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
253
254
|
// SPDX-License-Identifier: GPL-2.0
/*
* FUSE inode io modes.
*
* Copyright (c) 2024 CTERA Networks.
*/
#include "fuse_i.h"
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/file.h>
#include <linux/fs.h>
/*
* Return true if need to wait for new opens in caching mode.
*/
static inline bool fuse_is_io_cache_wait(struct fuse_inode *fi)
{
return READ_ONCE(fi->iocachectr) < 0 && !fuse_inode_backing(fi);
}
/*
* Start cached io mode.
*
* Blocks new parallel dio writes and waits for the in-progress parallel dio
* writes to complete.
*/
int fuse_file_cached_io_start(struct inode *inode, struct fuse_file *ff)
{
struct fuse_inode *fi = get_fuse_inode(inode);
/* There are no io modes if server does not implement open */
if (!ff->args)
return 0;
spin_lock(&fi->lock);
/*
* Setting the bit advises new direct-io writes to use an exclusive
* lock - without it the wait below might be forever.
*/
while (fuse_is_io_cache_wait(fi)) {
set_bit(FUSE_I_CACHE_IO_MODE, &fi->state);
spin_unlock(&fi->lock);
wait_event(fi->direct_io_waitq, !fuse_is_io_cache_wait(fi));
spin_lock(&fi->lock);
}
/*
* Check if inode entered passthrough io mode while waiting for parallel
* dio write completion.
*/
if (fuse_inode_backing(fi)) {
clear_bit(FUSE_I_CACHE_IO_MODE, &fi->state);
spin_unlock(&fi->lock);
return -ETXTBSY;
}
WARN_ON(ff->iomode == IOM_UNCACHED);
if (ff->iomode == IOM_NONE) {
ff->iomode = IOM_CACHED;
if (fi->iocachectr == 0)
set_bit(FUSE_I_CACHE_IO_MODE, &fi->state);
fi->iocachectr++;
}
spin_unlock(&fi->lock);
return 0;
}
static void fuse_file_cached_io_end(struct inode *inode, struct fuse_file *ff)
{
struct fuse_inode *fi = get_fuse_inode(inode);
spin_lock(&fi->lock);
WARN_ON(fi->iocachectr <= 0);
WARN_ON(ff->iomode != IOM_CACHED);
ff->iomode = IOM_NONE;
fi->iocachectr--;
if (fi->iocachectr == 0)
clear_bit(FUSE_I_CACHE_IO_MODE, &fi->state);
spin_unlock(&fi->lock);
}
/* Start strictly uncached io mode where cache access is not allowed */
int fuse_file_uncached_io_start(struct inode *inode, struct fuse_file *ff, struct fuse_backing *fb)
{
struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_backing *oldfb;
int err = 0;
spin_lock(&fi->lock);
/* deny conflicting backing files on same fuse inode */
oldfb = fuse_inode_backing(fi);
if (oldfb && oldfb != fb) {
err = -EBUSY;
goto unlock;
}
if (fi->iocachectr > 0) {
err = -ETXTBSY;
goto unlock;
}
WARN_ON(ff->iomode != IOM_NONE);
fi->iocachectr--;
ff->iomode = IOM_UNCACHED;
/* fuse inode holds a single refcount of backing file */
if (!oldfb) {
oldfb = fuse_inode_backing_set(fi, fb);
WARN_ON_ONCE(oldfb != NULL);
} else {
fuse_backing_put(fb);
}
unlock:
spin_unlock(&fi->lock);
return err;
}
void fuse_file_uncached_io_end(struct inode *inode, struct fuse_file *ff)
{
struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_backing *oldfb = NULL;
spin_lock(&fi->lock);
WARN_ON(fi->iocachectr >= 0);
WARN_ON(ff->iomode != IOM_UNCACHED);
ff->iomode = IOM_NONE;
fi->iocachectr++;
if (!fi->iocachectr) {
wake_up(&fi->direct_io_waitq);
oldfb = fuse_inode_backing_set(fi, NULL);
}
spin_unlock(&fi->lock);
if (oldfb)
fuse_backing_put(oldfb);
}
/*
* Open flags that are allowed in combination with FOPEN_PASSTHROUGH.
* A combination of FOPEN_PASSTHROUGH and FOPEN_DIRECT_IO means that read/write
* operations go directly to the server, but mmap is done on the backing file.
* FOPEN_PASSTHROUGH mode should not co-exist with any users of the fuse inode
* page cache, so FOPEN_KEEP_CACHE is a strange and undesired combination.
*/
#define FOPEN_PASSTHROUGH_MASK \
(FOPEN_PASSTHROUGH | FOPEN_DIRECT_IO | FOPEN_PARALLEL_DIRECT_WRITES | \
FOPEN_NOFLUSH)
static int fuse_file_passthrough_open(struct inode *inode, struct file *file)
{
struct fuse_file *ff = file->private_data;
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_backing *fb;
int err;
/* Check allowed conditions for file open in passthrough mode */
if (!IS_ENABLED(CONFIG_FUSE_PASSTHROUGH) || !fc->passthrough ||
(ff->open_flags & ~FOPEN_PASSTHROUGH_MASK))
return -EINVAL;
fb = fuse_passthrough_open(file, inode,
ff->args->open_outarg.backing_id);
if (IS_ERR(fb))
return PTR_ERR(fb);
/* First passthrough file open denies caching inode io mode */
err = fuse_file_uncached_io_start(inode, ff, fb);
if (!err)
return 0;
fuse_passthrough_release(ff, fb);
fuse_backing_put(fb);
return err;
}
/* Request access to submit new io to inode via open file */
int fuse_file_io_open(struct file *file, struct inode *inode)
{
struct fuse_file *ff = file->private_data;
struct fuse_inode *fi = get_fuse_inode(inode);
int err;
/*
* io modes are not relevant with DAX and with server that does not
* implement open.
*/
if (FUSE_IS_DAX(inode) || !ff->args)
return 0;
/*
* Server is expected to use FOPEN_PASSTHROUGH for all opens of an inode
* which is already open for passthrough.
*/
err = -EINVAL;
if (fuse_inode_backing(fi) && !(ff->open_flags & FOPEN_PASSTHROUGH))
goto fail;
/*
* FOPEN_PARALLEL_DIRECT_WRITES requires FOPEN_DIRECT_IO.
*/
if (!(ff->open_flags & FOPEN_DIRECT_IO))
ff->open_flags &= ~FOPEN_PARALLEL_DIRECT_WRITES;
/*
* First passthrough file open denies caching inode io mode.
* First caching file open enters caching inode io mode.
*
* Note that if user opens a file open with O_DIRECT, but server did
* not specify FOPEN_DIRECT_IO, a later fcntl() could remove O_DIRECT,
* so we put the inode in caching mode to prevent parallel dio.
*/
if ((ff->open_flags & FOPEN_DIRECT_IO) &&
!(ff->open_flags & FOPEN_PASSTHROUGH))
return 0;
if (ff->open_flags & FOPEN_PASSTHROUGH)
err = fuse_file_passthrough_open(inode, file);
else
err = fuse_file_cached_io_start(inode, ff);
if (err)
goto fail;
return 0;
fail:
pr_debug("failed to open file in requested io mode (open_flags=0x%x, err=%i).\n",
ff->open_flags, err);
/*
* The file open mode determines the inode io mode.
* Using incorrect open mode is a server mistake, which results in
* user visible failure of open() with EIO error.
*/
return -EIO;
}
/* No more pending io and no new io possible to inode via open/mmapped file */
void fuse_file_io_release(struct fuse_file *ff, struct inode *inode)
{
/*
* Last parallel dio close allows caching inode io mode.
* Last caching file close exits caching inode io mode.
*/
switch (ff->iomode) {
case IOM_NONE:
/* Nothing to do */
break;
case IOM_UNCACHED:
fuse_file_uncached_io_end(inode, ff);
break;
case IOM_CACHED:
fuse_file_cached_io_end(inode, ff);
break;
}
}
|
