Merge git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw

* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw: (51 commits)
[DLM] block dlm_recv in recovery transition
[DLM] don't overwrite castparam if it's NULL
[GFS2] Get superblock a different way
[GFS2] Don't try to remove buffers that don't exist
[GFS2] Alternate gfs2_iget to avoid looking up inodes being freed
[GFS2] Data corruption fix
[GFS2] Clean up journaled data writing
[GFS2] GFS2: chmod hung - fix race in thread creation
[DLM] Make dlm_sendd cond_resched more
[GFS2] Move inode deletion out of blocking_cb
[GFS2] flocks from same process trip kernel BUG at fs/gfs2/glock.c:1118!
[GFS2] Clean up gfs2_trans_add_revoke()
[GFS2] Use slab operations for all gfs2_bufdata allocations
[GFS2] Replace revoke structure with bufdata structure
[GFS2] Fix ordering of dirty/journal for ordered buffer unstuffing
[GFS2] Clean up ordered write code
[GFS2] Move pin/unpin into lops.c, clean up locking
[GFS2] Don't mark jdata dirty in gfs2_unstuffer_page()
[GFS2] Introduce gfs2_remove_from_ail
[GFS2] Correct lock ordering in unlink
...

fs/dlm/dlm_internal.h

···
 	uint64_t		ls_recover_seq;
 	struct dlm_recover	*ls_recover_args;
 	struct rw_semaphore	ls_in_recovery;	/* block local requests */
+	struct rw_semaphore	ls_recv_active;	/* block dlm_recv */
 	struct list_head	ls_requestqueue;/* queue remote requests */
 	struct mutex		ls_requestqueue_mutex;
 	char			*ls_recover_buf;

fs/dlm/lock.c

···
 	dlm_put_lkb(lkb);
 }
 
-int dlm_receive_message(struct dlm_header *hd, int nodeid, int recovery)
+static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms)
 {
-	struct dlm_message *ms = (struct dlm_message *) hd;
-	struct dlm_ls *ls;
-	int error = 0;
-
-	if (!recovery)
-		dlm_message_in(ms);
-
-	ls = dlm_find_lockspace_global(hd->h_lockspace);
-	if (!ls) {
-		log_print("drop message %d from %d for unknown lockspace %d",
-			  ms->m_type, nodeid, hd->h_lockspace);
-		return -EINVAL;
-	}
-
-	/* recovery may have just ended leaving a bunch of backed-up requests
-	   in the requestqueue; wait while dlm_recoverd clears them */
-
-	if (!recovery)
-		dlm_wait_requestqueue(ls);
-
-	/* recovery may have just started while there were a bunch of
-	   in-flight requests -- save them in requestqueue to be processed
-	   after recovery.  we can't let dlm_recvd block on the recovery
-	   lock.  if dlm_recoverd is calling this function to clear the
-	   requestqueue, it needs to be interrupted (-EINTR) if another
-	   recovery operation is starting. */
-
-	while (1) {
-		if (dlm_locking_stopped(ls)) {
-			if (recovery) {
-				error = -EINTR;
-				goto out;
-			}
-			error = dlm_add_requestqueue(ls, nodeid, hd);
-			if (error == -EAGAIN)
-				continue;
-			else {
-				error = -EINTR;
-				goto out;
-			}
-		}
-
-		if (dlm_lock_recovery_try(ls))
-			break;
-		schedule();
-	}
-
 	switch (ms->m_type) {
 
 	/* messages sent to a master node */
···
 		log_error(ls, "unknown message type %d", ms->m_type);
 	}
 
-	dlm_unlock_recovery(ls);
- out:
-	dlm_put_lockspace(ls);
 	dlm_astd_wake();
-	return error;
 }
 
+/* If the lockspace is in recovery mode (locking stopped), then normal
+   messages are saved on the requestqueue for processing after recovery is
+   done.  When not in recovery mode, we wait for dlm_recoverd to drain saved
+   messages off the requestqueue before we process new ones. This occurs right
+   after recovery completes when we transition from saving all messages on
+   requestqueue, to processing all the saved messages, to processing new
+   messages as they arrive. */
 
-/*
- * Recovery related
- */
+static void dlm_receive_message(struct dlm_ls *ls, struct dlm_message *ms,
+				int nodeid)
+{
+	if (dlm_locking_stopped(ls)) {
+		dlm_add_requestqueue(ls, nodeid, (struct dlm_header *) ms);
+	} else {
+		dlm_wait_requestqueue(ls);
+		_receive_message(ls, ms);
+	}
+}
+
+/* This is called by dlm_recoverd to process messages that were saved on
+   the requestqueue. */
+
+void dlm_receive_message_saved(struct dlm_ls *ls, struct dlm_message *ms)
+{
+	_receive_message(ls, ms);
+}
+
+/* This is called by the midcomms layer when something is received for
+   the lockspace.  It could be either a MSG (normal message sent as part of
+   standard locking activity) or an RCOM (recovery message sent as part of
+   lockspace recovery). */
+
+void dlm_receive_buffer(struct dlm_header *hd, int nodeid)
+{
+	struct dlm_message *ms = (struct dlm_message *) hd;
+	struct dlm_rcom *rc = (struct dlm_rcom *) hd;
+	struct dlm_ls *ls;
+	int type = 0;
+
+	switch (hd->h_cmd) {
+	case DLM_MSG:
+		dlm_message_in(ms);
+		type = ms->m_type;
+		break;
+	case DLM_RCOM:
+		dlm_rcom_in(rc);
+		type = rc->rc_type;
+		break;
+	default:
+		log_print("invalid h_cmd %d from %u", hd->h_cmd, nodeid);
+		return;
+	}
+
+	if (hd->h_nodeid != nodeid) {
+		log_print("invalid h_nodeid %d from %d lockspace %x",
+			  hd->h_nodeid, nodeid, hd->h_lockspace);
+		return;
+	}
+
+	ls = dlm_find_lockspace_global(hd->h_lockspace);
+	if (!ls) {
+		log_print("invalid h_lockspace %x from %d cmd %d type %d",
+			  hd->h_lockspace, nodeid, hd->h_cmd, type);
+
+		if (hd->h_cmd == DLM_RCOM && type == DLM_RCOM_STATUS)
+			dlm_send_ls_not_ready(nodeid, rc);
+		return;
+	}
+
+	/* this rwsem allows dlm_ls_stop() to wait for all dlm_recv threads to
+	   be inactive (in this ls) before transitioning to recovery mode */
+
+	down_read(&ls->ls_recv_active);
+	if (hd->h_cmd == DLM_MSG)
+		dlm_receive_message(ls, ms, nodeid);
+	else
+		dlm_receive_rcom(ls, rc, nodeid);
+	up_read(&ls->ls_recv_active);
+
+	dlm_put_lockspace(ls);
+}
 
 static void recover_convert_waiter(struct dlm_ls *ls, struct dlm_lkb *lkb)
 {
···
 
 	if (lvb_in && ua->lksb.sb_lvbptr)
 		memcpy(ua->lksb.sb_lvbptr, lvb_in, DLM_USER_LVB_LEN);
-	ua->castparam = ua_tmp->castparam;
+	if (ua_tmp->castparam)
+		ua->castparam = ua_tmp->castparam;
 	ua->user_lksb = ua_tmp->user_lksb;
 
 	error = set_unlock_args(flags, ua, &args);
···
 		goto out;
 
 	ua = (struct dlm_user_args *)lkb->lkb_astparam;
-	ua->castparam = ua_tmp->castparam;
+	if (ua_tmp->castparam)
+		ua->castparam = ua_tmp->castparam;
 	ua->user_lksb = ua_tmp->user_lksb;
 
 	error = set_unlock_args(flags, ua, &args);

fs/dlm/lock.h

···
 void dlm_print_rsb(struct dlm_rsb *r);
 void dlm_dump_rsb(struct dlm_rsb *r);
 void dlm_print_lkb(struct dlm_lkb *lkb);
-int dlm_receive_message(struct dlm_header *hd, int nodeid, int recovery);
+void dlm_receive_message_saved(struct dlm_ls *ls, struct dlm_message *ms);
+void dlm_receive_buffer(struct dlm_header *hd, int nodeid);
 int dlm_modes_compat(int mode1, int mode2);
 int dlm_find_rsb(struct dlm_ls *ls, char *name, int namelen,
 	unsigned int flags, struct dlm_rsb **r_ret);

fs/dlm/lockspace.c

···
 	ls->ls_recover_seq = 0;
 	ls->ls_recover_args = NULL;
 	init_rwsem(&ls->ls_in_recovery);
+	init_rwsem(&ls->ls_recv_active);
 	INIT_LIST_HEAD(&ls->ls_requestqueue);
 	mutex_init(&ls->ls_requestqueue_mutex);
 	mutex_init(&ls->ls_clear_proc_locks);

fs/dlm/lowcomms.c

···
 		con->rx_page = NULL;
 	}
 
-	/* If we are an 'othercon' then NULL the pointer to us
-	   from the parent and tidy ourself up */
-	if (test_bit(CF_IS_OTHERCON, &con->flags)) {
-		struct connection *parent = __nodeid2con(con->nodeid, 0);
-		parent->othercon = NULL;
-		kmem_cache_free(con_cache, con);
-	}
-	else {
-		/* Parent connections get reused */
-		con->retries = 0;
-		mutex_unlock(&con->sock_mutex);
-	}
+	con->retries = 0;
+	mutex_unlock(&con->sock_mutex);
 }
 
 /* We only send shutdown messages to nodes that are not part of the cluster */
···
 			INIT_WORK(&othercon->swork, process_send_sockets);
 			INIT_WORK(&othercon->rwork, process_recv_sockets);
 			set_bit(CF_IS_OTHERCON, &othercon->flags);
+		}
+		if (!othercon->sock) {
 			newcon->othercon = othercon;
 			othercon->sock = newsock;
 			newsock->sk->sk_user_data = othercon;
···
 		if (len) {
 			ret = sendpage(con->sock, e->page, offset, len,
 				       msg_flags);
-			if (ret == -EAGAIN || ret == 0)
+			if (ret == -EAGAIN || ret == 0) {
+				cond_resched();
 				goto out;
+			}
 			if (ret <= 0)
 				goto send_error;
-		} else {
+		}
 			/* Don't starve people filling buffers */
 			cond_resched();
-		}
 
 		spin_lock(&con->writequeue_lock);
 		e->offset += ret;

fs/dlm/member.c

···
 #include "rcom.h"
 #include "config.h"
 
-/*
- * Following called by dlm_recoverd thread
- */
-
 static void add_ordered_member(struct dlm_ls *ls, struct dlm_member *new)
 {
 	struct dlm_member *memb = NULL;
···
 	return error;
 }
 
-/*
- * Following called from lockspace.c
- */
+/* Userspace guarantees that dlm_ls_stop() has completed on all nodes before
+   dlm_ls_start() is called on any of them to start the new recovery. */
 
 int dlm_ls_stop(struct dlm_ls *ls)
 {
 	int new;
 
 	/*
-	 * A stop cancels any recovery that's in progress (see RECOVERY_STOP,
-	 * dlm_recovery_stopped()) and prevents any new locks from being
-	 * processed (see RUNNING, dlm_locking_stopped()).
+	 * Prevent dlm_recv from being in the middle of something when we do
+	 * the stop.  This includes ensuring dlm_recv isn't processing a
+	 * recovery message (rcom), while dlm_recoverd is aborting and
+	 * resetting things from an in-progress recovery.  i.e. we want
+	 * dlm_recoverd to abort its recovery without worrying about dlm_recv
+	 * processing an rcom at the same time.  Stopping dlm_recv also makes
+	 * it easy for dlm_receive_message() to check locking stopped and add a
+	 * message to the requestqueue without races.
+	 */
+
+	down_write(&ls->ls_recv_active);
+
+	/*
+	 * Abort any recovery that's in progress (see RECOVERY_STOP,
+	 * dlm_recovery_stopped()) and tell any other threads running in the
+	 * dlm to quit any processing (see RUNNING, dlm_locking_stopped()).
 	 */
 
 	spin_lock(&ls->ls_recover_lock);
···
 	spin_unlock(&ls->ls_recover_lock);
 
 	/*
+	 * Let dlm_recv run again, now any normal messages will be saved on the
+	 * requestqueue for later.
+	 */
+
+	up_write(&ls->ls_recv_active);
+
+	/*
 	 * This in_recovery lock does two things:
-	 *
 	 * 1) Keeps this function from returning until all threads are out
 	 *    of locking routines and locking is truely stopped.
 	 * 2) Keeps any new requests from being processed until it's unlocked
···
 
 	/*
 	 * The recoverd suspend/resume makes sure that dlm_recoverd (if
-	 * running) has noticed the clearing of RUNNING above and quit
-	 * processing the previous recovery.  This will be true for all nodes
-	 * before any nodes start the new recovery.
+	 * running) has noticed RECOVERY_STOP above and quit processing the
+	 * previous recovery.
 	 */
 
 	dlm_recoverd_suspend(ls);

fs/dlm/midcomms.c

···
 *******************************************************************************
 **
 **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
-**  Copyright (C) 2004-2005 Red Hat, Inc.  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
···
 #include "dlm_internal.h"
 #include "lowcomms.h"
 #include "config.h"
-#include "rcom.h"
 #include "lock.h"
 #include "midcomms.h"
 
···
 		offset &= (limit - 1);
 		len -= msglen;
 
-		switch (msg->h_cmd) {
-		case DLM_MSG:
-			dlm_receive_message(msg, nodeid, 0);
-			break;
-
-		case DLM_RCOM:
-			dlm_receive_rcom(msg, nodeid);
-			break;
-
-		default:
-			log_print("unknown msg type %x from %u: %u %u %u %u",
-				  msg->h_cmd, nodeid, msglen, len, offset, ret);
-		}
+		dlm_receive_buffer(msg, nodeid);
 	}
 
 	if (msg != (struct dlm_header *) __tmp)

fs/dlm/rcom.c

···
 *******************************************************************************
 **
 **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
-**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2005-2007 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
···
 	dlm_recover_process_copy(ls, rc_in);
 }
 
-static int send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in)
+/* If the lockspace doesn't exist then still send a status message
+   back; it's possible that it just doesn't have its global_id yet. */
+
+int dlm_send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in)
 {
 	struct dlm_rcom *rc;
 	struct rcom_config *rf;
···
 	return rv;
 }
 
-/* Called by dlm_recvd; corresponds to dlm_receive_message() but special
+/* Called by dlm_recv; corresponds to dlm_receive_message() but special
    recovery-only comms are sent through here. */
 
-void dlm_receive_rcom(struct dlm_header *hd, int nodeid)
+void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid)
 {
-	struct dlm_rcom *rc = (struct dlm_rcom *) hd;
-	struct dlm_ls *ls;
-
-	dlm_rcom_in(rc);
-
-	/* If the lockspace doesn't exist then still send a status message
-	   back; it's possible that it just doesn't have its global_id yet. */
-
-	ls = dlm_find_lockspace_global(hd->h_lockspace);
-	if (!ls) {
-		log_print("lockspace %x from %d type %x not found",
-			  hd->h_lockspace, nodeid, rc->rc_type);
-		if (rc->rc_type == DLM_RCOM_STATUS)
-			send_ls_not_ready(nodeid, rc);
-		return;
-	}
-
 	if (dlm_recovery_stopped(ls) && (rc->rc_type != DLM_RCOM_STATUS)) {
 		log_debug(ls, "ignoring recovery message %x from %d",
 			  rc->rc_type, nodeid);
···
 
 	if (is_old_reply(ls, rc))
 		goto out;
-
-	if (nodeid != rc->rc_header.h_nodeid) {
-		log_error(ls, "bad rcom nodeid %d from %d",
-			  rc->rc_header.h_nodeid, nodeid);
-		goto out;
-	}
 
 	switch (rc->rc_type) {
 	case DLM_RCOM_STATUS:
···
 		DLM_ASSERT(0, printk("rc_type=%x\n", rc->rc_type););
 	}
  out:
-	dlm_put_lockspace(ls);
+	return;
 }
 

fs/dlm/rcom.h

···
 *******************************************************************************
 **
 **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
-**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2005-2007 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
···
 int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name,int last_len);
 int dlm_send_rcom_lookup(struct dlm_rsb *r, int dir_nodeid);
 int dlm_send_rcom_lock(struct dlm_rsb *r, struct dlm_lkb *lkb);
-void dlm_receive_rcom(struct dlm_header *hd, int nodeid);
+void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid);
+int dlm_send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in);
 
 #endif
 

fs/dlm/recoverd.c

···
 
 
 /* If the start for which we're re-enabling locking (seq) has been superseded
-   by a newer stop (ls_recover_seq), we need to leave locking disabled. */
+   by a newer stop (ls_recover_seq), we need to leave locking disabled.
+
+   We suspend dlm_recv threads here to avoid the race where dlm_recv a) sees
+   locking stopped and b) adds a message to the requestqueue, but dlm_recoverd
+   enables locking and clears the requestqueue between a and b. */
 
 static int enable_locking(struct dlm_ls *ls, uint64_t seq)
 {
 	int error = -EINTR;
 
+	down_write(&ls->ls_recv_active);
+
 	spin_lock(&ls->ls_recover_lock);
 	if (ls->ls_recover_seq == seq) {
 		set_bit(LSFL_RUNNING, &ls->ls_flags);
+		/* unblocks processes waiting to enter the dlm */
 		up_write(&ls->ls_in_recovery);
 		error = 0;
 	}
 	spin_unlock(&ls->ls_recover_lock);
+
+	up_write(&ls->ls_recv_active);
 	return error;
 }
 

fs/dlm/requestqueue.c

···
 /******************************************************************************
 *******************************************************************************
 **
-**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2005-2007 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
···
 struct rq_entry {
 	struct list_head list;
 	int nodeid;
-	char request[1];
+	char request[0];
 };
 
 /*
···
  * lockspace is enabled on some while still suspended on others.
  */
 
-int dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_header *hd)
+void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_header *hd)
 {
 	struct rq_entry *e;
 	int length = hd->h_length;
-	int rv = 0;
 
 	e = kmalloc(sizeof(struct rq_entry) + length, GFP_KERNEL);
 	if (!e) {
-		log_print("dlm_add_requestqueue: out of memory\n");
-		return 0;
+		log_print("dlm_add_requestqueue: out of memory len %d", length);
+		return;
 	}
 
 	e->nodeid = nodeid;
 	memcpy(e->request, hd, length);
 
-	/* We need to check dlm_locking_stopped() after taking the mutex to
-	   avoid a race where dlm_recoverd enables locking and runs
-	   process_requestqueue between our earlier dlm_locking_stopped check
-	   and this addition to the requestqueue. */
-
 	mutex_lock(&ls->ls_requestqueue_mutex);
-	if (dlm_locking_stopped(ls))
-		list_add_tail(&e->list, &ls->ls_requestqueue);
-	else {
-		log_debug(ls, "dlm_add_requestqueue skip from %d", nodeid);
-		kfree(e);
-		rv = -EAGAIN;
-	}
+	list_add_tail(&e->list, &ls->ls_requestqueue);
 	mutex_unlock(&ls->ls_requestqueue_mutex);
-	return rv;
 }
+
+/*
+ * Called by dlm_recoverd to process normal messages saved while recovery was
+ * happening.  Normal locking has been enabled before this is called.  dlm_recv
+ * upon receiving a message, will wait for all saved messages to be drained
+ * here before processing the message it got.  If a new dlm_ls_stop() arrives
+ * while we're processing these saved messages, it may block trying to suspend
+ * dlm_recv if dlm_recv is waiting for us in dlm_wait_requestqueue.  In that
+ * case, we don't abort since locking_stopped is still 0.  If dlm_recv is not
+ * waiting for us, then this processing may be aborted due to locking_stopped.
+ */
 
 int dlm_process_requestqueue(struct dlm_ls *ls)
 {
 	struct rq_entry *e;
-	struct dlm_header *hd;
 	int error = 0;
 
 	mutex_lock(&ls->ls_requestqueue_mutex);
···
 		e = list_entry(ls->ls_requestqueue.next, struct rq_entry, list);
 		mutex_unlock(&ls->ls_requestqueue_mutex);
 
-		hd = (struct dlm_header *) e->request;
-		error = dlm_receive_message(hd, e->nodeid, 1);
-
-		if (error == -EINTR) {
-			/* entry is left on requestqueue */
-			log_debug(ls, "process_requestqueue abort eintr");
-			break;
-		}
+		dlm_receive_message_saved(ls, (struct dlm_message *)e->request);
 
 		mutex_lock(&ls->ls_requestqueue_mutex);
 		list_del(&e->list);
···
 
 /*
  * After recovery is done, locking is resumed and dlm_recoverd takes all the
- * saved requests and processes them as they would have been by dlm_recvd.  At
- * the same time, dlm_recvd will start receiving new requests from remote
- * nodes.  We want to delay dlm_recvd processing new requests until
- * dlm_recoverd has finished processing the old saved requests.
+ * saved requests and processes them as they would have been by dlm_recv.  At
+ * the same time, dlm_recv will start receiving new requests from remote nodes.
+ * We want to delay dlm_recv processing new requests until dlm_recoverd has
+ * finished processing the old saved requests.  We don't check for locking
+ * stopped here because dlm_ls_stop won't stop locking until it's suspended us
+ * (dlm_recv).
  */
 
 void dlm_wait_requestqueue(struct dlm_ls *ls)
···
 	for (;;) {
 		mutex_lock(&ls->ls_requestqueue_mutex);
 		if (list_empty(&ls->ls_requestqueue))
-			break;
-		if (dlm_locking_stopped(ls))
 			break;
 		mutex_unlock(&ls->ls_requestqueue_mutex);
 		schedule();

fs/dlm/requestqueue.h

···
 /******************************************************************************
 *******************************************************************************
 **
-**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2005-2007 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
···
 #ifndef __REQUESTQUEUE_DOT_H__
 #define __REQUESTQUEUE_DOT_H__
 
-int dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_header *hd);
+void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_header *hd);
 int dlm_process_requestqueue(struct dlm_ls *ls);
 void dlm_wait_requestqueue(struct dlm_ls *ls);
 void dlm_purge_requestqueue(struct dlm_ls *ls);

fs/gfs2/bmap.c

···
 		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);
···
 	return error;
 }
 
+static int do_touch(struct gfs2_inode *ip, u64 size)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head *dibh;
+	int error;
+
+	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
+	if (error)
+		return error;
+
+	down_write(&ip->i_rw_mutex);
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		goto do_touch_out;
+
+	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_dinode_out(ip, dibh->b_data);
+	brelse(dibh);
+
+do_touch_out:
+	up_write(&ip->i_rw_mutex);
+	gfs2_trans_end(sdp);
+	return error;
+}
+
 /**
  * gfs2_truncatei - make a file a given size
  * @ip: the inode
···
 
 	if (size > ip->i_di.di_size)
 		error = do_grow(ip, size);
-	else
+	else if (size < ip->i_di.di_size)
 		error = do_shrink(ip, size);
+	else
+		/* update time stamps */
+		error = do_touch(ip, size);
 
 	return error;
 }

fs/gfs2/daemon.c

···
    The kthread functions used to start these daemons block and flush signals. */
 
 /**
- * gfs2_scand - Look for cached glocks and inodes to toss from memory
- * @sdp: Pointer to GFS2 superblock
- *
- * One of these daemons runs, finding candidates to add to sd_reclaim_list.
- * See gfs2_glockd()
- */
-
-int gfs2_scand(void *data)
-{
-	struct gfs2_sbd *sdp = data;
-	unsigned long t;
-
-	while (!kthread_should_stop()) {
-		gfs2_scand_internal(sdp);
-		t = gfs2_tune_get(sdp, gt_scand_secs) * HZ;
-		if (freezing(current))
-			refrigerator();
-		schedule_timeout_interruptible(t);
-	}
-
-	return 0;
-}
-
-/**
  * gfs2_glockd - Reclaim unused glock structures
  * @sdp: Pointer to GFS2 superblock
  *

fs/gfs2/daemon.h

···
 #ifndef __DAEMON_DOT_H__
 #define __DAEMON_DOT_H__
 
-int gfs2_scand(void *data);
 int gfs2_glockd(void *data);
 int gfs2_recoverd(void *data);
 int gfs2_logd(void *data);

fs/gfs2/dir.c

···
 
 	error = gfs2_meta_inode_buffer(dip, &dibh);
 	if (!gfs2_assert_withdraw(GFS2_SB(&dip->i_inode), !error)) {
+		gfs2_trans_add_bh(dip->i_gl, dibh, 1);
 		dip->i_di.di_blocks++;
 		gfs2_set_inode_blocks(&dip->i_inode);
 		gfs2_dinode_out(dip, dibh->b_data);
···
 		inode = gfs2_inode_lookup(dir->i_sb, 
 				be16_to_cpu(dent->de_type),
 				be64_to_cpu(dent->de_inum.no_addr),
-				be64_to_cpu(dent->de_inum.no_formal_ino));
+				be64_to_cpu(dent->de_inum.no_formal_ino), 0);
 		brelse(bh);
 		return inode;
 	}

fs/gfs2/eaops.c

···
 	return gfs2_ea_remove_i(ip, er);
 }
 
-static struct gfs2_eattr_operations gfs2_user_eaops = {
+static const struct gfs2_eattr_operations gfs2_user_eaops = {
 	.eo_get = user_eo_get,
 	.eo_set = user_eo_set,
 	.eo_remove = user_eo_remove,
 	.eo_name = "user",
 };
 
-struct gfs2_eattr_operations gfs2_system_eaops = {
+const struct gfs2_eattr_operations gfs2_system_eaops = {
 	.eo_get = system_eo_get,
 	.eo_set = system_eo_set,
 	.eo_remove = system_eo_remove,
 	.eo_name = "system",
 };
 
-static struct gfs2_eattr_operations gfs2_security_eaops = {
+static const struct gfs2_eattr_operations gfs2_security_eaops = {
 	.eo_get = security_eo_get,
 	.eo_set = security_eo_set,
 	.eo_remove = security_eo_remove,
 	.eo_name = "security",
 };
 
-struct gfs2_eattr_operations *gfs2_ea_ops[] = {
+const struct gfs2_eattr_operations *gfs2_ea_ops[] = {
 	NULL,
 	&gfs2_user_eaops,
 	&gfs2_system_eaops,

fs/gfs2/eaops.h

···
 
 unsigned int gfs2_ea_name2type(const char *name, const char **truncated_name);
 
-extern struct gfs2_eattr_operations gfs2_system_eaops;
+extern const struct gfs2_eattr_operations gfs2_system_eaops;
 
-extern struct gfs2_eattr_operations *gfs2_ea_ops[];
+extern const struct gfs2_eattr_operations *gfs2_ea_ops[];
 
 #endif /* __EAOPS_DOT_H__ */
 

fs/gfs2/glock.c

···
 #include <asm/uaccess.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
-#include <linux/module.h>
-#include <linux/kallsyms.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/workqueue.h>
+#include <linux/jiffies.h>
 
 #include "gfs2.h"
 #include "incore.h"
···
 	int hash;                     /* hash bucket index         */
 	struct gfs2_sbd *sdp;         /* incore superblock         */
 	struct gfs2_glock *gl;        /* current glock struct      */
-	struct hlist_head *hb_list;   /* current hash bucket ptr   */
 	struct seq_file *seq;         /* sequence file for debugfs */
 	char string[512];             /* scratch space             */
 };
···
 static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl);
 static void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh);
 static void gfs2_glock_drop_th(struct gfs2_glock *gl);
+static void run_queue(struct gfs2_glock *gl);
+
 static DECLARE_RWSEM(gfs2_umount_flush_sem);
 static struct dentry *gfs2_root;
+static struct task_struct *scand_process;
+static unsigned int scand_secs = 5;
+static struct workqueue_struct *glock_workqueue;
 
 #define GFS2_GL_HASH_SHIFT      15
 #define GFS2_GL_HASH_SIZE       (1 << GFS2_GL_HASH_SHIFT)
···
 	return gl;
 }
 
+static void glock_work_func(struct work_struct *work)
+{
+	struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work);
+
+	spin_lock(&gl->gl_spin);
+	if (test_and_clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags))
+		set_bit(GLF_DEMOTE, &gl->gl_flags);
+	run_queue(gl);
+	spin_unlock(&gl->gl_spin);
+	gfs2_glock_put(gl);
+}
+
 /**
  * gfs2_glock_get() - Get a glock, or create one if one doesn't exist
  * @sdp: The GFS2 superblock
···
 	gl->gl_name = name;
 	atomic_set(&gl->gl_ref, 1);
 	gl->gl_state = LM_ST_UNLOCKED;
+	gl->gl_demote_state = LM_ST_EXCLUSIVE;
 	gl->gl_hash = hash;
 	gl->gl_owner_pid = 0;
 	gl->gl_ip = 0;
···
 	gl->gl_req_bh = NULL;
 	gl->gl_vn = 0;
 	gl->gl_stamp = jiffies;
+	gl->gl_tchange = jiffies;
 	gl->gl_object = NULL;
 	gl->gl_sbd = sdp;
 	gl->gl_aspace = NULL;
 	lops_init_le(&gl->gl_le, &gfs2_glock_lops);
+	INIT_DELAYED_WORK(&gl->gl_work, glock_work_func);
 
 	/* If this glock protects actual on-disk data or metadata blocks,
 	   create a VFS inode to manage the pages/buffers holding them. */
···
 
 static void gfs2_demote_wake(struct gfs2_glock *gl)
 {
+	BUG_ON(!spin_is_locked(&gl->gl_spin));
+	gl->gl_demote_state = LM_ST_EXCLUSIVE;
         clear_bit(GLF_DEMOTE, &gl->gl_flags);
         smp_mb__after_clear_bit();
         wake_up_bit(&gl->gl_flags, GLF_DEMOTE);
···
 		return 0;
 	}
 	set_bit(GLF_LOCK, &gl->gl_flags);
-	spin_unlock(&gl->gl_spin);
 	if (gl->gl_demote_state == LM_ST_UNLOCKED ||
-	    gl->gl_state != LM_ST_EXCLUSIVE)
+	    gl->gl_state != LM_ST_EXCLUSIVE) {
+		spin_unlock(&gl->gl_spin);
 		gfs2_glock_drop_th(gl);
-	else
+	} else {
+		spin_unlock(&gl->gl_spin);
 		gfs2_glock_xmote_th(gl, NULL);
+	}
 	spin_lock(&gl->gl_spin);
 
 	return 0;
···
  * practise: LM_ST_SHARED and LM_ST_UNLOCKED
  */
 
-static void handle_callback(struct gfs2_glock *gl, unsigned int state, int remote)
+static void handle_callback(struct gfs2_glock *gl, unsigned int state,
+			    int remote, unsigned long delay)
 {
+	int bit = delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE;
+
 	spin_lock(&gl->gl_spin);
-	if (test_and_set_bit(GLF_DEMOTE, &gl->gl_flags) == 0) {
+	set_bit(bit, &gl->gl_flags);
+	if (gl->gl_demote_state == LM_ST_EXCLUSIVE) {
 		gl->gl_demote_state = state;
 		gl->gl_demote_time = jiffies;
 		if (remote && gl->gl_ops->go_type == LM_TYPE_IOPEN &&
 		    gl->gl_object) {
-			struct inode *inode = igrab(gl->gl_object);
+			gfs2_glock_schedule_for_reclaim(gl);
 			spin_unlock(&gl->gl_spin);
-			if (inode) {
-				d_prune_aliases(inode);
-				iput(inode);
-			}
 			return;
 		}
-	} else if (gl->gl_demote_state != LM_ST_UNLOCKED) {
-		gl->gl_demote_state = state;
+	} else if (gl->gl_demote_state != LM_ST_UNLOCKED &&
+			gl->gl_demote_state != state) {
+		gl->gl_demote_state = LM_ST_UNLOCKED;
 	}
 	spin_unlock(&gl->gl_spin);
 }
···
 	}
 
 	gl->gl_state = new_state;
+	gl->gl_tchange = jiffies;
 }
 
 /**
···
 
 	if (!gh) {
 		gl->gl_stamp = jiffies;
-		if (ret & LM_OUT_CANCELED)
+		if (ret & LM_OUT_CANCELED) {
 			op_done = 0;
-		else
+		} else {
+			spin_lock(&gl->gl_spin);
+			if (gl->gl_state != gl->gl_demote_state) {
+				gl->gl_req_bh = NULL;
+				spin_unlock(&gl->gl_spin);
+				gfs2_glock_drop_th(gl);
+				gfs2_glock_put(gl);
+				return;
+			}
 			gfs2_demote_wake(gl);
+			spin_unlock(&gl->gl_spin);
+		}
 	} else {
 		spin_lock(&gl->gl_spin);
 		list_del_init(&gh->gh_list);
···
 		gl->gl_req_gh = NULL;
 		gl->gl_req_bh = NULL;
 		clear_bit(GLF_LOCK, &gl->gl_flags);
-		run_queue(gl);
 		spin_unlock(&gl->gl_spin);
 	}
 
···
  *
  */
 
-void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh)
+static void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	int flags = gh ? gh->gh_flags : 0;
···
 	gfs2_assert_warn(sdp, !ret);
 
 	state_change(gl, LM_ST_UNLOCKED);
-	gfs2_demote_wake(gl);
 
 	if (glops->go_inval)
 		glops->go_inval(gl, DIO_METADATA);
···
 	}
 
 	spin_lock(&gl->gl_spin);
+	gfs2_demote_wake(gl);
 	gl->gl_req_gh = NULL;
 	gl->gl_req_bh = NULL;
 	clear_bit(GLF_LOCK, &gl->gl_flags);
-	run_queue(gl);
 	spin_unlock(&gl->gl_spin);
 
 	gfs2_glock_put(gl);
···
 	if (test_and_set_bit(HIF_WAIT, &gh->gh_iflags))
 		BUG();
 
-	existing = find_holder_by_owner(&gl->gl_holders, gh->gh_owner_pid);
-	if (existing) {
-		print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip);
-		printk(KERN_INFO "pid : %d\n", existing->gh_owner_pid);
-		printk(KERN_INFO "lock type : %d lock state : %d\n",
-				existing->gh_gl->gl_name.ln_type, existing->gh_gl->gl_state);
-		print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
-		printk(KERN_INFO "pid : %d\n", gh->gh_owner_pid);
-		printk(KERN_INFO "lock type : %d lock state : %d\n",
-				gl->gl_name.ln_type, gl->gl_state);
-		BUG();
-	}
-
-	existing = find_holder_by_owner(&gl->gl_waiters3, gh->gh_owner_pid);
-	if (existing) {
-		print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip);
-		print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
-		BUG();
+	if (!(gh->gh_flags & GL_FLOCK)) {
+		existing = find_holder_by_owner(&gl->gl_holders, 
+						gh->gh_owner_pid);
+		if (existing) {
+			print_symbol(KERN_WARNING "original: %s\n", 
+				     existing->gh_ip);
+			printk(KERN_INFO "pid : %d\n", existing->gh_owner_pid);
+			printk(KERN_INFO "lock type : %d lock state : %d\n",
+			       existing->gh_gl->gl_name.ln_type, 
+			       existing->gh_gl->gl_state);
+			print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
+			printk(KERN_INFO "pid : %d\n", gh->gh_owner_pid);
+			printk(KERN_INFO "lock type : %d lock state : %d\n",
+			       gl->gl_name.ln_type, gl->gl_state);
+			BUG();
+		}
+		
+		existing = find_holder_by_owner(&gl->gl_waiters3, 
+						gh->gh_owner_pid);
+		if (existing) {
+			print_symbol(KERN_WARNING "original: %s\n", 
+				     existing->gh_ip);
+			print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
+			BUG();
+		}
 	}
 
 	if (gh->gh_flags & LM_FLAG_PRIORITY)
···
 {
 	struct gfs2_glock *gl = gh->gh_gl;
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
+	unsigned delay = 0;
 
 	if (gh->gh_flags & GL_NOCACHE)
-		handle_callback(gl, LM_ST_UNLOCKED, 0);
+		handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
 
 	gfs2_glmutex_lock(gl);
 
···
 	}
 
 	clear_bit(GLF_LOCK, &gl->gl_flags);
-	run_queue(gl);
 	spin_unlock(&gl->gl_spin);
+
+	gfs2_glock_hold(gl);
+	if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+	    !test_bit(GLF_DEMOTE, &gl->gl_flags))
+		delay = gl->gl_ops->go_min_hold_time;
+	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
+		gfs2_glock_put(gl);
 }
 
 void gfs2_glock_dq_wait(struct gfs2_holder *gh)
···
 			unsigned int state)
 {
 	struct gfs2_glock *gl;
+	unsigned long delay = 0;
+	unsigned long holdtime;
+	unsigned long now = jiffies;
 
 	gl = gfs2_glock_find(sdp, name);
 	if (!gl)
 		return;
 
-	handle_callback(gl, state, 1);
+	holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
+	if (time_before(now, holdtime))
+		delay = holdtime - now;
 
-	spin_lock(&gl->gl_spin);
-	run_queue(gl);
-	spin_unlock(&gl->gl_spin);
-
-	gfs2_glock_put(gl);
+	handle_callback(gl, state, 1, delay);
+	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
+		gfs2_glock_put(gl);
 }
 
 /**
···
 			return;
 		if (!gfs2_assert_warn(sdp, gl->gl_req_bh))
 			gl->gl_req_bh(gl, async->lc_ret);
-		gfs2_glock_put(gl);
+		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+			gfs2_glock_put(gl);
 		up_read(&gfs2_umount_flush_sem);
 		return;
 	}
···
 	if (gfs2_glmutex_trylock(gl)) {
 		if (list_empty(&gl->gl_holders) &&
 		    gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl))
-			handle_callback(gl, LM_ST_UNLOCKED, 0);
+			handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
 		gfs2_glmutex_unlock(gl);
 	}
 
···
 		goto out;
 	gl = list_entry(head->first, struct gfs2_glock, gl_list);
 	while(1) {
-		if (gl->gl_sbd == sdp) {
+		if (!sdp || gl->gl_sbd == sdp) {
 			gfs2_glock_hold(gl);
 			read_unlock(gl_lock_addr(hash));
 			if (prev)
···
 	read_unlock(gl_lock_addr(hash));
 	if (prev)
 		gfs2_glock_put(prev);
+	cond_resched();
 	return has_entries;
 }
 
···
 }
 
 /**
- * gfs2_scand_internal - Look for glocks and inodes to toss from memory
- * @sdp: the filesystem
- *
- */
-
-void gfs2_scand_internal(struct gfs2_sbd *sdp)
-{
-	unsigned int x;
-
-	for (x = 0; x < GFS2_GL_HASH_SIZE; x++)
-		examine_bucket(scan_glock, sdp, x);
-}
-
-/**
  * clear_glock - look at a glock and see if we can free it from glock cache
  * @gl: the glock to look at
  *
···
 	if (gfs2_glmutex_trylock(gl)) {
 		if (list_empty(&gl->gl_holders) &&
 		    gl->gl_state != LM_ST_UNLOCKED)
-			handle_callback(gl, LM_ST_UNLOCKED, 0);
+			handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
 		gfs2_glmutex_unlock(gl);
 	}
 }
···
 
 	spin_lock(&gl->gl_spin);
 
-	print_dbg(gi, "Glock 0x%p (%u, %llu)\n", gl, gl->gl_name.ln_type,
+	print_dbg(gi, "Glock 0x%p (%u, 0x%llx)\n", gl, gl->gl_name.ln_type,
 		   (unsigned long long)gl->gl_name.ln_number);
 	print_dbg(gi, "  gl_flags =");
 	for (x = 0; x < 32; x++) {
···
 	return error;
 }
 
+/**
+ * gfs2_scand - Look for cached glocks and inodes to toss from memory
+ * @sdp: Pointer to GFS2 superblock
+ *
+ * One of these daemons runs, finding candidates to add to sd_reclaim_list.
+ * See gfs2_glockd()
+ */
+
+static int gfs2_scand(void *data)
+{
+	unsigned x;
+	unsigned delay;
+
+	while (!kthread_should_stop()) {
+		for (x = 0; x < GFS2_GL_HASH_SIZE; x++)
+			examine_bucket(scan_glock, NULL, x);
+		if (freezing(current))
+			refrigerator();
+		delay = scand_secs;
+		if (delay < 1)
+			delay = 1;
+		schedule_timeout_interruptible(delay * HZ);
+	}
+
+	return 0;
+}
+
+
+
 int __init gfs2_glock_init(void)
 {
 	unsigned i;
···
 		rwlock_init(&gl_hash_locks[i]);
 	}
 #endif
+
+	scand_process = kthread_run(gfs2_scand, NULL, "gfs2_scand");
+	if (IS_ERR(scand_process))
+		return PTR_ERR(scand_process);
+
+	glock_workqueue = create_workqueue("glock_workqueue");
+	if (IS_ERR(glock_workqueue)) {
+		kthread_stop(scand_process);
+		return PTR_ERR(glock_workqueue);
+	}
+
 	return 0;
 }
 
+void gfs2_glock_exit(void)
+{
+	destroy_workqueue(glock_workqueue);
+	kthread_stop(scand_process);
+}
+
+module_param(scand_secs, uint, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(scand_secs, "The number of seconds between scand runs");
+
 static int gfs2_glock_iter_next(struct glock_iter *gi)
 {
+	struct gfs2_glock *gl;
+
+restart:
 	read_lock(gl_lock_addr(gi->hash));
-	while (1) {
-		if (!gi->hb_list) {  /* If we don't have a hash bucket yet */
-			gi->hb_list = &gl_hash_table[gi->hash].hb_list;
-			if (hlist_empty(gi->hb_list)) {
-				read_unlock(gl_lock_addr(gi->hash));
-				gi->hash++;
-				read_lock(gl_lock_addr(gi->hash));
-				gi->hb_list = NULL;
-				if (gi->hash >= GFS2_GL_HASH_SIZE) {
-					read_unlock(gl_lock_addr(gi->hash));
-					return 1;
-				}
-				else
-					continue;
-			}
-			if (!hlist_empty(gi->hb_list)) {
-				gi->gl = list_entry(gi->hb_list->first,
-						    struct gfs2_glock,
-						    gl_list);
-			}
-		} else {
-			if (gi->gl->gl_list.next == NULL) {
-				read_unlock(gl_lock_addr(gi->hash));
-				gi->hash++;
-				read_lock(gl_lock_addr(gi->hash));
-				gi->hb_list = NULL;
-				continue;
-			}
-			gi->gl = list_entry(gi->gl->gl_list.next,
-					    struct gfs2_glock, gl_list);
-		}
+	gl = gi->gl;
+	if (gl) {
+		gi->gl = hlist_entry(gl->gl_list.next,
+				     struct gfs2_glock, gl_list);
 		if (gi->gl)
-			break;
+			gfs2_glock_hold(gi->gl);
 	}
 	read_unlock(gl_lock_addr(gi->hash));
+	if (gl)
+		gfs2_glock_put(gl);
+	if (gl && gi->gl == NULL)
+		gi->hash++;
+	while(gi->gl == NULL) {
+		if (gi->hash >= GFS2_GL_HASH_SIZE)
+			return 1;
+		read_lock(gl_lock_addr(gi->hash));
+		gi->gl = hlist_entry(gl_hash_table[gi->hash].hb_list.first,
+				     struct gfs2_glock, gl_list);
+		if (gi->gl)
+			gfs2_glock_hold(gi->gl);
+		read_unlock(gl_lock_addr(gi->hash));
+		gi->hash++;
+	}
+
+	if (gi->sdp != gi->gl->gl_sbd)
+		goto restart;
+
 	return 0;
 }
 
 static void gfs2_glock_iter_free(struct glock_iter *gi)
 {
+	if (gi->gl)
+		gfs2_glock_put(gi->gl);
 	kfree(gi);
 }
 
···
 
 	gi->sdp = sdp;
 	gi->hash = 0;
-	gi->gl = NULL;
-	gi->hb_list = NULL;
 	gi->seq = NULL;
+	gi->gl = NULL;
 	memset(gi->string, 0, sizeof(gi->string));
 
 	if (gfs2_glock_iter_next(gi)) {
···
 	if (!gi)
 		return NULL;
 
-	while (n--) {
+	while(n--) {
 		if (gfs2_glock_iter_next(gi)) {
 			gfs2_glock_iter_free(gi);
 			return NULL;
···
 
 static void gfs2_glock_seq_stop(struct seq_file *file, void *iter_ptr)
 {
-	/* nothing for now */
+	struct glock_iter *gi = iter_ptr;
+	if (gi)
+		gfs2_glock_iter_free(gi);
 }
 
 static int gfs2_glock_seq_show(struct seq_file *file, void *iter_ptr)
···
 	return 0;
 }
 
-static struct seq_operations gfs2_glock_seq_ops = {
+static const struct seq_operations gfs2_glock_seq_ops = {
 	.start = gfs2_glock_seq_start,
 	.next  = gfs2_glock_seq_next,
 	.stop  = gfs2_glock_seq_stop,

fs/gfs2/glock.h

···
 #define GL_SKIP			0x00000100
 #define GL_ATIME		0x00000200
 #define GL_NOCACHE		0x00000400
+#define GL_FLOCK		0x00000800
 #define GL_NOCANCEL		0x00001000
 
 #define GLR_TRYFAILED		13
···
 
 void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl);
 void gfs2_reclaim_glock(struct gfs2_sbd *sdp);
-
-void gfs2_scand_internal(struct gfs2_sbd *sdp);
 void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait);
 
 int __init gfs2_glock_init(void);
+void gfs2_glock_exit(void);
+
 int gfs2_create_debugfs_file(struct gfs2_sbd *sdp);
 void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp);
 int gfs2_register_debugfs(void);

fs/gfs2/glops.c

···
 	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);
···
 		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);
···
 		ip = NULL;
 
 	if (test_bit(GLF_DIRTY, &gl->gl_flags)) {
-		if (ip)
+		if (ip && !gfs2_is_jdata(ip))
 			filemap_fdatawrite(ip->i_inode.i_mapping);
 		gfs2_log_flush(gl->gl_sbd, gl);
+		if (ip && gfs2_is_jdata(ip))
+			filemap_fdatawrite(ip->i_inode.i_mapping);
 		gfs2_meta_sync(gl);
 		if (ip) {
 			struct address_space *mapping = ip->i_inode.i_mapping;
···
 	.go_lock = inode_go_lock,
 	.go_unlock = inode_go_unlock,
 	.go_type = LM_TYPE_INODE,
+	.go_min_hold_time = HZ / 10,
 };
 
 const struct gfs2_glock_operations gfs2_rgrp_glops = {
···
 	.go_lock = rgrp_go_lock,
 	.go_unlock = rgrp_go_unlock,
 	.go_type = LM_TYPE_RGRP,
+	.go_min_hold_time = HZ / 10,
 };
 
 const struct gfs2_glock_operations gfs2_trans_glops = {

fs/gfs2/incore.h

···
 #define __INCORE_DOT_H__
 
 #include <linux/fs.h>
+#include <linux/workqueue.h>
 
 #define DIO_WAIT	0x00000010
 #define DIO_METADATA	0x00000020
···
 	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;
···
 	int (*go_lock) (struct gfs2_holder *gh);
 	void (*go_unlock) (struct gfs2_holder *gh);
 	const int go_type;
+	const unsigned long go_min_hold_time;
 };
 
 enum {
···
 	GLF_LOCK		= 1,
 	GLF_STICKY		= 2,
 	GLF_DEMOTE		= 3,
+	GLF_PENDING_DEMOTE	= 4,
 	GLF_DIRTY		= 5,
 };
 
···
 
 	u64 gl_vn;
 	unsigned long gl_stamp;
+	unsigned long gl_tchange;
 	void *gl_object;
 
 	struct list_head gl_reclaim;
···
 	struct gfs2_log_element gl_le;
 	struct list_head gl_ail_list;
 	atomic_t gl_ail_count;
+	struct delayed_work gl_work;
 };
 
 struct gfs2_alloc {
···
 	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;
···
 	u64 qd_sync_gen;
 	unsigned long qd_last_warn;
 	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 int gt_log_flush_secs;
 	unsigned int gt_jindex_refresh_secs; /* Check for new journal index */
 
-	unsigned int gt_scand_secs;
 	unsigned int gt_recoverd_secs;
 	unsigned int gt_logd_secs;
 	unsigned int gt_quotad_secs;
···
 
 	/* Daemon stuff */
 
-	struct task_struct *sd_scand_process;
 	struct task_struct *sd_recoverd_process;
 	struct task_struct *sd_logd_process;
 	struct task_struct *sd_quotad_process;
···
 	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;
···
 
 	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;

fs/gfs2/inode.c

···
 	return iget5_locked(sb, hash, iget_test, iget_set, &no_addr);
 }
 
+struct gfs2_skip_data {
+	u64	no_addr;
+	int	skipped;
+};
+
+static int iget_skip_test(struct inode *inode, void *opaque)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_skip_data *data = opaque;
+
+	if (ip->i_no_addr == data->no_addr && inode->i_private != NULL){
+		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)){
+			data->skipped = 1;
+			return 0;
+		}
+		return 1;
+	}
+	return 0;
+}
+
+static int iget_skip_set(struct inode *inode, void *opaque)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_skip_data *data = opaque;
+
+	if (data->skipped)
+		return 1;
+	inode->i_ino = (unsigned long)(data->no_addr);
+	ip->i_no_addr = data->no_addr;
+	return 0;
+}
+
+static struct inode *gfs2_iget_skip(struct super_block *sb,
+				    u64 no_addr)
+{
+	struct gfs2_skip_data data;
+	unsigned long hash = (unsigned long)no_addr;
+
+	data.no_addr = no_addr;
+	data.skipped = 0;
+	return iget5_locked(sb, hash, iget_skip_test, iget_skip_set, &data);
+}
+
 /**
  * GFS2 lookup code fills in vfs inode contents based on info obtained
  * from directory entry inside gfs2_inode_lookup(). This has caused issues
···
  * @sb: The super block
  * @no_addr: The inode number
  * @type: The type of the inode
+ * @skip_freeing: set this not return an inode if it is currently being freed.
  *
  * Returns: A VFS inode, or an error
  */
···
 struct inode *gfs2_inode_lookup(struct super_block *sb, 
 				unsigned int type,
 				u64 no_addr,
-				u64 no_formal_ino)
+				u64 no_formal_ino, int skip_freeing)
 {
-	struct inode *inode = gfs2_iget(sb, no_addr);
-	struct gfs2_inode *ip = GFS2_I(inode);
+	struct inode *inode;
+	struct gfs2_inode *ip;
 	struct gfs2_glock *io_gl;
 	int error;
+
+	if (skip_freeing)
+		inode = gfs2_iget_skip(sb, no_addr);
+	else
+		inode = gfs2_iget(sb, no_addr);
+	ip = GFS2_I(inode);
 
 	if (!inode)
 		return ERR_PTR(-ENOBUFS);
···
 
 	di->di_eattr = be64_to_cpu(str->di_eattr);
 	return 0;
+}
+
+static void gfs2_inode_bh(struct gfs2_inode *ip, struct buffer_head *bh)
+{
+	ip->i_cache[0] = bh;
 }
 
 /**
···
 static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
 			const struct gfs2_inum_host *inum, unsigned int mode,
 			unsigned int uid, unsigned int gid,
-			const u64 *generation, dev_t dev)
+			const u64 *generation, dev_t dev, struct buffer_head **bhp)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
 	struct gfs2_dinode *di;
···
 	di->di_mtime_nsec = cpu_to_be32(tv.tv_nsec);
 	di->di_ctime_nsec = cpu_to_be32(tv.tv_nsec);
 	memset(&di->di_reserved, 0, sizeof(di->di_reserved));
+	
+	set_buffer_uptodate(dibh);
 
-	brelse(dibh);
+	*bhp = dibh;
 }
 
 static int make_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
 		       unsigned int mode, const struct gfs2_inum_host *inum,
-		       const u64 *generation, dev_t dev)
+		       const u64 *generation, dev_t dev, struct buffer_head **bhp)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
 	unsigned int uid, gid;
···
 	if (error)
 		goto out_quota;
 
-	init_dinode(dip, gl, inum, mode, uid, gid, generation, dev);
+	init_dinode(dip, gl, inum, mode, uid, gid, generation, dev, bhp);
 	gfs2_quota_change(dip, +1, uid, gid);
 	gfs2_trans_end(sdp);
 
···
 	struct gfs2_inum_host inum = { .no_addr = 0, .no_formal_ino = 0 };
 	int error;
 	u64 generation;
+	struct buffer_head *bh=NULL;
 
 	if (!name->len || name->len > GFS2_FNAMESIZE)
 		return ERR_PTR(-ENAMETOOLONG);
···
 	if (error)
 		goto fail_gunlock;
 
-	error = make_dinode(dip, ghs[1].gh_gl, mode, &inum, &generation, dev);
+	error = make_dinode(dip, ghs[1].gh_gl, mode, &inum, &generation, dev, &bh);
 	if (error)
 		goto fail_gunlock2;
 
 	inode = gfs2_inode_lookup(dir->i_sb, IF2DT(mode),
 					inum.no_addr,
-					inum.no_formal_ino);
+					inum.no_formal_ino, 0);
 	if (IS_ERR(inode))
 		goto fail_gunlock2;
+
+	gfs2_inode_bh(GFS2_I(inode), bh);
 
 	error = gfs2_inode_refresh(GFS2_I(inode));
 	if (error)

fs/gfs2/inode.h

···
 void gfs2_inode_attr_in(struct gfs2_inode *ip);
 void gfs2_set_iop(struct inode *inode);
 struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, 
-				u64 no_addr, u64 no_formal_ino);
+				u64 no_addr, u64 no_formal_ino,
+				int skip_freeing);
 struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr);
 
 int gfs2_inode_refresh(struct gfs2_inode *ip);

fs/gfs2/locking/dlm/lock_dlm.h

···
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
-#include <linux/module.h>
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/list.h>

fs/gfs2/locking/dlm/plock.c

···
 
 static unsigned int dev_poll(struct file *file, poll_table *wait)
 {
+	unsigned int mask = 0;
+
 	poll_wait(file, &send_wq, wait);
 
 	spin_lock(&ops_lock);
-	if (!list_empty(&send_list)) {
-		spin_unlock(&ops_lock);
-		return POLLIN | POLLRDNORM;
-	}
+	if (!list_empty(&send_list))
+		mask = POLLIN | POLLRDNORM;
 	spin_unlock(&ops_lock);
-	return 0;
+
+	return mask;
 }
 
 static const struct file_operations dev_fops = {

fs/gfs2/locking/dlm/thread.c

···
 	return 0;
 }
 
-static int gdlm_thread(void *data)
+static int gdlm_thread(void *data, int blist)
 {
 	struct gdlm_ls *ls = (struct gdlm_ls *) data;
 	struct gdlm_lock *lp = NULL;
-	int blist = 0;
 	uint8_t complete, blocking, submit, drop;
 	DECLARE_WAITQUEUE(wait, current);
 
 	/* Only thread1 is allowed to do blocking callbacks since gfs
 	   may wait for a completion callback within a blocking cb. */
-
-	if (current == ls->thread1)
-		blist = 1;
 
 	while (!kthread_should_stop()) {
 		set_current_state(TASK_INTERRUPTIBLE);
···
 	return 0;
 }
 
+static int gdlm_thread1(void *data)
+{
+	return gdlm_thread(data, 1);
+}
+
+static int gdlm_thread2(void *data)
+{
+	return gdlm_thread(data, 0);
+}
+
 int gdlm_init_threads(struct gdlm_ls *ls)
 {
 	struct task_struct *p;
 	int error;
 
-	p = kthread_run(gdlm_thread, ls, "lock_dlm1");
+	p = kthread_run(gdlm_thread1, ls, "lock_dlm1");
 	error = IS_ERR(p);
 	if (error) {
 		log_error("can't start lock_dlm1 thread %d", error);
···
 	}
 	ls->thread1 = p;
 
-	p = kthread_run(gdlm_thread, ls, "lock_dlm2");
+	p = kthread_run(gdlm_thread2, ls, "lock_dlm2");
 	error = IS_ERR(p);
 	if (error) {
 		log_error("can't start lock_dlm2 thread %d", error);

fs/gfs2/locking/nolock/main.c

···
 
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/fs.h>

fs/gfs2/log.c

···
 }
 
 /**
+ * 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
···
 
 			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);
+				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;
 			}
···
 
 			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;
···
 					 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)) {
···
 
 static void gfs2_ail1_start(struct gfs2_sbd *sdp, int flags)
 {
-	struct list_head *head = &sdp->sd_ail1_list;
+	struct list_head *head;
 	u64 sync_gen;
 	struct list_head *first;
 	struct gfs2_ail *first_ai, *ai, *tmp;
 	int done = 0;
 
 	gfs2_log_lock(sdp);
+	head = &sdp->sd_ail1_list;
 	if (list_empty(head)) {
 		gfs2_log_unlock(sdp);
 		return;
···
 		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);
+		gfs2_remove_from_ail(bd->bd_bh->b_page->mapping, bd);
 	}
 }
 
···
 	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;
 		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);
 }
 
 /**
···
 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_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);
 }
 
 /**
···
 				      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;
 }
···
 		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;
+	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;
-	int flushcount = 0;
+	LIST_HEAD(written);
 
-	while (!list_empty(head)) {
-		lb = list_entry(head->next, struct gfs2_log_buf, lb_list);
-		list_del(&lb->lb_list);
-		bh = lb->lb_bh;
-
-		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
+	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);
 }
 
 /**
···
 	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);
 
···
 	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);
···
 	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);

fs/gfs2/log.h

···
 
 int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks);
 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);

fs/gfs2/lops.c

···
 #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;
···
 	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);
 }
 
···
 	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)
···
 	struct buffer_head *bh;
 	struct gfs2_log_descriptor *ld;
 	struct gfs2_bufdata *bd1 = NULL, *bd2;
-	unsigned int total = sdp->sd_log_num_buf;
-	unsigned int offset = BUF_OFFSET;
+	unsigned int total;
 	unsigned int limit;
 	unsigned int num;
 	unsigned n;
···
 	limit = buf_limit(sdp);
 	/* for 4k blocks, limit = 503 */
 
+	gfs2_log_lock(sdp);
+	total = sdp->sd_log_num_buf;
 	bd1 = bd2 = list_prepare_entry(bd1, &sdp->sd_log_le_buf, bd_le.le_list);
 	while(total) {
 		num = total;
 		if (total > limit)
 			num = limit;
-		bh = gfs2_log_get_buf(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);
+		gfs2_log_unlock(sdp);
+		bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_METADATA);
+		gfs2_log_lock(sdp);
+		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,
···
 				break;
 		}
 
-		set_buffer_dirty(bh);
-		ll_rw_block(WRITE, 1, &bh);
+		gfs2_log_unlock(sdp);
+		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;
 		}
 
+		BUG_ON(total < num);
 		total -= num;
 	}
+	gfs2_log_unlock(sdp);
 }
 
 static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
···
 	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)
···
 	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;
···
 			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,
···
 	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);
+}
 
-	return rv;
+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;
+
+	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 = sdp->sd_log_num_jdata;
-	unsigned int num, n;
-	__be64 *ptr = NULL;
+	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);
 
-	limit = databuf_limit(sdp);
-
-	/*
-	 * Start writing ordered buffers, write journaled buffers
-	 * into the log along with a header
-	 */
 	gfs2_log_lock(sdp);
-	total_dbuf = sdp->sd_log_num_databuf;
-	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_mapped(bh);
-			set_buffer_dirty(bh);
-			ll_rw_block(WRITE, 1, &bh);
-			bh = 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,
···
 		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);
 }
 
 
···
 
 const struct gfs2_log_operations *gfs2_log_ops[] = {
 	&gfs2_glock_lops,
-	&gfs2_buf_lops,
-	&gfs2_revoke_lops,
-	&gfs2_rg_lops,
 	&gfs2_databuf_lops,
+	&gfs2_buf_lops,
+	&gfs2_rg_lops,
+	&gfs2_revoke_lops,
 	NULL,
 };
 

fs/gfs2/main.c

···
 fail_unregister:
 	unregister_filesystem(&gfs2_fs_type);
 fail:
+	gfs2_glock_exit();
+
 	if (gfs2_bufdata_cachep)
 		kmem_cache_destroy(gfs2_bufdata_cachep);
 
···
 
 static void __exit exit_gfs2_fs(void)
 {
+	gfs2_glock_exit();
 	gfs2_unregister_debugfs();
 	unregister_filesystem(&gfs2_fs_type);
 	unregister_filesystem(&gfs2meta_fs_type);

fs/gfs2/meta_io.c

···
 		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);
 }
 
 /**
···
 	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);
 		}
 
···
 
 	for (x = 0; x < GFS2_MAX_META_HEIGHT; x++) {
 		bh_slot = &ip->i_cache[x];
-		if (!*bh_slot)
-			break;
-		brelse(*bh_slot);
-		*bh_slot = NULL;
+		if (*bh_slot) {
+			brelse(*bh_slot);
+			*bh_slot = NULL;
+		}
 	}
 
 	spin_unlock(&ip->i_spin);

fs/gfs2/meta_io.h

···
 
 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);
 

fs/gfs2/mount.c

···
 	Opt_nosuiddir,
 	Opt_data_writeback,
 	Opt_data_ordered,
+	Opt_err,
 };
 
 static match_table_t tokens = {
···
 	{Opt_suiddir, "suiddir"},
 	{Opt_nosuiddir, "nosuiddir"},
 	{Opt_data_writeback, "data=writeback"},
-	{Opt_data_ordered, "data=ordered"}
+	{Opt_data_ordered, "data=ordered"},
+	{Opt_err, NULL}
 };
 
 /**
···
 		case Opt_data_ordered:
 			args->ar_data = GFS2_DATA_ORDERED;
 			break;
+		case Opt_err:
 		default:
 			fs_info(sdp, "unknown option: %s\n", o);
 			error = -EINVAL;

fs/gfs2/ops_address.c

···
 	error = gfs2_block_map(inode, lblock, 0, bh_result);
 	if (error)
 		return error;
-	if (bh_result->b_blocknr == 0)
+	if (!buffer_mapped(bh_result))
 		return -EIO;
 	return 0;
 }
···
 	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;
 
···
 	return dblock;
 }
 
-static void discard_buffer(struct gfs2_sbd *sdp, struct buffer_head *bh)
+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) {
-		bd->bd_bh = NULL;
-		bh->b_private = NULL;
-		if (!bd->bd_ail && list_empty(&bd->bd_le.le_list))
-			kmem_cache_free(gfs2_bufdata_cachep, 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);
 	}
-	gfs2_log_unlock(sdp);
-
-	lock_buffer(bh);
-	clear_buffer_dirty(bh);
 	bh->b_bdev = NULL;
 	clear_buffer_mapped(bh);
 	clear_buffer_req(bh);
 	clear_buffer_new(bh);
-	clear_buffer_delay(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 *head, *bh, *next;
-	unsigned int curr_off = 0;
+	struct buffer_head *bh, *head;
+	unsigned long pos = 0;
 
 	BUG_ON(!PageLocked(page));
 	if (offset == 0)
 		ClearPageChecked(page);
 	if (!page_has_buffers(page))
-		return;
+		goto out;
 
 	bh = head = page_buffers(page);
 	do {
-		unsigned int next_off = curr_off + bh->b_size;
-		next = bh->b_this_page;
-
-		if (offset <= curr_off)
-			discard_buffer(sdp, bh);
-
-		curr_off = next_off;
-		bh = next;
+		if (offset <= pos)
+			gfs2_discard(sdp, bh);
+		pos += bh->b_size;
+		bh = bh->b_this_page;
 	} while (bh != head);
-
-	if (!offset)
+out:
+	if (offset == 0)
 		try_to_release_page(page, 0);
-
-	return;
 }
 
 /**
···
 }
 
 /**
- * stuck_releasepage - We're stuck in gfs2_releasepage().  Print stuff out.
- * @bh: the buffer we're stuck on
- *
- */
-
-static void stuck_releasepage(struct buffer_head *bh)
-{
-	struct inode *inode = bh->b_page->mapping->host;
-	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
-	struct gfs2_bufdata *bd = bh->b_private;
-	struct gfs2_glock *gl;
-static unsigned limit = 0;
-
-	if (limit > 3)
-		return;
-	limit++;
-
-	fs_warn(sdp, "stuck in gfs2_releasepage() %p\n", inode);
-	fs_warn(sdp, "blkno = %llu, bh->b_count = %d\n",
-		(unsigned long long)bh->b_blocknr, atomic_read(&bh->b_count));
-	fs_warn(sdp, "pinned = %u\n", buffer_pinned(bh));
-	fs_warn(sdp, "bh->b_private = %s\n", (bd) ? "!NULL" : "NULL");
-
-	if (!bd)
-		return;
-
-	gl = bd->bd_gl;
-
-	fs_warn(sdp, "gl = (%u, %llu)\n",
-		gl->gl_name.ln_type, (unsigned long long)gl->gl_name.ln_number);
-
-	fs_warn(sdp, "bd_list_tr = %s, bd_le.le_list = %s\n",
-		(list_empty(&bd->bd_list_tr)) ? "no" : "yes",
-		(list_empty(&bd->bd_le.le_list)) ? "no" : "yes");
-
-	if (gl->gl_ops == &gfs2_inode_glops) {
-		struct gfs2_inode *ip = gl->gl_object;
-		unsigned int x;
-
-		if (!ip)
-			return;
-
-		fs_warn(sdp, "ip = %llu %llu\n",
-			(unsigned long long)ip->i_no_formal_ino,
-			(unsigned long long)ip->i_no_addr);
-
-		for (x = 0; x < GFS2_MAX_META_HEIGHT; x++)
-			fs_warn(sdp, "ip->i_cache[%u] = %s\n",
-				x, (ip->i_cache[x]) ? "!NULL" : "NULL");
-	}
-}
-
-/**
  * gfs2_releasepage - free the metadata associated with a page
  * @page: the page that's being released
  * @gfp_mask: passed from Linux VFS, ignored by us
···
 	struct gfs2_sbd *sdp = aspace->i_sb->s_fs_info;
 	struct buffer_head *bh, *head;
 	struct gfs2_bufdata *bd;
-	unsigned long t = jiffies + gfs2_tune_get(sdp, gt_stall_secs) * HZ;
 
 	if (!page_has_buffers(page))
-		goto out;
+		return 0;
+
+	gfs2_log_lock(sdp);
+	head = bh = page_buffers(page);
+	do {
+		if (atomic_read(&bh->b_count))
+			goto cannot_release;
+		bd = bh->b_private;
+		if (bd && bd->bd_ail)
+			goto cannot_release;
+		gfs2_assert_warn(sdp, !buffer_pinned(bh));
+		gfs2_assert_warn(sdp, !buffer_dirty(bh));
+		bh = bh->b_this_page;
+	} while(bh != head);
+	gfs2_log_unlock(sdp);
 
 	head = bh = page_buffers(page);
 	do {
-		while (atomic_read(&bh->b_count)) {
-			if (!atomic_read(&aspace->i_writecount))
-				return 0;
-
-			if (!(gfp_mask & __GFP_WAIT))
-				return 0;
-
-			if (time_after_eq(jiffies, t)) {
-				stuck_releasepage(bh);
-				/* should we withdraw here? */
-				return 0;
-			}
-
-			yield();
-		}
-
-		gfs2_assert_warn(sdp, !buffer_pinned(bh));
-		gfs2_assert_warn(sdp, !buffer_dirty(bh));
-
 		gfs2_log_lock(sdp);
 		bd = bh->b_private;
 		if (bd) {
 			gfs2_assert_warn(sdp, bd->bd_bh == bh);
 			gfs2_assert_warn(sdp, list_empty(&bd->bd_list_tr));
-			gfs2_assert_warn(sdp, !bd->bd_ail);
-			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);
···
 		bh = bh->b_this_page;
 	} while (bh != head);
 
-out:
 	return try_to_free_buffers(page);
+cannot_release:
+	gfs2_log_unlock(sdp);
+	return 0;
 }
 
 const struct address_space_operations gfs2_file_aops = {

fs/gfs2/ops_export.c

···
 
 	inode = gfs2_inode_lookup(sb, DT_UNKNOWN,
 					inum->no_addr,
-					0);
+					0, 0);
 	if (!inode)
 		goto fail;
 	if (IS_ERR(inode)) {

fs/gfs2/ops_file.c

···
 	int error = 0;
 
 	state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
-	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;
+	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE 
+		| GL_FLOCK;
 
 	mutex_lock(&fp->f_fl_mutex);
 
···
 	if (gl) {
 		if (fl_gh->gh_state == state)
 			goto out;
-		gfs2_glock_hold(gl);
 		flock_lock_file_wait(file,
 				     &(struct file_lock){.fl_type = F_UNLCK});
-		gfs2_glock_dq_uninit(fl_gh);
+		gfs2_glock_dq_wait(fl_gh);
+		gfs2_holder_reinit(state, flags, fl_gh);
 	} else {
 		error = gfs2_glock_get(GFS2_SB(&ip->i_inode),
 				      ip->i_no_addr, &gfs2_flock_glops,
 				      CREATE, &gl);
 		if (error)
 			goto out;
+		gfs2_holder_init(gl, state, flags, fl_gh);
+		gfs2_glock_put(gl);
 	}
-
-	gfs2_holder_init(gl, state, flags, fl_gh);
-	gfs2_glock_put(gl);
-
 	error = gfs2_glock_nq(fl_gh);
 	if (error) {
 		gfs2_holder_uninit(fl_gh);

fs/gfs2/ops_fstype.c

···
 #include "lm.h"
 #include "mount.h"
 #include "ops_fstype.h"
+#include "ops_dentry.h"
 #include "ops_super.h"
 #include "recovery.h"
 #include "rgrp.h"
 #include "super.h"
 #include "sys.h"
 #include "util.h"
+#include "log.h"
 
 #define DO 0
 #define UNDO 1
-
-extern struct dentry_operations gfs2_dops;
 
 static struct gfs2_sbd *init_sbd(struct super_block *sb)
 {
···
 	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);
 
···
 	snprintf(sdp->sd_proto_name, GFS2_FSNAME_LEN, "%s", proto);
 	snprintf(sdp->sd_table_name, GFS2_FSNAME_LEN, "%s", table);
 
-	while ((table = strchr(sdp->sd_table_name, '/')))
+	table = sdp->sd_table_name;
+	while ((table = strchr(table, '/')))
 		*table = '_';
 
 out:
···
 
 	if (undo)
 		goto fail_trans;
-
-	p = kthread_run(gfs2_scand, sdp, "gfs2_scand");
-	error = IS_ERR(p);
-	if (error) {
-		fs_err(sdp, "can't start scand thread: %d\n", error);
-		return error;
-	}
-	sdp->sd_scand_process = p;
 
 	for (sdp->sd_glockd_num = 0;
 	     sdp->sd_glockd_num < sdp->sd_args.ar_num_glockd;
···
 	while (sdp->sd_glockd_num--)
 		kthread_stop(sdp->sd_glockd_process[sdp->sd_glockd_num]);
 
-	kthread_stop(sdp->sd_scand_process);
 	return error;
 }
 
 static inline struct inode *gfs2_lookup_root(struct super_block *sb,
 					     u64 no_addr)
 {
-	return gfs2_inode_lookup(sb, DT_DIR, no_addr, 0);
+	return gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
 }
 
 static int init_sb(struct gfs2_sbd *sdp, int silent, int undo)
···
 		fs_err(sdp, "can't get root dentry\n");
 		error = -ENOMEM;
 		iput(inode);
-	}
-	sb->s_root->d_op = &gfs2_dops;
+	} else
+		sb->s_root->d_op = &gfs2_dops;
+	
 out:
 	gfs2_glock_dq_uninit(&sb_gh);
 	return error;
···
 
 		ip = GFS2_I(sdp->sd_jdesc->jd_inode);
 		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
-					   LM_FLAG_NOEXP | GL_EXACT,
+					   LM_FLAG_NOEXP | GL_EXACT | GL_NOCACHE,
 					   &sdp->sd_jinode_gh);
 		if (error) {
 			fs_err(sdp, "can't acquire journal inode glock: %d\n",
···
 	struct nameidata nd;
 	struct file_system_type *fstype;
 	struct super_block *sb = NULL, *s;
-	struct list_head *l;
 	int error;
 
 	error = path_lookup(dev_name, LOOKUP_FOLLOW, &nd);
···
 	error = vfs_getattr(nd.mnt, nd.dentry, &stat);
 
 	fstype = get_fs_type("gfs2");
-	list_for_each(l, &fstype->fs_supers) {
-		s = list_entry(l, struct super_block, s_instances);
+	list_for_each_entry(s, &fstype->fs_supers, s_instances) {
 		if ((S_ISBLK(stat.mode) && s->s_dev == stat.rdev) ||
 		    (S_ISDIR(stat.mode) && s == nd.dentry->d_inode->i_sb)) {
 			sb = s;
···
 		error = -ENOENT;
 		goto error;
 	}
-	sdp = (struct gfs2_sbd*) sb->s_fs_info;
+	sdp = sb->s_fs_info;
 	if (sdp->sd_vfs_meta) {
 		printk(KERN_WARNING "GFS2: gfs2meta mount already exists\n");
 		error = -EBUSY;
···
 
 static void gfs2_kill_sb(struct super_block *sb)
 {
-	gfs2_delete_debugfs_file(sb->s_fs_info);
+	if (sb->s_fs_info) {
+		gfs2_delete_debugfs_file(sb->s_fs_info);
+		gfs2_meta_syncfs(sb->s_fs_info);
+	}
 	kill_block_super(sb);
 }
 

fs/gfs2/ops_inode.c

···
 			mark_inode_dirty(inode);
 			break;
 		} else if (PTR_ERR(inode) != -EEXIST ||
-			   (nd->intent.open.flags & O_EXCL)) {
+			   (nd && (nd->intent.open.flags & O_EXCL))) {
 			gfs2_holder_uninit(ghs);
 			return PTR_ERR(inode);
 		}
···
 	gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2);
 
 
-	error = gfs2_glock_nq_m(3, ghs);
+	error = gfs2_glock_nq(ghs); /* parent */
 	if (error)
-		goto out;
+		goto out_parent;
+
+	error = gfs2_glock_nq(ghs + 1); /* child */
+	if (error)
+		goto out_child;
+
+	error = gfs2_glock_nq(ghs + 2); /* rgrp */
+	if (error)
+		goto out_rgrp;
 
 	error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
 	if (error)
-		goto out_gunlock;
+		goto out_rgrp;
 
 	error = gfs2_trans_begin(sdp, 2*RES_DINODE + RES_LEAF + RES_RG_BIT, 0);
 	if (error)
-		goto out_gunlock;
+		goto out_rgrp;
 
 	error = gfs2_dir_del(dip, &dentry->d_name);
         if (error)
···
 
 out_end_trans:
 	gfs2_trans_end(sdp);
-out_gunlock:
-	gfs2_glock_dq_m(3, ghs);
-out:
-	gfs2_holder_uninit(ghs);
-	gfs2_holder_uninit(ghs + 1);
+	gfs2_glock_dq(ghs + 2);
+out_rgrp:
 	gfs2_holder_uninit(ghs + 2);
+	gfs2_glock_dq(ghs + 1);
+out_child:
+	gfs2_holder_uninit(ghs + 1);
+	gfs2_glock_dq(ghs);
+out_parent:
+	gfs2_holder_uninit(ghs);
 	gfs2_glock_dq_uninit(&ri_gh);
 	return error;
 }
···
 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;
 	}
 

fs/gfs2/ops_super.c

···
 	kthread_stop(sdp->sd_recoverd_process);
 	while (sdp->sd_glockd_num--)
 		kthread_stop(sdp->sd_glockd_process[sdp->sd_glockd_num]);
-	kthread_stop(sdp->sd_scand_process);
 
 	if (!(sb->s_flags & MS_RDONLY)) {
 		error = gfs2_make_fs_ro(sdp);
···
 	}
 
 	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);

fs/gfs2/quota.c

···
 	u64 qu_limit;
 	u64 qu_warn;
 	s64 qu_value;
+	u32 qu_ll_next;
 };
 
 struct gfs2_quota_change_host {
···
 	qu->qu_limit = be64_to_cpu(str->qu_limit);
 	qu->qu_warn = be64_to_cpu(str->qu_warn);
 	qu->qu_value = be64_to_cpu(str->qu_value);
+	qu->qu_ll_next = be32_to_cpu(str->qu_ll_next);
 }
 
 static void gfs2_quota_out(const struct gfs2_quota_host *qu, void *buf)
···
 	str->qu_limit = cpu_to_be64(qu->qu_limit);
 	str->qu_warn = cpu_to_be64(qu->qu_warn);
 	str->qu_value = cpu_to_be64(qu->qu_value);
+	str->qu_ll_next = cpu_to_be32(qu->qu_ll_next);
 	memset(&str->qu_reserved, 0, sizeof(str->qu_reserved));
 }
 
···
 	s64 value;
 	int err = -EIO;
 
+	if (gfs2_is_stuffed(ip)) {
+		struct gfs2_alloc *al = NULL;
+		al = gfs2_alloc_get(ip);
+		/* just request 1 blk */
+		al->al_requested = 1;
+		gfs2_inplace_reserve(ip);
+		gfs2_unstuff_dinode(ip, NULL);
+		gfs2_inplace_release(ip);
+		gfs2_alloc_put(ip);
+	}
 	page = grab_cache_page(mapping, index);
 	if (!page)
 		return -ENOMEM;

fs/gfs2/recovery.c

···
 		};
 
 		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
-					   LM_FLAG_NOEXP, &ji_gh);
+					   LM_FLAG_NOEXP | GL_NOCACHE, &ji_gh);
 		if (error)
 			goto fail_gunlock_j;
 	} else {

fs/gfs2/rgrp.c

···
 #include "inode.h"
 
 #define BFITNOENT ((u32)~0)
+#define NO_BLOCK ((u64)~0)
 
 /*
  * These routines are used by the resource group routines (rgrp.c)
···
  * @buffer: the buffer that holds the bitmaps
  * @buflen: the length (in bytes) of the buffer
  * @goal: start search at this block's bit-pair (within @buffer)
- * @old_state: GFS2_BLKST_XXX the state of the block we're looking for;
- *       bit 0 = alloc(1)/free(0), bit 1 = meta(1)/data(0)
+ * @old_state: GFS2_BLKST_XXX the state of the block we're looking for.
  *
  * Scope of @goal and returned block number is only within this bitmap buffer,
  * not entire rgrp or filesystem.  @buffer will be offset from the actual
···
 	byte = buffer + (goal / GFS2_NBBY);
 	bit = (goal % GFS2_NBBY) * GFS2_BIT_SIZE;
 	end = buffer + buflen;
-	alloc = (old_state & 1) ? 0 : 0x55;
+	alloc = (old_state == GFS2_BLKST_FREE) ? 0x55 : 0;
 
 	while (byte < end) {
+		/* If we're looking for a free block we can eliminate all
+		   bitmap settings with 0x55, which represents four data
+		   blocks in a row.  If we're looking for a data block, we can
+		   eliminate 0x00 which corresponds to four free blocks. */
 		if ((*byte & 0x55) == alloc) {
 			blk += (8 - bit) >> 1;
 
···
 static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked)
 {
 	struct inode *inode;
-	u32 goal = 0;
+	u32 goal = 0, block;
 	u64 no_addr;
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
 
 	for(;;) {
 		if (goal >= rgd->rd_data)
 			break;
-		goal = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED,
-				    GFS2_BLKST_UNLINKED);
-		if (goal == BFITNOENT)
+		down_write(&sdp->sd_log_flush_lock);
+		block = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED,
+				     GFS2_BLKST_UNLINKED);
+		up_write(&sdp->sd_log_flush_lock);
+		if (block == BFITNOENT)
 			break;
-		no_addr = goal + rgd->rd_data0;
+		/* rgblk_search can return a block < goal, so we need to
+		   keep it marching forward. */
+		no_addr = block + rgd->rd_data0;
 		goal++;
-		if (no_addr < *last_unlinked)
+		if (*last_unlinked != NO_BLOCK && no_addr <= *last_unlinked)
 			continue;
 		*last_unlinked = no_addr;
 		inode = gfs2_inode_lookup(rgd->rd_sbd->sd_vfs, DT_UNKNOWN,
-					  no_addr, -1);
+					  no_addr, -1, 1);
 		if (!IS_ERR(inode))
 			return inode;
 	}
···
 	struct gfs2_alloc *al = &ip->i_alloc;
 	struct inode *inode;
 	int error = 0;
-	u64 last_unlinked = 0;
+	u64 last_unlinked = NO_BLOCK;
 
 	if (gfs2_assert_warn(sdp, al->al_requested))
 		return -EINVAL;
···
 	   allocatable block anywhere else, we want to be able wrap around and
 	   search in the first part of our first-searched bit block.  */
 	for (x = 0; x <= length; x++) {
-		if (bi->bi_clone)
+		/* The GFS2_BLKST_UNLINKED state doesn't apply to the clone
+		   bitmaps, so we must search the originals for that. */
+		if (old_state != GFS2_BLKST_UNLINKED && bi->bi_clone)
 			blk = gfs2_bitfit(rgd, bi->bi_clone + bi->bi_offset,
 					  bi->bi_len, goal, old_state);
 		else
···
 		goal = 0;
 	}
 
-	if (old_state != new_state) {
-		gfs2_assert_withdraw(rgd->rd_sbd, blk != BFITNOENT);
-
+	if (blk != BFITNOENT && old_state != new_state) {
 		gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1);
 		gfs2_setbit(rgd, bi->bi_bh->b_data + bi->bi_offset,
 			    bi->bi_len, blk, new_state);

fs/gfs2/super.c

···
 	gt->gt_incore_log_blocks = 1024;
 	gt->gt_log_flush_secs = 60;
 	gt->gt_jindex_refresh_secs = 60;
-	gt->gt_scand_secs = 15;
 	gt->gt_recoverd_secs = 60;
 	gt->gt_logd_secs = 1;
 	gt->gt_quotad_secs = 5;

fs/gfs2/sys.c

···
 TUNE_ATTR(quota_cache_secs, 1);
 TUNE_ATTR(stall_secs, 1);
 TUNE_ATTR(statfs_quantum, 1);
-TUNE_ATTR_DAEMON(scand_secs, scand_process);
 TUNE_ATTR_DAEMON(recoverd_secs, recoverd_process);
 TUNE_ATTR_DAEMON(logd_secs, logd_process);
 TUNE_ATTR_DAEMON(quotad_secs, quotad_process);
···
 	&tune_attr_quota_cache_secs.attr,
 	&tune_attr_stall_secs.attr,
 	&tune_attr_statfs_quantum.attr,
-	&tune_attr_scand_secs.attr,
 	&tune_attr_recoverd_secs.attr,
 	&tune_attr_logd_secs.attr,
 	&tune_attr_quotad_secs.attr,

fs/gfs2/trans.c

···
 	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;
···
 
 	if (found) {
 		struct gfs2_trans *tr = current->journal_info;
-		kfree(rv);
+		kmem_cache_free(gfs2_bufdata_cachep, bd);
 		tr->tr_num_revoke_rm++;
 	}
 }

fs/gfs2/trans.h

···
 
 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);
 

include/linux/gfs2_ondisk.h

···
 };
 
 /*
+ * quota linked list: user quotas and group quotas form two separate 
+ * singly linked lists. ll_next stores uids or gids of next quotas in the 
+ * linked list.
+
+Given the uid/gid, how to calculate the quota file offsets for the corresponding
+gfs2_quota structures on disk:
+
+for user quotas, given uid,
+offset = uid * sizeof(struct gfs2_quota);
+
+for group quotas, given gid,
+offset = (gid * sizeof(struct gfs2_quota)) + sizeof(struct gfs2_quota);
+
+
+  uid:0   gid:0       uid:12   gid:12      uid:17   gid:17     uid:5142 gid:5142
++-------+-------+    +-------+-------+    +-------+- - - -+    +- - - -+-------+
+| valid | valid | :: | valid | valid | :: | valid | inval | :: | inval | valid |
++-------+-------+    +-------+-------+    +-------+- - - -+    +- - - -+-------+
+next:12   next:12    next:17 next:5142    next:NULL                    next:NULL
+    |       |            |       |            |<-- user quota list         |
+     \______|___________/ \______|___________/         group quota list -->|
+            |                    |                                         |
+             \__________________/ \_______________________________________/
+
+*/
+
+/*
  * quota structure
  */
 
···
 	__be64 qu_limit;
 	__be64 qu_warn;
 	__be64 qu_value;
-	__u8 qu_reserved[64];
+	__be32 qu_ll_next; /* location of next quota in list */
+	__u8 qu_reserved[60];
 };
 
 /*