*
* 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 v.2.
+ * of the GNU General Public License version 2.
*/
#include <linux/sched.h>
#include <linux/buffer_head.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
+#include <linux/lm_interface.h>
+#include <linux/delay.h>
#include "gfs2.h"
-#include "lm_interface.h"
#include "incore.h"
#include "bmap.h"
#include "glock.h"
unsigned int first, second;
blks = 1;
- first = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) /
- ssize;
+ first = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / ssize;
if (nstruct > first) {
second = (sdp->sd_sb.sb_bsize -
return blks;
}
-void gfs2_ail1_start(struct gfs2_sbd *sdp, int flags)
+/**
+ * gfs2_ail1_start_one - Start I/O on a part of the AIL
+ * @sdp: the filesystem
+ * @tr: the part of the AIL
+ *
+ */
+
+static void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+ struct gfs2_bufdata *bd, *s;
+ struct buffer_head *bh;
+ int retry;
+
+ BUG_ON(!spin_is_locked(&sdp->sd_log_lock));
+
+ do {
+ retry = 0;
+
+ 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 (!bh){
+ list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
+ continue;
+ }
+
+ if (!buffer_busy(bh)) {
+ if (!buffer_uptodate(bh)) {
+ gfs2_log_unlock(sdp);
+ gfs2_io_error_bh(sdp, bh);
+ gfs2_log_lock(sdp);
+ }
+ list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
+ continue;
+ }
+
+ if (!buffer_dirty(bh))
+ continue;
+
+ list_move(&bd->bd_ail_st_list, &ai->ai_ail1_list);
+
+ gfs2_log_unlock(sdp);
+ wait_on_buffer(bh);
+ ll_rw_block(WRITE, 1, &bh);
+ gfs2_log_lock(sdp);
+
+ retry = 1;
+ break;
+ }
+ } while (retry);
+}
+
+/**
+ * gfs2_ail1_empty_one - Check whether or not a trans in the AIL has been synced
+ * @sdp: the filesystem
+ * @ai: the AIL entry
+ *
+ */
+
+static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai, int flags)
+{
+ 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;
+
+ if (!bh){
+ list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
+ continue;
+ }
+
+ gfs2_assert(sdp, bd->bd_ail == ai);
+
+ if (buffer_busy(bh)) {
+ if (flags & DIO_ALL)
+ continue;
+ else
+ break;
+ }
+
+ if (!buffer_uptodate(bh))
+ gfs2_io_error_bh(sdp, bh);
+
+ list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
+ }
+
+ return list_empty(&ai->ai_ail1_list);
+}
+
+static void gfs2_ail1_start(struct gfs2_sbd *sdp, int flags)
{
struct list_head *head = &sdp->sd_ail1_list;
- uint64_t sync_gen;
- struct list_head *first, *tmp;
- struct gfs2_ail *first_ai, *ai;
+ u64 sync_gen;
+ struct list_head *first;
+ struct gfs2_ail *first_ai, *ai, *tmp;
+ int done = 0;
gfs2_log_lock(sdp);
if (list_empty(head)) {
first = head->prev;
first_ai = list_entry(first, struct gfs2_ail, ai_list);
first_ai->ai_sync_gen = sync_gen;
- gfs2_ail1_start_one(sdp, first_ai);
+ gfs2_ail1_start_one(sdp, first_ai); /* This may drop log lock */
if (flags & DIO_ALL)
first = NULL;
- for (;;) {
+ while(!done) {
if (first && (head->prev != first ||
gfs2_ail1_empty_one(sdp, first_ai, 0)))
break;
- for (tmp = head->prev; tmp != head; tmp = tmp->prev) {
- ai = list_entry(tmp, struct gfs2_ail, ai_list);
+ done = 1;
+ list_for_each_entry_safe_reverse(ai, tmp, head, ai_list) {
if (ai->ai_sync_gen >= sync_gen)
continue;
ai->ai_sync_gen = sync_gen;
- gfs2_ail1_start_one(sdp, ai);
+ gfs2_ail1_start_one(sdp, ai); /* This may drop log lock */
+ done = 0;
break;
}
-
- if (tmp == head)
- break;
}
gfs2_log_unlock(sdp);
return ret;
}
+
+/**
+ * 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);
+ bd->bd_ail = NULL;
+ list_del(&bd->bd_ail_st_list);
+ list_del(&bd->bd_ail_gl_list);
+ atomic_dec(&bd->bd_gl->gl_ail_count);
+ brelse(bd->bd_bh);
+ }
+}
+
static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
{
struct gfs2_ail *ai, *safe;
* @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.
+ *
* Returns: errno
*/
int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
{
unsigned int try = 0;
+ unsigned reserved_blks = 6 * (4096 / sdp->sd_vfs->s_blocksize);
if (gfs2_assert_warn(sdp, blks) ||
gfs2_assert_warn(sdp, blks <= sdp->sd_jdesc->jd_blocks))
mutex_lock(&sdp->sd_log_reserve_mutex);
gfs2_log_lock(sdp);
- while(sdp->sd_log_blks_free <= blks) {
+ while(sdp->sd_log_blks_free <= (blks + reserved_blks)) {
gfs2_log_unlock(sdp);
gfs2_ail1_empty(sdp, 0);
gfs2_log_flush(sdp, NULL);
gfs2_log_lock(sdp);
}
sdp->sd_log_blks_free -= blks;
- /* printk(KERN_INFO "reserved %u blocks (%u left)\n", blks, sdp->sd_log_blks_free); */
gfs2_log_unlock(sdp);
mutex_unlock(&sdp->sd_log_reserve_mutex);
gfs2_log_lock(sdp);
sdp->sd_log_blks_free += blks;
- /* printk(KERN_INFO "released %u blocks (%u left)\n", blks, sdp->sd_log_blks_free); */
gfs2_assert_withdraw(sdp,
sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks);
gfs2_log_unlock(sdp);
up_read(&sdp->sd_log_flush_lock);
}
-static uint64_t log_bmap(struct gfs2_sbd *sdp, unsigned int lbn)
+static u64 log_bmap(struct gfs2_sbd *sdp, unsigned int lbn)
{
- int new = 0;
- uint64_t dbn;
+ struct inode *inode = sdp->sd_jdesc->jd_inode;
int error;
- int bdy;
+ struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 };
- error = gfs2_block_map(sdp->sd_jdesc->jd_inode, lbn, &new, &dbn, &bdy);
- if (!(!error && dbn)) {
- printk(KERN_INFO "error=%d, dbn=%llu lbn=%u", error, (unsigned long long)dbn, lbn);
- }
- gfs2_assert_withdraw(sdp, !error && dbn);
+ bh_map.b_size = 1 << inode->i_blkbits;
+ error = gfs2_block_map(inode, lbn, 0, &bh_map);
+ if (error || !bh_map.b_blocknr)
+ printk(KERN_INFO "error=%d, dbn=%llu lbn=%u", error,
+ (unsigned long long)bh_map.b_blocknr, lbn);
+ gfs2_assert_withdraw(sdp, !error && bh_map.b_blocknr);
- return dbn;
+ return bh_map.b_blocknr;
}
/**
* Returns: the distance in blocks
*/
-static inline unsigned int log_distance(struct gfs2_sbd *sdp,
- unsigned int newer,
+static inline unsigned int log_distance(struct gfs2_sbd *sdp, unsigned int newer,
unsigned int older)
{
int dist;
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)
+ 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;
gfs2_log_lock(sdp);
- if (list_empty(&sdp->sd_ail1_list))
+ 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);
+ } else {
+ ai = list_entry(sdp->sd_ail1_list.prev, struct gfs2_ail, ai_list);
tail = ai->ai_first;
}
static inline void log_incr_head(struct gfs2_sbd *sdp)
{
if (sdp->sd_log_flush_head == sdp->sd_log_tail)
- gfs2_assert_withdraw(sdp,
- sdp->sd_log_flush_head == sdp->sd_log_head);
+ gfs2_assert_withdraw(sdp, 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;
struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp)
{
- uint64_t blkno = log_bmap(sdp, sdp->sd_log_flush_head);
+ u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
struct gfs2_log_buf *lb;
struct buffer_head *bh;
struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
struct buffer_head *real)
{
- uint64_t blkno = log_bmap(sdp, sdp->sd_log_flush_head);
+ u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
struct gfs2_log_buf *lb;
struct buffer_head *bh;
return bh;
}
-static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail, int pull)
+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);
gfs2_log_lock(sdp);
- sdp->sd_log_blks_free += dist - ((pull) ? 1 : 0);
- /* printk(KERN_INFO "pull tail refunding %u blocks (%u left) pull=%d\n", dist - ((pull) ? 1 : 0), sdp->sd_log_blks_free, pull); */
- gfs2_assert_withdraw(sdp,
- sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks);
+ sdp->sd_log_blks_free += dist;
+ gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks);
gfs2_log_unlock(sdp);
sdp->sd_log_tail = new_tail;
* Returns: the initialized log buffer descriptor
*/
-static void log_write_header(struct gfs2_sbd *sdp, uint32_t flags, int pull)
+static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
{
- uint64_t blkno = log_bmap(sdp, sdp->sd_log_flush_head);
+ u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
struct buffer_head *bh;
struct gfs2_log_header *lh;
unsigned int tail;
- uint32_t hash;
-
- /* printk(KERN_INFO "log write header start (flags=%08x, pull=%d)\n", flags, pull); */
+ u32 hash;
bh = sb_getblk(sdp->sd_vfs, blkno);
lock_buffer(bh);
brelse(bh);
if (sdp->sd_log_tail != tail)
- log_pull_tail(sdp, tail, pull);
+ log_pull_tail(sdp, tail);
else
gfs2_assert_withdraw(sdp, !pull);
sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
log_incr_head(sdp);
-
- /* printk(KERN_INFO "log write header out\n"); */
}
static void log_flush_commit(struct gfs2_sbd *sdp)
struct list_head *head = &sdp->sd_log_flush_list;
struct gfs2_log_buf *lb;
struct buffer_head *bh;
-#if 0
- unsigned int d;
-
- d = log_distance(sdp, sdp->sd_log_flush_head, sdp->sd_log_head);
-
- gfs2_assert_withdraw(sdp, d + 1 == sdp->sd_log_blks_reserved);
-#endif
+ int flushcount = 0;
while (!list_empty(head)) {
lb = list_entry(head->next, struct gfs2_log_buf, lb_list);
} else
brelse(bh);
kfree(lb);
+ flushcount++;
}
- log_write_header(sdp, 0, 0);
+ /* If nothing was journaled, the header is unplanned and unwanted. */
+ if (flushcount) {
+ log_write_header(sdp, 0, 0);
+ } else {
+ unsigned int tail;
+ tail = current_tail(sdp);
+
+ gfs2_ail1_empty(sdp, 0);
+ if (sdp->sd_log_tail != tail)
+ log_pull_tail(sdp, tail);
+ }
}
/**
INIT_LIST_HEAD(&ai->ai_ail2_list);
gfs2_assert_withdraw(sdp,
- sdp->sd_log_num_buf == sdp->sd_log_commited_buf);
+ sdp->sd_log_num_buf + sdp->sd_log_num_jdata ==
+ sdp->sd_log_commited_buf +
+ sdp->sd_log_commited_databuf);
gfs2_assert_withdraw(sdp,
sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke);
lops_before_commit(sdp);
if (!list_empty(&sdp->sd_log_flush_list))
log_flush_commit(sdp);
- else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle)
+ else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
+ gfs2_log_lock(sdp);
+ sdp->sd_log_blks_free--; /* Adjust for unreserved buffer */
+ gfs2_log_unlock(sdp);
log_write_header(sdp, 0, PULL);
+ }
lops_after_commit(sdp, ai);
- sdp->sd_log_head = sdp->sd_log_flush_head;
-
- /* printk(KERN_INFO "sd_log_num_hdrs %u\n", sdp->sd_log_num_hdrs); */
- sdp->sd_log_blks_free -= sdp->sd_log_num_hdrs;
-
- sdp->sd_log_blks_reserved =
- sdp->sd_log_commited_buf =
- sdp->sd_log_num_hdrs =
- sdp->sd_log_commited_revoke = 0;
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;
+
if (!list_empty(&ai->ai_ail1_list)) {
list_add(&ai->ai_list, &sdp->sd_ail1_list);
ai = NULL;
static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
- unsigned int reserved = 1;
+ unsigned int reserved;
unsigned int old;
gfs2_log_lock(sdp);
sdp->sd_log_commited_buf += tr->tr_num_buf_new - tr->tr_num_buf_rm;
- gfs2_assert_withdraw(sdp, ((int)sdp->sd_log_commited_buf) >= 0);
+ 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;
gfs2_assert_withdraw(sdp, ((int)sdp->sd_log_commited_revoke) >= 0);
-
- if (sdp->sd_log_commited_buf)
- reserved += sdp->sd_log_commited_buf;
- if (sdp->sd_log_commited_revoke)
- reserved += gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke,
- sizeof(uint64_t));
-
+ reserved = calc_reserved(sdp);
old = sdp->sd_log_blks_free;
sdp->sd_log_blks_free += tr->tr_reserved -
(reserved - sdp->sd_log_blks_reserved);
gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free >= old);
- gfs2_assert_withdraw(sdp,
- sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks +
- sdp->sd_log_num_hdrs);
+ gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free <=
+ sdp->sd_jdesc->jd_blocks);
sdp->sd_log_blks_reserved = reserved;
up_read(&sdp->sd_log_flush_lock);
gfs2_log_lock(sdp);
- if (sdp->sd_log_num_buf > gfs2_tune_get(sdp, gt_incore_log_blocks)) {
- gfs2_log_unlock(sdp);
- gfs2_log_flush(sdp, NULL);
- } else
- gfs2_log_unlock(sdp);
+ if (sdp->sd_log_num_buf > gfs2_tune_get(sdp, gt_incore_log_blocks))
+ wake_up_process(sdp->sd_logd_process);
+ gfs2_log_unlock(sdp);
}
/**
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, !sdp->sd_log_num_hdrs);
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, 0);
+ log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT,
+ (sdp->sd_log_tail == current_tail(sdp)) ? 0 : PULL);
- /* printk(KERN_INFO "sd_log_blks_free %u, sd_jdesc->jd_blocks %u\n", sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks); */
gfs2_assert_warn(sdp, 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));
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, DIO_ALL);
+ if (gfs2_ail1_empty(sdp, DIO_ALL))
+ break;
+ msleep(10);
+ }
+}
+