inode.c 12.2 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498
/*
 * Copyright (c) 2002 Red Hat, Inc. All rights reserved.
 *
 * This software may be freely redistributed under the terms of the
 * GNU General Public License.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 *
 * Authors: David Woodhouse <dwmw2@infradead.org>
 *          David Howells <dhowells@redhat.com>
 *
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/sched.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include "internal.h"

struct afs_iget_data {
	struct afs_fid		fid;
	struct afs_volume	*volume;	/* volume on which resides */
};

/*
 * map the AFS file status to the inode member variables
 */
static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
{
	struct inode *inode = AFS_VNODE_TO_I(vnode);

	_debug("FS: ft=%d lk=%d sz=%llu ver=%Lu mod=%hu",
	       vnode->status.type,
	       vnode->status.nlink,
	       (unsigned long long) vnode->status.size,
	       vnode->status.data_version,
	       vnode->status.mode);

	switch (vnode->status.type) {
	case AFS_FTYPE_FILE:
		inode->i_mode	= S_IFREG | vnode->status.mode;
		inode->i_op	= &afs_file_inode_operations;
		inode->i_fop	= &afs_file_operations;
		break;
	case AFS_FTYPE_DIR:
		inode->i_mode	= S_IFDIR | vnode->status.mode;
		inode->i_op	= &afs_dir_inode_operations;
		inode->i_fop	= &afs_dir_file_operations;
		break;
	case AFS_FTYPE_SYMLINK:
		inode->i_mode	= S_IFLNK | vnode->status.mode;
		inode->i_op	= &page_symlink_inode_operations;
		break;
	default:
		printk("kAFS: AFS vnode with undefined type\n");
		return -EBADMSG;
	}

#ifdef CONFIG_AFS_FSCACHE
	if (vnode->status.size != inode->i_size)
		fscache_attr_changed(vnode->cache);
#endif

	set_nlink(inode, vnode->status.nlink);
	inode->i_uid		= vnode->status.owner;
	inode->i_gid		= 0;
	inode->i_size		= vnode->status.size;
	inode->i_ctime.tv_sec	= vnode->status.mtime_server;
	inode->i_ctime.tv_nsec	= 0;
	inode->i_atime		= inode->i_mtime = inode->i_ctime;
	inode->i_blocks		= 0;
	inode->i_generation	= vnode->fid.unique;
	inode->i_version	= vnode->status.data_version;
	inode->i_mapping->a_ops	= &afs_fs_aops;

	/* check to see whether a symbolic link is really a mountpoint */
	if (vnode->status.type == AFS_FTYPE_SYMLINK) {
		afs_mntpt_check_symlink(vnode, key);

		if (test_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags)) {
			inode->i_mode	= S_IFDIR | vnode->status.mode;
			inode->i_op	= &afs_mntpt_inode_operations;
			inode->i_fop	= &afs_mntpt_file_operations;
		}
	}

	return 0;
}

/*
 * iget5() comparator
 */
static int afs_iget5_test(struct inode *inode, void *opaque)
{
	struct afs_iget_data *data = opaque;

	return inode->i_ino == data->fid.vnode &&
		inode->i_generation == data->fid.unique;
}

/*
 * iget5() comparator for inode created by autocell operations
 *
 * These pseudo inodes don't match anything.
 */
static int afs_iget5_autocell_test(struct inode *inode, void *opaque)
{
	return 0;
}

/*
 * iget5() inode initialiser
 */
static int afs_iget5_set(struct inode *inode, void *opaque)
{
	struct afs_iget_data *data = opaque;
	struct afs_vnode *vnode = AFS_FS_I(inode);

	inode->i_ino = data->fid.vnode;
	inode->i_generation = data->fid.unique;
	vnode->fid = data->fid;
	vnode->volume = data->volume;

	return 0;
}

/*
 * inode retrieval for autocell
 */
struct inode *afs_iget_autocell(struct inode *dir, const char *dev_name,
				int namesz, struct key *key)
{
	struct afs_iget_data data;
	struct afs_super_info *as;
	struct afs_vnode *vnode;
	struct super_block *sb;
	struct inode *inode;
	static atomic_t afs_autocell_ino;

	_enter("{%x:%u},%*.*s,",
	       AFS_FS_I(dir)->fid.vid, AFS_FS_I(dir)->fid.vnode,
	       namesz, namesz, dev_name ?: "");

	sb = dir->i_sb;
	as = sb->s_fs_info;
	data.volume = as->volume;
	data.fid.vid = as->volume->vid;
	data.fid.unique = 0;
	data.fid.vnode = 0;

	inode = iget5_locked(sb, atomic_inc_return(&afs_autocell_ino),
			     afs_iget5_autocell_test, afs_iget5_set,
			     &data);
	if (!inode) {
		_leave(" = -ENOMEM");
		return ERR_PTR(-ENOMEM);
	}

	_debug("GOT INODE %p { ino=%lu, vl=%x, vn=%x, u=%x }",
	       inode, inode->i_ino, data.fid.vid, data.fid.vnode,
	       data.fid.unique);

	vnode = AFS_FS_I(inode);

	/* there shouldn't be an existing inode */
	BUG_ON(!(inode->i_state & I_NEW));

	inode->i_size		= 0;
	inode->i_mode		= S_IFDIR | S_IRUGO | S_IXUGO;
	inode->i_op		= &afs_autocell_inode_operations;
	set_nlink(inode, 2);
	inode->i_uid		= 0;
	inode->i_gid		= 0;
	inode->i_ctime.tv_sec	= get_seconds();
	inode->i_ctime.tv_nsec	= 0;
	inode->i_atime		= inode->i_mtime = inode->i_ctime;
	inode->i_blocks		= 0;
	inode->i_version	= 0;
	inode->i_generation	= 0;

	set_bit(AFS_VNODE_PSEUDODIR, &vnode->flags);
	set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
	inode->i_flags |= S_AUTOMOUNT | S_NOATIME;
	unlock_new_inode(inode);
	_leave(" = %p", inode);
	return inode;
}

/*
 * inode retrieval
 */
struct inode *afs_iget(struct super_block *sb, struct key *key,
		       struct afs_fid *fid, struct afs_file_status *status,
		       struct afs_callback *cb)
{
	struct afs_iget_data data = { .fid = *fid };
	struct afs_super_info *as;
	struct afs_vnode *vnode;
	struct inode *inode;
	int ret;

	_enter(",{%x:%u.%u},,", fid->vid, fid->vnode, fid->unique);

	as = sb->s_fs_info;
	data.volume = as->volume;

	inode = iget5_locked(sb, fid->vnode, afs_iget5_test, afs_iget5_set,
			     &data);
	if (!inode) {
		_leave(" = -ENOMEM");
		return ERR_PTR(-ENOMEM);
	}

	_debug("GOT INODE %p { vl=%x vn=%x, u=%x }",
	       inode, fid->vid, fid->vnode, fid->unique);

	vnode = AFS_FS_I(inode);

	/* deal with an existing inode */
	if (!(inode->i_state & I_NEW)) {
		_leave(" = %p", inode);
		return inode;
	}

	if (!status) {
		/* it's a remotely extant inode */
		set_bit(AFS_VNODE_CB_BROKEN, &vnode->flags);
		ret = afs_vnode_fetch_status(vnode, NULL, key);
		if (ret < 0)
			goto bad_inode;
	} else {
		/* it's an inode we just created */
		memcpy(&vnode->status, status, sizeof(vnode->status));

		if (!cb) {
			/* it's a symlink we just created (the fileserver
			 * didn't give us a callback) */
			vnode->cb_version = 0;
			vnode->cb_expiry = 0;
			vnode->cb_type = 0;
			vnode->cb_expires = get_seconds();
		} else {
			vnode->cb_version = cb->version;
			vnode->cb_expiry = cb->expiry;
			vnode->cb_type = cb->type;
			vnode->cb_expires = vnode->cb_expiry + get_seconds();
		}
	}

	/* set up caching before mapping the status, as map-status reads the
	 * first page of symlinks to see if they're really mountpoints */
	inode->i_size = vnode->status.size;
#ifdef CONFIG_AFS_FSCACHE
	vnode->cache = fscache_acquire_cookie(vnode->volume->cache,
					      &afs_vnode_cache_index_def,
					      vnode);
#endif

	ret = afs_inode_map_status(vnode, key);
	if (ret < 0)
		goto bad_inode;

	/* success */
	clear_bit(AFS_VNODE_UNSET, &vnode->flags);
	inode->i_flags |= S_NOATIME;
	unlock_new_inode(inode);
	_leave(" = %p [CB { v=%u t=%u }]", inode, vnode->cb_version, vnode->cb_type);
	return inode;

	/* failure */
bad_inode:
#ifdef CONFIG_AFS_FSCACHE
	fscache_relinquish_cookie(vnode->cache, 0);
	vnode->cache = NULL;
#endif
	iget_failed(inode);
	_leave(" = %d [bad]", ret);
	return ERR_PTR(ret);
}

/*
 * mark the data attached to an inode as obsolete due to a write on the server
 * - might also want to ditch all the outstanding writes and dirty pages
 */
void afs_zap_data(struct afs_vnode *vnode)
{
	_enter("{%x:%u}", vnode->fid.vid, vnode->fid.vnode);

	/* nuke all the non-dirty pages that aren't locked, mapped or being
	 * written back in a regular file and completely discard the pages in a
	 * directory or symlink */
	if (S_ISREG(vnode->vfs_inode.i_mode))
		invalidate_remote_inode(&vnode->vfs_inode);
	else
		invalidate_inode_pages2(vnode->vfs_inode.i_mapping);
}

/*
 * validate a vnode/inode
 * - there are several things we need to check
 *   - parent dir data changes (rm, rmdir, rename, mkdir, create, link,
 *     symlink)
 *   - parent dir metadata changed (security changes)
 *   - dentry data changed (write, truncate)
 *   - dentry metadata changed (security changes)
 */
int afs_validate(struct afs_vnode *vnode, struct key *key)
{
	int ret;

	_enter("{v={%x:%u} fl=%lx},%x",
	       vnode->fid.vid, vnode->fid.vnode, vnode->flags,
	       key_serial(key));

	if (vnode->cb_promised &&
	    !test_bit(AFS_VNODE_CB_BROKEN, &vnode->flags) &&
	    !test_bit(AFS_VNODE_MODIFIED, &vnode->flags) &&
	    !test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) {
		if (vnode->cb_expires < get_seconds() + 10) {
			_debug("callback expired");
			set_bit(AFS_VNODE_CB_BROKEN, &vnode->flags);
		} else {
			goto valid;
		}
	}

	if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
		goto valid;

	mutex_lock(&vnode->validate_lock);

	/* if the promise has expired, we need to check the server again to get
	 * a new promise - note that if the (parent) directory's metadata was
	 * changed then the security may be different and we may no longer have
	 * access */
	if (!vnode->cb_promised ||
	    test_bit(AFS_VNODE_CB_BROKEN, &vnode->flags)) {
		_debug("not promised");
		ret = afs_vnode_fetch_status(vnode, NULL, key);
		if (ret < 0)
			goto error_unlock;
		_debug("new promise [fl=%lx]", vnode->flags);
	}

	if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
		_debug("file already deleted");
		ret = -ESTALE;
		goto error_unlock;
	}

	/* if the vnode's data version number changed then its contents are
	 * different */
	if (test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags))
		afs_zap_data(vnode);

	clear_bit(AFS_VNODE_MODIFIED, &vnode->flags);
	mutex_unlock(&vnode->validate_lock);
valid:
	_leave(" = 0");
	return 0;

error_unlock:
	mutex_unlock(&vnode->validate_lock);
	_leave(" = %d", ret);
	return ret;
}

/*
 * read the attributes of an inode
 */
int afs_getattr(struct vfsmount *mnt, struct dentry *dentry,
		      struct kstat *stat)
{
	struct inode *inode;

	inode = dentry->d_inode;

	_enter("{ ino=%lu v=%u }", inode->i_ino, inode->i_generation);

	generic_fillattr(inode, stat);
	return 0;
}

/*
 * discard an AFS inode
 */
int afs_drop_inode(struct inode *inode)
{
	_enter("");

	if (test_bit(AFS_VNODE_PSEUDODIR, &AFS_FS_I(inode)->flags))
		return generic_delete_inode(inode);
	else
		return generic_drop_inode(inode);
}

/*
 * clear an AFS inode
 */
void afs_evict_inode(struct inode *inode)
{
	struct afs_permits *permits;
	struct afs_vnode *vnode;

	vnode = AFS_FS_I(inode);

	_enter("{%x:%u.%d} v=%u x=%u t=%u }",
	       vnode->fid.vid,
	       vnode->fid.vnode,
	       vnode->fid.unique,
	       vnode->cb_version,
	       vnode->cb_expiry,
	       vnode->cb_type);

	_debug("CLEAR INODE %p", inode);

	ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode);

	truncate_inode_pages(&inode->i_data, 0);
	end_writeback(inode);

	afs_give_up_callback(vnode);

	if (vnode->server) {
		spin_lock(&vnode->server->fs_lock);
		rb_erase(&vnode->server_rb, &vnode->server->fs_vnodes);
		spin_unlock(&vnode->server->fs_lock);
		afs_put_server(vnode->server);
		vnode->server = NULL;
	}

	ASSERT(list_empty(&vnode->writebacks));
	ASSERT(!vnode->cb_promised);

#ifdef CONFIG_AFS_FSCACHE
	fscache_relinquish_cookie(vnode->cache, 0);
	vnode->cache = NULL;
#endif

	mutex_lock(&vnode->permits_lock);
	permits = vnode->permits;
	rcu_assign_pointer(vnode->permits, NULL);
	mutex_unlock(&vnode->permits_lock);
	if (permits)
		call_rcu(&permits->rcu, afs_zap_permits);

	_leave("");
}

/*
 * set the attributes of an inode
 */
int afs_setattr(struct dentry *dentry, struct iattr *attr)
{
	struct afs_vnode *vnode = AFS_FS_I(dentry->d_inode);
	struct key *key;
	int ret;

	_enter("{%x:%u},{n=%s},%x",
	       vnode->fid.vid, vnode->fid.vnode, dentry->d_name.name,
	       attr->ia_valid);

	if (!(attr->ia_valid & (ATTR_SIZE | ATTR_MODE | ATTR_UID | ATTR_GID |
				ATTR_MTIME))) {
		_leave(" = 0 [unsupported]");
		return 0;
	}

	/* flush any dirty data outstanding on a regular file */
	if (S_ISREG(vnode->vfs_inode.i_mode)) {
		filemap_write_and_wait(vnode->vfs_inode.i_mapping);
		afs_writeback_all(vnode);
	}

	if (attr->ia_valid & ATTR_FILE) {
		key = attr->ia_file->private_data;
	} else {
		key = afs_request_key(vnode->volume->cell);
		if (IS_ERR(key)) {
			ret = PTR_ERR(key);
			goto error;
		}
	}

	ret = afs_vnode_setattr(vnode, key, attr);
	if (!(attr->ia_valid & ATTR_FILE))
		key_put(key);

error:
	_leave(" = %d", ret);
	return ret;
}