sync.c 11.1 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
{
30
	/* Avoid doing twice syncing and cache pruning for quota sync */
31
	if (!wait) {
32
		writeout_quota_sb(sb, -1);
33 34
		writeback_inodes_sb(sb);
	} else {
35
		sync_quota_sb(sb, -1);
36 37
		sync_inodes_sb(sb);
	}
38 39 40 41 42 43 44 45 46 47
	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.
 */
48
int sync_filesystem(struct super_block *sb)
49 50 51
{
	int ret;

52 53 54 55 56 57 58 59 60 61 62 63
	/*
	 * 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;

64
	ret = __sync_filesystem(sb, 0);
65 66
	if (ret < 0)
		return ret;
67
	return __sync_filesystem(sb, 1);
68
}
69
EXPORT_SYMBOL_GPL(sync_filesystem);
70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91

/*
 * 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);
92
	list_for_each_entry(sb, &super_blocks, s_list)
93 94 95 96 97 98 99 100 101
		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);
102

103
		down_read(&sb->s_umount);
104
		if (!(sb->s_flags & MS_RDONLY) && sb->s_root)
105
			__sync_filesystem(sb, wait);
106
		up_read(&sb->s_umount);
107

108 109 110 111 112 113 114 115 116
		/* 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);
}

117 118 119 120
/*
 * sync everything.  Start out by waking pdflush, because that writes back
 * all queues in parallel.
 */
121
SYSCALL_DEFINE0(sync)
122
{
123
	wakeup_pdflush(0);
124 125
	sync_filesystems(0);
	sync_filesystems(1);
126 127 128 129 130
	if (unlikely(laptop_mode))
		laptop_sync_completion();
	return 0;
}

131 132
static void do_sync_work(struct work_struct *work)
{
133 134 135 136 137 138 139
	/*
	 * 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");
140 141 142
	kfree(work);
}

143 144
void emergency_sync(void)
{
145 146 147 148 149 150 151
	struct work_struct *work;

	work = kmalloc(sizeof(*work), GFP_ATOMIC);
	if (work) {
		INIT_WORK(work, do_sync_work);
		schedule_work(work);
	}
152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169
}

/*
 * 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;
170
	if (sb->s_dirt && sb->s_op->write_super)
171 172 173 174 175 176 177 178 179
		sb->s_op->write_super(sb);

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

C
Christoph Hellwig 已提交
180 181 182 183 184 185 186 187 188 189 190 191 192 193
/**
 * vfs_fsync - perform a fsync or fdatasync on a file
 * @file:		file to sync
 * @dentry:		dentry of @file
 * @data:		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)
194
{
C
Christoph Hellwig 已提交
195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210
	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;
	}
211

C
Christoph Hellwig 已提交
212
	if (!fop || !fop->fsync) {
213 214 215 216 217 218 219 220 221 222 223
		ret = -EINVAL;
		goto out;
	}

	ret = filemap_fdatawrite(mapping);

	/*
	 * 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
224
	err = fop->fsync(file, dentry, datasync);
225 226 227 228 229 230 231 232 233
	if (!ret)
		ret = err;
	mutex_unlock(&mapping->host->i_mutex);
	err = filemap_fdatawait(mapping);
	if (!ret)
		ret = err;
out:
	return ret;
}
C
Christoph Hellwig 已提交
234
EXPORT_SYMBOL(vfs_fsync);
235

C
Christoph Hellwig 已提交
236
static int do_fsync(unsigned int fd, int datasync)
237 238 239 240 241 242
{
	struct file *file;
	int ret = -EBADF;

	file = fget(fd);
	if (file) {
C
Christoph Hellwig 已提交
243
		ret = vfs_fsync(file, file->f_path.dentry, datasync);
244 245 246 247 248
		fput(file);
	}
	return ret;
}

249
SYSCALL_DEFINE1(fsync, unsigned int, fd)
250
{
C
Christoph Hellwig 已提交
251
	return do_fsync(fd, 0);
252 253
}

254
SYSCALL_DEFINE1(fdatasync, unsigned int, fd)
255
{
C
Christoph Hellwig 已提交
256
	return do_fsync(fd, 1);
257 258
}

A
Andrew Morton 已提交
259 260 261 262 263 264 265 266 267 268 269
/*
 * 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
270 271
 * 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
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
 *
 * 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.
 */
306 307
SYSCALL_DEFINE(sync_file_range)(int fd, loff_t offset, loff_t nbytes,
				unsigned int flags)
A
Andrew Morton 已提交
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
{
	int ret;
	struct file *file;
	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)
346
		endbyte = LLONG_MAX;
A
Andrew Morton 已提交
347 348 349 350 351 352 353 354
	else
		endbyte--;		/* inclusive */

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

355
	i_mode = file->f_path.dentry->d_inode->i_mode;
A
Andrew Morton 已提交
356 357 358 359 360
	ret = -ESPIPE;
	if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) &&
			!S_ISLNK(i_mode))
		goto out_put;

M
Mark Fasheh 已提交
361
	ret = do_sync_mapping_range(file->f_mapping, offset, endbyte, flags);
A
Andrew Morton 已提交
362 363 364 365 366
out_put:
	fput_light(file, fput_needed);
out:
	return ret;
}
367 368 369 370 371 372 373 374 375
#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
376

377 378
/* It would be nice if people remember that not all the world's an i386
   when they introduce new system calls */
379 380
SYSCALL_DEFINE(sync_file_range2)(int fd, unsigned int flags,
				 loff_t offset, loff_t nbytes)
381 382 383
{
	return sys_sync_file_range(fd, offset, nbytes, flags);
}
384 385 386 387 388 389 390 391 392
#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
393

A
Andrew Morton 已提交
394 395 396
/*
 * `endbyte' is inclusive
 */
397 398
int do_sync_mapping_range(struct address_space *mapping, loff_t offset,
			  loff_t endbyte, unsigned int flags)
A
Andrew Morton 已提交
399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417
{
	int ret;

	if (!mapping) {
		ret = -EINVAL;
		goto out;
	}

	ret = 0;
	if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) {
		ret = wait_on_page_writeback_range(mapping,
					offset >> PAGE_CACHE_SHIFT,
					endbyte >> PAGE_CACHE_SHIFT);
		if (ret < 0)
			goto out;
	}

	if (flags & SYNC_FILE_RANGE_WRITE) {
		ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
418
						WB_SYNC_ALL);
A
Andrew Morton 已提交
419 420 421 422 423 424 425 426 427 428 429 430
		if (ret < 0)
			goto out;
	}

	if (flags & SYNC_FILE_RANGE_WAIT_AFTER) {
		ret = wait_on_page_writeback_range(mapping,
					offset >> PAGE_CACHE_SHIFT,
					endbyte >> PAGE_CACHE_SHIFT);
	}
out:
	return ret;
}
431
EXPORT_SYMBOL_GPL(do_sync_mapping_range);