/* * Returns %true if the given DIO request should be attempted with DIO, or * %false if it should fall back to buffered I/O. * * DIO isn't well specified; when it's unsupported (either due to the request * being misaligned, or due to the file not supporting DIO at all), filesystems * either fall back to buffered I/O or return EINVAL. For files that don't use * any special features like encryption or verity, ext4 has traditionally * returned EINVAL for misaligned DIO. iomap_dio_rw() uses this convention too. * In this case, we should attempt the DIO, *not* fall back to buffered I/O. * * In contrast, in cases where DIO is unsupported due to ext4 features, ext4 * traditionally falls back to buffered I/O. * * This function implements the traditional ext4 behavior in all these cases.
*/ staticbool ext4_should_use_dio(struct kiocb *iocb, struct iov_iter *iter)
{ struct inode *inode = file_inode(iocb->ki_filp);
u32 dio_align = ext4_dio_alignment(inode);
if (iocb->ki_flags & IOCB_NOWAIT) { if (!inode_trylock_shared(inode)) return -EAGAIN;
} else {
inode_lock_shared(inode);
}
if (!ext4_should_use_dio(iocb, to)) {
inode_unlock_shared(inode); /* * Fallback to buffered I/O if the operation being performed on * the inode is not supported by direct I/O. The IOCB_DIRECT * flag needs to be cleared here in order to ensure that the * direct I/O path within generic_file_read_iter() is not * taken.
*/
iocb->ki_flags &= ~IOCB_DIRECT; return generic_file_read_iter(iocb, to);
}
ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0, NULL, 0);
inode_unlock_shared(inode);
if (iocb->ki_flags & IOCB_NOWAIT) { if (!inode_trylock_shared(inode)) return -EAGAIN;
} else {
inode_lock_shared(inode);
} /* * Recheck under inode lock - at this point we are sure it cannot * change anymore
*/ if (!IS_DAX(inode)) {
inode_unlock_shared(inode); /* Fallback to buffered IO in case we cannot support DAX */ return generic_file_read_iter(iocb, to);
}
ret = dax_iomap_rw(iocb, to, &ext4_iomap_ops);
inode_unlock_shared(inode);
/* * Called when an inode is released. Note that this is different * from ext4_file_open: open gets called at every open, but release * gets called only when /all/ the files are closed.
*/ staticint ext4_release_file(struct inode *inode, struct file *filp)
{ if (ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE)) {
ext4_alloc_da_blocks(inode);
ext4_clear_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
} /* if we are the last writer on the inode, drop the block reservation */ if ((filp->f_mode & FMODE_WRITE) &&
(atomic_read(&inode->i_writecount) == 1) &&
!EXT4_I(inode)->i_reserved_data_blocks) {
down_write(&EXT4_I(inode)->i_data_sem);
ext4_discard_preallocations(inode);
up_write(&EXT4_I(inode)->i_data_sem);
} if (is_dx(inode) && filp->private_data)
ext4_htree_free_dir_info(filp->private_data);
return 0;
}
/* * This tests whether the IO in question is block-aligned or not. * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they * are converted to written only after the IO is complete. Until they are * mapped, these blocks appear as holes, so dio_zero_block() will assume that * it needs to zero out portions of the start and/or end block. If 2 AIO * threads are at work on the same unwritten block, they must be synchronized * or one thread will zero the other's data, causing corruption.
*/ staticbool
ext4_unaligned_io(struct inode *inode, struct iov_iter *from, loff_t pos)
{ struct super_block *sb = inode->i_sb; unsignedlong blockmask = sb->s_blocksize - 1;
if ((pos | iov_iter_alignment(from)) & blockmask) returntrue;
returnfalse;
}
staticbool
ext4_extending_io(struct inode *inode, loff_t offset, size_t len)
{ if (offset + len > i_size_read(inode) ||
offset + len > EXT4_I(inode)->i_disksize) returntrue; returnfalse;
}
/* Is IO overwriting allocated or initialized blocks? */ staticbool ext4_overwrite_io(struct inode *inode,
loff_t pos, loff_t len, bool *unwritten)
{ struct ext4_map_blocks map; unsignedint blkbits = inode->i_blkbits; int err, blklen;
err = ext4_map_blocks(NULL, inode, &map, 0); if (err != blklen) returnfalse; /* * 'err==len' means that all of the blocks have been preallocated, * regardless of whether they have been initialized or not. We need to * check m_flags to distinguish the unwritten extents.
*/
*unwritten = !(map.m_flags & EXT4_MAP_MAPPED); returntrue;
}
ret = generic_write_checks(iocb, from); if (ret <= 0) return ret;
/* * If we have encountered a bitmap-format file, the size limit * is smaller than s_maxbytes, which is for extent-mapped files.
*/ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
lockdep_assert_held_write(&inode->i_rwsem);
handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) return PTR_ERR(handle);
if (ext4_update_inode_size(inode, offset + written)) { int ret = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret)) {
ext4_journal_stop(handle); return ret;
}
}
if ((written == count) && inode->i_nlink)
ext4_orphan_del(handle, inode);
ext4_journal_stop(handle);
return written;
}
/* * Clean up the inode after DIO or DAX extending write has completed and the * inode size has been updated using ext4_handle_inode_extension().
*/ staticvoid ext4_inode_extension_cleanup(struct inode *inode, bool need_trunc)
{
lockdep_assert_held_write(&inode->i_rwsem); if (need_trunc) {
ext4_truncate_failed_write(inode); /* * If the truncate operation failed early, then the inode may * still be on the orphan list. In that case, we need to try * remove the inode from the in-memory linked list.
*/ if (inode->i_nlink)
ext4_orphan_del(NULL, inode); return;
} /* * If i_disksize got extended either due to writeback of delalloc * blocks or extending truncate while the DIO was running we could fail * to cleanup the orphan list in ext4_handle_inode_extension(). Do it * now.
*/ if (ext4_inode_orphan_tracked(inode) && inode->i_nlink) {
handle_t *handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
if (IS_ERR(handle)) { /* * The write has successfully completed. Not much to * do with the error here so just cleanup the orphan * list and hope for the best.
*/
ext4_orphan_del(NULL, inode); return;
}
ext4_orphan_del(handle, inode);
ext4_journal_stop(handle);
}
}
if (!error && size && (flags & IOMAP_DIO_UNWRITTEN) &&
(iocb->ki_flags & IOCB_ATOMIC))
error = ext4_convert_unwritten_extents_atomic(NULL, inode, pos,
size); elseif (!error && size && flags & IOMAP_DIO_UNWRITTEN)
error = ext4_convert_unwritten_extents(NULL, inode, pos, size); if (error) return error; /* * Note that EXT4_I(inode)->i_disksize can get extended up to * inode->i_size while the I/O was running due to writeback of delalloc * blocks. But the code in ext4_iomap_alloc() is careful to use * zeroed/unwritten extents if this is possible; thus we won't leave * uninitialized blocks in a file even if we didn't succeed in writing * as much as we intended. Also we can race with truncate or write * expanding the file so we have to be a bit careful here.
*/ if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize) &&
pos + size <= i_size_read(inode)) return 0;
error = ext4_handle_inode_extension(inode, pos, size, size); return error < 0 ? error : 0;
}
/* * The intention here is to start with shared lock acquired then see if any * condition requires an exclusive inode lock. If yes, then we restart the * whole operation by releasing the shared lock and acquiring exclusive lock. * * - For unaligned_io we never take shared lock as it may cause data corruption * when two unaligned IO tries to modify the same block e.g. while zeroing. * * - For extending writes case we don't take the shared lock, since it requires * updating inode i_disksize and/or orphan handling with exclusive lock. * * - shared locking will only be true mostly with overwrites, including * initialized blocks and unwritten blocks. For overwrite unwritten blocks * we protect splitting extents by i_data_sem in ext4_inode_info, so we can * also release exclusive i_rwsem lock. * * - Otherwise we will switch to exclusive i_rwsem lock.
*/ static ssize_t ext4_dio_write_checks(struct kiocb *iocb, struct iov_iter *from, bool *ilock_shared, bool *extend, bool *unwritten, int *dio_flags)
{ struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file);
loff_t offset;
size_t count;
ssize_t ret; bool overwrite, unaligned_io;
restart:
ret = ext4_generic_write_checks(iocb, from); if (ret <= 0) goto out;
/* * Determine whether we need to upgrade to an exclusive lock. This is * required to change security info in file_modified(), for extending * I/O, any form of non-overwrite I/O, and unaligned I/O to unwritten * extents (as partial block zeroing may be required). * * Note that unaligned writes are allowed under shared lock so long as * they are pure overwrites. Otherwise, concurrent unaligned writes risk * data corruption due to partial block zeroing in the dio layer, and so * the I/O must occur exclusively.
*/ if (*ilock_shared &&
((!IS_NOSEC(inode) || *extend || !overwrite ||
(unaligned_io && *unwritten)))) { if (iocb->ki_flags & IOCB_NOWAIT) {
ret = -EAGAIN; goto out;
}
inode_unlock_shared(inode);
*ilock_shared = false;
inode_lock(inode); goto restart;
}
/* * Now that locking is settled, determine dio flags and exclusivity * requirements. We don't use DIO_OVERWRITE_ONLY because we enforce * behavior already. The inode lock is already held exclusive if the * write is non-overwrite or extending, so drain all outstanding dio and * set the force wait dio flag.
*/ if (!*ilock_shared && (unaligned_io || *extend)) { if (iocb->ki_flags & IOCB_NOWAIT) {
ret = -EAGAIN; goto out;
} if (unaligned_io && (!overwrite || *unwritten))
inode_dio_wait(inode);
*dio_flags = IOMAP_DIO_FORCE_WAIT;
}
/* * Quick check here without any i_rwsem lock to see if it is extending * IO. A more reliable check is done in ext4_dio_write_checks() with * proper locking in place.
*/ if (offset + count > i_size_read(inode))
ilock_shared = false;
if (iocb->ki_flags & IOCB_NOWAIT) { if (ilock_shared) { if (!inode_trylock_shared(inode)) return -EAGAIN;
} else { if (!inode_trylock(inode)) return -EAGAIN;
}
} else { if (ilock_shared)
inode_lock_shared(inode); else
inode_lock(inode);
}
/* Fallback to buffered I/O if the inode does not support direct I/O. */ if (!ext4_should_use_dio(iocb, from)) { if (ilock_shared)
inode_unlock_shared(inode); else
inode_unlock(inode); return ext4_buffered_write_iter(iocb, from);
}
/* * Prevent inline data from being created since we are going to allocate * blocks for DIO. We know the inode does not currently have inline data * because ext4_should_use_dio() checked for it, but we have to clear * the state flag before the write checks because a lock cycle could * introduce races with other writers.
*/
ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend,
&unwritten, &dio_flags); if (ret <= 0) return ret;
offset = iocb->ki_pos;
count = ret;
if (extend) {
handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) {
ret = PTR_ERR(handle); goto out;
}
ret = ext4_orphan_add(handle, inode);
ext4_journal_stop(handle); if (ret) goto out;
}
if (ilock_shared && !unwritten)
iomap_ops = &ext4_iomap_overwrite_ops;
ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops,
dio_flags, NULL, 0); if (ret == -ENOTBLK)
ret = 0; if (extend) { /* * We always perform extending DIO write synchronously so by * now the IO is completed and ext4_handle_inode_extension() * was called. Cleanup the inode in case of error or race with * writeback of delalloc blocks.
*/
WARN_ON_ONCE(ret == -EIOCBQUEUED);
ext4_inode_extension_cleanup(inode, ret < 0);
}
out: if (ilock_shared)
inode_unlock_shared(inode); else
inode_unlock(inode);
/* * There is no support for atomic writes on buffered-io yet, * we should never fallback to buffered-io for DIO atomic * writes.
*/
WARN_ON_ONCE(iocb->ki_flags & IOCB_ATOMIC);
/* * We need to ensure that the pages within the page cache for * the range covered by this I/O are written to disk and * invalidated. This is in attempt to preserve the expected * direct I/O semantics in the case we fallback to buffered I/O * to complete off the I/O request.
*/
ret += err;
endbyte = offset + err - 1;
err = filemap_write_and_wait_range(iocb->ki_filp->f_mapping,
offset, endbyte); if (!err)
invalidate_mapping_pages(iocb->ki_filp->f_mapping,
offset >> PAGE_SHIFT,
endbyte >> PAGE_SHIFT);
}
/* * We have to distinguish real writes from writes which will result in a * COW page; COW writes should *not* poke the journal (the file will not * be changed). Doing so would cause unintended failures when mounted * read-only. * * We check for VM_SHARED rather than vmf->cow_page since the latter is * unset for order != 0 (i.e. only in do_cow_fault); for * other sizes, dax_iomap_fault will handle splitting / fallback so that * we eventually come back with a COW page.
*/ bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
(vmf->vma->vm_flags & VM_SHARED); struct address_space *mapping = vmf->vma->vm_file->f_mapping; unsignedlong pfn;
if (write) {
sb_start_pagefault(sb);
file_update_time(vmf->vma->vm_file);
filemap_invalidate_lock_shared(mapping);
retry:
handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
EXT4_DATA_TRANS_BLOCKS(sb)); if (IS_ERR(handle)) {
filemap_invalidate_unlock_shared(mapping);
sb_end_pagefault(sb); return VM_FAULT_SIGBUS;
}
} else {
filemap_invalidate_lock_shared(mapping);
}
result = dax_iomap_fault(vmf, order, &pfn, &error, &ext4_iomap_ops); if (write) {
ext4_journal_stop(handle);
if (file->f_mode & FMODE_WRITE)
ret = ext4_emergency_state(inode->i_sb); else
ret = ext4_forced_shutdown(inode->i_sb) ? -EIO : 0; if (unlikely(ret)) return ret;
/* * We don't support synchronous mappings for non-DAX files and * for DAX files if underneath dax_device is not synchronous.
*/ if (!daxdev_mapping_supported(desc->vm_flags, file_inode(file), dax_dev)) return -EOPNOTSUPP;
if (likely(ext4_test_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED))) return 0;
if (ext4_emergency_state(sb) || sb_rdonly(sb) ||
!sb_start_intwrite_trylock(sb)) return 0;
ext4_set_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED); /* * Sample where the filesystem has been mounted and * store it in the superblock for sysadmin convenience * when trying to sort through large numbers of block * devices or filesystem images.
*/
memset(buf, 0, sizeof(buf));
path.mnt = mnt;
path.dentry = mnt->mnt_root;
cp = d_path(&path, buf, sizeof(buf));
err = 0; if (IS_ERR(cp)) goto out;
staticint ext4_file_open(struct inode *inode, struct file *filp)
{ int ret;
if (filp->f_mode & FMODE_WRITE)
ret = ext4_emergency_state(inode->i_sb); else
ret = ext4_forced_shutdown(inode->i_sb) ? -EIO : 0; if (unlikely(ret)) return ret;
ret = ext4_sample_last_mounted(inode->i_sb, filp->f_path.mnt); if (ret) return ret;
ret = fscrypt_file_open(inode, filp); if (ret) return ret;
ret = fsverity_file_open(inode, filp); if (ret) return ret;
/* * Set up the jbd2_inode if we are opening the inode for * writing and the journal is present
*/ if (filp->f_mode & FMODE_WRITE) {
ret = ext4_inode_attach_jinode(inode); if (ret < 0) return ret;
}
if (ext4_inode_can_atomic_write(inode))
filp->f_mode |= FMODE_CAN_ATOMIC_WRITE;
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.