From: Steven Whitehouse <swhiteho@redhat.com>
Subject: [RHEL 5.1] [GFS2] Solve journaling/{release|invalidate}page issues (bz #253008)
Date: Mon, 24 Sep 2007 16:27:19 +0100
Bugzilla: 253008
Message-Id: <1190647639.1068.151.camel@quoit>
Changelog: [GFS2] Solve journaling/{release|invalidate}page issues
Hi,
This patch for bz #253008 is a combination of several upstream patches which fix
some issues relating to journaling and invalidate/releasepage. The main change is
the merging of the gfs2_bufdata and gfs2_revoke structures. Since at every point
where we need a gfs2_revoke, there is also a gfs2_bufdata, then we can avoid
freeing one and allocating the other in this way. This then allows a number of
simplifications to the journal code, including one which resolves a bug where we
need to revoke journalled data buffers in a context where memory allocation is
not allowed.
In addition we now have a different method of keeping track of buffers which are being
written to the journal. The old method was to allocate a small chunk of memory for
each buffer and put them in a list. The new method just keeps a count of the outstanding
buffers and waits for the count to hit zero during the log flush process. This also
removes a busy wait in the journal commit code.
The combination of the above and the rewrite of the code dealing with ordered buffers
means that the old databuf_lo_before_commit() function is now much simpler in form. It
has previously been the location of a number of bugs as a result of it trying to do
too many things. Now that the ordered write code is separate, the code layout is much
more logical, solving the originally reported oops in this function which was the
original reason for this bugzilla.
Also this fixes a bug (which was carried forward from gfs1) where ->releasepage() was
not being skipped in the case that it was called for a page with no buffers.
Steve.
diff -Npru linux-rhel-base/fs/gfs2/bmap.c linux-2.6.18.noarch/fs/gfs2/bmap.c
--- linux-rhel-base/fs/gfs2/bmap.c 2007-09-24 14:51:17.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/bmap.c 2007-09-24 14:59:02.000000000 +0100
@@ -93,9 +93,10 @@ static int gfs2_unstuffer_page(struct gf
map_bh(bh, inode->i_sb, block);
set_buffer_uptodate(bh);
+ if (!gfs2_is_jdata(ip))
+ mark_buffer_dirty(bh);
if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip))
gfs2_trans_add_bh(ip->i_gl, bh, 0);
- mark_buffer_dirty(bh);
if (release) {
unlock_page(page);
diff -Npru linux-rhel-base/fs/gfs2/glops.c linux-2.6.18.noarch/fs/gfs2/glops.c
--- linux-rhel-base/fs/gfs2/glops.c 2007-09-24 14:51:17.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/glops.c 2007-09-24 14:59:02.000000000 +0100
@@ -41,7 +41,6 @@ static void gfs2_ail_empty_gl(struct gfs
struct list_head *head = &gl->gl_ail_list;
struct gfs2_bufdata *bd;
struct buffer_head *bh;
- u64 blkno;
int error;
blocks = atomic_read(&gl->gl_ail_count);
@@ -57,19 +56,12 @@ static void gfs2_ail_empty_gl(struct gfs
bd = list_entry(head->next, struct gfs2_bufdata,
bd_ail_gl_list);
bh = bd->bd_bh;
- blkno = bh->b_blocknr;
+ gfs2_remove_from_ail(NULL, bd);
+ bd->bd_bh = NULL;
+ bh->b_private = NULL;
+ bd->bd_blkno = bh->b_blocknr;
gfs2_assert_withdraw(sdp, !buffer_busy(bh));
-
- bd->bd_ail = NULL;
- list_del(&bd->bd_ail_st_list);
- list_del(&bd->bd_ail_gl_list);
- atomic_dec(&gl->gl_ail_count);
- brelse(bh);
- gfs2_log_unlock(sdp);
-
- gfs2_trans_add_revoke(sdp, blkno);
-
- gfs2_log_lock(sdp);
+ gfs2_trans_add_revoke(sdp, bd);
}
gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
gfs2_log_unlock(sdp);
diff -Npru linux-rhel-base/fs/gfs2/incore.h linux-2.6.18.noarch/fs/gfs2/incore.h
--- linux-rhel-base/fs/gfs2/incore.h 2007-09-24 14:51:17.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/incore.h 2007-09-24 14:59:02.000000000 +0100
@@ -114,7 +114,13 @@ struct gfs2_bufdata {
struct buffer_head *bd_bh;
struct gfs2_glock *bd_gl;
- struct list_head bd_list_tr;
+ union {
+ struct list_head list_tr;
+ u64 blkno;
+ } u;
+#define bd_list_tr u.list_tr
+#define bd_blkno u.blkno
+
struct gfs2_log_element bd_le;
struct gfs2_ail *bd_ail;
@@ -298,11 +304,6 @@ struct gfs2_file {
struct gfs2_holder f_fl_gh;
};
-struct gfs2_revoke {
- struct gfs2_log_element rv_le;
- u64 rv_blkno;
-};
-
struct gfs2_revoke_replay {
struct list_head rr_list;
u64 rr_blkno;
@@ -340,12 +341,6 @@ struct gfs2_quota_data {
unsigned long qd_last_touched;
};
-struct gfs2_log_buf {
- struct list_head lb_list;
- struct buffer_head *lb_bh;
- struct buffer_head *lb_real;
-};
-
struct gfs2_trans {
unsigned long tr_ip;
@@ -612,13 +607,13 @@ struct gfs2_sbd {
unsigned int sd_log_num_revoke;
unsigned int sd_log_num_rg;
unsigned int sd_log_num_databuf;
- unsigned int sd_log_num_jdata;
struct list_head sd_log_le_gl;
struct list_head sd_log_le_buf;
struct list_head sd_log_le_revoke;
struct list_head sd_log_le_rg;
struct list_head sd_log_le_databuf;
+ struct list_head sd_log_le_ordered;
unsigned int sd_log_blks_free;
struct mutex sd_log_reserve_mutex;
@@ -630,7 +625,8 @@ struct gfs2_sbd {
unsigned long sd_log_flush_time;
struct rw_semaphore sd_log_flush_lock;
- struct list_head sd_log_flush_list;
+ atomic_t sd_log_in_flight;
+ wait_queue_head_t sd_log_flush_wait;
unsigned int sd_log_flush_head;
u64 sd_log_flush_wrapped;
diff -Npru linux-rhel-base/fs/gfs2/log.c linux-2.6.18.noarch/fs/gfs2/log.c
--- linux-rhel-base/fs/gfs2/log.c 2007-09-24 14:51:18.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/log.c 2007-09-24 14:59:02.000000000 +0100
@@ -60,6 +60,26 @@ unsigned int gfs2_struct2blk(struct gfs2
}
/**
+ * 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 log lock _must_ be held when calling this function
+ *
+ */
+
+void gfs2_remove_from_ail(struct address_space *mapping, 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);
+ if (mapping)
+ gfs2_meta_cache_flush(GFS2_I(mapping->host));
+ brelse(bd->bd_bh);
+}
+
+/**
* gfs2_ail1_start_one - Start I/O on a part of the AIL
* @sdp: the filesystem
* @tr: the part of the AIL
@@ -84,11 +104,8 @@ static void gfs2_ail1_start_one(struct g
gfs2_assert(sdp, bd->bd_ail == ai);
if (!buffer_busy(bh)) {
- if (!buffer_uptodate(bh)) {
- gfs2_log_unlock(sdp);
+ if (!buffer_uptodate(bh))
gfs2_io_error_bh(sdp, bh);
- gfs2_log_lock(sdp);
- }
list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
continue;
}
@@ -98,9 +115,16 @@ static void gfs2_ail1_start_one(struct g
list_move(&bd->bd_ail_st_list, &ai->ai_ail1_list);
+ get_bh(bh);
gfs2_log_unlock(sdp);
- wait_on_buffer(bh);
- ll_rw_block(WRITE, 1, &bh);
+ lock_buffer(bh);
+ if (test_clear_buffer_dirty(bh)) {
+ bh->b_end_io = end_buffer_write_sync;
+ submit_bh(WRITE, bh);
+ } else {
+ unlock_buffer(bh);
+ brelse(bh);
+ }
gfs2_log_lock(sdp);
retry = 1;
@@ -219,21 +243,12 @@ static void gfs2_ail2_empty_one(struct g
{
struct list_head *head = &ai->ai_ail2_list;
struct gfs2_bufdata *bd;
- struct gfs2_inode *bh_ip;
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);
- if (bd->bd_bh->b_page->mapping) {
- bh_ip = GFS2_I(bd->bd_bh->b_page->mapping->host);
- gfs2_meta_cache_flush(bh_ip);
- }
- brelse(bd->bd_bh);
+ gfs2_remove_from_ail(bd->bd_bh->b_page->mapping, bd);
}
}
@@ -450,10 +465,10 @@ static unsigned int current_tail(struct
return tail;
}
-static inline void log_incr_head(struct gfs2_sbd *sdp)
+void gfs2_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);
+ 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;
@@ -462,6 +477,23 @@ static inline void log_incr_head(struct
}
/**
+ * 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
*
@@ -471,25 +503,42 @@ static inline void log_incr_head(struct
struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp)
{
u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
- struct gfs2_log_buf *lb;
struct buffer_head *bh;
- lb = kzalloc(sizeof(struct gfs2_log_buf), GFP_NOFS | __GFP_NOFAIL);
- list_add(&lb->lb_list, &sdp->sd_log_flush_list);
-
- bh = lb->lb_bh = sb_getblk(sdp->sd_vfs, blkno);
+ 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);
- unlock_buffer(bh);
-
- log_incr_head(sdp);
+ 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_sbd *sdp = GFS2_SB(real_bh->b_page->mapping->host);
+
+ 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
@@ -501,22 +550,20 @@ struct buffer_head *gfs2_log_fake_buf(st
struct buffer_head *real)
{
u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
- struct gfs2_log_buf *lb;
struct buffer_head *bh;
- lb = kzalloc(sizeof(struct gfs2_log_buf), GFP_NOFS | __GFP_NOFAIL);
- list_add(&lb->lb_list, &sdp->sd_log_flush_list);
- lb->lb_real = real;
-
- bh = lb->lb_bh = alloc_buffer_head(GFP_NOFS | __GFP_NOFAIL);
+ bh = alloc_buffer_head(GFP_NOFS | __GFP_NOFAIL);
atomic_set(&bh->b_count, 1);
- bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate);
+ 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;
- log_incr_head(sdp);
+ gfs2_log_incr_head(sdp);
+ atomic_inc(&sdp->sd_log_in_flight);
return bh;
}
@@ -583,45 +630,75 @@ static void log_write_header(struct gfs2
gfs2_assert_withdraw(sdp, !pull);
sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
- log_incr_head(sdp);
+ gfs2_log_incr_head(sdp);
}
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;
- int flushcount = 0;
+ DEFINE_WAIT(wait);
- while (!list_empty(head)) {
- lb = list_entry(head->next, struct gfs2_log_buf, lb_list);
- list_del(&lb->lb_list);
- bh = lb->lb_bh;
+ 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);
+ }
- wait_on_buffer(bh);
- if (!buffer_uptodate(bh))
- gfs2_io_error_bh(sdp, bh);
- if (lb->lb_real) {
- while (atomic_read(&bh->b_count) != 1) /* Grrrr... */
- schedule();
- free_buffer_head(bh);
- } else
+ 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 (test_clear_buffer_dirty(bh)) {
+ bh->b_end_io = end_buffer_write_sync;
+ submit_bh(WRITE, bh);
+ } else {
+ unlock_buffer(bh);
brelse(bh);
- kfree(lb);
- flushcount++;
+ }
+ gfs2_log_lock(sdp);
}
+ list_splice(&written, &sdp->sd_log_le_ordered);
+ gfs2_log_unlock(sdp);
+}
- /* 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);
+static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
+{
+ struct gfs2_bufdata *bd;
+ struct buffer_head *bh;
- gfs2_ail1_empty(sdp, 0);
- if (sdp->sd_log_tail != tail)
- log_pull_tail(sdp, tail);
+ 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);
}
/**
@@ -651,10 +728,16 @@ void gfs2_log_flush(struct gfs2_sbd *sdp
INIT_LIST_HEAD(&ai->ai_ail1_list);
INIT_LIST_HEAD(&ai->ai_ail2_list);
- gfs2_assert_withdraw(sdp,
- sdp->sd_log_num_buf + sdp->sd_log_num_jdata ==
- sdp->sd_log_commited_buf +
- sdp->sd_log_commited_databuf);
+ 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);
@@ -662,8 +745,11 @@ void gfs2_log_flush(struct gfs2_sbd *sdp
sdp->sd_log_flush_wrapped = 0;
ai->ai_first = sdp->sd_log_flush_head;
+ gfs2_ordered_write(sdp);
lops_before_commit(sdp);
- if (!list_empty(&sdp->sd_log_flush_list))
+ 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);
@@ -755,7 +841,6 @@ void gfs2_log_shutdown(struct gfs2_sbd *
gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved);
gfs2_assert_withdraw(sdp, !sdp->sd_log_num_gl);
gfs2_assert_withdraw(sdp, !sdp->sd_log_num_buf);
- gfs2_assert_withdraw(sdp, !sdp->sd_log_num_jdata);
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);
diff -Npru linux-rhel-base/fs/gfs2/log.h linux-2.6.18.noarch/fs/gfs2/log.h
--- linux-rhel-base/fs/gfs2/log.h 2007-09-24 14:51:18.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/log.h 2007-09-24 14:59:02.000000000 +0100
@@ -52,12 +52,14 @@ int gfs2_ail1_empty(struct gfs2_sbd *sdp
int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks, int wait);
void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks);
+void gfs2_log_incr_head(struct gfs2_sbd *sdp);
struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp);
struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
struct buffer_head *real);
void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl);
void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
+void gfs2_remove_from_ail(struct address_space *mapping, struct gfs2_bufdata *bd);
void gfs2_log_shutdown(struct gfs2_sbd *sdp);
void gfs2_meta_syncfs(struct gfs2_sbd *sdp);
diff -Npru linux-rhel-base/fs/gfs2/lops.c linux-2.6.18.noarch/fs/gfs2/lops.c
--- linux-rhel-base/fs/gfs2/lops.c 2007-09-24 14:51:17.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/lops.c 2007-09-24 14:59:45.000000000 +0100
@@ -27,7 +27,104 @@
#include "trans.h"
#include "util.h"
-static void glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+/**
+ * gfs2_pin - Pin a buffer in memory
+ * @sdp: The superblock
+ * @bh: The buffer to be pinned
+ *
+ * The log lock must be held when calling this function
+ */
+static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
+{
+ struct gfs2_bufdata *bd;
+
+ gfs2_assert_withdraw(sdp, test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags));
+
+ clear_buffer_dirty(bh);
+ if (test_set_buffer_pinned(bh))
+ gfs2_assert_withdraw(sdp, 0);
+ if (!buffer_uptodate(bh))
+ gfs2_io_error_bh(sdp, bh);
+ bd = bh->b_private;
+ /* If this buffer is in the AIL and it has already been written
+ * to in-place disk block, remove it from the AIL.
+ */
+ if (bd->bd_ail)
+ list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list);
+ get_bh(bh);
+}
+
+/**
+ * gfs2_unpin - Unpin a buffer
+ * @sdp: the filesystem the buffer belongs to
+ * @bh: The buffer to unpin
+ * @ai:
+ *
+ */
+
+static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
+ struct gfs2_ail *ai)
+{
+ struct gfs2_bufdata *bd = bh->b_private;
+
+ gfs2_assert_withdraw(sdp, buffer_uptodate(bh));
+
+ if (!buffer_pinned(bh))
+ gfs2_assert_withdraw(sdp, 0);
+
+ lock_buffer(bh);
+ mark_buffer_dirty(bh);
+ clear_buffer_pinned(bh);
+
+ gfs2_log_lock(sdp);
+ if (bd->bd_ail) {
+ list_del(&bd->bd_ail_st_list);
+ brelse(bh);
+ } else {
+ struct gfs2_glock *gl = bd->bd_gl;
+ list_add(&bd->bd_ail_gl_list, &gl->gl_ail_list);
+ atomic_inc(&gl->gl_ail_count);
+ }
+ bd->bd_ail = ai;
+ list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list);
+ gfs2_log_unlock(sdp);
+ unlock_buffer(bh);
+}
+
+
+static inline struct gfs2_log_descriptor *bh_log_desc(struct buffer_head *bh)
+{
+ return (struct gfs2_log_descriptor *)bh->b_data;
+}
+
+static inline __be64 *bh_log_ptr(struct buffer_head *bh)
+{
+ struct gfs2_log_descriptor *ld = bh_log_desc(bh);
+ return (__force __be64 *)(ld + 1);
+}
+
+static inline __be64 *bh_ptr_end(struct buffer_head *bh)
+{
+ return (__force __be64 *)(bh->b_data + bh->b_size);
+}
+
+
+static struct buffer_head *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type)
+{
+ struct buffer_head *bh = gfs2_log_get_buf(sdp);
+ struct gfs2_log_descriptor *ld = bh_log_desc(bh);
+ ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+ ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD);
+ ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD);
+ ld->ld_type = cpu_to_be32(ld_type);
+ ld->ld_length = 0;
+ ld->ld_data1 = 0;
+ ld->ld_data2 = 0;
+ memset(ld->ld_reserved, 0, sizeof(ld->ld_reserved));
+ return bh;
+}
+
+static void __glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
{
struct gfs2_glock *gl;
struct gfs2_trans *tr = current->journal_info;
@@ -38,15 +135,19 @@ static void glock_lo_add(struct gfs2_sbd
if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(gl)))
return;
- gfs2_log_lock(sdp);
- if (!list_empty(&le->le_list)){
- gfs2_log_unlock(sdp);
+ if (!list_empty(&le->le_list))
return;
- }
+
gfs2_glock_hold(gl);
set_bit(GLF_DIRTY, &gl->gl_flags);
sdp->sd_log_num_gl++;
list_add(&le->le_list, &sdp->sd_log_le_gl);
+}
+
+static void glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+{
+ gfs2_log_lock(sdp);
+ __glock_lo_add(sdp, le);
gfs2_log_unlock(sdp);
}
@@ -71,30 +172,25 @@ static void buf_lo_add(struct gfs2_sbd *
struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le);
struct gfs2_trans *tr;
+ lock_buffer(bd->bd_bh);
gfs2_log_lock(sdp);
- if (!list_empty(&bd->bd_list_tr)) {
- gfs2_log_unlock(sdp);
- return;
- }
+ if (!list_empty(&bd->bd_list_tr))
+ goto out;
tr = current->journal_info;
tr->tr_touched = 1;
tr->tr_num_buf++;
list_add(&bd->bd_list_tr, &tr->tr_list_buf);
- gfs2_log_unlock(sdp);
-
if (!list_empty(&le->le_list))
- return;
-
- gfs2_trans_add_gl(bd->bd_gl);
-
+ goto out;
+ __glock_lo_add(sdp, &bd->bd_gl->gl_le);
gfs2_meta_check(sdp, bd->bd_bh);
gfs2_pin(sdp, bd->bd_bh);
- gfs2_log_lock(sdp);
sdp->sd_log_num_buf++;
list_add(&le->le_list, &sdp->sd_log_le_buf);
- gfs2_log_unlock(sdp);
-
tr->tr_num_buf_new++;
+out:
+ gfs2_log_unlock(sdp);
+ unlock_buffer(bd->bd_bh);
}
static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
@@ -118,7 +214,6 @@ static void buf_lo_before_commit(struct
struct gfs2_log_descriptor *ld;
struct gfs2_bufdata *bd1 = NULL, *bd2;
unsigned int total;
- unsigned int offset = BUF_OFFSET;
unsigned int limit;
unsigned int num;
unsigned n;
@@ -135,18 +230,12 @@ static void buf_lo_before_commit(struct
if (total > limit)
num = limit;
gfs2_log_unlock(sdp);
- bh = gfs2_log_get_buf(sdp);
+ bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_METADATA);
gfs2_log_lock(sdp);
- ld = (struct gfs2_log_descriptor *)bh->b_data;
- ptr = (__be64 *)(bh->b_data + offset);
- ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
- ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD);
- ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD);
- ld->ld_type = cpu_to_be32(GFS2_LOG_DESC_METADATA);
+ ld = bh_log_desc(bh);
+ ptr = bh_log_ptr(bh);
ld->ld_length = cpu_to_be32(num + 1);
ld->ld_data1 = cpu_to_be32(num);
- ld->ld_data2 = cpu_to_be32(0);
- memset(ld->ld_reserved, 0, sizeof(ld->ld_reserved));
n = 0;
list_for_each_entry_continue(bd1, &sdp->sd_log_le_buf,
@@ -157,17 +246,17 @@ static void buf_lo_before_commit(struct
}
gfs2_log_unlock(sdp);
- set_buffer_dirty(bh);
- ll_rw_block(WRITE, 1, &bh);
+ submit_bh(WRITE, bh);
gfs2_log_lock(sdp);
n = 0;
list_for_each_entry_continue(bd2, &sdp->sd_log_le_buf,
bd_le.le_list) {
+ get_bh(bd2->bd_bh);
gfs2_log_unlock(sdp);
+ lock_buffer(bd2->bd_bh);
bh = gfs2_log_fake_buf(sdp, bd2->bd_bh);
- set_buffer_dirty(bh);
- ll_rw_block(WRITE, 1, &bh);
+ submit_bh(WRITE, bh);
gfs2_log_lock(sdp);
if (++n >= num)
break;
@@ -280,11 +369,8 @@ static void revoke_lo_add(struct gfs2_sb
tr = current->journal_info;
tr->tr_touched = 1;
tr->tr_num_revoke++;
-
- gfs2_log_lock(sdp);
sdp->sd_log_num_revoke++;
list_add(&le->le_list, &sdp->sd_log_le_revoke);
- gfs2_log_unlock(sdp);
}
static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
@@ -294,32 +380,25 @@ static void revoke_lo_before_commit(stru
struct buffer_head *bh;
unsigned int offset;
struct list_head *head = &sdp->sd_log_le_revoke;
- struct gfs2_revoke *rv;
+ struct gfs2_bufdata *bd;
if (!sdp->sd_log_num_revoke)
return;
- bh = gfs2_log_get_buf(sdp);
- ld = (struct gfs2_log_descriptor *)bh->b_data;
- ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
- ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD);
- ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD);
- ld->ld_type = cpu_to_be32(GFS2_LOG_DESC_REVOKE);
+ bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE);
+ ld = bh_log_desc(bh);
ld->ld_length = cpu_to_be32(gfs2_struct2blk(sdp, sdp->sd_log_num_revoke,
sizeof(u64)));
ld->ld_data1 = cpu_to_be32(sdp->sd_log_num_revoke);
- ld->ld_data2 = cpu_to_be32(0);
- memset(ld->ld_reserved, 0, sizeof(ld->ld_reserved));
offset = sizeof(struct gfs2_log_descriptor);
while (!list_empty(head)) {
- rv = list_entry(head->next, struct gfs2_revoke, rv_le.le_list);
- list_del_init(&rv->rv_le.le_list);
+ bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list);
+ list_del_init(&bd->bd_le.le_list);
sdp->sd_log_num_revoke--;
if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) {
- set_buffer_dirty(bh);
- ll_rw_block(WRITE, 1, &bh);
+ submit_bh(WRITE, bh);
bh = gfs2_log_get_buf(sdp);
mh = (struct gfs2_meta_header *)bh->b_data;
@@ -329,15 +408,14 @@ static void revoke_lo_before_commit(stru
offset = sizeof(struct gfs2_meta_header);
}
- *(__be64 *)(bh->b_data + offset) = cpu_to_be64(rv->rv_blkno);
- kfree(rv);
+ *(__be64 *)(bh->b_data + offset) = cpu_to_be64(bd->bd_blkno);
+ kmem_cache_free(gfs2_bufdata_cachep, bd);
offset += sizeof(u64);
}
gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
- set_buffer_dirty(bh);
- ll_rw_block(WRITE, 1, &bh);
+ submit_bh(WRITE, bh);
}
static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
@@ -476,223 +554,136 @@ static void databuf_lo_add(struct gfs2_s
struct address_space *mapping = bd->bd_bh->b_page->mapping;
struct gfs2_inode *ip = GFS2_I(mapping->host);
+ lock_buffer(bd->bd_bh);
gfs2_log_lock(sdp);
- if (!list_empty(&bd->bd_list_tr)) {
- gfs2_log_unlock(sdp);
- return;
- }
+ if (!list_empty(&bd->bd_list_tr))
+ goto out;
tr->tr_touched = 1;
if (gfs2_is_jdata(ip)) {
tr->tr_num_buf++;
list_add(&bd->bd_list_tr, &tr->tr_list_buf);
}
- gfs2_log_unlock(sdp);
if (!list_empty(&le->le_list))
- return;
+ goto out;
- gfs2_trans_add_gl(bd->bd_gl);
+ __glock_lo_add(sdp, &bd->bd_gl->gl_le);
if (gfs2_is_jdata(ip)) {
- sdp->sd_log_num_jdata++;
gfs2_pin(sdp, bd->bd_bh);
tr->tr_num_databuf_new++;
+ sdp->sd_log_num_databuf++;
+ list_add(&le->le_list, &sdp->sd_log_le_databuf);
+ } else {
+ list_add(&le->le_list, &sdp->sd_log_le_ordered);
}
- gfs2_log_lock(sdp);
- sdp->sd_log_num_databuf++;
- list_add(&le->le_list, &sdp->sd_log_le_databuf);
+out:
gfs2_log_unlock(sdp);
+ unlock_buffer(bd->bd_bh);
}
-static int gfs2_check_magic(struct buffer_head *bh)
+static void gfs2_check_magic(struct buffer_head *bh)
{
- struct page *page = bh->b_page;
void *kaddr;
__be32 *ptr;
- int rv = 0;
- kaddr = kmap_atomic(page, KM_USER0);
+ clear_buffer_escaped(bh);
+ kaddr = kmap_atomic(bh->b_page, KM_USER0);
ptr = kaddr + bh_offset(bh);
if (*ptr == cpu_to_be32(GFS2_MAGIC))
- rv = 1;
+ set_buffer_escaped(bh);
kunmap_atomic(kaddr, KM_USER0);
+}
+
+static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh,
+ struct list_head *list, struct list_head *done,
+ unsigned int n)
+{
+ struct buffer_head *bh1;
+ struct gfs2_log_descriptor *ld;
+ struct gfs2_bufdata *bd;
+ __be64 *ptr;
- return rv;
+ if (!bh)
+ return;
+
+ ld = bh_log_desc(bh);
+ ld->ld_length = cpu_to_be32(n + 1);
+ ld->ld_data1 = cpu_to_be32(n);
+
+ ptr = bh_log_ptr(bh);
+
+ get_bh(bh);
+ submit_bh(WRITE, bh);
+ gfs2_log_lock(sdp);
+ while(!list_empty(list)) {
+ bd = list_entry(list->next, struct gfs2_bufdata, bd_le.le_list);
+ list_move_tail(&bd->bd_le.le_list, done);
+ get_bh(bd->bd_bh);
+ while (be64_to_cpu(*ptr) != bd->bd_bh->b_blocknr) {
+ gfs2_log_incr_head(sdp);
+ ptr += 2;
+ }
+ gfs2_log_unlock(sdp);
+ lock_buffer(bd->bd_bh);
+ if (buffer_escaped(bd->bd_bh)) {
+ void *kaddr;
+ bh1 = gfs2_log_get_buf(sdp);
+ kaddr = kmap_atomic(bd->bd_bh->b_page, KM_USER0);
+ memcpy(bh1->b_data, kaddr + bh_offset(bd->bd_bh),
+ bh1->b_size);
+ kunmap_atomic(kaddr, KM_USER0);
+ *(__be32 *)bh1->b_data = 0;
+ clear_buffer_escaped(bd->bd_bh);
+ unlock_buffer(bd->bd_bh);
+ brelse(bd->bd_bh);
+ } else {
+ bh1 = gfs2_log_fake_buf(sdp, bd->bd_bh);
+ }
+ submit_bh(WRITE, bh1);
+ gfs2_log_lock(sdp);
+ ptr += 2;
+ }
+ gfs2_log_unlock(sdp);
+ brelse(bh);
}
/**
* databuf_lo_before_commit - Scan the data buffers, writing as we go
*
- * Here we scan through the lists of buffers and make the assumption
- * that any buffer thats been pinned is being journaled, and that
- * any unpinned buffer is an ordered write data buffer and therefore
- * will be written back rather than journaled.
*/
+
static void databuf_lo_before_commit(struct gfs2_sbd *sdp)
{
- LIST_HEAD(started);
- struct gfs2_bufdata *bd1 = NULL, *bd2, *bdt;
- struct buffer_head *bh = NULL,*bh1 = NULL;
- struct gfs2_log_descriptor *ld;
- unsigned int limit;
- unsigned int total_dbuf;
- unsigned int total_jdata;
- unsigned int num, n;
- __be64 *ptr = NULL;
-
- limit = databuf_limit(sdp);
-
- /*
- * Start writing ordered buffers, write journaled buffers
- * into the log along with a header
- */
+ struct gfs2_bufdata *bd = NULL;
+ struct buffer_head *bh = NULL;
+ unsigned int n = 0;
+ __be64 *ptr = NULL, *end = NULL;
+ LIST_HEAD(processed);
+ LIST_HEAD(in_progress);
+
gfs2_log_lock(sdp);
- total_dbuf = sdp->sd_log_num_databuf;
- total_jdata = sdp->sd_log_num_jdata;
- bd2 = bd1 = list_prepare_entry(bd1, &sdp->sd_log_le_databuf,
- bd_le.le_list);
- while(total_dbuf) {
- num = total_jdata;
- if (num > limit)
- num = limit;
- n = 0;
- list_for_each_entry_safe_continue(bd1, bdt,
- &sdp->sd_log_le_databuf,
- bd_le.le_list) {
- /* store off the buffer head in a local ptr since
- * gfs2_bufdata might change when we drop the log lock
- */
- bh1 = bd1->bd_bh;
-
- /* An ordered write buffer */
- if (bh1 && !buffer_pinned(bh1)) {
- list_move(&bd1->bd_le.le_list, &started);
- if (bd1 == bd2) {
- bd2 = NULL;
- bd2 = list_prepare_entry(bd2,
- &sdp->sd_log_le_databuf,
- bd_le.le_list);
- }
- total_dbuf--;
- if (bh1) {
- if (buffer_dirty(bh1)) {
- get_bh(bh1);
-
- gfs2_log_unlock(sdp);
-
- ll_rw_block(SWRITE, 1, &bh1);
- brelse(bh1);
-
- gfs2_log_lock(sdp);
- }
- continue;
- }
- continue;
- } else if (bh1) { /* A journaled buffer */
- int magic;
- gfs2_log_unlock(sdp);
- if (!bh) {
- bh = gfs2_log_get_buf(sdp);
- ld = (struct gfs2_log_descriptor *)
- bh->b_data;
- ptr = (__be64 *)(bh->b_data +
- DATABUF_OFFSET);
- ld->ld_header.mh_magic =
- cpu_to_be32(GFS2_MAGIC);
- ld->ld_header.mh_type =
- cpu_to_be32(GFS2_METATYPE_LD);
- ld->ld_header.mh_format =
- cpu_to_be32(GFS2_FORMAT_LD);
- ld->ld_type =
- cpu_to_be32(GFS2_LOG_DESC_JDATA);
- ld->ld_length = cpu_to_be32(num + 1);
- ld->ld_data1 = cpu_to_be32(num);
- ld->ld_data2 = cpu_to_be32(0);
- memset(ld->ld_reserved, 0, sizeof(ld->ld_reserved));
- }
- magic = gfs2_check_magic(bh1);
- *ptr++ = cpu_to_be64(bh1->b_blocknr);
- *ptr++ = cpu_to_be64((__u64)magic);
- clear_buffer_escaped(bh1);
- if (unlikely(magic != 0))
- set_buffer_escaped(bh1);
- gfs2_log_lock(sdp);
- if (++n >= num)
- break;
- } else if (!bh1) {
- total_dbuf--;
- sdp->sd_log_num_databuf--;
- list_del_init(&bd1->bd_le.le_list);
- if (bd1 == bd2) {
- bd2 = NULL;
- bd2 = list_prepare_entry(bd2,
- &sdp->sd_log_le_databuf,
- bd_le.le_list);
- }
- kmem_cache_free(gfs2_bufdata_cachep, bd1);
- }
- }
- gfs2_log_unlock(sdp);
- if (bh) {
- set_buffer_dirty(bh);
- ll_rw_block(WRITE, 1, &bh);
- bh = NULL;
- ptr = NULL;
- }
- n = 0;
- gfs2_log_lock(sdp);
- list_for_each_entry_continue(bd2, &sdp->sd_log_le_databuf,
- bd_le.le_list) {
- if (!bd2->bd_bh)
- continue;
- /* copy buffer if it needs escaping */
+ while (!list_empty(&sdp->sd_log_le_databuf)) {
+ if (ptr == end) {
gfs2_log_unlock(sdp);
- if (unlikely(buffer_escaped(bd2->bd_bh))) {
- void *kaddr;
- struct page *page = bd2->bd_bh->b_page;
- bh = gfs2_log_get_buf(sdp);
- kaddr = kmap_atomic(page, KM_USER0);
- memcpy(bh->b_data,
- kaddr + bh_offset(bd2->bd_bh),
- sdp->sd_sb.sb_bsize);
- kunmap_atomic(kaddr, KM_USER0);
- *(__be32 *)bh->b_data = 0;
- } else {
- bh = gfs2_log_fake_buf(sdp, bd2->bd_bh);
- }
- set_buffer_dirty(bh);
- ll_rw_block(WRITE, 1, &bh);
+ gfs2_write_blocks(sdp, bh, &in_progress, &processed, n);
+ n = 0;
+ bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_JDATA);
+ ptr = bh_log_ptr(bh);
+ end = bh_ptr_end(bh) - 1;
gfs2_log_lock(sdp);
- if (++n >= num)
- break;
+ continue;
}
- bh = NULL;
- BUG_ON(total_dbuf < num);
- total_dbuf -= num;
- total_jdata -= num;
+ bd = list_entry(sdp->sd_log_le_databuf.next, struct gfs2_bufdata, bd_le.le_list);
+ list_move_tail(&bd->bd_le.le_list, &in_progress);
+ gfs2_check_magic(bd->bd_bh);
+ *ptr++ = cpu_to_be64(bd->bd_bh->b_blocknr);
+ *ptr++ = cpu_to_be64(buffer_escaped(bh) ? 1 : 0);
+ n++;
}
gfs2_log_unlock(sdp);
-
- /* Wait on all ordered buffers */
- while (!list_empty(&started)) {
- gfs2_log_lock(sdp);
- bd1 = list_entry(started.next, struct gfs2_bufdata,
- bd_le.le_list);
- list_del_init(&bd1->bd_le.le_list);
- sdp->sd_log_num_databuf--;
- bh = bd1->bd_bh;
- if (bh) {
- bh->b_private = NULL;
- get_bh(bh);
- gfs2_log_unlock(sdp);
- wait_on_buffer(bh);
- brelse(bh);
- } else
- gfs2_log_unlock(sdp);
-
- kmem_cache_free(gfs2_bufdata_cachep, bd1);
- }
-
- /* We've removed all the ordered write bufs here, so only jdata left */
- gfs2_assert_warn(sdp, sdp->sd_log_num_databuf == sdp->sd_log_num_jdata);
+ gfs2_write_blocks(sdp, bh, &in_progress, &processed, n);
+ gfs2_log_lock(sdp);
+ list_splice(&processed, &sdp->sd_log_le_databuf);
+ gfs2_log_unlock(sdp);
}
static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
@@ -776,11 +767,9 @@ static void databuf_lo_after_commit(stru
bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list);
list_del_init(&bd->bd_le.le_list);
sdp->sd_log_num_databuf--;
- sdp->sd_log_num_jdata--;
gfs2_unpin(sdp, bd->bd_bh, ai);
}
gfs2_assert_warn(sdp, !sdp->sd_log_num_databuf);
- gfs2_assert_warn(sdp, !sdp->sd_log_num_jdata);
}
@@ -828,10 +817,10 @@ const struct gfs2_log_operations gfs2_da
const struct gfs2_log_operations *gfs2_log_ops[] = {
&gfs2_glock_lops,
+ &gfs2_databuf_lops,
&gfs2_buf_lops,
- &gfs2_revoke_lops,
&gfs2_rg_lops,
- &gfs2_databuf_lops,
+ &gfs2_revoke_lops,
NULL,
};
diff -Npru linux-rhel-base/fs/gfs2/meta_io.c linux-2.6.18.noarch/fs/gfs2/meta_io.c
--- linux-rhel-base/fs/gfs2/meta_io.c 2007-09-24 14:51:16.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/meta_io.c 2007-09-24 14:59:02.000000000 +0100
@@ -297,74 +297,35 @@ void gfs2_attach_bufdata(struct gfs2_glo
unlock_page(bh->b_page);
}
-/**
- * gfs2_pin - Pin a buffer in memory
- * @sdp: the filesystem the buffer belongs to
- * @bh: The buffer to be pinned
- *
- */
-
-void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
+void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int meta)
{
+ struct gfs2_sbd *sdp = GFS2_SB(bh->b_page->mapping->host);
struct gfs2_bufdata *bd = bh->b_private;
-
- gfs2_assert_withdraw(sdp, test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags));
-
- if (test_set_buffer_pinned(bh))
- gfs2_assert_withdraw(sdp, 0);
-
- wait_on_buffer(bh);
-
- /* If this buffer is in the AIL and it has already been written
- to in-place disk block, remove it from the AIL. */
-
- gfs2_log_lock(sdp);
- if (bd->bd_ail && !buffer_in_io(bh))
- list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list);
- gfs2_log_unlock(sdp);
-
- clear_buffer_dirty(bh);
- wait_on_buffer(bh);
-
- if (!buffer_uptodate(bh))
- gfs2_io_error_bh(sdp, bh);
-
- get_bh(bh);
-}
-
-/**
- * gfs2_unpin - Unpin a buffer
- * @sdp: the filesystem the buffer belongs to
- * @bh: The buffer to unpin
- * @ai:
- *
- */
-
-void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
- struct gfs2_ail *ai)
-{
- struct gfs2_bufdata *bd = bh->b_private;
-
- gfs2_assert_withdraw(sdp, buffer_uptodate(bh));
-
- if (!buffer_pinned(bh))
- gfs2_assert_withdraw(sdp, 0);
-
- mark_buffer_dirty(bh);
- clear_buffer_pinned(bh);
-
- gfs2_log_lock(sdp);
- if (bd->bd_ail) {
- list_del(&bd->bd_ail_st_list);
+ if (test_clear_buffer_pinned(bh)) {
+ list_del_init(&bd->bd_le.le_list);
+ if (meta) {
+ gfs2_assert_warn(sdp, sdp->sd_log_num_buf);
+ sdp->sd_log_num_buf--;
+ tr->tr_num_buf_rm++;
+ } else {
+ gfs2_assert_warn(sdp, sdp->sd_log_num_databuf);
+ sdp->sd_log_num_databuf--;
+ tr->tr_num_databuf_rm++;
+ }
+ tr->tr_touched = 1;
brelse(bh);
- } else {
- struct gfs2_glock *gl = bd->bd_gl;
- list_add(&bd->bd_ail_gl_list, &gl->gl_ail_list);
- atomic_inc(&gl->gl_ail_count);
}
- bd->bd_ail = ai;
- list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list);
- gfs2_log_unlock(sdp);
+ if (bd) {
+ if (bd->bd_ail) {
+ gfs2_remove_from_ail(NULL, bd);
+ bh->b_private = NULL;
+ bd->bd_bh = NULL;
+ bd->bd_blkno = bh->b_blocknr;
+ gfs2_trans_add_revoke(sdp, bd);
+ }
+ }
+ clear_buffer_dirty(bh);
+ clear_buffer_uptodate(bh);
}
/**
@@ -383,44 +344,11 @@ void gfs2_meta_wipe(struct gfs2_inode *i
while (blen) {
bh = getbuf(ip->i_gl, bstart, NO_CREATE);
if (bh) {
- struct gfs2_bufdata *bd = bh->b_private;
-
- if (test_clear_buffer_pinned(bh)) {
- struct gfs2_trans *tr = current->journal_info;
- struct gfs2_inode *bh_ip =
- GFS2_I(bh->b_page->mapping->host);
-
- gfs2_log_lock(sdp);
- list_del_init(&bd->bd_le.le_list);
- gfs2_assert_warn(sdp, sdp->sd_log_num_buf);
- sdp->sd_log_num_buf--;
- gfs2_log_unlock(sdp);
- if (bh_ip->i_inode.i_private != NULL)
- tr->tr_num_databuf_rm++;
- else
- tr->tr_num_buf_rm++;
- brelse(bh);
- }
- if (bd) {
- gfs2_log_lock(sdp);
- if (bd->bd_ail) {
- u64 blkno = bh->b_blocknr;
- 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(bh);
- gfs2_log_unlock(sdp);
- gfs2_trans_add_revoke(sdp, blkno);
- } else
- gfs2_log_unlock(sdp);
- }
-
lock_buffer(bh);
- clear_buffer_dirty(bh);
- clear_buffer_uptodate(bh);
+ gfs2_log_lock(sdp);
+ gfs2_remove_from_journal(bh, current->journal_info, 1);
+ gfs2_log_unlock(sdp);
unlock_buffer(bh);
-
brelse(bh);
}
diff -Npru linux-rhel-base/fs/gfs2/meta_io.h linux-2.6.18.noarch/fs/gfs2/meta_io.h
--- linux-rhel-base/fs/gfs2/meta_io.h 2007-09-24 14:51:10.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/meta_io.h 2007-09-24 14:59:02.000000000 +0100
@@ -50,9 +50,9 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp,
void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
int meta);
-void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
-void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
- struct gfs2_ail *ai);
+
+void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr,
+ int meta);
void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen);
diff -Npru linux-rhel-base/fs/gfs2/ops_address.c linux-2.6.18.noarch/fs/gfs2/ops_address.c
--- linux-rhel-base/fs/gfs2/ops_address.c 2007-09-24 14:51:18.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/ops_address.c 2007-09-24 15:00:41.000000000 +0100
@@ -429,7 +429,8 @@ static int gfs2_prepare_write(struct fil
if (ind_blocks || data_blocks)
rblocks += RES_STATFS + RES_QUOTA;
- error = gfs2_trans_begin(sdp, rblocks, 0);
+ error = gfs2_trans_begin(sdp, rblocks,
+ PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
if (error)
goto out_trans_fail;
@@ -630,13 +631,50 @@ static sector_t gfs2_bmap(struct address
return dblock;
}
+static void gfs2_discard(struct gfs2_sbd *sdp, struct buffer_head *bh)
+{
+ struct gfs2_bufdata *bd;
+
+ lock_buffer(bh);
+ gfs2_log_lock(sdp);
+ clear_buffer_dirty(bh);
+ bd = bh->b_private;
+ if (bd) {
+ if (!list_empty(&bd->bd_le.le_list) && !buffer_pinned(bh))
+ list_del_init(&bd->bd_le.le_list);
+ else
+ gfs2_remove_from_journal(bh, current->journal_info, 0);
+ }
+ bh->b_bdev = NULL;
+ clear_buffer_mapped(bh);
+ clear_buffer_req(bh);
+ clear_buffer_new(bh);
+ gfs2_log_unlock(sdp);
+ unlock_buffer(bh);
+}
+
static void gfs2_invalidatepage(struct page *page, unsigned long offset)
{
+ struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
+ struct buffer_head *bh, *head;
+ unsigned long pos = 0;
+
BUG_ON(!PageLocked(page));
if (offset == 0)
ClearPageChecked(page);
+ if (!page_has_buffers(page))
+ goto out;
- block_invalidatepage(page, offset);
+ bh = head = page_buffers(page);
+ do {
+ if (offset <= pos)
+ gfs2_discard(sdp, bh);
+ pos += bh->b_size;
+ bh = bh->b_this_page;
+ } while (bh != head);
+out:
+ if (offset == 0)
+ try_to_release_page(page, 0);
}
/**
@@ -723,7 +761,7 @@ int gfs2_releasepage(struct page *page,
struct gfs2_bufdata *bd;
if (!page_has_buffers(page))
- goto out;
+ return 0;
gfs2_log_lock(sdp);
head = bh = page_buffers(page);
@@ -746,9 +784,14 @@ int gfs2_releasepage(struct page *page,
if (bd) {
gfs2_assert_warn(sdp, bd->bd_bh == bh);
gfs2_assert_warn(sdp, list_empty(&bd->bd_list_tr));
- bd->bd_bh = NULL;
- if (!list_empty(&bd->bd_le.le_list))
- bd = NULL;
+ if (!list_empty(&bd->bd_le.le_list)) {
+ if (!buffer_pinned(bh))
+ list_del_init(&bd->bd_le.le_list);
+ else
+ bd = NULL;
+ }
+ if (bd)
+ bd->bd_bh = NULL;
bh->b_private = NULL;
}
gfs2_log_unlock(sdp);
@@ -758,7 +801,6 @@ int gfs2_releasepage(struct page *page,
bh = bh->b_this_page;
} while (bh != head);
-out:
return try_to_free_buffers(page);
cannot_release:
gfs2_log_unlock(sdp);
diff -Npru linux-rhel-base/fs/gfs2/ops_fstype.c linux-2.6.18.noarch/fs/gfs2/ops_fstype.c
--- linux-rhel-base/fs/gfs2/ops_fstype.c 2007-09-24 14:51:17.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/ops_fstype.c 2007-09-24 14:59:02.000000000 +0100
@@ -83,13 +83,15 @@ static struct gfs2_sbd *init_sbd(struct
INIT_LIST_HEAD(&sdp->sd_log_le_revoke);
INIT_LIST_HEAD(&sdp->sd_log_le_rg);
INIT_LIST_HEAD(&sdp->sd_log_le_databuf);
+ INIT_LIST_HEAD(&sdp->sd_log_le_ordered);
mutex_init(&sdp->sd_log_reserve_mutex);
INIT_LIST_HEAD(&sdp->sd_ail1_list);
INIT_LIST_HEAD(&sdp->sd_ail2_list);
init_rwsem(&sdp->sd_log_flush_lock);
- INIT_LIST_HEAD(&sdp->sd_log_flush_list);
+ atomic_set(&sdp->sd_log_in_flight, 0);
+ init_waitqueue_head(&sdp->sd_log_flush_wait);
INIT_LIST_HEAD(&sdp->sd_revoke_list);
diff -Npru linux-rhel-base/fs/gfs2/ops_inode.c linux-2.6.18.noarch/fs/gfs2/ops_inode.c
--- linux-rhel-base/fs/gfs2/ops_inode.c 2007-09-24 14:51:17.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/ops_inode.c 2007-09-24 14:59:02.000000000 +0100
@@ -905,12 +905,17 @@ static int gfs2_permission(struct inode
static int setattr_size(struct inode *inode, struct iattr *attr)
{
struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
int error;
if (attr->ia_size != ip->i_di.di_size) {
- error = vmtruncate(inode, attr->ia_size);
+ error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
if (error)
return error;
+ error = vmtruncate(inode, attr->ia_size);
+ gfs2_trans_end(sdp);
+ if (error)
+ return error;
}
error = gfs2_truncatei(ip, attr->ia_size);
diff -Npru linux-rhel-base/fs/gfs2/ops_super.c linux-2.6.18.noarch/fs/gfs2/ops_super.c
--- linux-rhel-base/fs/gfs2/ops_super.c 2007-09-24 14:51:16.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/ops_super.c 2007-09-24 14:59:02.000000000 +0100
@@ -455,12 +455,15 @@ static void gfs2_delete_inode(struct ino
}
error = gfs2_dinode_dealloc(ip);
- /*
- * Must do this before unlock to avoid trying to write back
- * potentially dirty data now that inode no longer exists
- * on disk.
- */
+ if (error)
+ goto out_unlock;
+
+ error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
+ if (error)
+ goto out_unlock;
+ /* Needs to be done before glock release & also in a transaction */
truncate_inode_pages(&inode->i_data, 0);
+ gfs2_trans_end(sdp);
out_unlock:
gfs2_glock_dq(&ip->i_iopen_gh);
diff -Npru linux-rhel-base/fs/gfs2/trans.c linux-2.6.18.noarch/fs/gfs2/trans.c
--- linux-rhel-base/fs/gfs2/trans.c 2007-09-24 14:51:18.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/trans.c 2007-09-24 14:59:02.000000000 +0100
@@ -142,25 +142,25 @@ void gfs2_trans_add_bh(struct gfs2_glock
lops_add(sdp, &bd->bd_le);
}
-void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, u64 blkno)
+void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
{
- struct gfs2_revoke *rv = kmalloc(sizeof(struct gfs2_revoke),
- GFP_NOFS | __GFP_NOFAIL);
- lops_init_le(&rv->rv_le, &gfs2_revoke_lops);
- rv->rv_blkno = blkno;
- lops_add(sdp, &rv->rv_le);
+ BUG_ON(!list_empty(&bd->bd_le.le_list));
+ BUG_ON(!list_empty(&bd->bd_ail_st_list));
+ BUG_ON(!list_empty(&bd->bd_ail_gl_list));
+ lops_init_le(&bd->bd_le, &gfs2_revoke_lops);
+ lops_add(sdp, &bd->bd_le);
}
void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno)
{
- struct gfs2_revoke *rv;
+ struct gfs2_bufdata *bd;
int found = 0;
gfs2_log_lock(sdp);
- list_for_each_entry(rv, &sdp->sd_log_le_revoke, rv_le.le_list) {
- if (rv->rv_blkno == blkno) {
- list_del(&rv->rv_le.le_list);
+ list_for_each_entry(bd, &sdp->sd_log_le_revoke, bd_le.le_list) {
+ if (bd->bd_blkno == blkno) {
+ list_del_init(&bd->bd_le.le_list);
gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke);
sdp->sd_log_num_revoke--;
found = 1;
@@ -172,7 +172,7 @@ void gfs2_trans_add_unrevoke(struct gfs2
if (found) {
struct gfs2_trans *tr = current->journal_info;
- kfree(rv);
+ kmem_cache_free(gfs2_bufdata_cachep, bd);
tr->tr_num_revoke_rm++;
}
}
diff -Npru linux-rhel-base/fs/gfs2/trans.h linux-2.6.18.noarch/fs/gfs2/trans.h
--- linux-rhel-base/fs/gfs2/trans.h 2007-09-24 14:51:18.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/trans.h 2007-09-24 14:59:02.000000000 +0100
@@ -32,7 +32,7 @@ void gfs2_trans_end(struct gfs2_sbd *sdp
void gfs2_trans_add_gl(struct gfs2_glock *gl);
void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta);
-void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, u64 blkno);
+void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno);
void gfs2_trans_add_rg(struct gfs2_rgrpd *rgd);
distrib
>
Scientific%20Linux
>
5x
>
x86_64
>
by-pkgid
>
27922b4260f65d317aabda37e42bbbff
>
files
>
1392
