aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ext2/file.c
blob: 423cc01c9d41fda452594481a16f8038f1925a71 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
/*
 *  linux/fs/ext2/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
 *
 *  ext2 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/pagemap.h>
#include <linux/dax.h>
#include <linux/quotaops.h>
#include <linux/iomap.h>
#include <linux/uio.h>
#include "ext2.h"
#include "xattr.h"
#include "acl.h"

#ifdef CONFIG_FS_DAX
static ssize_t ext2_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct inode *inode = iocb->ki_filp->f_mapping->host;
	ssize_t ret;

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

	inode_lock_shared(inode);
	ret = iomap_dax_rw(iocb, to, &ext2_iomap_ops);
	inode_unlock_shared(inode);

	file_accessed(iocb->ki_filp);
	return ret;
}

static ssize_t ext2_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;
	ssize_t ret;

	inode_lock(inode);
	ret = generic_write_checks(iocb, from);
	if (ret <= 0)
		goto out_unlock;
	ret = file_remove_privs(file);
	if (ret)
		goto out_unlock;
	ret = file_update_time(file);
	if (ret)
		goto out_unlock;

	ret = iomap_dax_rw(iocb, from, &ext2_iomap_ops);
	if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
		i_size_write(inode, iocb->ki_pos);
		mark_inode_dirty(inode);
	}

out_unlock:
	inode_unlock(inode);
	if (ret > 0)
		ret = generic_write_sync(iocb, ret);
	return ret;
}

/*
 * The lock ordering for ext2 DAX fault paths is:
 *
 * mmap_sem (MM)
 *   sb_start_pagefault (vfs, freeze)
 *     ext2_inode_info->dax_sem
 *       address_space->i_mmap_rwsem or page_lock (mutually exclusive in DAX)
 *         ext2_inode_info->truncate_mutex
 *
 * The default page_lock and i_size verification done by non-DAX fault paths
 * is sufficient because ext2 doesn't support hole punching.
 */
static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct inode *inode = file_inode(vma->vm_file);
	struct ext2_inode_info *ei = EXT2_I(inode);
	int ret;

	if (vmf->flags & FAULT_FLAG_WRITE) {
		sb_start_pagefault(inode->i_sb);
		file_update_time(vma->vm_file);
	}
	down_read(&ei->dax_sem);

	ret = iomap_dax_fault(vma, vmf, &ext2_iomap_ops);

	up_read(&ei->dax_sem);
	if (vmf->flags & FAULT_FLAG_WRITE)
		sb_end_pagefault(inode->i_sb);
	return ret;
}

static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
						pmd_t *pmd, unsigned int flags)
{
	struct inode *inode = file_inode(vma->vm_file);
	struct ext2_inode_info *ei = EXT2_I(inode);
	int ret;

	if (flags & FAULT_FLAG_WRITE) {
		sb_start_pagefault(inode->i_sb);
		file_update_time(vma->vm_file);
	}
	down_read(&ei->dax_sem);

	ret = dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block);

	up_read(&ei->dax_sem);
	if (flags & FAULT_FLAG_WRITE)
		sb_end_pagefault(inode->i_sb);
	return ret;
}

static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
		struct vm_fault *vmf)
{
	struct inode *inode = file_inode(vma->vm_file);
	struct ext2_inode_info *ei = EXT2_I(inode);
	loff_t size;
	int ret;

	sb_start_pagefault(inode->i_sb);
	file_update_time(vma->vm_file);
	down_read(&ei->dax_sem);

	/* check that the faulting page hasn't raced with truncate */
	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
	if (vmf->pgoff >= size)
		ret = VM_FAULT_SIGBUS;
	else
		ret = dax_pfn_mkwrite(vma, vmf);

	up_read(&ei->dax_sem);
	sb_end_pagefault(inode->i_sb);
	return ret;
}

static const struct vm_operations_struct ext2_dax_vm_ops = {
	.fault		= ext2_dax_fault,
	.pmd_fault	= ext2_dax_pmd_fault,
	.page_mkwrite	= ext2_dax_fault,
	.pfn_mkwrite	= ext2_dax_pfn_mkwrite,
};

static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	if (!IS_DAX(file_inode(file)))
		return generic_file_mmap(file, vma);

	file_accessed(file);
	vma->vm_ops = &ext2_dax_vm_ops;
	vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
	return 0;
}
#else
#define ext2_file_mmap	generic_file_mmap
#endif

/*
 * Called when filp is released. This happens when all file descriptors
 * for a single struct file are closed. Note that different open() calls
 * for the same file yield different struct file structures.
 */
static int ext2_release_file (struct inode * inode, struct file * filp)
{
	if (filp->f_mode & FMODE_WRITE) {
		mutex_lock(&EXT2_I(inode)->truncate_mutex);
		ext2_discard_reservation(inode);
		mutex_unlock(&EXT2_I(inode)->truncate_mutex);
	}
	return 0;
}

int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
	int ret;
	struct super_block *sb = file->f_mapping->host->i_sb;
	struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;

	ret = generic_file_fsync(file, start, end, datasync);
	if (ret == -EIO || test_and_clear_bit(AS_EIO, &mapping->flags)) {
		/* We don't really know where the IO error happened... */
		ext2_error(sb, __func__,
			   "detected IO error when writing metadata buffers");
		ret = -EIO;
	}
	return ret;
}

static ssize_t ext2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
#ifdef CONFIG_FS_DAX
	if (IS_DAX(iocb->ki_filp->f_mapping->host))
		return ext2_dax_read_iter(iocb, to);
#endif
	return generic_file_read_iter(iocb, to);
}

static ssize_t ext2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
#ifdef CONFIG_FS_DAX
	if (IS_DAX(iocb->ki_filp->f_mapping->host))
		return ext2_dax_write_iter(iocb, from);
#endif
	return generic_file_write_iter(iocb, from);
}

const struct file_operations ext2_file_operations = {
	.llseek		= generic_file_llseek,
	.read_iter	= ext2_file_read_iter,
	.write_iter	= ext2_file_write_iter,
	.unlocked_ioctl = ext2_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= ext2_compat_ioctl,
#endif
	.mmap		= ext2_file_mmap,
	.open		= dquot_file_open,
	.release	= ext2_release_file,
	.fsync		= ext2_fsync,
	.splice_read	= generic_file_splice_read,
	.splice_write	= iter_file_splice_write,
};

const struct inode_operations ext2_file_inode_operations = {
#ifdef CONFIG_EXT2_FS_XATTR
	.setxattr	= generic_setxattr,
	.getxattr	= generic_getxattr,
	.listxattr	= ext2_listxattr,
	.removexattr	= generic_removexattr,
#endif
	.setattr	= ext2_setattr,
	.get_acl	= ext2_get_acl,
	.set_acl	= ext2_set_acl,
	.fiemap		= ext2_fiemap,
};