Something went wrong. Try again.
(I'm so sorry!) Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
C
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381// SPDX-License-Identifier: GPL-2.0/* * High-level sync()-related operations */
#include <linux/blkdev.h>#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"
#define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \ SYNC_FILE_RANGE_WAIT_AFTER)
/* * 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 = 0;
/* * 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;
/* * Do the filesystem syncing work. For simple filesystems * writeback_inodes_sb(sb) just dirties buffers with inodes so we have * to submit I/O for these buffers via sync_blockdev(). This also * speeds up the wait == 1 case since in that case write_inode() * methods call sync_dirty_buffer() and thus effectively write one block * at a time. */ writeback_inodes_sb(sb, WB_REASON_SYNC); if (sb->s_op->sync_fs) { ret = sb->s_op->sync_fs(sb, 0); if (ret) return ret; } ret = sync_blockdev_nowait(sb->s_bdev); if (ret) return ret;
sync_inodes_sb(sb); if (sb->s_op->sync_fs) { ret = sb->s_op->sync_fs(sb, 1); if (ret) return ret; } return sync_blockdev(sb->s_bdev);}EXPORT_SYMBOL(sync_filesystem);
static void sync_inodes_one_sb(struct super_block *sb, void *arg){ if (!sb_rdonly(sb)) sync_inodes_sb(sb);}
static void sync_fs_one_sb(struct super_block *sb, void *arg){ if (!sb_rdonly(sb) && !(sb->s_iflags & SB_I_SKIP_SYNC) && sb->s_op->sync_fs) sb->s_op->sync_fs(sb, *(int *)arg);}
/* * 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); sync_bdevs(false); sync_bdevs(true);}
SYSCALL_DEFINE0(sync){ ksys_sync(); return 0;}
static void do_sync_work(struct work_struct *work){ int nowait = 0; int wait = 1;
/* * Sync twice to reduce the possibility we skipped some inodes / pages * because they were temporarily locked */ iterate_supers(sync_inodes_one_sb, NULL); iterate_supers(sync_fs_one_sb, &nowait); sync_bdevs(false); iterate_supers(sync_inodes_one_sb, NULL); iterate_supers(sync_fs_one_sb, &wait); sync_bdevs(false); printk("Emergency Sync complete\n"); kfree(work);}
void emergency_sync(void){ struct work_struct *work;
work = kmalloc_obj(*work, GFP_ATOMIC); if (work) { INIT_WORK(work, do_sync_work); schedule_work(work); }}
/* * sync a single super */SYSCALL_DEFINE1(syncfs, int, fd){ CLASS(fd, f)(fd); struct super_block *sb; int ret, ret2;
if (fd_empty(f)) return -EBADF; sb = fd_file(f)->f_path.dentry->d_sb;
down_read(&sb->s_umount); ret = sync_filesystem(sb); up_read(&sb->s_umount);
ret2 = errseq_check_and_advance(&sb->s_wb_err, &fd_file(f)->f_sb_err);
return ret ? ret : ret2;}
/** * 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) sync_lazytime(inode); return file->f_op->fsync(file, start, end, datasync);}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);}EXPORT_SYMBOL(vfs_fsync);
static int do_fsync(unsigned int fd, int datasync){ CLASS(fd, f)(fd);
if (fd_empty(f)) return -EBADF;
return vfs_fsync(fd_file(f), datasync);}
SYSCALL_DEFINE1(fsync, unsigned int, fd){ return do_fsync(fd, 0);}
SYSCALL_DEFINE1(fdatasync, unsigned int, fd){ return do_fsync(fd, 1);}
int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, unsigned int flags){ int ret; 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 */
i_mode = file_inode(file)->i_mode; ret = -ESPIPE; if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode)) goto out;
mapping = file->f_mapping; ret = 0; if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) { ret = file_fdatawait_range(file, offset, endbyte); if (ret < 0) goto out; }
if (flags & SYNC_FILE_RANGE_WRITE) { if ((flags & SYNC_FILE_RANGE_WRITE_AND_WAIT) == SYNC_FILE_RANGE_WRITE_AND_WAIT) ret = filemap_fdatawrite_range(mapping, offset, endbyte); else ret = filemap_flush_range(mapping, offset, endbyte); if (ret < 0) goto out; }
if (flags & SYNC_FILE_RANGE_WAIT_AFTER) ret = file_fdatawait_range(file, offset, endbyte);
out: return ret;}
/* * ksys_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 ksys_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 ksys_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.k.a. SYNC_FILE_RANGE_WRITE_AND_WAIT): * 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 * ksys_sync_file_range() are written to disk. It should be noted that disk * caches are not flushed by this call, so there are no guarantees here that the * data will be available on disk after a crash. * * * 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){ CLASS(fd, f)(fd);
if (fd_empty(f)) return -EBADF;
return sync_file_range(fd_file(f), offset, nbytes, flags);}
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);}
#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_SYNC_FILE_RANGE)COMPAT_SYSCALL_DEFINE6(sync_file_range, int, fd, compat_arg_u64_dual(offset), compat_arg_u64_dual(nbytes), unsigned int, flags){ return ksys_sync_file_range(fd, compat_arg_u64_glue(offset), compat_arg_u64_glue(nbytes), flags);}#endif
/* 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);}