Release 4.15 fs/ext4/file.c

// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/ext4/file.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/file.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  ext4 fs regular file handling primitives
 *
 *  64-bit file support on 64-bit platforms by Jakub Jelinek
 *      (jj@sunsite.ms.mff.cuni.cz)
 */

#include <linux/time.h>
#include <linux/fs.h>
#include <linux/iomap.h>
#include <linux/mount.h>
#include <linux/path.h>
#include <linux/dax.h>
#include <linux/quotaops.h>
#include <linux/pagevec.h>
#include <linux/uio.h>
#include <linux/mman.h>
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"

#ifdef CONFIG_FS_DAX


static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	ssize_t ret;

	if (!inode_trylock_shared(inode)) {
		if (iocb->ki_flags & IOCB_NOWAIT)
			return -EAGAIN;
		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);

	file_accessed(iocb->ki_filp);
	return ret;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Jan Kara
88
80.00%
1
50.00%
Goldwyn Rodrigues
22
20.00%
1
50.00%
Total
110
100.00%
2
100.00%

#endif



static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb))))
		return -EIO;

	if (!iov_iter_count(to))
		return 0; /* skip atime */

#ifdef CONFIG_FS_DAX
	if (IS_DAX(file_inode(iocb->ki_filp)))
		return ext4_dax_read_iter(iocb, to);
#endif
	return generic_file_read_iter(iocb, to);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jan Kara
61
71.76%
1
50.00%
Theodore Y. Ts'o
24
28.24%
1
50.00%
Total
85
100.00%
2
100.00%

/*
 * 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.
 */


static int 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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dave Kleikamp
80
66.67%
1
14.29%
Theodore Y. Ts'o
24
20.00%
3
42.86%
Aneesh Kumar K.V
12
10.00%
2
28.57%
Mingming Cao
4
3.33%
1
14.29%
Total
120
100.00%
7
100.00%



static void ext4_unwritten_wait(struct inode *inode)
{
	wait_queue_head_t *wq = ext4_ioend_wq(inode);

	wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Sandeen
38
92.68%
1
33.33%
Dmitriy Monakhov
2
4.88%
1
33.33%
Stephen Hemminger
1
2.44%
1
33.33%
Total
41
100.00%
3
100.00%

/*
 * 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.
 */

static int

ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos)
{
	struct super_block *sb = inode->i_sb;
	int blockmask = sb->s_blocksize - 1;

	if (pos >= i_size_read(inode))
		return 0;

	if ((pos | iov_iter_alignment(from)) & blockmask)
		return 1;

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Sandeen
58
85.29%
1
33.33%
Al Viro
7
10.29%
1
33.33%
Theodore Y. Ts'o
3
4.41%
1
33.33%
Total
68
100.00%
3
100.00%

/* Is IO overwriting allocated and initialized blocks? */


static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
{
	struct ext4_map_blocks map;
	unsigned int blkbits = inode->i_blkbits;
	int err, blklen;

	if (pos + len > i_size_read(inode))
		return false;

	map.m_lblk = pos >> blkbits;
	map.m_len = EXT4_MAX_BLOCKS(len, pos, blkbits);
	blklen = map.m_len;

	err = ext4_map_blocks(NULL, inode, &map, 0);
	/*
         * 'err==len' means that all of the blocks have been preallocated,
         * regardless of whether they have been initialized or not. To exclude
         * unwritten extents, we need to check m_flags.
         */
	return err == blklen && (map.m_flags & EXT4_MAP_MAPPED);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jan Kara
103
100.00%
1
100.00%
Total
103
100.00%
1
100.00%



static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	ssize_t ret;

	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);

		if (iocb->ki_pos >= sbi->s_bitmap_maxbytes)
			return -EFBIG;
		iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos);
	}
	return iov_iter_count(from);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jan Kara
109
100.00%
1
100.00%
Total
109
100.00%
1
100.00%

#ifdef CONFIG_FS_DAX

static ssize_t

ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	ssize_t ret;

	if (!inode_trylock(inode)) {
		if (iocb->ki_flags & IOCB_NOWAIT)
			return -EAGAIN;
		inode_lock(inode);
	}
	ret = ext4_write_checks(iocb, from);
	if (ret <= 0)
		goto out;
	ret = file_remove_privs(iocb->ki_filp);
	if (ret)
		goto out;
	ret = file_update_time(iocb->ki_filp);
	if (ret)
		goto out;

	ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
out:
	inode_unlock(inode);
	if (ret > 0)
		ret = generic_write_sync(iocb, ret);
	return ret;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Jan Kara
123
84.83%
1
50.00%
Goldwyn Rodrigues
22
15.17%
1
50.00%
Total
145
100.00%
2
100.00%

#endif


static ssize_t

ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	int o_direct = iocb->ki_flags & IOCB_DIRECT;
	int unaligned_aio = 0;
	int overwrite = 0;
	ssize_t ret;

	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
		return -EIO;

#ifdef CONFIG_FS_DAX
	if (IS_DAX(inode))
		return ext4_dax_write_iter(iocb, from);
#endif
	if (!o_direct && (iocb->ki_flags & IOCB_NOWAIT))
		return -EOPNOTSUPP;

	if (!inode_trylock(inode)) {
		if (iocb->ki_flags & IOCB_NOWAIT)
			return -EAGAIN;
		inode_lock(inode);
	}

	ret = ext4_write_checks(iocb, from);
	if (ret <= 0)
		goto out;

	/*
         * Unaligned direct AIO must be serialized among each other as zeroing
         * of partial blocks of two competing unaligned AIOs can result in data
         * corruption.
         */
	if (o_direct && ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
	    !is_sync_kiocb(iocb) &&
	    ext4_unaligned_aio(inode, from, iocb->ki_pos)) {
		unaligned_aio = 1;
		ext4_unwritten_wait(inode);
	}

	iocb->private = &overwrite;
	/* Check whether we do a DIO overwrite or not */
	if (o_direct && !unaligned_aio) {
		if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
			if (ext4_should_dioread_nolock(inode))
				overwrite = 1;
		} else if (iocb->ki_flags & IOCB_NOWAIT) {
			ret = -EAGAIN;
			goto out;
		}
	}

	ret = __generic_file_write_iter(iocb, from);
	inode_unlock(inode);

	if (ret > 0)
		ret = generic_write_sync(iocb, ret);

	return ret;

out:
	inode_unlock(inode);
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Theodore Y. Ts'o
65
21.81%
4
19.05%
Jan Kara
61
20.47%
3
14.29%
Goldwyn Rodrigues
55
18.46%
1
4.76%
Zheng Liu
45
15.10%
2
9.52%
Al Viro
24
8.05%
4
19.05%
Christoph Hellwig
19
6.38%
3
14.29%
Dave Kleikamp
16
5.37%
1
4.76%
Dmitriy Monakhov
7
2.35%
1
4.76%
Eric Sandeen
5
1.68%
1
4.76%
Fabian Frederick
1
0.34%
1
4.76%
Total
298
100.00%
21
100.00%

#ifdef CONFIG_FS_DAX


static int ext4_dax_huge_fault(struct vm_fault *vmf,
		enum page_entry_size pe_size)
{
	int result;
	handle_t *handle = NULL;
	struct inode *inode = file_inode(vmf->vma->vm_file);
	struct super_block *sb = inode->i_sb;

	/*
         * 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 pe_size != PE_SIZE_PTE (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);
	pfn_t pfn;

	if (write) {
		sb_start_pagefault(sb);
		file_update_time(vmf->vma->vm_file);
		down_read(&EXT4_I(inode)->i_mmap_sem);
		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
					       EXT4_DATA_TRANS_BLOCKS(sb));
		if (IS_ERR(handle)) {
			up_read(&EXT4_I(inode)->i_mmap_sem);
			sb_end_pagefault(sb);
			return VM_FAULT_SIGBUS;
		}
	} else {
		down_read(&EXT4_I(inode)->i_mmap_sem);
	}
	result = dax_iomap_fault(vmf, pe_size, &pfn, &ext4_iomap_ops);
	if (write) {
		ext4_journal_stop(handle);
		/* Handling synchronous page fault? */
		if (result & VM_FAULT_NEEDDSYNC)
			result = dax_finish_sync_fault(vmf, pe_size, pfn);
		up_read(&EXT4_I(inode)->i_mmap_sem);
		sb_end_pagefault(sb);
	} else {
		up_read(&EXT4_I(inode)->i_mmap_sem);
	}

	return result;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jan Kara
145
61.44%
6
54.55%
Matthew Wilcox
52
22.03%
1
9.09%
Ross Zwisler
15
6.36%
1
9.09%
Randy Dodgen
13
5.51%
1
9.09%
Dave Jiang
11
4.66%
2
18.18%
Total
236
100.00%
11
100.00%



static int ext4_dax_fault(struct vm_fault *vmf)
{
	return ext4_dax_huge_fault(vmf, PE_SIZE_PTE);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dave Jiang
19
100.00%
1
100.00%
Total
19
100.00%
1
100.00%


static const struct vm_operations_struct ext4_dax_vm_ops = {
	.fault		= ext4_dax_fault,
	.huge_fault	= ext4_dax_huge_fault,
	.page_mkwrite	= ext4_dax_fault,
	.pfn_mkwrite	= ext4_dax_fault,
};
#else

#define ext4_dax_vm_ops	ext4_file_vm_ops
#endif


static const struct vm_operations_struct ext4_file_vm_ops = {
	.fault		= ext4_filemap_fault,
	.map_pages	= filemap_map_pages,
	.page_mkwrite   = ext4_page_mkwrite,
};



static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct inode *inode = file->f_mapping->host;

	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
		return -EIO;

	/*
         * We don't support synchronous mappings for non-DAX files. At least
         * until someone comes with a sensible use case.
         */
	if (!IS_DAX(file_inode(file)) && (vma->vm_flags & VM_SYNC))
		return -EOPNOTSUPP;

	file_accessed(file);
	if (IS_DAX(file_inode(file))) {
		vma->vm_ops = &ext4_dax_vm_ops;
		vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
	} else {
		vma->vm_ops = &ext4_file_vm_ops;
	}
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Aneesh Kumar K.V
31
26.96%
1
16.67%
Ross Zwisler
28
24.35%
1
16.67%
Jan Kara
24
20.87%
1
16.67%
Theodore Y. Ts'o
17
14.78%
1
16.67%
Michael Halcrow
13
11.30%
1
16.67%
Matthew Wilcox
2
1.74%
1
16.67%
Total
115
100.00%
6
100.00%



static int ext4_file_open(struct inode * inode, struct file * filp)
{
	struct super_block *sb = inode->i_sb;
	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
	struct vfsmount *mnt = filp->f_path.mnt;
	struct path path;
	char buf[64], *cp;
	int ret;

	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
		return -EIO;

	if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
		     !sb_rdonly(sb))) {
		sbi->s_mount_flags |= 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));
		if (!IS_ERR(cp)) {
			handle_t *handle;
			int err;

			handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
			if (IS_ERR(handle))
				return PTR_ERR(handle);
			BUFFER_TRACE(sbi->s_sbh, "get_write_access");
			err = ext4_journal_get_write_access(handle, sbi->s_sbh);
			if (err) {
				ext4_journal_stop(handle);
				return err;
			}
			strlcpy(sbi->s_es->s_last_mounted, cp,
				sizeof(sbi->s_es->s_last_mounted));
			ext4_handle_dirty_super(handle, sb);
			ext4_journal_stop(handle);
		}
	}

	ret = fscrypt_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;
	}

	filp->f_mode |= FMODE_NOWAIT;
	return dquot_file_open(inode, filp);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Theodore Y. Ts'o
206
64.98%
6
33.33%
Jan Kara
63
19.87%
2
11.11%
Michael Halcrow
21
6.62%
1
5.56%
liang xie
9
2.84%
1
5.56%
Goldwyn Rodrigues
5
1.58%
1
5.56%
Eric Biggers
4
1.26%
1
5.56%
David Howells
3
0.95%
1
5.56%
Miklos Szeredi
3
0.95%
2
11.11%
Al Viro
1
0.32%
1
5.56%
Darrick J. Wong
1
0.32%
1
5.56%
Christoph Hellwig
1
0.32%
1
5.56%
Total
317
100.00%
18
100.00%

/*
 * ext4_llseek() handles both block-mapped and extent-mapped maxbytes values
 * by calling generic_file_llseek_size() with the appropriate maxbytes
 * value for each.
 */


loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
{
	struct inode *inode = file->f_mapping->host;
	loff_t maxbytes;

	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
		maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
	else
		maxbytes = inode->i_sb->s_maxbytes;

	switch (whence) {
	default:
		return generic_file_llseek_size(file, offset, whence,
						maxbytes, i_size_read(inode));
	case SEEK_HOLE:
		inode_lock_shared(inode);
		offset = iomap_seek_hole(inode, offset, &ext4_iomap_ops);
		inode_unlock_shared(inode);
		break;
	case SEEK_DATA:
		inode_lock_shared(inode);
		offset = iomap_seek_data(inode, offset, &ext4_iomap_ops);
		inode_unlock_shared(inode);
		break;
	}

	if (offset < 0)
		return offset;
	return vfs_setpos(file, offset, maxbytes);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
100
63.69%
1
11.11%
Zheng Liu
30
19.11%
1
11.11%
Toshiyuki Okajima
16
10.19%
1
11.11%
Jan Kara
4
2.55%
3
33.33%
Theodore Y. Ts'o
4
2.55%
1
11.11%
Eric Sandeen
2
1.27%
1
11.11%
Andrew Morton
1
0.64%
1
11.11%
Total
157
100.00%
9
100.00%


const struct file_operations ext4_file_operations = {
	.llseek		= ext4_llseek,
	.read_iter	= ext4_file_read_iter,
	.write_iter	= ext4_file_write_iter,
	.unlocked_ioctl = ext4_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= ext4_compat_ioctl,
#endif
	.mmap		= ext4_file_mmap,
	.mmap_supported_flags = MAP_SYNC,
	.open		= ext4_file_open,
	.release	= ext4_release_file,
	.fsync		= ext4_sync_file,
	.get_unmapped_area = thp_get_unmapped_area,
	.splice_read	= generic_file_splice_read,
	.splice_write	= iter_file_splice_write,
	.fallocate	= ext4_fallocate,
};


const struct inode_operations ext4_file_inode_operations = {
	.setattr	= ext4_setattr,
	.getattr	= ext4_file_getattr,
	.listxattr	= ext4_listxattr,
	.get_acl	= ext4_get_acl,
	.set_acl	= ext4_set_acl,
	.fiemap		= ext4_fiemap,
};

Overall Contributors
Person
Tokens
Prop
Commits
CommitProp
Jan Kara
802
37.10%
15
16.30%
Theodore Y. Ts'o
350
16.19%
14
15.22%
Dave Kleikamp
181
8.37%
1
1.09%
Christoph Hellwig
143
6.61%
10
10.87%
Eric Sandeen
107
4.95%
3
3.26%
Goldwyn Rodrigues
104
4.81%
1
1.09%
Zheng Liu
77
3.56%
3
3.26%
Ross Zwisler
73
3.38%
3
3.26%
Matthew Wilcox
60
2.78%
3
3.26%
Aneesh Kumar K.V
60
2.78%
3
3.26%
Al Viro
36
1.67%
7
7.61%
Michael Halcrow
34
1.57%
1
1.09%
Dave Jiang
32
1.48%
3
3.26%
Mingming Cao
18
0.83%
2
2.17%
Toshiyuki Okajima
17
0.79%
1
1.09%
Randy Dodgen
13
0.60%
1
1.09%
liang xie
9
0.42%
1
1.09%
Dmitriy Monakhov
9
0.42%
2
2.17%
Kirill A. Shutemov
5
0.23%
1
1.09%
Toshi Kani
5
0.23%
1
1.09%
David Howells
4
0.19%
2
2.17%
Eric Biggers
4
0.19%
1
1.09%
Boaz Harrosh
4
0.19%
1
1.09%
Miklos Szeredi
3
0.14%
2
2.17%
Kent Overstreet
2
0.09%
1
1.09%
Amit Arora
2
0.09%
1
1.09%
Stephen Hemminger
1
0.05%
1
1.09%
Fabian Frederick
1
0.05%
1
1.09%
Andi Kleen
1
0.05%
1
1.09%
Alexey Dobriyan
1
0.05%
1
1.09%
Arjan van de Ven
1
0.05%
1
1.09%
Greg Kroah-Hartman
1
0.05%
1
1.09%
Andrew Morton
1
0.05%
1
1.09%
Darrick J. Wong
1
0.05%
1
1.09%
Total
2162
100.00%
92
100.00%
Directory: fs/ext4

Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.