swh:1:snp:c2847dfd741eae21606027cf29250d1ebcd63fb4
Tip revision: 2c53b436a30867eb6b47dd7bab23ba638d1fb0d2 authored by Linus Torvalds on 13 June 2011, 22:29:59 UTC
Linux 3.0-rc3
Linux 3.0-rc3
Tip revision: 2c53b43
log.c
/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
* Copyright (C) 2004-2007 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.
*/
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/bio.h>
#include <linux/writeback.h>
#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "glock.h"
#include "log.h"
#include "lops.h"
#include "meta_io.h"
#include "util.h"
#include "dir.h"
#include "trace_gfs2.h"
#define PULL 1
/**
* gfs2_struct2blk - compute stuff
* @sdp: the filesystem
* @nstruct: the number of structures
* @ssize: the size of the structures
*
* Compute the number of log descriptor blocks needed to hold a certain number
* of structures of a certain size.
*
* Returns: the number of blocks needed (minimum is always 1)
*/
unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
unsigned int ssize)
{
unsigned int blks;
unsigned int first, second;
blks = 1;
first = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / ssize;
if (nstruct > first) {
second = (sdp->sd_sb.sb_bsize -
sizeof(struct gfs2_meta_header)) / ssize;
blks += DIV_ROUND_UP(nstruct - first, second);
}
return blks;
}
/**
* gfs2_remove_from_ail - Remove an entry from the ail lists, updating counters
* @mapping: The associated mapping (maybe NULL)
* @bd: The gfs2_bufdata to remove
*
* The ail lock _must_ be held when calling this function
*
*/
void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
{
bd->bd_ail = NULL;
list_del_init(&bd->bd_ail_st_list);
list_del_init(&bd->bd_ail_gl_list);
atomic_dec(&bd->bd_gl->gl_ail_count);
brelse(bd->bd_bh);
}
/**
* gfs2_ail1_start_one - Start I/O on a part of the AIL
* @sdp: the filesystem
* @wbc: The writeback control structure
* @ai: The ail structure
*
*/
static int gfs2_ail1_start_one(struct gfs2_sbd *sdp,
struct writeback_control *wbc,
struct gfs2_ail *ai)
__releases(&sdp->sd_ail_lock)
__acquires(&sdp->sd_ail_lock)
{
struct gfs2_glock *gl = NULL;
struct address_space *mapping;
struct gfs2_bufdata *bd, *s;
struct buffer_head *bh;
list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list, bd_ail_st_list) {
bh = bd->bd_bh;
gfs2_assert(sdp, bd->bd_ail == ai);
if (!buffer_busy(bh)) {
if (!buffer_uptodate(bh))
gfs2_io_error_bh(sdp, bh);
list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
continue;
}
if (!buffer_dirty(bh))
continue;
if (gl == bd->bd_gl)
continue;
gl = bd->bd_gl;
list_move(&bd->bd_ail_st_list, &ai->ai_ail1_list);
mapping = bh->b_page->mapping;
if (!mapping)
continue;
spin_unlock(&sdp->sd_ail_lock);
generic_writepages(mapping, wbc);
spin_lock(&sdp->sd_ail_lock);
if (wbc->nr_to_write <= 0)
break;
return 1;
}
return 0;
}
/**
* gfs2_ail1_flush - start writeback of some ail1 entries
* @sdp: The super block
* @wbc: The writeback control structure
*
* Writes back some ail1 entries, according to the limits in the
* writeback control structure
*/
void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc)
{
struct list_head *head = &sdp->sd_ail1_list;
struct gfs2_ail *ai;
trace_gfs2_ail_flush(sdp, wbc, 1);
spin_lock(&sdp->sd_ail_lock);
restart:
list_for_each_entry_reverse(ai, head, ai_list) {
if (wbc->nr_to_write <= 0)
break;
if (gfs2_ail1_start_one(sdp, wbc, ai))
goto restart;
}
spin_unlock(&sdp->sd_ail_lock);
trace_gfs2_ail_flush(sdp, wbc, 0);
}
/**
* gfs2_ail1_start - start writeback of all ail1 entries
* @sdp: The superblock
*/
static void gfs2_ail1_start(struct gfs2_sbd *sdp)
{
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
.nr_to_write = LONG_MAX,
.range_start = 0,
.range_end = LLONG_MAX,
};
return gfs2_ail1_flush(sdp, &wbc);
}
/**
* gfs2_ail1_empty_one - Check whether or not a trans in the AIL has been synced
* @sdp: the filesystem
* @ai: the AIL entry
*
*/
static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
{
struct gfs2_bufdata *bd, *s;
struct buffer_head *bh;
list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list,
bd_ail_st_list) {
bh = bd->bd_bh;
gfs2_assert(sdp, bd->bd_ail == ai);
if (buffer_busy(bh))
continue;
if (!buffer_uptodate(bh))
gfs2_io_error_bh(sdp, bh);
list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
}
}
/**
* gfs2_ail1_empty - Try to empty the ail1 lists
* @sdp: The superblock
*
* Tries to empty the ail1 lists, starting with the oldest first
*/
static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
{
struct gfs2_ail *ai, *s;
int ret;
spin_lock(&sdp->sd_ail_lock);
list_for_each_entry_safe_reverse(ai, s, &sdp->sd_ail1_list, ai_list) {
gfs2_ail1_empty_one(sdp, ai);
if (list_empty(&ai->ai_ail1_list))
list_move(&ai->ai_list, &sdp->sd_ail2_list);
else
break;
}
ret = list_empty(&sdp->sd_ail1_list);
spin_unlock(&sdp->sd_ail_lock);
return ret;
}
static void gfs2_ail1_wait(struct gfs2_sbd *sdp)
{
struct gfs2_ail *ai;
struct gfs2_bufdata *bd;
struct buffer_head *bh;
spin_lock(&sdp->sd_ail_lock);
list_for_each_entry_reverse(ai, &sdp->sd_ail1_list, ai_list) {
list_for_each_entry(bd, &ai->ai_ail1_list, bd_ail_st_list) {
bh = bd->bd_bh;
if (!buffer_locked(bh))
continue;
get_bh(bh);
spin_unlock(&sdp->sd_ail_lock);
wait_on_buffer(bh);
brelse(bh);
return;
}
}
spin_unlock(&sdp->sd_ail_lock);
}
/**
* gfs2_ail2_empty_one - Check whether or not a trans in the AIL has been synced
* @sdp: the filesystem
* @ai: the AIL entry
*
*/
static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
{
struct list_head *head = &ai->ai_ail2_list;
struct gfs2_bufdata *bd;
while (!list_empty(head)) {
bd = list_entry(head->prev, struct gfs2_bufdata,
bd_ail_st_list);
gfs2_assert(sdp, bd->bd_ail == ai);
gfs2_remove_from_ail(bd);
}
}
static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
{
struct gfs2_ail *ai, *safe;
unsigned int old_tail = sdp->sd_log_tail;
int wrap = (new_tail < old_tail);
int a, b, rm;
spin_lock(&sdp->sd_ail_lock);
list_for_each_entry_safe(ai, safe, &sdp->sd_ail2_list, ai_list) {
a = (old_tail <= ai->ai_first);
b = (ai->ai_first < new_tail);
rm = (wrap) ? (a || b) : (a && b);
if (!rm)
continue;
gfs2_ail2_empty_one(sdp, ai);
list_del(&ai->ai_list);
gfs2_assert_warn(sdp, list_empty(&ai->ai_ail1_list));
gfs2_assert_warn(sdp, list_empty(&ai->ai_ail2_list));
kfree(ai);
}
spin_unlock(&sdp->sd_ail_lock);
}
/**
* gfs2_log_reserve - Make a log reservation
* @sdp: The GFS2 superblock
* @blks: The number of blocks to reserve
*
* Note that we never give out the last few blocks of the journal. Thats
* due to the fact that there is a small number of header blocks
* associated with each log flush. The exact number can't be known until
* flush time, so we ensure that we have just enough free blocks at all
* times to avoid running out during a log flush.
*
* We no longer flush the log here, instead we wake up logd to do that
* for us. To avoid the thundering herd and to ensure that we deal fairly
* with queued waiters, we use an exclusive wait. This means that when we
* get woken with enough journal space to get our reservation, we need to
* wake the next waiter on the list.
*
* Returns: errno
*/
int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
{
unsigned reserved_blks = 6 * (4096 / sdp->sd_vfs->s_blocksize);
unsigned wanted = blks + reserved_blks;
DEFINE_WAIT(wait);
int did_wait = 0;
unsigned int free_blocks;
if (gfs2_assert_warn(sdp, blks) ||
gfs2_assert_warn(sdp, blks <= sdp->sd_jdesc->jd_blocks))
return -EINVAL;
retry:
free_blocks = atomic_read(&sdp->sd_log_blks_free);
if (unlikely(free_blocks <= wanted)) {
do {
prepare_to_wait_exclusive(&sdp->sd_log_waitq, &wait,
TASK_UNINTERRUPTIBLE);
wake_up(&sdp->sd_logd_waitq);
did_wait = 1;
if (atomic_read(&sdp->sd_log_blks_free) <= wanted)
io_schedule();
free_blocks = atomic_read(&sdp->sd_log_blks_free);
} while(free_blocks <= wanted);
finish_wait(&sdp->sd_log_waitq, &wait);
}
if (atomic_cmpxchg(&sdp->sd_log_blks_free, free_blocks,
free_blocks - blks) != free_blocks)
goto retry;
trace_gfs2_log_blocks(sdp, -blks);
/*
* If we waited, then so might others, wake them up _after_ we get
* our share of the log.
*/
if (unlikely(did_wait))
wake_up(&sdp->sd_log_waitq);
down_read(&sdp->sd_log_flush_lock);
return 0;
}
static u64 log_bmap(struct gfs2_sbd *sdp, unsigned int lbn)
{
struct gfs2_journal_extent *je;
list_for_each_entry(je, &sdp->sd_jdesc->extent_list, extent_list) {
if (lbn >= je->lblock && lbn < je->lblock + je->blocks)
return je->dblock + lbn - je->lblock;
}
return -1;
}
/**
* log_distance - Compute distance between two journal blocks
* @sdp: The GFS2 superblock
* @newer: The most recent journal block of the pair
* @older: The older journal block of the pair
*
* Compute the distance (in the journal direction) between two
* blocks in the journal
*
* Returns: the distance in blocks
*/
static inline unsigned int log_distance(struct gfs2_sbd *sdp, unsigned int newer,
unsigned int older)
{
int dist;
dist = newer - older;
if (dist < 0)
dist += sdp->sd_jdesc->jd_blocks;
return dist;
}
/**
* calc_reserved - Calculate the number of blocks to reserve when
* refunding a transaction's unused buffers.
* @sdp: The GFS2 superblock
*
* This is complex. We need to reserve room for all our currently used
* metadata buffers (e.g. normal file I/O rewriting file time stamps) and
* all our journaled data buffers for journaled files (e.g. files in the
* meta_fs like rindex, or files for which chattr +j was done.)
* If we don't reserve enough space, gfs2_log_refund and gfs2_log_flush
* will count it as free space (sd_log_blks_free) and corruption will follow.
*
* We can have metadata bufs and jdata bufs in the same journal. So each
* type gets its own log header, for which we need to reserve a block.
* In fact, each type has the potential for needing more than one header
* in cases where we have more buffers than will fit on a journal page.
* Metadata journal entries take up half the space of journaled buffer entries.
* Thus, metadata entries have buf_limit (502) and journaled buffers have
* databuf_limit (251) before they cause a wrap around.
*
* Also, we need to reserve blocks for revoke journal entries and one for an
* overall header for the lot.
*
* Returns: the number of blocks reserved
*/
static unsigned int calc_reserved(struct gfs2_sbd *sdp)
{
unsigned int reserved = 0;
unsigned int mbuf_limit, metabufhdrs_needed;
unsigned int dbuf_limit, databufhdrs_needed;
unsigned int revokes = 0;
mbuf_limit = buf_limit(sdp);
metabufhdrs_needed = (sdp->sd_log_commited_buf +
(mbuf_limit - 1)) / mbuf_limit;
dbuf_limit = databuf_limit(sdp);
databufhdrs_needed = (sdp->sd_log_commited_databuf +
(dbuf_limit - 1)) / dbuf_limit;
if (sdp->sd_log_commited_revoke > 0)
revokes = gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke,
sizeof(u64));
reserved = sdp->sd_log_commited_buf + metabufhdrs_needed +
sdp->sd_log_commited_databuf + databufhdrs_needed +
revokes;
/* One for the overall header */
if (reserved)
reserved++;
return reserved;
}
static unsigned int current_tail(struct gfs2_sbd *sdp)
{
struct gfs2_ail *ai;
unsigned int tail;
spin_lock(&sdp->sd_ail_lock);
if (list_empty(&sdp->sd_ail1_list)) {
tail = sdp->sd_log_head;
} else {
ai = list_entry(sdp->sd_ail1_list.prev, struct gfs2_ail, ai_list);
tail = ai->ai_first;
}
spin_unlock(&sdp->sd_ail_lock);
return tail;
}
void gfs2_log_incr_head(struct gfs2_sbd *sdp)
{
if (sdp->sd_log_flush_head == sdp->sd_log_tail)
BUG_ON(sdp->sd_log_flush_head != sdp->sd_log_head);
if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) {
sdp->sd_log_flush_head = 0;
sdp->sd_log_flush_wrapped = 1;
}
}
/**
* gfs2_log_write_endio - End of I/O for a log buffer
* @bh: The buffer head
* @uptodate: I/O Status
*
*/
static void gfs2_log_write_endio(struct buffer_head *bh, int uptodate)
{
struct gfs2_sbd *sdp = bh->b_private;
bh->b_private = NULL;
end_buffer_write_sync(bh, uptodate);
if (atomic_dec_and_test(&sdp->sd_log_in_flight))
wake_up(&sdp->sd_log_flush_wait);
}
/**
* gfs2_log_get_buf - Get and initialize a buffer to use for log control data
* @sdp: The GFS2 superblock
*
* Returns: the buffer_head
*/
struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp)
{
u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
struct buffer_head *bh;
bh = sb_getblk(sdp->sd_vfs, blkno);
lock_buffer(bh);
memset(bh->b_data, 0, bh->b_size);
set_buffer_uptodate(bh);
clear_buffer_dirty(bh);
gfs2_log_incr_head(sdp);
atomic_inc(&sdp->sd_log_in_flight);
bh->b_private = sdp;
bh->b_end_io = gfs2_log_write_endio;
return bh;
}
/**
* gfs2_fake_write_endio -
* @bh: The buffer head
* @uptodate: The I/O Status
*
*/
static void gfs2_fake_write_endio(struct buffer_head *bh, int uptodate)
{
struct buffer_head *real_bh = bh->b_private;
struct gfs2_bufdata *bd = real_bh->b_private;
struct gfs2_sbd *sdp = bd->bd_gl->gl_sbd;
end_buffer_write_sync(bh, uptodate);
free_buffer_head(bh);
unlock_buffer(real_bh);
brelse(real_bh);
if (atomic_dec_and_test(&sdp->sd_log_in_flight))
wake_up(&sdp->sd_log_flush_wait);
}
/**
* gfs2_log_fake_buf - Build a fake buffer head to write metadata buffer to log
* @sdp: the filesystem
* @data: the data the buffer_head should point to
*
* Returns: the log buffer descriptor
*/
struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
struct buffer_head *real)
{
u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
struct buffer_head *bh;
bh = alloc_buffer_head(GFP_NOFS | __GFP_NOFAIL);
atomic_set(&bh->b_count, 1);
bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate) | (1 << BH_Lock);
set_bh_page(bh, real->b_page, bh_offset(real));
bh->b_blocknr = blkno;
bh->b_size = sdp->sd_sb.sb_bsize;
bh->b_bdev = sdp->sd_vfs->s_bdev;
bh->b_private = real;
bh->b_end_io = gfs2_fake_write_endio;
gfs2_log_incr_head(sdp);
atomic_inc(&sdp->sd_log_in_flight);
return bh;
}
static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
{
unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail);
ail2_empty(sdp, new_tail);
atomic_add(dist, &sdp->sd_log_blks_free);
trace_gfs2_log_blocks(sdp, dist);
gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
sdp->sd_jdesc->jd_blocks);
sdp->sd_log_tail = new_tail;
}
/**
* log_write_header - Get and initialize a journal header buffer
* @sdp: The GFS2 superblock
*
* Returns: the initialized log buffer descriptor
*/
static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
{
u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
struct buffer_head *bh;
struct gfs2_log_header *lh;
unsigned int tail;
u32 hash;
bh = sb_getblk(sdp->sd_vfs, blkno);
lock_buffer(bh);
memset(bh->b_data, 0, bh->b_size);
set_buffer_uptodate(bh);
clear_buffer_dirty(bh);
gfs2_ail1_empty(sdp);
tail = current_tail(sdp);
lh = (struct gfs2_log_header *)bh->b_data;
memset(lh, 0, sizeof(struct gfs2_log_header));
lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH);
lh->lh_header.__pad0 = cpu_to_be64(0);
lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH);
lh->lh_header.mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
lh->lh_sequence = cpu_to_be64(sdp->sd_log_sequence++);
lh->lh_flags = cpu_to_be32(flags);
lh->lh_tail = cpu_to_be32(tail);
lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head);
hash = gfs2_disk_hash(bh->b_data, sizeof(struct gfs2_log_header));
lh->lh_hash = cpu_to_be32(hash);
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
submit_bh(WRITE_SYNC | REQ_META, bh);
else
submit_bh(WRITE_FLUSH_FUA | REQ_META, bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh))
gfs2_io_error_bh(sdp, bh);
brelse(bh);
if (sdp->sd_log_tail != tail)
log_pull_tail(sdp, tail);
else
gfs2_assert_withdraw(sdp, !pull);
sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
gfs2_log_incr_head(sdp);
}
static void log_flush_commit(struct gfs2_sbd *sdp)
{
DEFINE_WAIT(wait);
if (atomic_read(&sdp->sd_log_in_flight)) {
do {
prepare_to_wait(&sdp->sd_log_flush_wait, &wait,
TASK_UNINTERRUPTIBLE);
if (atomic_read(&sdp->sd_log_in_flight))
io_schedule();
} while(atomic_read(&sdp->sd_log_in_flight));
finish_wait(&sdp->sd_log_flush_wait, &wait);
}
log_write_header(sdp, 0, 0);
}
static void gfs2_ordered_write(struct gfs2_sbd *sdp)
{
struct gfs2_bufdata *bd;
struct buffer_head *bh;
LIST_HEAD(written);
gfs2_log_lock(sdp);
while (!list_empty(&sdp->sd_log_le_ordered)) {
bd = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_bufdata, bd_le.le_list);
list_move(&bd->bd_le.le_list, &written);
bh = bd->bd_bh;
if (!buffer_dirty(bh))
continue;
get_bh(bh);
gfs2_log_unlock(sdp);
lock_buffer(bh);
if (buffer_mapped(bh) && test_clear_buffer_dirty(bh)) {
bh->b_end_io = end_buffer_write_sync;
submit_bh(WRITE_SYNC, bh);
} else {
unlock_buffer(bh);
brelse(bh);
}
gfs2_log_lock(sdp);
}
list_splice(&written, &sdp->sd_log_le_ordered);
gfs2_log_unlock(sdp);
}
static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
{
struct gfs2_bufdata *bd;
struct buffer_head *bh;
gfs2_log_lock(sdp);
while (!list_empty(&sdp->sd_log_le_ordered)) {
bd = list_entry(sdp->sd_log_le_ordered.prev, struct gfs2_bufdata, bd_le.le_list);
bh = bd->bd_bh;
if (buffer_locked(bh)) {
get_bh(bh);
gfs2_log_unlock(sdp);
wait_on_buffer(bh);
brelse(bh);
gfs2_log_lock(sdp);
continue;
}
list_del_init(&bd->bd_le.le_list);
}
gfs2_log_unlock(sdp);
}
/**
* gfs2_log_flush - flush incore transaction(s)
* @sdp: the filesystem
* @gl: The glock structure to flush. If NULL, flush the whole incore log
*
*/
void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
{
struct gfs2_ail *ai;
down_write(&sdp->sd_log_flush_lock);
/* Log might have been flushed while we waited for the flush lock */
if (gl && !test_bit(GLF_LFLUSH, &gl->gl_flags)) {
up_write(&sdp->sd_log_flush_lock);
return;
}
trace_gfs2_log_flush(sdp, 1);
ai = kzalloc(sizeof(struct gfs2_ail), GFP_NOFS | __GFP_NOFAIL);
INIT_LIST_HEAD(&ai->ai_ail1_list);
INIT_LIST_HEAD(&ai->ai_ail2_list);
if (sdp->sd_log_num_buf != sdp->sd_log_commited_buf) {
printk(KERN_INFO "GFS2: log buf %u %u\n", sdp->sd_log_num_buf,
sdp->sd_log_commited_buf);
gfs2_assert_withdraw(sdp, 0);
}
if (sdp->sd_log_num_databuf != sdp->sd_log_commited_databuf) {
printk(KERN_INFO "GFS2: log databuf %u %u\n",
sdp->sd_log_num_databuf, sdp->sd_log_commited_databuf);
gfs2_assert_withdraw(sdp, 0);
}
gfs2_assert_withdraw(sdp,
sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke);
sdp->sd_log_flush_head = sdp->sd_log_head;
sdp->sd_log_flush_wrapped = 0;
ai->ai_first = sdp->sd_log_flush_head;
gfs2_ordered_write(sdp);
lops_before_commit(sdp);
gfs2_ordered_wait(sdp);
if (sdp->sd_log_head != sdp->sd_log_flush_head)
log_flush_commit(sdp);
else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
gfs2_log_lock(sdp);
atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
trace_gfs2_log_blocks(sdp, -1);
gfs2_log_unlock(sdp);
log_write_header(sdp, 0, PULL);
}
lops_after_commit(sdp, ai);
gfs2_log_lock(sdp);
sdp->sd_log_head = sdp->sd_log_flush_head;
sdp->sd_log_blks_reserved = 0;
sdp->sd_log_commited_buf = 0;
sdp->sd_log_commited_databuf = 0;
sdp->sd_log_commited_revoke = 0;
spin_lock(&sdp->sd_ail_lock);
if (!list_empty(&ai->ai_ail1_list)) {
list_add(&ai->ai_list, &sdp->sd_ail1_list);
ai = NULL;
}
spin_unlock(&sdp->sd_ail_lock);
gfs2_log_unlock(sdp);
trace_gfs2_log_flush(sdp, 0);
up_write(&sdp->sd_log_flush_lock);
kfree(ai);
}
static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
unsigned int reserved;
unsigned int unused;
gfs2_log_lock(sdp);
sdp->sd_log_commited_buf += tr->tr_num_buf_new - tr->tr_num_buf_rm;
sdp->sd_log_commited_databuf += tr->tr_num_databuf_new -
tr->tr_num_databuf_rm;
gfs2_assert_withdraw(sdp, (((int)sdp->sd_log_commited_buf) >= 0) ||
(((int)sdp->sd_log_commited_databuf) >= 0));
sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
reserved = calc_reserved(sdp);
gfs2_assert_withdraw(sdp, sdp->sd_log_blks_reserved + tr->tr_reserved >= reserved);
unused = sdp->sd_log_blks_reserved - reserved + tr->tr_reserved;
atomic_add(unused, &sdp->sd_log_blks_free);
trace_gfs2_log_blocks(sdp, unused);
gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
sdp->sd_jdesc->jd_blocks);
sdp->sd_log_blks_reserved = reserved;
gfs2_log_unlock(sdp);
}
static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
struct list_head *head = &tr->tr_list_buf;
struct gfs2_bufdata *bd;
gfs2_log_lock(sdp);
while (!list_empty(head)) {
bd = list_entry(head->next, struct gfs2_bufdata, bd_list_tr);
list_del_init(&bd->bd_list_tr);
tr->tr_num_buf--;
}
gfs2_log_unlock(sdp);
gfs2_assert_warn(sdp, !tr->tr_num_buf);
}
/**
* gfs2_log_commit - Commit a transaction to the log
* @sdp: the filesystem
* @tr: the transaction
*
* We wake up gfs2_logd if the number of pinned blocks exceed thresh1
* or the total number of used blocks (pinned blocks plus AIL blocks)
* is greater than thresh2.
*
* At mount time thresh1 is 1/3rd of journal size, thresh2 is 2/3rd of
* journal size.
*
* Returns: errno
*/
void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
log_refund(sdp, tr);
buf_lo_incore_commit(sdp, tr);
up_read(&sdp->sd_log_flush_lock);
if (atomic_read(&sdp->sd_log_pinned) > atomic_read(&sdp->sd_log_thresh1) ||
((sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free)) >
atomic_read(&sdp->sd_log_thresh2)))
wake_up(&sdp->sd_logd_waitq);
}
/**
* gfs2_log_shutdown - write a shutdown header into a journal
* @sdp: the filesystem
*
*/
void gfs2_log_shutdown(struct gfs2_sbd *sdp)
{
down_write(&sdp->sd_log_flush_lock);
gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved);
gfs2_assert_withdraw(sdp, !sdp->sd_log_num_buf);
gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
gfs2_assert_withdraw(sdp, !sdp->sd_log_num_rg);
gfs2_assert_withdraw(sdp, !sdp->sd_log_num_databuf);
gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list));
sdp->sd_log_flush_head = sdp->sd_log_head;
sdp->sd_log_flush_wrapped = 0;
log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT,
(sdp->sd_log_tail == current_tail(sdp)) ? 0 : PULL);
gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks);
gfs2_assert_warn(sdp, sdp->sd_log_head == sdp->sd_log_tail);
gfs2_assert_warn(sdp, list_empty(&sdp->sd_ail2_list));
sdp->sd_log_head = sdp->sd_log_flush_head;
sdp->sd_log_tail = sdp->sd_log_head;
up_write(&sdp->sd_log_flush_lock);
}
/**
* gfs2_meta_syncfs - sync all the buffers in a filesystem
* @sdp: the filesystem
*
*/
void gfs2_meta_syncfs(struct gfs2_sbd *sdp)
{
gfs2_log_flush(sdp, NULL);
for (;;) {
gfs2_ail1_start(sdp);
gfs2_ail1_wait(sdp);
if (gfs2_ail1_empty(sdp))
break;
}
}
static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp)
{
return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1));
}
static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
{
unsigned int used_blocks = sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free);
return used_blocks >= atomic_read(&sdp->sd_log_thresh2);
}
/**
* gfs2_logd - Update log tail as Active Items get flushed to in-place blocks
* @sdp: Pointer to GFS2 superblock
*
* Also, periodically check to make sure that we're using the most recent
* journal index.
*/
int gfs2_logd(void *data)
{
struct gfs2_sbd *sdp = data;
unsigned long t = 1;
DEFINE_WAIT(wait);
unsigned preflush;
while (!kthread_should_stop()) {
preflush = atomic_read(&sdp->sd_log_pinned);
if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
gfs2_ail1_empty(sdp);
gfs2_log_flush(sdp, NULL);
}
if (gfs2_ail_flush_reqd(sdp)) {
gfs2_ail1_start(sdp);
gfs2_ail1_wait(sdp);
gfs2_ail1_empty(sdp);
gfs2_log_flush(sdp, NULL);
}
if (!gfs2_ail_flush_reqd(sdp))
wake_up(&sdp->sd_log_waitq);
t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
if (freezing(current))
refrigerator();
do {
prepare_to_wait(&sdp->sd_logd_waitq, &wait,
TASK_INTERRUPTIBLE);
if (!gfs2_ail_flush_reqd(sdp) &&
!gfs2_jrnl_flush_reqd(sdp) &&
!kthread_should_stop())
t = schedule_timeout(t);
} while(t && !gfs2_ail_flush_reqd(sdp) &&
!gfs2_jrnl_flush_reqd(sdp) &&
!kthread_should_stop());
finish_wait(&sdp->sd_logd_waitq, &wait);
}
return 0;
}