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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2016 Trond Myklebust
* Copyright (c) 2019 Jeff Layton
*
* I/O and data path helper functionality.
*
* Heavily borrowed from equivalent code in fs/nfs/io.c
*/
#include <linux/ceph/ceph_debug.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/rwsem.h>
#include <linux/fs.h>
#include "super.h"
#include "io.h"
/* Call with exclusively locked inode->i_rwsem */
static void ceph_block_o_direct(struct ceph_inode_info *ci, struct inode *inode)
{
bool is_odirect;
lockdep_assert_held_write(&inode->i_rwsem);
spin_lock(&ci->i_ceph_lock);
/* ensure that bit state is consistent */
smp_mb__before_atomic();
is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
if (is_odirect) {
clear_bit(CEPH_I_ODIRECT_BIT, &ci->i_ceph_flags);
/* ensure modified bit is visible */
smp_mb__after_atomic();
}
spin_unlock(&ci->i_ceph_lock);
if (is_odirect)
inode_dio_wait(inode);
}
/**
* ceph_start_io_read - declare the file is being used for buffered reads
* @inode: file inode
*
* Declare that a buffered read operation is about to start, and ensure
* that we block all direct I/O.
* On exit, the function ensures that the CEPH_I_ODIRECT flag is unset,
* and holds a shared lock on inode->i_rwsem to ensure that the flag
* cannot be changed.
* In practice, this means that buffered read operations are allowed to
* execute in parallel, thanks to the shared lock, whereas direct I/O
* operations need to wait to grab an exclusive lock in order to set
* CEPH_I_ODIRECT.
* Note that buffered writes and truncates both take a write lock on
* inode->i_rwsem, meaning that those are serialised w.r.t. the reads.
*/
int ceph_start_io_read(struct inode *inode)
{
struct ceph_inode_info *ci = ceph_inode(inode);
bool is_odirect;
int err;
/* Be an optimist! */
err = down_read_killable(&inode->i_rwsem);
if (err)
return err;
spin_lock(&ci->i_ceph_lock);
/* ensure that bit state is consistent */
smp_mb__before_atomic();
is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
spin_unlock(&ci->i_ceph_lock);
if (!is_odirect)
return 0;
up_read(&inode->i_rwsem);
/* Slow path.... */
err = down_write_killable(&inode->i_rwsem);
if (err)
return err;
ceph_block_o_direct(ci, inode);
downgrade_write(&inode->i_rwsem);
return 0;
}
/**
* ceph_end_io_read - declare that the buffered read operation is done
* @inode: file inode
*
* Declare that a buffered read operation is done, and release the shared
* lock on inode->i_rwsem.
*/
void
ceph_end_io_read(struct inode *inode)
{
up_read(&inode->i_rwsem);
}
/**
* ceph_start_io_write - declare the file is being used for buffered writes
* @inode: file inode
*
* Declare that a buffered write operation is about to start, and ensure
* that we block all direct I/O.
*/
int ceph_start_io_write(struct inode *inode)
{
int err = down_write_killable(&inode->i_rwsem);
if (!err)
ceph_block_o_direct(ceph_inode(inode), inode);
return err;
}
/**
* ceph_end_io_write - declare that the buffered write operation is done
* @inode: file inode
*
* Declare that a buffered write operation is done, and release the
* lock on inode->i_rwsem.
*/
void
ceph_end_io_write(struct inode *inode)
{
up_write(&inode->i_rwsem);
}
/* Call with exclusively locked inode->i_rwsem */
static void ceph_block_buffered(struct ceph_inode_info *ci, struct inode *inode)
{
bool is_odirect;
lockdep_assert_held_write(&inode->i_rwsem);
spin_lock(&ci->i_ceph_lock);
/* ensure that bit state is consistent */
smp_mb__before_atomic();
is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
if (!is_odirect) {
set_bit(CEPH_I_ODIRECT_BIT, &ci->i_ceph_flags);
/* ensure modified bit is visible */
smp_mb__after_atomic();
}
spin_unlock(&ci->i_ceph_lock);
if (!is_odirect) {
/* FIXME: unmap_mapping_range? */
filemap_write_and_wait(inode->i_mapping);
}
}
/**
* ceph_start_io_direct - declare the file is being used for direct i/o
* @inode: file inode
*
* Declare that a direct I/O operation is about to start, and ensure
* that we block all buffered I/O.
* On exit, the function ensures that the CEPH_I_ODIRECT flag is set,
* and holds a shared lock on inode->i_rwsem to ensure that the flag
* cannot be changed.
* In practice, this means that direct I/O operations are allowed to
* execute in parallel, thanks to the shared lock, whereas buffered I/O
* operations need to wait to grab an exclusive lock in order to clear
* CEPH_I_ODIRECT.
* Note that buffered writes and truncates both take a write lock on
* inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT.
*/
int ceph_start_io_direct(struct inode *inode)
{
struct ceph_inode_info *ci = ceph_inode(inode);
bool is_odirect;
int err;
/* Be an optimist! */
err = down_read_killable(&inode->i_rwsem);
if (err)
return err;
spin_lock(&ci->i_ceph_lock);
/* ensure that bit state is consistent */
smp_mb__before_atomic();
is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT;
spin_unlock(&ci->i_ceph_lock);
if (is_odirect)
return 0;
up_read(&inode->i_rwsem);
/* Slow path.... */
err = down_write_killable(&inode->i_rwsem);
if (err)
return err;
ceph_block_buffered(ci, inode);
downgrade_write(&inode->i_rwsem);
return 0;
}
/**
* ceph_end_io_direct - declare that the direct i/o operation is done
* @inode: file inode
*
* Declare that a direct I/O operation is done, and release the shared
* lock on inode->i_rwsem.
*/
void
ceph_end_io_direct(struct inode *inode)
{
up_read(&inode->i_rwsem);
}
|
