cregit-Linux how code gets into the kernel

Release 4.18 fs/sync.c

Directory: fs
// SPDX-License-Identifier: GPL-2.0
 * High-level sync()-related operations

#include <linux/kernel.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/namei.h>
#include <linux/sched.h>
#include <linux/writeback.h>
#include <linux/syscalls.h>
#include <linux/linkage.h>
#include <linux/pagemap.h>
#include <linux/quotaops.h>
#include <linux/backing-dev.h>
#include "internal.h"


 * 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.

static int __sync_filesystem(struct super_block *sb, int wait) { if (wait) sync_inodes_sb(sb); else writeback_inodes_sb(sb, WB_REASON_SYNC); if (sb->s_op->sync_fs) sb->s_op->sync_fs(sb, wait); return __sync_blockdev(sb->s_bdev, wait); }


Jan Kara5083.33%342.86%
Jens Axboe58.33%228.57%
Christoph Hellwig35.00%114.29%
Curt Wohlgemuth23.33%114.29%

/* * 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. */
int sync_filesystem(struct super_block *sb) { int ret; /* * 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_rdonly(sb)) return 0; ret = __sync_filesystem(sb, 0); if (ret < 0) return ret; return __sync_filesystem(sb, 1); }


Jan Kara3961.90%250.00%
Christoph Hellwig2133.33%125.00%
David Howells34.76%125.00%

static void sync_inodes_one_sb(struct super_block *sb, void *arg) { if (!sb_rdonly(sb)) sync_inodes_sb(sb); }


Jan Kara1967.86%233.33%
Al Viro517.86%233.33%
David Howells310.71%116.67%
Christoph Hellwig13.57%116.67%

static void sync_fs_one_sb(struct super_block *sb, void *arg) { if (!sb_rdonly(sb) && sb->s_op->sync_fs) sb->s_op->sync_fs(sb, *(int *)arg); }


Jan Kara3680.00%250.00%
Al Viro613.33%125.00%
David Howells36.67%125.00%

static void fdatawrite_one_bdev(struct block_device *bdev, void *arg) { filemap_fdatawrite(bdev->bd_inode->i_mapping); }


Jan Kara1979.17%480.00%
Al Viro520.83%120.00%

static void fdatawait_one_bdev(struct block_device *bdev, void *arg) { /* * We keep the error status of individual mapping so that * applications can catch the writeback error using fsync(2). * See filemap_fdatawait_keep_errors() for details. */ filemap_fdatawait_keep_errors(bdev->bd_inode->i_mapping); }


Jan Kara2392.00%480.00%
Jun'ichi Nomura28.00%120.00%

/* * Sync everything. We start by waking flusher threads so that most of * writeback runs on all devices in parallel. Then we sync all inodes reliably * which effectively also waits for all flusher threads to finish doing * writeback. At this point all data is on disk so metadata should be stable * and we tell filesystems to sync their metadata via ->sync_fs() calls. * Finally, we writeout all block devices because some filesystems (e.g. ext2) * just write metadata (such as inodes or bitmaps) to block device page cache * and do not sync it on their own in ->sync_fs(). */
void ksys_sync(void) { int nowait = 0, wait = 1; wakeup_flusher_threads(WB_REASON_SYNC); iterate_supers(sync_inodes_one_sb, NULL); iterate_supers(sync_fs_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &wait); iterate_bdevs(fdatawrite_one_bdev, NULL); iterate_bdevs(fdatawait_one_bdev, NULL); if (unlikely(laptop_mode)) laptop_sync_completion(); }


Jan Kara4160.29%654.55%
David Howells1623.53%19.09%
Dominik Brodowski68.82%19.09%
Yanmin Zhang34.41%19.09%
Curt Wohlgemuth11.47%19.09%
Jens Axboe11.47%19.09%

SYSCALL_DEFINE0(sync) { ksys_sync(); return 0; }
static void do_sync_work(struct work_struct *work) { int nowait = 0; /* * Sync twice to reduce the possibility we skipped some inodes / pages * because they were temporarily locked */ iterate_supers(sync_inodes_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &nowait); iterate_bdevs(fdatawrite_one_bdev, NULL); iterate_supers(sync_inodes_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &nowait); iterate_bdevs(fdatawrite_one_bdev, NULL); printk("Emergency Sync complete\n"); kfree(work); }


Jan Kara5473.97%480.00%
Jens Axboe1926.03%120.00%

void emergency_sync(void) { struct work_struct *work; work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { INIT_WORK(work, do_sync_work); schedule_work(work); } }


Jens Axboe3274.42%150.00%
David Howells1125.58%150.00%

/* * sync a single super */ SYSCALL_DEFINE1(syncfs, int, fd) { struct fd f = fdget(fd); struct super_block *sb; int ret; if (!f.file) return -EBADF; sb = f.file->f_path.dentry->d_sb; down_read(&sb->s_umount); ret = sync_filesystem(sb); up_read(&sb->s_umount); fdput(f); return ret; } /** * vfs_fsync_range - helper to sync a range of data & metadata to disk * @file: file to sync * @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 * * 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. */
int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; if (!file->f_op->fsync) return -EINVAL; if (!datasync && (inode->i_state & I_DIRTY_TIME)) mark_inode_dirty_sync(inode); return file->f_op->fsync(file, start, end, datasync); }


Theodore Y. Ts'o2937.66%114.29%
David Howells2735.06%114.29%
Josef Bacik79.09%114.29%
Jan Kara79.09%114.29%
Jeff Layton56.49%114.29%
Christoph Hellwig22.60%228.57%

EXPORT_SYMBOL(vfs_fsync_range); /** * vfs_fsync - perform a fsync or fdatasync on a file * @file: file to sync * @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. */
int vfs_fsync(struct file *file, int datasync) { return vfs_fsync_range(file, 0, LLONG_MAX, datasync); }


Jan Kara25100.00%1100.00%

static int do_fsync(unsigned int fd, int datasync) { struct fd f = fdget(fd); int ret = -EBADF; if (f.file) { ret = vfs_fsync(f.file, datasync); fdput(f); } return ret; }


David Howells3970.91%133.33%
Al Viro1323.64%133.33%
Christoph Hellwig35.45%133.33%

SYSCALL_DEFINE1(fsync, unsigned int, fd) { return do_fsync(fd, 0); } SYSCALL_DEFINE1(fdatasync, unsigned int, fd) { return do_fsync(fd, 1); } /* * 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 * range which are not presently under writeback. Note that this may block for * significant periods due to exhaustion of disk request structures. * * 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. */
int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes, unsigned int flags) { int ret; struct fd f; struct address_space *mapping; loff_t endbyte; /* inclusive */ 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_SHIFT)) { /* * The range starts outside a 32 bit machine's * pagecache addressing capabilities. Let it "succeed" */ ret = 0; goto out; } if (endbyte >= (0x100000000ULL << PAGE_SHIFT)) { /* * Out to EOF */ nbytes = 0; } } if (nbytes == 0) endbyte = LLONG_MAX; else endbyte--; /* inclusive */ ret = -EBADF; f = fdget(fd); if (!f.file) goto out; i_mode = file_inode(f.file)->i_mode; ret = -ESPIPE; if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) && !S_ISLNK(i_mode)) goto out_put; mapping = f.file->f_mapping; ret = 0; if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) { ret = file_fdatawait_range(f.file, offset, endbyte); if (ret < 0) goto out_put; } if (flags & SYNC_FILE_RANGE_WRITE) { ret = __filemap_fdatawrite_range(mapping, offset, endbyte, WB_SYNC_NONE); if (ret < 0) goto out_put; } if (flags & SYNC_FILE_RANGE_WAIT_AFTER) ret = file_fdatawait_range(f.file, offset, endbyte); out_put: fdput(f); out: return ret; }


Andrew Morton20663.58%110.00%
Christoph Hellwig7121.91%110.00%
Dominik Brodowski164.94%110.00%
Al Viro154.63%220.00%
Jeff Layton82.47%110.00%
Jan Kara30.93%110.00%
Kirill A. Shutemov20.62%110.00%
Mark Fasheh20.62%110.00%
Hirofumi Ogawa10.31%110.00%

SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, unsigned int, flags) { return ksys_sync_file_range(fd, offset, nbytes, flags); } /* It would be nice if people remember that not all the world's an i386 when they introduce new system calls */ SYSCALL_DEFINE4(sync_file_range2, int, fd, unsigned int, flags, loff_t, offset, loff_t, nbytes) { return ksys_sync_file_range(fd, offset, nbytes, flags); }

Overall Contributors

Jan Kara32827.84%1222.64%
Andrew Morton23419.86%11.89%
David Howells12910.95%23.77%
Christoph Hellwig1109.34%59.43%
Al Viro776.54%713.21%
Sage Weil695.86%11.89%
Dominik Brodowski655.52%23.77%
Jens Axboe584.92%47.55%
Heiko Carstens322.72%23.77%
Theodore Y. Ts'o292.46%11.89%
Jeff Layton131.10%23.77%
Josef Bacik70.59%11.89%
David Woodhouse40.34%11.89%
Tejun Heo30.25%11.89%
Yanmin Zhang30.25%11.89%
Curt Wohlgemuth30.25%11.89%
Jörn Engel30.25%11.89%
Mark Fasheh20.17%11.89%
Kirill A. Shutemov20.17%11.89%
Jun'ichi Nomura20.17%11.89%
Anton Altaparmakov10.08%11.89%
Paul Gortmaker10.08%11.89%
Pavel Machek10.08%11.89%
Hirofumi Ogawa10.08%11.89%
Greg Kroah-Hartman10.08%11.89%
Directory: fs
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with cregit.