summaryrefslogtreecommitdiffstats
path: root/fs/jbd/commit.c
blob: 4bd882548c456bc496c9facab237e12445efaed1 (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
pre { line-height: 125%; }
td.linenos .normal { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
span.linenos { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
td.linenos .special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
span.linenos.special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
.highlight .hll { background-color: #ffffcc }
.highlight .c { color: #888888 } /* Comment */
.highlight .err { color: #a61717; background-color: #e3d2d2 } /* Error */
.highlight .k { color: #008800; font-weight: bold } /* Keyword */
.highlight .ch { color: #888888 } /* Comment.Hashbang */
.highlight .cm { color: #888888 } /* Comment.Multiline */
.highlight .cp { color: #cc0000; font-weight: bold } /* Comment.Preproc */
.highlight .cpf { color: #888888 } /* Comment.PreprocFile */
.highlight .c1 { color: #888888 } /* Comment.Single */
.highlight .cs { color: #cc0000; font-weight: bold; background-color: #fff0f0 } /* Comment.Special */
.highlight .gd { color: #000000; background-color: #ffdddd } /* Generic.Deleted */
.highlight .ge { font-style: italic } /* Generic.Emph */
.highlight .ges { font-weight: bold; font-style: italic } /* Generic.EmphStrong */
.highlight .gr { color: #aa0000 } /* Generic.Error */
.highlight .gh { color: #333333 } /* Generic.Heading */
.highlight .gi { color: #000000; background-color: #ddffdd } /* Generic.Inserted */
.highlight .go { color: #888888 } /* Generic.Output */
.highlight .gp { color: #555555 } /* Generic.Prompt */
.highlight .gs { font-weight: bold } /* Generic.Strong */
.highlight .gu { color: #666666 } /* Generic.Subheading */
.highlight .gt { color: #aa0000 } /* Generic.Traceback */
.highlight .kc { color: #008800; font-weight: bold } /* Keyword.Constant */
.highlight .kd { color: #008800; font-weight: bold } /* Keyword.Declaration */
.highlight .kn { color: #008800; font-weight: bold } /* Keyword.Namespace */
.highlight .kp { color: #008800 } /* Keyword.Pseudo */
.highlight .kr { color: #008800; font-weight: bold } /* Keyword.Reserved */
.highlight .kt { color: #888888; font-weight: bold } /* Keyword.Type */
.highlight .m { color: #0000DD; font-weight: bold } /* Literal.Number */
.highlight .s { color: #dd2200; background-color: #fff0f0 } /* Literal.String */
.highlight .na { color: #336699 } /* Name.Attribute */
.highlight .nb { color: #003388 } /* Name.Builtin */
.highlight .nc { color: #bb0066; font-weight: bold } /* Name.Class */
.highlight .no { color: #003366; font-weight: bold } /* Name.Constant */
.highlight .nd { color: #555555 } /* Name.Decorator */
.highlight .ne { color: #bb0066; font-weight: bold } /* Name.Exception */
.highlight .nf { color: #0066bb; font-weight: bold } /* Name.Function */
.highlight .nl { color: #336699; font-style: italic } /* Name.Label */
.highlight .nn { color: #bb0066; font-weight: bold } /* Name.Namespace */
.highlight .py { color: #336699; font-weight: bold } /* Name.Property */
.highlight .nt { color: #bb0066; font-weight: bold } /* Name.Tag */
.highlight .nv { color: #336699 } /* Name.Variable */
.highlight .ow { color: #008800 } /* Operator.Word */
.highlight .w { color: #bbbbbb } /* Text.Whitespace */
.highlight .mb { color: #0000DD; font-weight: bold } /* Literal.Number.Bin */
.highlight .mf { color: #0000DD; font-weight: bold } /* Literal.Number.Float */
.highlight .mh { color: #0000DD; font-weight: bold } /* Literal.Number.Hex */
.highlight .mi { color: #0000DD; font-weight: bold } /* Literal.Number.Integer */
.highlight .mo { color: #0000DD; font-weight: bold } /* Literal.Number.Oct */
.highlight .sa { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Affix */
.highlight .sb { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Backtick */
.highlight .sc { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Char */
.highlight .dl { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Delimiter */
.highlight .sd { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Doc */
.highlight .s2 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Double */
.highlight .se { color: #0044dd; background-color: #fff0f0 } /* Literal.String.Escape */
.highlight .sh { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Heredoc */
.highlight .si { color: #3333bb; background-color: #fff0f0 } /* Literal.String.Interpol */
.highlight .sx { color: #22bb22; background-color: #f0fff0 } /* Literal.String.Other */
.highlight .sr { color: #008800; background-color: #fff0ff } /* Literal.String.Regex */
.highlight .s1 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Single */
.highlight .ss { color: #aa6600; background-color: #fff0f0 } /* Literal.String.Symbol */
.highlight .bp { color: #003388 } /* Name.Builtin.Pseudo */
.highlight .fm { color: #0066bb; font-weight: bold } /* Name.Function.Magic */
.highlight .vc { color: #336699 } /* Name.Variable.Class */
.highlight .vg { color: #dd7700 } /* Name.Variable.Global */
.highlight .vi { color: #3333bb } /* Name.Variable.Instance */
.highlight .vm { color: #336699 } /* Name.Variable.Magic */
.highlight .il { color: #0000DD; font-weight: bold } /* Literal.Number.Integer.Long */
/*
 * Author: Tatu Ylonen <ylo@cs.hut.fi>
 * Copyright (c) 1995 Tatu Ylonen <ylo@cs.hut.fi>, Espoo, Finland
 *                    All rights reserved
 * Functions for manipulating fifo buffers (that can grow if needed).
 *
 * As far as I am concerned, the code I have written for this software
 * can be used freely for any purpose.  Any derived versions of this
 * software must be clearly marked as such, and if the derived work is
 * incompatible with the protocol description in the RFC file, it must be
 * called by a name other than "ssh" or "Secure Shell".
 */

#include "includes.h"
RCSID("$OpenBSD: buffer.c,v 1.15 2002/01/18 18:14:17 stevesk Exp $");

#include "xmalloc.h"
#include "buffer.h"
#include "log.h"

/* Initializes the buffer structure. */

void
buffer_init(Buffer *buffer)
{
	buffer->alloc = 4096;
	buffer->buf = xmalloc(buffer->alloc);
	buffer->offset = 0;
	buffer->end = 0;
}

/* Frees any memory used for the buffer. */

void
buffer_free(Buffer *buffer)
{
	memset(buffer->buf, 0, buffer->alloc);
	xfree(buffer->buf);
}

/*
 * Clears any data from the buffer, making it empty.  This does not actually
 * zero the memory.
 */

void
buffer_clear(Buffer *buffer)
{
	buffer->offset = 0;
	buffer->end = 0;
}

/* Appends data to the buffer, expanding it if necessary. */

void
buffer_append(Buffer *buffer, const void *data, u_int len)
{
	void *p;
	p = buffer_append_space(buffer, len);
	memcpy(p, data, len);
}

/*
 * Appends space to the buffer, expanding the buffer if necessary. This does
 * not actually copy the data into the buffer, but instead returns a pointer
 * to the allocated region.
 */

void *
buffer_append_space(Buffer *buffer, u_int len)
{
	void *p;

	/* If the buffer is empty, start using it from the beginning. */
	if (buffer->offset == buffer->end) {
		buffer->offset = 0;
		buffer->end = 0;
	}
restart:
	/* If there is enough space to store all data, store it now. */
	if (buffer->end + len < buffer->alloc) {
		p = buffer->buf + buffer->end;
		buffer->end += len;
		return p;
	}
	/*
	 * If the buffer is quite empty, but all data is at the end, move the
	 * data to the beginning and retry.
	 */
	if (buffer->offset > buffer->alloc / 2) {
		memmove(buffer->buf, buffer->buf + buffer->offset,
			buffer->end - buffer->offset);
		buffer->end -= buffer->offset;
		buffer->offset = 0;
		goto restart;
	}
	/* Increase the size of the buffer and retry. */
	buffer->alloc += len + 32768;
	buffer->buf = xrealloc(buffer->buf, buffer->alloc);
	goto restart;
	/* NOTREACHED */
}

/* Returns the number of bytes of data in the buffer. */

u_int
buffer_len(Buffer *buffer)
{
	return buffer->end - buffer->offset;
}

/* Gets data from the beginning of the buffer. */

void
buffer_get(Buffer *buffer, void *buf, u_int len)
{
	if (len > buffer->end - buffer->offset)
		fatal("buffer_get: trying to get more bytes %d than in buffer %d",
		    len, buffer->end - buffer->offset);
	memcpy(buf, buffer->buf + buffer->offset, len);
	buffer->offset += len;
}

/* Consumes the given number of bytes from the beginning of the buffer. */

void
buffer_consume(Buffer *buffer, u_int bytes)
{
	if (bytes > buffer->end - buffer->offset)
		fatal("buffer_consume: trying to get more bytes than in buffer");
	buffer->offset += bytes;
}

/* Consumes the given number of bytes from the end of the buffer. */

void
buffer_consume_end(Buffer *buffer, u_int bytes)
{
	if (bytes > buffer->end - buffer->offset)
		fatal("buffer_consume_end: trying to get more bytes than in buffer");
	buffer->end -= bytes;
}

/* Returns a pointer to the first used byte in the buffer. */

void *
buffer_ptr(Buffer *buffer)
{
	return buffer->buf + buffer->offset;
}

/* Du
/*
 * linux/fs/jbd/commit.c
 *
 * Written by Stephen C. Tweedie <sct@redhat.com>, 1998
 *
 * Copyright 1998 Red Hat corp --- All Rights Reserved
 *
 * This file is part of the Linux kernel and is made available under
 * the terms of the GNU General Public License, version 2, or at your
 * option, any later version, incorporated herein by reference.
 *
 * Journal commit routines for the generic filesystem journaling code;
 * part of the ext2fs journaling system.
 */

#include <linux/time.h>
#include <linux/fs.h>
#include <linux/jbd.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/bio.h>

/*
 * Default IO end handler for temporary BJ_IO buffer_heads.
 */
static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
{
	BUFFER_TRACE(bh, "");
	if (uptodate)
		set_buffer_uptodate(bh);
	else
		clear_buffer_uptodate(bh);
	unlock_buffer(bh);
}

/*
 * When an ext3-ordered file is truncated, it is possible that many pages are
 * not successfully freed, because they are attached to a committing transaction.
 * After the transaction commits, these pages are left on the LRU, with no
 * ->mapping, and with attached buffers.  These pages are trivially reclaimable
 * by the VM, but their apparent absence upsets the VM accounting, and it makes
 * the numbers in /proc/meminfo look odd.
 *
 * So here, we have a buffer which has just come off the forget list.  Look to
 * see if we can strip all buffers from the backing page.
 *
 * Called under journal->j_list_lock.  The caller provided us with a ref
 * against the buffer, and we drop that here.
 */
static void release_buffer_page(struct buffer_head *bh)
{
	struct page *page;

	if (buffer_dirty(bh))
		goto nope;
	if (atomic_read(&bh->b_count) != 1)
		goto nope;
	page = bh->b_page;
	if (!page)
		goto nope;
	if (page->mapping)
		goto nope;

	/* OK, it's a truncated page */
	if (!trylock_page(page))
		goto nope;

	page_cache_get(page);
	__brelse(bh);
	try_to_free_buffers(page);
	unlock_page(page);
	page_cache_release(page);
	return;

nope:
	__brelse(bh);
}

/*
 * Decrement reference counter for data buffer. If it has been marked
 * 'BH_Freed', release it and the page to which it belongs if possible.
 */
static void release_data_buffer(struct buffer_head *bh)
{
	if (buffer_freed(bh)) {
		clear_buffer_freed(bh);
		release_buffer_page(bh);
	} else
		put_bh(bh);
}

/*
 * Try to acquire jbd_lock_bh_state() against the buffer, when j_list_lock is
 * held.  For ranking reasons we must trylock.  If we lose, schedule away and
 * return 0.  j_list_lock is dropped in this case.
 */
static int inverted_lock(journal_t *journal, struct buffer_head *bh)
{
	if (!jbd_trylock_bh_state(bh)) {
		spin_unlock(&journal->j_list_lock);
		schedule();
		return 0;
	}
	return 1;
}

/* Done it all: now write the commit record.  We should have
 * cleaned up our previous buffers by now, so if we are in abort
 * mode we can now just skip the rest of the journal write
 * entirely.
 *
 * Returns 1 if the journal needs to be aborted or 0 on success
 */
static int journal_write_commit_record(journal_t *journal,
					transaction_t *commit_transaction)
{
	struct journal_head *descriptor;
	struct buffer_head *bh;
	journal_header_t *header;
	int ret;
	int barrier_done = 0;

	if (is_journal_aborted(journal))
		return 0;

	descriptor = journal_get_descriptor_buffer(journal);
	if (!descriptor)
		return 1;

	bh = jh2bh(descriptor);

	header = (journal_header_t *)(bh->b_data);
	header->h_magic = cpu_to_be32(JFS_MAGIC_NUMBER);
	header->h_blocktype = cpu_to_be32(JFS_COMMIT_BLOCK);
	header->h_sequence = cpu_to_be32(commit_transaction->t_tid);

	JBUFFER_TRACE(descriptor, "write commit block");
	set_buffer_dirty(bh);
	if (journal->j_flags & JFS_BARRIER) {
		set_buffer_ordered(bh);
		barrier_done = 1;
	}
	ret = sync_dirty_buffer(bh);
	if (barrier_done)
		clear_buffer_ordered(bh);
	/* is it possible for another commit to fail at roughly
	 * the same time as this one?  If so, we don't want to
	 * trust the barrier flag in the super, but instead want
	 * to remember if we sent a barrier request
	 */
	if (ret == -EOPNOTSUPP && barrier_done) {
		char b[BDEVNAME_SIZE];

		printk(KERN_WARNING
			"JBD: barrier-based sync failed on %s - "
			"disabling barriers\n",
			bdevname(journal->j_dev, b));
		spin_lock(&journal->j_state_lock);
		journal->j_flags &= ~JFS_BARRIER;
		spin_unlock(&journal->j_state_lock);

		/* And try again, without the barrier */
		set_buffer_uptodate(bh);
		set_buffer_dirty(bh);
		ret = sync_dirty_buffer(bh);
	}
	put_bh(bh);		/* One for getblk() */
	journal_put_journal_head(descriptor);

	return (ret == -EIO);
}

static void journal_do_submit_data(struct buffer_head **wbuf, int bufs,
				   int write_op)
{
	int i;

	for (i = 0; i < bufs; i++) {
		wbuf[i]->b_end_io = end_buffer_write_sync;
		/* We use-up our safety reference in submit_bh() */
		submit_bh(write_op, wbuf[i]);
	}
}

/*
 *  Submit all the data buffers to disk
 */
static int journal_submit_data_buffers(journal_t *journal,
				       transaction_t *commit_transaction,
				       int write_op)
{
	struct journal_head *jh;
	struct buffer_head<