summaryrefslogtreecommitdiff
path: root/fs/gfs2/trans.c
blob: a85ca8b2c9ba4aa43439e2f350acbab9dda73b91 (plain)
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
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
 *
 * This copyrighted material is made available to anyone wishing to use,
 * modify, copy, or redistribute it subject to the terms and conditions
 * of the GNU General Public License version 2.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/kallsyms.h>
#include <linux/gfs2_ondisk.h>

#include "gfs2.h"
#include "incore.h"
#include "glock.h"
#include "inode.h"
#include "log.h"
#include "lops.h"
#include "meta_io.h"
#include "trans.h"
#include "util.h"
#include "trace_gfs2.h"

int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
		     unsigned int revokes)
{
	struct gfs2_trans *tr;
	int error;

	BUG_ON(current->journal_info);
	BUG_ON(blocks == 0 && revokes == 0);

	if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
		return -EROFS;

	tr = kzalloc(sizeof(struct gfs2_trans), GFP_NOFS);
	if (!tr)
		return -ENOMEM;

	tr->tr_ip = _RET_IP_;
	tr->tr_blocks = blocks;
	tr->tr_revokes = revokes;
	tr->tr_reserved = 1;
	set_bit(TR_ALLOCED, &tr->tr_flags);
	if (blocks)
		tr->tr_reserved += 6 + blocks;
	if (revokes)
		tr->tr_reserved += gfs2_struct2blk(sdp, revokes,
						   sizeof(u64));
	INIT_LIST_HEAD(&tr->tr_databuf);
	INIT_LIST_HEAD(&tr->tr_buf);

	sb_start_intwrite(sdp->sd_vfs);

	error = gfs2_log_reserve(sdp, tr->tr_reserved);
	if (error)
		goto fail;

	current->journal_info = tr;

	return 0;

fail:
	sb_end_intwrite(sdp->sd_vfs);
	kfree(tr);

	return error;
}

static void gfs2_print_trans(const struct gfs2_trans *tr)
{
	pr_warn("Transaction created at: %pSR\n", (void *)tr->tr_ip);
	pr_warn("blocks=%u revokes=%u reserved=%u touched=%u\n",
		tr->tr_blocks, tr->tr_revokes, tr->tr_reserved,
		test_bit(TR_TOUCHED, &tr->tr_flags));
	pr_warn("Buf %u/%u Databuf %u/%u Revoke %u/%u\n",
		tr->tr_num_buf_new, tr->tr_num_buf_rm,
		tr->tr_num_databuf_new, tr->tr_num_databuf_rm,
		tr->tr_num_revoke, tr->tr_num_revoke_rm);
}

void gfs2_trans_end(struct gfs2_sbd *sdp)
{
	struct gfs2_trans *tr = current->journal_info;
	s64 nbuf;
	int alloced = test_bit(TR_ALLOCED, &tr->tr_flags);

	BUG_ON(!tr);
	current->journal_info = NULL;

	if (!test_bit(TR_TOUCHED, &tr->tr_flags)) {
		gfs2_log_release(sdp, tr->tr_reserved);
		if (alloced) {
			kfree(tr);
			sb_end_intwrite(sdp->sd_vfs);
		}
		return;
	}

	nbuf = tr->tr_num_buf_new + tr->tr_num_databuf_new;
	nbuf -= tr->tr_num_buf_rm;
	nbuf -= tr->tr_num_databuf_rm;

	if (gfs2_assert_withdraw(sdp, (nbuf <= tr->tr_blocks) &&
				       (tr->tr_num_revoke <= tr->tr_revokes)))
		gfs2_print_trans(tr);

	gfs2_log_commit(sdp, tr);
	if (alloced && !test_bit(TR_ATTACHED, &tr->tr_flags))
		kfree(tr);
	up_read(&sdp->sd_log_flush_lock);

	if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS)
		gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
	if (alloced)
		sb_end_intwrite(sdp->sd_vfs);
}

static struct gfs2_bufdata *gfs2_alloc_bufdata(struct gfs2_glock *gl,
					       struct buffer_head *bh,
					       const struct gfs2_log_operations *lops)
{
	struct gfs2_bufdata *bd;

	bd = kmem_cache_zalloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL);
	bd->bd_bh = bh;
	bd->bd_gl = gl;
	bd->bd_ops = lops;
	INIT_LIST_HEAD(&bd->bd_list);
	bh->b_private = bd;
	return bd;
}

/**
 * gfs2_trans_add_data - Add a databuf to the transaction.
 * @gl: The inode glock associated with the buffer
 * @bh: The buffer to add
 *
 * This is used in two distinct cases:
 * i) In ordered write mode
 *    We put the data buffer on a list so that we can ensure that it's
 *    synced to disk at the right time
 * ii) In journaled data mode
 *    We need to journal the data block in the same way as metadata in
 *    the functions above. The difference is that here we have a tag
 *    which is two __be64's being the block number (as per meta data)
 *    and a flag which says whether the data block needs escaping or
 *    not. This means we need a new log entry for each 251 or so data
 *    blocks, which isn't an enormous overhead but twice as much as
 *    for normal metadata blocks.
 */
void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
{
	struct gfs2_trans *tr = current->journal_info;
	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
	struct address_space *mapping = bh->b_page->mapping;
	struct gfs2_inode *ip = GFS2_I(mapping->host);
	struct gfs2_bufdata *bd;

	if (!gfs2_is_jdata(ip)) {
		gfs2_ordered_add_inode(ip);
		return;
	}

	lock_buffer(bh);
	if (buffer_pinned(bh)) {
		set_bit(TR_TOUCHED, &tr->tr_flags);
		goto out;
	}
	gfs2_log_lock(sdp);
	bd = bh->b_private;
	if (bd == NULL) {
		gfs2_log_unlock(sdp);
		unlock_buffer(bh);
		if (bh->b_private == NULL)
			bd = gfs2_alloc_bufdata(gl, bh, &gfs2_databuf_lops);
		else
			bd = bh->b_private;
		lock_buffer(bh);
		gfs2_log_lock(sdp);
	}
	gfs2_assert(sdp, bd->bd_gl == gl);
	set_bit(TR_TOUCHED, &tr->tr_flags);
	if (list_empty(&bd->bd_list)) {
		set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
		set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
		gfs2_pin(sdp, bd->bd_bh);
		tr->tr_num_databuf_new++;
		list_add_tail(&bd->bd_list, &tr->tr_databuf);
	}
	gfs2_log_unlock(sdp);
out:
	unlock_buffer(bh);
}

void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh)
{

	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
	struct gfs2_bufdata *bd;
	struct gfs2_meta_header *mh;
	struct gfs2_trans *tr = current->journal_info;
	enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);

	lock_buffer(bh);
	if (buffer_pinned(bh)) {
		set_bit(TR_TOUCHED, &tr->tr_flags);
		goto out;
	}
	gfs2_log_lock(sdp);
	bd = bh->b_private;
	if (bd == NULL) {
		gfs2_log_unlock(sdp);
		unlock_buffer(bh);
		lock_page(bh->b_page);
		if (bh->b_private == NULL)
			bd = gfs2_alloc_bufdata(gl, bh, &gfs2_buf_lops);
		else
			bd = bh->b_private;
		unlock_page(bh->b_page);
		lock_buffer(bh);
		gfs2_log_lock(sdp);
	}
	gfs2_assert(sdp, bd->bd_gl == gl);
	set_bit(TR_TOUCHED, &tr->tr_flags);
	if (!list_empty(&bd->bd_list))
		goto out_unlock;
	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
	mh = (struct gfs2_meta_header *)bd->bd_bh->b_data;
	if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) {
		pr_err("Attempting to add uninitialised block to journal (inplace block=%lld)\n",
		       (unsigned long long)bd->bd_bh->b_blocknr);
		BUG();
	}
	if (unlikely(state == SFS_FROZEN)) {
		printk(KERN_INFO "GFS2:adding buf while frozen\n");
		gfs2_assert_withdraw(sdp, 0);
	}
	gfs2_pin(sdp, bd->bd_bh);
	mh->__pad0 = cpu_to_be64(0);
	mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
	list_add(&bd->bd_list, &tr->tr_buf);
	tr->tr_num_buf_new++;
out_unlock:
	gfs2_log_unlock(sdp);
out:
	unlock_buffer(bh);
}

void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
{
	struct gfs2_trans *tr = current->journal_info;

	BUG_ON(!list_empty(&bd->bd_list));
	gfs2_add_revoke(sdp, bd);
	set_bit(TR_TOUCHED, &tr->tr_flags);
	tr->tr_num_revoke++;
}

void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len)
{
	struct gfs2_bufdata *bd, *tmp;
	struct gfs2_trans *tr = current->journal_info;
	unsigned int n = len;

	gfs2_log_lock(sdp);
	list_for_each_entry_safe(bd, tmp, &sdp->sd_log_le_revoke, bd_list) {
		if ((bd->bd_blkno >= blkno) && (bd->bd_blkno < (blkno + len))) {
			list_del_init(&bd->bd_list);
			gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke);
			sdp->sd_log_num_revoke--;
			kmem_cache_free(gfs2_bufdata_cachep, bd);
			tr->tr_num_revoke_rm++;
			if (--n == 0)
				break;
		}
	}
	gfs2_log_unlock(sdp);
}