sync.c 12.3 KB
Newer Older
A
Andrew Morton 已提交
1 2 3 4 5 6 7 8
/*
 * High-level sync()-related operations
 */

#include <linux/kernel.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/module.h>
9
#include <linux/sched.h>
A
Andrew Morton 已提交
10 11 12 13
#include <linux/writeback.h>
#include <linux/syscalls.h>
#include <linux/linkage.h>
#include <linux/pagemap.h>
14 15
#include <linux/quotaops.h>
#include <linux/buffer_head.h>
16
#include "internal.h"
A
Andrew Morton 已提交
17 18 19 20

#define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \
			SYNC_FILE_RANGE_WAIT_AFTER)

21
/*
22 23 24 25 26
 * Do the filesystem syncing work. For simple filesystems
 * writeback_inodes_sb(sb) just dirties buffers with inodes so we have to
 * submit IO for these buffers via __sync_blockdev(). This also speeds up the
 * wait == 1 case since in that case write_inode() functions do
 * sync_dirty_buffer() and thus effectively write one block at a time.
27
 */
28
static int __sync_filesystem(struct super_block *sb, int wait)
29
{
J
Jens Axboe 已提交
30 31 32 33 34 35 36
	/*
	 * This should be safe, as we require bdi backing to actually
	 * write out data in the first place
	 */
	if (!sb->s_bdi)
		return 0;

37
	/* Avoid doing twice syncing and cache pruning for quota sync */
38
	if (!wait) {
39
		writeout_quota_sb(sb, -1);
40 41
		writeback_inodes_sb(sb);
	} else {
42
		sync_quota_sb(sb, -1);
43 44
		sync_inodes_sb(sb);
	}
45 46 47 48 49 50 51 52 53 54
	if (sb->s_op->sync_fs)
		sb->s_op->sync_fs(sb, wait);
	return __sync_blockdev(sb->s_bdev, wait);
}

/*
 * Write out and wait upon all dirty data associated with this
 * superblock.  Filesystem data as well as the underlying block
 * device.  Takes the superblock lock.
 */
55
int sync_filesystem(struct super_block *sb)
56 57 58
{
	int ret;

59 60 61 62 63 64 65 66 67 68 69 70
	/*
	 * We need to be protected against the filesystem going from
	 * r/o to r/w or vice versa.
	 */
	WARN_ON(!rwsem_is_locked(&sb->s_umount));

	/*
	 * No point in syncing out anything if the filesystem is read-only.
	 */
	if (sb->s_flags & MS_RDONLY)
		return 0;

71
	ret = __sync_filesystem(sb, 0);
72 73
	if (ret < 0)
		return ret;
74
	return __sync_filesystem(sb, 1);
75
}
76
EXPORT_SYMBOL_GPL(sync_filesystem);
77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98

/*
 * Sync all the data for all the filesystems (called by sys_sync() and
 * emergency sync)
 *
 * This operation is careful to avoid the livelock which could easily happen
 * if two or more filesystems are being continuously dirtied.  s_need_sync
 * is used only here.  We set it against all filesystems and then clear it as
 * we sync them.  So redirtied filesystems are skipped.
 *
 * But if process A is currently running sync_filesystems and then process B
 * calls sync_filesystems as well, process B will set all the s_need_sync
 * flags again, which will cause process A to resync everything.  Fix that with
 * a local mutex.
 */
static void sync_filesystems(int wait)
{
	struct super_block *sb;
	static DEFINE_MUTEX(mutex);

	mutex_lock(&mutex);		/* Could be down_interruptible */
	spin_lock(&sb_lock);
99
	list_for_each_entry(sb, &super_blocks, s_list)
100 101 102 103 104 105 106 107 108
		sb->s_need_sync = 1;

restart:
	list_for_each_entry(sb, &super_blocks, s_list) {
		if (!sb->s_need_sync)
			continue;
		sb->s_need_sync = 0;
		sb->s_count++;
		spin_unlock(&sb_lock);
109

110
		down_read(&sb->s_umount);
J
Jens Axboe 已提交
111
		if (!(sb->s_flags & MS_RDONLY) && sb->s_root && sb->s_bdi)
112
			__sync_filesystem(sb, wait);
113
		up_read(&sb->s_umount);
114

115 116 117 118 119 120 121 122 123
		/* restart only when sb is no longer on the list */
		spin_lock(&sb_lock);
		if (__put_super_and_need_restart(sb))
			goto restart;
	}
	spin_unlock(&sb_lock);
	mutex_unlock(&mutex);
}

124 125 126 127
/*
 * sync everything.  Start out by waking pdflush, because that writes back
 * all queues in parallel.
 */
128
SYSCALL_DEFINE0(sync)
129
{
130
	wakeup_flusher_threads(0);
131 132
	sync_filesystems(0);
	sync_filesystems(1);
133 134 135 136 137
	if (unlikely(laptop_mode))
		laptop_sync_completion();
	return 0;
}

138 139
static void do_sync_work(struct work_struct *work)
{
140 141 142 143 144 145 146
	/*
	 * Sync twice to reduce the possibility we skipped some inodes / pages
	 * because they were temporarily locked
	 */
	sync_filesystems(0);
	sync_filesystems(0);
	printk("Emergency Sync complete\n");
147 148 149
	kfree(work);
}

150 151
void emergency_sync(void)
{
152 153 154 155 156 157 158
	struct work_struct *work;

	work = kmalloc(sizeof(*work), GFP_ATOMIC);
	if (work) {
		INIT_WORK(work, do_sync_work);
		schedule_work(work);
	}
159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176
}

/*
 * Generic function to fsync a file.
 *
 * filp may be NULL if called via the msync of a vma.
 */
int file_fsync(struct file *filp, struct dentry *dentry, int datasync)
{
	struct inode * inode = dentry->d_inode;
	struct super_block * sb;
	int ret, err;

	/* sync the inode to buffers */
	ret = write_inode_now(inode, 0);

	/* sync the superblock to buffers */
	sb = inode->i_sb;
177
	if (sb->s_dirt && sb->s_op->write_super)
178 179 180 181 182 183 184 185
		sb->s_op->write_super(sb);

	/* .. finally sync the buffers to disk */
	err = sync_blockdev(sb->s_bdev);
	if (!ret)
		ret = err;
	return ret;
}
186
EXPORT_SYMBOL(file_fsync);
187

C
Christoph Hellwig 已提交
188
/**
189
 * vfs_fsync_range - helper to sync a range of data & metadata to disk
C
Christoph Hellwig 已提交
190 191
 * @file:		file to sync
 * @dentry:		dentry of @file
192 193 194
 * @start:		offset in bytes of the beginning of data range to sync
 * @end:		offset in bytes of the end of data range (inclusive)
 * @datasync:		perform only datasync
C
Christoph Hellwig 已提交
195
 *
196 197 198
 * Write back data in range @start..@end and metadata for @file to disk.  If
 * @datasync is set only metadata needed to access modified file data is
 * written.
C
Christoph Hellwig 已提交
199 200 201 202 203
 *
 * In case this function is called from nfsd @file may be %NULL and
 * only @dentry is set.  This can only happen when the filesystem
 * implements the export_operations API.
 */
204 205
int vfs_fsync_range(struct file *file, struct dentry *dentry, loff_t start,
		    loff_t end, int datasync)
206
{
C
Christoph Hellwig 已提交
207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222
	const struct file_operations *fop;
	struct address_space *mapping;
	int err, ret;

	/*
	 * Get mapping and operations from the file in case we have
	 * as file, or get the default values for them in case we
	 * don't have a struct file available.  Damn nfsd..
	 */
	if (file) {
		mapping = file->f_mapping;
		fop = file->f_op;
	} else {
		mapping = dentry->d_inode->i_mapping;
		fop = dentry->d_inode->i_fop;
	}
223

C
Christoph Hellwig 已提交
224
	if (!fop || !fop->fsync) {
225 226 227 228
		ret = -EINVAL;
		goto out;
	}

229
	ret = filemap_write_and_wait_range(mapping, start, end);
230 231 232 233 234 235

	/*
	 * We need to protect against concurrent writers, which could cause
	 * livelocks in fsync_buffers_list().
	 */
	mutex_lock(&mapping->host->i_mutex);
C
Christoph Hellwig 已提交
236
	err = fop->fsync(file, dentry, datasync);
237 238 239
	if (!ret)
		ret = err;
	mutex_unlock(&mapping->host->i_mutex);
240

241 242 243
out:
	return ret;
}
244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262
EXPORT_SYMBOL(vfs_fsync_range);

/**
 * vfs_fsync - perform a fsync or fdatasync on a file
 * @file:		file to sync
 * @dentry:		dentry of @file
 * @datasync:		only perform a fdatasync operation
 *
 * Write back data and metadata for @file to disk.  If @datasync is
 * set only metadata needed to access modified file data is written.
 *
 * In case this function is called from nfsd @file may be %NULL and
 * only @dentry is set.  This can only happen when the filesystem
 * implements the export_operations API.
 */
int vfs_fsync(struct file *file, struct dentry *dentry, int datasync)
{
	return vfs_fsync_range(file, dentry, 0, LLONG_MAX, datasync);
}
C
Christoph Hellwig 已提交
263
EXPORT_SYMBOL(vfs_fsync);
264

C
Christoph Hellwig 已提交
265
static int do_fsync(unsigned int fd, int datasync)
266 267 268 269 270 271
{
	struct file *file;
	int ret = -EBADF;

	file = fget(fd);
	if (file) {
C
Christoph Hellwig 已提交
272
		ret = vfs_fsync(file, file->f_path.dentry, datasync);
273 274 275 276 277
		fput(file);
	}
	return ret;
}

278
SYSCALL_DEFINE1(fsync, unsigned int, fd)
279
{
C
Christoph Hellwig 已提交
280
	return do_fsync(fd, 0);
281 282
}

283
SYSCALL_DEFINE1(fdatasync, unsigned int, fd)
284
{
C
Christoph Hellwig 已提交
285
	return do_fsync(fd, 1);
286 287
}

288 289 290 291 292 293 294 295 296 297
/**
 * generic_write_sync - perform syncing after a write if file / inode is sync
 * @file:	file to which the write happened
 * @pos:	offset where the write started
 * @count:	length of the write
 *
 * This is just a simple wrapper about our general syncing function.
 */
int generic_write_sync(struct file *file, loff_t pos, loff_t count)
{
298
	if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host))
299 300
		return 0;
	return vfs_fsync_range(file, file->f_path.dentry, pos,
301 302
			       pos + count - 1,
			       (file->f_flags & __O_SYNC) ? 0 : 1);
303 304 305
}
EXPORT_SYMBOL(generic_write_sync);

A
Andrew Morton 已提交
306 307 308 309 310 311 312 313 314 315 316
/*
 * sys_sync_file_range() permits finely controlled syncing over a segment of
 * a file in the range offset .. (offset+nbytes-1) inclusive.  If nbytes is
 * zero then sys_sync_file_range() will operate from offset out to EOF.
 *
 * The flag bits are:
 *
 * SYNC_FILE_RANGE_WAIT_BEFORE: wait upon writeout of all pages in the range
 * before performing the write.
 *
 * SYNC_FILE_RANGE_WRITE: initiate writeout of all those dirty pages in the
317 318
 * range which are not presently under writeback. Note that this may block for
 * significant periods due to exhaustion of disk request structures.
A
Andrew Morton 已提交
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
 *
 * SYNC_FILE_RANGE_WAIT_AFTER: wait upon writeout of all pages in the range
 * after performing the write.
 *
 * Useful combinations of the flag bits are:
 *
 * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE: ensures that all pages
 * in the range which were dirty on entry to sys_sync_file_range() are placed
 * under writeout.  This is a start-write-for-data-integrity operation.
 *
 * SYNC_FILE_RANGE_WRITE: start writeout of all dirty pages in the range which
 * are not presently under writeout.  This is an asynchronous flush-to-disk
 * operation.  Not suitable for data integrity operations.
 *
 * SYNC_FILE_RANGE_WAIT_BEFORE (or SYNC_FILE_RANGE_WAIT_AFTER): wait for
 * completion of writeout of all pages in the range.  This will be used after an
 * earlier SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE operation to wait
 * for that operation to complete and to return the result.
 *
 * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER:
 * a traditional sync() operation.  This is a write-for-data-integrity operation
 * which will ensure that all pages in the range which were dirty on entry to
 * sys_sync_file_range() are committed to disk.
 *
 *
 * SYNC_FILE_RANGE_WAIT_BEFORE and SYNC_FILE_RANGE_WAIT_AFTER will detect any
 * I/O errors or ENOSPC conditions and will return those to the caller, after
 * clearing the EIO and ENOSPC flags in the address_space.
 *
 * It should be noted that none of these operations write out the file's
 * metadata.  So unless the application is strictly performing overwrites of
 * already-instantiated disk blocks, there are no guarantees here that the data
 * will be available after a crash.
 */
353 354
SYSCALL_DEFINE(sync_file_range)(int fd, loff_t offset, loff_t nbytes,
				unsigned int flags)
A
Andrew Morton 已提交
355 356 357
{
	int ret;
	struct file *file;
358
	struct address_space *mapping;
A
Andrew Morton 已提交
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
	loff_t endbyte;			/* inclusive */
	int fput_needed;
	umode_t i_mode;

	ret = -EINVAL;
	if (flags & ~VALID_FLAGS)
		goto out;

	endbyte = offset + nbytes;

	if ((s64)offset < 0)
		goto out;
	if ((s64)endbyte < 0)
		goto out;
	if (endbyte < offset)
		goto out;

	if (sizeof(pgoff_t) == 4) {
		if (offset >= (0x100000000ULL << PAGE_CACHE_SHIFT)) {
			/*
			 * The range starts outside a 32 bit machine's
			 * pagecache addressing capabilities.  Let it "succeed"
			 */
			ret = 0;
			goto out;
		}
		if (endbyte >= (0x100000000ULL << PAGE_CACHE_SHIFT)) {
			/*
			 * Out to EOF
			 */
			nbytes = 0;
		}
	}

	if (nbytes == 0)
394
		endbyte = LLONG_MAX;
A
Andrew Morton 已提交
395 396 397 398 399 400 401 402
	else
		endbyte--;		/* inclusive */

	ret = -EBADF;
	file = fget_light(fd, &fput_needed);
	if (!file)
		goto out;

403
	i_mode = file->f_path.dentry->d_inode->i_mode;
A
Andrew Morton 已提交
404 405 406 407 408
	ret = -ESPIPE;
	if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) &&
			!S_ISLNK(i_mode))
		goto out_put;

409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430
	mapping = file->f_mapping;
	if (!mapping) {
		ret = -EINVAL;
		goto out_put;
	}

	ret = 0;
	if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) {
		ret = filemap_fdatawait_range(mapping, offset, endbyte);
		if (ret < 0)
			goto out_put;
	}

	if (flags & SYNC_FILE_RANGE_WRITE) {
		ret = filemap_fdatawrite_range(mapping, offset, endbyte);
		if (ret < 0)
			goto out_put;
	}

	if (flags & SYNC_FILE_RANGE_WAIT_AFTER)
		ret = filemap_fdatawait_range(mapping, offset, endbyte);

A
Andrew Morton 已提交
431 432 433 434 435
out_put:
	fput_light(file, fput_needed);
out:
	return ret;
}
436 437 438 439 440 441 442 443 444
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_sync_file_range(long fd, loff_t offset, loff_t nbytes,
				    long flags)
{
	return SYSC_sync_file_range((int) fd, offset, nbytes,
				    (unsigned int) flags);
}
SYSCALL_ALIAS(sys_sync_file_range, SyS_sync_file_range);
#endif
A
Andrew Morton 已提交
445

446 447
/* It would be nice if people remember that not all the world's an i386
   when they introduce new system calls */
448 449
SYSCALL_DEFINE(sync_file_range2)(int fd, unsigned int flags,
				 loff_t offset, loff_t nbytes)
450 451 452
{
	return sys_sync_file_range(fd, offset, nbytes, flags);
}
453 454 455 456 457 458 459 460 461
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_sync_file_range2(long fd, long flags,
				     loff_t offset, loff_t nbytes)
{
	return SYSC_sync_file_range2((int) fd, (unsigned int) flags,
				     offset, nbytes);
}
SYSCALL_ALIAS(sys_sync_file_range2, SyS_sync_file_range2);
#endif