattrs.index_version = 0;

	ci->i_caps = RB_ROOT;
	ci->i_auth_cap = NULL;
	ci->i_dirty_caps = 0;
	ci->i_flushing_caps = 0;
	INIT_LIST_HEAD(&ci->i_dirty_item);
	INIT_LIST_HEAD(&ci->i_flushing_item);
	ci->i_cap_flush_seq = 0;
	ci->i_cap_flush_last_tid = 0;
	memset(&ci->i_cap_flush_tid, 0, sizeof(ci->i_cap_flush_tid));
	init_waitqueue_head(&ci->i_cap_wq);
	ci->i_hold_caps_min = 0;
	ci->i_hold_caps_max = 0;
	INIT_LIST_HEAD(&ci->i_cap_delay_list);
	ci->i_cap_exporting_mds = 0;
	ci->i_cap_exporting_mseq = 0;
	ci->i_cap_exporting_issued = 0;
	INIT_LIST_HEAD(&ci->i_cap_snaps);
	ci->i_head_snapc = NULL;
	ci->i_snap_caps = 0;

	for (i = 0; i < CEPH_FILE_MODE_NUM; i++)
		ci->i_nr_by_mode[i] = 0;

Y
Yan, Zheng 已提交
349
	mutex_init(&ci->i_truncate_mutex);
S
Sage Weil 已提交
350 351 352 353 354 355 356 357 358 359 360 361 362
	ci->i_truncate_seq = 0;
	ci->i_truncate_size = 0;
	ci->i_truncate_pending = 0;

	ci->i_max_size = 0;
	ci->i_reported_size = 0;
	ci->i_wanted_max_size = 0;
	ci->i_requested_max_size = 0;

	ci->i_pin_ref = 0;
	ci->i_rd_ref = 0;
	ci->i_rdcache_ref = 0;
	ci->i_wr_ref = 0;
363
	ci->i_wb_ref = 0;
S
Sage Weil 已提交
364 365 366 367 368 369 370 371 372 373 374 375 376 377
	ci->i_wrbuffer_ref = 0;
	ci->i_wrbuffer_ref_head = 0;
	ci->i_shared_gen = 0;
	ci->i_rdcache_gen = 0;
	ci->i_rdcache_revoking = 0;

	INIT_LIST_HEAD(&ci->i_unsafe_writes);
	INIT_LIST_HEAD(&ci->i_unsafe_dirops);
	spin_lock_init(&ci->i_unsafe_lock);

	ci->i_snap_realm = NULL;
	INIT_LIST_HEAD(&ci->i_snap_realm_item);
	INIT_LIST_HEAD(&ci->i_snap_flush_item);

378 379
	INIT_WORK(&ci->i_wb_work, ceph_writeback_work);
	INIT_WORK(&ci->i_pg_inv_work, ceph_invalidate_work);
S
Sage Weil 已提交
380 381 382

	INIT_WORK(&ci->i_vmtruncate_work, ceph_vmtruncate_work);

383 384
	ceph_fscache_inode_init(ci);

S
Sage Weil 已提交
385 386 387
	return &ci->vfs_inode;
}

N
Nick Piggin 已提交
388 389 390 391 392 393 394 395
static void ceph_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	struct ceph_inode_info *ci = ceph_inode(inode);

	kmem_cache_free(ceph_inode_cachep, ci);
}

S
Sage Weil 已提交
396 397 398 399 400 401 402 403
void ceph_destroy_inode(struct inode *inode)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_inode_frag *frag;
	struct rb_node *n;

	dout("destroy_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode));

404 405
	ceph_fscache_unregister_inode_cookie(ci);

S
Sage Weil 已提交
406 407
	ceph_queue_caps_release(inode);

408 409 410 411 412 413
	/*
	 * we may still have a snap_realm reference if there are stray
	 * caps in i_cap_exporting_issued or i_snap_caps.
	 */
	if (ci->i_snap_realm) {
		struct ceph_mds_client *mdsc =
414
			ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
415 416 417 418 419 420 421 422 423
		struct ceph_snap_realm *realm = ci->i_snap_realm;

		dout(" dropping residual ref to snap realm %p\n", realm);
		spin_lock(&realm->inodes_with_caps_lock);
		list_del_init(&ci->i_snap_realm_item);
		spin_unlock(&realm->inodes_with_caps_lock);
		ceph_put_snap_realm(mdsc, realm);
	}

S
Sage Weil 已提交
424 425 426 427 428 429 430 431
	kfree(ci->i_symlink);
	while ((n = rb_first(&ci->i_fragtree)) != NULL) {
		frag = rb_entry(n, struct ceph_inode_frag, node);
		rb_erase(n, &ci->i_fragtree);
		kfree(frag);
	}

	__ceph_destroy_xattrs(ci);
S
Sage Weil 已提交
432 433 434 435
	if (ci->i_xattrs.blob)
		ceph_buffer_put(ci->i_xattrs.blob);
	if (ci->i_xattrs.prealloc_blob)
		ceph_buffer_put(ci->i_xattrs.prealloc_blob);
S
Sage Weil 已提交
436

N
Nick Piggin 已提交
437
	call_rcu(&inode->i_rcu, ceph_i_callback);
S
Sage Weil 已提交
438 439
}

Y
Yan, Zheng 已提交
440 441 442 443 444 445 446 447 448 449
int ceph_drop_inode(struct inode *inode)
{
	/*
	 * Positve dentry and corresponding inode are always accompanied
	 * in MDS reply. So no need to keep inode in the cache after
	 * dropping all its aliases.
	 */
	return 1;
}

S
Sage Weil 已提交
450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473
/*
 * Helpers to fill in size, ctime, mtime, and atime.  We have to be
 * careful because either the client or MDS may have more up to date
 * info, depending on which capabilities are held, and whether
 * time_warp_seq or truncate_seq have increased.  (Ordinarily, mtime
 * and size are monotonically increasing, except when utimes() or
 * truncate() increments the corresponding _seq values.)
 */
int ceph_fill_file_size(struct inode *inode, int issued,
			u32 truncate_seq, u64 truncate_size, u64 size)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	int queue_trunc = 0;

	if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) > 0 ||
	    (truncate_seq == ci->i_truncate_seq && size > inode->i_size)) {
		dout("size %lld -> %llu\n", inode->i_size, size);
		inode->i_size = size;
		inode->i_blocks = (size + (1<<9) - 1) >> 9;
		ci->i_reported_size = size;
		if (truncate_seq != ci->i_truncate_seq) {
			dout("truncate_seq %u -> %u\n",
			     ci->i_truncate_seq, truncate_seq);
			ci->i_truncate_seq = truncate_seq;
Y
Yan, Zheng 已提交
474 475 476 477 478 479

			/* the MDS should have revoked these caps */
			WARN_ON_ONCE(issued & (CEPH_CAP_FILE_EXCL |
					       CEPH_CAP_FILE_RD |
					       CEPH_CAP_FILE_WR |
					       CEPH_CAP_FILE_LAZYIO));
480 481 482 483 484 485
			/*
			 * If we hold relevant caps, or in the case where we're
			 * not the only client referencing this file and we
			 * don't hold those caps, then we need to check whether
			 * the file is either opened or mmaped
			 */
Y
Yan, Zheng 已提交
486 487
			if ((issued & (CEPH_CAP_FILE_CACHE|
				       CEPH_CAP_FILE_BUFFER)) ||
488 489
			    mapping_mapped(inode->i_mapping) ||
			    __ceph_caps_file_wanted(ci)) {
S
Sage Weil 已提交
490 491 492 493 494 495 496 497 498 499 500
				ci->i_truncate_pending++;
				queue_trunc = 1;
			}
		}
	}
	if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) >= 0 &&
	    ci->i_truncate_size != truncate_size) {
		dout("truncate_size %lld -> %llu\n", ci->i_truncate_size,
		     truncate_size);
		ci->i_truncate_size = truncate_size;
	}
501 502 503 504

	if (queue_trunc)
		ceph_fscache_invalidate(inode);

S
Sage Weil 已提交
505 506 507 508 509 510 511 512 513 514 515 516
	return queue_trunc;
}

void ceph_fill_file_time(struct inode *inode, int issued,
			 u64 time_warp_seq, struct timespec *ctime,
			 struct timespec *mtime, struct timespec *atime)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	int warn = 0;

	if (issued & (CEPH_CAP_FILE_EXCL|
		      CEPH_CAP_FILE_WR|
S
Sage Weil 已提交
517 518 519
		      CEPH_CAP_FILE_BUFFER|
		      CEPH_CAP_AUTH_EXCL|
		      CEPH_CAP_XATTR_EXCL)) {
S
Sage Weil 已提交
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
		if (timespec_compare(ctime, &inode->i_ctime) > 0) {
			dout("ctime %ld.%09ld -> %ld.%09ld inc w/ cap\n",
			     inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
			     ctime->tv_sec, ctime->tv_nsec);
			inode->i_ctime = *ctime;
		}
		if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) > 0) {
			/* the MDS did a utimes() */
			dout("mtime %ld.%09ld -> %ld.%09ld "
			     "tw %d -> %d\n",
			     inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec,
			     mtime->tv_sec, mtime->tv_nsec,
			     ci->i_time_warp_seq, (int)time_warp_seq);

			inode->i_mtime = *mtime;
			inode->i_atime = *atime;
			ci->i_time_warp_seq = time_warp_seq;
		} else if (time_warp_seq == ci->i_time_warp_seq) {
			/* nobody did utimes(); take the max */
			if (timespec_compare(mtime, &inode->i_mtime) > 0) {
				dout("mtime %ld.%09ld -> %ld.%09ld inc\n",
				     inode->i_mtime.tv_sec,
				     inode->i_mtime.tv_nsec,
				     mtime->tv_sec, mtime->tv_nsec);
				inode->i_mtime = *mtime;
			}
			if (timespec_compare(atime, &inode->i_atime) > 0) {
				dout("atime %ld.%09ld -> %ld.%09ld inc\n",
				     inode->i_atime.tv_sec,
				     inode->i_atime.tv_nsec,
				     atime->tv_sec, atime->tv_nsec);
				inode->i_atime = *atime;
			}
		} else if (issued & CEPH_CAP_FILE_EXCL) {
			/* we did a utimes(); ignore mds values */
		} else {
			warn = 1;
		}
	} else {
S
Sage Weil 已提交
559
		/* we have no write|excl caps; whatever the MDS says is true */
S
Sage Weil 已提交
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
		if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) >= 0) {
			inode->i_ctime = *ctime;
			inode->i_mtime = *mtime;
			inode->i_atime = *atime;
			ci->i_time_warp_seq = time_warp_seq;
		} else {
			warn = 1;
		}
	}
	if (warn) /* time_warp_seq shouldn't go backwards */
		dout("%p mds time_warp_seq %llu < %u\n",
		     inode, time_warp_seq, ci->i_time_warp_seq);
}

/*
 * Populate an inode based on info from mds.  May be called on new or
 * existing inodes.
 */
static int fill_inode(struct inode *inode,
		      struct ceph_mds_reply_info_in *iinfo,
		      struct ceph_mds_reply_dirfrag *dirinfo,
		      struct ceph_mds_session *session,
		      unsigned long ttl_from, int cap_fmode,
		      struct ceph_cap_reservation *caps_reservation)
{
	struct ceph_mds_reply_inode *info = iinfo->in;
	struct ceph_inode_info *ci = ceph_inode(inode);
	int i;
588
	int issued = 0, implemented;
S
Sage Weil 已提交
589 590
	struct timespec mtime, atime, ctime;
	u32 nsplits;
591 592
	struct ceph_inode_frag *frag;
	struct rb_node *rb_node;
S
Sage Weil 已提交
593 594 595 596 597 598 599 600 601 602 603 604 605 606
	struct ceph_buffer *xattr_blob = NULL;
	int err = 0;
	int queue_trunc = 0;

	dout("fill_inode %p ino %llx.%llx v %llu had %llu\n",
	     inode, ceph_vinop(inode), le64_to_cpu(info->version),
	     ci->i_version);

	/*
	 * prealloc xattr data, if it looks like we'll need it.  only
	 * if len > 4 (meaning there are actually xattrs; the first 4
	 * bytes are the xattr count).
	 */
	if (iinfo->xattr_len > 4) {
S
Sage Weil 已提交
607
		xattr_blob = ceph_buffer_new(iinfo->xattr_len, GFP_NOFS);
S
Sage Weil 已提交
608 609 610 611 612
		if (!xattr_blob)
			pr_err("fill_inode ENOMEM xattr blob %d bytes\n",
			       iinfo->xattr_len);
	}

613
	spin_lock(&ci->i_ceph_lock);
S
Sage Weil 已提交
614 615 616

	/*
	 * provided version will be odd if inode value is projected,
617 618 619 620 621 622 623 624
	 * even if stable.  skip the update if we have newer stable
	 * info (ours>=theirs, e.g. due to racing mds replies), unless
	 * we are getting projected (unstable) info (in which case the
	 * version is odd, and we want ours>theirs).
	 *   us   them
	 *   2    2     skip
	 *   3    2     skip
	 *   3    3     update
S
Sage Weil 已提交
625 626
	 */
	if (le64_to_cpu(info->version) > 0 &&
627
	    (ci->i_version & ~1) >= le64_to_cpu(info->version))
S
Sage Weil 已提交
628
		goto no_change;
629
	
S
Sage Weil 已提交
630 631 632 633 634 635 636 637 638 639
	issued = __ceph_caps_issued(ci, &implemented);
	issued |= implemented | __ceph_caps_dirty(ci);

	/* update inode */
	ci->i_version = le64_to_cpu(info->version);
	inode->i_version++;
	inode->i_rdev = le32_to_cpu(info->rdev);

	if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
		inode->i_mode = le32_to_cpu(info->mode);
640 641
		inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(info->uid));
		inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(info->gid));
S
Sage Weil 已提交
642
		dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
643 644
		     from_kuid(&init_user_ns, inode->i_uid),
		     from_kgid(&init_user_ns, inode->i_gid));
S
Sage Weil 已提交
645 646 647
	}

	if ((issued & CEPH_CAP_LINK_EXCL) == 0)
M
Miklos Szeredi 已提交
648
		set_nlink(inode, le32_to_cpu(info->nlink));
S
Sage Weil 已提交
649 650 651 652 653 654 655 656 657 658 659 660 661

	/* be careful with mtime, atime, size */
	ceph_decode_timespec(&atime, &info->atime);
	ceph_decode_timespec(&mtime, &info->mtime);
	ceph_decode_timespec(&ctime, &info->ctime);
	queue_trunc = ceph_fill_file_size(inode, issued,
					  le32_to_cpu(info->truncate_seq),
					  le64_to_cpu(info->truncate_size),
					  le64_to_cpu(info->size));
	ceph_fill_file_time(inode, issued,
			    le32_to_cpu(info->time_warp_seq),
			    &ctime, &mtime, &atime);

662 663 664 665 666 667 668 669
	/* only update max_size on auth cap */
	if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
	    ci->i_max_size != le64_to_cpu(info->max_size)) {
		dout("max_size %lld -> %llu\n", ci->i_max_size,
		     le64_to_cpu(info->max_size));
		ci->i_max_size = le64_to_cpu(info->max_size);
	}

S
Sage Weil 已提交
670 671 672 673 674 675 676 677 678 679 680 681 682 683
	ci->i_layout = info->layout;
	inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;

	/* xattrs */
	/* note that if i_xattrs.len <= 4, i_xattrs.data will still be NULL. */
	if ((issued & CEPH_CAP_XATTR_EXCL) == 0 &&
	    le64_to_cpu(info->xattr_version) > ci->i_xattrs.version) {
		if (ci->i_xattrs.blob)
			ceph_buffer_put(ci->i_xattrs.blob);
		ci->i_xattrs.blob = xattr_blob;
		if (xattr_blob)
			memcpy(ci->i_xattrs.blob->vec.iov_base,
			       iinfo->xattr_data, iinfo->xattr_len);
		ci->i_xattrs.version = le64_to_cpu(info->xattr_version);
G
Guangliang Zhao 已提交
684
		ceph_forget_all_cached_acls(inode);
685
		xattr_blob = NULL;
S
Sage Weil 已提交
686 687 688 689
	}

	inode->i_mapping->a_ops = &ceph_aops;
	inode->i_mapping->backing_dev_info =
690
		&ceph_sb_to_client(inode->i_sb)->backing_dev_info;
S
Sage Weil 已提交
691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706

	switch (inode->i_mode & S_IFMT) {
	case S_IFIFO:
	case S_IFBLK:
	case S_IFCHR:
	case S_IFSOCK:
		init_special_inode(inode, inode->i_mode, inode->i_rdev);
		inode->i_op = &ceph_file_iops;
		break;
	case S_IFREG:
		inode->i_op = &ceph_file_iops;
		inode->i_fop = &ceph_file_fops;
		break;
	case S_IFLNK:
		inode->i_op = &ceph_symlink_iops;
		if (!ci->i_symlink) {
707
			u32 symlen = iinfo->symlink_len;
S
Sage Weil 已提交
708 709
			char *sym;

710
			spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
711

712 713 714 715
			err = -EINVAL;
			if (WARN_ON(symlen != inode->i_size))
				goto out;

S
Sage Weil 已提交
716
			err = -ENOMEM;
717
			sym = kstrndup(iinfo->symlink, symlen, GFP_NOFS);
S
Sage Weil 已提交
718 719 720
			if (!sym)
				goto out;

721
			spin_lock(&ci->i_ceph_lock);
S
Sage Weil 已提交
722 723 724 725 726 727 728 729 730 731
			if (!ci->i_symlink)
				ci->i_symlink = sym;
			else
				kfree(sym); /* lost a race */
		}
		break;
	case S_IFDIR:
		inode->i_op = &ceph_dir_iops;
		inode->i_fop = &ceph_dir_fops;

732 733
		ci->i_dir_layout = iinfo->dir_layout;

S
Sage Weil 已提交
734 735 736 737 738 739 740 741 742 743 744 745
		ci->i_files = le64_to_cpu(info->files);
		ci->i_subdirs = le64_to_cpu(info->subdirs);
		ci->i_rbytes = le64_to_cpu(info->rbytes);
		ci->i_rfiles = le64_to_cpu(info->rfiles);
		ci->i_rsubdirs = le64_to_cpu(info->rsubdirs);
		ceph_decode_timespec(&ci->i_rctime, &info->rctime);
		break;
	default:
		pr_err("fill_inode %llx.%llx BAD mode 0%o\n",
		       ceph_vinop(inode), inode->i_mode);
	}

746 747 748 749 750 751
	/* set dir completion flag? */
	if (S_ISDIR(inode->i_mode) &&
	    ci->i_files == 0 && ci->i_subdirs == 0 &&
	    ceph_snap(inode) == CEPH_NOSNAP &&
	    (le32_to_cpu(info->cap.caps) & CEPH_CAP_FILE_SHARED) &&
	    (issued & CEPH_CAP_FILE_EXCL) == 0 &&
752
	    !__ceph_dir_is_complete(ci)) {
753
		dout(" marking %p complete (empty)\n", inode);
754
		__ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count));
755 756
		ci->i_max_offset = 2;
	}
S
Sage Weil 已提交
757
no_change:
758
	spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
759 760 761

	/* queue truncate if we saw i_size decrease */
	if (queue_trunc)
762
		ceph_queue_vmtruncate(inode);
S
Sage Weil 已提交
763 764 765 766 767

	/* populate frag tree */
	/* FIXME: move me up, if/when version reflects fragtree changes */
	nsplits = le32_to_cpu(info->fragtree.nsplits);
	mutex_lock(&ci->i_fragtree_mutex);
768
	rb_node = rb_first(&ci->i_fragtree);
S
Sage Weil 已提交
769 770
	for (i = 0; i < nsplits; i++) {
		u32 id = le32_to_cpu(info->fragtree.splits[i].frag);
771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790
		frag = NULL;
		while (rb_node) {
			frag = rb_entry(rb_node, struct ceph_inode_frag, node);
			if (ceph_frag_compare(frag->frag, id) >= 0) {
				if (frag->frag != id)
					frag = NULL;
				else
					rb_node = rb_next(rb_node);
				break;
			}
			rb_node = rb_next(rb_node);
			rb_erase(&frag->node, &ci->i_fragtree);
			kfree(frag);
			frag = NULL;
		}
		if (!frag) {
			frag = __get_or_create_frag(ci, id);
			if (IS_ERR(frag))
				continue;
		}
S
Sage Weil 已提交
791 792 793
		frag->split_by = le32_to_cpu(info->fragtree.splits[i].by);
		dout(" frag %x split by %d\n", frag->frag, frag->split_by);
	}
794 795 796 797 798 799
	while (rb_node) {
		frag = rb_entry(rb_node, struct ceph_inode_frag, node);
		rb_node = rb_next(rb_node);
		rb_erase(&frag->node, &ci->i_fragtree);
		kfree(frag);
	}
S
Sage Weil 已提交
800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815
	mutex_unlock(&ci->i_fragtree_mutex);

	/* were we issued a capability? */
	if (info->cap.caps) {
		if (ceph_snap(inode) == CEPH_NOSNAP) {
			ceph_add_cap(inode, session,
				     le64_to_cpu(info->cap.cap_id),
				     cap_fmode,
				     le32_to_cpu(info->cap.caps),
				     le32_to_cpu(info->cap.wanted),
				     le32_to_cpu(info->cap.seq),
				     le32_to_cpu(info->cap.mseq),
				     le64_to_cpu(info->cap.realm),
				     info->cap.flags,
				     caps_reservation);
		} else {
816
			spin_lock(&ci->i_ceph_lock);
S
Sage Weil 已提交
817 818 819 820 821
			dout(" %p got snap_caps %s\n", inode,
			     ceph_cap_string(le32_to_cpu(info->cap.caps)));
			ci->i_snap_caps |= le32_to_cpu(info->cap.caps);
			if (cap_fmode >= 0)
				__ceph_get_fmode(ci, cap_fmode);
822
			spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
823
		}
824 825 826 827
	} else if (cap_fmode >= 0) {
		pr_warning("mds issued no caps on %llx.%llx\n",
			   ceph_vinop(inode));
		__ceph_get_fmode(ci, cap_fmode);
S
Sage Weil 已提交
828 829 830 831 832 833 834 835 836
	}

	/* update delegation info? */
	if (dirinfo)
		ceph_fill_dirfrag(inode, dirinfo);

	err = 0;

out:
S
Sage Weil 已提交
837 838
	if (xattr_blob)
		ceph_buffer_put(xattr_blob);
S
Sage Weil 已提交
839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860
	return err;
}

/*
 * caller should hold session s_mutex.
 */
static void update_dentry_lease(struct dentry *dentry,
				struct ceph_mds_reply_lease *lease,
				struct ceph_mds_session *session,
				unsigned long from_time)
{
	struct ceph_dentry_info *di = ceph_dentry(dentry);
	long unsigned duration = le32_to_cpu(lease->duration_ms);
	long unsigned ttl = from_time + (duration * HZ) / 1000;
	long unsigned half_ttl = from_time + (duration * HZ / 2) / 1000;
	struct inode *dir;

	/* only track leases on regular dentries */
	if (dentry->d_op != &ceph_dentry_ops)
		return;

	spin_lock(&dentry->d_lock);
S
Sage Weil 已提交
861 862
	dout("update_dentry_lease %p duration %lu ms ttl %lu\n",
	     dentry, duration, ttl);
S
Sage Weil 已提交
863 864 865 866 867

	/* make lease_rdcache_gen match directory */
	dir = dentry->d_parent->d_inode;
	di->lease_shared_gen = ceph_inode(dir)->i_shared_gen;

S
Sage Weil 已提交
868
	if (duration == 0)
S
Sage Weil 已提交
869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891
		goto out_unlock;

	if (di->lease_gen == session->s_cap_gen &&
	    time_before(ttl, dentry->d_time))
		goto out_unlock;  /* we already have a newer lease. */

	if (di->lease_session && di->lease_session != session)
		goto out_unlock;

	ceph_dentry_lru_touch(dentry);

	if (!di->lease_session)
		di->lease_session = ceph_get_mds_session(session);
	di->lease_gen = session->s_cap_gen;
	di->lease_seq = le32_to_cpu(lease->seq);
	di->lease_renew_after = half_ttl;
	di->lease_renew_from = 0;
	dentry->d_time = ttl;
out_unlock:
	spin_unlock(&dentry->d_lock);
	return;
}

S
Sage Weil 已提交
892 893 894
/*
 * Set dentry's directory position based on the current dir's max, and
 * order it in d_subdirs, so that dcache_readdir behaves.
895 896
 *
 * Always called under directory's i_mutex.
S
Sage Weil 已提交
897 898 899 900
 */
static void ceph_set_dentry_offset(struct dentry *dn)
{
	struct dentry *dir = dn->d_parent;
901
	struct inode *inode = dir->d_inode;
902
	struct ceph_inode_info *ci;
S
Sage Weil 已提交
903 904 905 906
	struct ceph_dentry_info *di;

	BUG_ON(!inode);

907
	ci = ceph_inode(inode);
S
Sage Weil 已提交
908 909
	di = ceph_dentry(dn);

910
	spin_lock(&ci->i_ceph_lock);
911
	if (!__ceph_dir_is_complete(ci)) {
912
		spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
913 914 915
		return;
	}
	di->offset = ceph_inode(inode)->i_max_offset++;
916
	spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
917

N
Nick Piggin 已提交
918 919
	spin_lock(&dir->d_lock);
	spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
920
	list_move(&dn->d_u.d_child, &dir->d_subdirs);
S
Sage Weil 已提交
921 922 923
	dout("set_dentry_offset %p %lld (%p %p)\n", dn, di->offset,
	     dn->d_u.d_child.prev, dn->d_u.d_child.next);
	spin_unlock(&dn->d_lock);
N
Nick Piggin 已提交
924
	spin_unlock(&dir->d_lock);
S
Sage Weil 已提交
925 926
}

S
Sage Weil 已提交
927 928 929 930 931 932 933 934 935
/*
 * splice a dentry to an inode.
 * caller must hold directory i_mutex for this to be safe.
 *
 * we will only rehash the resulting dentry if @prehash is
 * true; @prehash will be set to false (for the benefit of
 * the caller) if we fail.
 */
static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
936
				    bool *prehash, bool set_offset)
S
Sage Weil 已提交
937 938 939
{
	struct dentry *realdn;

S
Sage Weil 已提交
940 941
	BUG_ON(dn->d_inode);

S
Sage Weil 已提交
942 943 944 945 946
	/* dn must be unhashed */
	if (!d_unhashed(dn))
		d_drop(dn);
	realdn = d_materialise_unique(dn, in);
	if (IS_ERR(realdn)) {
947 948
		pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n",
		       PTR_ERR(realdn), dn, in, ceph_vinop(in));
S
Sage Weil 已提交
949 950 951 952 953 954 955
		if (prehash)
			*prehash = false; /* don't rehash on error */
		dn = realdn; /* note realdn contains the error */
		goto out;
	} else if (realdn) {
		dout("dn %p (%d) spliced with %p (%d) "
		     "inode %p ino %llx.%llx\n",
A
Al Viro 已提交
956 957
		     dn, d_count(dn),
		     realdn, d_count(realdn),
S
Sage Weil 已提交
958 959 960 961 962 963 964 965 966 967
		     realdn->d_inode, ceph_vinop(realdn->d_inode));
		dput(dn);
		dn = realdn;
	} else {
		BUG_ON(!ceph_dentry(dn));
		dout("dn %p attached to %p ino %llx.%llx\n",
		     dn, dn->d_inode, ceph_vinop(dn->d_inode));
	}
	if ((!prehash || *prehash) && d_unhashed(dn))
		d_rehash(dn);
968 969
	if (set_offset)
		ceph_set_dentry_offset(dn);
S
Sage Weil 已提交
970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991
out:
	return dn;
}

/*
 * Incorporate results into the local cache.  This is either just
 * one inode, or a directory, dentry, and possibly linked-to inode (e.g.,
 * after a lookup).
 *
 * A reply may contain
 *         a directory inode along with a dentry.
 *  and/or a target inode
 *
 * Called with snap_rwsem (read).
 */
int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
		    struct ceph_mds_session *session)
{
	struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
	struct inode *in = NULL;
	struct ceph_mds_reply_inode *ininfo;
	struct ceph_vino vino;
992
	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
S
Sage Weil 已提交
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
	int err = 0;

	dout("fill_trace %p is_dentry %d is_target %d\n", req,
	     rinfo->head->is_dentry, rinfo->head->is_target);

#if 0
	/*
	 * Debugging hook:
	 *
	 * If we resend completed ops to a recovering mds, we get no
	 * trace.  Since that is very rare, pretend this is the case
	 * to ensure the 'no trace' handlers in the callers behave.
	 *
	 * Fill in inodes unconditionally to avoid breaking cap
	 * invariants.
	 */
	if (rinfo->head->op & CEPH_MDS_OP_WRITE) {
		pr_info("fill_trace faking empty trace on %lld %s\n",
			req->r_tid, ceph_mds_op_name(rinfo->head->op));
		if (rinfo->head->is_dentry) {
			rinfo->head->is_dentry = 0;
			err = fill_inode(req->r_locked_dir,
					 &rinfo->diri, rinfo->dirfrag,
					 session, req->r_request_started, -1);
		}
		if (rinfo->head->is_target) {
			rinfo->head->is_target = 0;
			ininfo = rinfo->targeti.in;
			vino.ino = le64_to_cpu(ininfo->ino);
			vino.snap = le64_to_cpu(ininfo->snapid);
			in = ceph_get_inode(sb, vino);
			err = fill_inode(in, &rinfo->targeti, NULL,
					 session, req->r_request_started,
					 req->r_fmode);
			iput(in);
		}
	}
#endif

	if (!rinfo->head->is_target && !rinfo->head->is_dentry) {
		dout("fill_trace reply is empty!\n");
1034 1035
		if (rinfo->head->result == 0 && req->r_locked_dir)
			ceph_invalidate_dir_request(req);
S
Sage Weil 已提交
1036 1037 1038 1039
		return 0;
	}

	if (rinfo->head->is_dentry) {
1040 1041
		struct inode *dir = req->r_locked_dir;

1042 1043 1044 1045 1046 1047 1048 1049 1050
		if (dir) {
			err = fill_inode(dir, &rinfo->diri, rinfo->dirfrag,
					 session, req->r_request_started, -1,
					 &req->r_caps_reservation);
			if (err < 0)
				return err;
		} else {
			WARN_ON_ONCE(1);
		}
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
	if (rinfo->head->is_target) {
		vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
		vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);

		in = ceph_get_inode(sb, vino);
		if (IS_ERR(in)) {
			err = PTR_ERR(in);
			goto done;
		}
		req->r_target_inode = in;

		err = fill_inode(in, &rinfo->targeti, NULL,
				session, req->r_request_started,
				(le32_to_cpu(rinfo->head->result) == 0) ?
				req->r_fmode : -1,
				&req->r_caps_reservation);
		if (err < 0) {
			pr_err("fill_inode badness %p %llx.%llx\n",
				in, ceph_vinop(in));
			goto done;
		}
	}

1076 1077 1078 1079 1080
	/*
	 * ignore null lease/binding on snapdir ENOENT, or else we
	 * will have trouble splicing in the virtual snapdir later
	 */
	if (rinfo->head->is_dentry && !req->r_aborted &&
1081
	    req->r_locked_dir &&
1082
	    (rinfo->head->is_target || strncmp(req->r_dentry->d_name.name,
1083
					       fsc->mount_options->snapdir_name,
1084
					       req->r_dentry->d_name.len))) {
S
Sage Weil 已提交
1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108
		/*
		 * lookup link rename   : null -> possibly existing inode
		 * mknod symlink mkdir  : null -> new inode
		 * unlink               : linked -> null
		 */
		struct inode *dir = req->r_locked_dir;
		struct dentry *dn = req->r_dentry;
		bool have_dir_cap, have_lease;

		BUG_ON(!dn);
		BUG_ON(!dir);
		BUG_ON(dn->d_parent->d_inode != dir);
		BUG_ON(ceph_ino(dir) !=
		       le64_to_cpu(rinfo->diri.in->ino));
		BUG_ON(ceph_snap(dir) !=
		       le64_to_cpu(rinfo->diri.in->snapid));

		/* do we have a lease on the whole dir? */
		have_dir_cap =
			(le32_to_cpu(rinfo->diri.in->cap.caps) &
			 CEPH_CAP_FILE_SHARED);

		/* do we have a dn lease? */
		have_lease = have_dir_cap ||
S
Sage Weil 已提交
1109
			le32_to_cpu(rinfo->dlease->duration_ms);
S
Sage Weil 已提交
1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121
		if (!have_lease)
			dout("fill_trace  no dentry lease or dir cap\n");

		/* rename? */
		if (req->r_old_dentry && req->r_op == CEPH_MDS_OP_RENAME) {
			dout(" src %p '%.*s' dst %p '%.*s'\n",
			     req->r_old_dentry,
			     req->r_old_dentry->d_name.len,
			     req->r_old_dentry->d_name.name,
			     dn, dn->d_name.len, dn->d_name.name);
			dout("fill_trace doing d_move %p -> %p\n",
			     req->r_old_dentry, dn);
S
Sage Weil 已提交
1122

S
Sage Weil 已提交
1123 1124 1125 1126 1127 1128
			d_move(req->r_old_dentry, dn);
			dout(" src %p '%.*s' dst %p '%.*s'\n",
			     req->r_old_dentry,
			     req->r_old_dentry->d_name.len,
			     req->r_old_dentry->d_name.name,
			     dn, dn->d_name.len, dn->d_name.name);
1129

1130 1131
			/* ensure target dentry is invalidated, despite
			   rehashing bug in vfs_rename_dir */
1132 1133
			ceph_invalidate_dentry_lease(dn);

1134 1135 1136
			/*
			 * d_move() puts the renamed dentry at the end of
			 * d_subdirs.  We need to assign it an appropriate
1137 1138
			 * directory offset so we can behave when dir is
			 * complete.
1139 1140
			 */
			ceph_set_dentry_offset(req->r_old_dentry);
1141
			dout("dn %p gets new offset %lld\n", req->r_old_dentry,
S
Sage Weil 已提交
1142
			     ceph_dentry(req->r_old_dentry)->offset);
1143

S
Sage Weil 已提交
1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165
			dn = req->r_old_dentry;  /* use old_dentry */
		}

		/* null dentry? */
		if (!rinfo->head->is_target) {
			dout("fill_trace null dentry\n");
			if (dn->d_inode) {
				dout("d_delete %p\n", dn);
				d_delete(dn);
			} else {
				dout("d_instantiate %p NULL\n", dn);
				d_instantiate(dn, NULL);
				if (have_lease && d_unhashed(dn))
					d_rehash(dn);
				update_dentry_lease(dn, rinfo->dlease,
						    session,
						    req->r_request_started);
			}
			goto done;
		}

		/* attach proper inode */
1166 1167
		if (!dn->d_inode) {
			ihold(in);
1168
			dn = splice_dentry(dn, in, &have_lease, true);
S
Sage Weil 已提交
1169 1170 1171 1172 1173
			if (IS_ERR(dn)) {
				err = PTR_ERR(dn);
				goto done;
			}
			req->r_dentry = dn;  /* may have spliced */
1174
		} else if (dn->d_inode && dn->d_inode != in) {
S
Sage Weil 已提交
1175
			dout(" %p links to %p %llx.%llx, not %llx.%llx\n",
1176 1177
			     dn, dn->d_inode, ceph_vinop(dn->d_inode),
			     ceph_vinop(in));
S
Sage Weil 已提交
1178 1179 1180 1181 1182 1183 1184
			have_lease = false;
		}

		if (have_lease)
			update_dentry_lease(dn, rinfo->dlease, session,
					    req->r_request_started);
		dout(" final dn %p\n", dn);
1185 1186 1187
	} else if (!req->r_aborted &&
		   (req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
		    req->r_op == CEPH_MDS_OP_MKSNAP)) {
S
Sage Weil 已提交
1188 1189 1190 1191 1192 1193 1194 1195 1196 1197
		struct dentry *dn = req->r_dentry;

		/* fill out a snapdir LOOKUPSNAP dentry */
		BUG_ON(!dn);
		BUG_ON(!req->r_locked_dir);
		BUG_ON(ceph_snap(req->r_locked_dir) != CEPH_SNAPDIR);
		ininfo = rinfo->targeti.in;
		vino.ino = le64_to_cpu(ininfo->ino);
		vino.snap = le64_to_cpu(ininfo->snapid);
		dout(" linking snapped dir %p to dn %p\n", in, dn);
1198
		ihold(in);
1199
		dn = splice_dentry(dn, in, NULL, true);
S
Sage Weil 已提交
1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213
		if (IS_ERR(dn)) {
			err = PTR_ERR(dn);
			goto done;
		}
		req->r_dentry = dn;  /* may have spliced */
	}
done:
	dout("fill_trace done err=%d\n", err);
	return err;
}

/*
 * Prepopulate our cache with readdir results, leases, etc.
 */
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
static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
					   struct ceph_mds_session *session)
{
	struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
	int i, err = 0;

	for (i = 0; i < rinfo->dir_nr; i++) {
		struct ceph_vino vino;
		struct inode *in;
		int rc;

		vino.ino = le64_to_cpu(rinfo->dir_in[i].in->ino);
		vino.snap = le64_to_cpu(rinfo->dir_in[i].in->snapid);

		in = ceph_get_inode(req->r_dentry->d_sb, vino);
		if (IS_ERR(in)) {
			err = PTR_ERR(in);
			dout("new_inode badness got %d\n", err);
			continue;
		}
		rc = fill_inode(in, &rinfo->dir_in[i], NULL, session,
				req->r_request_started, -1,
				&req->r_caps_reservation);
		if (rc < 0) {
			pr_err("fill_inode badness on %p got %d\n", in, rc);
			err = rc;
			continue;
		}
	}

	return err;
}

S
Sage Weil 已提交
1247 1248 1249 1250 1251 1252 1253 1254
int ceph_readdir_prepopulate(struct ceph_mds_request *req,
			     struct ceph_mds_session *session)
{
	struct dentry *parent = req->r_dentry;
	struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
	struct qstr dname;
	struct dentry *dn;
	struct inode *in;
1255
	int err = 0, ret, i;
S
Sage Weil 已提交
1256 1257 1258
	struct inode *snapdir = NULL;
	struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
	struct ceph_dentry_info *di;
1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271
	u64 r_readdir_offset = req->r_readdir_offset;
	u32 frag = le32_to_cpu(rhead->args.readdir.frag);

	if (rinfo->dir_dir &&
	    le32_to_cpu(rinfo->dir_dir->frag) != frag) {
		dout("readdir_prepopulate got new frag %x -> %x\n",
		     frag, le32_to_cpu(rinfo->dir_dir->frag));
		frag = le32_to_cpu(rinfo->dir_dir->frag);
		if (ceph_frag_is_leftmost(frag))
			r_readdir_offset = 2;
		else
			r_readdir_offset = 0;
	}
S
Sage Weil 已提交
1272

1273 1274
	if (req->r_aborted)
		return readdir_prepopulate_inodes_only(req, session);
S
Sage Weil 已提交
1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287

	if (le32_to_cpu(rinfo->head->op) == CEPH_MDS_OP_LSSNAP) {
		snapdir = ceph_get_snapdir(parent->d_inode);
		parent = d_find_alias(snapdir);
		dout("readdir_prepopulate %d items under SNAPDIR dn %p\n",
		     rinfo->dir_nr, parent);
	} else {
		dout("readdir_prepopulate %d items under dn %p\n",
		     rinfo->dir_nr, parent);
		if (rinfo->dir_dir)
			ceph_fill_dirfrag(parent->d_inode, rinfo->dir_dir);
	}

1288
	/* FIXME: release caps/leases if error occurs */
S
Sage Weil 已提交
1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312
	for (i = 0; i < rinfo->dir_nr; i++) {
		struct ceph_vino vino;

		dname.name = rinfo->dir_dname[i];
		dname.len = rinfo->dir_dname_len[i];
		dname.hash = full_name_hash(dname.name, dname.len);

		vino.ino = le64_to_cpu(rinfo->dir_in[i].in->ino);
		vino.snap = le64_to_cpu(rinfo->dir_in[i].in->snapid);

retry_lookup:
		dn = d_lookup(parent, &dname);
		dout("d_lookup on parent=%p name=%.*s got %p\n",
		     parent, dname.len, dname.name, dn);

		if (!dn) {
			dn = d_alloc(parent, &dname);
			dout("d_alloc %p '%.*s' = %p\n", parent,
			     dname.len, dname.name, dn);
			if (dn == NULL) {
				dout("d_alloc badness\n");
				err = -ENOMEM;
				goto out;
			}
1313 1314
			ret = ceph_init_dentry(dn);
			if (ret < 0) {
1315
				dput(dn);
1316
				err = ret;
S
Sage Weil 已提交
1317
				goto out;
1318
			}
S
Sage Weil 已提交
1319 1320 1321 1322 1323 1324 1325 1326 1327 1328
		} else if (dn->d_inode &&
			   (ceph_ino(dn->d_inode) != vino.ino ||
			    ceph_snap(dn->d_inode) != vino.snap)) {
			dout(" dn %p points to wrong inode %p\n",
			     dn, dn->d_inode);
			d_delete(dn);
			dput(dn);
			goto retry_lookup;
		} else {
			/* reorder parent's d_subdirs */
N
Nick Piggin 已提交
1329 1330
			spin_lock(&parent->d_lock);
			spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
S
Sage Weil 已提交
1331 1332
			list_move(&dn->d_u.d_child, &parent->d_subdirs);
			spin_unlock(&dn->d_lock);
N
Nick Piggin 已提交
1333
			spin_unlock(&parent->d_lock);
S
Sage Weil 已提交
1334 1335 1336 1337 1338 1339 1340
		}

		/* inode */
		if (dn->d_inode) {
			in = dn->d_inode;
		} else {
			in = ceph_get_inode(parent->d_sb, vino);
1341
			if (IS_ERR(in)) {
S
Sage Weil 已提交
1342
				dout("new_inode badness\n");
1343
				d_drop(dn);
S
Sage Weil 已提交
1344
				dput(dn);
1345
				err = PTR_ERR(in);
S
Sage Weil 已提交
1346 1347 1348 1349 1350 1351 1352 1353
				goto out;
			}
		}

		if (fill_inode(in, &rinfo->dir_in[i], NULL, session,
			       req->r_request_started, -1,
			       &req->r_caps_reservation) < 0) {
			pr_err("fill_inode badness on %p\n", in);
1354 1355 1356
			if (!dn->d_inode)
				iput(in);
			d_drop(dn);
1357
			goto next_item;
S
Sage Weil 已提交
1358
		}
1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374

		if (!dn->d_inode) {
			dn = splice_dentry(dn, in, NULL, false);
			if (IS_ERR(dn)) {
				err = PTR_ERR(dn);
				dn = NULL;
				goto next_item;
			}
		}

		di = dn->d_fsdata;
		di->offset = ceph_make_fpos(frag, i + r_readdir_offset);

		update_dentry_lease(dn, rinfo->dir_dlease[i],
				    req->r_session,
				    req->r_request_started);
1375 1376 1377
next_item:
		if (dn)
			dput(dn);
S
Sage Weil 已提交
1378
	}
1379 1380
	if (err == 0)
		req->r_did_prepopulate = true;
S
Sage Weil 已提交
1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395

out:
	if (snapdir) {
		iput(snapdir);
		dput(parent);
	}
	dout("readdir_prepopulate done\n");
	return err;
}

int ceph_inode_set_size(struct inode *inode, loff_t size)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	int ret = 0;

1396
	spin_lock(&ci->i_ceph_lock);
S
Sage Weil 已提交
1397 1398 1399 1400 1401 1402 1403 1404 1405
	dout("set_size %p %llu -> %llu\n", inode, inode->i_size, size);
	inode->i_size = size;
	inode->i_blocks = (size + (1 << 9) - 1) >> 9;

	/* tell the MDS if we are approaching max_size */
	if ((size << 1) >= ci->i_max_size &&
	    (ci->i_reported_size << 1) < ci->i_max_size)
		ret = 1;

1406
	spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
1407 1408 1409 1410 1411 1412 1413
	return ret;
}

/*
 * Write back inode data in a worker thread.  (This can't be done
 * in the message handler context.)
 */
1414 1415
void ceph_queue_writeback(struct inode *inode)
{
1416
	ihold(inode);
1417 1418
	if (queue_work(ceph_inode_to_client(inode)->wb_wq,
		       &ceph_inode(inode)->i_wb_work)) {
1419
		dout("ceph_queue_writeback %p\n", inode);
1420
	} else {
1421
		dout("ceph_queue_writeback %p failed\n", inode);
1422
		iput(inode);
1423 1424 1425 1426
	}
}

static void ceph_writeback_work(struct work_struct *work)
S
Sage Weil 已提交
1427 1428 1429 1430 1431 1432 1433 1434 1435 1436
{
	struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
						  i_wb_work);
	struct inode *inode = &ci->vfs_inode;

	dout("writeback %p\n", inode);
	filemap_fdatawrite(&inode->i_data);
	iput(inode);
}

1437 1438 1439 1440 1441
/*
 * queue an async invalidation
 */
void ceph_queue_invalidate(struct inode *inode)
{
1442
	ihold(inode);
1443 1444 1445 1446 1447
	if (queue_work(ceph_inode_to_client(inode)->pg_inv_wq,
		       &ceph_inode(inode)->i_pg_inv_work)) {
		dout("ceph_queue_invalidate %p\n", inode);
	} else {
		dout("ceph_queue_invalidate %p failed\n", inode);
1448
		iput(inode);
1449 1450 1451
	}
}

S
Sage Weil 已提交
1452 1453 1454 1455
/*
 * Invalidate inode pages in a worker thread.  (This can't be done
 * in the message handler context.)
 */
1456
static void ceph_invalidate_work(struct work_struct *work)
S
Sage Weil 已提交
1457 1458 1459 1460 1461 1462 1463
{
	struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
						  i_pg_inv_work);
	struct inode *inode = &ci->vfs_inode;
	u32 orig_gen;
	int check = 0;

Y
Yan, Zheng 已提交
1464
	mutex_lock(&ci->i_truncate_mutex);
1465
	spin_lock(&ci->i_ceph_lock);
S
Sage Weil 已提交
1466 1467
	dout("invalidate_pages %p gen %d revoking %d\n", inode,
	     ci->i_rdcache_gen, ci->i_rdcache_revoking);
1468
	if (ci->i_rdcache_revoking != ci->i_rdcache_gen) {
Y
Yan, Zheng 已提交
1469 1470
		if (__ceph_caps_revoking_other(ci, NULL, CEPH_CAP_FILE_CACHE))
			check = 1;
1471
		spin_unlock(&ci->i_ceph_lock);
Y
Yan, Zheng 已提交
1472
		mutex_unlock(&ci->i_truncate_mutex);
S
Sage Weil 已提交
1473 1474 1475
		goto out;
	}
	orig_gen = ci->i_rdcache_gen;
1476
	spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
1477

Y
Yan, Zheng 已提交
1478
	truncate_inode_pages(inode->i_mapping, 0);
S
Sage Weil 已提交
1479

1480
	spin_lock(&ci->i_ceph_lock);
1481 1482
	if (orig_gen == ci->i_rdcache_gen &&
	    orig_gen == ci->i_rdcache_revoking) {
S
Sage Weil 已提交
1483 1484
		dout("invalidate_pages %p gen %d successful\n", inode,
		     ci->i_rdcache_gen);
1485
		ci->i_rdcache_revoking--;
S
Sage Weil 已提交
1486 1487
		check = 1;
	} else {
1488 1489 1490
		dout("invalidate_pages %p gen %d raced, now %d revoking %d\n",
		     inode, orig_gen, ci->i_rdcache_gen,
		     ci->i_rdcache_revoking);
Y
Yan, Zheng 已提交
1491 1492
		if (__ceph_caps_revoking_other(ci, NULL, CEPH_CAP_FILE_CACHE))
			check = 1;
S
Sage Weil 已提交
1493
	}
1494
	spin_unlock(&ci->i_ceph_lock);
Y
Yan, Zheng 已提交
1495
	mutex_unlock(&ci->i_truncate_mutex);
Y
Yan, Zheng 已提交
1496
out:
S
Sage Weil 已提交
1497 1498 1499 1500 1501 1502 1503
	if (check)
		ceph_check_caps(ci, 0, NULL);
	iput(inode);
}


/*
1504
 * called by trunc_wq;
S
Sage Weil 已提交
1505 1506 1507
 *
 * We also truncate in a separate thread as well.
 */
1508
static void ceph_vmtruncate_work(struct work_struct *work)
S
Sage Weil 已提交
1509 1510 1511 1512 1513 1514
{
	struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
						  i_vmtruncate_work);
	struct inode *inode = &ci->vfs_inode;

	dout("vmtruncate_work %p\n", inode);
Y
Yan, Zheng 已提交
1515
	__ceph_do_pending_vmtruncate(inode);
S
Sage Weil 已提交
1516 1517 1518
	iput(inode);
}

1519 1520 1521 1522 1523 1524 1525 1526
/*
 * Queue an async vmtruncate.  If we fail to queue work, we will handle
 * the truncation the next time we call __ceph_do_pending_vmtruncate.
 */
void ceph_queue_vmtruncate(struct inode *inode)
{
	struct ceph_inode_info *ci = ceph_inode(inode);

1527
	ihold(inode);
1528

1529
	if (queue_work(ceph_sb_to_client(inode->i_sb)->trunc_wq,
1530 1531 1532 1533 1534
		       &ci->i_vmtruncate_work)) {
		dout("ceph_queue_vmtruncate %p\n", inode);
	} else {
		dout("ceph_queue_vmtruncate %p failed, pending=%d\n",
		     inode, ci->i_truncate_pending);
1535
		iput(inode);
1536 1537 1538
	}
}

S
Sage Weil 已提交
1539 1540 1541 1542
/*
 * Make sure any pending truncation is applied before doing anything
 * that may depend on it.
 */
Y
Yan, Zheng 已提交
1543
void __ceph_do_pending_vmtruncate(struct inode *inode)
S
Sage Weil 已提交
1544 1545 1546
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	u64 to;
1547
	int wrbuffer_refs, finish = 0;
S
Sage Weil 已提交
1548

Y
Yan, Zheng 已提交
1549
	mutex_lock(&ci->i_truncate_mutex);
S
Sage Weil 已提交
1550
retry:
1551
	spin_lock(&ci->i_ceph_lock);
S
Sage Weil 已提交
1552 1553
	if (ci->i_truncate_pending == 0) {
		dout("__do_pending_vmtruncate %p none pending\n", inode);
1554
		spin_unlock(&ci->i_ceph_lock);
Y
Yan, Zheng 已提交
1555
		mutex_unlock(&ci->i_truncate_mutex);
S
Sage Weil 已提交
1556 1557 1558 1559 1560 1561 1562 1563 1564 1565
		return;
	}

	/*
	 * make sure any dirty snapped pages are flushed before we
	 * possibly truncate them.. so write AND block!
	 */
	if (ci->i_wrbuffer_ref_head < ci->i_wrbuffer_ref) {
		dout("__do_pending_vmtruncate %p flushing snaps first\n",
		     inode);
1566
		spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
1567 1568 1569 1570 1571
		filemap_write_and_wait_range(&inode->i_data, 0,
					     inode->i_sb->s_maxbytes);
		goto retry;
	}

Y
Yan, Zheng 已提交
1572 1573 1574
	/* there should be no reader or writer */
	WARN_ON_ONCE(ci->i_rd_ref || ci->i_wr_ref);

S
Sage Weil 已提交
1575 1576 1577 1578
	to = ci->i_truncate_size;
	wrbuffer_refs = ci->i_wrbuffer_ref;
	dout("__do_pending_vmtruncate %p (%d) to %lld\n", inode,
	     ci->i_truncate_pending, to);
1579
	spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
1580 1581 1582

	truncate_inode_pages(inode->i_mapping, to);

1583
	spin_lock(&ci->i_ceph_lock);
1584 1585 1586 1587
	if (to == ci->i_truncate_size) {
		ci->i_truncate_pending = 0;
		finish = 1;
	}
1588
	spin_unlock(&ci->i_ceph_lock);
1589 1590
	if (!finish)
		goto retry;
S
Sage Weil 已提交
1591

Y
Yan, Zheng 已提交
1592 1593
	mutex_unlock(&ci->i_truncate_mutex);

S
Sage Weil 已提交
1594 1595
	if (wrbuffer_refs == 0)
		ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
1596 1597

	wake_up_all(&ci->i_cap_wq);
S
Sage Weil 已提交
1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612
}

/*
 * symlinks
 */
static void *ceph_sym_follow_link(struct dentry *dentry, struct nameidata *nd)
{
	struct ceph_inode_info *ci = ceph_inode(dentry->d_inode);
	nd_set_link(nd, ci->i_symlink);
	return NULL;
}

static const struct inode_operations ceph_symlink_iops = {
	.readlink = generic_readlink,
	.follow_link = ceph_sym_follow_link,
Y
Yan, Zheng 已提交
1613 1614 1615 1616 1617 1618
	.setattr = ceph_setattr,
	.getattr = ceph_getattr,
	.setxattr = ceph_setxattr,
	.getxattr = ceph_getxattr,
	.listxattr = ceph_listxattr,
	.removexattr = ceph_removexattr,
G
Guangliang Zhao 已提交
1619
	.get_acl = ceph_get_acl,
S
Sage Weil 已提交
1620 1621 1622 1623 1624 1625 1626 1627 1628
};

/*
 * setattr
 */
int ceph_setattr(struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
S
Sage Weil 已提交
1629
	struct inode *parent_inode;
S
Sage Weil 已提交
1630 1631
	const unsigned int ia_valid = attr->ia_valid;
	struct ceph_mds_request *req;
1632
	struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc;
S
Sage Weil 已提交
1633 1634 1635 1636
	int issued;
	int release = 0, dirtied = 0;
	int mask = 0;
	int err = 0;
1637
	int inode_dirty_flags = 0;
S
Sage Weil 已提交
1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650

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

	err = inode_change_ok(inode, attr);
	if (err != 0)
		return err;

	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETATTR,
				       USE_AUTH_MDS);
	if (IS_ERR(req))
		return PTR_ERR(req);

1651
	spin_lock(&ci->i_ceph_lock);
S
Sage Weil 已提交
1652 1653 1654 1655 1656
	issued = __ceph_caps_issued(ci, NULL);
	dout("setattr %p issued %s\n", inode, ceph_cap_string(issued));

	if (ia_valid & ATTR_UID) {
		dout("setattr %p uid %d -> %d\n", inode,
1657 1658
		     from_kuid(&init_user_ns, inode->i_uid),
		     from_kuid(&init_user_ns, attr->ia_uid));
S
Sage Weil 已提交
1659 1660 1661 1662
		if (issued & CEPH_CAP_AUTH_EXCL) {
			inode->i_uid = attr->ia_uid;
			dirtied |= CEPH_CAP_AUTH_EXCL;
		} else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
1663 1664 1665
			   !uid_eq(attr->ia_uid, inode->i_uid)) {
			req->r_args.setattr.uid = cpu_to_le32(
				from_kuid(&init_user_ns, attr->ia_uid));
S
Sage Weil 已提交
1666 1667 1668 1669 1670 1671
			mask |= CEPH_SETATTR_UID;
			release |= CEPH_CAP_AUTH_SHARED;
		}
	}
	if (ia_valid & ATTR_GID) {
		dout("setattr %p gid %d -> %d\n", inode,
1672 1673
		     from_kgid(&init_user_ns, inode->i_gid),
		     from_kgid(&init_user_ns, attr->ia_gid));
S
Sage Weil 已提交
1674 1675 1676 1677
		if (issued & CEPH_CAP_AUTH_EXCL) {
			inode->i_gid = attr->ia_gid;
			dirtied |= CEPH_CAP_AUTH_EXCL;
		} else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
1678 1679 1680
			   !gid_eq(attr->ia_gid, inode->i_gid)) {
			req->r_args.setattr.gid = cpu_to_le32(
				from_kgid(&init_user_ns, attr->ia_gid));
S
Sage Weil 已提交
1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692
			mask |= CEPH_SETATTR_GID;
			release |= CEPH_CAP_AUTH_SHARED;
		}
	}
	if (ia_valid & ATTR_MODE) {
		dout("setattr %p mode 0%o -> 0%o\n", inode, inode->i_mode,
		     attr->ia_mode);
		if (issued & CEPH_CAP_AUTH_EXCL) {
			inode->i_mode = attr->ia_mode;
			dirtied |= CEPH_CAP_AUTH_EXCL;
		} else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
			   attr->ia_mode != inode->i_mode) {
G
Guangliang Zhao 已提交
1693
			inode->i_mode = attr->ia_mode;
S
Sage Weil 已提交
1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798
			req->r_args.setattr.mode = cpu_to_le32(attr->ia_mode);
			mask |= CEPH_SETATTR_MODE;
			release |= CEPH_CAP_AUTH_SHARED;
		}
	}

	if (ia_valid & ATTR_ATIME) {
		dout("setattr %p atime %ld.%ld -> %ld.%ld\n", inode,
		     inode->i_atime.tv_sec, inode->i_atime.tv_nsec,
		     attr->ia_atime.tv_sec, attr->ia_atime.tv_nsec);
		if (issued & CEPH_CAP_FILE_EXCL) {
			ci->i_time_warp_seq++;
			inode->i_atime = attr->ia_atime;
			dirtied |= CEPH_CAP_FILE_EXCL;
		} else if ((issued & CEPH_CAP_FILE_WR) &&
			   timespec_compare(&inode->i_atime,
					    &attr->ia_atime) < 0) {
			inode->i_atime = attr->ia_atime;
			dirtied |= CEPH_CAP_FILE_WR;
		} else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
			   !timespec_equal(&inode->i_atime, &attr->ia_atime)) {
			ceph_encode_timespec(&req->r_args.setattr.atime,
					     &attr->ia_atime);
			mask |= CEPH_SETATTR_ATIME;
			release |= CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_RD |
				CEPH_CAP_FILE_WR;
		}
	}
	if (ia_valid & ATTR_MTIME) {
		dout("setattr %p mtime %ld.%ld -> %ld.%ld\n", inode,
		     inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec,
		     attr->ia_mtime.tv_sec, attr->ia_mtime.tv_nsec);
		if (issued & CEPH_CAP_FILE_EXCL) {
			ci->i_time_warp_seq++;
			inode->i_mtime = attr->ia_mtime;
			dirtied |= CEPH_CAP_FILE_EXCL;
		} else if ((issued & CEPH_CAP_FILE_WR) &&
			   timespec_compare(&inode->i_mtime,
					    &attr->ia_mtime) < 0) {
			inode->i_mtime = attr->ia_mtime;
			dirtied |= CEPH_CAP_FILE_WR;
		} else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
			   !timespec_equal(&inode->i_mtime, &attr->ia_mtime)) {
			ceph_encode_timespec(&req->r_args.setattr.mtime,
					     &attr->ia_mtime);
			mask |= CEPH_SETATTR_MTIME;
			release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_RD |
				CEPH_CAP_FILE_WR;
		}
	}
	if (ia_valid & ATTR_SIZE) {
		dout("setattr %p size %lld -> %lld\n", inode,
		     inode->i_size, attr->ia_size);
		if (attr->ia_size > inode->i_sb->s_maxbytes) {
			err = -EINVAL;
			goto out;
		}
		if ((issued & CEPH_CAP_FILE_EXCL) &&
		    attr->ia_size > inode->i_size) {
			inode->i_size = attr->ia_size;
			inode->i_blocks =
				(attr->ia_size + (1 << 9) - 1) >> 9;
			inode->i_ctime = attr->ia_ctime;
			ci->i_reported_size = attr->ia_size;
			dirtied |= CEPH_CAP_FILE_EXCL;
		} else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
			   attr->ia_size != inode->i_size) {
			req->r_args.setattr.size = cpu_to_le64(attr->ia_size);
			req->r_args.setattr.old_size =
				cpu_to_le64(inode->i_size);
			mask |= CEPH_SETATTR_SIZE;
			release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_RD |
				CEPH_CAP_FILE_WR;
		}
	}

	/* these do nothing */
	if (ia_valid & ATTR_CTIME) {
		bool only = (ia_valid & (ATTR_SIZE|ATTR_MTIME|ATTR_ATIME|
					 ATTR_MODE|ATTR_UID|ATTR_GID)) == 0;
		dout("setattr %p ctime %ld.%ld -> %ld.%ld (%s)\n", inode,
		     inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
		     attr->ia_ctime.tv_sec, attr->ia_ctime.tv_nsec,
		     only ? "ctime only" : "ignored");
		inode->i_ctime = attr->ia_ctime;
		if (only) {
			/*
			 * if kernel wants to dirty ctime but nothing else,
			 * we need to choose a cap to dirty under, or do
			 * a almost-no-op setattr
			 */
			if (issued & CEPH_CAP_AUTH_EXCL)
				dirtied |= CEPH_CAP_AUTH_EXCL;
			else if (issued & CEPH_CAP_FILE_EXCL)
				dirtied |= CEPH_CAP_FILE_EXCL;
			else if (issued & CEPH_CAP_XATTR_EXCL)
				dirtied |= CEPH_CAP_XATTR_EXCL;
			else
				mask |= CEPH_SETATTR_CTIME;
		}
	}
	if (ia_valid & ATTR_FILE)
		dout("setattr %p ATTR_FILE ... hrm!\n", inode);

	if (dirtied) {
1799
		inode_dirty_flags = __ceph_mark_dirty_caps(ci, dirtied);
S
Sage Weil 已提交
1800 1801 1802 1803
		inode->i_ctime = CURRENT_TIME;
	}

	release &= issued;
1804
	spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
1805

1806 1807 1808
	if (inode_dirty_flags)
		__mark_inode_dirty(inode, inode_dirty_flags);

G
Guangliang Zhao 已提交
1809 1810 1811 1812 1813 1814
	if (ia_valid & ATTR_MODE) {
		err = ceph_acl_chmod(dentry, inode);
		if (err)
			goto out_put;
	}

S
Sage Weil 已提交
1815
	if (mask) {
1816 1817
		req->r_inode = inode;
		ihold(inode);
S
Sage Weil 已提交
1818 1819 1820
		req->r_inode_drop = release;
		req->r_args.setattr.mask = cpu_to_le32(mask);
		req->r_num_caps = 1;
S
Sage Weil 已提交
1821
		parent_inode = ceph_get_dentry_parent_inode(dentry);
S
Sage Weil 已提交
1822
		err = ceph_mdsc_do_request(mdsc, parent_inode, req);
S
Sage Weil 已提交
1823
		iput(parent_inode);
S
Sage Weil 已提交
1824 1825 1826 1827 1828
	}
	dout("setattr %p result=%d (%s locally, %d remote)\n", inode, err,
	     ceph_cap_string(dirtied), mask);

	ceph_mdsc_put_request(req);
Y
Yan, Zheng 已提交
1829 1830
	if (mask & CEPH_SETATTR_SIZE)
		__ceph_do_pending_vmtruncate(inode);
S
Sage Weil 已提交
1831 1832
	return err;
out:
1833
	spin_unlock(&ci->i_ceph_lock);
G
Guangliang Zhao 已提交
1834
out_put:
S
Sage Weil 已提交
1835 1836 1837 1838 1839 1840 1841 1842 1843 1844
	ceph_mdsc_put_request(req);
	return err;
}

/*
 * Verify that we have a lease on the given mask.  If not,
 * do a getattr against an mds.
 */
int ceph_do_getattr(struct inode *inode, int mask)
{
1845 1846
	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
S
Sage Weil 已提交
1847 1848 1849 1850 1851 1852 1853 1854
	struct ceph_mds_request *req;
	int err;

	if (ceph_snap(inode) == CEPH_SNAPDIR) {
		dout("do_getattr inode %p SNAPDIR\n", inode);
		return 0;
	}

1855
	dout("do_getattr inode %p mask %s mode 0%o\n", inode, ceph_cap_string(mask), inode->i_mode);
S
Sage Weil 已提交
1856 1857 1858 1859 1860 1861
	if (ceph_caps_issued_mask(ceph_inode(inode), mask, 1))
		return 0;

	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, USE_ANY_MDS);
	if (IS_ERR(req))
		return PTR_ERR(req);
1862 1863
	req->r_inode = inode;
	ihold(inode);
S
Sage Weil 已提交
1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876
	req->r_num_caps = 1;
	req->r_args.getattr.mask = cpu_to_le32(mask);
	err = ceph_mdsc_do_request(mdsc, NULL, req);
	ceph_mdsc_put_request(req);
	dout("do_getattr result=%d\n", err);
	return err;
}


/*
 * Check inode permissions.  We verify we have a valid value for
 * the AUTH cap, then call the generic handler.
 */
1877
int ceph_permission(struct inode *inode, int mask)
S
Sage Weil 已提交
1878
{
1879 1880
	int err;

1881
	if (mask & MAY_NOT_BLOCK)
1882 1883 1884
		return -ECHILD;

	err = ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED);
S
Sage Weil 已提交
1885 1886

	if (!err)
1887
		err = generic_permission(inode, mask);
S
Sage Weil 已提交
1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898
	return err;
}

/*
 * Get all attributes.  Hopefully somedata we'll have a statlite()
 * and can limit the fields we require to be accurate.
 */
int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
		 struct kstat *stat)
{
	struct inode *inode = dentry->d_inode;
1899
	struct ceph_inode_info *ci = ceph_inode(inode);
S
Sage Weil 已提交
1900 1901 1902 1903 1904
	int err;

	err = ceph_do_getattr(inode, CEPH_STAT_CAP_INODE_ALL);
	if (!err) {
		generic_fillattr(inode, stat);
Y
Yehuda Sadeh 已提交
1905
		stat->ino = ceph_translate_ino(inode->i_sb, inode->i_ino);
S
Sage Weil 已提交
1906 1907 1908 1909
		if (ceph_snap(inode) != CEPH_NOSNAP)
			stat->dev = ceph_snap(inode);
		else
			stat->dev = 0;
1910
		if (S_ISDIR(inode->i_mode)) {
1911 1912 1913 1914 1915
			if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb),
						RBYTES))
				stat->size = ci->i_rbytes;
			else
				stat->size = ci->i_files + ci->i_subdirs;
1916
			stat->blocks = 0;
S
Sage Weil 已提交
1917
			stat->blksize = 65536;
1918
		}
S
Sage Weil 已提交
1919 1920 1921
	}
	return err;
}