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

* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6: (292 commits)
  [GFS2] Fix endian bug for de_type
  [GFS2] Initialize SELinux extended attributes at inode creation time.
  [GFS2] Move logging code into log.c (mostly)
  [GFS2] Mark nlink cleared so VFS sees it happen
  [GFS2] Two redundant casts removed
  [GFS2] Remove uneeded endian conversion
  [GFS2] Remove duplicate sb reading code
  [GFS2] Mark metadata reads for blktrace
  [GFS2] Remove iflags.h, use FS_
  [GFS2] Fix code style/indent in ops_file.c
  [GFS2] streamline-generic_file_-interfaces-and-filemap gfs fix
  [GFS2] Remove readv/writev methods and use aio_read/aio_write instead (gfs bits)
  [GFS2] inode-diet: Eliminate i_blksize from the inode structure
  [GFS2] inode_diet: Replace inode.u.generic_ip with inode.i_private (gfs)
  [GFS2] Fix typo in last patch
  [GFS2] Fix direct i/o logic in filemap.c
  [GFS2] Fix bug in Makefiles for lock modules
  [GFS2] Remove (extra) fs_subsys declaration
  [GFS2/DLM] Fix trailing whitespace
  [GFS2] Tidy up meta_io code
  ...

CREDITS

@@ -3578,11 +3578,11 @@ S: Fargo, North Dakota 58122
 S: USA
 
 N: Steven Whitehouse
-E: SteveW@ACM.org
+E: steve@chygwyn.com
 W: http://www.chygwyn.com/~steve
-D: Linux DECnet project: http://www.sucs.swan.ac.uk/~rohan/DECnet/index.html
+D: Linux DECnet project
 D: Minor debugging of other networking protocols.
-D: Misc bug fixes and filesystem development
+D: Misc bug fixes and GFS2 filesystem development
 
 N: Hans-Joachim Widmaier
 E: hjw@zvw.de

Documentation/filesystems/gfs2.txt

@@ -0,0 +1,43 @@
+Global File System
+------------------
+
+http://sources.redhat.com/cluster/
+
+GFS is a cluster file system. It allows a cluster of computers to
+simultaneously use a block device that is shared between them (with FC,
+iSCSI, NBD, etc).  GFS reads and writes to the block device like a local
+file system, but also uses a lock module to allow the computers coordinate
+their I/O so file system consistency is maintained.  One of the nifty
+features of GFS is perfect consistency -- changes made to the file system
+on one machine show up immediately on all other machines in the cluster.
+
+GFS uses interchangable inter-node locking mechanisms.  Different lock
+modules can plug into GFS and each file system selects the appropriate
+lock module at mount time.  Lock modules include:
+
+  lock_nolock -- allows gfs to be used as a local file system
+
+  lock_dlm -- uses a distributed lock manager (dlm) for inter-node locking
+  The dlm is found at linux/fs/dlm/
+
+In addition to interfacing with an external locking manager, a gfs lock
+module is responsible for interacting with external cluster management
+systems.  Lock_dlm depends on user space cluster management systems found
+at the URL above.
+
+To use gfs as a local file system, no external clustering systems are
+needed, simply:
+
+  $ mkfs -t gfs2 -p lock_nolock -j 1 /dev/block_device
+  $ mount -t gfs2 /dev/block_device /dir
+
+GFS2 is not on-disk compatible with previous versions of GFS.
+
+The following man pages can be found at the URL above:
+  gfs2_fsck	to repair a filesystem
+  gfs2_grow	to expand a filesystem online
+  gfs2_jadd	to add journals to a filesystem online
+  gfs2_tool	to manipulate, examine and tune a filesystem
+  gfs2_quota	to examine and change quota values in a filesystem
+  mount.gfs2	to help mount(8) mount a filesystem
+  mkfs.gfs2	to make a filesystem

MAINTAINERS

@@ -898,6 +898,16 @@ M:	jack@suse.cz
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 
+DISTRIBUTED LOCK MANAGER
+P:	Patrick Caulfield
+M:	pcaulfie@redhat.com
+P:	David Teigland
+M:	teigland@redhat.com
+L:	cluster-devel@redhat.com
+W:	http://sources.redhat.com/cluster/
+T:	git kernel.org:/pub/scm/linux/kernel/git/steve/gfs-2.6.git
+S:	Supported
+
 DAVICOM FAST ETHERNET (DMFE) NETWORK DRIVER
 P:	Tobias Ringstrom
 M:	tori@unhappy.mine.nu
@@ -1173,6 +1183,14 @@ M:	khc@pm.waw.pl
 W:	http://www.kernel.org/pub/linux/utils/net/hdlc/
 S:	Maintained
 
+GFS2 FILE SYSTEM
+P:	Steven Whitehouse
+M:	swhiteho@redhat.com
+L:	cluster-devel@redhat.com
+W:	http://sources.redhat.com/cluster/
+T:	git kernel.org:/pub/scm/linux/kernel/git/steve/gfs-2.6.git
+S:	Supported
+
 GIGASET ISDN DRIVERS
 P:	Hansjoerg Lipp
 M:	hjlipp@web.de

fs/Kconfig

@@ -325,6 +325,7 @@ config FS_POSIX_ACL
 	default n
 
 source "fs/xfs/Kconfig"
+source "fs/gfs2/Kconfig"
 
 config OCFS2_FS
 	tristate "OCFS2 file system support"
@@ -1995,6 +1996,7 @@ endmenu
 endif
 
 source "fs/nls/Kconfig"
+source "fs/dlm/Kconfig"
 
 endmenu
 

fs/Makefile

@@ -57,6 +57,7 @@ obj-$(CONFIG_CONFIGFS_FS)	+= configfs/
 obj-y				+= devpts/
 
 obj-$(CONFIG_PROFILING)		+= dcookies.o
+obj-$(CONFIG_DLM)		+= dlm/
  
 # Do not add any filesystems before this line
 obj-$(CONFIG_REISERFS_FS)	+= reiserfs/
@@ -110,3 +111,4 @@ obj-$(CONFIG_HOSTFS)		+= hostfs/
 obj-$(CONFIG_HPPFS)		+= hppfs/
 obj-$(CONFIG_DEBUG_FS)		+= debugfs/
 obj-$(CONFIG_OCFS2_FS)		+= ocfs2/
+obj-$(CONFIG_GFS2_FS)           += gfs2/

fs/configfs/item.c

@@ -224,4 +224,4 @@ EXPORT_SYMBOL(config_item_init);
 EXPORT_SYMBOL(config_group_init);
 EXPORT_SYMBOL(config_item_get);
 EXPORT_SYMBOL(config_item_put);
-
+EXPORT_SYMBOL(config_group_find_obj);

fs/dlm/Kconfig

@@ -0,0 +1,21 @@
+menu "Distributed Lock Manager"
+	depends on INET && EXPERIMENTAL
+
+config DLM
+	tristate "Distributed Lock Manager (DLM)"
+	depends on IPV6 || IPV6=n
+	depends on IP_SCTP
+	select CONFIGFS_FS
+	help
+	A general purpose distributed lock manager for kernel or userspace
+	applications.
+
+config DLM_DEBUG
+	bool "DLM debugging"
+	depends on DLM
+	help
+	Under the debugfs mount point, the name of each lockspace will
+	appear as a file in the "dlm" directory.  The output is the
+	list of resource and locks the local node knows about.
+
+endmenu

fs/dlm/Makefile

@@ -0,0 +1,19 @@
+obj-$(CONFIG_DLM) +=		dlm.o
+dlm-y :=			ast.o \
+				config.o \
+				dir.o \
+				lock.o \
+				lockspace.o \
+				lowcomms.o \
+				main.o \
+				member.o \
+				memory.o \
+				midcomms.o \
+				rcom.o \
+				recover.o \
+				recoverd.o \
+				requestqueue.o \
+				user.o \
+				util.o
+dlm-$(CONFIG_DLM_DEBUG) +=	debug_fs.o
+

fs/dlm/ast.c

@@ -0,0 +1,173 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lock.h"
+#include "user.h"
+
+#define WAKE_ASTS  0
+
+static struct list_head		ast_queue;
+static spinlock_t		ast_queue_lock;
+static struct task_struct *	astd_task;
+static unsigned long		astd_wakeflags;
+static struct mutex		astd_running;
+
+
+void dlm_del_ast(struct dlm_lkb *lkb)
+{
+	spin_lock(&ast_queue_lock);
+	if (lkb->lkb_ast_type & (AST_COMP | AST_BAST))
+		list_del(&lkb->lkb_astqueue);
+	spin_unlock(&ast_queue_lock);
+}
+
+void dlm_add_ast(struct dlm_lkb *lkb, int type)
+{
+	if (lkb->lkb_flags & DLM_IFL_USER) {
+		dlm_user_add_ast(lkb, type);
+		return;
+	}
+	DLM_ASSERT(lkb->lkb_astaddr != DLM_FAKE_USER_AST, dlm_print_lkb(lkb););
+
+	spin_lock(&ast_queue_lock);
+	if (!(lkb->lkb_ast_type & (AST_COMP | AST_BAST))) {
+		kref_get(&lkb->lkb_ref);
+		list_add_tail(&lkb->lkb_astqueue, &ast_queue);
+	}
+	lkb->lkb_ast_type |= type;
+	spin_unlock(&ast_queue_lock);
+
+	set_bit(WAKE_ASTS, &astd_wakeflags);
+	wake_up_process(astd_task);
+}
+
+static void process_asts(void)
+{
+	struct dlm_ls *ls = NULL;
+	struct dlm_rsb *r = NULL;
+	struct dlm_lkb *lkb;
+	void (*cast) (long param);
+	void (*bast) (long param, int mode);
+	int type = 0, found, bmode;
+
+	for (;;) {
+		found = 0;
+		spin_lock(&ast_queue_lock);
+		list_for_each_entry(lkb, &ast_queue, lkb_astqueue) {
+			r = lkb->lkb_resource;
+			ls = r->res_ls;
+
+			if (dlm_locking_stopped(ls))
+				continue;
+
+			list_del(&lkb->lkb_astqueue);
+			type = lkb->lkb_ast_type;
+			lkb->lkb_ast_type = 0;
+			found = 1;
+			break;
+		}
+		spin_unlock(&ast_queue_lock);
+
+		if (!found)
+			break;
+
+		cast = lkb->lkb_astaddr;
+		bast = lkb->lkb_bastaddr;
+		bmode = lkb->lkb_bastmode;
+
+		if ((type & AST_COMP) && cast)
+			cast(lkb->lkb_astparam);
+
+		/* FIXME: Is it safe to look at lkb_grmode here
+		   without doing a lock_rsb() ?
+		   Look at other checks in v1 to avoid basts. */
+
+		if ((type & AST_BAST) && bast)
+			if (!dlm_modes_compat(lkb->lkb_grmode, bmode))
+				bast(lkb->lkb_astparam, bmode);
+
+		/* this removes the reference added by dlm_add_ast
+		   and may result in the lkb being freed */
+		dlm_put_lkb(lkb);
+
+		schedule();
+	}
+}
+
+static inline int no_asts(void)
+{
+	int ret;
+
+	spin_lock(&ast_queue_lock);
+	ret = list_empty(&ast_queue);
+	spin_unlock(&ast_queue_lock);
+	return ret;
+}
+
+static int dlm_astd(void *data)
+{
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (!test_bit(WAKE_ASTS, &astd_wakeflags))
+			schedule();
+		set_current_state(TASK_RUNNING);
+
+		mutex_lock(&astd_running);
+		if (test_and_clear_bit(WAKE_ASTS, &astd_wakeflags))
+			process_asts();
+		mutex_unlock(&astd_running);
+	}
+	return 0;
+}
+
+void dlm_astd_wake(void)
+{
+	if (!no_asts()) {
+		set_bit(WAKE_ASTS, &astd_wakeflags);
+		wake_up_process(astd_task);
+	}
+}
+
+int dlm_astd_start(void)
+{
+	struct task_struct *p;
+	int error = 0;
+
+	INIT_LIST_HEAD(&ast_queue);
+	spin_lock_init(&ast_queue_lock);
+	mutex_init(&astd_running);
+
+	p = kthread_run(dlm_astd, NULL, "dlm_astd");
+	if (IS_ERR(p))
+		error = PTR_ERR(p);
+	else
+		astd_task = p;
+	return error;
+}
+
+void dlm_astd_stop(void)
+{
+	kthread_stop(astd_task);
+}
+
+void dlm_astd_suspend(void)
+{
+	mutex_lock(&astd_running);
+}
+
+void dlm_astd_resume(void)
+{
+	mutex_unlock(&astd_running);
+}
+

fs/dlm/ast.h

@@ -0,0 +1,26 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __ASTD_DOT_H__
+#define __ASTD_DOT_H__
+
+void dlm_add_ast(struct dlm_lkb *lkb, int type);
+void dlm_del_ast(struct dlm_lkb *lkb);
+
+void dlm_astd_wake(void);
+int dlm_astd_start(void);
+void dlm_astd_stop(void);
+void dlm_astd_suspend(void);
+void dlm_astd_resume(void);
+
+#endif
+

fs/dlm/config.c

@@ -0,0 +1,789 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/configfs.h>
+#include <net/sock.h>
+
+#include "config.h"
+#include "lowcomms.h"
+
+/*
+ * /config/dlm/<cluster>/spaces/<space>/nodes/<node>/nodeid
+ * /config/dlm/<cluster>/spaces/<space>/nodes/<node>/weight
+ * /config/dlm/<cluster>/comms/<comm>/nodeid
+ * /config/dlm/<cluster>/comms/<comm>/local
+ * /config/dlm/<cluster>/comms/<comm>/addr
+ * The <cluster> level is useless, but I haven't figured out how to avoid it.
+ */
+
+static struct config_group *space_list;
+static struct config_group *comm_list;
+static struct comm *local_comm;
+
+struct clusters;
+struct cluster;
+struct spaces;
+struct space;
+struct comms;
+struct comm;
+struct nodes;
+struct node;
+
+static struct config_group *make_cluster(struct config_group *, const char *);
+static void drop_cluster(struct config_group *, struct config_item *);
+static void release_cluster(struct config_item *);
+static struct config_group *make_space(struct config_group *, const char *);
+static void drop_space(struct config_group *, struct config_item *);
+static void release_space(struct config_item *);
+static struct config_item *make_comm(struct config_group *, const char *);
+static void drop_comm(struct config_group *, struct config_item *);
+static void release_comm(struct config_item *);
+static struct config_item *make_node(struct config_group *, const char *);
+static void drop_node(struct config_group *, struct config_item *);
+static void release_node(struct config_item *);
+
+static ssize_t show_comm(struct config_item *i, struct configfs_attribute *a,
+			 char *buf);
+static ssize_t store_comm(struct config_item *i, struct configfs_attribute *a,
+			  const char *buf, size_t len);
+static ssize_t show_node(struct config_item *i, struct configfs_attribute *a,
+			 char *buf);
+static ssize_t store_node(struct config_item *i, struct configfs_attribute *a,
+			  const char *buf, size_t len);
+
+static ssize_t comm_nodeid_read(struct comm *cm, char *buf);
+static ssize_t comm_nodeid_write(struct comm *cm, const char *buf, size_t len);
+static ssize_t comm_local_read(struct comm *cm, char *buf);
+static ssize_t comm_local_write(struct comm *cm, const char *buf, size_t len);
+static ssize_t comm_addr_write(struct comm *cm, const char *buf, size_t len);
+static ssize_t node_nodeid_read(struct node *nd, char *buf);
+static ssize_t node_nodeid_write(struct node *nd, const char *buf, size_t len);
+static ssize_t node_weight_read(struct node *nd, char *buf);
+static ssize_t node_weight_write(struct node *nd, const char *buf, size_t len);
+
+enum {
+	COMM_ATTR_NODEID = 0,
+	COMM_ATTR_LOCAL,
+	COMM_ATTR_ADDR,
+};
+
+struct comm_attribute {
+	struct configfs_attribute attr;
+	ssize_t (*show)(struct comm *, char *);
+	ssize_t (*store)(struct comm *, const char *, size_t);
+};
+
+static struct comm_attribute comm_attr_nodeid = {
+	.attr   = { .ca_owner = THIS_MODULE,
+                    .ca_name = "nodeid",
+                    .ca_mode = S_IRUGO | S_IWUSR },
+	.show   = comm_nodeid_read,
+	.store  = comm_nodeid_write,
+};
+
+static struct comm_attribute comm_attr_local = {
+	.attr   = { .ca_owner = THIS_MODULE,
+                    .ca_name = "local",
+                    .ca_mode = S_IRUGO | S_IWUSR },
+	.show   = comm_local_read,
+	.store  = comm_local_write,
+};
+
+static struct comm_attribute comm_attr_addr = {
+	.attr   = { .ca_owner = THIS_MODULE,
+                    .ca_name = "addr",
+                    .ca_mode = S_IRUGO | S_IWUSR },
+	.store  = comm_addr_write,
+};
+
+static struct configfs_attribute *comm_attrs[] = {
+	[COMM_ATTR_NODEID] = &comm_attr_nodeid.attr,
+	[COMM_ATTR_LOCAL] = &comm_attr_local.attr,
+	[COMM_ATTR_ADDR] = &comm_attr_addr.attr,
+	NULL,
+};
+
+enum {
+	NODE_ATTR_NODEID = 0,
+	NODE_ATTR_WEIGHT,
+};
+
+struct node_attribute {
+	struct configfs_attribute attr;
+	ssize_t (*show)(struct node *, char *);
+	ssize_t (*store)(struct node *, const char *, size_t);
+};
+
+static struct node_attribute node_attr_nodeid = {
+	.attr   = { .ca_owner = THIS_MODULE,
+                    .ca_name = "nodeid",
+                    .ca_mode = S_IRUGO | S_IWUSR },
+	.show   = node_nodeid_read,
+	.store  = node_nodeid_write,
+};
+
+static struct node_attribute node_attr_weight = {
+	.attr   = { .ca_owner = THIS_MODULE,
+                    .ca_name = "weight",
+                    .ca_mode = S_IRUGO | S_IWUSR },
+	.show   = node_weight_read,
+	.store  = node_weight_write,
+};
+
+static struct configfs_attribute *node_attrs[] = {
+	[NODE_ATTR_NODEID] = &node_attr_nodeid.attr,
+	[NODE_ATTR_WEIGHT] = &node_attr_weight.attr,
+	NULL,
+};
+
+struct clusters {
+	struct configfs_subsystem subsys;
+};
+
+struct cluster {
+	struct config_group group;
+};
+
+struct spaces {
+	struct config_group ss_group;
+};
+
+struct space {
+	struct config_group group;
+	struct list_head members;
+	struct mutex members_lock;
+	int members_count;
+};
+
+struct comms {
+	struct config_group cs_group;
+};
+
+struct comm {
+	struct config_item item;
+	int nodeid;
+	int local;
+	int addr_count;
+	struct sockaddr_storage *addr[DLM_MAX_ADDR_COUNT];
+};
+
+struct nodes {
+	struct config_group ns_group;
+};
+
+struct node {
+	struct config_item item;
+	struct list_head list; /* space->members */
+	int nodeid;
+	int weight;
+};
+
+static struct configfs_group_operations clusters_ops = {
+	.make_group = make_cluster,
+	.drop_item = drop_cluster,
+};
+
+static struct configfs_item_operations cluster_ops = {
+	.release = release_cluster,
+};
+
+static struct configfs_group_operations spaces_ops = {
+	.make_group = make_space,
+	.drop_item = drop_space,
+};
+
+static struct configfs_item_operations space_ops = {
+	.release = release_space,
+};
+
+static struct configfs_group_operations comms_ops = {
+	.make_item = make_comm,
+	.drop_item = drop_comm,
+};
+
+static struct configfs_item_operations comm_ops = {
+	.release = release_comm,
+	.show_attribute = show_comm,
+	.store_attribute = store_comm,
+};
+
+static struct configfs_group_operations nodes_ops = {
+	.make_item = make_node,
+	.drop_item = drop_node,
+};
+
+static struct configfs_item_operations node_ops = {
+	.release = release_node,
+	.show_attribute = show_node,
+	.store_attribute = store_node,
+};
+
+static struct config_item_type clusters_type = {
+	.ct_group_ops = &clusters_ops,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct config_item_type cluster_type = {
+	.ct_item_ops = &cluster_ops,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct config_item_type spaces_type = {
+	.ct_group_ops = &spaces_ops,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct config_item_type space_type = {
+	.ct_item_ops = &space_ops,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct config_item_type comms_type = {
+	.ct_group_ops = &comms_ops,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct config_item_type comm_type = {
+	.ct_item_ops = &comm_ops,
+	.ct_attrs = comm_attrs,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct config_item_type nodes_type = {
+	.ct_group_ops = &nodes_ops,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct config_item_type node_type = {
+	.ct_item_ops = &node_ops,
+	.ct_attrs = node_attrs,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct cluster *to_cluster(struct config_item *i)
+{
+	return i ? container_of(to_config_group(i), struct cluster, group):NULL;
+}
+
+static struct space *to_space(struct config_item *i)
+{
+	return i ? container_of(to_config_group(i), struct space, group) : NULL;
+}
+
+static struct comm *to_comm(struct config_item *i)
+{
+	return i ? container_of(i, struct comm, item) : NULL;
+}
+
+static struct node *to_node(struct config_item *i)
+{
+	return i ? container_of(i, struct node, item) : NULL;
+}
+
+static struct config_group *make_cluster(struct config_group *g,
+					 const char *name)
+{
+	struct cluster *cl = NULL;
+	struct spaces *sps = NULL;
+	struct comms *cms = NULL;
+	void *gps = NULL;
+
+	cl = kzalloc(sizeof(struct cluster), GFP_KERNEL);
+	gps = kcalloc(3, sizeof(struct config_group *), GFP_KERNEL);
+	sps = kzalloc(sizeof(struct spaces), GFP_KERNEL);
+	cms = kzalloc(sizeof(struct comms), GFP_KERNEL);
+
+	if (!cl || !gps || !sps || !cms)
+		goto fail;
+
+	config_group_init_type_name(&cl->group, name, &cluster_type);
+	config_group_init_type_name(&sps->ss_group, "spaces", &spaces_type);
+	config_group_init_type_name(&cms->cs_group, "comms", &comms_type);
+
+	cl->group.default_groups = gps;
+	cl->group.default_groups[0] = &sps->ss_group;
+	cl->group.default_groups[1] = &cms->cs_group;
+	cl->group.default_groups[2] = NULL;
+
+	space_list = &sps->ss_group;
+	comm_list = &cms->cs_group;
+	return &cl->group;
+
+ fail:
+	kfree(cl);
+	kfree(gps);
+	kfree(sps);
+	kfree(cms);
+	return NULL;
+}
+
+static void drop_cluster(struct config_group *g, struct config_item *i)
+{
+	struct cluster *cl = to_cluster(i);
+	struct config_item *tmp;
+	int j;
+
+	for (j = 0; cl->group.default_groups[j]; j++) {
+		tmp = &cl->group.default_groups[j]->cg_item;
+		cl->group.default_groups[j] = NULL;
+		config_item_put(tmp);
+	}
+
+	space_list = NULL;
+	comm_list = NULL;
+
+	config_item_put(i);
+}
+
+static void release_cluster(struct config_item *i)
+{
+	struct cluster *cl = to_cluster(i);
+	kfree(cl->group.default_groups);
+	kfree(cl);
+}
+
+static struct config_group *make_space(struct config_group *g, const char *name)
+{
+	struct space *sp = NULL;
+	struct nodes *nds = NULL;
+	void *gps = NULL;
+
+	sp = kzalloc(sizeof(struct space), GFP_KERNEL);
+	gps = kcalloc(2, sizeof(struct config_group *), GFP_KERNEL);
+	nds = kzalloc(sizeof(struct nodes), GFP_KERNEL);
+
+	if (!sp || !gps || !nds)
+		goto fail;
+
+	config_group_init_type_name(&sp->group, name, &space_type);
+	config_group_init_type_name(&nds->ns_group, "nodes", &nodes_type);
+
+	sp->group.default_groups = gps;
+	sp->group.default_groups[0] = &nds->ns_group;
+	sp->group.default_groups[1] = NULL;
+
+	INIT_LIST_HEAD(&sp->members);
+	mutex_init(&sp->members_lock);
+	sp->members_count = 0;
+	return &sp->group;
+
+ fail:
+	kfree(sp);
+	kfree(gps);
+	kfree(nds);
+	return NULL;
+}
+
+static void drop_space(struct config_group *g, struct config_item *i)
+{
+	struct space *sp = to_space(i);
+	struct config_item *tmp;
+	int j;
+
+	/* assert list_empty(&sp->members) */
+
+	for (j = 0; sp->group.default_groups[j]; j++) {
+		tmp = &sp->group.default_groups[j]->cg_item;
+		sp->group.default_groups[j] = NULL;
+		config_item_put(tmp);
+	}
+
+	config_item_put(i);
+}
+
+static void release_space(struct config_item *i)
+{
+	struct space *sp = to_space(i);
+	kfree(sp->group.default_groups);
+	kfree(sp);
+}
+
+static struct config_item *make_comm(struct config_group *g, const char *name)
+{
+	struct comm *cm;
+
+	cm = kzalloc(sizeof(struct comm), GFP_KERNEL);
+	if (!cm)
+		return NULL;
+
+	config_item_init_type_name(&cm->item, name, &comm_type);
+	cm->nodeid = -1;
+	cm->local = 0;
+	cm->addr_count = 0;
+	return &cm->item;
+}
+
+static void drop_comm(struct config_group *g, struct config_item *i)
+{
+	struct comm *cm = to_comm(i);
+	if (local_comm == cm)
+		local_comm = NULL;
+	dlm_lowcomms_close(cm->nodeid);
+	while (cm->addr_count--)
+		kfree(cm->addr[cm->addr_count]);
+	config_item_put(i);
+}
+
+static void release_comm(struct config_item *i)
+{
+	struct comm *cm = to_comm(i);
+	kfree(cm);
+}
+
+static struct config_item *make_node(struct config_group *g, const char *name)
+{
+	struct space *sp = to_space(g->cg_item.ci_parent);
+	struct node *nd;
+
+	nd = kzalloc(sizeof(struct node), GFP_KERNEL);
+	if (!nd)
+		return NULL;
+
+	config_item_init_type_name(&nd->item, name, &node_type);
+	nd->nodeid = -1;
+	nd->weight = 1;  /* default weight of 1 if none is set */
+
+	mutex_lock(&sp->members_lock);
+	list_add(&nd->list, &sp->members);
+	sp->members_count++;
+	mutex_unlock(&sp->members_lock);
+
+	return &nd->item;
+}
+
+static void drop_node(struct config_group *g, struct config_item *i)
+{
+	struct space *sp = to_space(g->cg_item.ci_parent);
+	struct node *nd = to_node(i);
+
+	mutex_lock(&sp->members_lock);
+	list_del(&nd->list);
+	sp->members_count--;
+	mutex_unlock(&sp->members_lock);
+
+	config_item_put(i);
+}
+
+static void release_node(struct config_item *i)
+{
+	struct node *nd = to_node(i);
+	kfree(nd);
+}
+
+static struct clusters clusters_root = {
+	.subsys = {
+		.su_group = {
+			.cg_item = {
+				.ci_namebuf = "dlm",
+				.ci_type = &clusters_type,
+			},
+		},
+	},
+};
+
+int dlm_config_init(void)
+{
+	config_group_init(&clusters_root.subsys.su_group);
+	init_MUTEX(&clusters_root.subsys.su_sem);
+	return configfs_register_subsystem(&clusters_root.subsys);
+}
+
+void dlm_config_exit(void)
+{
+	configfs_unregister_subsystem(&clusters_root.subsys);
+}
+
+/*
+ * Functions for user space to read/write attributes
+ */
+
+static ssize_t show_comm(struct config_item *i, struct configfs_attribute *a,
+			 char *buf)
+{
+	struct comm *cm = to_comm(i);
+	struct comm_attribute *cma =
+			container_of(a, struct comm_attribute, attr);
+	return cma->show ? cma->show(cm, buf) : 0;
+}
+
+static ssize_t store_comm(struct config_item *i, struct configfs_attribute *a,
+			  const char *buf, size_t len)
+{
+	struct comm *cm = to_comm(i);
+	struct comm_attribute *cma =
+		container_of(a, struct comm_attribute, attr);
+	return cma->store ? cma->store(cm, buf, len) : -EINVAL;
+}
+
+static ssize_t comm_nodeid_read(struct comm *cm, char *buf)
+{
+	return sprintf(buf, "%d\n", cm->nodeid);
+}
+
+static ssize_t comm_nodeid_write(struct comm *cm, const char *buf, size_t len)
+{
+	cm->nodeid = simple_strtol(buf, NULL, 0);
+	return len;
+}
+
+static ssize_t comm_local_read(struct comm *cm, char *buf)
+{
+	return sprintf(buf, "%d\n", cm->local);
+}
+
+static ssize_t comm_local_write(struct comm *cm, const char *buf, size_t len)
+{
+	cm->local= simple_strtol(buf, NULL, 0);
+	if (cm->local && !local_comm)
+		local_comm = cm;
+	return len;
+}
+
+static ssize_t comm_addr_write(struct comm *cm, const char *buf, size_t len)
+{
+	struct sockaddr_storage *addr;
+
+	if (len != sizeof(struct sockaddr_storage))
+		return -EINVAL;
+
+	if (cm->addr_count >= DLM_MAX_ADDR_COUNT)
+		return -ENOSPC;
+
+	addr = kzalloc(sizeof(*addr), GFP_KERNEL);
+	if (!addr)
+		return -ENOMEM;
+
+	memcpy(addr, buf, len);
+	cm->addr[cm->addr_count++] = addr;
+	return len;
+}
+
+static ssize_t show_node(struct config_item *i, struct configfs_attribute *a,
+			 char *buf)
+{
+	struct node *nd = to_node(i);
+	struct node_attribute *nda =
+			container_of(a, struct node_attribute, attr);
+	return nda->show ? nda->show(nd, buf) : 0;
+}
+
+static ssize_t store_node(struct config_item *i, struct configfs_attribute *a,
+			  const char *buf, size_t len)
+{
+	struct node *nd = to_node(i);
+	struct node_attribute *nda =
+		container_of(a, struct node_attribute, attr);
+	return nda->store ? nda->store(nd, buf, len) : -EINVAL;
+}
+
+static ssize_t node_nodeid_read(struct node *nd, char *buf)
+{
+	return sprintf(buf, "%d\n", nd->nodeid);
+}
+
+static ssize_t node_nodeid_write(struct node *nd, const char *buf, size_t len)
+{
+	nd->nodeid = simple_strtol(buf, NULL, 0);
+	return len;
+}
+
+static ssize_t node_weight_read(struct node *nd, char *buf)
+{
+	return sprintf(buf, "%d\n", nd->weight);
+}
+
+static ssize_t node_weight_write(struct node *nd, const char *buf, size_t len)
+{
+	nd->weight = simple_strtol(buf, NULL, 0);
+	return len;
+}
+
+/*
+ * Functions for the dlm to get the info that's been configured
+ */
+
+static struct space *get_space(char *name)
+{
+	if (!space_list)
+		return NULL;
+	return to_space(config_group_find_obj(space_list, name));
+}
+
+static void put_space(struct space *sp)
+{
+	config_item_put(&sp->group.cg_item);
+}
+
+static struct comm *get_comm(int nodeid, struct sockaddr_storage *addr)
+{
+	struct config_item *i;
+	struct comm *cm = NULL;
+	int found = 0;
+
+	if (!comm_list)
+		return NULL;
+
+	down(&clusters_root.subsys.su_sem);
+
+	list_for_each_entry(i, &comm_list->cg_children, ci_entry) {
+		cm = to_comm(i);
+
+		if (nodeid) {
+			if (cm->nodeid != nodeid)
+				continue;
+			found = 1;
+			break;
+		} else {
+			if (!cm->addr_count ||
+			    memcmp(cm->addr[0], addr, sizeof(*addr)))
+				continue;
+			found = 1;
+			break;
+		}
+	}
+	up(&clusters_root.subsys.su_sem);
+
+	if (found)
+		config_item_get(i);
+	else
+		cm = NULL;
+	return cm;
+}
+
+static void put_comm(struct comm *cm)
+{
+	config_item_put(&cm->item);
+}
+
+/* caller must free mem */
+int dlm_nodeid_list(char *lsname, int **ids_out)
+{
+	struct space *sp;
+	struct node *nd;
+	int i = 0, rv = 0;
+	int *ids;
+
+	sp = get_space(lsname);
+	if (!sp)
+		return -EEXIST;
+
+	mutex_lock(&sp->members_lock);
+	if (!sp->members_count) {
+		rv = 0;
+		goto out;
+	}
+
+	ids = kcalloc(sp->members_count, sizeof(int), GFP_KERNEL);
+	if (!ids) {
+		rv = -ENOMEM;
+		goto out;
+	}
+
+	rv = sp->members_count;
+	list_for_each_entry(nd, &sp->members, list)
+		ids[i++] = nd->nodeid;
+
+	if (rv != i)
+		printk("bad nodeid count %d %d\n", rv, i);
+
+	*ids_out = ids;
+ out:
+	mutex_unlock(&sp->members_lock);
+	put_space(sp);
+	return rv;
+}
+
+int dlm_node_weight(char *lsname, int nodeid)
+{
+	struct space *sp;
+	struct node *nd;
+	int w = -EEXIST;
+
+	sp = get_space(lsname);
+	if (!sp)
+		goto out;
+
+	mutex_lock(&sp->members_lock);
+	list_for_each_entry(nd, &sp->members, list) {
+		if (nd->nodeid != nodeid)
+			continue;
+		w = nd->weight;
+		break;
+	}
+	mutex_unlock(&sp->members_lock);
+	put_space(sp);
+ out:
+	return w;
+}
+
+int dlm_nodeid_to_addr(int nodeid, struct sockaddr_storage *addr)
+{
+	struct comm *cm = get_comm(nodeid, NULL);
+	if (!cm)
+		return -EEXIST;
+	if (!cm->addr_count)
+		return -ENOENT;
+	memcpy(addr, cm->addr[0], sizeof(*addr));
+	put_comm(cm);
+	return 0;
+}
+
+int dlm_addr_to_nodeid(struct sockaddr_storage *addr, int *nodeid)
+{
+	struct comm *cm = get_comm(0, addr);
+	if (!cm)
+		return -EEXIST;
+	*nodeid = cm->nodeid;
+	put_comm(cm);
+	return 0;
+}
+
+int dlm_our_nodeid(void)
+{
+	return local_comm ? local_comm->nodeid : 0;
+}
+
+/* num 0 is first addr, num 1 is second addr */
+int dlm_our_addr(struct sockaddr_storage *addr, int num)
+{
+	if (!local_comm)
+		return -1;
+	if (num + 1 > local_comm->addr_count)
+		return -1;
+	memcpy(addr, local_comm->addr[num], sizeof(*addr));
+	return 0;
+}
+
+/* Config file defaults */
+#define DEFAULT_TCP_PORT       21064
+#define DEFAULT_BUFFER_SIZE     4096
+#define DEFAULT_RSBTBL_SIZE      256
+#define DEFAULT_LKBTBL_SIZE     1024
+#define DEFAULT_DIRTBL_SIZE      512
+#define DEFAULT_RECOVER_TIMER      5
+#define DEFAULT_TOSS_SECS         10
+#define DEFAULT_SCAN_SECS          5
+
+struct dlm_config_info dlm_config = {
+	.tcp_port = DEFAULT_TCP_PORT,
+	.buffer_size = DEFAULT_BUFFER_SIZE,
+	.rsbtbl_size = DEFAULT_RSBTBL_SIZE,
+	.lkbtbl_size = DEFAULT_LKBTBL_SIZE,
+	.dirtbl_size = DEFAULT_DIRTBL_SIZE,
+	.recover_timer = DEFAULT_RECOVER_TIMER,
+	.toss_secs = DEFAULT_TOSS_SECS,
+	.scan_secs = DEFAULT_SCAN_SECS
+};
+

fs/dlm/config.h

@@ -0,0 +1,42 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __CONFIG_DOT_H__
+#define __CONFIG_DOT_H__
+
+#define DLM_MAX_ADDR_COUNT 3
+
+struct dlm_config_info {
+	int tcp_port;
+	int buffer_size;
+	int rsbtbl_size;
+	int lkbtbl_size;
+	int dirtbl_size;
+	int recover_timer;
+	int toss_secs;
+	int scan_secs;
+};
+
+extern struct dlm_config_info dlm_config;
+
+int dlm_config_init(void);
+void dlm_config_exit(void);
+int dlm_node_weight(char *lsname, int nodeid);
+int dlm_nodeid_list(char *lsname, int **ids_out);
+int dlm_nodeid_to_addr(int nodeid, struct sockaddr_storage *addr);
+int dlm_addr_to_nodeid(struct sockaddr_storage *addr, int *nodeid);
+int dlm_our_nodeid(void);
+int dlm_our_addr(struct sockaddr_storage *addr, int num);
+
+#endif				/* __CONFIG_DOT_H__ */
+

fs/dlm/debug_fs.c

@@ -0,0 +1,387 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include <linux/pagemap.h>
+#include <linux/seq_file.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
+
+#include "dlm_internal.h"
+
+#define DLM_DEBUG_BUF_LEN 4096
+static char debug_buf[DLM_DEBUG_BUF_LEN];
+static struct mutex debug_buf_lock;
+
+static struct dentry *dlm_root;
+
+struct rsb_iter {
+	int entry;
+	struct dlm_ls *ls;
+	struct list_head *next;
+	struct dlm_rsb *rsb;
+};
+
+/*
+ * dump all rsb's in the lockspace hash table
+ */
+
+static char *print_lockmode(int mode)
+{
+	switch (mode) {
+	case DLM_LOCK_IV:
+		return "--";
+	case DLM_LOCK_NL:
+		return "NL";
+	case DLM_LOCK_CR:
+		return "CR";
+	case DLM_LOCK_CW:
+		return "CW";
+	case DLM_LOCK_PR:
+		return "PR";
+	case DLM_LOCK_PW:
+		return "PW";
+	case DLM_LOCK_EX:
+		return "EX";
+	default:
+		return "??";
+	}
+}
+
+static void print_lock(struct seq_file *s, struct dlm_lkb *lkb,
+		       struct dlm_rsb *res)
+{
+	seq_printf(s, "%08x %s", lkb->lkb_id, print_lockmode(lkb->lkb_grmode));
+
+	if (lkb->lkb_status == DLM_LKSTS_CONVERT
+	    || lkb->lkb_status == DLM_LKSTS_WAITING)
+		seq_printf(s, " (%s)", print_lockmode(lkb->lkb_rqmode));
+
+	if (lkb->lkb_nodeid) {
+		if (lkb->lkb_nodeid != res->res_nodeid)
+			seq_printf(s, " Remote: %3d %08x", lkb->lkb_nodeid,
+				   lkb->lkb_remid);
+		else
+			seq_printf(s, " Master:     %08x", lkb->lkb_remid);
+	}
+
+	if (lkb->lkb_wait_type)
+		seq_printf(s, " wait_type: %d", lkb->lkb_wait_type);
+
+	seq_printf(s, "\n");
+}
+
+static int print_resource(struct dlm_rsb *res, struct seq_file *s)
+{
+	struct dlm_lkb *lkb;
+	int i, lvblen = res->res_ls->ls_lvblen, recover_list, root_list;
+
+	seq_printf(s, "\nResource %p Name (len=%d) \"", res, res->res_length);
+	for (i = 0; i < res->res_length; i++) {
+		if (isprint(res->res_name[i]))
+			seq_printf(s, "%c", res->res_name[i]);
+		else
+			seq_printf(s, "%c", '.');
+	}
+	if (res->res_nodeid > 0)
+		seq_printf(s, "\"  \nLocal Copy, Master is node %d\n",
+			   res->res_nodeid);
+	else if (res->res_nodeid == 0)
+		seq_printf(s, "\"  \nMaster Copy\n");
+	else if (res->res_nodeid == -1)
+		seq_printf(s, "\"  \nLooking up master (lkid %x)\n",
+			   res->res_first_lkid);
+	else
+		seq_printf(s, "\"  \nInvalid master %d\n", res->res_nodeid);
+
+	/* Print the LVB: */
+	if (res->res_lvbptr) {
+		seq_printf(s, "LVB: ");
+		for (i = 0; i < lvblen; i++) {
+			if (i == lvblen / 2)
+				seq_printf(s, "\n     ");
+			seq_printf(s, "%02x ",
+				   (unsigned char) res->res_lvbptr[i]);
+		}
+		if (rsb_flag(res, RSB_VALNOTVALID))
+			seq_printf(s, " (INVALID)");
+		seq_printf(s, "\n");
+	}
+
+	root_list = !list_empty(&res->res_root_list);
+	recover_list = !list_empty(&res->res_recover_list);
+
+	if (root_list || recover_list) {
+		seq_printf(s, "Recovery: root %d recover %d flags %lx "
+			   "count %d\n", root_list, recover_list,
+			   res->res_flags, res->res_recover_locks_count);
+	}
+
+	/* Print the locks attached to this resource */
+	seq_printf(s, "Granted Queue\n");
+	list_for_each_entry(lkb, &res->res_grantqueue, lkb_statequeue)
+		print_lock(s, lkb, res);
+
+	seq_printf(s, "Conversion Queue\n");
+	list_for_each_entry(lkb, &res->res_convertqueue, lkb_statequeue)
+		print_lock(s, lkb, res);
+
+	seq_printf(s, "Waiting Queue\n");
+	list_for_each_entry(lkb, &res->res_waitqueue, lkb_statequeue)
+		print_lock(s, lkb, res);
+
+	if (list_empty(&res->res_lookup))
+		goto out;
+
+	seq_printf(s, "Lookup Queue\n");
+	list_for_each_entry(lkb, &res->res_lookup, lkb_rsb_lookup) {
+		seq_printf(s, "%08x %s", lkb->lkb_id,
+			   print_lockmode(lkb->lkb_rqmode));
+		if (lkb->lkb_wait_type)
+			seq_printf(s, " wait_type: %d", lkb->lkb_wait_type);
+		seq_printf(s, "\n");
+	}
+ out:
+	return 0;
+}
+
+static int rsb_iter_next(struct rsb_iter *ri)
+{
+	struct dlm_ls *ls = ri->ls;
+	int i;
+
+	if (!ri->next) {
+ top:
+		/* Find the next non-empty hash bucket */
+		for (i = ri->entry; i < ls->ls_rsbtbl_size; i++) {
+			read_lock(&ls->ls_rsbtbl[i].lock);
+			if (!list_empty(&ls->ls_rsbtbl[i].list)) {
+				ri->next = ls->ls_rsbtbl[i].list.next;
+				read_unlock(&ls->ls_rsbtbl[i].lock);
+				break;
+			}
+			read_unlock(&ls->ls_rsbtbl[i].lock);
+                }
+		ri->entry = i;
+
+		if (ri->entry >= ls->ls_rsbtbl_size)
+			return 1;
+	} else {
+		i = ri->entry;
+		read_lock(&ls->ls_rsbtbl[i].lock);
+		ri->next = ri->next->next;
+		if (ri->next->next == ls->ls_rsbtbl[i].list.next) {
+			/* End of list - move to next bucket */
+			ri->next = NULL;
+			ri->entry++;
+			read_unlock(&ls->ls_rsbtbl[i].lock);
+			goto top;
+                }
+		read_unlock(&ls->ls_rsbtbl[i].lock);
+	}
+	ri->rsb = list_entry(ri->next, struct dlm_rsb, res_hashchain);
+
+	return 0;
+}
+
+static void rsb_iter_free(struct rsb_iter *ri)
+{
+	kfree(ri);
+}
+
+static struct rsb_iter *rsb_iter_init(struct dlm_ls *ls)
+{
+	struct rsb_iter *ri;
+
+	ri = kmalloc(sizeof *ri, GFP_KERNEL);
+	if (!ri)
+		return NULL;
+
+	ri->ls = ls;
+	ri->entry = 0;
+	ri->next = NULL;
+
+	if (rsb_iter_next(ri)) {
+		rsb_iter_free(ri);
+		return NULL;
+	}
+
+	return ri;
+}
+
+static void *rsb_seq_start(struct seq_file *file, loff_t *pos)
+{
+	struct rsb_iter *ri;
+	loff_t n = *pos;
+
+	ri = rsb_iter_init(file->private);
+	if (!ri)
+		return NULL;
+
+	while (n--) {
+		if (rsb_iter_next(ri)) {
+			rsb_iter_free(ri);
+			return NULL;
+		}
+	}
+
+	return ri;
+}
+
+static void *rsb_seq_next(struct seq_file *file, void *iter_ptr, loff_t *pos)
+{
+	struct rsb_iter *ri = iter_ptr;
+
+	(*pos)++;
+
+	if (rsb_iter_next(ri)) {
+		rsb_iter_free(ri);
+		return NULL;
+	}
+
+	return ri;
+}
+
+static void rsb_seq_stop(struct seq_file *file, void *iter_ptr)
+{
+	/* nothing for now */
+}
+
+static int rsb_seq_show(struct seq_file *file, void *iter_ptr)
+{
+	struct rsb_iter *ri = iter_ptr;
+
+	print_resource(ri->rsb, file);
+
+	return 0;
+}
+
+static struct seq_operations rsb_seq_ops = {
+	.start = rsb_seq_start,
+	.next  = rsb_seq_next,
+	.stop  = rsb_seq_stop,
+	.show  = rsb_seq_show,
+};
+
+static int rsb_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq;
+	int ret;
+
+	ret = seq_open(file, &rsb_seq_ops);
+	if (ret)
+		return ret;
+
+	seq = file->private_data;
+	seq->private = inode->i_private;
+
+	return 0;
+}
+
+static struct file_operations rsb_fops = {
+	.owner   = THIS_MODULE,
+	.open    = rsb_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release
+};
+
+/*
+ * dump lkb's on the ls_waiters list
+ */
+
+static int waiters_open(struct inode *inode, struct file *file)
+{
+	file->private_data = inode->i_private;
+	return 0;
+}
+
+static ssize_t waiters_read(struct file *file, char __user *userbuf,
+			    size_t count, loff_t *ppos)
+{
+	struct dlm_ls *ls = file->private_data;
+	struct dlm_lkb *lkb;
+	size_t len = DLM_DEBUG_BUF_LEN, pos = 0, ret, rv;
+
+	mutex_lock(&debug_buf_lock);
+	mutex_lock(&ls->ls_waiters_mutex);
+	memset(debug_buf, 0, sizeof(debug_buf));
+
+	list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) {
+		ret = snprintf(debug_buf + pos, len - pos, "%x %d %d %s\n",
+			       lkb->lkb_id, lkb->lkb_wait_type,
+			       lkb->lkb_nodeid, lkb->lkb_resource->res_name);
+		if (ret >= len - pos)
+			break;
+		pos += ret;
+	}
+	mutex_unlock(&ls->ls_waiters_mutex);
+
+	rv = simple_read_from_buffer(userbuf, count, ppos, debug_buf, pos);
+	mutex_unlock(&debug_buf_lock);
+	return rv;
+}
+
+static struct file_operations waiters_fops = {
+	.owner   = THIS_MODULE,
+	.open    = waiters_open,
+	.read    = waiters_read
+};
+
+int dlm_create_debug_file(struct dlm_ls *ls)
+{
+	char name[DLM_LOCKSPACE_LEN+8];
+
+	ls->ls_debug_rsb_dentry = debugfs_create_file(ls->ls_name,
+						      S_IFREG | S_IRUGO,
+						      dlm_root,
+						      ls,
+						      &rsb_fops);
+	if (!ls->ls_debug_rsb_dentry)
+		return -ENOMEM;
+
+	memset(name, 0, sizeof(name));
+	snprintf(name, DLM_LOCKSPACE_LEN+8, "%s_waiters", ls->ls_name);
+
+	ls->ls_debug_waiters_dentry = debugfs_create_file(name,
+							  S_IFREG | S_IRUGO,
+							  dlm_root,
+							  ls,
+							  &waiters_fops);
+	if (!ls->ls_debug_waiters_dentry) {
+		debugfs_remove(ls->ls_debug_rsb_dentry);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void dlm_delete_debug_file(struct dlm_ls *ls)
+{
+	if (ls->ls_debug_rsb_dentry)
+		debugfs_remove(ls->ls_debug_rsb_dentry);
+	if (ls->ls_debug_waiters_dentry)
+		debugfs_remove(ls->ls_debug_waiters_dentry);
+}
+
+int dlm_register_debugfs(void)
+{
+	mutex_init(&debug_buf_lock);
+	dlm_root = debugfs_create_dir("dlm", NULL);
+	return dlm_root ? 0 : -ENOMEM;
+}
+
+void dlm_unregister_debugfs(void)
+{
+	debugfs_remove(dlm_root);
+}
+

fs/dlm/dir.c

@@ -0,0 +1,423 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "member.h"
+#include "lowcomms.h"
+#include "rcom.h"
+#include "config.h"
+#include "memory.h"
+#include "recover.h"
+#include "util.h"
+#include "lock.h"
+#include "dir.h"
+
+
+static void put_free_de(struct dlm_ls *ls, struct dlm_direntry *de)
+{
+	spin_lock(&ls->ls_recover_list_lock);
+	list_add(&de->list, &ls->ls_recover_list);
+	spin_unlock(&ls->ls_recover_list_lock);
+}
+
+static struct dlm_direntry *get_free_de(struct dlm_ls *ls, int len)
+{
+	int found = 0;
+	struct dlm_direntry *de;
+
+	spin_lock(&ls->ls_recover_list_lock);
+	list_for_each_entry(de, &ls->ls_recover_list, list) {
+		if (de->length == len) {
+			list_del(&de->list);
+			de->master_nodeid = 0;
+			memset(de->name, 0, len);
+			found = 1;
+			break;
+		}
+	}
+	spin_unlock(&ls->ls_recover_list_lock);
+
+	if (!found)
+		de = allocate_direntry(ls, len);
+	return de;
+}
+
+void dlm_clear_free_entries(struct dlm_ls *ls)
+{
+	struct dlm_direntry *de;
+
+	spin_lock(&ls->ls_recover_list_lock);
+	while (!list_empty(&ls->ls_recover_list)) {
+		de = list_entry(ls->ls_recover_list.next, struct dlm_direntry,
+				list);
+		list_del(&de->list);
+		free_direntry(de);
+	}
+	spin_unlock(&ls->ls_recover_list_lock);
+}
+
+/*
+ * We use the upper 16 bits of the hash value to select the directory node.
+ * Low bits are used for distribution of rsb's among hash buckets on each node.
+ *
+ * To give the exact range wanted (0 to num_nodes-1), we apply a modulus of
+ * num_nodes to the hash value.  This value in the desired range is used as an
+ * offset into the sorted list of nodeid's to give the particular nodeid.
+ */
+
+int dlm_hash2nodeid(struct dlm_ls *ls, uint32_t hash)
+{
+	struct list_head *tmp;
+	struct dlm_member *memb = NULL;
+	uint32_t node, n = 0;
+	int nodeid;
+
+	if (ls->ls_num_nodes == 1) {
+		nodeid = dlm_our_nodeid();
+		goto out;
+	}
+
+	if (ls->ls_node_array) {
+		node = (hash >> 16) % ls->ls_total_weight;
+		nodeid = ls->ls_node_array[node];
+		goto out;
+	}
+
+	/* make_member_array() failed to kmalloc ls_node_array... */
+
+	node = (hash >> 16) % ls->ls_num_nodes;
+
+	list_for_each(tmp, &ls->ls_nodes) {
+		if (n++ != node)
+			continue;
+		memb = list_entry(tmp, struct dlm_member, list);
+		break;
+	}
+
+	DLM_ASSERT(memb , printk("num_nodes=%u n=%u node=%u\n",
+				 ls->ls_num_nodes, n, node););
+	nodeid = memb->nodeid;
+ out:
+	return nodeid;
+}
+
+int dlm_dir_nodeid(struct dlm_rsb *r)
+{
+	return dlm_hash2nodeid(r->res_ls, r->res_hash);
+}
+
+static inline uint32_t dir_hash(struct dlm_ls *ls, char *name, int len)
+{
+	uint32_t val;
+
+	val = jhash(name, len, 0);
+	val &= (ls->ls_dirtbl_size - 1);
+
+	return val;
+}
+
+static void add_entry_to_hash(struct dlm_ls *ls, struct dlm_direntry *de)
+{
+	uint32_t bucket;
+
+	bucket = dir_hash(ls, de->name, de->length);
+	list_add_tail(&de->list, &ls->ls_dirtbl[bucket].list);
+}
+
+static struct dlm_direntry *search_bucket(struct dlm_ls *ls, char *name,
+					  int namelen, uint32_t bucket)
+{
+	struct dlm_direntry *de;
+
+	list_for_each_entry(de, &ls->ls_dirtbl[bucket].list, list) {
+		if (de->length == namelen && !memcmp(name, de->name, namelen))
+			goto out;
+	}
+	de = NULL;
+ out:
+	return de;
+}
+
+void dlm_dir_remove_entry(struct dlm_ls *ls, int nodeid, char *name, int namelen)
+{
+	struct dlm_direntry *de;
+	uint32_t bucket;
+
+	bucket = dir_hash(ls, name, namelen);
+
+	write_lock(&ls->ls_dirtbl[bucket].lock);
+
+	de = search_bucket(ls, name, namelen, bucket);
+
+	if (!de) {
+		log_error(ls, "remove fr %u none", nodeid);
+		goto out;
+	}
+
+	if (de->master_nodeid != nodeid) {
+		log_error(ls, "remove fr %u ID %u", nodeid, de->master_nodeid);
+		goto out;
+	}
+
+	list_del(&de->list);
+	free_direntry(de);
+ out:
+	write_unlock(&ls->ls_dirtbl[bucket].lock);
+}
+
+void dlm_dir_clear(struct dlm_ls *ls)
+{
+	struct list_head *head;
+	struct dlm_direntry *de;
+	int i;
+
+	DLM_ASSERT(list_empty(&ls->ls_recover_list), );
+
+	for (i = 0; i < ls->ls_dirtbl_size; i++) {
+		write_lock(&ls->ls_dirtbl[i].lock);
+		head = &ls->ls_dirtbl[i].list;
+		while (!list_empty(head)) {
+			de = list_entry(head->next, struct dlm_direntry, list);
+			list_del(&de->list);
+			put_free_de(ls, de);
+		}
+		write_unlock(&ls->ls_dirtbl[i].lock);
+	}
+}
+
+int dlm_recover_directory(struct dlm_ls *ls)
+{
+	struct dlm_member *memb;
+	struct dlm_direntry *de;
+	char *b, *last_name = NULL;
+	int error = -ENOMEM, last_len, count = 0;
+	uint16_t namelen;
+
+	log_debug(ls, "dlm_recover_directory");
+
+	if (dlm_no_directory(ls))
+		goto out_status;
+
+	dlm_dir_clear(ls);
+
+	last_name = kmalloc(DLM_RESNAME_MAXLEN, GFP_KERNEL);
+	if (!last_name)
+		goto out;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		memset(last_name, 0, DLM_RESNAME_MAXLEN);
+		last_len = 0;
+
+		for (;;) {
+			error = dlm_recovery_stopped(ls);
+			if (error)
+				goto out_free;
+
+			error = dlm_rcom_names(ls, memb->nodeid,
+					       last_name, last_len);
+			if (error)
+				goto out_free;
+
+			schedule();
+
+			/*
+			 * pick namelen/name pairs out of received buffer
+			 */
+
+			b = ls->ls_recover_buf + sizeof(struct dlm_rcom);
+
+			for (;;) {
+				memcpy(&namelen, b, sizeof(uint16_t));
+				namelen = be16_to_cpu(namelen);
+				b += sizeof(uint16_t);
+
+				/* namelen of 0xFFFFF marks end of names for
+				   this node; namelen of 0 marks end of the
+				   buffer */
+
+				if (namelen == 0xFFFF)
+					goto done;
+				if (!namelen)
+					break;
+
+				error = -ENOMEM;
+				de = get_free_de(ls, namelen);
+				if (!de)
+					goto out_free;
+
+				de->master_nodeid = memb->nodeid;
+				de->length = namelen;
+				last_len = namelen;
+				memcpy(de->name, b, namelen);
+				memcpy(last_name, b, namelen);
+				b += namelen;
+
+				add_entry_to_hash(ls, de);
+				count++;
+			}
+		}
+         done:
+		;
+	}
+
+ out_status:
+	error = 0;
+	dlm_set_recover_status(ls, DLM_RS_DIR);
+	log_debug(ls, "dlm_recover_directory %d entries", count);
+ out_free:
+	kfree(last_name);
+ out:
+	dlm_clear_free_entries(ls);
+	return error;
+}
+
+static int get_entry(struct dlm_ls *ls, int nodeid, char *name,
+		     int namelen, int *r_nodeid)
+{
+	struct dlm_direntry *de, *tmp;
+	uint32_t bucket;
+
+	bucket = dir_hash(ls, name, namelen);
+
+	write_lock(&ls->ls_dirtbl[bucket].lock);
+	de = search_bucket(ls, name, namelen, bucket);
+	if (de) {
+		*r_nodeid = de->master_nodeid;
+		write_unlock(&ls->ls_dirtbl[bucket].lock);
+		if (*r_nodeid == nodeid)
+			return -EEXIST;
+		return 0;
+	}
+
+	write_unlock(&ls->ls_dirtbl[bucket].lock);
+
+	de = allocate_direntry(ls, namelen);
+	if (!de)
+		return -ENOMEM;
+
+	de->master_nodeid = nodeid;
+	de->length = namelen;
+	memcpy(de->name, name, namelen);
+
+	write_lock(&ls->ls_dirtbl[bucket].lock);
+	tmp = search_bucket(ls, name, namelen, bucket);
+	if (tmp) {
+		free_direntry(de);
+		de = tmp;
+	} else {
+		list_add_tail(&de->list, &ls->ls_dirtbl[bucket].list);
+	}
+	*r_nodeid = de->master_nodeid;
+	write_unlock(&ls->ls_dirtbl[bucket].lock);
+	return 0;
+}
+
+int dlm_dir_lookup(struct dlm_ls *ls, int nodeid, char *name, int namelen,
+		   int *r_nodeid)
+{
+	return get_entry(ls, nodeid, name, namelen, r_nodeid);
+}
+
+/* Copy the names of master rsb's into the buffer provided.
+   Only select names whose dir node is the given nodeid. */
+
+void dlm_copy_master_names(struct dlm_ls *ls, char *inbuf, int inlen,
+ 			   char *outbuf, int outlen, int nodeid)
+{
+	struct list_head *list;
+	struct dlm_rsb *start_r = NULL, *r = NULL;
+	int offset = 0, start_namelen, error, dir_nodeid;
+	char *start_name;
+	uint16_t be_namelen;
+
+	/*
+	 * Find the rsb where we left off (or start again)
+	 */
+
+	start_namelen = inlen;
+	start_name = inbuf;
+
+	if (start_namelen > 1) {
+		/*
+		 * We could also use a find_rsb_root() function here that
+		 * searched the ls_root_list.
+		 */
+		error = dlm_find_rsb(ls, start_name, start_namelen, R_MASTER,
+				     &start_r);
+		DLM_ASSERT(!error && start_r,
+			   printk("error %d\n", error););
+		DLM_ASSERT(!list_empty(&start_r->res_root_list),
+			   dlm_print_rsb(start_r););
+		dlm_put_rsb(start_r);
+	}
+
+	/*
+	 * Send rsb names for rsb's we're master of and whose directory node
+	 * matches the requesting node.
+	 */
+
+	down_read(&ls->ls_root_sem);
+	if (start_r)
+		list = start_r->res_root_list.next;
+	else
+		list = ls->ls_root_list.next;
+
+	for (offset = 0; list != &ls->ls_root_list; list = list->next) {
+		r = list_entry(list, struct dlm_rsb, res_root_list);
+		if (r->res_nodeid)
+			continue;
+
+		dir_nodeid = dlm_dir_nodeid(r);
+		if (dir_nodeid != nodeid)
+			continue;
+
+		/*
+		 * The block ends when we can't fit the following in the
+		 * remaining buffer space:
+		 * namelen (uint16_t) +
+		 * name (r->res_length) +
+		 * end-of-block record 0x0000 (uint16_t)
+		 */
+
+		if (offset + sizeof(uint16_t)*2 + r->res_length > outlen) {
+			/* Write end-of-block record */
+			be_namelen = 0;
+			memcpy(outbuf + offset, &be_namelen, sizeof(uint16_t));
+			offset += sizeof(uint16_t);
+			goto out;
+		}
+
+		be_namelen = cpu_to_be16(r->res_length);
+		memcpy(outbuf + offset, &be_namelen, sizeof(uint16_t));
+		offset += sizeof(uint16_t);
+		memcpy(outbuf + offset, r->res_name, r->res_length);
+		offset += r->res_length;
+	}
+
+	/*
+	 * If we've reached the end of the list (and there's room) write a
+	 * terminating record.
+	 */
+
+	if ((list == &ls->ls_root_list) &&
+	    (offset + sizeof(uint16_t) <= outlen)) {
+		be_namelen = 0xFFFF;
+		memcpy(outbuf + offset, &be_namelen, sizeof(uint16_t));
+		offset += sizeof(uint16_t);
+	}
+
+ out:
+	up_read(&ls->ls_root_sem);
+}
+

fs/dlm/dir.h

@@ -0,0 +1,30 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __DIR_DOT_H__
+#define __DIR_DOT_H__
+
+
+int dlm_dir_nodeid(struct dlm_rsb *rsb);
+int dlm_hash2nodeid(struct dlm_ls *ls, uint32_t hash);
+void dlm_dir_remove_entry(struct dlm_ls *ls, int nodeid, char *name, int len);
+void dlm_dir_clear(struct dlm_ls *ls);
+void dlm_clear_free_entries(struct dlm_ls *ls);
+int dlm_recover_directory(struct dlm_ls *ls);
+int dlm_dir_lookup(struct dlm_ls *ls, int nodeid, char *name, int namelen,
+	int *r_nodeid);
+void dlm_copy_master_names(struct dlm_ls *ls, char *inbuf, int inlen,
+	char *outbuf, int outlen, int nodeid);
+
+#endif				/* __DIR_DOT_H__ */
+

fs/dlm/dlm_internal.h

@@ -0,0 +1,543 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __DLM_INTERNAL_DOT_H__
+#define __DLM_INTERNAL_DOT_H__
+
+/*
+ * This is the main header file to be included in each DLM source file.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/ctype.h>
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+#include <linux/list.h>
+#include <linux/errno.h>
+#include <linux/random.h>
+#include <linux/delay.h>
+#include <linux/socket.h>
+#include <linux/kthread.h>
+#include <linux/kobject.h>
+#include <linux/kref.h>
+#include <linux/kernel.h>
+#include <linux/jhash.h>
+#include <linux/miscdevice.h>
+#include <linux/mutex.h>
+#include <asm/semaphore.h>
+#include <asm/uaccess.h>
+
+#include <linux/dlm.h>
+
+#define DLM_LOCKSPACE_LEN	64
+
+/* Size of the temp buffer midcomms allocates on the stack.
+   We try to make this large enough so most messages fit.
+   FIXME: should sctp make this unnecessary? */
+
+#define DLM_INBUF_LEN		148
+
+struct dlm_ls;
+struct dlm_lkb;
+struct dlm_rsb;
+struct dlm_member;
+struct dlm_lkbtable;
+struct dlm_rsbtable;
+struct dlm_dirtable;
+struct dlm_direntry;
+struct dlm_recover;
+struct dlm_header;
+struct dlm_message;
+struct dlm_rcom;
+struct dlm_mhandle;
+
+#define log_print(fmt, args...) \
+	printk(KERN_ERR "dlm: "fmt"\n" , ##args)
+#define log_error(ls, fmt, args...) \
+	printk(KERN_ERR "dlm: %s: " fmt "\n", (ls)->ls_name , ##args)
+
+#define DLM_LOG_DEBUG
+#ifdef DLM_LOG_DEBUG
+#define log_debug(ls, fmt, args...) log_error(ls, fmt, ##args)
+#else
+#define log_debug(ls, fmt, args...)
+#endif
+
+#define DLM_ASSERT(x, do) \
+{ \
+  if (!(x)) \
+  { \
+    printk(KERN_ERR "\nDLM:  Assertion failed on line %d of file %s\n" \
+               "DLM:  assertion:  \"%s\"\n" \
+               "DLM:  time = %lu\n", \
+               __LINE__, __FILE__, #x, jiffies); \
+    {do} \
+    printk("\n"); \
+    BUG(); \
+    panic("DLM:  Record message above and reboot.\n"); \
+  } \
+}
+
+#define DLM_FAKE_USER_AST ERR_PTR(-EINVAL)
+
+
+struct dlm_direntry {
+	struct list_head	list;
+	uint32_t		master_nodeid;
+	uint16_t		length;
+	char			name[1];
+};
+
+struct dlm_dirtable {
+	struct list_head	list;
+	rwlock_t		lock;
+};
+
+struct dlm_rsbtable {
+	struct list_head	list;
+	struct list_head	toss;
+	rwlock_t		lock;
+};
+
+struct dlm_lkbtable {
+	struct list_head	list;
+	rwlock_t		lock;
+	uint16_t		counter;
+};
+
+/*
+ * Lockspace member (per node in a ls)
+ */
+
+struct dlm_member {
+	struct list_head	list;
+	int			nodeid;
+	int			weight;
+};
+
+/*
+ * Save and manage recovery state for a lockspace.
+ */
+
+struct dlm_recover {
+	struct list_head	list;
+	int			*nodeids;
+	int			node_count;
+	uint64_t		seq;
+};
+
+/*
+ * Pass input args to second stage locking function.
+ */
+
+struct dlm_args {
+	uint32_t		flags;
+	void			*astaddr;
+	long			astparam;
+	void			*bastaddr;
+	int			mode;
+	struct dlm_lksb		*lksb;
+};
+
+
+/*
+ * Lock block
+ *
+ * A lock can be one of three types:
+ *
+ * local copy      lock is mastered locally
+ *                 (lkb_nodeid is zero and DLM_LKF_MSTCPY is not set)
+ * process copy    lock is mastered on a remote node
+ *                 (lkb_nodeid is non-zero and DLM_LKF_MSTCPY is not set)
+ * master copy     master node's copy of a lock owned by remote node
+ *                 (lkb_nodeid is non-zero and DLM_LKF_MSTCPY is set)
+ *
+ * lkb_exflags: a copy of the most recent flags arg provided to dlm_lock or
+ * dlm_unlock.  The dlm does not modify these or use any private flags in
+ * this field; it only contains DLM_LKF_ flags from dlm.h.  These flags
+ * are sent as-is to the remote master when the lock is remote.
+ *
+ * lkb_flags: internal dlm flags (DLM_IFL_ prefix) from dlm_internal.h.
+ * Some internal flags are shared between the master and process nodes;
+ * these shared flags are kept in the lower two bytes.  One of these
+ * flags set on the master copy will be propagated to the process copy
+ * and v.v.  Other internal flags are private to the master or process
+ * node (e.g. DLM_IFL_MSTCPY).  These are kept in the high two bytes.
+ *
+ * lkb_sbflags: status block flags.  These flags are copied directly into
+ * the caller's lksb.sb_flags prior to the dlm_lock/dlm_unlock completion
+ * ast.  All defined in dlm.h with DLM_SBF_ prefix.
+ *
+ * lkb_status: the lock status indicates which rsb queue the lock is
+ * on, grant, convert, or wait.  DLM_LKSTS_ WAITING/GRANTED/CONVERT
+ *
+ * lkb_wait_type: the dlm message type (DLM_MSG_ prefix) for which a
+ * reply is needed.  Only set when the lkb is on the lockspace waiters
+ * list awaiting a reply from a remote node.
+ *
+ * lkb_nodeid: when the lkb is a local copy, nodeid is 0; when the lkb
+ * is a master copy, nodeid specifies the remote lock holder, when the
+ * lkb is a process copy, the nodeid specifies the lock master.
+ */
+
+/* lkb_ast_type */
+
+#define AST_COMP		1
+#define AST_BAST		2
+
+/* lkb_status */
+
+#define DLM_LKSTS_WAITING	1
+#define DLM_LKSTS_GRANTED	2
+#define DLM_LKSTS_CONVERT	3
+
+/* lkb_flags */
+
+#define DLM_IFL_MSTCPY		0x00010000
+#define DLM_IFL_RESEND		0x00020000
+#define DLM_IFL_DEAD		0x00040000
+#define DLM_IFL_USER		0x00000001
+#define DLM_IFL_ORPHAN		0x00000002
+
+struct dlm_lkb {
+	struct dlm_rsb		*lkb_resource;	/* the rsb */
+	struct kref		lkb_ref;
+	int			lkb_nodeid;	/* copied from rsb */
+	int			lkb_ownpid;	/* pid of lock owner */
+	uint32_t		lkb_id;		/* our lock ID */
+	uint32_t		lkb_remid;	/* lock ID on remote partner */
+	uint32_t		lkb_exflags;	/* external flags from caller */
+	uint32_t		lkb_sbflags;	/* lksb flags */
+	uint32_t		lkb_flags;	/* internal flags */
+	uint32_t		lkb_lvbseq;	/* lvb sequence number */
+
+	int8_t			lkb_status;     /* granted, waiting, convert */
+	int8_t			lkb_rqmode;	/* requested lock mode */
+	int8_t			lkb_grmode;	/* granted lock mode */
+	int8_t			lkb_bastmode;	/* requested mode */
+	int8_t			lkb_highbast;	/* highest mode bast sent for */
+
+	int8_t			lkb_wait_type;	/* type of reply waiting for */
+	int8_t			lkb_ast_type;	/* type of ast queued for */
+
+	struct list_head	lkb_idtbl_list;	/* lockspace lkbtbl */
+	struct list_head	lkb_statequeue;	/* rsb g/c/w list */
+	struct list_head	lkb_rsb_lookup;	/* waiting for rsb lookup */
+	struct list_head	lkb_wait_reply;	/* waiting for remote reply */
+	struct list_head	lkb_astqueue;	/* need ast to be sent */
+	struct list_head	lkb_ownqueue;	/* list of locks for a process */
+
+	char			*lkb_lvbptr;
+	struct dlm_lksb		*lkb_lksb;      /* caller's status block */
+	void			*lkb_astaddr;	/* caller's ast function */
+	void			*lkb_bastaddr;	/* caller's bast function */
+	long			lkb_astparam;	/* caller's ast arg */
+};
+
+
+struct dlm_rsb {
+	struct dlm_ls		*res_ls;	/* the lockspace */
+	struct kref		res_ref;
+	struct mutex		res_mutex;
+	unsigned long		res_flags;
+	int			res_length;	/* length of rsb name */
+	int			res_nodeid;
+	uint32_t                res_lvbseq;
+	uint32_t		res_hash;
+	uint32_t		res_bucket;	/* rsbtbl */
+	unsigned long		res_toss_time;
+	uint32_t		res_first_lkid;
+	struct list_head	res_lookup;	/* lkbs waiting on first */
+	struct list_head	res_hashchain;	/* rsbtbl */
+	struct list_head	res_grantqueue;
+	struct list_head	res_convertqueue;
+	struct list_head	res_waitqueue;
+
+	struct list_head	res_root_list;	    /* used for recovery */
+	struct list_head	res_recover_list;   /* used for recovery */
+	int			res_recover_locks_count;
+
+	char			*res_lvbptr;
+	char			res_name[1];
+};
+
+/* find_rsb() flags */
+
+#define R_MASTER		1	/* only return rsb if it's a master */
+#define R_CREATE		2	/* create/add rsb if not found */
+
+/* rsb_flags */
+
+enum rsb_flags {
+	RSB_MASTER_UNCERTAIN,
+	RSB_VALNOTVALID,
+	RSB_VALNOTVALID_PREV,
+	RSB_NEW_MASTER,
+	RSB_NEW_MASTER2,
+	RSB_RECOVER_CONVERT,
+	RSB_LOCKS_PURGED,
+};
+
+static inline void rsb_set_flag(struct dlm_rsb *r, enum rsb_flags flag)
+{
+	__set_bit(flag, &r->res_flags);
+}
+
+static inline void rsb_clear_flag(struct dlm_rsb *r, enum rsb_flags flag)
+{
+	__clear_bit(flag, &r->res_flags);
+}
+
+static inline int rsb_flag(struct dlm_rsb *r, enum rsb_flags flag)
+{
+	return test_bit(flag, &r->res_flags);
+}
+
+
+/* dlm_header is first element of all structs sent between nodes */
+
+#define DLM_HEADER_MAJOR	0x00020000
+#define DLM_HEADER_MINOR	0x00000001
+
+#define DLM_MSG			1
+#define DLM_RCOM		2
+
+struct dlm_header {
+	uint32_t		h_version;
+	uint32_t		h_lockspace;
+	uint32_t		h_nodeid;	/* nodeid of sender */
+	uint16_t		h_length;
+	uint8_t			h_cmd;		/* DLM_MSG, DLM_RCOM */
+	uint8_t			h_pad;
+};
+
+
+#define DLM_MSG_REQUEST		1
+#define DLM_MSG_CONVERT		2
+#define DLM_MSG_UNLOCK		3
+#define DLM_MSG_CANCEL		4
+#define DLM_MSG_REQUEST_REPLY	5
+#define DLM_MSG_CONVERT_REPLY	6
+#define DLM_MSG_UNLOCK_REPLY	7
+#define DLM_MSG_CANCEL_REPLY	8
+#define DLM_MSG_GRANT		9
+#define DLM_MSG_BAST		10
+#define DLM_MSG_LOOKUP		11
+#define DLM_MSG_REMOVE		12
+#define DLM_MSG_LOOKUP_REPLY	13
+
+struct dlm_message {
+	struct dlm_header	m_header;
+	uint32_t		m_type;		/* DLM_MSG_ */
+	uint32_t		m_nodeid;
+	uint32_t		m_pid;
+	uint32_t		m_lkid;		/* lkid on sender */
+	uint32_t		m_remid;	/* lkid on receiver */
+	uint32_t		m_parent_lkid;
+	uint32_t		m_parent_remid;
+	uint32_t		m_exflags;
+	uint32_t		m_sbflags;
+	uint32_t		m_flags;
+	uint32_t		m_lvbseq;
+	uint32_t		m_hash;
+	int			m_status;
+	int			m_grmode;
+	int			m_rqmode;
+	int			m_bastmode;
+	int			m_asts;
+	int			m_result;	/* 0 or -EXXX */
+	char			m_extra[0];	/* name or lvb */
+};
+
+
+#define DLM_RS_NODES		0x00000001
+#define DLM_RS_NODES_ALL	0x00000002
+#define DLM_RS_DIR		0x00000004
+#define DLM_RS_DIR_ALL		0x00000008
+#define DLM_RS_LOCKS		0x00000010
+#define DLM_RS_LOCKS_ALL	0x00000020
+#define DLM_RS_DONE		0x00000040
+#define DLM_RS_DONE_ALL		0x00000080
+
+#define DLM_RCOM_STATUS		1
+#define DLM_RCOM_NAMES		2
+#define DLM_RCOM_LOOKUP		3
+#define DLM_RCOM_LOCK		4
+#define DLM_RCOM_STATUS_REPLY	5
+#define DLM_RCOM_NAMES_REPLY	6
+#define DLM_RCOM_LOOKUP_REPLY	7
+#define DLM_RCOM_LOCK_REPLY	8
+
+struct dlm_rcom {
+	struct dlm_header	rc_header;
+	uint32_t		rc_type;	/* DLM_RCOM_ */
+	int			rc_result;	/* multi-purpose */
+	uint64_t		rc_id;		/* match reply with request */
+	char			rc_buf[0];
+};
+
+struct rcom_config {
+	uint32_t		rf_lvblen;
+	uint32_t		rf_lsflags;
+	uint64_t		rf_unused;
+};
+
+struct rcom_lock {
+	uint32_t		rl_ownpid;
+	uint32_t		rl_lkid;
+	uint32_t		rl_remid;
+	uint32_t		rl_parent_lkid;
+	uint32_t		rl_parent_remid;
+	uint32_t		rl_exflags;
+	uint32_t		rl_flags;
+	uint32_t		rl_lvbseq;
+	int			rl_result;
+	int8_t			rl_rqmode;
+	int8_t			rl_grmode;
+	int8_t			rl_status;
+	int8_t			rl_asts;
+	uint16_t		rl_wait_type;
+	uint16_t		rl_namelen;
+	char			rl_name[DLM_RESNAME_MAXLEN];
+	char			rl_lvb[0];
+};
+
+struct dlm_ls {
+	struct list_head	ls_list;	/* list of lockspaces */
+	dlm_lockspace_t		*ls_local_handle;
+	uint32_t		ls_global_id;	/* global unique lockspace ID */
+	uint32_t		ls_exflags;
+	int			ls_lvblen;
+	int			ls_count;	/* reference count */
+	unsigned long		ls_flags;	/* LSFL_ */
+	struct kobject		ls_kobj;
+
+	struct dlm_rsbtable	*ls_rsbtbl;
+	uint32_t		ls_rsbtbl_size;
+
+	struct dlm_lkbtable	*ls_lkbtbl;
+	uint32_t		ls_lkbtbl_size;
+
+	struct dlm_dirtable	*ls_dirtbl;
+	uint32_t		ls_dirtbl_size;
+
+	struct mutex		ls_waiters_mutex;
+	struct list_head	ls_waiters;	/* lkbs needing a reply */
+
+	struct list_head	ls_nodes;	/* current nodes in ls */
+	struct list_head	ls_nodes_gone;	/* dead node list, recovery */
+	int			ls_num_nodes;	/* number of nodes in ls */
+	int			ls_low_nodeid;
+	int			ls_total_weight;
+	int			*ls_node_array;
+
+	struct dlm_rsb		ls_stub_rsb;	/* for returning errors */
+	struct dlm_lkb		ls_stub_lkb;	/* for returning errors */
+	struct dlm_message	ls_stub_ms;	/* for faking a reply */
+
+	struct dentry		*ls_debug_rsb_dentry; /* debugfs */
+	struct dentry		*ls_debug_waiters_dentry; /* debugfs */
+
+	wait_queue_head_t	ls_uevent_wait;	/* user part of join/leave */
+	int			ls_uevent_result;
+
+	struct miscdevice       ls_device;
+
+	/* recovery related */
+
+	struct timer_list	ls_timer;
+	struct task_struct	*ls_recoverd_task;
+	struct mutex		ls_recoverd_active;
+	spinlock_t		ls_recover_lock;
+	uint32_t		ls_recover_status; /* DLM_RS_ */
+	uint64_t		ls_recover_seq;
+	struct dlm_recover	*ls_recover_args;
+	struct rw_semaphore	ls_in_recovery;	/* block local requests */
+	struct list_head	ls_requestqueue;/* queue remote requests */
+	struct mutex		ls_requestqueue_mutex;
+	char			*ls_recover_buf;
+	int			ls_recover_nodeid; /* for debugging */
+	uint64_t		ls_rcom_seq;
+	struct list_head	ls_recover_list;
+	spinlock_t		ls_recover_list_lock;
+	int			ls_recover_list_count;
+	wait_queue_head_t	ls_wait_general;
+	struct mutex		ls_clear_proc_locks;
+
+	struct list_head	ls_root_list;	/* root resources */
+	struct rw_semaphore	ls_root_sem;	/* protect root_list */
+
+	int			ls_namelen;
+	char			ls_name[1];
+};
+
+#define LSFL_WORK		0
+#define LSFL_RUNNING		1
+#define LSFL_RECOVERY_STOP	2
+#define LSFL_RCOM_READY		3
+#define LSFL_UEVENT_WAIT	4
+
+/* much of this is just saving user space pointers associated with the
+   lock that we pass back to the user lib with an ast */
+
+struct dlm_user_args {
+	struct dlm_user_proc	*proc; /* each process that opens the lockspace
+					  device has private data
+					  (dlm_user_proc) on the struct file,
+					  the process's locks point back to it*/
+	struct dlm_lksb		lksb;
+	int			old_mode;
+	int			update_user_lvb;
+	struct dlm_lksb __user	*user_lksb;
+	void __user		*castparam;
+	void __user		*castaddr;
+	void __user		*bastparam;
+	void __user		*bastaddr;
+};
+
+#define DLM_PROC_FLAGS_CLOSING 1
+#define DLM_PROC_FLAGS_COMPAT  2
+
+/* locks list is kept so we can remove all a process's locks when it
+   exits (or orphan those that are persistent) */
+
+struct dlm_user_proc {
+	dlm_lockspace_t		*lockspace;
+	unsigned long		flags; /* DLM_PROC_FLAGS */
+	struct list_head	asts;
+	spinlock_t		asts_spin;
+	struct list_head	locks;
+	spinlock_t		locks_spin;
+	wait_queue_head_t	wait;
+};
+
+static inline int dlm_locking_stopped(struct dlm_ls *ls)
+{
+	return !test_bit(LSFL_RUNNING, &ls->ls_flags);
+}
+
+static inline int dlm_recovery_stopped(struct dlm_ls *ls)
+{
+	return test_bit(LSFL_RECOVERY_STOP, &ls->ls_flags);
+}
+
+static inline int dlm_no_directory(struct dlm_ls *ls)
+{
+	return (ls->ls_exflags & DLM_LSFL_NODIR) ? 1 : 0;
+}
+
+#endif				/* __DLM_INTERNAL_DOT_H__ */
+

fs/dlm/lock.h

@@ -0,0 +1,62 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __LOCK_DOT_H__
+#define __LOCK_DOT_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);
+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);
+void dlm_put_rsb(struct dlm_rsb *r);
+void dlm_hold_rsb(struct dlm_rsb *r);
+int dlm_put_lkb(struct dlm_lkb *lkb);
+void dlm_scan_rsbs(struct dlm_ls *ls);
+
+int dlm_purge_locks(struct dlm_ls *ls);
+void dlm_purge_mstcpy_locks(struct dlm_rsb *r);
+void dlm_grant_after_purge(struct dlm_ls *ls);
+int dlm_recover_waiters_post(struct dlm_ls *ls);
+void dlm_recover_waiters_pre(struct dlm_ls *ls);
+int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc);
+int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc);
+
+int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, int mode,
+	uint32_t flags, void *name, unsigned int namelen, uint32_t parent_lkid);
+int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
+	int mode, uint32_t flags, uint32_t lkid, char *lvb_in);
+int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
+	uint32_t flags, uint32_t lkid, char *lvb_in);
+int dlm_user_cancel(struct dlm_ls *ls,  struct dlm_user_args *ua_tmp,
+	uint32_t flags, uint32_t lkid);
+void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc);
+
+static inline int is_master(struct dlm_rsb *r)
+{
+	return !r->res_nodeid;
+}
+
+static inline void lock_rsb(struct dlm_rsb *r)
+{
+	mutex_lock(&r->res_mutex);
+}
+
+static inline void unlock_rsb(struct dlm_rsb *r)
+{
+	mutex_unlock(&r->res_mutex);
+}
+
+#endif
+

fs/dlm/lockspace.c

@@ -0,0 +1,717 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "member.h"
+#include "recoverd.h"
+#include "ast.h"
+#include "dir.h"
+#include "lowcomms.h"
+#include "config.h"
+#include "memory.h"
+#include "lock.h"
+#include "recover.h"
+
+#ifdef CONFIG_DLM_DEBUG
+int dlm_create_debug_file(struct dlm_ls *ls);
+void dlm_delete_debug_file(struct dlm_ls *ls);
+#else
+static inline int dlm_create_debug_file(struct dlm_ls *ls) { return 0; }
+static inline void dlm_delete_debug_file(struct dlm_ls *ls) { }
+#endif
+
+static int			ls_count;
+static struct mutex		ls_lock;
+static struct list_head		lslist;
+static spinlock_t		lslist_lock;
+static struct task_struct *	scand_task;
+
+
+static ssize_t dlm_control_store(struct dlm_ls *ls, const char *buf, size_t len)
+{
+	ssize_t ret = len;
+	int n = simple_strtol(buf, NULL, 0);
+
+	switch (n) {
+	case 0:
+		dlm_ls_stop(ls);
+		break;
+	case 1:
+		dlm_ls_start(ls);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	return ret;
+}
+
+static ssize_t dlm_event_store(struct dlm_ls *ls, const char *buf, size_t len)
+{
+	ls->ls_uevent_result = simple_strtol(buf, NULL, 0);
+	set_bit(LSFL_UEVENT_WAIT, &ls->ls_flags);
+	wake_up(&ls->ls_uevent_wait);
+	return len;
+}
+
+static ssize_t dlm_id_show(struct dlm_ls *ls, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%u\n", ls->ls_global_id);
+}
+
+static ssize_t dlm_id_store(struct dlm_ls *ls, const char *buf, size_t len)
+{
+	ls->ls_global_id = simple_strtoul(buf, NULL, 0);
+	return len;
+}
+
+static ssize_t dlm_recover_status_show(struct dlm_ls *ls, char *buf)
+{
+	uint32_t status = dlm_recover_status(ls);
+	return snprintf(buf, PAGE_SIZE, "%x\n", status);
+}
+
+static ssize_t dlm_recover_nodeid_show(struct dlm_ls *ls, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", ls->ls_recover_nodeid);
+}
+
+struct dlm_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct dlm_ls *, char *);
+	ssize_t (*store)(struct dlm_ls *, const char *, size_t);
+};
+
+static struct dlm_attr dlm_attr_control = {
+	.attr  = {.name = "control", .mode = S_IWUSR},
+	.store = dlm_control_store
+};
+
+static struct dlm_attr dlm_attr_event = {
+	.attr  = {.name = "event_done", .mode = S_IWUSR},
+	.store = dlm_event_store
+};
+
+static struct dlm_attr dlm_attr_id = {
+	.attr  = {.name = "id", .mode = S_IRUGO | S_IWUSR},
+	.show  = dlm_id_show,
+	.store = dlm_id_store
+};
+
+static struct dlm_attr dlm_attr_recover_status = {
+	.attr  = {.name = "recover_status", .mode = S_IRUGO},
+	.show  = dlm_recover_status_show
+};
+
+static struct dlm_attr dlm_attr_recover_nodeid = {
+	.attr  = {.name = "recover_nodeid", .mode = S_IRUGO},
+	.show  = dlm_recover_nodeid_show
+};
+
+static struct attribute *dlm_attrs[] = {
+	&dlm_attr_control.attr,
+	&dlm_attr_event.attr,
+	&dlm_attr_id.attr,
+	&dlm_attr_recover_status.attr,
+	&dlm_attr_recover_nodeid.attr,
+	NULL,
+};
+
+static ssize_t dlm_attr_show(struct kobject *kobj, struct attribute *attr,
+			     char *buf)
+{
+	struct dlm_ls *ls  = container_of(kobj, struct dlm_ls, ls_kobj);
+	struct dlm_attr *a = container_of(attr, struct dlm_attr, attr);
+	return a->show ? a->show(ls, buf) : 0;
+}
+
+static ssize_t dlm_attr_store(struct kobject *kobj, struct attribute *attr,
+			      const char *buf, size_t len)
+{
+	struct dlm_ls *ls  = container_of(kobj, struct dlm_ls, ls_kobj);
+	struct dlm_attr *a = container_of(attr, struct dlm_attr, attr);
+	return a->store ? a->store(ls, buf, len) : len;
+}
+
+static struct sysfs_ops dlm_attr_ops = {
+	.show  = dlm_attr_show,
+	.store = dlm_attr_store,
+};
+
+static struct kobj_type dlm_ktype = {
+	.default_attrs = dlm_attrs,
+	.sysfs_ops     = &dlm_attr_ops,
+};
+
+static struct kset dlm_kset = {
+	.subsys = &kernel_subsys,
+	.kobj   = {.name = "dlm",},
+	.ktype  = &dlm_ktype,
+};
+
+static int kobject_setup(struct dlm_ls *ls)
+{
+	char lsname[DLM_LOCKSPACE_LEN];
+	int error;
+
+	memset(lsname, 0, DLM_LOCKSPACE_LEN);
+	snprintf(lsname, DLM_LOCKSPACE_LEN, "%s", ls->ls_name);
+
+	error = kobject_set_name(&ls->ls_kobj, "%s", lsname);
+	if (error)
+		return error;
+
+	ls->ls_kobj.kset = &dlm_kset;
+	ls->ls_kobj.ktype = &dlm_ktype;
+	return 0;
+}
+
+static int do_uevent(struct dlm_ls *ls, int in)
+{
+	int error;
+
+	if (in)
+		kobject_uevent(&ls->ls_kobj, KOBJ_ONLINE);
+	else
+		kobject_uevent(&ls->ls_kobj, KOBJ_OFFLINE);
+
+	error = wait_event_interruptible(ls->ls_uevent_wait,
+			test_and_clear_bit(LSFL_UEVENT_WAIT, &ls->ls_flags));
+	if (error)
+		goto out;
+
+	error = ls->ls_uevent_result;
+ out:
+	return error;
+}
+
+
+int dlm_lockspace_init(void)
+{
+	int error;
+
+	ls_count = 0;
+	mutex_init(&ls_lock);
+	INIT_LIST_HEAD(&lslist);
+	spin_lock_init(&lslist_lock);
+
+	error = kset_register(&dlm_kset);
+	if (error)
+		printk("dlm_lockspace_init: cannot register kset %d\n", error);
+	return error;
+}
+
+void dlm_lockspace_exit(void)
+{
+	kset_unregister(&dlm_kset);
+}
+
+static int dlm_scand(void *data)
+{
+	struct dlm_ls *ls;
+
+	while (!kthread_should_stop()) {
+		list_for_each_entry(ls, &lslist, ls_list)
+			dlm_scan_rsbs(ls);
+		schedule_timeout_interruptible(dlm_config.scan_secs * HZ);
+	}
+	return 0;
+}
+
+static int dlm_scand_start(void)
+{
+	struct task_struct *p;
+	int error = 0;
+
+	p = kthread_run(dlm_scand, NULL, "dlm_scand");
+	if (IS_ERR(p))
+		error = PTR_ERR(p);
+	else
+		scand_task = p;
+	return error;
+}
+
+static void dlm_scand_stop(void)
+{
+	kthread_stop(scand_task);
+}
+
+static struct dlm_ls *dlm_find_lockspace_name(char *name, int namelen)
+{
+	struct dlm_ls *ls;
+
+	spin_lock(&lslist_lock);
+
+	list_for_each_entry(ls, &lslist, ls_list) {
+		if (ls->ls_namelen == namelen &&
+		    memcmp(ls->ls_name, name, namelen) == 0)
+			goto out;
+	}
+	ls = NULL;
+ out:
+	spin_unlock(&lslist_lock);
+	return ls;
+}
+
+struct dlm_ls *dlm_find_lockspace_global(uint32_t id)
+{
+	struct dlm_ls *ls;
+
+	spin_lock(&lslist_lock);
+
+	list_for_each_entry(ls, &lslist, ls_list) {
+		if (ls->ls_global_id == id) {
+			ls->ls_count++;
+			goto out;
+		}
+	}
+	ls = NULL;
+ out:
+	spin_unlock(&lslist_lock);
+	return ls;
+}
+
+struct dlm_ls *dlm_find_lockspace_local(dlm_lockspace_t *lockspace)
+{
+	struct dlm_ls *ls;
+
+	spin_lock(&lslist_lock);
+	list_for_each_entry(ls, &lslist, ls_list) {
+		if (ls->ls_local_handle == lockspace) {
+			ls->ls_count++;
+			goto out;
+		}
+	}
+	ls = NULL;
+ out:
+	spin_unlock(&lslist_lock);
+	return ls;
+}
+
+struct dlm_ls *dlm_find_lockspace_device(int minor)
+{
+	struct dlm_ls *ls;
+
+	spin_lock(&lslist_lock);
+	list_for_each_entry(ls, &lslist, ls_list) {
+		if (ls->ls_device.minor == minor) {
+			ls->ls_count++;
+			goto out;
+		}
+	}
+	ls = NULL;
+ out:
+	spin_unlock(&lslist_lock);
+	return ls;
+}
+
+void dlm_put_lockspace(struct dlm_ls *ls)
+{
+	spin_lock(&lslist_lock);
+	ls->ls_count--;
+	spin_unlock(&lslist_lock);
+}
+
+static void remove_lockspace(struct dlm_ls *ls)
+{
+	for (;;) {
+		spin_lock(&lslist_lock);
+		if (ls->ls_count == 0) {
+			list_del(&ls->ls_list);
+			spin_unlock(&lslist_lock);
+			return;
+		}
+		spin_unlock(&lslist_lock);
+		ssleep(1);
+	}
+}
+
+static int threads_start(void)
+{
+	int error;
+
+	/* Thread which process lock requests for all lockspace's */
+	error = dlm_astd_start();
+	if (error) {
+		log_print("cannot start dlm_astd thread %d", error);
+		goto fail;
+	}
+
+	error = dlm_scand_start();
+	if (error) {
+		log_print("cannot start dlm_scand thread %d", error);
+		goto astd_fail;
+	}
+
+	/* Thread for sending/receiving messages for all lockspace's */
+	error = dlm_lowcomms_start();
+	if (error) {
+		log_print("cannot start dlm lowcomms %d", error);
+		goto scand_fail;
+	}
+
+	return 0;
+
+ scand_fail:
+	dlm_scand_stop();
+ astd_fail:
+	dlm_astd_stop();
+ fail:
+	return error;
+}
+
+static void threads_stop(void)
+{
+	dlm_scand_stop();
+	dlm_lowcomms_stop();
+	dlm_astd_stop();
+}
+
+static int new_lockspace(char *name, int namelen, void **lockspace,
+			 uint32_t flags, int lvblen)
+{
+	struct dlm_ls *ls;
+	int i, size, error = -ENOMEM;
+
+	if (namelen > DLM_LOCKSPACE_LEN)
+		return -EINVAL;
+
+	if (!lvblen || (lvblen % 8))
+		return -EINVAL;
+
+	if (!try_module_get(THIS_MODULE))
+		return -EINVAL;
+
+	ls = dlm_find_lockspace_name(name, namelen);
+	if (ls) {
+		*lockspace = ls;
+		module_put(THIS_MODULE);
+		return -EEXIST;
+	}
+
+	ls = kzalloc(sizeof(struct dlm_ls) + namelen, GFP_KERNEL);
+	if (!ls)
+		goto out;
+	memcpy(ls->ls_name, name, namelen);
+	ls->ls_namelen = namelen;
+	ls->ls_exflags = flags;
+	ls->ls_lvblen = lvblen;
+	ls->ls_count = 0;
+	ls->ls_flags = 0;
+
+	size = dlm_config.rsbtbl_size;
+	ls->ls_rsbtbl_size = size;
+
+	ls->ls_rsbtbl = kmalloc(sizeof(struct dlm_rsbtable) * size, GFP_KERNEL);
+	if (!ls->ls_rsbtbl)
+		goto out_lsfree;
+	for (i = 0; i < size; i++) {
+		INIT_LIST_HEAD(&ls->ls_rsbtbl[i].list);
+		INIT_LIST_HEAD(&ls->ls_rsbtbl[i].toss);
+		rwlock_init(&ls->ls_rsbtbl[i].lock);
+	}
+
+	size = dlm_config.lkbtbl_size;
+	ls->ls_lkbtbl_size = size;
+
+	ls->ls_lkbtbl = kmalloc(sizeof(struct dlm_lkbtable) * size, GFP_KERNEL);
+	if (!ls->ls_lkbtbl)
+		goto out_rsbfree;
+	for (i = 0; i < size; i++) {
+		INIT_LIST_HEAD(&ls->ls_lkbtbl[i].list);
+		rwlock_init(&ls->ls_lkbtbl[i].lock);
+		ls->ls_lkbtbl[i].counter = 1;
+	}
+
+	size = dlm_config.dirtbl_size;
+	ls->ls_dirtbl_size = size;
+
+	ls->ls_dirtbl = kmalloc(sizeof(struct dlm_dirtable) * size, GFP_KERNEL);
+	if (!ls->ls_dirtbl)
+		goto out_lkbfree;
+	for (i = 0; i < size; i++) {
+		INIT_LIST_HEAD(&ls->ls_dirtbl[i].list);
+		rwlock_init(&ls->ls_dirtbl[i].lock);
+	}
+
+	INIT_LIST_HEAD(&ls->ls_waiters);
+	mutex_init(&ls->ls_waiters_mutex);
+
+	INIT_LIST_HEAD(&ls->ls_nodes);
+	INIT_LIST_HEAD(&ls->ls_nodes_gone);
+	ls->ls_num_nodes = 0;
+	ls->ls_low_nodeid = 0;
+	ls->ls_total_weight = 0;
+	ls->ls_node_array = NULL;
+
+	memset(&ls->ls_stub_rsb, 0, sizeof(struct dlm_rsb));
+	ls->ls_stub_rsb.res_ls = ls;
+
+	ls->ls_debug_rsb_dentry = NULL;
+	ls->ls_debug_waiters_dentry = NULL;
+
+	init_waitqueue_head(&ls->ls_uevent_wait);
+	ls->ls_uevent_result = 0;
+
+	ls->ls_recoverd_task = NULL;
+	mutex_init(&ls->ls_recoverd_active);
+	spin_lock_init(&ls->ls_recover_lock);
+	ls->ls_recover_status = 0;
+	ls->ls_recover_seq = 0;
+	ls->ls_recover_args = NULL;
+	init_rwsem(&ls->ls_in_recovery);
+	INIT_LIST_HEAD(&ls->ls_requestqueue);
+	mutex_init(&ls->ls_requestqueue_mutex);
+	mutex_init(&ls->ls_clear_proc_locks);
+
+	ls->ls_recover_buf = kmalloc(dlm_config.buffer_size, GFP_KERNEL);
+	if (!ls->ls_recover_buf)
+		goto out_dirfree;
+
+	INIT_LIST_HEAD(&ls->ls_recover_list);
+	spin_lock_init(&ls->ls_recover_list_lock);
+	ls->ls_recover_list_count = 0;
+	ls->ls_local_handle = ls;
+	init_waitqueue_head(&ls->ls_wait_general);
+	INIT_LIST_HEAD(&ls->ls_root_list);
+	init_rwsem(&ls->ls_root_sem);
+
+	down_write(&ls->ls_in_recovery);
+
+	spin_lock(&lslist_lock);
+	list_add(&ls->ls_list, &lslist);
+	spin_unlock(&lslist_lock);
+
+	/* needs to find ls in lslist */
+	error = dlm_recoverd_start(ls);
+	if (error) {
+		log_error(ls, "can't start dlm_recoverd %d", error);
+		goto out_rcomfree;
+	}
+
+	dlm_create_debug_file(ls);
+
+	error = kobject_setup(ls);
+	if (error)
+		goto out_del;
+
+	error = kobject_register(&ls->ls_kobj);
+	if (error)
+		goto out_del;
+
+	error = do_uevent(ls, 1);
+	if (error)
+		goto out_unreg;
+
+	*lockspace = ls;
+	return 0;
+
+ out_unreg:
+	kobject_unregister(&ls->ls_kobj);
+ out_del:
+	dlm_delete_debug_file(ls);
+	dlm_recoverd_stop(ls);
+ out_rcomfree:
+	spin_lock(&lslist_lock);
+	list_del(&ls->ls_list);
+	spin_unlock(&lslist_lock);
+	kfree(ls->ls_recover_buf);
+ out_dirfree:
+	kfree(ls->ls_dirtbl);
+ out_lkbfree:
+	kfree(ls->ls_lkbtbl);
+ out_rsbfree:
+	kfree(ls->ls_rsbtbl);
+ out_lsfree:
+	kfree(ls);
+ out:
+	module_put(THIS_MODULE);
+	return error;
+}
+
+int dlm_new_lockspace(char *name, int namelen, void **lockspace,
+		      uint32_t flags, int lvblen)
+{
+	int error = 0;
+
+	mutex_lock(&ls_lock);
+	if (!ls_count)
+		error = threads_start();
+	if (error)
+		goto out;
+
+	error = new_lockspace(name, namelen, lockspace, flags, lvblen);
+	if (!error)
+		ls_count++;
+ out:
+	mutex_unlock(&ls_lock);
+	return error;
+}
+
+/* Return 1 if the lockspace still has active remote locks,
+ *        2 if the lockspace still has active local locks.
+ */
+static int lockspace_busy(struct dlm_ls *ls)
+{
+	int i, lkb_found = 0;
+	struct dlm_lkb *lkb;
+
+	/* NOTE: We check the lockidtbl here rather than the resource table.
+	   This is because there may be LKBs queued as ASTs that have been
+	   unlinked from their RSBs and are pending deletion once the AST has
+	   been delivered */
+
+	for (i = 0; i < ls->ls_lkbtbl_size; i++) {
+		read_lock(&ls->ls_lkbtbl[i].lock);
+		if (!list_empty(&ls->ls_lkbtbl[i].list)) {
+			lkb_found = 1;
+			list_for_each_entry(lkb, &ls->ls_lkbtbl[i].list,
+					    lkb_idtbl_list) {
+				if (!lkb->lkb_nodeid) {
+					read_unlock(&ls->ls_lkbtbl[i].lock);
+					return 2;
+				}
+			}
+		}
+		read_unlock(&ls->ls_lkbtbl[i].lock);
+	}
+	return lkb_found;
+}
+
+static int release_lockspace(struct dlm_ls *ls, int force)
+{
+	struct dlm_lkb *lkb;
+	struct dlm_rsb *rsb;
+	struct list_head *head;
+	int i;
+	int busy = lockspace_busy(ls);
+
+	if (busy > force)
+		return -EBUSY;
+
+	if (force < 3)
+		do_uevent(ls, 0);
+
+	dlm_recoverd_stop(ls);
+
+	remove_lockspace(ls);
+
+	dlm_delete_debug_file(ls);
+
+	dlm_astd_suspend();
+
+	kfree(ls->ls_recover_buf);
+
+	/*
+	 * Free direntry structs.
+	 */
+
+	dlm_dir_clear(ls);
+	kfree(ls->ls_dirtbl);
+
+	/*
+	 * Free all lkb's on lkbtbl[] lists.
+	 */
+
+	for (i = 0; i < ls->ls_lkbtbl_size; i++) {
+		head = &ls->ls_lkbtbl[i].list;
+		while (!list_empty(head)) {
+			lkb = list_entry(head->next, struct dlm_lkb,
+					 lkb_idtbl_list);
+
+			list_del(&lkb->lkb_idtbl_list);
+
+			dlm_del_ast(lkb);
+
+			if (lkb->lkb_lvbptr && lkb->lkb_flags & DLM_IFL_MSTCPY)
+				free_lvb(lkb->lkb_lvbptr);
+
+			free_lkb(lkb);
+		}
+	}
+	dlm_astd_resume();
+
+	kfree(ls->ls_lkbtbl);
+
+	/*
+	 * Free all rsb's on rsbtbl[] lists
+	 */
+
+	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
+		head = &ls->ls_rsbtbl[i].list;
+		while (!list_empty(head)) {
+			rsb = list_entry(head->next, struct dlm_rsb,
+					 res_hashchain);
+
+			list_del(&rsb->res_hashchain);
+			free_rsb(rsb);
+		}
+
+		head = &ls->ls_rsbtbl[i].toss;
+		while (!list_empty(head)) {
+			rsb = list_entry(head->next, struct dlm_rsb,
+					 res_hashchain);
+			list_del(&rsb->res_hashchain);
+			free_rsb(rsb);
+		}
+	}
+
+	kfree(ls->ls_rsbtbl);
+
+	/*
+	 * Free structures on any other lists
+	 */
+
+	kfree(ls->ls_recover_args);
+	dlm_clear_free_entries(ls);
+	dlm_clear_members(ls);
+	dlm_clear_members_gone(ls);
+	kfree(ls->ls_node_array);
+	kobject_unregister(&ls->ls_kobj);
+	kfree(ls);
+
+	mutex_lock(&ls_lock);
+	ls_count--;
+	if (!ls_count)
+		threads_stop();
+	mutex_unlock(&ls_lock);
+
+	module_put(THIS_MODULE);
+	return 0;
+}
+
+/*
+ * Called when a system has released all its locks and is not going to use the
+ * lockspace any longer.  We free everything we're managing for this lockspace.
+ * Remaining nodes will go through the recovery process as if we'd died.  The
+ * lockspace must continue to function as usual, participating in recoveries,
+ * until this returns.
+ *
+ * Force has 4 possible values:
+ * 0 - don't destroy locksapce if it has any LKBs
+ * 1 - destroy lockspace if it has remote LKBs but not if it has local LKBs
+ * 2 - destroy lockspace regardless of LKBs
+ * 3 - destroy lockspace as part of a forced shutdown
+ */
+
+int dlm_release_lockspace(void *lockspace, int force)
+{
+	struct dlm_ls *ls;
+
+	ls = dlm_find_lockspace_local(lockspace);
+	if (!ls)
+		return -EINVAL;
+	dlm_put_lockspace(ls);
+	return release_lockspace(ls, force);
+}
+

fs/dlm/lockspace.h

@@ -0,0 +1,25 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __LOCKSPACE_DOT_H__
+#define __LOCKSPACE_DOT_H__
+
+int dlm_lockspace_init(void);
+void dlm_lockspace_exit(void);
+struct dlm_ls *dlm_find_lockspace_global(uint32_t id);
+struct dlm_ls *dlm_find_lockspace_local(void *id);
+struct dlm_ls *dlm_find_lockspace_device(int minor);
+void dlm_put_lockspace(struct dlm_ls *ls);
+
+#endif				/* __LOCKSPACE_DOT_H__ */
+

fs/dlm/lowcomms.h

@@ -0,0 +1,26 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __LOWCOMMS_DOT_H__
+#define __LOWCOMMS_DOT_H__
+
+int dlm_lowcomms_init(void);
+void dlm_lowcomms_exit(void);
+int dlm_lowcomms_start(void);
+void dlm_lowcomms_stop(void);
+int dlm_lowcomms_close(int nodeid);
+void *dlm_lowcomms_get_buffer(int nodeid, int len, int allocation, char **ppc);
+void dlm_lowcomms_commit_buffer(void *mh);
+
+#endif				/* __LOWCOMMS_DOT_H__ */
+

fs/dlm/lvb_table.h

@@ -0,0 +1,18 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __LVB_TABLE_DOT_H__
+#define __LVB_TABLE_DOT_H__
+
+extern const int dlm_lvb_operations[8][8];
+
+#endif

fs/dlm/main.c

@@ -0,0 +1,97 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "lock.h"
+#include "user.h"
+#include "memory.h"
+#include "lowcomms.h"
+#include "config.h"
+
+#ifdef CONFIG_DLM_DEBUG
+int dlm_register_debugfs(void);
+void dlm_unregister_debugfs(void);
+#else
+static inline int dlm_register_debugfs(void) { return 0; }
+static inline void dlm_unregister_debugfs(void) { }
+#endif
+
+static int __init init_dlm(void)
+{
+	int error;
+
+	error = dlm_memory_init();
+	if (error)
+		goto out;
+
+	error = dlm_lockspace_init();
+	if (error)
+		goto out_mem;
+
+	error = dlm_config_init();
+	if (error)
+		goto out_lockspace;
+
+	error = dlm_register_debugfs();
+	if (error)
+		goto out_config;
+
+	error = dlm_lowcomms_init();
+	if (error)
+		goto out_debug;
+
+	error = dlm_user_init();
+	if (error)
+		goto out_lowcomms;
+
+	printk("DLM (built %s %s) installed\n", __DATE__, __TIME__);
+
+	return 0;
+
+ out_lowcomms:
+	dlm_lowcomms_exit();
+ out_debug:
+	dlm_unregister_debugfs();
+ out_config:
+	dlm_config_exit();
+ out_lockspace:
+	dlm_lockspace_exit();
+ out_mem:
+	dlm_memory_exit();
+ out:
+	return error;
+}
+
+static void __exit exit_dlm(void)
+{
+	dlm_user_exit();
+	dlm_lowcomms_exit();
+	dlm_config_exit();
+	dlm_memory_exit();
+	dlm_lockspace_exit();
+	dlm_unregister_debugfs();
+}
+
+module_init(init_dlm);
+module_exit(exit_dlm);
+
+MODULE_DESCRIPTION("Distributed Lock Manager");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+EXPORT_SYMBOL_GPL(dlm_new_lockspace);
+EXPORT_SYMBOL_GPL(dlm_release_lockspace);
+EXPORT_SYMBOL_GPL(dlm_lock);
+EXPORT_SYMBOL_GPL(dlm_unlock);
+

fs/dlm/member.c

@@ -0,0 +1,327 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "member.h"
+#include "recoverd.h"
+#include "recover.h"
+#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;
+	struct list_head *tmp;
+	struct list_head *newlist = &new->list;
+	struct list_head *head = &ls->ls_nodes;
+
+	list_for_each(tmp, head) {
+		memb = list_entry(tmp, struct dlm_member, list);
+		if (new->nodeid < memb->nodeid)
+			break;
+	}
+
+	if (!memb)
+		list_add_tail(newlist, head);
+	else {
+		/* FIXME: can use list macro here */
+		newlist->prev = tmp->prev;
+		newlist->next = tmp;
+		tmp->prev->next = newlist;
+		tmp->prev = newlist;
+	}
+}
+
+static int dlm_add_member(struct dlm_ls *ls, int nodeid)
+{
+	struct dlm_member *memb;
+	int w;
+
+	memb = kzalloc(sizeof(struct dlm_member), GFP_KERNEL);
+	if (!memb)
+		return -ENOMEM;
+
+	w = dlm_node_weight(ls->ls_name, nodeid);
+	if (w < 0)
+		return w;
+
+	memb->nodeid = nodeid;
+	memb->weight = w;
+	add_ordered_member(ls, memb);
+	ls->ls_num_nodes++;
+	return 0;
+}
+
+static void dlm_remove_member(struct dlm_ls *ls, struct dlm_member *memb)
+{
+	list_move(&memb->list, &ls->ls_nodes_gone);
+	ls->ls_num_nodes--;
+}
+
+static int dlm_is_member(struct dlm_ls *ls, int nodeid)
+{
+	struct dlm_member *memb;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (memb->nodeid == nodeid)
+			return 1;
+	}
+	return 0;
+}
+
+int dlm_is_removed(struct dlm_ls *ls, int nodeid)
+{
+	struct dlm_member *memb;
+
+	list_for_each_entry(memb, &ls->ls_nodes_gone, list) {
+		if (memb->nodeid == nodeid)
+			return 1;
+	}
+	return 0;
+}
+
+static void clear_memb_list(struct list_head *head)
+{
+	struct dlm_member *memb;
+
+	while (!list_empty(head)) {
+		memb = list_entry(head->next, struct dlm_member, list);
+		list_del(&memb->list);
+		kfree(memb);
+	}
+}
+
+void dlm_clear_members(struct dlm_ls *ls)
+{
+	clear_memb_list(&ls->ls_nodes);
+	ls->ls_num_nodes = 0;
+}
+
+void dlm_clear_members_gone(struct dlm_ls *ls)
+{
+	clear_memb_list(&ls->ls_nodes_gone);
+}
+
+static void make_member_array(struct dlm_ls *ls)
+{
+	struct dlm_member *memb;
+	int i, w, x = 0, total = 0, all_zero = 0, *array;
+
+	kfree(ls->ls_node_array);
+	ls->ls_node_array = NULL;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (memb->weight)
+			total += memb->weight;
+	}
+
+	/* all nodes revert to weight of 1 if all have weight 0 */
+
+	if (!total) {
+		total = ls->ls_num_nodes;
+		all_zero = 1;
+	}
+
+	ls->ls_total_weight = total;
+
+	array = kmalloc(sizeof(int) * total, GFP_KERNEL);
+	if (!array)
+		return;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (!all_zero && !memb->weight)
+			continue;
+
+		if (all_zero)
+			w = 1;
+		else
+			w = memb->weight;
+
+		DLM_ASSERT(x < total, printk("total %d x %d\n", total, x););
+
+		for (i = 0; i < w; i++)
+			array[x++] = memb->nodeid;
+	}
+
+	ls->ls_node_array = array;
+}
+
+/* send a status request to all members just to establish comms connections */
+
+static int ping_members(struct dlm_ls *ls)
+{
+	struct dlm_member *memb;
+	int error = 0;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		error = dlm_recovery_stopped(ls);
+		if (error)
+			break;
+		error = dlm_rcom_status(ls, memb->nodeid);
+		if (error)
+			break;
+	}
+	if (error)
+		log_debug(ls, "ping_members aborted %d last nodeid %d",
+			  error, ls->ls_recover_nodeid);
+	return error;
+}
+
+int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
+{
+	struct dlm_member *memb, *safe;
+	int i, error, found, pos = 0, neg = 0, low = -1;
+
+	/* move departed members from ls_nodes to ls_nodes_gone */
+
+	list_for_each_entry_safe(memb, safe, &ls->ls_nodes, list) {
+		found = 0;
+		for (i = 0; i < rv->node_count; i++) {
+			if (memb->nodeid == rv->nodeids[i]) {
+				found = 1;
+				break;
+			}
+		}
+
+		if (!found) {
+			neg++;
+			dlm_remove_member(ls, memb);
+			log_debug(ls, "remove member %d", memb->nodeid);
+		}
+	}
+
+	/* add new members to ls_nodes */
+
+	for (i = 0; i < rv->node_count; i++) {
+		if (dlm_is_member(ls, rv->nodeids[i]))
+			continue;
+		dlm_add_member(ls, rv->nodeids[i]);
+		pos++;
+		log_debug(ls, "add member %d", rv->nodeids[i]);
+	}
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		if (low == -1 || memb->nodeid < low)
+			low = memb->nodeid;
+	}
+	ls->ls_low_nodeid = low;
+
+	make_member_array(ls);
+	dlm_set_recover_status(ls, DLM_RS_NODES);
+	*neg_out = neg;
+
+	error = ping_members(ls);
+	if (error)
+		goto out;
+
+	error = dlm_recover_members_wait(ls);
+ out:
+	log_debug(ls, "total members %d error %d", ls->ls_num_nodes, error);
+	return error;
+}
+
+/*
+ * Following called from lockspace.c
+ */
+
+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()).
+	 */
+
+	spin_lock(&ls->ls_recover_lock);
+	set_bit(LSFL_RECOVERY_STOP, &ls->ls_flags);
+	new = test_and_clear_bit(LSFL_RUNNING, &ls->ls_flags);
+	ls->ls_recover_seq++;
+	spin_unlock(&ls->ls_recover_lock);
+
+	/*
+	 * 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
+	 *    when recovery is complete.
+	 */
+
+	if (new)
+		down_write(&ls->ls_in_recovery);
+
+	/*
+	 * 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.
+	 */
+
+	dlm_recoverd_suspend(ls);
+	ls->ls_recover_status = 0;
+	dlm_recoverd_resume(ls);
+	return 0;
+}
+
+int dlm_ls_start(struct dlm_ls *ls)
+{
+	struct dlm_recover *rv = NULL, *rv_old;
+	int *ids = NULL;
+	int error, count;
+
+	rv = kzalloc(sizeof(struct dlm_recover), GFP_KERNEL);
+	if (!rv)
+		return -ENOMEM;
+
+	error = count = dlm_nodeid_list(ls->ls_name, &ids);
+	if (error <= 0)
+		goto fail;
+
+	spin_lock(&ls->ls_recover_lock);
+
+	/* the lockspace needs to be stopped before it can be started */
+
+	if (!dlm_locking_stopped(ls)) {
+		spin_unlock(&ls->ls_recover_lock);
+		log_error(ls, "start ignored: lockspace running");
+		error = -EINVAL;
+		goto fail;
+	}
+
+	rv->nodeids = ids;
+	rv->node_count = count;
+	rv->seq = ++ls->ls_recover_seq;
+	rv_old = ls->ls_recover_args;
+	ls->ls_recover_args = rv;
+	spin_unlock(&ls->ls_recover_lock);
+
+	if (rv_old) {
+		kfree(rv_old->nodeids);
+		kfree(rv_old);
+	}
+
+	dlm_recoverd_kick(ls);
+	return 0;
+
+ fail:
+	kfree(rv);
+	kfree(ids);
+	return error;
+}
+

fs/dlm/member.h

@@ -0,0 +1,24 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __MEMBER_DOT_H__
+#define __MEMBER_DOT_H__
+
+int dlm_ls_stop(struct dlm_ls *ls);
+int dlm_ls_start(struct dlm_ls *ls);
+void dlm_clear_members(struct dlm_ls *ls);
+void dlm_clear_members_gone(struct dlm_ls *ls);
+int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv,int *neg_out);
+int dlm_is_removed(struct dlm_ls *ls, int nodeid);
+
+#endif                          /* __MEMBER_DOT_H__ */
+

fs/dlm/memory.c

@@ -0,0 +1,116 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "config.h"
+#include "memory.h"
+
+static kmem_cache_t *lkb_cache;
+
+
+int dlm_memory_init(void)
+{
+	int ret = 0;
+
+	lkb_cache = kmem_cache_create("dlm_lkb", sizeof(struct dlm_lkb),
+				__alignof__(struct dlm_lkb), 0, NULL, NULL);
+	if (!lkb_cache)
+		ret = -ENOMEM;
+	return ret;
+}
+
+void dlm_memory_exit(void)
+{
+	if (lkb_cache)
+		kmem_cache_destroy(lkb_cache);
+}
+
+char *allocate_lvb(struct dlm_ls *ls)
+{
+	char *p;
+
+	p = kmalloc(ls->ls_lvblen, GFP_KERNEL);
+	if (p)
+		memset(p, 0, ls->ls_lvblen);
+	return p;
+}
+
+void free_lvb(char *p)
+{
+	kfree(p);
+}
+
+/* FIXME: have some minimal space built-in to rsb for the name and
+   kmalloc a separate name if needed, like dentries are done */
+
+struct dlm_rsb *allocate_rsb(struct dlm_ls *ls, int namelen)
+{
+	struct dlm_rsb *r;
+
+	DLM_ASSERT(namelen <= DLM_RESNAME_MAXLEN,);
+
+	r = kmalloc(sizeof(*r) + namelen, GFP_KERNEL);
+	if (r)
+		memset(r, 0, sizeof(*r) + namelen);
+	return r;
+}
+
+void free_rsb(struct dlm_rsb *r)
+{
+	if (r->res_lvbptr)
+		free_lvb(r->res_lvbptr);
+	kfree(r);
+}
+
+struct dlm_lkb *allocate_lkb(struct dlm_ls *ls)
+{
+	struct dlm_lkb *lkb;
+
+	lkb = kmem_cache_alloc(lkb_cache, GFP_KERNEL);
+	if (lkb)
+		memset(lkb, 0, sizeof(*lkb));
+	return lkb;
+}
+
+void free_lkb(struct dlm_lkb *lkb)
+{
+	if (lkb->lkb_flags & DLM_IFL_USER) {
+		struct dlm_user_args *ua;
+		ua = (struct dlm_user_args *)lkb->lkb_astparam;
+		if (ua) {
+			if (ua->lksb.sb_lvbptr)
+				kfree(ua->lksb.sb_lvbptr);
+			kfree(ua);
+		}
+	}
+	kmem_cache_free(lkb_cache, lkb);
+}
+
+struct dlm_direntry *allocate_direntry(struct dlm_ls *ls, int namelen)
+{
+	struct dlm_direntry *de;
+
+	DLM_ASSERT(namelen <= DLM_RESNAME_MAXLEN,
+		   printk("namelen = %d\n", namelen););
+
+	de = kmalloc(sizeof(*de) + namelen, GFP_KERNEL);
+	if (de)
+		memset(de, 0, sizeof(*de) + namelen);
+	return de;
+}
+
+void free_direntry(struct dlm_direntry *de)
+{
+	kfree(de);
+}
+

fs/dlm/memory.h

@@ -0,0 +1,29 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __MEMORY_DOT_H__
+#define __MEMORY_DOT_H__
+
+int dlm_memory_init(void);
+void dlm_memory_exit(void);
+struct dlm_rsb *allocate_rsb(struct dlm_ls *ls, int namelen);
+void free_rsb(struct dlm_rsb *r);
+struct dlm_lkb *allocate_lkb(struct dlm_ls *ls);
+void free_lkb(struct dlm_lkb *l);
+struct dlm_direntry *allocate_direntry(struct dlm_ls *ls, int namelen);
+void free_direntry(struct dlm_direntry *de);
+char *allocate_lvb(struct dlm_ls *ls);
+void free_lvb(char *l);
+
+#endif		/* __MEMORY_DOT_H__ */
+

fs/dlm/midcomms.c

@@ -0,0 +1,140 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+/*
+ * midcomms.c
+ *
+ * This is the appallingly named "mid-level" comms layer.
+ *
+ * Its purpose is to take packets from the "real" comms layer,
+ * split them up into packets and pass them to the interested
+ * part of the locking mechanism.
+ *
+ * It also takes messages from the locking layer, formats them
+ * into packets and sends them to the comms layer.
+ */
+
+#include "dlm_internal.h"
+#include "lowcomms.h"
+#include "config.h"
+#include "rcom.h"
+#include "lock.h"
+#include "midcomms.h"
+
+
+static void copy_from_cb(void *dst, const void *base, unsigned offset,
+			 unsigned len, unsigned limit)
+{
+	unsigned copy = len;
+
+	if ((copy + offset) > limit)
+		copy = limit - offset;
+	memcpy(dst, base + offset, copy);
+	len -= copy;
+	if (len)
+		memcpy(dst + copy, base, len);
+}
+
+/*
+ * Called from the low-level comms layer to process a buffer of
+ * commands.
+ *
+ * Only complete messages are processed here, any "spare" bytes from
+ * the end of a buffer are saved and tacked onto the front of the next
+ * message that comes in. I doubt this will happen very often but we
+ * need to be able to cope with it and I don't want the task to be waiting
+ * for packets to come in when there is useful work to be done.
+ */
+
+int dlm_process_incoming_buffer(int nodeid, const void *base,
+				unsigned offset, unsigned len, unsigned limit)
+{
+	unsigned char __tmp[DLM_INBUF_LEN];
+	struct dlm_header *msg = (struct dlm_header *) __tmp;
+	int ret = 0;
+	int err = 0;
+	uint16_t msglen;
+	uint32_t lockspace;
+
+	while (len > sizeof(struct dlm_header)) {
+
+		/* Copy just the header to check the total length.  The
+		   message may wrap around the end of the buffer back to the
+		   start, so we need to use a temp buffer and copy_from_cb. */
+
+		copy_from_cb(msg, base, offset, sizeof(struct dlm_header),
+			     limit);
+
+		msglen = le16_to_cpu(msg->h_length);
+		lockspace = msg->h_lockspace;
+
+		err = -EINVAL;
+		if (msglen < sizeof(struct dlm_header))
+			break;
+		err = -E2BIG;
+		if (msglen > dlm_config.buffer_size) {
+			log_print("message size %d from %d too big, buf len %d",
+				  msglen, nodeid, len);
+			break;
+		}
+		err = 0;
+
+		/* If only part of the full message is contained in this
+		   buffer, then do nothing and wait for lowcomms to call
+		   us again later with more data.  We return 0 meaning
+		   we've consumed none of the input buffer. */
+
+		if (msglen > len)
+			break;
+
+		/* Allocate a larger temp buffer if the full message won't fit
+		   in the buffer on the stack (which should work for most
+		   ordinary messages). */
+
+		if (msglen > sizeof(__tmp) &&
+		    msg == (struct dlm_header *) __tmp) {
+			msg = kmalloc(dlm_config.buffer_size, GFP_KERNEL);
+			if (msg == NULL)
+				return ret;
+		}
+
+		copy_from_cb(msg, base, offset, msglen, limit);
+
+		BUG_ON(lockspace != msg->h_lockspace);
+
+		ret += msglen;
+		offset += msglen;
+		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);
+		}
+	}
+
+	if (msg != (struct dlm_header *) __tmp)
+		kfree(msg);
+
+	return err ? err : ret;
+}
+

fs/dlm/midcomms.h

@@ -0,0 +1,21 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __MIDCOMMS_DOT_H__
+#define __MIDCOMMS_DOT_H__
+
+int dlm_process_incoming_buffer(int nodeid, const void *base, unsigned offset,
+				unsigned len, unsigned limit);
+
+#endif				/* __MIDCOMMS_DOT_H__ */
+

fs/dlm/rcom.c

@@ -0,0 +1,472 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "member.h"
+#include "lowcomms.h"
+#include "midcomms.h"
+#include "rcom.h"
+#include "recover.h"
+#include "dir.h"
+#include "config.h"
+#include "memory.h"
+#include "lock.h"
+#include "util.h"
+
+
+static int rcom_response(struct dlm_ls *ls)
+{
+	return test_bit(LSFL_RCOM_READY, &ls->ls_flags);
+}
+
+static int create_rcom(struct dlm_ls *ls, int to_nodeid, int type, int len,
+		       struct dlm_rcom **rc_ret, struct dlm_mhandle **mh_ret)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	char *mb;
+	int mb_len = sizeof(struct dlm_rcom) + len;
+
+	mh = dlm_lowcomms_get_buffer(to_nodeid, mb_len, GFP_KERNEL, &mb);
+	if (!mh) {
+		log_print("create_rcom to %d type %d len %d ENOBUFS",
+			  to_nodeid, type, len);
+		return -ENOBUFS;
+	}
+	memset(mb, 0, mb_len);
+
+	rc = (struct dlm_rcom *) mb;
+
+	rc->rc_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
+	rc->rc_header.h_lockspace = ls->ls_global_id;
+	rc->rc_header.h_nodeid = dlm_our_nodeid();
+	rc->rc_header.h_length = mb_len;
+	rc->rc_header.h_cmd = DLM_RCOM;
+
+	rc->rc_type = type;
+
+	*mh_ret = mh;
+	*rc_ret = rc;
+	return 0;
+}
+
+static void send_rcom(struct dlm_ls *ls, struct dlm_mhandle *mh,
+		      struct dlm_rcom *rc)
+{
+	dlm_rcom_out(rc);
+	dlm_lowcomms_commit_buffer(mh);
+}
+
+/* When replying to a status request, a node also sends back its
+   configuration values.  The requesting node then checks that the remote
+   node is configured the same way as itself. */
+
+static void make_config(struct dlm_ls *ls, struct rcom_config *rf)
+{
+	rf->rf_lvblen = ls->ls_lvblen;
+	rf->rf_lsflags = ls->ls_exflags;
+}
+
+static int check_config(struct dlm_ls *ls, struct rcom_config *rf, int nodeid)
+{
+	if (rf->rf_lvblen != ls->ls_lvblen ||
+	    rf->rf_lsflags != ls->ls_exflags) {
+		log_error(ls, "config mismatch: %d,%x nodeid %d: %d,%x",
+			  ls->ls_lvblen, ls->ls_exflags,
+			  nodeid, rf->rf_lvblen, rf->rf_lsflags);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int dlm_rcom_status(struct dlm_ls *ls, int nodeid)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	int error = 0;
+
+	memset(ls->ls_recover_buf, 0, dlm_config.buffer_size);
+	ls->ls_recover_nodeid = nodeid;
+
+	if (nodeid == dlm_our_nodeid()) {
+		rc = (struct dlm_rcom *) ls->ls_recover_buf;
+		rc->rc_result = dlm_recover_status(ls);
+		goto out;
+	}
+
+	error = create_rcom(ls, nodeid, DLM_RCOM_STATUS, 0, &rc, &mh);
+	if (error)
+		goto out;
+	rc->rc_id = ++ls->ls_rcom_seq;
+
+	send_rcom(ls, mh, rc);
+
+	error = dlm_wait_function(ls, &rcom_response);
+	clear_bit(LSFL_RCOM_READY, &ls->ls_flags);
+	if (error)
+		goto out;
+
+	rc = (struct dlm_rcom *) ls->ls_recover_buf;
+
+	if (rc->rc_result == -ESRCH) {
+		/* we pretend the remote lockspace exists with 0 status */
+		log_debug(ls, "remote node %d not ready", nodeid);
+		rc->rc_result = 0;
+	} else
+		error = check_config(ls, (struct rcom_config *) rc->rc_buf,
+				     nodeid);
+	/* the caller looks at rc_result for the remote recovery status */
+ out:
+	return error;
+}
+
+static void receive_rcom_status(struct dlm_ls *ls, struct dlm_rcom *rc_in)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	int error, nodeid = rc_in->rc_header.h_nodeid;
+
+	error = create_rcom(ls, nodeid, DLM_RCOM_STATUS_REPLY,
+			    sizeof(struct rcom_config), &rc, &mh);
+	if (error)
+		return;
+	rc->rc_id = rc_in->rc_id;
+	rc->rc_result = dlm_recover_status(ls);
+	make_config(ls, (struct rcom_config *) rc->rc_buf);
+
+	send_rcom(ls, mh, rc);
+}
+
+static void receive_sync_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
+{
+	if (rc_in->rc_id != ls->ls_rcom_seq) {
+		log_debug(ls, "reject old reply %d got %llx wanted %llx",
+			  rc_in->rc_type, rc_in->rc_id, ls->ls_rcom_seq);
+		return;
+	}
+	memcpy(ls->ls_recover_buf, rc_in, rc_in->rc_header.h_length);
+	set_bit(LSFL_RCOM_READY, &ls->ls_flags);
+	wake_up(&ls->ls_wait_general);
+}
+
+static void receive_rcom_status_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
+{
+	receive_sync_reply(ls, rc_in);
+}
+
+int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name, int last_len)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	int error = 0, len = sizeof(struct dlm_rcom);
+
+	memset(ls->ls_recover_buf, 0, dlm_config.buffer_size);
+	ls->ls_recover_nodeid = nodeid;
+
+	if (nodeid == dlm_our_nodeid()) {
+		dlm_copy_master_names(ls, last_name, last_len,
+		                      ls->ls_recover_buf + len,
+		                      dlm_config.buffer_size - len, nodeid);
+		goto out;
+	}
+
+	error = create_rcom(ls, nodeid, DLM_RCOM_NAMES, last_len, &rc, &mh);
+	if (error)
+		goto out;
+	memcpy(rc->rc_buf, last_name, last_len);
+	rc->rc_id = ++ls->ls_rcom_seq;
+
+	send_rcom(ls, mh, rc);
+
+	error = dlm_wait_function(ls, &rcom_response);
+	clear_bit(LSFL_RCOM_READY, &ls->ls_flags);
+ out:
+	return error;
+}
+
+static void receive_rcom_names(struct dlm_ls *ls, struct dlm_rcom *rc_in)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	int error, inlen, outlen;
+	int nodeid = rc_in->rc_header.h_nodeid;
+	uint32_t status = dlm_recover_status(ls);
+
+	/*
+	 * We can't run dlm_dir_rebuild_send (which uses ls_nodes) while
+	 * dlm_recoverd is running ls_nodes_reconfig (which changes ls_nodes).
+	 * It could only happen in rare cases where we get a late NAMES
+	 * message from a previous instance of recovery.
+	 */
+
+	if (!(status & DLM_RS_NODES)) {
+		log_debug(ls, "ignoring RCOM_NAMES from %u", nodeid);
+		return;
+	}
+
+	nodeid = rc_in->rc_header.h_nodeid;
+	inlen = rc_in->rc_header.h_length - sizeof(struct dlm_rcom);
+	outlen = dlm_config.buffer_size - sizeof(struct dlm_rcom);
+
+	error = create_rcom(ls, nodeid, DLM_RCOM_NAMES_REPLY, outlen, &rc, &mh);
+	if (error)
+		return;
+	rc->rc_id = rc_in->rc_id;
+
+	dlm_copy_master_names(ls, rc_in->rc_buf, inlen, rc->rc_buf, outlen,
+			      nodeid);
+	send_rcom(ls, mh, rc);
+}
+
+static void receive_rcom_names_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
+{
+	receive_sync_reply(ls, rc_in);
+}
+
+int dlm_send_rcom_lookup(struct dlm_rsb *r, int dir_nodeid)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	struct dlm_ls *ls = r->res_ls;
+	int error;
+
+	error = create_rcom(ls, dir_nodeid, DLM_RCOM_LOOKUP, r->res_length,
+			    &rc, &mh);
+	if (error)
+		goto out;
+	memcpy(rc->rc_buf, r->res_name, r->res_length);
+	rc->rc_id = (unsigned long) r;
+
+	send_rcom(ls, mh, rc);
+ out:
+	return error;
+}
+
+static void receive_rcom_lookup(struct dlm_ls *ls, struct dlm_rcom *rc_in)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	int error, ret_nodeid, nodeid = rc_in->rc_header.h_nodeid;
+	int len = rc_in->rc_header.h_length - sizeof(struct dlm_rcom);
+
+	error = create_rcom(ls, nodeid, DLM_RCOM_LOOKUP_REPLY, 0, &rc, &mh);
+	if (error)
+		return;
+
+	error = dlm_dir_lookup(ls, nodeid, rc_in->rc_buf, len, &ret_nodeid);
+	if (error)
+		ret_nodeid = error;
+	rc->rc_result = ret_nodeid;
+	rc->rc_id = rc_in->rc_id;
+
+	send_rcom(ls, mh, rc);
+}
+
+static void receive_rcom_lookup_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
+{
+	dlm_recover_master_reply(ls, rc_in);
+}
+
+static void pack_rcom_lock(struct dlm_rsb *r, struct dlm_lkb *lkb,
+			   struct rcom_lock *rl)
+{
+	memset(rl, 0, sizeof(*rl));
+
+	rl->rl_ownpid = lkb->lkb_ownpid;
+	rl->rl_lkid = lkb->lkb_id;
+	rl->rl_exflags = lkb->lkb_exflags;
+	rl->rl_flags = lkb->lkb_flags;
+	rl->rl_lvbseq = lkb->lkb_lvbseq;
+	rl->rl_rqmode = lkb->lkb_rqmode;
+	rl->rl_grmode = lkb->lkb_grmode;
+	rl->rl_status = lkb->lkb_status;
+	rl->rl_wait_type = lkb->lkb_wait_type;
+
+	if (lkb->lkb_bastaddr)
+		rl->rl_asts |= AST_BAST;
+	if (lkb->lkb_astaddr)
+		rl->rl_asts |= AST_COMP;
+
+	rl->rl_namelen = r->res_length;
+	memcpy(rl->rl_name, r->res_name, r->res_length);
+
+	/* FIXME: might we have an lvb without DLM_LKF_VALBLK set ?
+	   If so, receive_rcom_lock_args() won't take this copy. */
+
+	if (lkb->lkb_lvbptr)
+		memcpy(rl->rl_lvb, lkb->lkb_lvbptr, r->res_ls->ls_lvblen);
+}
+
+int dlm_send_rcom_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
+{
+	struct dlm_ls *ls = r->res_ls;
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	struct rcom_lock *rl;
+	int error, len = sizeof(struct rcom_lock);
+
+	if (lkb->lkb_lvbptr)
+		len += ls->ls_lvblen;
+
+	error = create_rcom(ls, r->res_nodeid, DLM_RCOM_LOCK, len, &rc, &mh);
+	if (error)
+		goto out;
+
+	rl = (struct rcom_lock *) rc->rc_buf;
+	pack_rcom_lock(r, lkb, rl);
+	rc->rc_id = (unsigned long) r;
+
+	send_rcom(ls, mh, rc);
+ out:
+	return error;
+}
+
+static void receive_rcom_lock(struct dlm_ls *ls, struct dlm_rcom *rc_in)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	int error, nodeid = rc_in->rc_header.h_nodeid;
+
+	dlm_recover_master_copy(ls, rc_in);
+
+	error = create_rcom(ls, nodeid, DLM_RCOM_LOCK_REPLY,
+			    sizeof(struct rcom_lock), &rc, &mh);
+	if (error)
+		return;
+
+	/* We send back the same rcom_lock struct we received, but
+	   dlm_recover_master_copy() has filled in rl_remid and rl_result */
+
+	memcpy(rc->rc_buf, rc_in->rc_buf, sizeof(struct rcom_lock));
+	rc->rc_id = rc_in->rc_id;
+
+	send_rcom(ls, mh, rc);
+}
+
+static void receive_rcom_lock_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
+{
+	uint32_t status = dlm_recover_status(ls);
+
+	if (!(status & DLM_RS_DIR)) {
+		log_debug(ls, "ignoring RCOM_LOCK_REPLY from %u",
+			  rc_in->rc_header.h_nodeid);
+		return;
+	}
+
+	dlm_recover_process_copy(ls, rc_in);
+}
+
+static int send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in)
+{
+	struct dlm_rcom *rc;
+	struct dlm_mhandle *mh;
+	char *mb;
+	int mb_len = sizeof(struct dlm_rcom);
+
+	mh = dlm_lowcomms_get_buffer(nodeid, mb_len, GFP_KERNEL, &mb);
+	if (!mh)
+		return -ENOBUFS;
+	memset(mb, 0, mb_len);
+
+	rc = (struct dlm_rcom *) mb;
+
+	rc->rc_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
+	rc->rc_header.h_lockspace = rc_in->rc_header.h_lockspace;
+	rc->rc_header.h_nodeid = dlm_our_nodeid();
+	rc->rc_header.h_length = mb_len;
+	rc->rc_header.h_cmd = DLM_RCOM;
+
+	rc->rc_type = DLM_RCOM_STATUS_REPLY;
+	rc->rc_id = rc_in->rc_id;
+	rc->rc_result = -ESRCH;
+
+	dlm_rcom_out(rc);
+	dlm_lowcomms_commit_buffer(mh);
+
+	return 0;
+}
+
+/* Called by dlm_recvd; corresponds to dlm_receive_message() but special
+   recovery-only comms are sent through here. */
+
+void dlm_receive_rcom(struct dlm_header *hd, 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 not found",
+			  hd->h_lockspace, nodeid);
+		send_ls_not_ready(nodeid, rc);
+		return;
+	}
+
+	if (dlm_recovery_stopped(ls) && (rc->rc_type != DLM_RCOM_STATUS)) {
+		log_error(ls, "ignoring recovery message %x from %d",
+			  rc->rc_type, nodeid);
+		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:
+		receive_rcom_status(ls, rc);
+		break;
+
+	case DLM_RCOM_NAMES:
+		receive_rcom_names(ls, rc);
+		break;
+
+	case DLM_RCOM_LOOKUP:
+		receive_rcom_lookup(ls, rc);
+		break;
+
+	case DLM_RCOM_LOCK:
+		receive_rcom_lock(ls, rc);
+		break;
+
+	case DLM_RCOM_STATUS_REPLY:
+		receive_rcom_status_reply(ls, rc);
+		break;
+
+	case DLM_RCOM_NAMES_REPLY:
+		receive_rcom_names_reply(ls, rc);
+		break;
+
+	case DLM_RCOM_LOOKUP_REPLY:
+		receive_rcom_lookup_reply(ls, rc);
+		break;
+
+	case DLM_RCOM_LOCK_REPLY:
+		receive_rcom_lock_reply(ls, rc);
+		break;
+
+	default:
+		DLM_ASSERT(0, printk("rc_type=%x\n", rc->rc_type););
+	}
+ out:
+	dlm_put_lockspace(ls);
+}
+

fs/dlm/rcom.h

@@ -0,0 +1,24 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __RCOM_DOT_H__
+#define __RCOM_DOT_H__
+
+int dlm_rcom_status(struct dlm_ls *ls, int nodeid);
+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);
+
+#endif
+

fs/dlm/recover.c

@@ -0,0 +1,765 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "dir.h"
+#include "config.h"
+#include "ast.h"
+#include "memory.h"
+#include "rcom.h"
+#include "lock.h"
+#include "lowcomms.h"
+#include "member.h"
+#include "recover.h"
+
+
+/*
+ * Recovery waiting routines: these functions wait for a particular reply from
+ * a remote node, or for the remote node to report a certain status.  They need
+ * to abort if the lockspace is stopped indicating a node has failed (perhaps
+ * the one being waited for).
+ */
+
+/*
+ * Wait until given function returns non-zero or lockspace is stopped
+ * (LS_RECOVERY_STOP set due to failure of a node in ls_nodes).  When another
+ * function thinks it could have completed the waited-on task, they should wake
+ * up ls_wait_general to get an immediate response rather than waiting for the
+ * timer to detect the result.  A timer wakes us up periodically while waiting
+ * to see if we should abort due to a node failure.  This should only be called
+ * by the dlm_recoverd thread.
+ */
+
+static void dlm_wait_timer_fn(unsigned long data)
+{
+	struct dlm_ls *ls = (struct dlm_ls *) data;
+	mod_timer(&ls->ls_timer, jiffies + (dlm_config.recover_timer * HZ));
+	wake_up(&ls->ls_wait_general);
+}
+
+int dlm_wait_function(struct dlm_ls *ls, int (*testfn) (struct dlm_ls *ls))
+{
+	int error = 0;
+
+	init_timer(&ls->ls_timer);
+	ls->ls_timer.function = dlm_wait_timer_fn;
+	ls->ls_timer.data = (long) ls;
+	ls->ls_timer.expires = jiffies + (dlm_config.recover_timer * HZ);
+	add_timer(&ls->ls_timer);
+
+	wait_event(ls->ls_wait_general, testfn(ls) || dlm_recovery_stopped(ls));
+	del_timer_sync(&ls->ls_timer);
+
+	if (dlm_recovery_stopped(ls)) {
+		log_debug(ls, "dlm_wait_function aborted");
+		error = -EINTR;
+	}
+	return error;
+}
+
+/*
+ * An efficient way for all nodes to wait for all others to have a certain
+ * status.  The node with the lowest nodeid polls all the others for their
+ * status (wait_status_all) and all the others poll the node with the low id
+ * for its accumulated result (wait_status_low).  When all nodes have set
+ * status flag X, then status flag X_ALL will be set on the low nodeid.
+ */
+
+uint32_t dlm_recover_status(struct dlm_ls *ls)
+{
+	uint32_t status;
+	spin_lock(&ls->ls_recover_lock);
+	status = ls->ls_recover_status;
+	spin_unlock(&ls->ls_recover_lock);
+	return status;
+}
+
+void dlm_set_recover_status(struct dlm_ls *ls, uint32_t status)
+{
+	spin_lock(&ls->ls_recover_lock);
+	ls->ls_recover_status |= status;
+	spin_unlock(&ls->ls_recover_lock);
+}
+
+static int wait_status_all(struct dlm_ls *ls, uint32_t wait_status)
+{
+	struct dlm_rcom *rc = (struct dlm_rcom *) ls->ls_recover_buf;
+	struct dlm_member *memb;
+	int error = 0, delay;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		delay = 0;
+		for (;;) {
+			if (dlm_recovery_stopped(ls)) {
+				error = -EINTR;
+				goto out;
+			}
+
+			error = dlm_rcom_status(ls, memb->nodeid);
+			if (error)
+				goto out;
+
+			if (rc->rc_result & wait_status)
+				break;
+			if (delay < 1000)
+				delay += 20;
+			msleep(delay);
+		}
+	}
+ out:
+	return error;
+}
+
+static int wait_status_low(struct dlm_ls *ls, uint32_t wait_status)
+{
+	struct dlm_rcom *rc = (struct dlm_rcom *) ls->ls_recover_buf;
+	int error = 0, delay = 0, nodeid = ls->ls_low_nodeid;
+
+	for (;;) {
+		if (dlm_recovery_stopped(ls)) {
+			error = -EINTR;
+			goto out;
+		}
+
+		error = dlm_rcom_status(ls, nodeid);
+		if (error)
+			break;
+
+		if (rc->rc_result & wait_status)
+			break;
+		if (delay < 1000)
+			delay += 20;
+		msleep(delay);
+	}
+ out:
+	return error;
+}
+
+static int wait_status(struct dlm_ls *ls, uint32_t status)
+{
+	uint32_t status_all = status << 1;
+	int error;
+
+	if (ls->ls_low_nodeid == dlm_our_nodeid()) {
+		error = wait_status_all(ls, status);
+		if (!error)
+			dlm_set_recover_status(ls, status_all);
+	} else
+		error = wait_status_low(ls, status_all);
+
+	return error;
+}
+
+int dlm_recover_members_wait(struct dlm_ls *ls)
+{
+	return wait_status(ls, DLM_RS_NODES);
+}
+
+int dlm_recover_directory_wait(struct dlm_ls *ls)
+{
+	return wait_status(ls, DLM_RS_DIR);
+}
+
+int dlm_recover_locks_wait(struct dlm_ls *ls)
+{
+	return wait_status(ls, DLM_RS_LOCKS);
+}
+
+int dlm_recover_done_wait(struct dlm_ls *ls)
+{
+	return wait_status(ls, DLM_RS_DONE);
+}
+
+/*
+ * The recover_list contains all the rsb's for which we've requested the new
+ * master nodeid.  As replies are returned from the resource directories the
+ * rsb's are removed from the list.  When the list is empty we're done.
+ *
+ * The recover_list is later similarly used for all rsb's for which we've sent
+ * new lkb's and need to receive new corresponding lkid's.
+ *
+ * We use the address of the rsb struct as a simple local identifier for the
+ * rsb so we can match an rcom reply with the rsb it was sent for.
+ */
+
+static int recover_list_empty(struct dlm_ls *ls)
+{
+	int empty;
+
+	spin_lock(&ls->ls_recover_list_lock);
+	empty = list_empty(&ls->ls_recover_list);
+	spin_unlock(&ls->ls_recover_list_lock);
+
+	return empty;
+}
+
+static void recover_list_add(struct dlm_rsb *r)
+{
+	struct dlm_ls *ls = r->res_ls;
+
+	spin_lock(&ls->ls_recover_list_lock);
+	if (list_empty(&r->res_recover_list)) {
+		list_add_tail(&r->res_recover_list, &ls->ls_recover_list);
+		ls->ls_recover_list_count++;
+		dlm_hold_rsb(r);
+	}
+	spin_unlock(&ls->ls_recover_list_lock);
+}
+
+static void recover_list_del(struct dlm_rsb *r)
+{
+	struct dlm_ls *ls = r->res_ls;
+
+	spin_lock(&ls->ls_recover_list_lock);
+	list_del_init(&r->res_recover_list);
+	ls->ls_recover_list_count--;
+	spin_unlock(&ls->ls_recover_list_lock);
+
+	dlm_put_rsb(r);
+}
+
+static struct dlm_rsb *recover_list_find(struct dlm_ls *ls, uint64_t id)
+{
+	struct dlm_rsb *r = NULL;
+
+	spin_lock(&ls->ls_recover_list_lock);
+
+	list_for_each_entry(r, &ls->ls_recover_list, res_recover_list) {
+		if (id == (unsigned long) r)
+			goto out;
+	}
+	r = NULL;
+ out:
+	spin_unlock(&ls->ls_recover_list_lock);
+	return r;
+}
+
+static void recover_list_clear(struct dlm_ls *ls)
+{
+	struct dlm_rsb *r, *s;
+
+	spin_lock(&ls->ls_recover_list_lock);
+	list_for_each_entry_safe(r, s, &ls->ls_recover_list, res_recover_list) {
+		list_del_init(&r->res_recover_list);
+		dlm_put_rsb(r);
+		ls->ls_recover_list_count--;
+	}
+
+	if (ls->ls_recover_list_count != 0) {
+		log_error(ls, "warning: recover_list_count %d",
+			  ls->ls_recover_list_count);
+		ls->ls_recover_list_count = 0;
+	}
+	spin_unlock(&ls->ls_recover_list_lock);
+}
+
+
+/* Master recovery: find new master node for rsb's that were
+   mastered on nodes that have been removed.
+
+   dlm_recover_masters
+   recover_master
+   dlm_send_rcom_lookup            ->  receive_rcom_lookup
+                                       dlm_dir_lookup
+   receive_rcom_lookup_reply       <-
+   dlm_recover_master_reply
+   set_new_master
+   set_master_lkbs
+   set_lock_master
+*/
+
+/*
+ * Set the lock master for all LKBs in a lock queue
+ * If we are the new master of the rsb, we may have received new
+ * MSTCPY locks from other nodes already which we need to ignore
+ * when setting the new nodeid.
+ */
+
+static void set_lock_master(struct list_head *queue, int nodeid)
+{
+	struct dlm_lkb *lkb;
+
+	list_for_each_entry(lkb, queue, lkb_statequeue)
+		if (!(lkb->lkb_flags & DLM_IFL_MSTCPY))
+			lkb->lkb_nodeid = nodeid;
+}
+
+static void set_master_lkbs(struct dlm_rsb *r)
+{
+	set_lock_master(&r->res_grantqueue, r->res_nodeid);
+	set_lock_master(&r->res_convertqueue, r->res_nodeid);
+	set_lock_master(&r->res_waitqueue, r->res_nodeid);
+}
+
+/*
+ * Propogate the new master nodeid to locks
+ * The NEW_MASTER flag tells dlm_recover_locks() which rsb's to consider.
+ * The NEW_MASTER2 flag tells recover_lvb() and set_locks_purged() which
+ * rsb's to consider.
+ */
+
+static void set_new_master(struct dlm_rsb *r, int nodeid)
+{
+	lock_rsb(r);
+	r->res_nodeid = nodeid;
+	set_master_lkbs(r);
+	rsb_set_flag(r, RSB_NEW_MASTER);
+	rsb_set_flag(r, RSB_NEW_MASTER2);
+	unlock_rsb(r);
+}
+
+/*
+ * We do async lookups on rsb's that need new masters.  The rsb's
+ * waiting for a lookup reply are kept on the recover_list.
+ */
+
+static int recover_master(struct dlm_rsb *r)
+{
+	struct dlm_ls *ls = r->res_ls;
+	int error, dir_nodeid, ret_nodeid, our_nodeid = dlm_our_nodeid();
+
+	dir_nodeid = dlm_dir_nodeid(r);
+
+	if (dir_nodeid == our_nodeid) {
+		error = dlm_dir_lookup(ls, our_nodeid, r->res_name,
+				       r->res_length, &ret_nodeid);
+		if (error)
+			log_error(ls, "recover dir lookup error %d", error);
+
+		if (ret_nodeid == our_nodeid)
+			ret_nodeid = 0;
+		set_new_master(r, ret_nodeid);
+	} else {
+		recover_list_add(r);
+		error = dlm_send_rcom_lookup(r, dir_nodeid);
+	}
+
+	return error;
+}
+
+/*
+ * When not using a directory, most resource names will hash to a new static
+ * master nodeid and the resource will need to be remastered.
+ */
+
+static int recover_master_static(struct dlm_rsb *r)
+{
+	int master = dlm_dir_nodeid(r);
+
+	if (master == dlm_our_nodeid())
+		master = 0;
+
+	if (r->res_nodeid != master) {
+		if (is_master(r))
+			dlm_purge_mstcpy_locks(r);
+		set_new_master(r, master);
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * Go through local root resources and for each rsb which has a master which
+ * has departed, get the new master nodeid from the directory.  The dir will
+ * assign mastery to the first node to look up the new master.  That means
+ * we'll discover in this lookup if we're the new master of any rsb's.
+ *
+ * We fire off all the dir lookup requests individually and asynchronously to
+ * the correct dir node.
+ */
+
+int dlm_recover_masters(struct dlm_ls *ls)
+{
+	struct dlm_rsb *r;
+	int error = 0, count = 0;
+
+	log_debug(ls, "dlm_recover_masters");
+
+	down_read(&ls->ls_root_sem);
+	list_for_each_entry(r, &ls->ls_root_list, res_root_list) {
+		if (dlm_recovery_stopped(ls)) {
+			up_read(&ls->ls_root_sem);
+			error = -EINTR;
+			goto out;
+		}
+
+		if (dlm_no_directory(ls))
+			count += recover_master_static(r);
+		else if (!is_master(r) && dlm_is_removed(ls, r->res_nodeid)) {
+			recover_master(r);
+			count++;
+		}
+
+		schedule();
+	}
+	up_read(&ls->ls_root_sem);
+
+	log_debug(ls, "dlm_recover_masters %d resources", count);
+
+	error = dlm_wait_function(ls, &recover_list_empty);
+ out:
+	if (error)
+		recover_list_clear(ls);
+	return error;
+}
+
+int dlm_recover_master_reply(struct dlm_ls *ls, struct dlm_rcom *rc)
+{
+	struct dlm_rsb *r;
+	int nodeid;
+
+	r = recover_list_find(ls, rc->rc_id);
+	if (!r) {
+		log_error(ls, "dlm_recover_master_reply no id %llx",
+			  (unsigned long long)rc->rc_id);
+		goto out;
+	}
+
+	nodeid = rc->rc_result;
+	if (nodeid == dlm_our_nodeid())
+		nodeid = 0;
+
+	set_new_master(r, nodeid);
+	recover_list_del(r);
+
+	if (recover_list_empty(ls))
+		wake_up(&ls->ls_wait_general);
+ out:
+	return 0;
+}
+
+
+/* Lock recovery: rebuild the process-copy locks we hold on a
+   remastered rsb on the new rsb master.
+
+   dlm_recover_locks
+   recover_locks
+   recover_locks_queue
+   dlm_send_rcom_lock              ->  receive_rcom_lock
+                                       dlm_recover_master_copy
+   receive_rcom_lock_reply         <-
+   dlm_recover_process_copy
+*/
+
+
+/*
+ * keep a count of the number of lkb's we send to the new master; when we get
+ * an equal number of replies then recovery for the rsb is done
+ */
+
+static int recover_locks_queue(struct dlm_rsb *r, struct list_head *head)
+{
+	struct dlm_lkb *lkb;
+	int error = 0;
+
+	list_for_each_entry(lkb, head, lkb_statequeue) {
+	   	error = dlm_send_rcom_lock(r, lkb);
+		if (error)
+			break;
+		r->res_recover_locks_count++;
+	}
+
+	return error;
+}
+
+static int recover_locks(struct dlm_rsb *r)
+{
+	int error = 0;
+
+	lock_rsb(r);
+
+	DLM_ASSERT(!r->res_recover_locks_count, dlm_dump_rsb(r););
+
+	error = recover_locks_queue(r, &r->res_grantqueue);
+	if (error)
+		goto out;
+	error = recover_locks_queue(r, &r->res_convertqueue);
+	if (error)
+		goto out;
+	error = recover_locks_queue(r, &r->res_waitqueue);
+	if (error)
+		goto out;
+
+	if (r->res_recover_locks_count)
+		recover_list_add(r);
+	else
+		rsb_clear_flag(r, RSB_NEW_MASTER);
+ out:
+	unlock_rsb(r);
+	return error;
+}
+
+int dlm_recover_locks(struct dlm_ls *ls)
+{
+	struct dlm_rsb *r;
+	int error, count = 0;
+
+	log_debug(ls, "dlm_recover_locks");
+
+	down_read(&ls->ls_root_sem);
+	list_for_each_entry(r, &ls->ls_root_list, res_root_list) {
+		if (is_master(r)) {
+			rsb_clear_flag(r, RSB_NEW_MASTER);
+			continue;
+		}
+
+		if (!rsb_flag(r, RSB_NEW_MASTER))
+			continue;
+
+		if (dlm_recovery_stopped(ls)) {
+			error = -EINTR;
+			up_read(&ls->ls_root_sem);
+			goto out;
+		}
+
+		error = recover_locks(r);
+		if (error) {
+			up_read(&ls->ls_root_sem);
+			goto out;
+		}
+
+		count += r->res_recover_locks_count;
+	}
+	up_read(&ls->ls_root_sem);
+
+	log_debug(ls, "dlm_recover_locks %d locks", count);
+
+	error = dlm_wait_function(ls, &recover_list_empty);
+ out:
+	if (error)
+		recover_list_clear(ls);
+	else
+		dlm_set_recover_status(ls, DLM_RS_LOCKS);
+	return error;
+}
+
+void dlm_recovered_lock(struct dlm_rsb *r)
+{
+	DLM_ASSERT(rsb_flag(r, RSB_NEW_MASTER), dlm_dump_rsb(r););
+
+	r->res_recover_locks_count--;
+	if (!r->res_recover_locks_count) {
+		rsb_clear_flag(r, RSB_NEW_MASTER);
+		recover_list_del(r);
+	}
+
+	if (recover_list_empty(r->res_ls))
+		wake_up(&r->res_ls->ls_wait_general);
+}
+
+/*
+ * The lvb needs to be recovered on all master rsb's.  This includes setting
+ * the VALNOTVALID flag if necessary, and determining the correct lvb contents
+ * based on the lvb's of the locks held on the rsb.
+ *
+ * RSB_VALNOTVALID is set if there are only NL/CR locks on the rsb.  If it
+ * was already set prior to recovery, it's not cleared, regardless of locks.
+ *
+ * The LVB contents are only considered for changing when this is a new master
+ * of the rsb (NEW_MASTER2).  Then, the rsb's lvb is taken from any lkb with
+ * mode > CR.  If no lkb's exist with mode above CR, the lvb contents are taken
+ * from the lkb with the largest lvb sequence number.
+ */
+
+static void recover_lvb(struct dlm_rsb *r)
+{
+	struct dlm_lkb *lkb, *high_lkb = NULL;
+	uint32_t high_seq = 0;
+	int lock_lvb_exists = 0;
+	int big_lock_exists = 0;
+	int lvblen = r->res_ls->ls_lvblen;
+
+	list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) {
+		if (!(lkb->lkb_exflags & DLM_LKF_VALBLK))
+			continue;
+
+		lock_lvb_exists = 1;
+
+		if (lkb->lkb_grmode > DLM_LOCK_CR) {
+			big_lock_exists = 1;
+			goto setflag;
+		}
+
+		if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) {
+			high_lkb = lkb;
+			high_seq = lkb->lkb_lvbseq;
+		}
+	}
+
+	list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) {
+		if (!(lkb->lkb_exflags & DLM_LKF_VALBLK))
+			continue;
+
+		lock_lvb_exists = 1;
+
+		if (lkb->lkb_grmode > DLM_LOCK_CR) {
+			big_lock_exists = 1;
+			goto setflag;
+		}
+
+		if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) {
+			high_lkb = lkb;
+			high_seq = lkb->lkb_lvbseq;
+		}
+	}
+
+ setflag:
+	if (!lock_lvb_exists)
+		goto out;
+
+	if (!big_lock_exists)
+		rsb_set_flag(r, RSB_VALNOTVALID);
+
+	/* don't mess with the lvb unless we're the new master */
+	if (!rsb_flag(r, RSB_NEW_MASTER2))
+		goto out;
+
+	if (!r->res_lvbptr) {
+		r->res_lvbptr = allocate_lvb(r->res_ls);
+		if (!r->res_lvbptr)
+			goto out;
+	}
+
+	if (big_lock_exists) {
+		r->res_lvbseq = lkb->lkb_lvbseq;
+		memcpy(r->res_lvbptr, lkb->lkb_lvbptr, lvblen);
+	} else if (high_lkb) {
+		r->res_lvbseq = high_lkb->lkb_lvbseq;
+		memcpy(r->res_lvbptr, high_lkb->lkb_lvbptr, lvblen);
+	} else {
+		r->res_lvbseq = 0;
+		memset(r->res_lvbptr, 0, lvblen);
+	}
+ out:
+	return;
+}
+
+/* All master rsb's flagged RECOVER_CONVERT need to be looked at.  The locks
+   converting PR->CW or CW->PR need to have their lkb_grmode set. */
+
+static void recover_conversion(struct dlm_rsb *r)
+{
+	struct dlm_lkb *lkb;
+	int grmode = -1;
+
+	list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) {
+		if (lkb->lkb_grmode == DLM_LOCK_PR ||
+		    lkb->lkb_grmode == DLM_LOCK_CW) {
+			grmode = lkb->lkb_grmode;
+			break;
+		}
+	}
+
+	list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) {
+		if (lkb->lkb_grmode != DLM_LOCK_IV)
+			continue;
+		if (grmode == -1)
+			lkb->lkb_grmode = lkb->lkb_rqmode;
+		else
+			lkb->lkb_grmode = grmode;
+	}
+}
+
+/* We've become the new master for this rsb and waiting/converting locks may
+   need to be granted in dlm_grant_after_purge() due to locks that may have
+   existed from a removed node. */
+
+static void set_locks_purged(struct dlm_rsb *r)
+{
+	if (!list_empty(&r->res_waitqueue) || !list_empty(&r->res_convertqueue))
+		rsb_set_flag(r, RSB_LOCKS_PURGED);
+}
+
+void dlm_recover_rsbs(struct dlm_ls *ls)
+{
+	struct dlm_rsb *r;
+	int count = 0;
+
+	log_debug(ls, "dlm_recover_rsbs");
+
+	down_read(&ls->ls_root_sem);
+	list_for_each_entry(r, &ls->ls_root_list, res_root_list) {
+		lock_rsb(r);
+		if (is_master(r)) {
+			if (rsb_flag(r, RSB_RECOVER_CONVERT))
+				recover_conversion(r);
+			if (rsb_flag(r, RSB_NEW_MASTER2))
+				set_locks_purged(r);
+			recover_lvb(r);
+			count++;
+		}
+		rsb_clear_flag(r, RSB_RECOVER_CONVERT);
+		rsb_clear_flag(r, RSB_NEW_MASTER2);
+		unlock_rsb(r);
+	}
+	up_read(&ls->ls_root_sem);
+
+	log_debug(ls, "dlm_recover_rsbs %d rsbs", count);
+}
+
+/* Create a single list of all root rsb's to be used during recovery */
+
+int dlm_create_root_list(struct dlm_ls *ls)
+{
+	struct dlm_rsb *r;
+	int i, error = 0;
+
+	down_write(&ls->ls_root_sem);
+	if (!list_empty(&ls->ls_root_list)) {
+		log_error(ls, "root list not empty");
+		error = -EINVAL;
+		goto out;
+	}
+
+	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
+		read_lock(&ls->ls_rsbtbl[i].lock);
+		list_for_each_entry(r, &ls->ls_rsbtbl[i].list, res_hashchain) {
+			list_add(&r->res_root_list, &ls->ls_root_list);
+			dlm_hold_rsb(r);
+		}
+		read_unlock(&ls->ls_rsbtbl[i].lock);
+	}
+ out:
+	up_write(&ls->ls_root_sem);
+	return error;
+}
+
+void dlm_release_root_list(struct dlm_ls *ls)
+{
+	struct dlm_rsb *r, *safe;
+
+	down_write(&ls->ls_root_sem);
+	list_for_each_entry_safe(r, safe, &ls->ls_root_list, res_root_list) {
+		list_del_init(&r->res_root_list);
+		dlm_put_rsb(r);
+	}
+	up_write(&ls->ls_root_sem);
+}
+
+void dlm_clear_toss_list(struct dlm_ls *ls)
+{
+	struct dlm_rsb *r, *safe;
+	int i;
+
+	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
+		write_lock(&ls->ls_rsbtbl[i].lock);
+		list_for_each_entry_safe(r, safe, &ls->ls_rsbtbl[i].toss,
+					 res_hashchain) {
+			list_del(&r->res_hashchain);
+			free_rsb(r);
+		}
+		write_unlock(&ls->ls_rsbtbl[i].lock);
+	}
+}
+

fs/dlm/recover.h

@@ -0,0 +1,34 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __RECOVER_DOT_H__
+#define __RECOVER_DOT_H__
+
+int dlm_wait_function(struct dlm_ls *ls, int (*testfn) (struct dlm_ls *ls));
+uint32_t dlm_recover_status(struct dlm_ls *ls);
+void dlm_set_recover_status(struct dlm_ls *ls, uint32_t status);
+int dlm_recover_members_wait(struct dlm_ls *ls);
+int dlm_recover_directory_wait(struct dlm_ls *ls);
+int dlm_recover_locks_wait(struct dlm_ls *ls);
+int dlm_recover_done_wait(struct dlm_ls *ls);
+int dlm_recover_masters(struct dlm_ls *ls);
+int dlm_recover_master_reply(struct dlm_ls *ls, struct dlm_rcom *rc);
+int dlm_recover_locks(struct dlm_ls *ls);
+void dlm_recovered_lock(struct dlm_rsb *r);
+int dlm_create_root_list(struct dlm_ls *ls);
+void dlm_release_root_list(struct dlm_ls *ls);
+void dlm_clear_toss_list(struct dlm_ls *ls);
+void dlm_recover_rsbs(struct dlm_ls *ls);
+
+#endif				/* __RECOVER_DOT_H__ */
+

fs/dlm/recoverd.c

@@ -0,0 +1,290 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "member.h"
+#include "dir.h"
+#include "ast.h"
+#include "recover.h"
+#include "lowcomms.h"
+#include "lock.h"
+#include "requestqueue.h"
+#include "recoverd.h"
+
+
+/* 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. */
+
+static int enable_locking(struct dlm_ls *ls, uint64_t seq)
+{
+	int error = -EINTR;
+
+	spin_lock(&ls->ls_recover_lock);
+	if (ls->ls_recover_seq == seq) {
+		set_bit(LSFL_RUNNING, &ls->ls_flags);
+		up_write(&ls->ls_in_recovery);
+		error = 0;
+	}
+	spin_unlock(&ls->ls_recover_lock);
+	return error;
+}
+
+static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
+{
+	unsigned long start;
+	int error, neg = 0;
+
+	log_debug(ls, "recover %llx", rv->seq);
+
+	mutex_lock(&ls->ls_recoverd_active);
+
+	/*
+	 * Suspending and resuming dlm_astd ensures that no lkb's from this ls
+	 * will be processed by dlm_astd during recovery.
+	 */
+
+	dlm_astd_suspend();
+	dlm_astd_resume();
+
+	/*
+	 * This list of root rsb's will be the basis of most of the recovery
+	 * routines.
+	 */
+
+	dlm_create_root_list(ls);
+
+	/*
+	 * Free all the tossed rsb's so we don't have to recover them.
+	 */
+
+	dlm_clear_toss_list(ls);
+
+	/*
+	 * Add or remove nodes from the lockspace's ls_nodes list.
+	 * Also waits for all nodes to complete dlm_recover_members.
+	 */
+
+	error = dlm_recover_members(ls, rv, &neg);
+	if (error) {
+		log_error(ls, "recover_members failed %d", error);
+		goto fail;
+	}
+	start = jiffies;
+
+	/*
+	 * Rebuild our own share of the directory by collecting from all other
+	 * nodes their master rsb names that hash to us.
+	 */
+
+	error = dlm_recover_directory(ls);
+	if (error) {
+		log_error(ls, "recover_directory failed %d", error);
+		goto fail;
+	}
+
+	/*
+	 * Purge directory-related requests that are saved in requestqueue.
+	 * All dir requests from before recovery are invalid now due to the dir
+	 * rebuild and will be resent by the requesting nodes.
+	 */
+
+	dlm_purge_requestqueue(ls);
+
+	/*
+	 * Wait for all nodes to complete directory rebuild.
+	 */
+
+	error = dlm_recover_directory_wait(ls);
+	if (error) {
+		log_error(ls, "recover_directory_wait failed %d", error);
+		goto fail;
+	}
+
+	/*
+	 * We may have outstanding operations that are waiting for a reply from
+	 * a failed node.  Mark these to be resent after recovery.  Unlock and
+	 * cancel ops can just be completed.
+	 */
+
+	dlm_recover_waiters_pre(ls);
+
+	error = dlm_recovery_stopped(ls);
+	if (error)
+		goto fail;
+
+	if (neg || dlm_no_directory(ls)) {
+		/*
+		 * Clear lkb's for departed nodes.
+		 */
+
+		dlm_purge_locks(ls);
+
+		/*
+		 * Get new master nodeid's for rsb's that were mastered on
+		 * departed nodes.
+		 */
+
+		error = dlm_recover_masters(ls);
+		if (error) {
+			log_error(ls, "recover_masters failed %d", error);
+			goto fail;
+		}
+
+		/*
+		 * Send our locks on remastered rsb's to the new masters.
+		 */
+
+		error = dlm_recover_locks(ls);
+		if (error) {
+			log_error(ls, "recover_locks failed %d", error);
+			goto fail;
+		}
+
+		error = dlm_recover_locks_wait(ls);
+		if (error) {
+			log_error(ls, "recover_locks_wait failed %d", error);
+			goto fail;
+		}
+
+		/*
+		 * Finalize state in master rsb's now that all locks can be
+		 * checked.  This includes conversion resolution and lvb
+		 * settings.
+		 */
+
+		dlm_recover_rsbs(ls);
+	}
+
+	dlm_release_root_list(ls);
+
+	dlm_set_recover_status(ls, DLM_RS_DONE);
+	error = dlm_recover_done_wait(ls);
+	if (error) {
+		log_error(ls, "recover_done_wait failed %d", error);
+		goto fail;
+	}
+
+	dlm_clear_members_gone(ls);
+
+	error = enable_locking(ls, rv->seq);
+	if (error) {
+		log_error(ls, "enable_locking failed %d", error);
+		goto fail;
+	}
+
+	error = dlm_process_requestqueue(ls);
+	if (error) {
+		log_error(ls, "process_requestqueue failed %d", error);
+		goto fail;
+	}
+
+	error = dlm_recover_waiters_post(ls);
+	if (error) {
+		log_error(ls, "recover_waiters_post failed %d", error);
+		goto fail;
+	}
+
+	dlm_grant_after_purge(ls);
+
+	dlm_astd_wake();
+
+	log_debug(ls, "recover %llx done: %u ms", rv->seq,
+		  jiffies_to_msecs(jiffies - start));
+	mutex_unlock(&ls->ls_recoverd_active);
+
+	return 0;
+
+ fail:
+	dlm_release_root_list(ls);
+	log_debug(ls, "recover %llx error %d", rv->seq, error);
+	mutex_unlock(&ls->ls_recoverd_active);
+	return error;
+}
+
+static void do_ls_recovery(struct dlm_ls *ls)
+{
+	struct dlm_recover *rv = NULL;
+
+	spin_lock(&ls->ls_recover_lock);
+	rv = ls->ls_recover_args;
+	ls->ls_recover_args = NULL;
+	clear_bit(LSFL_RECOVERY_STOP, &ls->ls_flags);
+	spin_unlock(&ls->ls_recover_lock);
+
+	if (rv) {
+		ls_recover(ls, rv);
+		kfree(rv->nodeids);
+		kfree(rv);
+	}
+}
+
+static int dlm_recoverd(void *arg)
+{
+	struct dlm_ls *ls;
+
+	ls = dlm_find_lockspace_local(arg);
+	if (!ls) {
+		log_print("dlm_recoverd: no lockspace %p", arg);
+		return -1;
+	}
+
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (!test_bit(LSFL_WORK, &ls->ls_flags))
+			schedule();
+		set_current_state(TASK_RUNNING);
+
+		if (test_and_clear_bit(LSFL_WORK, &ls->ls_flags))
+			do_ls_recovery(ls);
+	}
+
+	dlm_put_lockspace(ls);
+	return 0;
+}
+
+void dlm_recoverd_kick(struct dlm_ls *ls)
+{
+	set_bit(LSFL_WORK, &ls->ls_flags);
+	wake_up_process(ls->ls_recoverd_task);
+}
+
+int dlm_recoverd_start(struct dlm_ls *ls)
+{
+	struct task_struct *p;
+	int error = 0;
+
+	p = kthread_run(dlm_recoverd, ls, "dlm_recoverd");
+	if (IS_ERR(p))
+		error = PTR_ERR(p);
+	else
+                ls->ls_recoverd_task = p;
+	return error;
+}
+
+void dlm_recoverd_stop(struct dlm_ls *ls)
+{
+	kthread_stop(ls->ls_recoverd_task);
+}
+
+void dlm_recoverd_suspend(struct dlm_ls *ls)
+{
+	wake_up(&ls->ls_wait_general);
+	mutex_lock(&ls->ls_recoverd_active);
+}
+
+void dlm_recoverd_resume(struct dlm_ls *ls)
+{
+	mutex_unlock(&ls->ls_recoverd_active);
+}
+

fs/dlm/recoverd.h

@@ -0,0 +1,24 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
+**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __RECOVERD_DOT_H__
+#define __RECOVERD_DOT_H__
+
+void dlm_recoverd_kick(struct dlm_ls *ls);
+void dlm_recoverd_stop(struct dlm_ls *ls);
+int dlm_recoverd_start(struct dlm_ls *ls);
+void dlm_recoverd_suspend(struct dlm_ls *ls);
+void dlm_recoverd_resume(struct dlm_ls *ls);
+
+#endif				/* __RECOVERD_DOT_H__ */
+

fs/dlm/requestqueue.c

@@ -0,0 +1,184 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "member.h"
+#include "lock.h"
+#include "dir.h"
+#include "config.h"
+#include "requestqueue.h"
+
+struct rq_entry {
+	struct list_head list;
+	int nodeid;
+	char request[1];
+};
+
+/*
+ * Requests received while the lockspace is in recovery get added to the
+ * request queue and processed when recovery is complete.  This happens when
+ * the lockspace is suspended on some nodes before it is on others, or the
+ * lockspace is enabled on some while still suspended on others.
+ */
+
+void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_header *hd)
+{
+	struct rq_entry *e;
+	int length = hd->h_length;
+
+	if (dlm_is_removed(ls, nodeid))
+		return;
+
+	e = kmalloc(sizeof(struct rq_entry) + length, GFP_KERNEL);
+	if (!e) {
+		log_print("dlm_add_requestqueue: out of memory\n");
+		return;
+	}
+
+	e->nodeid = nodeid;
+	memcpy(e->request, hd, length);
+
+	mutex_lock(&ls->ls_requestqueue_mutex);
+	list_add_tail(&e->list, &ls->ls_requestqueue);
+	mutex_unlock(&ls->ls_requestqueue_mutex);
+}
+
+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);
+
+	for (;;) {
+		if (list_empty(&ls->ls_requestqueue)) {
+			mutex_unlock(&ls->ls_requestqueue_mutex);
+			error = 0;
+			break;
+		}
+		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;
+		}
+
+		mutex_lock(&ls->ls_requestqueue_mutex);
+		list_del(&e->list);
+		kfree(e);
+
+		if (dlm_locking_stopped(ls)) {
+			log_debug(ls, "process_requestqueue abort running");
+			mutex_unlock(&ls->ls_requestqueue_mutex);
+			error = -EINTR;
+			break;
+		}
+		schedule();
+	}
+
+	return error;
+}
+
+/*
+ * 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.
+ */
+
+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();
+	}
+	mutex_unlock(&ls->ls_requestqueue_mutex);
+}
+
+static int purge_request(struct dlm_ls *ls, struct dlm_message *ms, int nodeid)
+{
+	uint32_t type = ms->m_type;
+
+	if (dlm_is_removed(ls, nodeid))
+		return 1;
+
+	/* directory operations are always purged because the directory is
+	   always rebuilt during recovery and the lookups resent */
+
+	if (type == DLM_MSG_REMOVE ||
+	    type == DLM_MSG_LOOKUP ||
+	    type == DLM_MSG_LOOKUP_REPLY)
+		return 1;
+
+	if (!dlm_no_directory(ls))
+		return 0;
+
+	/* with no directory, the master is likely to change as a part of
+	   recovery; requests to/from the defunct master need to be purged */
+
+	switch (type) {
+	case DLM_MSG_REQUEST:
+	case DLM_MSG_CONVERT:
+	case DLM_MSG_UNLOCK:
+	case DLM_MSG_CANCEL:
+		/* we're no longer the master of this resource, the sender
+		   will resend to the new master (see waiter_needs_recovery) */
+
+		if (dlm_hash2nodeid(ls, ms->m_hash) != dlm_our_nodeid())
+			return 1;
+		break;
+
+	case DLM_MSG_REQUEST_REPLY:
+	case DLM_MSG_CONVERT_REPLY:
+	case DLM_MSG_UNLOCK_REPLY:
+	case DLM_MSG_CANCEL_REPLY:
+	case DLM_MSG_GRANT:
+		/* this reply is from the former master of the resource,
+		   we'll resend to the new master if needed */
+
+		if (dlm_hash2nodeid(ls, ms->m_hash) != nodeid)
+			return 1;
+		break;
+	}
+
+	return 0;
+}
+
+void dlm_purge_requestqueue(struct dlm_ls *ls)
+{
+	struct dlm_message *ms;
+	struct rq_entry *e, *safe;
+
+	mutex_lock(&ls->ls_requestqueue_mutex);
+	list_for_each_entry_safe(e, safe, &ls->ls_requestqueue, list) {
+		ms = (struct dlm_message *) e->request;
+
+		if (purge_request(ls, ms, e->nodeid)) {
+			list_del(&e->list);
+			kfree(e);
+		}
+	}
+	mutex_unlock(&ls->ls_requestqueue_mutex);
+}
+

fs/dlm/requestqueue.h

@@ -0,0 +1,22 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __REQUESTQUEUE_DOT_H__
+#define __REQUESTQUEUE_DOT_H__
+
+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);
+
+#endif
+

fs/dlm/user.c

@@ -0,0 +1,788 @@
+/*
+ * Copyright (C) 2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License v.2.
+ */
+
+#include <linux/miscdevice.h>
+#include <linux/init.h>
+#include <linux/wait.h>
+#include <linux/module.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/poll.h>
+#include <linux/signal.h>
+#include <linux/spinlock.h>
+#include <linux/dlm.h>
+#include <linux/dlm_device.h>
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+#include "lock.h"
+#include "lvb_table.h"
+
+static const char *name_prefix="dlm";
+static struct miscdevice ctl_device;
+static struct file_operations device_fops;
+
+#ifdef CONFIG_COMPAT
+
+struct dlm_lock_params32 {
+	__u8 mode;
+	__u8 namelen;
+	__u16 flags;
+	__u32 lkid;
+	__u32 parent;
+
+	__u32 castparam;
+	__u32 castaddr;
+	__u32 bastparam;
+	__u32 bastaddr;
+	__u32 lksb;
+
+	char lvb[DLM_USER_LVB_LEN];
+	char name[0];
+};
+
+struct dlm_write_request32 {
+	__u32 version[3];
+	__u8 cmd;
+	__u8 is64bit;
+	__u8 unused[2];
+
+	union  {
+		struct dlm_lock_params32 lock;
+		struct dlm_lspace_params lspace;
+	} i;
+};
+
+struct dlm_lksb32 {
+	__u32 sb_status;
+	__u32 sb_lkid;
+	__u8 sb_flags;
+	__u32 sb_lvbptr;
+};
+
+struct dlm_lock_result32 {
+	__u32 length;
+	__u32 user_astaddr;
+	__u32 user_astparam;
+	__u32 user_lksb;
+	struct dlm_lksb32 lksb;
+	__u8 bast_mode;
+	__u8 unused[3];
+	/* Offsets may be zero if no data is present */
+	__u32 lvb_offset;
+};
+
+static void compat_input(struct dlm_write_request *kb,
+			 struct dlm_write_request32 *kb32)
+{
+	kb->version[0] = kb32->version[0];
+	kb->version[1] = kb32->version[1];
+	kb->version[2] = kb32->version[2];
+
+	kb->cmd = kb32->cmd;
+	kb->is64bit = kb32->is64bit;
+	if (kb->cmd == DLM_USER_CREATE_LOCKSPACE ||
+	    kb->cmd == DLM_USER_REMOVE_LOCKSPACE) {
+		kb->i.lspace.flags = kb32->i.lspace.flags;
+		kb->i.lspace.minor = kb32->i.lspace.minor;
+		strcpy(kb->i.lspace.name, kb32->i.lspace.name);
+	} else {
+		kb->i.lock.mode = kb32->i.lock.mode;
+		kb->i.lock.namelen = kb32->i.lock.namelen;
+		kb->i.lock.flags = kb32->i.lock.flags;
+		kb->i.lock.lkid = kb32->i.lock.lkid;
+		kb->i.lock.parent = kb32->i.lock.parent;
+		kb->i.lock.castparam = (void *)(long)kb32->i.lock.castparam;
+		kb->i.lock.castaddr = (void *)(long)kb32->i.lock.castaddr;
+		kb->i.lock.bastparam = (void *)(long)kb32->i.lock.bastparam;
+		kb->i.lock.bastaddr = (void *)(long)kb32->i.lock.bastaddr;
+		kb->i.lock.lksb = (void *)(long)kb32->i.lock.lksb;
+		memcpy(kb->i.lock.lvb, kb32->i.lock.lvb, DLM_USER_LVB_LEN);
+		memcpy(kb->i.lock.name, kb32->i.lock.name, kb->i.lock.namelen);
+	}
+}
+
+static void compat_output(struct dlm_lock_result *res,
+			  struct dlm_lock_result32 *res32)
+{
+	res32->length = res->length - (sizeof(struct dlm_lock_result) -
+				       sizeof(struct dlm_lock_result32));
+	res32->user_astaddr = (__u32)(long)res->user_astaddr;
+	res32->user_astparam = (__u32)(long)res->user_astparam;
+	res32->user_lksb = (__u32)(long)res->user_lksb;
+	res32->bast_mode = res->bast_mode;
+
+	res32->lvb_offset = res->lvb_offset;
+	res32->length = res->length;
+
+	res32->lksb.sb_status = res->lksb.sb_status;
+	res32->lksb.sb_flags = res->lksb.sb_flags;
+	res32->lksb.sb_lkid = res->lksb.sb_lkid;
+	res32->lksb.sb_lvbptr = (__u32)(long)res->lksb.sb_lvbptr;
+}
+#endif
+
+
+void dlm_user_add_ast(struct dlm_lkb *lkb, int type)
+{
+	struct dlm_ls *ls;
+	struct dlm_user_args *ua;
+	struct dlm_user_proc *proc;
+	int remove_ownqueue = 0;
+
+	/* dlm_clear_proc_locks() sets ORPHAN/DEAD flag on each
+	   lkb before dealing with it.  We need to check this
+	   flag before taking ls_clear_proc_locks mutex because if
+	   it's set, dlm_clear_proc_locks() holds the mutex. */
+
+	if (lkb->lkb_flags & (DLM_IFL_ORPHAN | DLM_IFL_DEAD)) {
+		/* log_print("user_add_ast skip1 %x", lkb->lkb_flags); */
+		return;
+	}
+
+	ls = lkb->lkb_resource->res_ls;
+	mutex_lock(&ls->ls_clear_proc_locks);
+
+	/* If ORPHAN/DEAD flag is set, it means the process is dead so an ast
+	   can't be delivered.  For ORPHAN's, dlm_clear_proc_locks() freed
+	   lkb->ua so we can't try to use it. */
+
+	if (lkb->lkb_flags & (DLM_IFL_ORPHAN | DLM_IFL_DEAD)) {
+		/* log_print("user_add_ast skip2 %x", lkb->lkb_flags); */
+		goto out;
+	}
+
+	DLM_ASSERT(lkb->lkb_astparam, dlm_print_lkb(lkb););
+	ua = (struct dlm_user_args *)lkb->lkb_astparam;
+	proc = ua->proc;
+
+	if (type == AST_BAST && ua->bastaddr == NULL)
+		goto out;
+
+	spin_lock(&proc->asts_spin);
+	if (!(lkb->lkb_ast_type & (AST_COMP | AST_BAST))) {
+		kref_get(&lkb->lkb_ref);
+		list_add_tail(&lkb->lkb_astqueue, &proc->asts);
+		lkb->lkb_ast_type |= type;
+		wake_up_interruptible(&proc->wait);
+	}
+
+	/* noqueue requests that fail may need to be removed from the
+	   proc's locks list, there should be a better way of detecting
+	   this situation than checking all these things... */
+
+	if (type == AST_COMP && lkb->lkb_grmode == DLM_LOCK_IV &&
+	    ua->lksb.sb_status == -EAGAIN && !list_empty(&lkb->lkb_ownqueue))
+		remove_ownqueue = 1;
+
+	/* We want to copy the lvb to userspace when the completion
+	   ast is read if the status is 0, the lock has an lvb and
+	   lvb_ops says we should.  We could probably have set_lvb_lock()
+	   set update_user_lvb instead and not need old_mode */
+
+	if ((lkb->lkb_ast_type & AST_COMP) &&
+	    (lkb->lkb_lksb->sb_status == 0) &&
+	    lkb->lkb_lksb->sb_lvbptr &&
+	    dlm_lvb_operations[ua->old_mode + 1][lkb->lkb_grmode + 1])
+		ua->update_user_lvb = 1;
+	else
+		ua->update_user_lvb = 0;
+
+	spin_unlock(&proc->asts_spin);
+
+	if (remove_ownqueue) {
+		spin_lock(&ua->proc->locks_spin);
+		list_del_init(&lkb->lkb_ownqueue);
+		spin_unlock(&ua->proc->locks_spin);
+		dlm_put_lkb(lkb);
+	}
+ out:
+	mutex_unlock(&ls->ls_clear_proc_locks);
+}
+
+static int device_user_lock(struct dlm_user_proc *proc,
+			    struct dlm_lock_params *params)
+{
+	struct dlm_ls *ls;
+	struct dlm_user_args *ua;
+	int error = -ENOMEM;
+
+	ls = dlm_find_lockspace_local(proc->lockspace);
+	if (!ls)
+		return -ENOENT;
+
+	if (!params->castaddr || !params->lksb) {
+		error = -EINVAL;
+		goto out;
+	}
+
+	ua = kzalloc(sizeof(struct dlm_user_args), GFP_KERNEL);
+	if (!ua)
+		goto out;
+	ua->proc = proc;
+	ua->user_lksb = params->lksb;
+	ua->castparam = params->castparam;
+	ua->castaddr = params->castaddr;
+	ua->bastparam = params->bastparam;
+	ua->bastaddr = params->bastaddr;
+
+	if (params->flags & DLM_LKF_CONVERT)
+		error = dlm_user_convert(ls, ua,
+				         params->mode, params->flags,
+				         params->lkid, params->lvb);
+	else {
+		error = dlm_user_request(ls, ua,
+					 params->mode, params->flags,
+					 params->name, params->namelen,
+					 params->parent);
+		if (!error)
+			error = ua->lksb.sb_lkid;
+	}
+ out:
+	dlm_put_lockspace(ls);
+	return error;
+}
+
+static int device_user_unlock(struct dlm_user_proc *proc,
+			      struct dlm_lock_params *params)
+{
+	struct dlm_ls *ls;
+	struct dlm_user_args *ua;
+	int error = -ENOMEM;
+
+	ls = dlm_find_lockspace_local(proc->lockspace);
+	if (!ls)
+		return -ENOENT;
+
+	ua = kzalloc(sizeof(struct dlm_user_args), GFP_KERNEL);
+	if (!ua)
+		goto out;
+	ua->proc = proc;
+	ua->user_lksb = params->lksb;
+	ua->castparam = params->castparam;
+	ua->castaddr = params->castaddr;
+
+	if (params->flags & DLM_LKF_CANCEL)
+		error = dlm_user_cancel(ls, ua, params->flags, params->lkid);
+	else
+		error = dlm_user_unlock(ls, ua, params->flags, params->lkid,
+					params->lvb);
+ out:
+	dlm_put_lockspace(ls);
+	return error;
+}
+
+static int device_create_lockspace(struct dlm_lspace_params *params)
+{
+	dlm_lockspace_t *lockspace;
+	struct dlm_ls *ls;
+	int error, len;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	error = dlm_new_lockspace(params->name, strlen(params->name),
+				  &lockspace, 0, DLM_USER_LVB_LEN);
+	if (error)
+		return error;
+
+	ls = dlm_find_lockspace_local(lockspace);
+	if (!ls)
+		return -ENOENT;
+
+	error = -ENOMEM;
+	len = strlen(params->name) + strlen(name_prefix) + 2;
+	ls->ls_device.name = kzalloc(len, GFP_KERNEL);
+	if (!ls->ls_device.name)
+		goto fail;
+	snprintf((char *)ls->ls_device.name, len, "%s_%s", name_prefix,
+		 params->name);
+	ls->ls_device.fops = &device_fops;
+	ls->ls_device.minor = MISC_DYNAMIC_MINOR;
+
+	error = misc_register(&ls->ls_device);
+	if (error) {
+		kfree(ls->ls_device.name);
+		goto fail;
+	}
+
+	error = ls->ls_device.minor;
+	dlm_put_lockspace(ls);
+	return error;
+
+ fail:
+	dlm_put_lockspace(ls);
+	dlm_release_lockspace(lockspace, 0);
+	return error;
+}
+
+static int device_remove_lockspace(struct dlm_lspace_params *params)
+{
+	dlm_lockspace_t *lockspace;
+	struct dlm_ls *ls;
+	int error, force = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	ls = dlm_find_lockspace_device(params->minor);
+	if (!ls)
+		return -ENOENT;
+
+	error = misc_deregister(&ls->ls_device);
+	if (error) {
+		dlm_put_lockspace(ls);
+		goto out;
+	}
+	kfree(ls->ls_device.name);
+
+	if (params->flags & DLM_USER_LSFLG_FORCEFREE)
+		force = 2;
+
+	lockspace = ls->ls_local_handle;
+
+	/* dlm_release_lockspace waits for references to go to zero,
+	   so all processes will need to close their device for the ls
+	   before the release will procede */
+
+	dlm_put_lockspace(ls);
+	error = dlm_release_lockspace(lockspace, force);
+ out:
+	return error;
+}
+
+/* Check the user's version matches ours */
+static int check_version(struct dlm_write_request *req)
+{
+	if (req->version[0] != DLM_DEVICE_VERSION_MAJOR ||
+	    (req->version[0] == DLM_DEVICE_VERSION_MAJOR &&
+	     req->version[1] > DLM_DEVICE_VERSION_MINOR)) {
+
+		printk(KERN_DEBUG "dlm: process %s (%d) version mismatch "
+		       "user (%d.%d.%d) kernel (%d.%d.%d)\n",
+		       current->comm,
+		       current->pid,
+		       req->version[0],
+		       req->version[1],
+		       req->version[2],
+		       DLM_DEVICE_VERSION_MAJOR,
+		       DLM_DEVICE_VERSION_MINOR,
+		       DLM_DEVICE_VERSION_PATCH);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/*
+ * device_write
+ *
+ *   device_user_lock
+ *     dlm_user_request -> request_lock
+ *     dlm_user_convert -> convert_lock
+ *
+ *   device_user_unlock
+ *     dlm_user_unlock -> unlock_lock
+ *     dlm_user_cancel -> cancel_lock
+ *
+ *   device_create_lockspace
+ *     dlm_new_lockspace
+ *
+ *   device_remove_lockspace
+ *     dlm_release_lockspace
+ */
+
+/* a write to a lockspace device is a lock or unlock request, a write
+   to the control device is to create/remove a lockspace */
+
+static ssize_t device_write(struct file *file, const char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+	struct dlm_user_proc *proc = file->private_data;
+	struct dlm_write_request *kbuf;
+	sigset_t tmpsig, allsigs;
+	int error;
+
+#ifdef CONFIG_COMPAT
+	if (count < sizeof(struct dlm_write_request32))
+#else
+	if (count < sizeof(struct dlm_write_request))
+#endif
+		return -EINVAL;
+
+	kbuf = kmalloc(count, GFP_KERNEL);
+	if (!kbuf)
+		return -ENOMEM;
+
+	if (copy_from_user(kbuf, buf, count)) {
+		error = -EFAULT;
+		goto out_free;
+	}
+
+	if (check_version(kbuf)) {
+		error = -EBADE;
+		goto out_free;
+	}
+
+#ifdef CONFIG_COMPAT
+	if (!kbuf->is64bit) {
+		struct dlm_write_request32 *k32buf;
+		k32buf = (struct dlm_write_request32 *)kbuf;
+		kbuf = kmalloc(count + (sizeof(struct dlm_write_request) -
+			       sizeof(struct dlm_write_request32)), GFP_KERNEL);
+		if (!kbuf)
+			return -ENOMEM;
+
+		if (proc)
+			set_bit(DLM_PROC_FLAGS_COMPAT, &proc->flags);
+		compat_input(kbuf, k32buf);
+		kfree(k32buf);
+	}
+#endif
+
+	/* do we really need this? can a write happen after a close? */
+	if ((kbuf->cmd == DLM_USER_LOCK || kbuf->cmd == DLM_USER_UNLOCK) &&
+	    test_bit(DLM_PROC_FLAGS_CLOSING, &proc->flags))
+		return -EINVAL;
+
+	sigfillset(&allsigs);
+	sigprocmask(SIG_BLOCK, &allsigs, &tmpsig);
+
+	error = -EINVAL;
+
+	switch (kbuf->cmd)
+	{
+	case DLM_USER_LOCK:
+		if (!proc) {
+			log_print("no locking on control device");
+			goto out_sig;
+		}
+		error = device_user_lock(proc, &kbuf->i.lock);
+		break;
+
+	case DLM_USER_UNLOCK:
+		if (!proc) {
+			log_print("no locking on control device");
+			goto out_sig;
+		}
+		error = device_user_unlock(proc, &kbuf->i.lock);
+		break;
+
+	case DLM_USER_CREATE_LOCKSPACE:
+		if (proc) {
+			log_print("create/remove only on control device");
+			goto out_sig;
+		}
+		error = device_create_lockspace(&kbuf->i.lspace);
+		break;
+
+	case DLM_USER_REMOVE_LOCKSPACE:
+		if (proc) {
+			log_print("create/remove only on control device");
+			goto out_sig;
+		}
+		error = device_remove_lockspace(&kbuf->i.lspace);
+		break;
+
+	default:
+		log_print("Unknown command passed to DLM device : %d\n",
+			  kbuf->cmd);
+	}
+
+ out_sig:
+	sigprocmask(SIG_SETMASK, &tmpsig, NULL);
+	recalc_sigpending();
+ out_free:
+	kfree(kbuf);
+	return error;
+}
+
+/* Every process that opens the lockspace device has its own "proc" structure
+   hanging off the open file that's used to keep track of locks owned by the
+   process and asts that need to be delivered to the process. */
+
+static int device_open(struct inode *inode, struct file *file)
+{
+	struct dlm_user_proc *proc;
+	struct dlm_ls *ls;
+
+	ls = dlm_find_lockspace_device(iminor(inode));
+	if (!ls)
+		return -ENOENT;
+
+	proc = kzalloc(sizeof(struct dlm_user_proc), GFP_KERNEL);
+	if (!proc) {
+		dlm_put_lockspace(ls);
+		return -ENOMEM;
+	}
+
+	proc->lockspace = ls->ls_local_handle;
+	INIT_LIST_HEAD(&proc->asts);
+	INIT_LIST_HEAD(&proc->locks);
+	spin_lock_init(&proc->asts_spin);
+	spin_lock_init(&proc->locks_spin);
+	init_waitqueue_head(&proc->wait);
+	file->private_data = proc;
+
+	return 0;
+}
+
+static int device_close(struct inode *inode, struct file *file)
+{
+	struct dlm_user_proc *proc = file->private_data;
+	struct dlm_ls *ls;
+	sigset_t tmpsig, allsigs;
+
+	ls = dlm_find_lockspace_local(proc->lockspace);
+	if (!ls)
+		return -ENOENT;
+
+	sigfillset(&allsigs);
+	sigprocmask(SIG_BLOCK, &allsigs, &tmpsig);
+
+	set_bit(DLM_PROC_FLAGS_CLOSING, &proc->flags);
+
+	dlm_clear_proc_locks(ls, proc);
+
+	/* at this point no more lkb's should exist for this lockspace,
+	   so there's no chance of dlm_user_add_ast() being called and
+	   looking for lkb->ua->proc */
+
+	kfree(proc);
+	file->private_data = NULL;
+
+	dlm_put_lockspace(ls);
+	dlm_put_lockspace(ls);  /* for the find in device_open() */
+
+	/* FIXME: AUTOFREE: if this ls is no longer used do
+	   device_remove_lockspace() */
+
+	sigprocmask(SIG_SETMASK, &tmpsig, NULL);
+	recalc_sigpending();
+
+	return 0;
+}
+
+static int copy_result_to_user(struct dlm_user_args *ua, int compat, int type,
+			       int bmode, char __user *buf, size_t count)
+{
+#ifdef CONFIG_COMPAT
+	struct dlm_lock_result32 result32;
+#endif
+	struct dlm_lock_result result;
+	void *resultptr;
+	int error=0;
+	int len;
+	int struct_len;
+
+	memset(&result, 0, sizeof(struct dlm_lock_result));
+	memcpy(&result.lksb, &ua->lksb, sizeof(struct dlm_lksb));
+	result.user_lksb = ua->user_lksb;
+
+	/* FIXME: dlm1 provides for the user's bastparam/addr to not be updated
+	   in a conversion unless the conversion is successful.  See code
+	   in dlm_user_convert() for updating ua from ua_tmp.  OpenVMS, though,
+	   notes that a new blocking AST address and parameter are set even if
+	   the conversion fails, so maybe we should just do that. */
+
+	if (type == AST_BAST) {
+		result.user_astaddr = ua->bastaddr;
+		result.user_astparam = ua->bastparam;
+		result.bast_mode = bmode;
+	} else {
+		result.user_astaddr = ua->castaddr;
+		result.user_astparam = ua->castparam;
+	}
+
+#ifdef CONFIG_COMPAT
+	if (compat)
+		len = sizeof(struct dlm_lock_result32);
+	else
+#endif
+		len = sizeof(struct dlm_lock_result);
+	struct_len = len;
+
+	/* copy lvb to userspace if there is one, it's been updated, and
+	   the user buffer has space for it */
+
+	if (ua->update_user_lvb && ua->lksb.sb_lvbptr &&
+	    count >= len + DLM_USER_LVB_LEN) {
+		if (copy_to_user(buf+len, ua->lksb.sb_lvbptr,
+				 DLM_USER_LVB_LEN)) {
+			error = -EFAULT;
+			goto out;
+		}
+
+		result.lvb_offset = len;
+		len += DLM_USER_LVB_LEN;
+	}
+
+	result.length = len;
+	resultptr = &result;
+#ifdef CONFIG_COMPAT
+	if (compat) {
+		compat_output(&result, &result32);
+		resultptr = &result32;
+	}
+#endif
+
+	if (copy_to_user(buf, resultptr, struct_len))
+		error = -EFAULT;
+	else
+		error = len;
+ out:
+	return error;
+}
+
+/* a read returns a single ast described in a struct dlm_lock_result */
+
+static ssize_t device_read(struct file *file, char __user *buf, size_t count,
+			   loff_t *ppos)
+{
+	struct dlm_user_proc *proc = file->private_data;
+	struct dlm_lkb *lkb;
+	struct dlm_user_args *ua;
+	DECLARE_WAITQUEUE(wait, current);
+	int error, type=0, bmode=0, removed = 0;
+
+#ifdef CONFIG_COMPAT
+	if (count < sizeof(struct dlm_lock_result32))
+#else
+	if (count < sizeof(struct dlm_lock_result))
+#endif
+		return -EINVAL;
+
+	/* do we really need this? can a read happen after a close? */
+	if (test_bit(DLM_PROC_FLAGS_CLOSING, &proc->flags))
+		return -EINVAL;
+
+	spin_lock(&proc->asts_spin);
+	if (list_empty(&proc->asts)) {
+		if (file->f_flags & O_NONBLOCK) {
+			spin_unlock(&proc->asts_spin);
+			return -EAGAIN;
+		}
+
+		add_wait_queue(&proc->wait, &wait);
+
+	repeat:
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (list_empty(&proc->asts) && !signal_pending(current)) {
+			spin_unlock(&proc->asts_spin);
+			schedule();
+			spin_lock(&proc->asts_spin);
+			goto repeat;
+		}
+		set_current_state(TASK_RUNNING);
+		remove_wait_queue(&proc->wait, &wait);
+
+		if (signal_pending(current)) {
+			spin_unlock(&proc->asts_spin);
+			return -ERESTARTSYS;
+		}
+	}
+
+	if (list_empty(&proc->asts)) {
+		spin_unlock(&proc->asts_spin);
+		return -EAGAIN;
+	}
+
+	/* there may be both completion and blocking asts to return for
+	   the lkb, don't remove lkb from asts list unless no asts remain */
+
+	lkb = list_entry(proc->asts.next, struct dlm_lkb, lkb_astqueue);
+
+	if (lkb->lkb_ast_type & AST_COMP) {
+		lkb->lkb_ast_type &= ~AST_COMP;
+		type = AST_COMP;
+	} else if (lkb->lkb_ast_type & AST_BAST) {
+		lkb->lkb_ast_type &= ~AST_BAST;
+		type = AST_BAST;
+		bmode = lkb->lkb_bastmode;
+	}
+
+	if (!lkb->lkb_ast_type) {
+		list_del(&lkb->lkb_astqueue);
+		removed = 1;
+	}
+	spin_unlock(&proc->asts_spin);
+
+	ua = (struct dlm_user_args *)lkb->lkb_astparam;
+	error = copy_result_to_user(ua,
+			 	test_bit(DLM_PROC_FLAGS_COMPAT, &proc->flags),
+				type, bmode, buf, count);
+
+	/* removes reference for the proc->asts lists added by
+	   dlm_user_add_ast() and may result in the lkb being freed */
+	if (removed)
+		dlm_put_lkb(lkb);
+
+	return error;
+}
+
+static unsigned int device_poll(struct file *file, poll_table *wait)
+{
+	struct dlm_user_proc *proc = file->private_data;
+
+	poll_wait(file, &proc->wait, wait);
+
+	spin_lock(&proc->asts_spin);
+	if (!list_empty(&proc->asts)) {
+		spin_unlock(&proc->asts_spin);
+		return POLLIN | POLLRDNORM;
+	}
+	spin_unlock(&proc->asts_spin);
+	return 0;
+}
+
+static int ctl_device_open(struct inode *inode, struct file *file)
+{
+	file->private_data = NULL;
+	return 0;
+}
+
+static int ctl_device_close(struct inode *inode, struct file *file)
+{
+	return 0;
+}
+
+static struct file_operations device_fops = {
+	.open    = device_open,
+	.release = device_close,
+	.read    = device_read,
+	.write   = device_write,
+	.poll    = device_poll,
+	.owner   = THIS_MODULE,
+};
+
+static struct file_operations ctl_device_fops = {
+	.open    = ctl_device_open,
+	.release = ctl_device_close,
+	.write   = device_write,
+	.owner   = THIS_MODULE,
+};
+
+int dlm_user_init(void)
+{
+	int error;
+
+	ctl_device.name = "dlm-control";
+	ctl_device.fops = &ctl_device_fops;
+	ctl_device.minor = MISC_DYNAMIC_MINOR;
+
+	error = misc_register(&ctl_device);
+	if (error)
+		log_print("misc_register failed for control device");
+
+	return error;
+}
+
+void dlm_user_exit(void)
+{
+	misc_deregister(&ctl_device);
+}
+

fs/dlm/user.h

@@ -0,0 +1,16 @@
+/*
+ * Copyright (C) 2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License v.2.
+ */
+
+#ifndef __USER_DOT_H__
+#define __USER_DOT_H__
+
+void dlm_user_add_ast(struct dlm_lkb *lkb, int type);
+int dlm_user_init(void);
+void dlm_user_exit(void);
+
+#endif

fs/dlm/util.c

@@ -0,0 +1,161 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#include "dlm_internal.h"
+#include "rcom.h"
+#include "util.h"
+
+static void header_out(struct dlm_header *hd)
+{
+	hd->h_version		= cpu_to_le32(hd->h_version);
+	hd->h_lockspace		= cpu_to_le32(hd->h_lockspace);
+	hd->h_nodeid		= cpu_to_le32(hd->h_nodeid);
+	hd->h_length		= cpu_to_le16(hd->h_length);
+}
+
+static void header_in(struct dlm_header *hd)
+{
+	hd->h_version		= le32_to_cpu(hd->h_version);
+	hd->h_lockspace		= le32_to_cpu(hd->h_lockspace);
+	hd->h_nodeid		= le32_to_cpu(hd->h_nodeid);
+	hd->h_length		= le16_to_cpu(hd->h_length);
+}
+
+void dlm_message_out(struct dlm_message *ms)
+{
+	struct dlm_header *hd = (struct dlm_header *) ms;
+
+	header_out(hd);
+
+	ms->m_type		= cpu_to_le32(ms->m_type);
+	ms->m_nodeid		= cpu_to_le32(ms->m_nodeid);
+	ms->m_pid		= cpu_to_le32(ms->m_pid);
+	ms->m_lkid		= cpu_to_le32(ms->m_lkid);
+	ms->m_remid		= cpu_to_le32(ms->m_remid);
+	ms->m_parent_lkid	= cpu_to_le32(ms->m_parent_lkid);
+	ms->m_parent_remid	= cpu_to_le32(ms->m_parent_remid);
+	ms->m_exflags		= cpu_to_le32(ms->m_exflags);
+	ms->m_sbflags		= cpu_to_le32(ms->m_sbflags);
+	ms->m_flags		= cpu_to_le32(ms->m_flags);
+	ms->m_lvbseq		= cpu_to_le32(ms->m_lvbseq);
+	ms->m_hash		= cpu_to_le32(ms->m_hash);
+	ms->m_status		= cpu_to_le32(ms->m_status);
+	ms->m_grmode		= cpu_to_le32(ms->m_grmode);
+	ms->m_rqmode		= cpu_to_le32(ms->m_rqmode);
+	ms->m_bastmode		= cpu_to_le32(ms->m_bastmode);
+	ms->m_asts		= cpu_to_le32(ms->m_asts);
+	ms->m_result		= cpu_to_le32(ms->m_result);
+}
+
+void dlm_message_in(struct dlm_message *ms)
+{
+	struct dlm_header *hd = (struct dlm_header *) ms;
+
+	header_in(hd);
+
+	ms->m_type		= le32_to_cpu(ms->m_type);
+	ms->m_nodeid		= le32_to_cpu(ms->m_nodeid);
+	ms->m_pid		= le32_to_cpu(ms->m_pid);
+	ms->m_lkid		= le32_to_cpu(ms->m_lkid);
+	ms->m_remid		= le32_to_cpu(ms->m_remid);
+	ms->m_parent_lkid	= le32_to_cpu(ms->m_parent_lkid);
+	ms->m_parent_remid	= le32_to_cpu(ms->m_parent_remid);
+	ms->m_exflags		= le32_to_cpu(ms->m_exflags);
+	ms->m_sbflags		= le32_to_cpu(ms->m_sbflags);
+	ms->m_flags		= le32_to_cpu(ms->m_flags);
+	ms->m_lvbseq		= le32_to_cpu(ms->m_lvbseq);
+	ms->m_hash		= le32_to_cpu(ms->m_hash);
+	ms->m_status		= le32_to_cpu(ms->m_status);
+	ms->m_grmode		= le32_to_cpu(ms->m_grmode);
+	ms->m_rqmode		= le32_to_cpu(ms->m_rqmode);
+	ms->m_bastmode		= le32_to_cpu(ms->m_bastmode);
+	ms->m_asts		= le32_to_cpu(ms->m_asts);
+	ms->m_result		= le32_to_cpu(ms->m_result);
+}
+
+static void rcom_lock_out(struct rcom_lock *rl)
+{
+	rl->rl_ownpid		= cpu_to_le32(rl->rl_ownpid);
+	rl->rl_lkid		= cpu_to_le32(rl->rl_lkid);
+	rl->rl_remid		= cpu_to_le32(rl->rl_remid);
+	rl->rl_parent_lkid	= cpu_to_le32(rl->rl_parent_lkid);
+	rl->rl_parent_remid	= cpu_to_le32(rl->rl_parent_remid);
+	rl->rl_exflags		= cpu_to_le32(rl->rl_exflags);
+	rl->rl_flags		= cpu_to_le32(rl->rl_flags);
+	rl->rl_lvbseq		= cpu_to_le32(rl->rl_lvbseq);
+	rl->rl_result		= cpu_to_le32(rl->rl_result);
+	rl->rl_wait_type	= cpu_to_le16(rl->rl_wait_type);
+	rl->rl_namelen		= cpu_to_le16(rl->rl_namelen);
+}
+
+static void rcom_lock_in(struct rcom_lock *rl)
+{
+	rl->rl_ownpid		= le32_to_cpu(rl->rl_ownpid);
+	rl->rl_lkid		= le32_to_cpu(rl->rl_lkid);
+	rl->rl_remid		= le32_to_cpu(rl->rl_remid);
+	rl->rl_parent_lkid	= le32_to_cpu(rl->rl_parent_lkid);
+	rl->rl_parent_remid	= le32_to_cpu(rl->rl_parent_remid);
+	rl->rl_exflags		= le32_to_cpu(rl->rl_exflags);
+	rl->rl_flags		= le32_to_cpu(rl->rl_flags);
+	rl->rl_lvbseq		= le32_to_cpu(rl->rl_lvbseq);
+	rl->rl_result		= le32_to_cpu(rl->rl_result);
+	rl->rl_wait_type	= le16_to_cpu(rl->rl_wait_type);
+	rl->rl_namelen		= le16_to_cpu(rl->rl_namelen);
+}
+
+static void rcom_config_out(struct rcom_config *rf)
+{
+	rf->rf_lvblen		= cpu_to_le32(rf->rf_lvblen);
+	rf->rf_lsflags		= cpu_to_le32(rf->rf_lsflags);
+}
+
+static void rcom_config_in(struct rcom_config *rf)
+{
+	rf->rf_lvblen		= le32_to_cpu(rf->rf_lvblen);
+	rf->rf_lsflags		= le32_to_cpu(rf->rf_lsflags);
+}
+
+void dlm_rcom_out(struct dlm_rcom *rc)
+{
+	struct dlm_header *hd = (struct dlm_header *) rc;
+	int type = rc->rc_type;
+
+	header_out(hd);
+
+	rc->rc_type		= cpu_to_le32(rc->rc_type);
+	rc->rc_result		= cpu_to_le32(rc->rc_result);
+	rc->rc_id		= cpu_to_le64(rc->rc_id);
+
+	if (type == DLM_RCOM_LOCK)
+		rcom_lock_out((struct rcom_lock *) rc->rc_buf);
+
+	else if (type == DLM_RCOM_STATUS_REPLY)
+		rcom_config_out((struct rcom_config *) rc->rc_buf);
+}
+
+void dlm_rcom_in(struct dlm_rcom *rc)
+{
+	struct dlm_header *hd = (struct dlm_header *) rc;
+
+	header_in(hd);
+
+	rc->rc_type		= le32_to_cpu(rc->rc_type);
+	rc->rc_result		= le32_to_cpu(rc->rc_result);
+	rc->rc_id		= le64_to_cpu(rc->rc_id);
+
+	if (rc->rc_type == DLM_RCOM_LOCK)
+		rcom_lock_in((struct rcom_lock *) rc->rc_buf);
+
+	else if (rc->rc_type == DLM_RCOM_STATUS_REPLY)
+		rcom_config_in((struct rcom_config *) rc->rc_buf);
+}
+

fs/dlm/util.h

@@ -0,0 +1,22 @@
+/******************************************************************************
+*******************************************************************************
+**
+**  Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+**
+**  This copyrighted material is made available to anyone wishing to use,
+**  modify, copy, or redistribute it subject to the terms and conditions
+**  of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+#ifndef __UTIL_DOT_H__
+#define __UTIL_DOT_H__
+
+void dlm_message_out(struct dlm_message *ms);
+void dlm_message_in(struct dlm_message *ms);
+void dlm_rcom_out(struct dlm_rcom *rc);
+void dlm_rcom_in(struct dlm_rcom *rc);
+
+#endif
+

fs/gfs2/Kconfig

@@ -0,0 +1,44 @@
+config GFS2_FS
+	tristate "GFS2 file system support"
+	depends on EXPERIMENTAL
+	select FS_POSIX_ACL
+	help
+	A cluster filesystem.
+
+	Allows a cluster of computers to simultaneously use a block device
+	that is shared between them (with FC, iSCSI, NBD, etc...).  GFS reads
+	and writes to the block device like a local filesystem, but also uses
+	a lock module to allow the computers coordinate their I/O so
+	filesystem consistency is maintained.  One of the nifty features of
+	GFS is perfect consistency -- changes made to the filesystem on one
+	machine show up immediately on all other machines in the cluster.
+
+	To use the GFS2 filesystem, you will need to enable one or more of
+	the below locking modules. Documentation and utilities for GFS2 can
+	be found here: http://sources.redhat.com/cluster
+
+config GFS2_FS_LOCKING_NOLOCK
+	tristate "GFS2 \"nolock\" locking module"
+	depends on GFS2_FS
+	help
+	Single node locking module for GFS2.
+
+	Use this module if you want to use GFS2 on a single node without
+	its clustering features. You can still take advantage of the
+	large file support, and upgrade to running a full cluster later on
+	if required.
+
+	If you will only be using GFS2 in cluster mode, you do not need this
+	module.
+
+config GFS2_FS_LOCKING_DLM
+	tristate "GFS2 DLM locking module"
+	depends on GFS2_FS
+	select DLM
+	help
+	Multiple node locking module for GFS2
+
+	Most users of GFS2 will require this module. It provides the locking
+	interface between GFS2 and the DLM, which is required to use GFS2
+	in a cluster environment.
+

fs/gfs2/Makefile

@@ -0,0 +1,10 @@
+obj-$(CONFIG_GFS2_FS) += gfs2.o
+gfs2-y := acl.o bmap.o daemon.o dir.o eaops.o eattr.o glock.o \
+	glops.o inode.o lm.o log.o lops.o locking.o main.o meta_io.o \
+	mount.o ondisk.o ops_address.o ops_dentry.o ops_export.o ops_file.o \
+	ops_fstype.o ops_inode.o ops_super.o ops_vm.o quota.o \
+	recovery.o rgrp.o super.o sys.o trans.o util.o
+
+obj-$(CONFIG_GFS2_FS_LOCKING_NOLOCK) += locking/nolock/
+obj-$(CONFIG_GFS2_FS_LOCKING_DLM) += locking/dlm/
+

fs/gfs2/acl.c

@@ -0,0 +1,309 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "acl.h"
+#include "eaops.h"
+#include "eattr.h"
+#include "glock.h"
+#include "inode.h"
+#include "meta_io.h"
+#include "trans.h"
+#include "util.h"
+
+#define ACL_ACCESS 1
+#define ACL_DEFAULT 0
+
+int gfs2_acl_validate_set(struct gfs2_inode *ip, int access,
+		      struct gfs2_ea_request *er,
+		      int *remove, mode_t *mode)
+{
+	struct posix_acl *acl;
+	int error;
+
+	error = gfs2_acl_validate_remove(ip, access);
+	if (error)
+		return error;
+
+	if (!er->er_data)
+		return -EINVAL;
+
+	acl = posix_acl_from_xattr(er->er_data, er->er_data_len);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (!acl) {
+		*remove = 1;
+		return 0;
+	}
+
+	error = posix_acl_valid(acl);
+	if (error)
+		goto out;
+
+	if (access) {
+		error = posix_acl_equiv_mode(acl, mode);
+		if (!error)
+			*remove = 1;
+		else if (error > 0)
+			error = 0;
+	}
+
+out:
+	posix_acl_release(acl);
+	return error;
+}
+
+int gfs2_acl_validate_remove(struct gfs2_inode *ip, int access)
+{
+	if (!GFS2_SB(&ip->i_inode)->sd_args.ar_posix_acl)
+		return -EOPNOTSUPP;
+	if (current->fsuid != ip->i_di.di_uid && !capable(CAP_FOWNER))
+		return -EPERM;
+	if (S_ISLNK(ip->i_di.di_mode))
+		return -EOPNOTSUPP;
+	if (!access && !S_ISDIR(ip->i_di.di_mode))
+		return -EACCES;
+
+	return 0;
+}
+
+static int acl_get(struct gfs2_inode *ip, int access, struct posix_acl **acl,
+		   struct gfs2_ea_location *el, char **data, unsigned int *len)
+{
+	struct gfs2_ea_request er;
+	struct gfs2_ea_location el_this;
+	int error;
+
+	if (!ip->i_di.di_eattr)
+		return 0;
+
+	memset(&er, 0, sizeof(struct gfs2_ea_request));
+	if (access) {
+		er.er_name = GFS2_POSIX_ACL_ACCESS;
+		er.er_name_len = GFS2_POSIX_ACL_ACCESS_LEN;
+	} else {
+		er.er_name = GFS2_POSIX_ACL_DEFAULT;
+		er.er_name_len = GFS2_POSIX_ACL_DEFAULT_LEN;
+	}
+	er.er_type = GFS2_EATYPE_SYS;
+
+	if (!el)
+		el = &el_this;
+
+	error = gfs2_ea_find(ip, &er, el);
+	if (error)
+		return error;
+	if (!el->el_ea)
+		return 0;
+	if (!GFS2_EA_DATA_LEN(el->el_ea))
+		goto out;
+
+	er.er_data_len = GFS2_EA_DATA_LEN(el->el_ea);
+	er.er_data = kmalloc(er.er_data_len, GFP_KERNEL);
+	error = -ENOMEM;
+	if (!er.er_data)
+		goto out;
+
+	error = gfs2_ea_get_copy(ip, el, er.er_data);
+	if (error)
+		goto out_kfree;
+
+	if (acl) {
+		*acl = posix_acl_from_xattr(er.er_data, er.er_data_len);
+		if (IS_ERR(*acl))
+			error = PTR_ERR(*acl);
+	}
+
+out_kfree:
+	if (error || !data)
+		kfree(er.er_data);
+	else {
+		*data = er.er_data;
+		*len = er.er_data_len;
+	}
+out:
+	if (error || el == &el_this)
+		brelse(el->el_bh);
+	return error;
+}
+
+/**
+ * gfs2_check_acl_locked - Check an ACL to see if we're allowed to do something
+ * @inode: the file we want to do something to
+ * @mask: what we want to do
+ *
+ * Returns: errno
+ */
+
+int gfs2_check_acl_locked(struct inode *inode, int mask)
+{
+	struct posix_acl *acl = NULL;
+	int error;
+
+	error = acl_get(GFS2_I(inode), ACL_ACCESS, &acl, NULL, NULL, NULL);
+	if (error)
+		return error;
+
+	if (acl) {
+		error = posix_acl_permission(inode, acl, mask);
+		posix_acl_release(acl);
+		return error;
+	}
+
+	return -EAGAIN;
+}
+
+int gfs2_check_acl(struct inode *inode, int mask)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder i_gh;
+	int error;
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+	if (!error) {
+		error = gfs2_check_acl_locked(inode, mask);
+		gfs2_glock_dq_uninit(&i_gh);
+	}
+
+	return error;
+}
+
+static int munge_mode(struct gfs2_inode *ip, mode_t mode)
+{
+	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;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (!error) {
+		gfs2_assert_withdraw(sdp,
+				(ip->i_di.di_mode & S_IFMT) == (mode & S_IFMT));
+		ip->i_di.di_mode = mode;
+		gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+		gfs2_dinode_out(&ip->i_di, dibh->b_data);
+		brelse(dibh);
+	}
+
+	gfs2_trans_end(sdp);
+
+	return 0;
+}
+
+int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
+	struct posix_acl *acl = NULL, *clone;
+	struct gfs2_ea_request er;
+	mode_t mode = ip->i_di.di_mode;
+	int error;
+
+	if (!sdp->sd_args.ar_posix_acl)
+		return 0;
+	if (S_ISLNK(ip->i_di.di_mode))
+		return 0;
+
+	memset(&er, 0, sizeof(struct gfs2_ea_request));
+	er.er_type = GFS2_EATYPE_SYS;
+
+	error = acl_get(dip, ACL_DEFAULT, &acl, NULL,
+			&er.er_data, &er.er_data_len);
+	if (error)
+		return error;
+	if (!acl) {
+		mode &= ~current->fs->umask;
+		if (mode != ip->i_di.di_mode)
+			error = munge_mode(ip, mode);
+		return error;
+	}
+
+	clone = posix_acl_clone(acl, GFP_KERNEL);
+	error = -ENOMEM;
+	if (!clone)
+		goto out;
+	posix_acl_release(acl);
+	acl = clone;
+
+	if (S_ISDIR(ip->i_di.di_mode)) {
+		er.er_name = GFS2_POSIX_ACL_DEFAULT;
+		er.er_name_len = GFS2_POSIX_ACL_DEFAULT_LEN;
+		error = gfs2_system_eaops.eo_set(ip, &er);
+		if (error)
+			goto out;
+	}
+
+	error = posix_acl_create_masq(acl, &mode);
+	if (error < 0)
+		goto out;
+	if (error > 0) {
+		er.er_name = GFS2_POSIX_ACL_ACCESS;
+		er.er_name_len = GFS2_POSIX_ACL_ACCESS_LEN;
+		posix_acl_to_xattr(acl, er.er_data, er.er_data_len);
+		er.er_mode = mode;
+		er.er_flags = GFS2_ERF_MODE;
+		error = gfs2_system_eaops.eo_set(ip, &er);
+		if (error)
+			goto out;
+	} else
+		munge_mode(ip, mode);
+
+out:
+	posix_acl_release(acl);
+	kfree(er.er_data);
+	return error;
+}
+
+int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr)
+{
+	struct posix_acl *acl = NULL, *clone;
+	struct gfs2_ea_location el;
+	char *data;
+	unsigned int len;
+	int error;
+
+	error = acl_get(ip, ACL_ACCESS, &acl, &el, &data, &len);
+	if (error)
+		return error;
+	if (!acl)
+		return gfs2_setattr_simple(ip, attr);
+
+	clone = posix_acl_clone(acl, GFP_KERNEL);
+	error = -ENOMEM;
+	if (!clone)
+		goto out;
+	posix_acl_release(acl);
+	acl = clone;
+
+	error = posix_acl_chmod_masq(acl, attr->ia_mode);
+	if (!error) {
+		posix_acl_to_xattr(acl, data, len);
+		error = gfs2_ea_acl_chmod(ip, &el, attr, data);
+	}
+
+out:
+	posix_acl_release(acl);
+	brelse(el.el_bh);
+	kfree(data);
+	return error;
+}
+

fs/gfs2/acl.h

@@ -0,0 +1,39 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __ACL_DOT_H__
+#define __ACL_DOT_H__
+
+#include "incore.h"
+
+#define GFS2_POSIX_ACL_ACCESS		"posix_acl_access"
+#define GFS2_POSIX_ACL_ACCESS_LEN	16
+#define GFS2_POSIX_ACL_DEFAULT		"posix_acl_default"
+#define GFS2_POSIX_ACL_DEFAULT_LEN	17
+
+#define GFS2_ACL_IS_ACCESS(name, len) \
+         ((len) == GFS2_POSIX_ACL_ACCESS_LEN && \
+         !memcmp(GFS2_POSIX_ACL_ACCESS, (name), (len)))
+
+#define GFS2_ACL_IS_DEFAULT(name, len) \
+         ((len) == GFS2_POSIX_ACL_DEFAULT_LEN && \
+         !memcmp(GFS2_POSIX_ACL_DEFAULT, (name), (len)))
+
+struct gfs2_ea_request;
+
+int gfs2_acl_validate_set(struct gfs2_inode *ip, int access,
+			  struct gfs2_ea_request *er,
+			  int *remove, mode_t *mode);
+int gfs2_acl_validate_remove(struct gfs2_inode *ip, int access);
+int gfs2_check_acl_locked(struct inode *inode, int mask);
+int gfs2_check_acl(struct inode *inode, int mask);
+int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip);
+int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr);
+
+#endif /* __ACL_DOT_H__ */

fs/gfs2/bmap.h

@@ -0,0 +1,31 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __BMAP_DOT_H__
+#define __BMAP_DOT_H__
+
+struct inode;
+struct gfs2_inode;
+struct page;
+
+int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page);
+int gfs2_block_map(struct inode *inode, u64 lblock, int create, struct buffer_head *bh, unsigned int maxlen);
+int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsigned *extlen);
+
+int gfs2_truncatei(struct gfs2_inode *ip, u64 size);
+int gfs2_truncatei_resume(struct gfs2_inode *ip);
+int gfs2_file_dealloc(struct gfs2_inode *ip);
+
+void gfs2_write_calc_reserv(struct gfs2_inode *ip, unsigned int len,
+			    unsigned int *data_blocks,
+			    unsigned int *ind_blocks);
+int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
+			      unsigned int len, int *alloc_required);
+
+#endif /* __BMAP_DOT_H__ */

fs/gfs2/daemon.c

@@ -0,0 +1,196 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/kthread.h>
+#include <linux/delay.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "daemon.h"
+#include "glock.h"
+#include "log.h"
+#include "quota.h"
+#include "recovery.h"
+#include "super.h"
+#include "util.h"
+
+/* This uses schedule_timeout() instead of msleep() because it's good for
+   the daemons to wake up more often than the timeout when unmounting so
+   the user's unmount doesn't sit there forever.
+
+   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;
+		schedule_timeout_interruptible(t);
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_glockd - Reclaim unused glock structures
+ * @sdp: Pointer to GFS2 superblock
+ *
+ * One or more of these daemons run, reclaiming glocks on sd_reclaim_list.
+ * Number of daemons can be set by user, with num_glockd mount option.
+ */
+
+int gfs2_glockd(void *data)
+{
+	struct gfs2_sbd *sdp = data;
+
+	while (!kthread_should_stop()) {
+		while (atomic_read(&sdp->sd_reclaim_count))
+			gfs2_reclaim_glock(sdp);
+
+		wait_event_interruptible(sdp->sd_reclaim_wq,
+					 (atomic_read(&sdp->sd_reclaim_count) ||
+					 kthread_should_stop()));
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_recoverd - Recover dead machine's journals
+ * @sdp: Pointer to GFS2 superblock
+ *
+ */
+
+int gfs2_recoverd(void *data)
+{
+	struct gfs2_sbd *sdp = data;
+	unsigned long t;
+
+	while (!kthread_should_stop()) {
+		gfs2_check_journals(sdp);
+		t = gfs2_tune_get(sdp,  gt_recoverd_secs) * HZ;
+		schedule_timeout_interruptible(t);
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_logd - Update log tail as Active Items get flushed to in-place blocks
+ * @sdp: Pointer to GFS2 superblock
+ *
+ * Also, periodically check to make sure that we're using the most recent
+ * journal index.
+ */
+
+int gfs2_logd(void *data)
+{
+	struct gfs2_sbd *sdp = data;
+	struct gfs2_holder ji_gh;
+	unsigned long t;
+
+	while (!kthread_should_stop()) {
+		/* Advance the log tail */
+
+		t = sdp->sd_log_flush_time +
+		    gfs2_tune_get(sdp, gt_log_flush_secs) * HZ;
+
+		gfs2_ail1_empty(sdp, DIO_ALL);
+
+		if (time_after_eq(jiffies, t)) {
+			gfs2_log_flush(sdp, NULL);
+			sdp->sd_log_flush_time = jiffies;
+		}
+
+		/* Check for latest journal index */
+
+		t = sdp->sd_jindex_refresh_time +
+		    gfs2_tune_get(sdp, gt_jindex_refresh_secs) * HZ;
+
+		if (time_after_eq(jiffies, t)) {
+			if (!gfs2_jindex_hold(sdp, &ji_gh))
+				gfs2_glock_dq_uninit(&ji_gh);
+			sdp->sd_jindex_refresh_time = jiffies;
+		}
+
+		t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
+		schedule_timeout_interruptible(t);
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_quotad - Write cached quota changes into the quota file
+ * @sdp: Pointer to GFS2 superblock
+ *
+ */
+
+int gfs2_quotad(void *data)
+{
+	struct gfs2_sbd *sdp = data;
+	unsigned long t;
+	int error;
+
+	while (!kthread_should_stop()) {
+		/* Update the master statfs file */
+
+		t = sdp->sd_statfs_sync_time +
+		    gfs2_tune_get(sdp, gt_statfs_quantum) * HZ;
+
+		if (time_after_eq(jiffies, t)) {
+			error = gfs2_statfs_sync(sdp);
+			if (error &&
+			    error != -EROFS &&
+			    !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+				fs_err(sdp, "quotad: (1) error=%d\n", error);
+			sdp->sd_statfs_sync_time = jiffies;
+		}
+
+		/* Update quota file */
+
+		t = sdp->sd_quota_sync_time +
+		    gfs2_tune_get(sdp, gt_quota_quantum) * HZ;
+
+		if (time_after_eq(jiffies, t)) {
+			error = gfs2_quota_sync(sdp);
+			if (error &&
+			    error != -EROFS &&
+			    !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+				fs_err(sdp, "quotad: (2) error=%d\n", error);
+			sdp->sd_quota_sync_time = jiffies;
+		}
+
+		gfs2_quota_scan(sdp);
+
+		t = gfs2_tune_get(sdp, gt_quotad_secs) * HZ;
+		schedule_timeout_interruptible(t);
+	}
+
+	return 0;
+}
+

fs/gfs2/daemon.h

@@ -0,0 +1,19 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#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);
+int gfs2_quotad(void *data);
+
+#endif /* __DAEMON_DOT_H__ */

fs/gfs2/dir.h

@@ -0,0 +1,79 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __DIR_DOT_H__
+#define __DIR_DOT_H__
+
+#include <linux/dcache.h>
+
+struct inode;
+struct gfs2_inode;
+struct gfs2_inum;
+
+/**
+ * gfs2_filldir_t - Report a directory entry to the caller of gfs2_dir_read()
+ * @opaque: opaque data used by the function
+ * @name: the name of the directory entry
+ * @length: the length of the name
+ * @offset: the entry's offset in the directory
+ * @inum: the inode number the entry points to
+ * @type: the type of inode the entry points to
+ *
+ * Returns: 0 on success, 1 if buffer full
+ */
+
+typedef int (*gfs2_filldir_t) (void *opaque,
+			      const char *name, unsigned int length,
+			      u64 offset,
+			      struct gfs2_inum *inum, unsigned int type);
+
+int gfs2_dir_search(struct inode *dir, const struct qstr *filename,
+		    struct gfs2_inum *inum, unsigned int *type);
+int gfs2_dir_add(struct inode *inode, const struct qstr *filename,
+		 const struct gfs2_inum *inum, unsigned int type);
+int gfs2_dir_del(struct gfs2_inode *dip, const struct qstr *filename);
+int gfs2_dir_read(struct inode *inode, u64 * offset, void *opaque,
+		  gfs2_filldir_t filldir);
+int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename,
+		   struct gfs2_inum *new_inum, unsigned int new_type);
+
+int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip);
+
+int gfs2_diradd_alloc_required(struct inode *dir,
+			       const struct qstr *filename);
+int gfs2_dir_get_new_buffer(struct gfs2_inode *ip, u64 block,
+			    struct buffer_head **bhp);
+
+static inline u32 gfs2_disk_hash(const char *data, int len)
+{
+        return crc32_le((u32)~0, data, len) ^ (u32)~0;
+}
+
+
+static inline void gfs2_str2qstr(struct qstr *name, const char *fname)
+{
+	name->name = fname;
+	name->len = strlen(fname);
+	name->hash = gfs2_disk_hash(name->name, name->len);
+}
+
+/* N.B. This probably ought to take inum & type as args as well */
+static inline void gfs2_qstr2dirent(const struct qstr *name, u16 reclen, struct gfs2_dirent *dent)
+{
+	dent->de_inum.no_addr = cpu_to_be64(0);
+	dent->de_inum.no_formal_ino = cpu_to_be64(0);
+	dent->de_hash = cpu_to_be32(name->hash);
+	dent->de_rec_len = cpu_to_be16(reclen);
+	dent->de_name_len = cpu_to_be16(name->len);
+	dent->de_type = cpu_to_be16(0);
+	memset(dent->__pad, 0, sizeof(dent->__pad));
+	memcpy(dent + 1, name->name, name->len);
+}
+
+#endif /* __DIR_DOT_H__ */

fs/gfs2/eaops.c

@@ -0,0 +1,230 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/xattr.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+#include <asm/uaccess.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "acl.h"
+#include "eaops.h"
+#include "eattr.h"
+#include "util.h"
+
+/**
+ * gfs2_ea_name2type - get the type of the ea, and truncate type from the name
+ * @namep: ea name, possibly with type appended
+ *
+ * Returns: GFS2_EATYPE_XXX
+ */
+
+unsigned int gfs2_ea_name2type(const char *name, const char **truncated_name)
+{
+	unsigned int type;
+
+	if (strncmp(name, "system.", 7) == 0) {
+		type = GFS2_EATYPE_SYS;
+		if (truncated_name)
+			*truncated_name = name + sizeof("system.") - 1;
+	} else if (strncmp(name, "user.", 5) == 0) {
+		type = GFS2_EATYPE_USR;
+		if (truncated_name)
+			*truncated_name = name + sizeof("user.") - 1;
+	} else if (strncmp(name, "security.", 9) == 0) {
+		type = GFS2_EATYPE_SECURITY;
+		if (truncated_name)
+			*truncated_name = name + sizeof("security.") - 1;
+	} else {
+		type = GFS2_EATYPE_UNUSED;
+		if (truncated_name)
+			*truncated_name = NULL;
+	}
+
+	return type;
+}
+
+static int user_eo_get(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	struct inode *inode = &ip->i_inode;
+	int error = permission(inode, MAY_READ, NULL);
+	if (error)
+		return error;
+
+	return gfs2_ea_get_i(ip, er);
+}
+
+static int user_eo_set(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	struct inode *inode = &ip->i_inode;
+
+	if (S_ISREG(inode->i_mode) ||
+	    (S_ISDIR(inode->i_mode) && !(inode->i_mode & S_ISVTX))) {
+		int error = permission(inode, MAY_WRITE, NULL);
+		if (error)
+			return error;
+	} else
+		return -EPERM;
+
+	return gfs2_ea_set_i(ip, er);
+}
+
+static int user_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	struct inode *inode = &ip->i_inode;
+
+	if (S_ISREG(inode->i_mode) ||
+	    (S_ISDIR(inode->i_mode) && !(inode->i_mode & S_ISVTX))) {
+		int error = permission(inode, MAY_WRITE, NULL);
+		if (error)
+			return error;
+	} else
+		return -EPERM;
+
+	return gfs2_ea_remove_i(ip, er);
+}
+
+static int system_eo_get(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	if (!GFS2_ACL_IS_ACCESS(er->er_name, er->er_name_len) &&
+	    !GFS2_ACL_IS_DEFAULT(er->er_name, er->er_name_len) &&
+	    !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (GFS2_SB(&ip->i_inode)->sd_args.ar_posix_acl == 0 &&
+	    (GFS2_ACL_IS_ACCESS(er->er_name, er->er_name_len) ||
+	     GFS2_ACL_IS_DEFAULT(er->er_name, er->er_name_len)))
+		return -EOPNOTSUPP;
+
+
+
+	return gfs2_ea_get_i(ip, er);
+}
+
+static int system_eo_set(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	int remove = 0;
+	int error;
+
+	if (GFS2_ACL_IS_ACCESS(er->er_name, er->er_name_len)) {
+		if (!(er->er_flags & GFS2_ERF_MODE)) {
+			er->er_mode = ip->i_di.di_mode;
+			er->er_flags |= GFS2_ERF_MODE;
+		}
+		error = gfs2_acl_validate_set(ip, 1, er,
+					      &remove, &er->er_mode);
+		if (error)
+			return error;
+		error = gfs2_ea_set_i(ip, er);
+		if (error)
+			return error;
+		if (remove)
+			gfs2_ea_remove_i(ip, er);
+		return 0;
+
+	} else if (GFS2_ACL_IS_DEFAULT(er->er_name, er->er_name_len)) {
+		error = gfs2_acl_validate_set(ip, 0, er,
+					      &remove, NULL);
+		if (error)
+			return error;
+		if (!remove)
+			error = gfs2_ea_set_i(ip, er);
+		else {
+			error = gfs2_ea_remove_i(ip, er);
+			if (error == -ENODATA)
+				error = 0;
+		}
+		return error;
+	}
+
+	return -EPERM;
+}
+
+static int system_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	if (GFS2_ACL_IS_ACCESS(er->er_name, er->er_name_len)) {
+		int error = gfs2_acl_validate_remove(ip, 1);
+		if (error)
+			return error;
+
+	} else if (GFS2_ACL_IS_DEFAULT(er->er_name, er->er_name_len)) {
+		int error = gfs2_acl_validate_remove(ip, 0);
+		if (error)
+			return error;
+
+	} else
+		return -EPERM;
+
+	return gfs2_ea_remove_i(ip, er);
+}
+
+static int security_eo_get(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	struct inode *inode = &ip->i_inode;
+	int error = permission(inode, MAY_READ, NULL);
+	if (error)
+		return error;
+
+	return gfs2_ea_get_i(ip, er);
+}
+
+static int security_eo_set(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	struct inode *inode = &ip->i_inode;
+	int error = permission(inode, MAY_WRITE, NULL);
+	if (error)
+		return error;
+
+	return gfs2_ea_set_i(ip, er);
+}
+
+static int security_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+{
+	struct inode *inode = &ip->i_inode;
+	int error = permission(inode, MAY_WRITE, NULL);
+	if (error)
+		return error;
+
+	return gfs2_ea_remove_i(ip, er);
+}
+
+static 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 = {
+	.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 = {
+	.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[] = {
+	NULL,
+	&gfs2_user_eaops,
+	&gfs2_system_eaops,
+	&gfs2_security_eaops,
+};
+

fs/gfs2/eaops.h

@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __EAOPS_DOT_H__
+#define __EAOPS_DOT_H__
+
+struct gfs2_ea_request;
+struct gfs2_inode;
+
+struct gfs2_eattr_operations {
+	int (*eo_get) (struct gfs2_inode *ip, struct gfs2_ea_request *er);
+	int (*eo_set) (struct gfs2_inode *ip, struct gfs2_ea_request *er);
+	int (*eo_remove) (struct gfs2_inode *ip, struct gfs2_ea_request *er);
+	char *eo_name;
+};
+
+unsigned int gfs2_ea_name2type(const char *name, const char **truncated_name);
+
+extern struct gfs2_eattr_operations gfs2_system_eaops;
+
+extern struct gfs2_eattr_operations *gfs2_ea_ops[];
+
+#endif /* __EAOPS_DOT_H__ */
+

fs/gfs2/eattr.h

@@ -0,0 +1,100 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __EATTR_DOT_H__
+#define __EATTR_DOT_H__
+
+struct gfs2_inode;
+struct iattr;
+
+#define GFS2_EA_REC_LEN(ea) be32_to_cpu((ea)->ea_rec_len)
+#define GFS2_EA_DATA_LEN(ea) be32_to_cpu((ea)->ea_data_len)
+
+#define GFS2_EA_SIZE(ea) \
+ALIGN(sizeof(struct gfs2_ea_header) + (ea)->ea_name_len + \
+      ((GFS2_EA_IS_STUFFED(ea)) ? GFS2_EA_DATA_LEN(ea) : \
+                                  (sizeof(u64) * (ea)->ea_num_ptrs)), 8)
+
+#define GFS2_EA_IS_STUFFED(ea) (!(ea)->ea_num_ptrs)
+#define GFS2_EA_IS_LAST(ea) ((ea)->ea_flags & GFS2_EAFLAG_LAST)
+
+#define GFS2_EAREQ_SIZE_STUFFED(er) \
+ALIGN(sizeof(struct gfs2_ea_header) + (er)->er_name_len + (er)->er_data_len, 8)
+
+#define GFS2_EAREQ_SIZE_UNSTUFFED(sdp, er) \
+ALIGN(sizeof(struct gfs2_ea_header) + (er)->er_name_len + \
+      sizeof(u64) * DIV_ROUND_UP((er)->er_data_len, (sdp)->sd_jbsize), 8)
+
+#define GFS2_EA2NAME(ea) ((char *)((struct gfs2_ea_header *)(ea) + 1))
+#define GFS2_EA2DATA(ea) (GFS2_EA2NAME(ea) + (ea)->ea_name_len)
+
+#define GFS2_EA2DATAPTRS(ea) \
+((u64 *)(GFS2_EA2NAME(ea) + ALIGN((ea)->ea_name_len, 8)))
+
+#define GFS2_EA2NEXT(ea) \
+((struct gfs2_ea_header *)((char *)(ea) + GFS2_EA_REC_LEN(ea)))
+
+#define GFS2_EA_BH2FIRST(bh) \
+((struct gfs2_ea_header *)((bh)->b_data + sizeof(struct gfs2_meta_header)))
+
+#define GFS2_ERF_MODE 0x80000000
+
+struct gfs2_ea_request {
+	const char *er_name;
+	char *er_data;
+	unsigned int er_name_len;
+	unsigned int er_data_len;
+	unsigned int er_type; /* GFS2_EATYPE_... */
+	int er_flags;
+	mode_t er_mode;
+};
+
+struct gfs2_ea_location {
+	struct buffer_head *el_bh;
+	struct gfs2_ea_header *el_ea;
+	struct gfs2_ea_header *el_prev;
+};
+
+int gfs2_ea_get_i(struct gfs2_inode *ip, struct gfs2_ea_request *er);
+int gfs2_ea_set_i(struct gfs2_inode *ip, struct gfs2_ea_request *er);
+int gfs2_ea_remove_i(struct gfs2_inode *ip, struct gfs2_ea_request *er);
+
+int gfs2_ea_list(struct gfs2_inode *ip, struct gfs2_ea_request *er);
+int gfs2_ea_get(struct gfs2_inode *ip, struct gfs2_ea_request *er);
+int gfs2_ea_set(struct gfs2_inode *ip, struct gfs2_ea_request *er);
+int gfs2_ea_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er);
+
+int gfs2_ea_dealloc(struct gfs2_inode *ip);
+
+/* Exported to acl.c */
+
+int gfs2_ea_find(struct gfs2_inode *ip,
+		 struct gfs2_ea_request *er,
+		 struct gfs2_ea_location *el);
+int gfs2_ea_get_copy(struct gfs2_inode *ip,
+		     struct gfs2_ea_location *el,
+		     char *data);
+int gfs2_ea_acl_chmod(struct gfs2_inode *ip, struct gfs2_ea_location *el,
+		      struct iattr *attr, char *data);
+
+static inline unsigned int gfs2_ea_strlen(struct gfs2_ea_header *ea)
+{
+	switch (ea->ea_type) {
+	case GFS2_EATYPE_USR:
+		return 5 + ea->ea_name_len + 1;
+	case GFS2_EATYPE_SYS:
+		return 7 + ea->ea_name_len + 1;
+	case GFS2_EATYPE_SECURITY:
+		return 9 + ea->ea_name_len + 1;
+	default:
+		return 0;
+	}
+}
+
+#endif /* __EATTR_DOT_H__ */

fs/gfs2/gfs2.h

@@ -0,0 +1,31 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __GFS2_DOT_H__
+#define __GFS2_DOT_H__
+
+enum {
+	NO_CREATE = 0,
+	CREATE = 1,
+};
+
+enum {
+	NO_WAIT = 0,
+	WAIT = 1,
+};
+
+enum {
+	NO_FORCE = 0,
+	FORCE = 1,
+};
+
+#define GFS2_FAST_NAME_SIZE 8
+
+#endif /* __GFS2_DOT_H__ */
+

fs/gfs2/glock.h

@@ -0,0 +1,153 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __GLOCK_DOT_H__
+#define __GLOCK_DOT_H__
+
+#include "incore.h"
+
+/* Flags for lock requests; used in gfs2_holder gh_flag field.
+   From lm_interface.h:
+#define LM_FLAG_TRY		0x00000001
+#define LM_FLAG_TRY_1CB		0x00000002
+#define LM_FLAG_NOEXP		0x00000004
+#define LM_FLAG_ANY		0x00000008
+#define LM_FLAG_PRIORITY	0x00000010 */
+
+#define GL_LOCAL_EXCL		0x00000020
+#define GL_ASYNC		0x00000040
+#define GL_EXACT		0x00000080
+#define GL_SKIP			0x00000100
+#define GL_ATIME		0x00000200
+#define GL_NOCACHE		0x00000400
+#define GL_NOCANCEL		0x00001000
+#define GL_AOP			0x00004000
+#define GL_DUMP			0x00008000
+
+#define GLR_TRYFAILED		13
+#define GLR_CANCELED		14
+
+static inline int gfs2_glock_is_locked_by_me(struct gfs2_glock *gl)
+{
+	struct gfs2_holder *gh;
+	int locked = 0;
+
+	/* Look in glock's list of holders for one with current task as owner */
+	spin_lock(&gl->gl_spin);
+	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+		if (gh->gh_owner == current) {
+			locked = 1;
+			break;
+		}
+	}
+	spin_unlock(&gl->gl_spin);
+
+	return locked;
+}
+
+static inline int gfs2_glock_is_held_excl(struct gfs2_glock *gl)
+{
+	return gl->gl_state == LM_ST_EXCLUSIVE;
+}
+
+static inline int gfs2_glock_is_held_dfrd(struct gfs2_glock *gl)
+{
+	return gl->gl_state == LM_ST_DEFERRED;
+}
+
+static inline int gfs2_glock_is_held_shrd(struct gfs2_glock *gl)
+{
+	return gl->gl_state == LM_ST_SHARED;
+}
+
+static inline int gfs2_glock_is_blocking(struct gfs2_glock *gl)
+{
+	int ret;
+	spin_lock(&gl->gl_spin);
+	ret = !list_empty(&gl->gl_waiters2) || !list_empty(&gl->gl_waiters3);
+	spin_unlock(&gl->gl_spin);
+	return ret;
+}
+
+int gfs2_glock_get(struct gfs2_sbd *sdp,
+		   u64 number, const struct gfs2_glock_operations *glops,
+		   int create, struct gfs2_glock **glp);
+void gfs2_glock_hold(struct gfs2_glock *gl);
+int gfs2_glock_put(struct gfs2_glock *gl);
+void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
+		      struct gfs2_holder *gh);
+void gfs2_holder_reinit(unsigned int state, unsigned flags,
+			struct gfs2_holder *gh);
+void gfs2_holder_uninit(struct gfs2_holder *gh);
+
+void gfs2_glock_xmote_th(struct gfs2_glock *gl, unsigned int state, int flags);
+void gfs2_glock_drop_th(struct gfs2_glock *gl);
+
+int gfs2_glock_nq(struct gfs2_holder *gh);
+int gfs2_glock_poll(struct gfs2_holder *gh);
+int gfs2_glock_wait(struct gfs2_holder *gh);
+void gfs2_glock_dq(struct gfs2_holder *gh);
+
+int gfs2_glock_be_greedy(struct gfs2_glock *gl, unsigned int time);
+
+void gfs2_glock_dq_uninit(struct gfs2_holder *gh);
+int gfs2_glock_nq_num(struct gfs2_sbd *sdp,
+		      u64 number, const struct gfs2_glock_operations *glops,
+		      unsigned int state, int flags, struct gfs2_holder *gh);
+
+int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs);
+void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs);
+void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs);
+
+void gfs2_glock_prefetch_num(struct gfs2_sbd *sdp, u64 number,
+			     const struct gfs2_glock_operations *glops,
+			     unsigned int state, int flags);
+void gfs2_glock_inode_squish(struct inode *inode);
+
+/**
+ * gfs2_glock_nq_init - intialize a holder and enqueue it on a glock
+ * @gl: the glock
+ * @state: the state we're requesting
+ * @flags: the modifier flags
+ * @gh: the holder structure
+ *
+ * Returns: 0, GLR_*, or errno
+ */
+
+static inline int gfs2_glock_nq_init(struct gfs2_glock *gl,
+				     unsigned int state, int flags,
+				     struct gfs2_holder *gh)
+{
+	int error;
+
+	gfs2_holder_init(gl, state, flags, gh);
+
+	error = gfs2_glock_nq(gh);
+	if (error)
+		gfs2_holder_uninit(gh);
+
+	return error;
+}
+
+/*  Lock Value Block functions  */
+
+int gfs2_lvb_hold(struct gfs2_glock *gl);
+void gfs2_lvb_unhold(struct gfs2_glock *gl);
+
+void gfs2_glock_cb(void *cb_data, unsigned int type, void *data);
+
+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);
+
+#endif /* __GLOCK_DOT_H__ */

fs/gfs2/glops.c

@@ -0,0 +1,615 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "log.h"
+#include "meta_io.h"
+#include "recovery.h"
+#include "rgrp.h"
+#include "util.h"
+#include "trans.h"
+
+/**
+ * ail_empty_gl - remove all buffers for a given lock from the AIL
+ * @gl: the glock
+ *
+ * None of the buffers should be dirty, locked, or pinned.
+ */
+
+static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	unsigned int blocks;
+	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);
+	if (!blocks)
+		return;
+
+	error = gfs2_trans_begin(sdp, 0, blocks);
+	if (gfs2_assert_withdraw(sdp, !error))
+		return;
+
+	gfs2_log_lock(sdp);
+	while (!list_empty(head)) {
+		bd = list_entry(head->next, struct gfs2_bufdata,
+				bd_ail_gl_list);
+		bh = bd->bd_bh;
+		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_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
+	gfs2_log_unlock(sdp);
+
+	gfs2_trans_end(sdp);
+	gfs2_log_flush(sdp, NULL);
+}
+
+/**
+ * gfs2_pte_inval - Sync and invalidate all PTEs associated with a glock
+ * @gl: the glock
+ *
+ */
+
+static void gfs2_pte_inval(struct gfs2_glock *gl)
+{
+	struct gfs2_inode *ip;
+	struct inode *inode;
+
+	ip = gl->gl_object;
+	inode = &ip->i_inode;
+	if (!ip || !S_ISREG(ip->i_di.di_mode))
+		return;
+
+	if (!test_bit(GIF_PAGED, &ip->i_flags))
+		return;
+
+	unmap_shared_mapping_range(inode->i_mapping, 0, 0);
+
+	if (test_bit(GIF_SW_PAGED, &ip->i_flags))
+		set_bit(GLF_DIRTY, &gl->gl_flags);
+
+	clear_bit(GIF_SW_PAGED, &ip->i_flags);
+}
+
+/**
+ * gfs2_page_inval - Invalidate all pages associated with a glock
+ * @gl: the glock
+ *
+ */
+
+static void gfs2_page_inval(struct gfs2_glock *gl)
+{
+	struct gfs2_inode *ip;
+	struct inode *inode;
+
+	ip = gl->gl_object;
+	inode = &ip->i_inode;
+	if (!ip || !S_ISREG(ip->i_di.di_mode))
+		return;
+
+	truncate_inode_pages(inode->i_mapping, 0);
+	gfs2_assert_withdraw(GFS2_SB(&ip->i_inode), !inode->i_mapping->nrpages);
+	clear_bit(GIF_PAGED, &ip->i_flags);
+}
+
+/**
+ * gfs2_page_wait - Wait for writeback of data
+ * @gl: the glock
+ *
+ * Syncs data (not metadata) for a regular file.
+ * No-op for all other types.
+ */
+
+static void gfs2_page_wait(struct gfs2_glock *gl)
+{
+	struct gfs2_inode *ip = gl->gl_object;
+	struct inode *inode = &ip->i_inode;
+	struct address_space *mapping = inode->i_mapping;
+	int error;
+
+	if (!S_ISREG(ip->i_di.di_mode))
+		return;
+
+	error = filemap_fdatawait(mapping);
+
+	/* Put back any errors cleared by filemap_fdatawait()
+	   so they can be caught by someone who can pass them
+	   up to user space. */
+
+	if (error == -ENOSPC)
+		set_bit(AS_ENOSPC, &mapping->flags);
+	else if (error)
+		set_bit(AS_EIO, &mapping->flags);
+
+}
+
+static void gfs2_page_writeback(struct gfs2_glock *gl)
+{
+	struct gfs2_inode *ip = gl->gl_object;
+	struct inode *inode = &ip->i_inode;
+	struct address_space *mapping = inode->i_mapping;
+
+	if (!S_ISREG(ip->i_di.di_mode))
+		return;
+
+	filemap_fdatawrite(mapping);
+}
+
+/**
+ * meta_go_sync - sync out the metadata for this glock
+ * @gl: the glock
+ * @flags: DIO_*
+ *
+ * Called when demoting or unlocking an EX glock.  We must flush
+ * to disk all dirty buffers/pages relating to this glock, and must not
+ * not return to caller to demote/unlock the glock until I/O is complete.
+ */
+
+static void meta_go_sync(struct gfs2_glock *gl, int flags)
+{
+	if (!(flags & DIO_METADATA))
+		return;
+
+	if (test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) {
+		gfs2_log_flush(gl->gl_sbd, gl);
+		gfs2_meta_sync(gl);
+		if (flags & DIO_RELEASE)
+			gfs2_ail_empty_gl(gl);
+	}
+
+}
+
+/**
+ * meta_go_inval - invalidate the metadata for this glock
+ * @gl: the glock
+ * @flags:
+ *
+ */
+
+static void meta_go_inval(struct gfs2_glock *gl, int flags)
+{
+	if (!(flags & DIO_METADATA))
+		return;
+
+	gfs2_meta_inval(gl);
+	gl->gl_vn++;
+}
+
+/**
+ * inode_go_xmote_th - promote/demote a glock
+ * @gl: the glock
+ * @state: the requested state
+ * @flags:
+ *
+ */
+
+static void inode_go_xmote_th(struct gfs2_glock *gl, unsigned int state,
+			      int flags)
+{
+	if (gl->gl_state != LM_ST_UNLOCKED)
+		gfs2_pte_inval(gl);
+	gfs2_glock_xmote_th(gl, state, flags);
+}
+
+/**
+ * inode_go_xmote_bh - After promoting/demoting a glock
+ * @gl: the glock
+ *
+ */
+
+static void inode_go_xmote_bh(struct gfs2_glock *gl)
+{
+	struct gfs2_holder *gh = gl->gl_req_gh;
+	struct buffer_head *bh;
+	int error;
+
+	if (gl->gl_state != LM_ST_UNLOCKED &&
+	    (!gh || !(gh->gh_flags & GL_SKIP))) {
+		error = gfs2_meta_read(gl, gl->gl_name.ln_number, 0, &bh);
+		if (!error)
+			brelse(bh);
+	}
+}
+
+/**
+ * inode_go_drop_th - unlock a glock
+ * @gl: the glock
+ *
+ * Invoked from rq_demote().
+ * Another node needs the lock in EXCLUSIVE mode, or lock (unused for too long)
+ * is being purged from our node's glock cache; we're dropping lock.
+ */
+
+static void inode_go_drop_th(struct gfs2_glock *gl)
+{
+	gfs2_pte_inval(gl);
+	gfs2_glock_drop_th(gl);
+}
+
+/**
+ * inode_go_sync - Sync the dirty data and/or metadata for an inode glock
+ * @gl: the glock protecting the inode
+ * @flags:
+ *
+ */
+
+static void inode_go_sync(struct gfs2_glock *gl, int flags)
+{
+	int meta = (flags & DIO_METADATA);
+	int data = (flags & DIO_DATA);
+
+	if (test_bit(GLF_DIRTY, &gl->gl_flags)) {
+		if (meta && data) {
+			gfs2_page_writeback(gl);
+			gfs2_log_flush(gl->gl_sbd, gl);
+			gfs2_meta_sync(gl);
+			gfs2_page_wait(gl);
+			clear_bit(GLF_DIRTY, &gl->gl_flags);
+		} else if (meta) {
+			gfs2_log_flush(gl->gl_sbd, gl);
+			gfs2_meta_sync(gl);
+		} else if (data) {
+			gfs2_page_writeback(gl);
+			gfs2_page_wait(gl);
+		}
+		if (flags & DIO_RELEASE)
+			gfs2_ail_empty_gl(gl);
+	}
+}
+
+/**
+ * inode_go_inval - prepare a inode glock to be released
+ * @gl: the glock
+ * @flags:
+ *
+ */
+
+static void inode_go_inval(struct gfs2_glock *gl, int flags)
+{
+	int meta = (flags & DIO_METADATA);
+	int data = (flags & DIO_DATA);
+
+	if (meta) {
+		gfs2_meta_inval(gl);
+		gl->gl_vn++;
+	}
+	if (data)
+		gfs2_page_inval(gl);
+}
+
+/**
+ * inode_go_demote_ok - Check to see if it's ok to unlock an inode glock
+ * @gl: the glock
+ *
+ * Returns: 1 if it's ok
+ */
+
+static int inode_go_demote_ok(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	int demote = 0;
+
+	if (!gl->gl_object && !gl->gl_aspace->i_mapping->nrpages)
+		demote = 1;
+	else if (!sdp->sd_args.ar_localcaching &&
+		 time_after_eq(jiffies, gl->gl_stamp +
+			       gfs2_tune_get(sdp, gt_demote_secs) * HZ))
+		demote = 1;
+
+	return demote;
+}
+
+/**
+ * inode_go_lock - operation done after an inode lock is locked by a process
+ * @gl: the glock
+ * @flags:
+ *
+ * Returns: errno
+ */
+
+static int inode_go_lock(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+	struct gfs2_inode *ip = gl->gl_object;
+	int error = 0;
+
+	if (!ip)
+		return 0;
+
+	if (ip->i_vn != gl->gl_vn) {
+		error = gfs2_inode_refresh(ip);
+		if (error)
+			return error;
+		gfs2_inode_attr_in(ip);
+	}
+
+	if ((ip->i_di.di_flags & GFS2_DIF_TRUNC_IN_PROG) &&
+	    (gl->gl_state == LM_ST_EXCLUSIVE) &&
+	    (gh->gh_flags & GL_LOCAL_EXCL))
+		error = gfs2_truncatei_resume(ip);
+
+	return error;
+}
+
+/**
+ * inode_go_unlock - operation done before an inode lock is unlocked by a
+ *		     process
+ * @gl: the glock
+ * @flags:
+ *
+ */
+
+static void inode_go_unlock(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+	struct gfs2_inode *ip = gl->gl_object;
+
+	if (ip == NULL)
+		return;
+	if (test_bit(GLF_DIRTY, &gl->gl_flags))
+		gfs2_inode_attr_in(ip);
+	gfs2_meta_cache_flush(ip);
+}
+
+/**
+ * inode_greedy -
+ * @gl: the glock
+ *
+ */
+
+static void inode_greedy(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_inode *ip = gl->gl_object;
+	unsigned int quantum = gfs2_tune_get(sdp, gt_greedy_quantum);
+	unsigned int max = gfs2_tune_get(sdp, gt_greedy_max);
+	unsigned int new_time;
+
+	spin_lock(&ip->i_spin);
+
+	if (time_after(ip->i_last_pfault + quantum, jiffies)) {
+		new_time = ip->i_greedy + quantum;
+		if (new_time > max)
+			new_time = max;
+	} else {
+		new_time = ip->i_greedy - quantum;
+		if (!new_time || new_time > max)
+			new_time = 1;
+	}
+
+	ip->i_greedy = new_time;
+
+	spin_unlock(&ip->i_spin);
+
+	iput(&ip->i_inode);
+}
+
+/**
+ * rgrp_go_demote_ok - Check to see if it's ok to unlock a RG's glock
+ * @gl: the glock
+ *
+ * Returns: 1 if it's ok
+ */
+
+static int rgrp_go_demote_ok(struct gfs2_glock *gl)
+{
+	return !gl->gl_aspace->i_mapping->nrpages;
+}
+
+/**
+ * rgrp_go_lock - operation done after an rgrp lock is locked by
+ *    a first holder on this node.
+ * @gl: the glock
+ * @flags:
+ *
+ * Returns: errno
+ */
+
+static int rgrp_go_lock(struct gfs2_holder *gh)
+{
+	return gfs2_rgrp_bh_get(gh->gh_gl->gl_object);
+}
+
+/**
+ * rgrp_go_unlock - operation done before an rgrp lock is unlocked by
+ *    a last holder on this node.
+ * @gl: the glock
+ * @flags:
+ *
+ */
+
+static void rgrp_go_unlock(struct gfs2_holder *gh)
+{
+	gfs2_rgrp_bh_put(gh->gh_gl->gl_object);
+}
+
+/**
+ * trans_go_xmote_th - promote/demote the transaction glock
+ * @gl: the glock
+ * @state: the requested state
+ * @flags:
+ *
+ */
+
+static void trans_go_xmote_th(struct gfs2_glock *gl, unsigned int state,
+			      int flags)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+
+	if (gl->gl_state != LM_ST_UNLOCKED &&
+	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+		gfs2_meta_syncfs(sdp);
+		gfs2_log_shutdown(sdp);
+	}
+
+	gfs2_glock_xmote_th(gl, state, flags);
+}
+
+/**
+ * trans_go_xmote_bh - After promoting/demoting the transaction glock
+ * @gl: the glock
+ *
+ */
+
+static void trans_go_xmote_bh(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
+	struct gfs2_glock *j_gl = ip->i_gl;
+	struct gfs2_log_header head;
+	int error;
+
+	if (gl->gl_state != LM_ST_UNLOCKED &&
+	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+		gfs2_meta_cache_flush(GFS2_I(sdp->sd_jdesc->jd_inode));
+		j_gl->gl_ops->go_inval(j_gl, DIO_METADATA | DIO_DATA);
+
+		error = gfs2_find_jhead(sdp->sd_jdesc, &head);
+		if (error)
+			gfs2_consist(sdp);
+		if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT))
+			gfs2_consist(sdp);
+
+		/*  Initialize some head of the log stuff  */
+		if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
+			sdp->sd_log_sequence = head.lh_sequence + 1;
+			gfs2_log_pointers_init(sdp, head.lh_blkno);
+		}
+	}
+}
+
+/**
+ * trans_go_drop_th - unlock the transaction glock
+ * @gl: the glock
+ *
+ * We want to sync the device even with localcaching.  Remember
+ * that localcaching journal replay only marks buffers dirty.
+ */
+
+static void trans_go_drop_th(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+
+	if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+		gfs2_meta_syncfs(sdp);
+		gfs2_log_shutdown(sdp);
+	}
+
+	gfs2_glock_drop_th(gl);
+}
+
+/**
+ * quota_go_demote_ok - Check to see if it's ok to unlock a quota glock
+ * @gl: the glock
+ *
+ * Returns: 1 if it's ok
+ */
+
+static int quota_go_demote_ok(struct gfs2_glock *gl)
+{
+	return !atomic_read(&gl->gl_lvb_count);
+}
+
+const struct gfs2_glock_operations gfs2_meta_glops = {
+	.go_xmote_th = gfs2_glock_xmote_th,
+	.go_drop_th = gfs2_glock_drop_th,
+	.go_type = LM_TYPE_META,
+};
+
+const struct gfs2_glock_operations gfs2_inode_glops = {
+	.go_xmote_th = inode_go_xmote_th,
+	.go_xmote_bh = inode_go_xmote_bh,
+	.go_drop_th = inode_go_drop_th,
+	.go_sync = inode_go_sync,
+	.go_inval = inode_go_inval,
+	.go_demote_ok = inode_go_demote_ok,
+	.go_lock = inode_go_lock,
+	.go_unlock = inode_go_unlock,
+	.go_greedy = inode_greedy,
+	.go_type = LM_TYPE_INODE,
+};
+
+const struct gfs2_glock_operations gfs2_rgrp_glops = {
+	.go_xmote_th = gfs2_glock_xmote_th,
+	.go_drop_th = gfs2_glock_drop_th,
+	.go_sync = meta_go_sync,
+	.go_inval = meta_go_inval,
+	.go_demote_ok = rgrp_go_demote_ok,
+	.go_lock = rgrp_go_lock,
+	.go_unlock = rgrp_go_unlock,
+	.go_type = LM_TYPE_RGRP,
+};
+
+const struct gfs2_glock_operations gfs2_trans_glops = {
+	.go_xmote_th = trans_go_xmote_th,
+	.go_xmote_bh = trans_go_xmote_bh,
+	.go_drop_th = trans_go_drop_th,
+	.go_type = LM_TYPE_NONDISK,
+};
+
+const struct gfs2_glock_operations gfs2_iopen_glops = {
+	.go_xmote_th = gfs2_glock_xmote_th,
+	.go_drop_th = gfs2_glock_drop_th,
+	.go_type = LM_TYPE_IOPEN,
+};
+
+const struct gfs2_glock_operations gfs2_flock_glops = {
+	.go_xmote_th = gfs2_glock_xmote_th,
+	.go_drop_th = gfs2_glock_drop_th,
+	.go_type = LM_TYPE_FLOCK,
+};
+
+const struct gfs2_glock_operations gfs2_nondisk_glops = {
+	.go_xmote_th = gfs2_glock_xmote_th,
+	.go_drop_th = gfs2_glock_drop_th,
+	.go_type = LM_TYPE_NONDISK,
+};
+
+const struct gfs2_glock_operations gfs2_quota_glops = {
+	.go_xmote_th = gfs2_glock_xmote_th,
+	.go_drop_th = gfs2_glock_drop_th,
+	.go_demote_ok = quota_go_demote_ok,
+	.go_type = LM_TYPE_QUOTA,
+};
+
+const struct gfs2_glock_operations gfs2_journal_glops = {
+	.go_xmote_th = gfs2_glock_xmote_th,
+	.go_drop_th = gfs2_glock_drop_th,
+	.go_type = LM_TYPE_JOURNAL,
+};
+

fs/gfs2/glops.h

@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __GLOPS_DOT_H__
+#define __GLOPS_DOT_H__
+
+#include "incore.h"
+
+extern const struct gfs2_glock_operations gfs2_meta_glops;
+extern const struct gfs2_glock_operations gfs2_inode_glops;
+extern const struct gfs2_glock_operations gfs2_rgrp_glops;
+extern const struct gfs2_glock_operations gfs2_trans_glops;
+extern const struct gfs2_glock_operations gfs2_iopen_glops;
+extern const struct gfs2_glock_operations gfs2_flock_glops;
+extern const struct gfs2_glock_operations gfs2_nondisk_glops;
+extern const struct gfs2_glock_operations gfs2_quota_glops;
+extern const struct gfs2_glock_operations gfs2_journal_glops;
+
+#endif /* __GLOPS_DOT_H__ */

fs/gfs2/incore.h

@@ -0,0 +1,634 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __INCORE_DOT_H__
+#define __INCORE_DOT_H__
+
+#include <linux/fs.h>
+
+#define DIO_WAIT	0x00000010
+#define DIO_METADATA	0x00000020
+#define DIO_DATA	0x00000040
+#define DIO_RELEASE	0x00000080
+#define DIO_ALL		0x00000100
+
+struct gfs2_log_operations;
+struct gfs2_log_element;
+struct gfs2_holder;
+struct gfs2_glock;
+struct gfs2_quota_data;
+struct gfs2_trans;
+struct gfs2_ail;
+struct gfs2_jdesc;
+struct gfs2_sbd;
+
+typedef void (*gfs2_glop_bh_t) (struct gfs2_glock *gl, unsigned int ret);
+
+/*
+ * Structure of operations that are associated with each
+ * type of element in the log.
+ */
+
+struct gfs2_log_operations {
+	void (*lo_add) (struct gfs2_sbd *sdp, struct gfs2_log_element *le);
+	void (*lo_incore_commit) (struct gfs2_sbd *sdp, struct gfs2_trans *tr);
+	void (*lo_before_commit) (struct gfs2_sbd *sdp);
+	void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_ail *ai);
+	void (*lo_before_scan) (struct gfs2_jdesc *jd,
+				struct gfs2_log_header *head, int pass);
+	int (*lo_scan_elements) (struct gfs2_jdesc *jd, unsigned int start,
+				 struct gfs2_log_descriptor *ld, __be64 *ptr,
+				 int pass);
+	void (*lo_after_scan) (struct gfs2_jdesc *jd, int error, int pass);
+	const char *lo_name;
+};
+
+struct gfs2_log_element {
+	struct list_head le_list;
+	const struct gfs2_log_operations *le_ops;
+};
+
+struct gfs2_bitmap {
+	struct buffer_head *bi_bh;
+	char *bi_clone;
+	u32 bi_offset;
+	u32 bi_start;
+	u32 bi_len;
+};
+
+struct gfs2_rgrpd {
+	struct list_head rd_list;	/* Link with superblock */
+	struct list_head rd_list_mru;
+	struct list_head rd_recent;	/* Recently used rgrps */
+	struct gfs2_glock *rd_gl;	/* Glock for this rgrp */
+	struct gfs2_rindex rd_ri;
+	struct gfs2_rgrp rd_rg;
+	u64 rd_rg_vn;
+	struct gfs2_bitmap *rd_bits;
+	unsigned int rd_bh_count;
+	struct mutex rd_mutex;
+	u32 rd_free_clone;
+	struct gfs2_log_element rd_le;
+	u32 rd_last_alloc_data;
+	u32 rd_last_alloc_meta;
+	struct gfs2_sbd *rd_sbd;
+};
+
+enum gfs2_state_bits {
+	BH_Pinned = BH_PrivateStart,
+	BH_Escaped = BH_PrivateStart + 1,
+};
+
+BUFFER_FNS(Pinned, pinned)
+TAS_BUFFER_FNS(Pinned, pinned)
+BUFFER_FNS(Escaped, escaped)
+TAS_BUFFER_FNS(Escaped, escaped)
+
+struct gfs2_bufdata {
+	struct buffer_head *bd_bh;
+	struct gfs2_glock *bd_gl;
+
+	struct list_head bd_list_tr;
+	struct gfs2_log_element bd_le;
+
+	struct gfs2_ail *bd_ail;
+	struct list_head bd_ail_st_list;
+	struct list_head bd_ail_gl_list;
+};
+
+struct gfs2_glock_operations {
+	void (*go_xmote_th) (struct gfs2_glock * gl, unsigned int state,
+			     int flags);
+	void (*go_xmote_bh) (struct gfs2_glock * gl);
+	void (*go_drop_th) (struct gfs2_glock * gl);
+	void (*go_drop_bh) (struct gfs2_glock * gl);
+	void (*go_sync) (struct gfs2_glock * gl, int flags);
+	void (*go_inval) (struct gfs2_glock * gl, int flags);
+	int (*go_demote_ok) (struct gfs2_glock * gl);
+	int (*go_lock) (struct gfs2_holder * gh);
+	void (*go_unlock) (struct gfs2_holder * gh);
+	void (*go_callback) (struct gfs2_glock * gl, unsigned int state);
+	void (*go_greedy) (struct gfs2_glock * gl);
+	const int go_type;
+};
+
+enum {
+	/* Actions */
+	HIF_MUTEX		= 0,
+	HIF_PROMOTE		= 1,
+	HIF_DEMOTE		= 2,
+	HIF_GREEDY		= 3,
+
+	/* States */
+	HIF_ALLOCED		= 4,
+	HIF_DEALLOC		= 5,
+	HIF_HOLDER		= 6,
+	HIF_FIRST		= 7,
+	HIF_ABORTED		= 9,
+};
+
+struct gfs2_holder {
+	struct list_head gh_list;
+
+	struct gfs2_glock *gh_gl;
+	struct task_struct *gh_owner;
+	unsigned int gh_state;
+	unsigned gh_flags;
+
+	int gh_error;
+	unsigned long gh_iflags;
+	struct completion gh_wait;
+	unsigned long gh_ip;
+};
+
+enum {
+	GLF_LOCK		= 1,
+	GLF_STICKY		= 2,
+	GLF_PREFETCH		= 3,
+	GLF_DIRTY		= 5,
+	GLF_SKIP_WAITERS2	= 6,
+	GLF_GREEDY		= 7,
+};
+
+struct gfs2_glock {
+	struct hlist_node gl_list;
+	unsigned long gl_flags;		/* GLF_... */
+	struct lm_lockname gl_name;
+	atomic_t gl_ref;
+
+	spinlock_t gl_spin;
+
+	unsigned int gl_state;
+	unsigned int gl_hash;
+	struct task_struct *gl_owner;
+	unsigned long gl_ip;
+	struct list_head gl_holders;
+	struct list_head gl_waiters1;	/* HIF_MUTEX */
+	struct list_head gl_waiters2;	/* HIF_DEMOTE, HIF_GREEDY */
+	struct list_head gl_waiters3;	/* HIF_PROMOTE */
+
+	const struct gfs2_glock_operations *gl_ops;
+
+	struct gfs2_holder *gl_req_gh;
+	gfs2_glop_bh_t gl_req_bh;
+
+	void *gl_lock;
+	char *gl_lvb;
+	atomic_t gl_lvb_count;
+
+	u64 gl_vn;
+	unsigned long gl_stamp;
+	void *gl_object;
+
+	struct list_head gl_reclaim;
+
+	struct gfs2_sbd *gl_sbd;
+
+	struct inode *gl_aspace;
+	struct gfs2_log_element gl_le;
+	struct list_head gl_ail_list;
+	atomic_t gl_ail_count;
+};
+
+struct gfs2_alloc {
+	/* Quota stuff */
+
+	struct gfs2_quota_data *al_qd[2*MAXQUOTAS];
+	struct gfs2_holder al_qd_ghs[2*MAXQUOTAS];
+	unsigned int al_qd_num;
+
+	u32 al_requested; /* Filled in by caller of gfs2_inplace_reserve() */
+	u32 al_alloced; /* Filled in by gfs2_alloc_*() */
+
+	/* Filled in by gfs2_inplace_reserve() */
+
+	unsigned int al_line;
+	char *al_file;
+	struct gfs2_holder al_ri_gh;
+	struct gfs2_holder al_rgd_gh;
+	struct gfs2_rgrpd *al_rgd;
+
+};
+
+enum {
+	GIF_QD_LOCKED		= 1,
+	GIF_PAGED		= 2,
+	GIF_SW_PAGED		= 3,
+};
+
+struct gfs2_inode {
+	struct inode i_inode;
+	struct gfs2_inum i_num;
+
+	unsigned long i_flags;		/* GIF_... */
+
+	u64 i_vn;
+	struct gfs2_dinode i_di; /* To be replaced by ref to block */
+
+	struct gfs2_glock *i_gl; /* Move into i_gh? */
+	struct gfs2_holder i_iopen_gh;
+	struct gfs2_holder i_gh; /* for prepare/commit_write only */
+	struct gfs2_alloc i_alloc;
+	u64 i_last_rg_alloc;
+
+	spinlock_t i_spin;
+	struct rw_semaphore i_rw_mutex;
+	unsigned int i_greedy;
+	unsigned long i_last_pfault;
+
+	struct buffer_head *i_cache[GFS2_MAX_META_HEIGHT];
+};
+
+/*
+ * Since i_inode is the first element of struct gfs2_inode,
+ * this is effectively a cast.
+ */
+static inline struct gfs2_inode *GFS2_I(struct inode *inode)
+{
+	return container_of(inode, struct gfs2_inode, i_inode);
+}
+
+/* To be removed? */
+static inline struct gfs2_sbd *GFS2_SB(struct inode *inode)
+{
+	return inode->i_sb->s_fs_info;
+}
+
+enum {
+	GFF_DID_DIRECT_ALLOC	= 0,
+	GFF_EXLOCK = 1,
+};
+
+struct gfs2_file {
+	unsigned long f_flags;		/* GFF_... */
+	struct mutex f_fl_mutex;
+	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;
+	unsigned int rr_where;
+};
+
+enum {
+	QDF_USER		= 0,
+	QDF_CHANGE		= 1,
+	QDF_LOCKED		= 2,
+};
+
+struct gfs2_quota_lvb {
+        __be32 qb_magic;
+        u32 __pad;
+        __be64 qb_limit;      /* Hard limit of # blocks to alloc */
+        __be64 qb_warn;       /* Warn user when alloc is above this # */
+        __be64 qb_value;       /* Current # blocks allocated */
+};
+
+struct gfs2_quota_data {
+	struct list_head qd_list;
+	unsigned int qd_count;
+
+	u32 qd_id;
+	unsigned long qd_flags;		/* QDF_... */
+
+	s64 qd_change;
+	s64 qd_change_sync;
+
+	unsigned int qd_slot;
+	unsigned int qd_slot_count;
+
+	struct buffer_head *qd_bh;
+	struct gfs2_quota_change *qd_bh_qc;
+	unsigned int qd_bh_count;
+
+	struct gfs2_glock *qd_gl;
+	struct gfs2_quota_lvb qd_qb;
+
+	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 long tr_ip;
+
+	unsigned int tr_blocks;
+	unsigned int tr_revokes;
+	unsigned int tr_reserved;
+
+	struct gfs2_holder tr_t_gh;
+
+	int tr_touched;
+
+	unsigned int tr_num_buf;
+	unsigned int tr_num_buf_new;
+	unsigned int tr_num_buf_rm;
+	struct list_head tr_list_buf;
+
+	unsigned int tr_num_revoke;
+	unsigned int tr_num_revoke_rm;
+};
+
+struct gfs2_ail {
+	struct list_head ai_list;
+
+	unsigned int ai_first;
+	struct list_head ai_ail1_list;
+	struct list_head ai_ail2_list;
+
+	u64 ai_sync_gen;
+};
+
+struct gfs2_jdesc {
+	struct list_head jd_list;
+
+	struct inode *jd_inode;
+	unsigned int jd_jid;
+	int jd_dirty;
+
+	unsigned int jd_blocks;
+};
+
+#define GFS2_GLOCKD_DEFAULT	1
+#define GFS2_GLOCKD_MAX		16
+
+#define GFS2_QUOTA_DEFAULT	GFS2_QUOTA_OFF
+#define GFS2_QUOTA_OFF		0
+#define GFS2_QUOTA_ACCOUNT	1
+#define GFS2_QUOTA_ON		2
+
+#define GFS2_DATA_DEFAULT	GFS2_DATA_ORDERED
+#define GFS2_DATA_WRITEBACK	1
+#define GFS2_DATA_ORDERED	2
+
+struct gfs2_args {
+	char ar_lockproto[GFS2_LOCKNAME_LEN]; /* Name of the Lock Protocol */
+	char ar_locktable[GFS2_LOCKNAME_LEN]; /* Name of the Lock Table */
+	char ar_hostdata[GFS2_LOCKNAME_LEN]; /* Host specific data */
+	int ar_spectator; /* Don't get a journal because we're always RO */
+	int ar_ignore_local_fs; /* Don't optimize even if local_fs is 1 */
+	int ar_localflocks; /* Let the VFS do flock|fcntl locks for us */
+	int ar_localcaching; /* Local-style caching (dangerous on multihost) */
+	int ar_debug; /* Oops on errors instead of trying to be graceful */
+	int ar_upgrade; /* Upgrade ondisk/multihost format */
+	unsigned int ar_num_glockd; /* Number of glockd threads */
+	int ar_posix_acl; /* Enable posix acls */
+	int ar_quota; /* off/account/on */
+	int ar_suiddir; /* suiddir support */
+	int ar_data; /* ordered/writeback */
+};
+
+struct gfs2_tune {
+	spinlock_t gt_spin;
+
+	unsigned int gt_ilimit;
+	unsigned int gt_ilimit_tries;
+	unsigned int gt_ilimit_min;
+	unsigned int gt_demote_secs; /* Cache retention for unheld glock */
+	unsigned int gt_incore_log_blocks;
+	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;
+
+	unsigned int gt_quota_simul_sync; /* Max quotavals to sync at once */
+	unsigned int gt_quota_warn_period; /* Secs between quota warn msgs */
+	unsigned int gt_quota_scale_num; /* Numerator */
+	unsigned int gt_quota_scale_den; /* Denominator */
+	unsigned int gt_quota_cache_secs;
+	unsigned int gt_quota_quantum; /* Secs between syncs to quota file */
+	unsigned int gt_atime_quantum; /* Min secs between atime updates */
+	unsigned int gt_new_files_jdata;
+	unsigned int gt_new_files_directio;
+	unsigned int gt_max_atomic_write; /* Split big writes into this size */
+	unsigned int gt_max_readahead; /* Max bytes to read-ahead from disk */
+	unsigned int gt_lockdump_size;
+	unsigned int gt_stall_secs; /* Detects trouble! */
+	unsigned int gt_complain_secs;
+	unsigned int gt_reclaim_limit; /* Max num of glocks in reclaim list */
+	unsigned int gt_entries_per_readdir;
+	unsigned int gt_prefetch_secs; /* Usage window for prefetched glocks */
+	unsigned int gt_greedy_default;
+	unsigned int gt_greedy_quantum;
+	unsigned int gt_greedy_max;
+	unsigned int gt_statfs_quantum;
+	unsigned int gt_statfs_slow;
+};
+
+enum {
+	SDF_JOURNAL_CHECKED	= 0,
+	SDF_JOURNAL_LIVE	= 1,
+	SDF_SHUTDOWN		= 2,
+	SDF_NOATIME		= 3,
+};
+
+#define GFS2_FSNAME_LEN		256
+
+struct gfs2_sbd {
+	struct super_block *sd_vfs;
+	struct super_block *sd_vfs_meta;
+	struct kobject sd_kobj;
+	unsigned long sd_flags;	/* SDF_... */
+	struct gfs2_sb sd_sb;
+
+	/* Constants computed on mount */
+
+	u32 sd_fsb2bb;
+	u32 sd_fsb2bb_shift;
+	u32 sd_diptrs;	/* Number of pointers in a dinode */
+	u32 sd_inptrs;	/* Number of pointers in a indirect block */
+	u32 sd_jbsize;	/* Size of a journaled data block */
+	u32 sd_hash_bsize;	/* sizeof(exhash block) */
+	u32 sd_hash_bsize_shift;
+	u32 sd_hash_ptrs;	/* Number of pointers in a hash block */
+	u32 sd_qc_per_block;
+	u32 sd_max_dirres;	/* Max blocks needed to add a directory entry */
+	u32 sd_max_height;	/* Max height of a file's metadata tree */
+	u64 sd_heightsize[GFS2_MAX_META_HEIGHT];
+	u32 sd_max_jheight; /* Max height of journaled file's meta tree */
+	u64 sd_jheightsize[GFS2_MAX_META_HEIGHT];
+
+	struct gfs2_args sd_args;	/* Mount arguments */
+	struct gfs2_tune sd_tune;	/* Filesystem tuning structure */
+
+	/* Lock Stuff */
+
+	struct lm_lockstruct sd_lockstruct;
+	struct list_head sd_reclaim_list;
+	spinlock_t sd_reclaim_lock;
+	wait_queue_head_t sd_reclaim_wq;
+	atomic_t sd_reclaim_count;
+	struct gfs2_holder sd_live_gh;
+	struct gfs2_glock *sd_rename_gl;
+	struct gfs2_glock *sd_trans_gl;
+
+	/* Inode Stuff */
+
+	struct inode *sd_master_dir;
+	struct inode *sd_jindex;
+	struct inode *sd_inum_inode;
+	struct inode *sd_statfs_inode;
+	struct inode *sd_ir_inode;
+	struct inode *sd_sc_inode;
+	struct inode *sd_qc_inode;
+	struct inode *sd_rindex;
+	struct inode *sd_quota_inode;
+
+	/* Inum stuff */
+
+	struct mutex sd_inum_mutex;
+
+	/* StatFS stuff */
+
+	spinlock_t sd_statfs_spin;
+	struct mutex sd_statfs_mutex;
+	struct gfs2_statfs_change sd_statfs_master;
+	struct gfs2_statfs_change sd_statfs_local;
+	unsigned long sd_statfs_sync_time;
+
+	/* Resource group stuff */
+
+	u64 sd_rindex_vn;
+	spinlock_t sd_rindex_spin;
+	struct mutex sd_rindex_mutex;
+	struct list_head sd_rindex_list;
+	struct list_head sd_rindex_mru_list;
+	struct list_head sd_rindex_recent_list;
+	struct gfs2_rgrpd *sd_rindex_forward;
+	unsigned int sd_rgrps;
+
+	/* Journal index stuff */
+
+	struct list_head sd_jindex_list;
+	spinlock_t sd_jindex_spin;
+	struct mutex sd_jindex_mutex;
+	unsigned int sd_journals;
+	unsigned long sd_jindex_refresh_time;
+
+	struct gfs2_jdesc *sd_jdesc;
+	struct gfs2_holder sd_journal_gh;
+	struct gfs2_holder sd_jinode_gh;
+
+	struct gfs2_holder sd_ir_gh;
+	struct gfs2_holder sd_sc_gh;
+	struct gfs2_holder sd_qc_gh;
+
+	/* 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;
+	struct task_struct *sd_glockd_process[GFS2_GLOCKD_MAX];
+	unsigned int sd_glockd_num;
+
+	/* Quota stuff */
+
+	struct list_head sd_quota_list;
+	atomic_t sd_quota_count;
+	spinlock_t sd_quota_spin;
+	struct mutex sd_quota_mutex;
+
+	unsigned int sd_quota_slots;
+	unsigned int sd_quota_chunks;
+	unsigned char **sd_quota_bitmap;
+
+	u64 sd_quota_sync_gen;
+	unsigned long sd_quota_sync_time;
+
+	/* Log stuff */
+
+	spinlock_t sd_log_lock;
+
+	unsigned int sd_log_blks_reserved;
+	unsigned int sd_log_commited_buf;
+	unsigned int sd_log_commited_revoke;
+
+	unsigned int sd_log_num_gl;
+	unsigned int sd_log_num_buf;
+	unsigned int sd_log_num_revoke;
+	unsigned int sd_log_num_rg;
+	unsigned int sd_log_num_databuf;
+	unsigned int sd_log_num_jdata;
+	unsigned int sd_log_num_hdrs;
+
+	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;
+
+	unsigned int sd_log_blks_free;
+	struct mutex sd_log_reserve_mutex;
+
+	u64 sd_log_sequence;
+	unsigned int sd_log_head;
+	unsigned int sd_log_tail;
+	int sd_log_idle;
+
+	unsigned long sd_log_flush_time;
+	struct rw_semaphore sd_log_flush_lock;
+	struct list_head sd_log_flush_list;
+
+	unsigned int sd_log_flush_head;
+	u64 sd_log_flush_wrapped;
+
+	struct list_head sd_ail1_list;
+	struct list_head sd_ail2_list;
+	u64 sd_ail_sync_gen;
+
+	/* Replay stuff */
+
+	struct list_head sd_revoke_list;
+	unsigned int sd_replay_tail;
+
+	unsigned int sd_found_blocks;
+	unsigned int sd_found_revokes;
+	unsigned int sd_replayed_blocks;
+
+	/* For quiescing the filesystem */
+
+	struct gfs2_holder sd_freeze_gh;
+	struct mutex sd_freeze_lock;
+	unsigned int sd_freeze_count;
+
+	/* Counters */
+
+	atomic_t sd_glock_count;
+	atomic_t sd_glock_held_count;
+	atomic_t sd_inode_count;
+	atomic_t sd_reclaimed;
+
+	char sd_fsname[GFS2_FSNAME_LEN];
+	char sd_table_name[GFS2_FSNAME_LEN];
+	char sd_proto_name[GFS2_FSNAME_LEN];
+
+	/* Debugging crud */
+
+	unsigned long sd_last_warning;
+	struct vfsmount *sd_gfs2mnt;
+};
+
+#endif /* __INCORE_DOT_H__ */
+

fs/gfs2/inode.h

@@ -0,0 +1,56 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __INODE_DOT_H__
+#define __INODE_DOT_H__
+
+static inline int gfs2_is_stuffed(struct gfs2_inode *ip)
+{
+	return !ip->i_di.di_height;
+}
+
+static inline int gfs2_is_jdata(struct gfs2_inode *ip)
+{
+	return ip->i_di.di_flags & GFS2_DIF_JDATA;
+}
+
+static inline int gfs2_is_dir(struct gfs2_inode *ip)
+{
+	return S_ISDIR(ip->i_di.di_mode);
+}
+
+void gfs2_inode_attr_in(struct gfs2_inode *ip);
+void gfs2_inode_attr_out(struct gfs2_inode *ip);
+struct inode *gfs2_inode_lookup(struct super_block *sb, struct gfs2_inum *inum, unsigned type);
+struct inode *gfs2_ilookup(struct super_block *sb, struct gfs2_inum *inum);
+
+int gfs2_inode_refresh(struct gfs2_inode *ip);
+
+int gfs2_dinode_dealloc(struct gfs2_inode *inode);
+int gfs2_change_nlink(struct gfs2_inode *ip, int diff);
+struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
+			   int is_root, struct nameidata *nd);
+struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
+			   unsigned int mode);
+int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
+		struct gfs2_inode *ip);
+int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
+		   struct gfs2_inode *ip);
+int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to);
+int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len);
+
+int gfs2_glock_nq_atime(struct gfs2_holder *gh);
+int gfs2_glock_nq_m_atime(unsigned int num_gh, struct gfs2_holder *ghs);
+
+int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
+
+struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
+
+#endif /* __INODE_DOT_H__ */
+

fs/gfs2/lm.c

@@ -0,0 +1,217 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/delay.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "lm.h"
+#include "super.h"
+#include "util.h"
+
+/**
+ * gfs2_lm_mount - mount a locking protocol
+ * @sdp: the filesystem
+ * @args: mount arguements
+ * @silent: if 1, don't complain if the FS isn't a GFS2 fs
+ *
+ * Returns: errno
+ */
+
+int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent)
+{
+	char *proto = sdp->sd_proto_name;
+	char *table = sdp->sd_table_name;
+	int flags = 0;
+	int error;
+
+	if (sdp->sd_args.ar_spectator)
+		flags |= LM_MFLAG_SPECTATOR;
+
+	fs_info(sdp, "Trying to join cluster \"%s\", \"%s\"\n", proto, table);
+
+	error = gfs2_mount_lockproto(proto, table, sdp->sd_args.ar_hostdata,
+				     gfs2_glock_cb, sdp,
+				     GFS2_MIN_LVB_SIZE, flags,
+				     &sdp->sd_lockstruct, &sdp->sd_kobj);
+	if (error) {
+		fs_info(sdp, "can't mount proto=%s, table=%s, hostdata=%s\n",
+			proto, table, sdp->sd_args.ar_hostdata);
+		goto out;
+	}
+
+	if (gfs2_assert_warn(sdp, sdp->sd_lockstruct.ls_lockspace) ||
+	    gfs2_assert_warn(sdp, sdp->sd_lockstruct.ls_ops) ||
+	    gfs2_assert_warn(sdp, sdp->sd_lockstruct.ls_lvb_size >=
+				  GFS2_MIN_LVB_SIZE)) {
+		gfs2_unmount_lockproto(&sdp->sd_lockstruct);
+		goto out;
+	}
+
+	if (sdp->sd_args.ar_spectator)
+		snprintf(sdp->sd_fsname, GFS2_FSNAME_LEN, "%s.s", table);
+	else
+		snprintf(sdp->sd_fsname, GFS2_FSNAME_LEN, "%s.%u", table,
+			 sdp->sd_lockstruct.ls_jid);
+
+	fs_info(sdp, "Joined cluster. Now mounting FS...\n");
+
+	if ((sdp->sd_lockstruct.ls_flags & LM_LSFLAG_LOCAL) &&
+	    !sdp->sd_args.ar_ignore_local_fs) {
+		sdp->sd_args.ar_localflocks = 1;
+		sdp->sd_args.ar_localcaching = 1;
+	}
+
+out:
+	return error;
+}
+
+void gfs2_lm_others_may_mount(struct gfs2_sbd *sdp)
+{
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		sdp->sd_lockstruct.ls_ops->lm_others_may_mount(
+					sdp->sd_lockstruct.ls_lockspace);
+}
+
+void gfs2_lm_unmount(struct gfs2_sbd *sdp)
+{
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		gfs2_unmount_lockproto(&sdp->sd_lockstruct);
+}
+
+int gfs2_lm_withdraw(struct gfs2_sbd *sdp, char *fmt, ...)
+{
+	va_list args;
+
+	if (test_and_set_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+		return 0;
+
+	va_start(args, fmt);
+	vprintk(fmt, args);
+	va_end(args);
+
+	fs_err(sdp, "about to withdraw from the cluster\n");
+	BUG_ON(sdp->sd_args.ar_debug);
+
+
+	fs_err(sdp, "waiting for outstanding I/O\n");
+
+	/* FIXME: suspend dm device so oustanding bio's complete
+	   and all further io requests fail */
+
+	fs_err(sdp, "telling LM to withdraw\n");
+	gfs2_withdraw_lockproto(&sdp->sd_lockstruct);
+	fs_err(sdp, "withdrawn\n");
+	dump_stack();
+
+	return -1;
+}
+
+int gfs2_lm_get_lock(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		     void **lockp)
+{
+	int error = -EIO;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		error = sdp->sd_lockstruct.ls_ops->lm_get_lock(
+				sdp->sd_lockstruct.ls_lockspace, name, lockp);
+	return error;
+}
+
+void gfs2_lm_put_lock(struct gfs2_sbd *sdp, void *lock)
+{
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		sdp->sd_lockstruct.ls_ops->lm_put_lock(lock);
+}
+
+unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock,
+			  unsigned int cur_state, unsigned int req_state,
+			  unsigned int flags)
+{
+	int ret = 0;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		ret = sdp->sd_lockstruct.ls_ops->lm_lock(lock, cur_state,
+							 req_state, flags);
+	return ret;
+}
+
+unsigned int gfs2_lm_unlock(struct gfs2_sbd *sdp, void *lock,
+			    unsigned int cur_state)
+{
+	int ret = 0;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		ret =  sdp->sd_lockstruct.ls_ops->lm_unlock(lock, cur_state);
+	return ret;
+}
+
+void gfs2_lm_cancel(struct gfs2_sbd *sdp, void *lock)
+{
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		sdp->sd_lockstruct.ls_ops->lm_cancel(lock);
+}
+
+int gfs2_lm_hold_lvb(struct gfs2_sbd *sdp, void *lock, char **lvbp)
+{
+	int error = -EIO;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		error = sdp->sd_lockstruct.ls_ops->lm_hold_lvb(lock, lvbp);
+	return error;
+}
+
+void gfs2_lm_unhold_lvb(struct gfs2_sbd *sdp, void *lock, char *lvb)
+{
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		sdp->sd_lockstruct.ls_ops->lm_unhold_lvb(lock, lvb);
+}
+
+int gfs2_lm_plock_get(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		      struct file *file, struct file_lock *fl)
+{
+	int error = -EIO;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		error = sdp->sd_lockstruct.ls_ops->lm_plock_get(
+				sdp->sd_lockstruct.ls_lockspace, name, file, fl);
+	return error;
+}
+
+int gfs2_lm_plock(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		  struct file *file, int cmd, struct file_lock *fl)
+{
+	int error = -EIO;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		error = sdp->sd_lockstruct.ls_ops->lm_plock(
+				sdp->sd_lockstruct.ls_lockspace, name, file, cmd, fl);
+	return error;
+}
+
+int gfs2_lm_punlock(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		    struct file *file, struct file_lock *fl)
+{
+	int error = -EIO;
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		error = sdp->sd_lockstruct.ls_ops->lm_punlock(
+				sdp->sd_lockstruct.ls_lockspace, name, file, fl);
+	return error;
+}
+
+void gfs2_lm_recovery_done(struct gfs2_sbd *sdp, unsigned int jid,
+			   unsigned int message)
+{
+	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		sdp->sd_lockstruct.ls_ops->lm_recovery_done(
+			sdp->sd_lockstruct.ls_lockspace, jid, message);
+}
+

fs/gfs2/lm.h

@@ -0,0 +1,42 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __LM_DOT_H__
+#define __LM_DOT_H__
+
+struct gfs2_sbd;
+
+#define GFS2_MIN_LVB_SIZE 32
+
+int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent);
+void gfs2_lm_others_may_mount(struct gfs2_sbd *sdp);
+void gfs2_lm_unmount(struct gfs2_sbd *sdp);
+int gfs2_lm_withdraw(struct gfs2_sbd *sdp, char *fmt, ...)
+				__attribute__ ((format(printf, 2, 3)));
+int gfs2_lm_get_lock(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		     void **lockp);
+void gfs2_lm_put_lock(struct gfs2_sbd *sdp, void *lock);
+unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock,
+			 unsigned int cur_state, unsigned int req_state,
+			 unsigned int flags);
+unsigned int gfs2_lm_unlock(struct gfs2_sbd *sdp, void *lock,
+			   unsigned int cur_state);
+void gfs2_lm_cancel(struct gfs2_sbd *sdp, void *lock);
+int gfs2_lm_hold_lvb(struct gfs2_sbd *sdp, void *lock, char **lvbp);
+void gfs2_lm_unhold_lvb(struct gfs2_sbd *sdp, void *lock, char *lvb);
+int gfs2_lm_plock_get(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		      struct file *file, struct file_lock *fl);
+int gfs2_lm_plock(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		  struct file *file, int cmd, struct file_lock *fl);
+int gfs2_lm_punlock(struct gfs2_sbd *sdp, struct lm_lockname *name,
+		    struct file *file, struct file_lock *fl);
+void gfs2_lm_recovery_done(struct gfs2_sbd *sdp, unsigned int jid,
+			   unsigned int message);
+
+#endif /* __LM_DOT_H__ */

fs/gfs2/locking.c

@@ -0,0 +1,184 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+#include <linux/kmod.h>
+#include <linux/fs.h>
+#include <linux/delay.h>
+#include <linux/lm_interface.h>
+
+struct lmh_wrapper {
+	struct list_head lw_list;
+	const struct lm_lockops *lw_ops;
+};
+
+/* List of registered low-level locking protocols.  A file system selects one
+   of them by name at mount time, e.g. lock_nolock, lock_dlm. */
+
+static LIST_HEAD(lmh_list);
+static DEFINE_MUTEX(lmh_lock);
+
+/**
+ * gfs2_register_lockproto - Register a low-level locking protocol
+ * @proto: the protocol definition
+ *
+ * Returns: 0 on success, -EXXX on failure
+ */
+
+int gfs2_register_lockproto(const struct lm_lockops *proto)
+{
+	struct lmh_wrapper *lw;
+
+	mutex_lock(&lmh_lock);
+
+	list_for_each_entry(lw, &lmh_list, lw_list) {
+		if (!strcmp(lw->lw_ops->lm_proto_name, proto->lm_proto_name)) {
+			mutex_unlock(&lmh_lock);
+			printk(KERN_INFO "GFS2: protocol %s already exists\n",
+			       proto->lm_proto_name);
+			return -EEXIST;
+		}
+	}
+
+	lw = kzalloc(sizeof(struct lmh_wrapper), GFP_KERNEL);
+	if (!lw) {
+		mutex_unlock(&lmh_lock);
+		return -ENOMEM;
+	}
+
+	lw->lw_ops = proto;
+	list_add(&lw->lw_list, &lmh_list);
+
+	mutex_unlock(&lmh_lock);
+
+	return 0;
+}
+
+/**
+ * gfs2_unregister_lockproto - Unregister a low-level locking protocol
+ * @proto: the protocol definition
+ *
+ */
+
+void gfs2_unregister_lockproto(const struct lm_lockops *proto)
+{
+	struct lmh_wrapper *lw;
+
+	mutex_lock(&lmh_lock);
+
+	list_for_each_entry(lw, &lmh_list, lw_list) {
+		if (!strcmp(lw->lw_ops->lm_proto_name, proto->lm_proto_name)) {
+			list_del(&lw->lw_list);
+			mutex_unlock(&lmh_lock);
+			kfree(lw);
+			return;
+		}
+	}
+
+	mutex_unlock(&lmh_lock);
+
+	printk(KERN_WARNING "GFS2: can't unregister lock protocol %s\n",
+	       proto->lm_proto_name);
+}
+
+/**
+ * gfs2_mount_lockproto - Mount a lock protocol
+ * @proto_name - the name of the protocol
+ * @table_name - the name of the lock space
+ * @host_data - data specific to this host
+ * @cb - the callback to the code using the lock module
+ * @sdp - The GFS2 superblock
+ * @min_lvb_size - the mininum LVB size that the caller can deal with
+ * @flags - LM_MFLAG_*
+ * @lockstruct - a structure returned describing the mount
+ *
+ * Returns: 0 on success, -EXXX on failure
+ */
+
+int gfs2_mount_lockproto(char *proto_name, char *table_name, char *host_data,
+			 lm_callback_t cb, void *cb_data,
+			 unsigned int min_lvb_size, int flags,
+			 struct lm_lockstruct *lockstruct,
+			 struct kobject *fskobj)
+{
+	struct lmh_wrapper *lw = NULL;
+	int try = 0;
+	int error, found;
+
+retry:
+	mutex_lock(&lmh_lock);
+
+	found = 0;
+	list_for_each_entry(lw, &lmh_list, lw_list) {
+		if (!strcmp(lw->lw_ops->lm_proto_name, proto_name)) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found) {
+		if (!try && capable(CAP_SYS_MODULE)) {
+			try = 1;
+			mutex_unlock(&lmh_lock);
+			request_module(proto_name);
+			goto retry;
+		}
+		printk(KERN_INFO "GFS2: can't find protocol %s\n", proto_name);
+		error = -ENOENT;
+		goto out;
+	}
+
+	if (!try_module_get(lw->lw_ops->lm_owner)) {
+		try = 0;
+		mutex_unlock(&lmh_lock);
+		msleep(1000);
+		goto retry;
+	}
+
+	error = lw->lw_ops->lm_mount(table_name, host_data, cb, cb_data,
+				     min_lvb_size, flags, lockstruct, fskobj);
+	if (error)
+		module_put(lw->lw_ops->lm_owner);
+out:
+	mutex_unlock(&lmh_lock);
+	return error;
+}
+
+void gfs2_unmount_lockproto(struct lm_lockstruct *lockstruct)
+{
+	mutex_lock(&lmh_lock);
+	lockstruct->ls_ops->lm_unmount(lockstruct->ls_lockspace);
+	if (lockstruct->ls_ops->lm_owner)
+		module_put(lockstruct->ls_ops->lm_owner);
+	mutex_unlock(&lmh_lock);
+}
+
+/**
+ * gfs2_withdraw_lockproto - abnormally unmount a lock module
+ * @lockstruct: the lockstruct passed into mount
+ *
+ */
+
+void gfs2_withdraw_lockproto(struct lm_lockstruct *lockstruct)
+{
+	mutex_lock(&lmh_lock);
+	lockstruct->ls_ops->lm_withdraw(lockstruct->ls_lockspace);
+	if (lockstruct->ls_ops->lm_owner)
+		module_put(lockstruct->ls_ops->lm_owner);
+	mutex_unlock(&lmh_lock);
+}
+
+EXPORT_SYMBOL_GPL(gfs2_register_lockproto);
+EXPORT_SYMBOL_GPL(gfs2_unregister_lockproto);
+

fs/gfs2/locking/dlm/Makefile

@@ -0,0 +1,3 @@
+obj-$(CONFIG_GFS2_FS_LOCKING_DLM) += lock_dlm.o
+lock_dlm-y := lock.o main.o mount.o sysfs.o thread.o plock.o
+

fs/gfs2/locking/dlm/lock.c

@@ -0,0 +1,524 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include "lock_dlm.h"
+
+static char junk_lvb[GDLM_LVB_SIZE];
+
+static void queue_complete(struct gdlm_lock *lp)
+{
+	struct gdlm_ls *ls = lp->ls;
+
+	clear_bit(LFL_ACTIVE, &lp->flags);
+
+	spin_lock(&ls->async_lock);
+	list_add_tail(&lp->clist, &ls->complete);
+	spin_unlock(&ls->async_lock);
+	wake_up(&ls->thread_wait);
+}
+
+static inline void gdlm_ast(void *astarg)
+{
+	queue_complete(astarg);
+}
+
+static inline void gdlm_bast(void *astarg, int mode)
+{
+	struct gdlm_lock *lp = astarg;
+	struct gdlm_ls *ls = lp->ls;
+
+	if (!mode) {
+		printk(KERN_INFO "lock_dlm: bast mode zero %x,%llx\n",
+			lp->lockname.ln_type,
+			(unsigned long long)lp->lockname.ln_number);
+		return;
+	}
+
+	spin_lock(&ls->async_lock);
+	if (!lp->bast_mode) {
+		list_add_tail(&lp->blist, &ls->blocking);
+		lp->bast_mode = mode;
+	} else if (lp->bast_mode < mode)
+		lp->bast_mode = mode;
+	spin_unlock(&ls->async_lock);
+	wake_up(&ls->thread_wait);
+}
+
+void gdlm_queue_delayed(struct gdlm_lock *lp)
+{
+	struct gdlm_ls *ls = lp->ls;
+
+	spin_lock(&ls->async_lock);
+	list_add_tail(&lp->delay_list, &ls->delayed);
+	spin_unlock(&ls->async_lock);
+}
+
+/* convert gfs lock-state to dlm lock-mode */
+
+static s16 make_mode(s16 lmstate)
+{
+	switch (lmstate) {
+	case LM_ST_UNLOCKED:
+		return DLM_LOCK_NL;
+	case LM_ST_EXCLUSIVE:
+		return DLM_LOCK_EX;
+	case LM_ST_DEFERRED:
+		return DLM_LOCK_CW;
+	case LM_ST_SHARED:
+		return DLM_LOCK_PR;
+	}
+	gdlm_assert(0, "unknown LM state %d", lmstate);
+	return -1;
+}
+
+/* convert dlm lock-mode to gfs lock-state */
+
+s16 gdlm_make_lmstate(s16 dlmmode)
+{
+	switch (dlmmode) {
+	case DLM_LOCK_IV:
+	case DLM_LOCK_NL:
+		return LM_ST_UNLOCKED;
+	case DLM_LOCK_EX:
+		return LM_ST_EXCLUSIVE;
+	case DLM_LOCK_CW:
+		return LM_ST_DEFERRED;
+	case DLM_LOCK_PR:
+		return LM_ST_SHARED;
+	}
+	gdlm_assert(0, "unknown DLM mode %d", dlmmode);
+	return -1;
+}
+
+/* verify agreement with GFS on the current lock state, NB: DLM_LOCK_NL and
+   DLM_LOCK_IV are both considered LM_ST_UNLOCKED by GFS. */
+
+static void check_cur_state(struct gdlm_lock *lp, unsigned int cur_state)
+{
+	s16 cur = make_mode(cur_state);
+	if (lp->cur != DLM_LOCK_IV)
+		gdlm_assert(lp->cur == cur, "%d, %d", lp->cur, cur);
+}
+
+static inline unsigned int make_flags(struct gdlm_lock *lp,
+				      unsigned int gfs_flags,
+				      s16 cur, s16 req)
+{
+	unsigned int lkf = 0;
+
+	if (gfs_flags & LM_FLAG_TRY)
+		lkf |= DLM_LKF_NOQUEUE;
+
+	if (gfs_flags & LM_FLAG_TRY_1CB) {
+		lkf |= DLM_LKF_NOQUEUE;
+		lkf |= DLM_LKF_NOQUEUEBAST;
+	}
+
+	if (gfs_flags & LM_FLAG_PRIORITY) {
+		lkf |= DLM_LKF_NOORDER;
+		lkf |= DLM_LKF_HEADQUE;
+	}
+
+	if (gfs_flags & LM_FLAG_ANY) {
+		if (req == DLM_LOCK_PR)
+			lkf |= DLM_LKF_ALTCW;
+		else if (req == DLM_LOCK_CW)
+			lkf |= DLM_LKF_ALTPR;
+	}
+
+	if (lp->lksb.sb_lkid != 0) {
+		lkf |= DLM_LKF_CONVERT;
+
+		/* Conversion deadlock avoidance by DLM */
+
+		if (!test_bit(LFL_FORCE_PROMOTE, &lp->flags) &&
+		    !(lkf & DLM_LKF_NOQUEUE) &&
+		    cur > DLM_LOCK_NL && req > DLM_LOCK_NL && cur != req)
+			lkf |= DLM_LKF_CONVDEADLK;
+	}
+
+	if (lp->lvb)
+		lkf |= DLM_LKF_VALBLK;
+
+	return lkf;
+}
+
+/* make_strname - convert GFS lock numbers to a string */
+
+static inline void make_strname(struct lm_lockname *lockname,
+				struct gdlm_strname *str)
+{
+	sprintf(str->name, "%8x%16llx", lockname->ln_type,
+		(unsigned long long)lockname->ln_number);
+	str->namelen = GDLM_STRNAME_BYTES;
+}
+
+static int gdlm_create_lp(struct gdlm_ls *ls, struct lm_lockname *name,
+			  struct gdlm_lock **lpp)
+{
+	struct gdlm_lock *lp;
+
+	lp = kzalloc(sizeof(struct gdlm_lock), GFP_KERNEL);
+	if (!lp)
+		return -ENOMEM;
+
+	lp->lockname = *name;
+	lp->ls = ls;
+	lp->cur = DLM_LOCK_IV;
+	lp->lvb = NULL;
+	lp->hold_null = NULL;
+	init_completion(&lp->ast_wait);
+	INIT_LIST_HEAD(&lp->clist);
+	INIT_LIST_HEAD(&lp->blist);
+	INIT_LIST_HEAD(&lp->delay_list);
+
+	spin_lock(&ls->async_lock);
+	list_add(&lp->all_list, &ls->all_locks);
+	ls->all_locks_count++;
+	spin_unlock(&ls->async_lock);
+
+	*lpp = lp;
+	return 0;
+}
+
+void gdlm_delete_lp(struct gdlm_lock *lp)
+{
+	struct gdlm_ls *ls = lp->ls;
+
+	spin_lock(&ls->async_lock);
+	if (!list_empty(&lp->clist))
+		list_del_init(&lp->clist);
+	if (!list_empty(&lp->blist))
+		list_del_init(&lp->blist);
+	if (!list_empty(&lp->delay_list))
+		list_del_init(&lp->delay_list);
+	gdlm_assert(!list_empty(&lp->all_list), "%x,%llx", lp->lockname.ln_type,
+		    (unsigned long long)lp->lockname.ln_number);
+	list_del_init(&lp->all_list);
+	ls->all_locks_count--;
+	spin_unlock(&ls->async_lock);
+
+	kfree(lp);
+}
+
+int gdlm_get_lock(void *lockspace, struct lm_lockname *name,
+		  void **lockp)
+{
+	struct gdlm_lock *lp;
+	int error;
+
+	error = gdlm_create_lp(lockspace, name, &lp);
+
+	*lockp = lp;
+	return error;
+}
+
+void gdlm_put_lock(void *lock)
+{
+	gdlm_delete_lp(lock);
+}
+
+unsigned int gdlm_do_lock(struct gdlm_lock *lp)
+{
+	struct gdlm_ls *ls = lp->ls;
+	struct gdlm_strname str;
+	int error, bast = 1;
+
+	/*
+	 * When recovery is in progress, delay lock requests for submission
+	 * once recovery is done.  Requests for recovery (NOEXP) and unlocks
+	 * can pass.
+	 */
+
+	if (test_bit(DFL_BLOCK_LOCKS, &ls->flags) &&
+	    !test_bit(LFL_NOBLOCK, &lp->flags) && lp->req != DLM_LOCK_NL) {
+		gdlm_queue_delayed(lp);
+		return LM_OUT_ASYNC;
+	}
+
+	/*
+	 * Submit the actual lock request.
+	 */
+
+	if (test_bit(LFL_NOBAST, &lp->flags))
+		bast = 0;
+
+	make_strname(&lp->lockname, &str);
+
+	set_bit(LFL_ACTIVE, &lp->flags);
+
+	log_debug("lk %x,%llx id %x %d,%d %x", lp->lockname.ln_type,
+		  (unsigned long long)lp->lockname.ln_number, lp->lksb.sb_lkid,
+		  lp->cur, lp->req, lp->lkf);
+
+	error = dlm_lock(ls->dlm_lockspace, lp->req, &lp->lksb, lp->lkf,
+			 str.name, str.namelen, 0, gdlm_ast, lp,
+			 bast ? gdlm_bast : NULL);
+
+	if ((error == -EAGAIN) && (lp->lkf & DLM_LKF_NOQUEUE)) {
+		lp->lksb.sb_status = -EAGAIN;
+		queue_complete(lp);
+		error = 0;
+	}
+
+	if (error) {
+		log_debug("%s: gdlm_lock %x,%llx err=%d cur=%d req=%d lkf=%x "
+			  "flags=%lx", ls->fsname, lp->lockname.ln_type,
+			  (unsigned long long)lp->lockname.ln_number, error,
+			  lp->cur, lp->req, lp->lkf, lp->flags);
+		return LM_OUT_ERROR;
+	}
+	return LM_OUT_ASYNC;
+}
+
+static unsigned int gdlm_do_unlock(struct gdlm_lock *lp)
+{
+	struct gdlm_ls *ls = lp->ls;
+	unsigned int lkf = 0;
+	int error;
+
+	set_bit(LFL_DLM_UNLOCK, &lp->flags);
+	set_bit(LFL_ACTIVE, &lp->flags);
+
+	if (lp->lvb)
+		lkf = DLM_LKF_VALBLK;
+
+	log_debug("un %x,%llx %x %d %x", lp->lockname.ln_type,
+		  (unsigned long long)lp->lockname.ln_number,
+		  lp->lksb.sb_lkid, lp->cur, lkf);
+
+	error = dlm_unlock(ls->dlm_lockspace, lp->lksb.sb_lkid, lkf, NULL, lp);
+
+	if (error) {
+		log_debug("%s: gdlm_unlock %x,%llx err=%d cur=%d req=%d lkf=%x "
+			  "flags=%lx", ls->fsname, lp->lockname.ln_type,
+			  (unsigned long long)lp->lockname.ln_number, error,
+			  lp->cur, lp->req, lp->lkf, lp->flags);
+		return LM_OUT_ERROR;
+	}
+	return LM_OUT_ASYNC;
+}
+
+unsigned int gdlm_lock(void *lock, unsigned int cur_state,
+		       unsigned int req_state, unsigned int flags)
+{
+	struct gdlm_lock *lp = lock;
+
+	clear_bit(LFL_DLM_CANCEL, &lp->flags);
+	if (flags & LM_FLAG_NOEXP)
+		set_bit(LFL_NOBLOCK, &lp->flags);
+
+	check_cur_state(lp, cur_state);
+	lp->req = make_mode(req_state);
+	lp->lkf = make_flags(lp, flags, lp->cur, lp->req);
+
+	return gdlm_do_lock(lp);
+}
+
+unsigned int gdlm_unlock(void *lock, unsigned int cur_state)
+{
+	struct gdlm_lock *lp = lock;
+
+	clear_bit(LFL_DLM_CANCEL, &lp->flags);
+	if (lp->cur == DLM_LOCK_IV)
+		return 0;
+	return gdlm_do_unlock(lp);
+}
+
+void gdlm_cancel(void *lock)
+{
+	struct gdlm_lock *lp = lock;
+	struct gdlm_ls *ls = lp->ls;
+	int error, delay_list = 0;
+
+	if (test_bit(LFL_DLM_CANCEL, &lp->flags))
+		return;
+
+	log_info("gdlm_cancel %x,%llx flags %lx", lp->lockname.ln_type,
+		 (unsigned long long)lp->lockname.ln_number, lp->flags);
+
+	spin_lock(&ls->async_lock);
+	if (!list_empty(&lp->delay_list)) {
+		list_del_init(&lp->delay_list);
+		delay_list = 1;
+	}
+	spin_unlock(&ls->async_lock);
+
+	if (delay_list) {
+		set_bit(LFL_CANCEL, &lp->flags);
+		set_bit(LFL_ACTIVE, &lp->flags);
+		queue_complete(lp);
+		return;
+	}
+
+	if (!test_bit(LFL_ACTIVE, &lp->flags) ||
+	    test_bit(LFL_DLM_UNLOCK, &lp->flags)) {
+		log_info("gdlm_cancel skip %x,%llx flags %lx",
+		 	 lp->lockname.ln_type,
+			 (unsigned long long)lp->lockname.ln_number, lp->flags);
+		return;
+	}
+
+	/* the lock is blocked in the dlm */
+
+	set_bit(LFL_DLM_CANCEL, &lp->flags);
+	set_bit(LFL_ACTIVE, &lp->flags);
+
+	error = dlm_unlock(ls->dlm_lockspace, lp->lksb.sb_lkid, DLM_LKF_CANCEL,
+			   NULL, lp);
+
+	log_info("gdlm_cancel rv %d %x,%llx flags %lx", error,
+		 lp->lockname.ln_type,
+		 (unsigned long long)lp->lockname.ln_number, lp->flags);
+
+	if (error == -EBUSY)
+		clear_bit(LFL_DLM_CANCEL, &lp->flags);
+}
+
+static int gdlm_add_lvb(struct gdlm_lock *lp)
+{
+	char *lvb;
+
+	lvb = kzalloc(GDLM_LVB_SIZE, GFP_KERNEL);
+	if (!lvb)
+		return -ENOMEM;
+
+	lp->lksb.sb_lvbptr = lvb;
+	lp->lvb = lvb;
+	return 0;
+}
+
+static void gdlm_del_lvb(struct gdlm_lock *lp)
+{
+	kfree(lp->lvb);
+	lp->lvb = NULL;
+	lp->lksb.sb_lvbptr = NULL;
+}
+
+/* This can do a synchronous dlm request (requiring a lock_dlm thread to get
+   the completion) because gfs won't call hold_lvb() during a callback (from
+   the context of a lock_dlm thread). */
+
+static int hold_null_lock(struct gdlm_lock *lp)
+{
+	struct gdlm_lock *lpn = NULL;
+	int error;
+
+	if (lp->hold_null) {
+		printk(KERN_INFO "lock_dlm: lvb already held\n");
+		return 0;
+	}
+
+	error = gdlm_create_lp(lp->ls, &lp->lockname, &lpn);
+	if (error)
+		goto out;
+
+	lpn->lksb.sb_lvbptr = junk_lvb;
+	lpn->lvb = junk_lvb;
+
+	lpn->req = DLM_LOCK_NL;
+	lpn->lkf = DLM_LKF_VALBLK | DLM_LKF_EXPEDITE;
+	set_bit(LFL_NOBAST, &lpn->flags);
+	set_bit(LFL_INLOCK, &lpn->flags);
+
+	init_completion(&lpn->ast_wait);
+	gdlm_do_lock(lpn);
+	wait_for_completion(&lpn->ast_wait);
+	error = lpn->lksb.sb_status;
+	if (error) {
+		printk(KERN_INFO "lock_dlm: hold_null_lock dlm error %d\n",
+		       error);
+		gdlm_delete_lp(lpn);
+		lpn = NULL;
+	}
+out:
+	lp->hold_null = lpn;
+	return error;
+}
+
+/* This cannot do a synchronous dlm request (requiring a lock_dlm thread to get
+   the completion) because gfs may call unhold_lvb() during a callback (from
+   the context of a lock_dlm thread) which could cause a deadlock since the
+   other lock_dlm thread could be engaged in recovery. */
+
+static void unhold_null_lock(struct gdlm_lock *lp)
+{
+	struct gdlm_lock *lpn = lp->hold_null;
+
+	gdlm_assert(lpn, "%x,%llx", lp->lockname.ln_type,
+		    (unsigned long long)lp->lockname.ln_number);
+	lpn->lksb.sb_lvbptr = NULL;
+	lpn->lvb = NULL;
+	set_bit(LFL_UNLOCK_DELETE, &lpn->flags);
+	gdlm_do_unlock(lpn);
+	lp->hold_null = NULL;
+}
+
+/* Acquire a NL lock because gfs requires the value block to remain
+   intact on the resource while the lvb is "held" even if it's holding no locks
+   on the resource. */
+
+int gdlm_hold_lvb(void *lock, char **lvbp)
+{
+	struct gdlm_lock *lp = lock;
+	int error;
+
+	error = gdlm_add_lvb(lp);
+	if (error)
+		return error;
+
+	*lvbp = lp->lvb;
+
+	error = hold_null_lock(lp);
+	if (error)
+		gdlm_del_lvb(lp);
+
+	return error;
+}
+
+void gdlm_unhold_lvb(void *lock, char *lvb)
+{
+	struct gdlm_lock *lp = lock;
+
+	unhold_null_lock(lp);
+	gdlm_del_lvb(lp);
+}
+
+void gdlm_submit_delayed(struct gdlm_ls *ls)
+{
+	struct gdlm_lock *lp, *safe;
+
+	spin_lock(&ls->async_lock);
+	list_for_each_entry_safe(lp, safe, &ls->delayed, delay_list) {
+		list_del_init(&lp->delay_list);
+		list_add_tail(&lp->delay_list, &ls->submit);
+	}
+	spin_unlock(&ls->async_lock);
+	wake_up(&ls->thread_wait);
+}
+
+int gdlm_release_all_locks(struct gdlm_ls *ls)
+{
+	struct gdlm_lock *lp, *safe;
+	int count = 0;
+
+	spin_lock(&ls->async_lock);
+	list_for_each_entry_safe(lp, safe, &ls->all_locks, all_list) {
+		list_del_init(&lp->all_list);
+
+		if (lp->lvb && lp->lvb != junk_lvb)
+			kfree(lp->lvb);
+		kfree(lp);
+		count++;
+	}
+	spin_unlock(&ls->async_lock);
+
+	return count;
+}
+

fs/gfs2/locking/dlm/lock_dlm.h

@@ -0,0 +1,187 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef LOCK_DLM_DOT_H
+#define LOCK_DLM_DOT_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>
+#include <linux/socket.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/kobject.h>
+#include <linux/fcntl.h>
+#include <linux/wait.h>
+#include <net/sock.h>
+
+#include <linux/dlm.h>
+#include <linux/lm_interface.h>
+
+/*
+ * Internally, we prefix things with gdlm_ and GDLM_ (for gfs-dlm) since a
+ * prefix of lock_dlm_ gets awkward.  Externally, GFS refers to this module
+ * as "lock_dlm".
+ */
+
+#define GDLM_STRNAME_BYTES	24
+#define GDLM_LVB_SIZE		32
+#define GDLM_DROP_COUNT		50000
+#define GDLM_DROP_PERIOD	60
+#define GDLM_NAME_LEN		128
+
+/* GFS uses 12 bytes to identify a resource (32 bit type + 64 bit number).
+   We sprintf these numbers into a 24 byte string of hex values to make them
+   human-readable (to make debugging simpler.) */
+
+struct gdlm_strname {
+	unsigned char		name[GDLM_STRNAME_BYTES];
+	unsigned short		namelen;
+};
+
+enum {
+	DFL_BLOCK_LOCKS		= 0,
+	DFL_SPECTATOR		= 1,
+	DFL_WITHDRAW		= 2,
+};
+
+struct gdlm_ls {
+	u32		id;
+	int			jid;
+	int			first;
+	int			first_done;
+	unsigned long		flags;
+	struct kobject		kobj;
+	char			clustername[GDLM_NAME_LEN];
+	char			fsname[GDLM_NAME_LEN];
+	int			fsflags;
+	dlm_lockspace_t		*dlm_lockspace;
+	lm_callback_t		fscb;
+	struct gfs2_sbd		*sdp;
+	int			recover_jid;
+	int			recover_jid_done;
+	int			recover_jid_status;
+	spinlock_t		async_lock;
+	struct list_head	complete;
+	struct list_head	blocking;
+	struct list_head	delayed;
+	struct list_head	submit;
+	struct list_head	all_locks;
+	u32		all_locks_count;
+	wait_queue_head_t	wait_control;
+	struct task_struct	*thread1;
+	struct task_struct	*thread2;
+	wait_queue_head_t	thread_wait;
+	unsigned long		drop_time;
+	int			drop_locks_count;
+	int			drop_locks_period;
+};
+
+enum {
+	LFL_NOBLOCK		= 0,
+	LFL_NOCACHE		= 1,
+	LFL_DLM_UNLOCK		= 2,
+	LFL_DLM_CANCEL		= 3,
+	LFL_SYNC_LVB		= 4,
+	LFL_FORCE_PROMOTE	= 5,
+	LFL_REREQUEST		= 6,
+	LFL_ACTIVE		= 7,
+	LFL_INLOCK		= 8,
+	LFL_CANCEL		= 9,
+	LFL_NOBAST		= 10,
+	LFL_HEADQUE		= 11,
+	LFL_UNLOCK_DELETE	= 12,
+};
+
+struct gdlm_lock {
+	struct gdlm_ls		*ls;
+	struct lm_lockname	lockname;
+	char			*lvb;
+	struct dlm_lksb		lksb;
+
+	s16			cur;
+	s16			req;
+	s16			prev_req;
+	u32			lkf;		/* dlm flags DLM_LKF_ */
+	unsigned long		flags;		/* lock_dlm flags LFL_ */
+
+	int			bast_mode;	/* protected by async_lock */
+	struct completion	ast_wait;
+
+	struct list_head	clist;		/* complete */
+	struct list_head	blist;		/* blocking */
+	struct list_head	delay_list;	/* delayed */
+	struct list_head	all_list;	/* all locks for the fs */
+	struct gdlm_lock	*hold_null;	/* NL lock for hold_lvb */
+};
+
+#define gdlm_assert(assertion, fmt, args...)                                  \
+do {                                                                          \
+	if (unlikely(!(assertion))) {                                         \
+		printk(KERN_EMERG "lock_dlm: fatal assertion failed \"%s\"\n" \
+				  "lock_dlm:  " fmt "\n",                     \
+				  #assertion, ##args);                        \
+		BUG();                                                        \
+	}                                                                     \
+} while (0)
+
+#define log_print(lev, fmt, arg...) printk(lev "lock_dlm: " fmt "\n" , ## arg)
+#define log_info(fmt, arg...)  log_print(KERN_INFO , fmt , ## arg)
+#define log_error(fmt, arg...) log_print(KERN_ERR , fmt , ## arg)
+#ifdef LOCK_DLM_LOG_DEBUG
+#define log_debug(fmt, arg...) log_print(KERN_DEBUG , fmt , ## arg)
+#else
+#define log_debug(fmt, arg...)
+#endif
+
+/* sysfs.c */
+
+int gdlm_sysfs_init(void);
+void gdlm_sysfs_exit(void);
+int gdlm_kobject_setup(struct gdlm_ls *, struct kobject *);
+void gdlm_kobject_release(struct gdlm_ls *);
+
+/* thread.c */
+
+int gdlm_init_threads(struct gdlm_ls *);
+void gdlm_release_threads(struct gdlm_ls *);
+
+/* lock.c */
+
+s16 gdlm_make_lmstate(s16);
+void gdlm_queue_delayed(struct gdlm_lock *);
+void gdlm_submit_delayed(struct gdlm_ls *);
+int gdlm_release_all_locks(struct gdlm_ls *);
+void gdlm_delete_lp(struct gdlm_lock *);
+unsigned int gdlm_do_lock(struct gdlm_lock *);
+
+int gdlm_get_lock(void *, struct lm_lockname *, void **);
+void gdlm_put_lock(void *);
+unsigned int gdlm_lock(void *, unsigned int, unsigned int, unsigned int);
+unsigned int gdlm_unlock(void *, unsigned int);
+void gdlm_cancel(void *);
+int gdlm_hold_lvb(void *, char **);
+void gdlm_unhold_lvb(void *, char *);
+
+/* plock.c */
+
+int gdlm_plock_init(void);
+void gdlm_plock_exit(void);
+int gdlm_plock(void *, struct lm_lockname *, struct file *, int,
+		struct file_lock *);
+int gdlm_plock_get(void *, struct lm_lockname *, struct file *,
+		struct file_lock *);
+int gdlm_punlock(void *, struct lm_lockname *, struct file *,
+		struct file_lock *);
+#endif
+

fs/gfs2/locking/dlm/main.c

@@ -0,0 +1,64 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/init.h>
+
+#include "lock_dlm.h"
+
+extern int gdlm_drop_count;
+extern int gdlm_drop_period;
+
+extern struct lm_lockops gdlm_ops;
+
+static int __init init_lock_dlm(void)
+{
+	int error;
+
+	error = gfs2_register_lockproto(&gdlm_ops);
+	if (error) {
+		printk(KERN_WARNING "lock_dlm:  can't register protocol: %d\n",
+		       error);
+		return error;
+	}
+
+	error = gdlm_sysfs_init();
+	if (error) {
+		gfs2_unregister_lockproto(&gdlm_ops);
+		return error;
+	}
+
+	error = gdlm_plock_init();
+	if (error) {
+		gdlm_sysfs_exit();
+		gfs2_unregister_lockproto(&gdlm_ops);
+		return error;
+	}
+
+	gdlm_drop_count = GDLM_DROP_COUNT;
+	gdlm_drop_period = GDLM_DROP_PERIOD;
+
+	printk(KERN_INFO
+	       "Lock_DLM (built %s %s) installed\n", __DATE__, __TIME__);
+	return 0;
+}
+
+static void __exit exit_lock_dlm(void)
+{
+	gdlm_plock_exit();
+	gdlm_sysfs_exit();
+	gfs2_unregister_lockproto(&gdlm_ops);
+}
+
+module_init(init_lock_dlm);
+module_exit(exit_lock_dlm);
+
+MODULE_DESCRIPTION("GFS DLM Locking Module");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+

fs/gfs2/locking/dlm/mount.c

@@ -0,0 +1,255 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include "lock_dlm.h"
+
+int gdlm_drop_count;
+int gdlm_drop_period;
+const struct lm_lockops gdlm_ops;
+
+
+static struct gdlm_ls *init_gdlm(lm_callback_t cb, struct gfs2_sbd *sdp,
+				 int flags, char *table_name)
+{
+	struct gdlm_ls *ls;
+	char buf[256], *p;
+
+	ls = kzalloc(sizeof(struct gdlm_ls), GFP_KERNEL);
+	if (!ls)
+		return NULL;
+
+	ls->drop_locks_count = gdlm_drop_count;
+	ls->drop_locks_period = gdlm_drop_period;
+	ls->fscb = cb;
+	ls->sdp = sdp;
+	ls->fsflags = flags;
+	spin_lock_init(&ls->async_lock);
+	INIT_LIST_HEAD(&ls->complete);
+	INIT_LIST_HEAD(&ls->blocking);
+	INIT_LIST_HEAD(&ls->delayed);
+	INIT_LIST_HEAD(&ls->submit);
+	INIT_LIST_HEAD(&ls->all_locks);
+	init_waitqueue_head(&ls->thread_wait);
+	init_waitqueue_head(&ls->wait_control);
+	ls->thread1 = NULL;
+	ls->thread2 = NULL;
+	ls->drop_time = jiffies;
+	ls->jid = -1;
+
+	strncpy(buf, table_name, 256);
+	buf[255] = '\0';
+
+	p = strstr(buf, ":");
+	if (!p) {
+		log_info("invalid table_name \"%s\"", table_name);
+		kfree(ls);
+		return NULL;
+	}
+	*p = '\0';
+	p++;
+
+	strncpy(ls->clustername, buf, GDLM_NAME_LEN);
+	strncpy(ls->fsname, p, GDLM_NAME_LEN);
+
+	return ls;
+}
+
+static int make_args(struct gdlm_ls *ls, char *data_arg, int *nodir)
+{
+	char data[256];
+	char *options, *x, *y;
+	int error = 0;
+
+	memset(data, 0, 256);
+	strncpy(data, data_arg, 255);
+
+	for (options = data; (x = strsep(&options, ":")); ) {
+		if (!*x)
+			continue;
+
+		y = strchr(x, '=');
+		if (y)
+			*y++ = 0;
+
+		if (!strcmp(x, "jid")) {
+			if (!y) {
+				log_error("need argument to jid");
+				error = -EINVAL;
+				break;
+			}
+			sscanf(y, "%u", &ls->jid);
+
+		} else if (!strcmp(x, "first")) {
+			if (!y) {
+				log_error("need argument to first");
+				error = -EINVAL;
+				break;
+			}
+			sscanf(y, "%u", &ls->first);
+
+		} else if (!strcmp(x, "id")) {
+			if (!y) {
+				log_error("need argument to id");
+				error = -EINVAL;
+				break;
+			}
+			sscanf(y, "%u", &ls->id);
+
+		} else if (!strcmp(x, "nodir")) {
+			if (!y) {
+				log_error("need argument to nodir");
+				error = -EINVAL;
+				break;
+			}
+			sscanf(y, "%u", nodir);
+
+		} else {
+			log_error("unkonwn option: %s", x);
+			error = -EINVAL;
+			break;
+		}
+	}
+
+	return error;
+}
+
+static int gdlm_mount(char *table_name, char *host_data,
+			lm_callback_t cb, void *cb_data,
+			unsigned int min_lvb_size, int flags,
+			struct lm_lockstruct *lockstruct,
+			struct kobject *fskobj)
+{
+	struct gdlm_ls *ls;
+	int error = -ENOMEM, nodir = 0;
+
+	if (min_lvb_size > GDLM_LVB_SIZE)
+		goto out;
+
+	ls = init_gdlm(cb, cb_data, flags, table_name);
+	if (!ls)
+		goto out;
+
+	error = make_args(ls, host_data, &nodir);
+	if (error)
+		goto out;
+
+	error = gdlm_init_threads(ls);
+	if (error)
+		goto out_free;
+
+	error = gdlm_kobject_setup(ls, fskobj);
+	if (error)
+		goto out_thread;
+
+	error = dlm_new_lockspace(ls->fsname, strlen(ls->fsname),
+				  &ls->dlm_lockspace,
+				  nodir ? DLM_LSFL_NODIR : 0,
+				  GDLM_LVB_SIZE);
+	if (error) {
+		log_error("dlm_new_lockspace error %d", error);
+		goto out_kobj;
+	}
+
+	lockstruct->ls_jid = ls->jid;
+	lockstruct->ls_first = ls->first;
+	lockstruct->ls_lockspace = ls;
+	lockstruct->ls_ops = &gdlm_ops;
+	lockstruct->ls_flags = 0;
+	lockstruct->ls_lvb_size = GDLM_LVB_SIZE;
+	return 0;
+
+out_kobj:
+	gdlm_kobject_release(ls);
+out_thread:
+	gdlm_release_threads(ls);
+out_free:
+	kfree(ls);
+out:
+	return error;
+}
+
+static void gdlm_unmount(void *lockspace)
+{
+	struct gdlm_ls *ls = lockspace;
+	int rv;
+
+	log_debug("unmount flags %lx", ls->flags);
+
+	/* FIXME: serialize unmount and withdraw in case they
+	   happen at once.  Also, if unmount follows withdraw,
+	   wait for withdraw to finish. */
+
+	if (test_bit(DFL_WITHDRAW, &ls->flags))
+		goto out;
+
+	gdlm_kobject_release(ls);
+	dlm_release_lockspace(ls->dlm_lockspace, 2);
+	gdlm_release_threads(ls);
+	rv = gdlm_release_all_locks(ls);
+	if (rv)
+		log_info("gdlm_unmount: %d stray locks freed", rv);
+out:
+	kfree(ls);
+}
+
+static void gdlm_recovery_done(void *lockspace, unsigned int jid,
+                               unsigned int message)
+{
+	struct gdlm_ls *ls = lockspace;
+	ls->recover_jid_done = jid;
+	ls->recover_jid_status = message;
+	kobject_uevent(&ls->kobj, KOBJ_CHANGE);
+}
+
+static void gdlm_others_may_mount(void *lockspace)
+{
+	struct gdlm_ls *ls = lockspace;
+	ls->first_done = 1;
+	kobject_uevent(&ls->kobj, KOBJ_CHANGE);
+}
+
+/* Userspace gets the offline uevent, blocks new gfs locks on
+   other mounters, and lets us know (sets WITHDRAW flag).  Then,
+   userspace leaves the mount group while we leave the lockspace. */
+
+static void gdlm_withdraw(void *lockspace)
+{
+	struct gdlm_ls *ls = lockspace;
+
+	kobject_uevent(&ls->kobj, KOBJ_OFFLINE);
+
+	wait_event_interruptible(ls->wait_control,
+				 test_bit(DFL_WITHDRAW, &ls->flags));
+
+	dlm_release_lockspace(ls->dlm_lockspace, 2);
+	gdlm_release_threads(ls);
+	gdlm_release_all_locks(ls);
+	gdlm_kobject_release(ls);
+}
+
+const struct lm_lockops gdlm_ops = {
+	.lm_proto_name = "lock_dlm",
+	.lm_mount = gdlm_mount,
+	.lm_others_may_mount = gdlm_others_may_mount,
+	.lm_unmount = gdlm_unmount,
+	.lm_withdraw = gdlm_withdraw,
+	.lm_get_lock = gdlm_get_lock,
+	.lm_put_lock = gdlm_put_lock,
+	.lm_lock = gdlm_lock,
+	.lm_unlock = gdlm_unlock,
+	.lm_plock = gdlm_plock,
+	.lm_punlock = gdlm_punlock,
+	.lm_plock_get = gdlm_plock_get,
+	.lm_cancel = gdlm_cancel,
+	.lm_hold_lvb = gdlm_hold_lvb,
+	.lm_unhold_lvb = gdlm_unhold_lvb,
+	.lm_recovery_done = gdlm_recovery_done,
+	.lm_owner = THIS_MODULE,
+};
+

fs/gfs2/locking/dlm/plock.c

@@ -0,0 +1,301 @@
+/*
+ * Copyright (C) 2005 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/miscdevice.h>
+#include <linux/lock_dlm_plock.h>
+
+#include "lock_dlm.h"
+
+
+static spinlock_t ops_lock;
+static struct list_head send_list;
+static struct list_head recv_list;
+static wait_queue_head_t send_wq;
+static wait_queue_head_t recv_wq;
+
+struct plock_op {
+	struct list_head list;
+	int done;
+	struct gdlm_plock_info info;
+};
+
+static inline void set_version(struct gdlm_plock_info *info)
+{
+	info->version[0] = GDLM_PLOCK_VERSION_MAJOR;
+	info->version[1] = GDLM_PLOCK_VERSION_MINOR;
+	info->version[2] = GDLM_PLOCK_VERSION_PATCH;
+}
+
+static int check_version(struct gdlm_plock_info *info)
+{
+	if ((GDLM_PLOCK_VERSION_MAJOR != info->version[0]) ||
+	    (GDLM_PLOCK_VERSION_MINOR < info->version[1])) {
+		log_error("plock device version mismatch: "
+			  "kernel (%u.%u.%u), user (%u.%u.%u)",
+			  GDLM_PLOCK_VERSION_MAJOR,
+			  GDLM_PLOCK_VERSION_MINOR,
+			  GDLM_PLOCK_VERSION_PATCH,
+			  info->version[0],
+			  info->version[1],
+			  info->version[2]);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void send_op(struct plock_op *op)
+{
+	set_version(&op->info);
+	INIT_LIST_HEAD(&op->list);
+	spin_lock(&ops_lock);
+	list_add_tail(&op->list, &send_list);
+	spin_unlock(&ops_lock);
+	wake_up(&send_wq);
+}
+
+int gdlm_plock(void *lockspace, struct lm_lockname *name,
+	       struct file *file, int cmd, struct file_lock *fl)
+{
+	struct gdlm_ls *ls = lockspace;
+	struct plock_op *op;
+	int rv;
+
+	op = kzalloc(sizeof(*op), GFP_KERNEL);
+	if (!op)
+		return -ENOMEM;
+
+	op->info.optype		= GDLM_PLOCK_OP_LOCK;
+	op->info.pid		= fl->fl_pid;
+	op->info.ex		= (fl->fl_type == F_WRLCK);
+	op->info.wait		= IS_SETLKW(cmd);
+	op->info.fsid		= ls->id;
+	op->info.number		= name->ln_number;
+	op->info.start		= fl->fl_start;
+	op->info.end		= fl->fl_end;
+	op->info.owner		= (__u64)(long) fl->fl_owner;
+
+	send_op(op);
+	wait_event(recv_wq, (op->done != 0));
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&op->list)) {
+		printk(KERN_INFO "plock op on list\n");
+		list_del(&op->list);
+	}
+	spin_unlock(&ops_lock);
+
+	rv = op->info.rv;
+
+	if (!rv) {
+		if (posix_lock_file_wait(file, fl) < 0)
+			log_error("gdlm_plock: vfs lock error %x,%llx",
+				  name->ln_type,
+				  (unsigned long long)name->ln_number);
+	}
+
+	kfree(op);
+	return rv;
+}
+
+int gdlm_punlock(void *lockspace, struct lm_lockname *name,
+		 struct file *file, struct file_lock *fl)
+{
+	struct gdlm_ls *ls = lockspace;
+	struct plock_op *op;
+	int rv;
+
+	op = kzalloc(sizeof(*op), GFP_KERNEL);
+	if (!op)
+		return -ENOMEM;
+
+	if (posix_lock_file_wait(file, fl) < 0)
+		log_error("gdlm_punlock: vfs unlock error %x,%llx",
+			  name->ln_type, (unsigned long long)name->ln_number);
+
+	op->info.optype		= GDLM_PLOCK_OP_UNLOCK;
+	op->info.pid		= fl->fl_pid;
+	op->info.fsid		= ls->id;
+	op->info.number		= name->ln_number;
+	op->info.start		= fl->fl_start;
+	op->info.end		= fl->fl_end;
+	op->info.owner		= (__u64)(long) fl->fl_owner;
+
+	send_op(op);
+	wait_event(recv_wq, (op->done != 0));
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&op->list)) {
+		printk(KERN_INFO "punlock op on list\n");
+		list_del(&op->list);
+	}
+	spin_unlock(&ops_lock);
+
+	rv = op->info.rv;
+
+	kfree(op);
+	return rv;
+}
+
+int gdlm_plock_get(void *lockspace, struct lm_lockname *name,
+		   struct file *file, struct file_lock *fl)
+{
+	struct gdlm_ls *ls = lockspace;
+	struct plock_op *op;
+	int rv;
+
+	op = kzalloc(sizeof(*op), GFP_KERNEL);
+	if (!op)
+		return -ENOMEM;
+
+	op->info.optype		= GDLM_PLOCK_OP_GET;
+	op->info.pid		= fl->fl_pid;
+	op->info.ex		= (fl->fl_type == F_WRLCK);
+	op->info.fsid		= ls->id;
+	op->info.number		= name->ln_number;
+	op->info.start		= fl->fl_start;
+	op->info.end		= fl->fl_end;
+
+	send_op(op);
+	wait_event(recv_wq, (op->done != 0));
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&op->list)) {
+		printk(KERN_INFO "plock_get op on list\n");
+		list_del(&op->list);
+	}
+	spin_unlock(&ops_lock);
+
+	rv = op->info.rv;
+
+	if (rv == 0)
+		fl->fl_type = F_UNLCK;
+	else if (rv > 0) {
+		fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK;
+		fl->fl_pid = op->info.pid;
+		fl->fl_start = op->info.start;
+		fl->fl_end = op->info.end;
+	}
+
+	kfree(op);
+	return rv;
+}
+
+/* a read copies out one plock request from the send list */
+static ssize_t dev_read(struct file *file, char __user *u, size_t count,
+			loff_t *ppos)
+{
+	struct gdlm_plock_info info;
+	struct plock_op *op = NULL;
+
+	if (count < sizeof(info))
+		return -EINVAL;
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&send_list)) {
+		op = list_entry(send_list.next, struct plock_op, list);
+		list_move(&op->list, &recv_list);
+		memcpy(&info, &op->info, sizeof(info));
+	}
+	spin_unlock(&ops_lock);
+
+	if (!op)
+		return -EAGAIN;
+
+	if (copy_to_user(u, &info, sizeof(info)))
+		return -EFAULT;
+	return sizeof(info);
+}
+
+/* a write copies in one plock result that should match a plock_op
+   on the recv list */
+static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
+			 loff_t *ppos)
+{
+	struct gdlm_plock_info info;
+	struct plock_op *op;
+	int found = 0;
+
+	if (count != sizeof(info))
+		return -EINVAL;
+
+	if (copy_from_user(&info, u, sizeof(info)))
+		return -EFAULT;
+
+	if (check_version(&info))
+		return -EINVAL;
+
+	spin_lock(&ops_lock);
+	list_for_each_entry(op, &recv_list, list) {
+		if (op->info.fsid == info.fsid && op->info.number == info.number &&
+		    op->info.owner == info.owner) {
+			list_del_init(&op->list);
+			found = 1;
+			op->done = 1;
+			memcpy(&op->info, &info, sizeof(info));
+			break;
+		}
+	}
+	spin_unlock(&ops_lock);
+
+	if (found)
+		wake_up(&recv_wq);
+	else
+		printk(KERN_INFO "gdlm dev_write no op %x %llx\n", info.fsid,
+			(unsigned long long)info.number);
+	return count;
+}
+
+static unsigned int dev_poll(struct file *file, poll_table *wait)
+{
+	poll_wait(file, &send_wq, wait);
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&send_list)) {
+		spin_unlock(&ops_lock);
+		return POLLIN | POLLRDNORM;
+	}
+	spin_unlock(&ops_lock);
+	return 0;
+}
+
+static struct file_operations dev_fops = {
+	.read    = dev_read,
+	.write   = dev_write,
+	.poll    = dev_poll,
+	.owner   = THIS_MODULE
+};
+
+static struct miscdevice plock_dev_misc = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = GDLM_PLOCK_MISC_NAME,
+	.fops = &dev_fops
+};
+
+int gdlm_plock_init(void)
+{
+	int rv;
+
+	spin_lock_init(&ops_lock);
+	INIT_LIST_HEAD(&send_list);
+	INIT_LIST_HEAD(&recv_list);
+	init_waitqueue_head(&send_wq);
+	init_waitqueue_head(&recv_wq);
+
+	rv = misc_register(&plock_dev_misc);
+	if (rv)
+		printk(KERN_INFO "gdlm_plock_init: misc_register failed %d",
+		       rv);
+	return rv;
+}
+
+void gdlm_plock_exit(void)
+{
+	if (misc_deregister(&plock_dev_misc) < 0)
+		printk(KERN_INFO "gdlm_plock_exit: misc_deregister failed");
+}
+

fs/gfs2/locking/dlm/sysfs.c

@@ -0,0 +1,226 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/ctype.h>
+#include <linux/stat.h>
+
+#include "lock_dlm.h"
+
+extern struct lm_lockops gdlm_ops;
+
+static ssize_t proto_name_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%s\n", gdlm_ops.lm_proto_name);
+}
+
+static ssize_t block_show(struct gdlm_ls *ls, char *buf)
+{
+	ssize_t ret;
+	int val = 0;
+
+	if (test_bit(DFL_BLOCK_LOCKS, &ls->flags))
+		val = 1;
+	ret = sprintf(buf, "%d\n", val);
+	return ret;
+}
+
+static ssize_t block_store(struct gdlm_ls *ls, const char *buf, size_t len)
+{
+	ssize_t ret = len;
+	int val;
+
+	val = simple_strtol(buf, NULL, 0);
+
+	if (val == 1)
+		set_bit(DFL_BLOCK_LOCKS, &ls->flags);
+	else if (val == 0) {
+		clear_bit(DFL_BLOCK_LOCKS, &ls->flags);
+		gdlm_submit_delayed(ls);
+	} else {
+		ret = -EINVAL;
+	}
+	return ret;
+}
+
+static ssize_t withdraw_show(struct gdlm_ls *ls, char *buf)
+{
+	ssize_t ret;
+	int val = 0;
+
+	if (test_bit(DFL_WITHDRAW, &ls->flags))
+		val = 1;
+	ret = sprintf(buf, "%d\n", val);
+	return ret;
+}
+
+static ssize_t withdraw_store(struct gdlm_ls *ls, const char *buf, size_t len)
+{
+	ssize_t ret = len;
+	int val;
+
+	val = simple_strtol(buf, NULL, 0);
+
+	if (val == 1)
+		set_bit(DFL_WITHDRAW, &ls->flags);
+	else
+		ret = -EINVAL;
+	wake_up(&ls->wait_control);
+	return ret;
+}
+
+static ssize_t id_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%u\n", ls->id);
+}
+
+static ssize_t jid_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%d\n", ls->jid);
+}
+
+static ssize_t first_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%d\n", ls->first);
+}
+
+static ssize_t first_done_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%d\n", ls->first_done);
+}
+
+static ssize_t recover_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%d\n", ls->recover_jid);
+}
+
+static ssize_t recover_store(struct gdlm_ls *ls, const char *buf, size_t len)
+{
+	ls->recover_jid = simple_strtol(buf, NULL, 0);
+	ls->fscb(ls->sdp, LM_CB_NEED_RECOVERY, &ls->recover_jid);
+	return len;
+}
+
+static ssize_t recover_done_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%d\n", ls->recover_jid_done);
+}
+
+static ssize_t recover_status_show(struct gdlm_ls *ls, char *buf)
+{
+	return sprintf(buf, "%d\n", ls->recover_jid_status);
+}
+
+struct gdlm_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct gdlm_ls *, char *);
+	ssize_t (*store)(struct gdlm_ls *, const char *, size_t);
+};
+
+#define GDLM_ATTR(_name,_mode,_show,_store) \
+static struct gdlm_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store)
+
+GDLM_ATTR(proto_name,     0444, proto_name_show,     NULL);
+GDLM_ATTR(block,          0644, block_show,          block_store);
+GDLM_ATTR(withdraw,       0644, withdraw_show,       withdraw_store);
+GDLM_ATTR(id,             0444, id_show,             NULL);
+GDLM_ATTR(jid,            0444, jid_show,            NULL);
+GDLM_ATTR(first,          0444, first_show,          NULL);
+GDLM_ATTR(first_done,     0444, first_done_show,     NULL);
+GDLM_ATTR(recover,        0644, recover_show,        recover_store);
+GDLM_ATTR(recover_done,   0444, recover_done_show,   NULL);
+GDLM_ATTR(recover_status, 0444, recover_status_show, NULL);
+
+static struct attribute *gdlm_attrs[] = {
+	&gdlm_attr_proto_name.attr,
+	&gdlm_attr_block.attr,
+	&gdlm_attr_withdraw.attr,
+	&gdlm_attr_id.attr,
+	&gdlm_attr_jid.attr,
+	&gdlm_attr_first.attr,
+	&gdlm_attr_first_done.attr,
+	&gdlm_attr_recover.attr,
+	&gdlm_attr_recover_done.attr,
+	&gdlm_attr_recover_status.attr,
+	NULL,
+};
+
+static ssize_t gdlm_attr_show(struct kobject *kobj, struct attribute *attr,
+			      char *buf)
+{
+	struct gdlm_ls *ls = container_of(kobj, struct gdlm_ls, kobj);
+	struct gdlm_attr *a = container_of(attr, struct gdlm_attr, attr);
+	return a->show ? a->show(ls, buf) : 0;
+}
+
+static ssize_t gdlm_attr_store(struct kobject *kobj, struct attribute *attr,
+			       const char *buf, size_t len)
+{
+	struct gdlm_ls *ls = container_of(kobj, struct gdlm_ls, kobj);
+	struct gdlm_attr *a = container_of(attr, struct gdlm_attr, attr);
+	return a->store ? a->store(ls, buf, len) : len;
+}
+
+static struct sysfs_ops gdlm_attr_ops = {
+	.show  = gdlm_attr_show,
+	.store = gdlm_attr_store,
+};
+
+static struct kobj_type gdlm_ktype = {
+	.default_attrs = gdlm_attrs,
+	.sysfs_ops     = &gdlm_attr_ops,
+};
+
+static struct kset gdlm_kset = {
+	.subsys = &kernel_subsys,
+	.kobj   = {.name = "lock_dlm",},
+	.ktype  = &gdlm_ktype,
+};
+
+int gdlm_kobject_setup(struct gdlm_ls *ls, struct kobject *fskobj)
+{
+	int error;
+
+	error = kobject_set_name(&ls->kobj, "%s", "lock_module");
+	if (error) {
+		log_error("can't set kobj name %d", error);
+		return error;
+	}
+
+	ls->kobj.kset = &gdlm_kset;
+	ls->kobj.ktype = &gdlm_ktype;
+	ls->kobj.parent = fskobj;
+
+	error = kobject_register(&ls->kobj);
+	if (error)
+		log_error("can't register kobj %d", error);
+
+	return error;
+}
+
+void gdlm_kobject_release(struct gdlm_ls *ls)
+{
+	kobject_unregister(&ls->kobj);
+}
+
+int gdlm_sysfs_init(void)
+{
+	int error;
+
+	error = kset_register(&gdlm_kset);
+	if (error)
+		printk("lock_dlm: cannot register kset %d\n", error);
+
+	return error;
+}
+
+void gdlm_sysfs_exit(void)
+{
+	kset_unregister(&gdlm_kset);
+}
+

fs/gfs2/locking/dlm/thread.c

@@ -0,0 +1,359 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include "lock_dlm.h"
+
+/* A lock placed on this queue is re-submitted to DLM as soon as the lock_dlm
+   thread gets to it. */
+
+static void queue_submit(struct gdlm_lock *lp)
+{
+	struct gdlm_ls *ls = lp->ls;
+
+	spin_lock(&ls->async_lock);
+	list_add_tail(&lp->delay_list, &ls->submit);
+	spin_unlock(&ls->async_lock);
+	wake_up(&ls->thread_wait);
+}
+
+static void process_blocking(struct gdlm_lock *lp, int bast_mode)
+{
+	struct gdlm_ls *ls = lp->ls;
+	unsigned int cb = 0;
+
+	switch (gdlm_make_lmstate(bast_mode)) {
+	case LM_ST_EXCLUSIVE:
+		cb = LM_CB_NEED_E;
+		break;
+	case LM_ST_DEFERRED:
+		cb = LM_CB_NEED_D;
+		break;
+	case LM_ST_SHARED:
+		cb = LM_CB_NEED_S;
+		break;
+	default:
+		gdlm_assert(0, "unknown bast mode %u", lp->bast_mode);
+	}
+
+	ls->fscb(ls->sdp, cb, &lp->lockname);
+}
+
+static void process_complete(struct gdlm_lock *lp)
+{
+	struct gdlm_ls *ls = lp->ls;
+	struct lm_async_cb acb;
+	s16 prev_mode = lp->cur;
+
+	memset(&acb, 0, sizeof(acb));
+
+	if (lp->lksb.sb_status == -DLM_ECANCEL) {
+		log_info("complete dlm cancel %x,%llx flags %lx",
+		 	 lp->lockname.ln_type,
+			 (unsigned long long)lp->lockname.ln_number,
+			 lp->flags);
+
+		lp->req = lp->cur;
+		acb.lc_ret |= LM_OUT_CANCELED;
+		if (lp->cur == DLM_LOCK_IV)
+			lp->lksb.sb_lkid = 0;
+		goto out;
+	}
+
+	if (test_and_clear_bit(LFL_DLM_UNLOCK, &lp->flags)) {
+		if (lp->lksb.sb_status != -DLM_EUNLOCK) {
+			log_info("unlock sb_status %d %x,%llx flags %lx",
+				 lp->lksb.sb_status, lp->lockname.ln_type,
+				 (unsigned long long)lp->lockname.ln_number,
+				 lp->flags);
+			return;
+		}
+
+		lp->cur = DLM_LOCK_IV;
+		lp->req = DLM_LOCK_IV;
+		lp->lksb.sb_lkid = 0;
+
+		if (test_and_clear_bit(LFL_UNLOCK_DELETE, &lp->flags)) {
+			gdlm_delete_lp(lp);
+			return;
+		}
+		goto out;
+	}
+
+	if (lp->lksb.sb_flags & DLM_SBF_VALNOTVALID)
+		memset(lp->lksb.sb_lvbptr, 0, GDLM_LVB_SIZE);
+
+	if (lp->lksb.sb_flags & DLM_SBF_ALTMODE) {
+		if (lp->req == DLM_LOCK_PR)
+			lp->req = DLM_LOCK_CW;
+		else if (lp->req == DLM_LOCK_CW)
+			lp->req = DLM_LOCK_PR;
+	}
+
+	/*
+	 * A canceled lock request.  The lock was just taken off the delayed
+	 * list and was never even submitted to dlm.
+	 */
+
+	if (test_and_clear_bit(LFL_CANCEL, &lp->flags)) {
+		log_info("complete internal cancel %x,%llx",
+		 	 lp->lockname.ln_type,
+			 (unsigned long long)lp->lockname.ln_number);
+		lp->req = lp->cur;
+		acb.lc_ret |= LM_OUT_CANCELED;
+		goto out;
+	}
+
+	/*
+	 * An error occured.
+	 */
+
+	if (lp->lksb.sb_status) {
+		/* a "normal" error */
+		if ((lp->lksb.sb_status == -EAGAIN) &&
+		    (lp->lkf & DLM_LKF_NOQUEUE)) {
+			lp->req = lp->cur;
+			if (lp->cur == DLM_LOCK_IV)
+				lp->lksb.sb_lkid = 0;
+			goto out;
+		}
+
+		/* this could only happen with cancels I think */
+		log_info("ast sb_status %d %x,%llx flags %lx",
+			 lp->lksb.sb_status, lp->lockname.ln_type,
+			 (unsigned long long)lp->lockname.ln_number,
+			 lp->flags);
+		return;
+	}
+
+	/*
+	 * This is an AST for an EX->EX conversion for sync_lvb from GFS.
+	 */
+
+	if (test_and_clear_bit(LFL_SYNC_LVB, &lp->flags)) {
+		complete(&lp->ast_wait);
+		return;
+	}
+
+	/*
+	 * A lock has been demoted to NL because it initially completed during
+	 * BLOCK_LOCKS.  Now it must be requested in the originally requested
+	 * mode.
+	 */
+
+	if (test_and_clear_bit(LFL_REREQUEST, &lp->flags)) {
+		gdlm_assert(lp->req == DLM_LOCK_NL, "%x,%llx",
+			    lp->lockname.ln_type,
+			    (unsigned long long)lp->lockname.ln_number);
+		gdlm_assert(lp->prev_req > DLM_LOCK_NL, "%x,%llx",
+			    lp->lockname.ln_type,
+			    (unsigned long long)lp->lockname.ln_number);
+
+		lp->cur = DLM_LOCK_NL;
+		lp->req = lp->prev_req;
+		lp->prev_req = DLM_LOCK_IV;
+		lp->lkf &= ~DLM_LKF_CONVDEADLK;
+
+		set_bit(LFL_NOCACHE, &lp->flags);
+
+		if (test_bit(DFL_BLOCK_LOCKS, &ls->flags) &&
+		    !test_bit(LFL_NOBLOCK, &lp->flags))
+			gdlm_queue_delayed(lp);
+		else
+			queue_submit(lp);
+		return;
+	}
+
+	/*
+	 * A request is granted during dlm recovery.  It may be granted
+	 * because the locks of a failed node were cleared.  In that case,
+	 * there may be inconsistent data beneath this lock and we must wait
+	 * for recovery to complete to use it.  When gfs recovery is done this
+	 * granted lock will be converted to NL and then reacquired in this
+	 * granted state.
+	 */
+
+	if (test_bit(DFL_BLOCK_LOCKS, &ls->flags) &&
+	    !test_bit(LFL_NOBLOCK, &lp->flags) &&
+	    lp->req != DLM_LOCK_NL) {
+
+		lp->cur = lp->req;
+		lp->prev_req = lp->req;
+		lp->req = DLM_LOCK_NL;
+		lp->lkf |= DLM_LKF_CONVERT;
+		lp->lkf &= ~DLM_LKF_CONVDEADLK;
+
+		log_debug("rereq %x,%llx id %x %d,%d",
+			  lp->lockname.ln_type,
+			  (unsigned long long)lp->lockname.ln_number,
+			  lp->lksb.sb_lkid, lp->cur, lp->req);
+
+		set_bit(LFL_REREQUEST, &lp->flags);
+		queue_submit(lp);
+		return;
+	}
+
+	/*
+	 * DLM demoted the lock to NL before it was granted so GFS must be
+	 * told it cannot cache data for this lock.
+	 */
+
+	if (lp->lksb.sb_flags & DLM_SBF_DEMOTED)
+		set_bit(LFL_NOCACHE, &lp->flags);
+
+out:
+	/*
+	 * This is an internal lock_dlm lock
+	 */
+
+	if (test_bit(LFL_INLOCK, &lp->flags)) {
+		clear_bit(LFL_NOBLOCK, &lp->flags);
+		lp->cur = lp->req;
+		complete(&lp->ast_wait);
+		return;
+	}
+
+	/*
+	 * Normal completion of a lock request.  Tell GFS it now has the lock.
+	 */
+
+	clear_bit(LFL_NOBLOCK, &lp->flags);
+	lp->cur = lp->req;
+
+	acb.lc_name = lp->lockname;
+	acb.lc_ret |= gdlm_make_lmstate(lp->cur);
+
+	if (!test_and_clear_bit(LFL_NOCACHE, &lp->flags) &&
+	    (lp->cur > DLM_LOCK_NL) && (prev_mode > DLM_LOCK_NL))
+		acb.lc_ret |= LM_OUT_CACHEABLE;
+
+	ls->fscb(ls->sdp, LM_CB_ASYNC, &acb);
+}
+
+static inline int no_work(struct gdlm_ls *ls, int blocking)
+{
+	int ret;
+
+	spin_lock(&ls->async_lock);
+	ret = list_empty(&ls->complete) && list_empty(&ls->submit);
+	if (ret && blocking)
+		ret = list_empty(&ls->blocking);
+	spin_unlock(&ls->async_lock);
+
+	return ret;
+}
+
+static inline int check_drop(struct gdlm_ls *ls)
+{
+	if (!ls->drop_locks_count)
+		return 0;
+
+	if (time_after(jiffies, ls->drop_time + ls->drop_locks_period * HZ)) {
+		ls->drop_time = jiffies;
+		if (ls->all_locks_count >= ls->drop_locks_count)
+			return 1;
+	}
+	return 0;
+}
+
+static int gdlm_thread(void *data)
+{
+	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);
+		add_wait_queue(&ls->thread_wait, &wait);
+		if (no_work(ls, blist))
+			schedule();
+		remove_wait_queue(&ls->thread_wait, &wait);
+		set_current_state(TASK_RUNNING);
+
+		complete = blocking = submit = drop = 0;
+
+		spin_lock(&ls->async_lock);
+
+		if (blist && !list_empty(&ls->blocking)) {
+			lp = list_entry(ls->blocking.next, struct gdlm_lock,
+					blist);
+			list_del_init(&lp->blist);
+			blocking = lp->bast_mode;
+			lp->bast_mode = 0;
+		} else if (!list_empty(&ls->complete)) {
+			lp = list_entry(ls->complete.next, struct gdlm_lock,
+					clist);
+			list_del_init(&lp->clist);
+			complete = 1;
+		} else if (!list_empty(&ls->submit)) {
+			lp = list_entry(ls->submit.next, struct gdlm_lock,
+					delay_list);
+			list_del_init(&lp->delay_list);
+			submit = 1;
+		}
+
+		drop = check_drop(ls);
+		spin_unlock(&ls->async_lock);
+
+		if (complete)
+			process_complete(lp);
+
+		else if (blocking)
+			process_blocking(lp, blocking);
+
+		else if (submit)
+			gdlm_do_lock(lp);
+
+		if (drop)
+			ls->fscb(ls->sdp, LM_CB_DROPLOCKS, NULL);
+
+		schedule();
+	}
+
+	return 0;
+}
+
+int gdlm_init_threads(struct gdlm_ls *ls)
+{
+	struct task_struct *p;
+	int error;
+
+	p = kthread_run(gdlm_thread, ls, "lock_dlm1");
+	error = IS_ERR(p);
+	if (error) {
+		log_error("can't start lock_dlm1 thread %d", error);
+		return error;
+	}
+	ls->thread1 = p;
+
+	p = kthread_run(gdlm_thread, ls, "lock_dlm2");
+	error = IS_ERR(p);
+	if (error) {
+		log_error("can't start lock_dlm2 thread %d", error);
+		kthread_stop(ls->thread1);
+		return error;
+	}
+	ls->thread2 = p;
+
+	return 0;
+}
+
+void gdlm_release_threads(struct gdlm_ls *ls)
+{
+	kthread_stop(ls->thread1);
+	kthread_stop(ls->thread2);
+}
+

fs/gfs2/locking/nolock/Makefile

@@ -0,0 +1,3 @@
+obj-$(CONFIG_GFS2_FS_LOCKING_NOLOCK) += lock_nolock.o
+lock_nolock-y := main.o
+

fs/gfs2/locking/nolock/main.c

@@ -0,0 +1,246 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/smp_lock.h>
+#include <linux/lm_interface.h>
+
+struct nolock_lockspace {
+	unsigned int nl_lvb_size;
+};
+
+static const struct lm_lockops nolock_ops;
+
+static int nolock_mount(char *table_name, char *host_data,
+			lm_callback_t cb, void *cb_data,
+			unsigned int min_lvb_size, int flags,
+			struct lm_lockstruct *lockstruct,
+			struct kobject *fskobj)
+{
+	char *c;
+	unsigned int jid;
+	struct nolock_lockspace *nl;
+
+	c = strstr(host_data, "jid=");
+	if (!c)
+		jid = 0;
+	else {
+		c += 4;
+		sscanf(c, "%u", &jid);
+	}
+
+	nl = kzalloc(sizeof(struct nolock_lockspace), GFP_KERNEL);
+	if (!nl)
+		return -ENOMEM;
+
+	nl->nl_lvb_size = min_lvb_size;
+
+	lockstruct->ls_jid = jid;
+	lockstruct->ls_first = 1;
+	lockstruct->ls_lvb_size = min_lvb_size;
+	lockstruct->ls_lockspace = nl;
+	lockstruct->ls_ops = &nolock_ops;
+	lockstruct->ls_flags = LM_LSFLAG_LOCAL;
+
+	return 0;
+}
+
+static void nolock_others_may_mount(void *lockspace)
+{
+}
+
+static void nolock_unmount(void *lockspace)
+{
+	struct nolock_lockspace *nl = lockspace;
+	kfree(nl);
+}
+
+static void nolock_withdraw(void *lockspace)
+{
+}
+
+/**
+ * nolock_get_lock - get a lm_lock_t given a descripton of the lock
+ * @lockspace: the lockspace the lock lives in
+ * @name: the name of the lock
+ * @lockp: return the lm_lock_t here
+ *
+ * Returns: 0 on success, -EXXX on failure
+ */
+
+static int nolock_get_lock(void *lockspace, struct lm_lockname *name,
+			   void **lockp)
+{
+	*lockp = lockspace;
+	return 0;
+}
+
+/**
+ * nolock_put_lock - get rid of a lock structure
+ * @lock: the lock to throw away
+ *
+ */
+
+static void nolock_put_lock(void *lock)
+{
+}
+
+/**
+ * nolock_lock - acquire a lock
+ * @lock: the lock to manipulate
+ * @cur_state: the current state
+ * @req_state: the requested state
+ * @flags: modifier flags
+ *
+ * Returns: A bitmap of LM_OUT_*
+ */
+
+static unsigned int nolock_lock(void *lock, unsigned int cur_state,
+				unsigned int req_state, unsigned int flags)
+{
+	return req_state | LM_OUT_CACHEABLE;
+}
+
+/**
+ * nolock_unlock - unlock a lock
+ * @lock: the lock to manipulate
+ * @cur_state: the current state
+ *
+ * Returns: 0
+ */
+
+static unsigned int nolock_unlock(void *lock, unsigned int cur_state)
+{
+	return 0;
+}
+
+static void nolock_cancel(void *lock)
+{
+}
+
+/**
+ * nolock_hold_lvb - hold on to a lock value block
+ * @lock: the lock the LVB is associated with
+ * @lvbp: return the lm_lvb_t here
+ *
+ * Returns: 0 on success, -EXXX on failure
+ */
+
+static int nolock_hold_lvb(void *lock, char **lvbp)
+{
+	struct nolock_lockspace *nl = lock;
+	int error = 0;
+
+	*lvbp = kzalloc(nl->nl_lvb_size, GFP_KERNEL);
+	if (!*lvbp)
+		error = -ENOMEM;
+
+	return error;
+}
+
+/**
+ * nolock_unhold_lvb - release a LVB
+ * @lock: the lock the LVB is associated with
+ * @lvb: the lock value block
+ *
+ */
+
+static void nolock_unhold_lvb(void *lock, char *lvb)
+{
+	kfree(lvb);
+}
+
+static int nolock_plock_get(void *lockspace, struct lm_lockname *name,
+			    struct file *file, struct file_lock *fl)
+{
+	struct file_lock tmp;
+	int ret;
+
+	ret = posix_test_lock(file, fl, &tmp);
+	fl->fl_type = F_UNLCK;
+	if (ret)
+		memcpy(fl, &tmp, sizeof(struct file_lock));
+
+	return 0;
+}
+
+static int nolock_plock(void *lockspace, struct lm_lockname *name,
+			struct file *file, int cmd, struct file_lock *fl)
+{
+	int error;
+	error = posix_lock_file_wait(file, fl);
+	return error;
+}
+
+static int nolock_punlock(void *lockspace, struct lm_lockname *name,
+			  struct file *file, struct file_lock *fl)
+{
+	int error;
+	error = posix_lock_file_wait(file, fl);
+	return error;
+}
+
+static void nolock_recovery_done(void *lockspace, unsigned int jid,
+				 unsigned int message)
+{
+}
+
+static const struct lm_lockops nolock_ops = {
+	.lm_proto_name = "lock_nolock",
+	.lm_mount = nolock_mount,
+	.lm_others_may_mount = nolock_others_may_mount,
+	.lm_unmount = nolock_unmount,
+	.lm_withdraw = nolock_withdraw,
+	.lm_get_lock = nolock_get_lock,
+	.lm_put_lock = nolock_put_lock,
+	.lm_lock = nolock_lock,
+	.lm_unlock = nolock_unlock,
+	.lm_cancel = nolock_cancel,
+	.lm_hold_lvb = nolock_hold_lvb,
+	.lm_unhold_lvb = nolock_unhold_lvb,
+	.lm_plock_get = nolock_plock_get,
+	.lm_plock = nolock_plock,
+	.lm_punlock = nolock_punlock,
+	.lm_recovery_done = nolock_recovery_done,
+	.lm_owner = THIS_MODULE,
+};
+
+static int __init init_nolock(void)
+{
+	int error;
+
+	error = gfs2_register_lockproto(&nolock_ops);
+	if (error) {
+		printk(KERN_WARNING
+		       "lock_nolock: can't register protocol: %d\n", error);
+		return error;
+	}
+
+	printk(KERN_INFO
+	       "Lock_Nolock (built %s %s) installed\n", __DATE__, __TIME__);
+	return 0;
+}
+
+static void __exit exit_nolock(void)
+{
+	gfs2_unregister_lockproto(&nolock_ops);
+}
+
+module_init(init_nolock);
+module_exit(exit_nolock);
+
+MODULE_DESCRIPTION("GFS Nolock Locking Module");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+

fs/gfs2/log.c

@@ -0,0 +1,687 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "log.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "util.h"
+#include "dir.h"
+
+#define PULL 1
+
+/**
+ * gfs2_struct2blk - compute stuff
+ * @sdp: the filesystem
+ * @nstruct: the number of structures
+ * @ssize: the size of the structures
+ *
+ * Compute the number of log descriptor blocks needed to hold a certain number
+ * of structures of a certain size.
+ *
+ * Returns: the number of blocks needed (minimum is always 1)
+ */
+
+unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
+			     unsigned int ssize)
+{
+	unsigned int blks;
+	unsigned int first, second;
+
+	blks = 1;
+	first = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / ssize;
+
+	if (nstruct > first) {
+		second = (sdp->sd_sb.sb_bsize -
+			  sizeof(struct gfs2_meta_header)) / ssize;
+		blks += DIV_ROUND_UP(nstruct - first, second);
+	}
+
+	return blks;
+}
+
+/**
+ * gfs2_ail1_start_one - Start I/O on a part of the AIL
+ * @sdp: the filesystem
+ * @tr: the part of the AIL
+ *
+ */
+
+static void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct gfs2_bufdata *bd, *s;
+	struct buffer_head *bh;
+	int retry;
+
+	BUG_ON(!spin_is_locked(&sdp->sd_log_lock));
+
+	do {
+		retry = 0;
+
+		list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list,
+						 bd_ail_st_list) {
+			bh = bd->bd_bh;
+
+			gfs2_assert(sdp, bd->bd_ail == ai);
+
+			if (!buffer_busy(bh)) {
+				if (!buffer_uptodate(bh)) {
+					gfs2_log_unlock(sdp);
+					gfs2_io_error_bh(sdp, bh);
+					gfs2_log_lock(sdp);
+				}
+				list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
+				continue;
+			}
+
+			if (!buffer_dirty(bh))
+				continue;
+
+			list_move(&bd->bd_ail_st_list, &ai->ai_ail1_list);
+
+			gfs2_log_unlock(sdp);
+			wait_on_buffer(bh);
+			ll_rw_block(WRITE, 1, &bh);
+			gfs2_log_lock(sdp);
+
+			retry = 1;
+			break;
+		}
+	} while (retry);
+}
+
+/**
+ * gfs2_ail1_empty_one - Check whether or not a trans in the AIL has been synced
+ * @sdp: the filesystem
+ * @ai: the AIL entry
+ *
+ */
+
+static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai, int flags)
+{
+	struct gfs2_bufdata *bd, *s;
+	struct buffer_head *bh;
+
+	list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list,
+					 bd_ail_st_list) {
+		bh = bd->bd_bh;
+
+		gfs2_assert(sdp, bd->bd_ail == ai);
+
+		if (buffer_busy(bh)) {
+			if (flags & DIO_ALL)
+				continue;
+			else
+				break;
+		}
+
+		if (!buffer_uptodate(bh))
+			gfs2_io_error_bh(sdp, bh);
+
+		list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
+	}
+
+	return list_empty(&ai->ai_ail1_list);
+}
+
+void gfs2_ail1_start(struct gfs2_sbd *sdp, int flags)
+{
+	struct list_head *head = &sdp->sd_ail1_list;
+	u64 sync_gen;
+	struct list_head *first;
+	struct gfs2_ail *first_ai, *ai, *tmp;
+	int done = 0;
+
+	gfs2_log_lock(sdp);
+	if (list_empty(head)) {
+		gfs2_log_unlock(sdp);
+		return;
+	}
+	sync_gen = sdp->sd_ail_sync_gen++;
+
+	first = head->prev;
+	first_ai = list_entry(first, struct gfs2_ail, ai_list);
+	first_ai->ai_sync_gen = sync_gen;
+	gfs2_ail1_start_one(sdp, first_ai); /* This may drop log lock */
+
+	if (flags & DIO_ALL)
+		first = NULL;
+
+	while(!done) {
+		if (first && (head->prev != first ||
+			      gfs2_ail1_empty_one(sdp, first_ai, 0)))
+			break;
+
+		done = 1;
+		list_for_each_entry_safe_reverse(ai, tmp, head, ai_list) {
+			if (ai->ai_sync_gen >= sync_gen)
+				continue;
+			ai->ai_sync_gen = sync_gen;
+			gfs2_ail1_start_one(sdp, ai); /* This may drop log lock */
+			done = 0;
+			break;
+		}
+	}
+
+	gfs2_log_unlock(sdp);
+}
+
+int gfs2_ail1_empty(struct gfs2_sbd *sdp, int flags)
+{
+	struct gfs2_ail *ai, *s;
+	int ret;
+
+	gfs2_log_lock(sdp);
+
+	list_for_each_entry_safe_reverse(ai, s, &sdp->sd_ail1_list, ai_list) {
+		if (gfs2_ail1_empty_one(sdp, ai, flags))
+			list_move(&ai->ai_list, &sdp->sd_ail2_list);
+		else if (!(flags & DIO_ALL))
+			break;
+	}
+
+	ret = list_empty(&sdp->sd_ail1_list);
+
+	gfs2_log_unlock(sdp);
+
+	return ret;
+}
+
+
+/**
+ * gfs2_ail2_empty_one - Check whether or not a trans in the AIL has been synced
+ * @sdp: the filesystem
+ * @ai: the AIL entry
+ *
+ */
+
+static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct list_head *head = &ai->ai_ail2_list;
+	struct gfs2_bufdata *bd;
+
+	while (!list_empty(head)) {
+		bd = list_entry(head->prev, struct gfs2_bufdata,
+				bd_ail_st_list);
+		gfs2_assert(sdp, bd->bd_ail == ai);
+		bd->bd_ail = NULL;
+		list_del(&bd->bd_ail_st_list);
+		list_del(&bd->bd_ail_gl_list);
+		atomic_dec(&bd->bd_gl->gl_ail_count);
+		brelse(bd->bd_bh);
+	}
+}
+
+static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
+{
+	struct gfs2_ail *ai, *safe;
+	unsigned int old_tail = sdp->sd_log_tail;
+	int wrap = (new_tail < old_tail);
+	int a, b, rm;
+
+	gfs2_log_lock(sdp);
+
+	list_for_each_entry_safe(ai, safe, &sdp->sd_ail2_list, ai_list) {
+		a = (old_tail <= ai->ai_first);
+		b = (ai->ai_first < new_tail);
+		rm = (wrap) ? (a || b) : (a && b);
+		if (!rm)
+			continue;
+
+		gfs2_ail2_empty_one(sdp, ai);
+		list_del(&ai->ai_list);
+		gfs2_assert_warn(sdp, list_empty(&ai->ai_ail1_list));
+		gfs2_assert_warn(sdp, list_empty(&ai->ai_ail2_list));
+		kfree(ai);
+	}
+
+	gfs2_log_unlock(sdp);
+}
+
+/**
+ * gfs2_log_reserve - Make a log reservation
+ * @sdp: The GFS2 superblock
+ * @blks: The number of blocks to reserve
+ *
+ * Returns: errno
+ */
+
+int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
+{
+	unsigned int try = 0;
+
+	if (gfs2_assert_warn(sdp, blks) ||
+	    gfs2_assert_warn(sdp, blks <= sdp->sd_jdesc->jd_blocks))
+		return -EINVAL;
+
+	mutex_lock(&sdp->sd_log_reserve_mutex);
+	gfs2_log_lock(sdp);
+	while(sdp->sd_log_blks_free <= blks) {
+		gfs2_log_unlock(sdp);
+		gfs2_ail1_empty(sdp, 0);
+		gfs2_log_flush(sdp, NULL);
+
+		if (try++)
+			gfs2_ail1_start(sdp, 0);
+		gfs2_log_lock(sdp);
+	}
+	sdp->sd_log_blks_free -= blks;
+	gfs2_log_unlock(sdp);
+	mutex_unlock(&sdp->sd_log_reserve_mutex);
+
+	down_read(&sdp->sd_log_flush_lock);
+
+	return 0;
+}
+
+/**
+ * gfs2_log_release - Release a given number of log blocks
+ * @sdp: The GFS2 superblock
+ * @blks: The number of blocks
+ *
+ */
+
+void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
+{
+
+	gfs2_log_lock(sdp);
+	sdp->sd_log_blks_free += blks;
+	gfs2_assert_withdraw(sdp,
+			     sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks);
+	gfs2_log_unlock(sdp);
+	up_read(&sdp->sd_log_flush_lock);
+}
+
+static u64 log_bmap(struct gfs2_sbd *sdp, unsigned int lbn)
+{
+	int error;
+	struct buffer_head bh_map;
+
+	error = gfs2_block_map(sdp->sd_jdesc->jd_inode, lbn, 0, &bh_map, 1);
+	if (error || !bh_map.b_blocknr)
+		printk(KERN_INFO "error=%d, dbn=%llu lbn=%u", error, bh_map.b_blocknr, lbn);
+	gfs2_assert_withdraw(sdp, !error && bh_map.b_blocknr);
+
+	return bh_map.b_blocknr;
+}
+
+/**
+ * log_distance - Compute distance between two journal blocks
+ * @sdp: The GFS2 superblock
+ * @newer: The most recent journal block of the pair
+ * @older: The older journal block of the pair
+ *
+ *   Compute the distance (in the journal direction) between two
+ *   blocks in the journal
+ *
+ * Returns: the distance in blocks
+ */
+
+static inline unsigned int log_distance(struct gfs2_sbd *sdp, unsigned int newer,
+					unsigned int older)
+{
+	int dist;
+
+	dist = newer - older;
+	if (dist < 0)
+		dist += sdp->sd_jdesc->jd_blocks;
+
+	return dist;
+}
+
+static unsigned int current_tail(struct gfs2_sbd *sdp)
+{
+	struct gfs2_ail *ai;
+	unsigned int tail;
+
+	gfs2_log_lock(sdp);
+
+	if (list_empty(&sdp->sd_ail1_list)) {
+		tail = sdp->sd_log_head;
+	} else {
+		ai = list_entry(sdp->sd_ail1_list.prev, struct gfs2_ail, ai_list);
+		tail = ai->ai_first;
+	}
+
+	gfs2_log_unlock(sdp);
+
+	return tail;
+}
+
+static inline void log_incr_head(struct gfs2_sbd *sdp)
+{
+	if (sdp->sd_log_flush_head == sdp->sd_log_tail)
+		gfs2_assert_withdraw(sdp, sdp->sd_log_flush_head == sdp->sd_log_head);
+
+	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_get_buf - Get and initialize a buffer to use for log control data
+ * @sdp: The GFS2 superblock
+ *
+ * Returns: the buffer_head
+ */
+
+struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp)
+{
+	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
+	struct 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);
+	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);
+
+	return bh;
+}
+
+/**
+ * gfs2_log_fake_buf - Build a fake buffer head to write metadata buffer to log
+ * @sdp: the filesystem
+ * @data: the data the buffer_head should point to
+ *
+ * Returns: the log buffer descriptor
+ */
+
+struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
+				      struct buffer_head *real)
+{
+	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
+	struct 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);
+	atomic_set(&bh->b_count, 1);
+	bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate);
+	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;
+
+	log_incr_head(sdp);
+
+	return bh;
+}
+
+static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail, int pull)
+{
+	unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail);
+
+	ail2_empty(sdp, new_tail);
+
+	gfs2_log_lock(sdp);
+	sdp->sd_log_blks_free += dist - (pull ? 1 : 0);
+	gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks);
+	gfs2_log_unlock(sdp);
+
+	sdp->sd_log_tail = new_tail;
+}
+
+/**
+ * log_write_header - Get and initialize a journal header buffer
+ * @sdp: The GFS2 superblock
+ *
+ * Returns: the initialized log buffer descriptor
+ */
+
+static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
+{
+	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
+	struct buffer_head *bh;
+	struct gfs2_log_header *lh;
+	unsigned int tail;
+	u32 hash;
+
+	bh = sb_getblk(sdp->sd_vfs, blkno);
+	lock_buffer(bh);
+	memset(bh->b_data, 0, bh->b_size);
+	set_buffer_uptodate(bh);
+	clear_buffer_dirty(bh);
+	unlock_buffer(bh);
+
+	gfs2_ail1_empty(sdp, 0);
+	tail = current_tail(sdp);
+
+	lh = (struct gfs2_log_header *)bh->b_data;
+	memset(lh, 0, sizeof(struct gfs2_log_header));
+	lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+	lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH);
+	lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH);
+	lh->lh_sequence = cpu_to_be64(sdp->sd_log_sequence++);
+	lh->lh_flags = cpu_to_be32(flags);
+	lh->lh_tail = cpu_to_be32(tail);
+	lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head);
+	hash = gfs2_disk_hash(bh->b_data, sizeof(struct gfs2_log_header));
+	lh->lh_hash = cpu_to_be32(hash);
+
+	set_buffer_dirty(bh);
+	if (sync_dirty_buffer(bh))
+		gfs2_io_error_bh(sdp, bh);
+	brelse(bh);
+
+	if (sdp->sd_log_tail != tail)
+		log_pull_tail(sdp, tail, pull);
+	else
+		gfs2_assert_withdraw(sdp, !pull);
+
+	sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
+	log_incr_head(sdp);
+}
+
+static void log_flush_commit(struct gfs2_sbd *sdp)
+{
+	struct list_head *head = &sdp->sd_log_flush_list;
+	struct gfs2_log_buf *lb;
+	struct buffer_head *bh;
+
+	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
+			brelse(bh);
+		kfree(lb);
+	}
+
+	log_write_header(sdp, 0, 0);
+}
+
+/**
+ * gfs2_log_flush - flush incore transaction(s)
+ * @sdp: the filesystem
+ * @gl: The glock structure to flush.  If NULL, flush the whole incore log
+ *
+ */
+
+void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
+{
+	struct gfs2_ail *ai;
+
+	down_write(&sdp->sd_log_flush_lock);
+
+	if (gl) {
+		gfs2_log_lock(sdp);
+		if (list_empty(&gl->gl_le.le_list)) {
+			gfs2_log_unlock(sdp);
+			up_write(&sdp->sd_log_flush_lock);
+			return;
+		}
+		gfs2_log_unlock(sdp);
+	}
+
+	ai = kzalloc(sizeof(struct gfs2_ail), GFP_NOFS | __GFP_NOFAIL);
+	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_commited_buf);
+	gfs2_assert_withdraw(sdp,
+			sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke);
+
+	sdp->sd_log_flush_head = sdp->sd_log_head;
+	sdp->sd_log_flush_wrapped = 0;
+	ai->ai_first = sdp->sd_log_flush_head;
+
+	lops_before_commit(sdp);
+	if (!list_empty(&sdp->sd_log_flush_list))
+		log_flush_commit(sdp);
+	else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle)
+		log_write_header(sdp, 0, PULL);
+	lops_after_commit(sdp, ai);
+	sdp->sd_log_head = sdp->sd_log_flush_head;
+
+	sdp->sd_log_blks_free -= sdp->sd_log_num_hdrs;
+
+	sdp->sd_log_blks_reserved = 0;
+	sdp->sd_log_commited_buf = 0;
+	sdp->sd_log_num_hdrs = 0;
+	sdp->sd_log_commited_revoke = 0;
+
+	gfs2_log_lock(sdp);
+	if (!list_empty(&ai->ai_ail1_list)) {
+		list_add(&ai->ai_list, &sdp->sd_ail1_list);
+		ai = NULL;
+	}
+	gfs2_log_unlock(sdp);
+
+	sdp->sd_vfs->s_dirt = 0;
+	up_write(&sdp->sd_log_flush_lock);
+
+	kfree(ai);
+}
+
+static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	unsigned int reserved = 0;
+	unsigned int old;
+
+	gfs2_log_lock(sdp);
+
+	sdp->sd_log_commited_buf += tr->tr_num_buf_new - tr->tr_num_buf_rm;
+	gfs2_assert_withdraw(sdp, ((int)sdp->sd_log_commited_buf) >= 0);
+	sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
+	gfs2_assert_withdraw(sdp, ((int)sdp->sd_log_commited_revoke) >= 0);
+
+	if (sdp->sd_log_commited_buf)
+		reserved += sdp->sd_log_commited_buf;
+	if (sdp->sd_log_commited_revoke)
+		reserved += gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke,
+					    sizeof(u64));
+	if (reserved)
+		reserved++;
+
+	old = sdp->sd_log_blks_free;
+	sdp->sd_log_blks_free += tr->tr_reserved -
+				 (reserved - sdp->sd_log_blks_reserved);
+
+	gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free >= old);
+	gfs2_assert_withdraw(sdp,
+			     sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks +
+			     sdp->sd_log_num_hdrs);
+
+	sdp->sd_log_blks_reserved = reserved;
+
+	gfs2_log_unlock(sdp);
+}
+
+/**
+ * gfs2_log_commit - Commit a transaction to the log
+ * @sdp: the filesystem
+ * @tr: the transaction
+ *
+ * Returns: errno
+ */
+
+void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	log_refund(sdp, tr);
+	lops_incore_commit(sdp, tr);
+
+	sdp->sd_vfs->s_dirt = 1;
+	up_read(&sdp->sd_log_flush_lock);
+
+	gfs2_log_lock(sdp);
+	if (sdp->sd_log_num_buf > gfs2_tune_get(sdp, gt_incore_log_blocks)) {
+		gfs2_log_unlock(sdp);
+		gfs2_log_flush(sdp, NULL);
+	} else {
+		gfs2_log_unlock(sdp);
+	}
+}
+
+/**
+ * gfs2_log_shutdown - write a shutdown header into a journal
+ * @sdp: the filesystem
+ *
+ */
+
+void gfs2_log_shutdown(struct gfs2_sbd *sdp)
+{
+	down_write(&sdp->sd_log_flush_lock);
+
+	gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved);
+	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_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);
+	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_hdrs);
+	gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list));
+
+	sdp->sd_log_flush_head = sdp->sd_log_head;
+	sdp->sd_log_flush_wrapped = 0;
+
+	log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT, 0);
+
+	gfs2_assert_warn(sdp, sdp->sd_log_blks_free == sdp->sd_jdesc->jd_blocks);
+	gfs2_assert_warn(sdp, sdp->sd_log_head == sdp->sd_log_tail);
+	gfs2_assert_warn(sdp, list_empty(&sdp->sd_ail2_list));
+
+	sdp->sd_log_head = sdp->sd_log_flush_head;
+	sdp->sd_log_tail = sdp->sd_log_head;
+
+	up_write(&sdp->sd_log_flush_lock);
+}
+

fs/gfs2/log.h

@@ -0,0 +1,65 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __LOG_DOT_H__
+#define __LOG_DOT_H__
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include "incore.h"
+
+/**
+ * gfs2_log_lock - acquire the right to mess with the log manager
+ * @sdp: the filesystem
+ *
+ */
+
+static inline void gfs2_log_lock(struct gfs2_sbd *sdp)
+{
+	spin_lock(&sdp->sd_log_lock);
+}
+
+/**
+ * gfs2_log_unlock - release the right to mess with the log manager
+ * @sdp: the filesystem
+ *
+ */
+
+static inline void gfs2_log_unlock(struct gfs2_sbd *sdp)
+{
+	spin_unlock(&sdp->sd_log_lock);
+}
+
+static inline void gfs2_log_pointers_init(struct gfs2_sbd *sdp,
+					  unsigned int value)
+{
+	if (++value == sdp->sd_jdesc->jd_blocks) {
+		value = 0;
+	}
+	sdp->sd_log_head = sdp->sd_log_tail = value;
+}
+
+unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
+			    unsigned int ssize);
+
+void gfs2_ail1_start(struct gfs2_sbd *sdp, int flags);
+int gfs2_ail1_empty(struct gfs2_sbd *sdp, int flags);
+
+int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks);
+void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks);
+
+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_log_shutdown(struct gfs2_sbd *sdp);
+
+#endif /* __LOG_DOT_H__ */

fs/gfs2/lops.c

@@ -0,0 +1,809 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "log.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "recovery.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+
+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;
+
+	tr->tr_touched = 1;
+
+	if (!list_empty(&le->le_list))
+		return;
+
+	gl = container_of(le, struct gfs2_glock, gl_le);
+	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(gl)))
+		return;
+	gfs2_glock_hold(gl);
+	set_bit(GLF_DIRTY, &gl->gl_flags);
+
+	gfs2_log_lock(sdp);
+	sdp->sd_log_num_gl++;
+	list_add(&le->le_list, &sdp->sd_log_le_gl);
+	gfs2_log_unlock(sdp);
+}
+
+static void glock_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct list_head *head = &sdp->sd_log_le_gl;
+	struct gfs2_glock *gl;
+
+	while (!list_empty(head)) {
+		gl = list_entry(head->next, struct gfs2_glock, gl_le.le_list);
+		list_del_init(&gl->gl_le.le_list);
+		sdp->sd_log_num_gl--;
+
+		gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(gl));
+		gfs2_glock_put(gl);
+	}
+	gfs2_assert_warn(sdp, !sdp->sd_log_num_gl);
+}
+
+static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+{
+	struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le);
+	struct gfs2_trans *tr;
+
+	if (!list_empty(&bd->bd_list_tr))
+		return;
+
+	tr = current->journal_info;
+	tr->tr_touched = 1;
+	tr->tr_num_buf++;
+	list_add(&bd->bd_list_tr, &tr->tr_list_buf);
+
+	if (!list_empty(&le->le_list))
+		return;
+
+	gfs2_trans_add_gl(bd->bd_gl);
+
+	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++;
+}
+
+static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	struct list_head *head = &tr->tr_list_buf;
+	struct gfs2_bufdata *bd;
+
+	while (!list_empty(head)) {
+		bd = list_entry(head->next, struct gfs2_bufdata, bd_list_tr);
+		list_del_init(&bd->bd_list_tr);
+		tr->tr_num_buf--;
+	}
+	gfs2_assert_warn(sdp, !tr->tr_num_buf);
+}
+
+static void buf_lo_before_commit(struct gfs2_sbd *sdp)
+{
+	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 = sizeof(struct gfs2_log_descriptor);
+	unsigned int limit;
+	unsigned int num;
+	unsigned n;
+	__be64 *ptr;
+
+	offset += sizeof(__be64) - 1;
+	offset &= ~(sizeof(__be64) - 1);
+	limit = (sdp->sd_sb.sb_bsize - offset)/sizeof(__be64);
+	/* for 4k blocks, limit = 503 */
+
+	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);
+		sdp->sd_log_num_hdrs++;
+		ld = (struct gfs2_log_descriptor *)bh->b_data;
+		ptr = (__be64 *)(bh->b_data + offset);
+		ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+		ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD);
+		ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD);
+		ld->ld_type = cpu_to_be32(GFS2_LOG_DESC_METADATA);
+		ld->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,
+					     bd_le.le_list) {
+			*ptr++ = cpu_to_be64(bd1->bd_bh->b_blocknr);
+			if (++n >= num)
+				break;
+		}
+
+		set_buffer_dirty(bh);
+		ll_rw_block(WRITE, 1, &bh);
+
+		n = 0;
+		list_for_each_entry_continue(bd2, &sdp->sd_log_le_buf,
+					     bd_le.le_list) {
+			bh = gfs2_log_fake_buf(sdp, bd2->bd_bh);
+			set_buffer_dirty(bh);
+			ll_rw_block(WRITE, 1, &bh);
+			if (++n >= num)
+				break;
+		}
+
+		total -= num;
+	}
+}
+
+static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct list_head *head = &sdp->sd_log_le_buf;
+	struct gfs2_bufdata *bd;
+
+	while (!list_empty(head)) {
+		bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list);
+		list_del_init(&bd->bd_le.le_list);
+		sdp->sd_log_num_buf--;
+
+		gfs2_unpin(sdp, bd->bd_bh, ai);
+	}
+	gfs2_assert_warn(sdp, !sdp->sd_log_num_buf);
+}
+
+static void buf_lo_before_scan(struct gfs2_jdesc *jd,
+			       struct gfs2_log_header *head, int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (pass != 0)
+		return;
+
+	sdp->sd_found_blocks = 0;
+	sdp->sd_replayed_blocks = 0;
+}
+
+static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				struct gfs2_log_descriptor *ld, __be64 *ptr,
+				int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	unsigned int blks = be32_to_cpu(ld->ld_data1);
+	struct buffer_head *bh_log, *bh_ip;
+	u64 blkno;
+	int error = 0;
+
+	if (pass != 1 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_METADATA)
+		return 0;
+
+	gfs2_replay_incr_blk(sdp, &start);
+
+	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
+		blkno = be64_to_cpu(*ptr++);
+
+		sdp->sd_found_blocks++;
+
+		if (gfs2_revoke_check(sdp, blkno, start))
+			continue;
+
+		error = gfs2_replay_read_block(jd, start, &bh_log);
+		if (error)
+			return error;
+
+		bh_ip = gfs2_meta_new(gl, blkno);
+		memcpy(bh_ip->b_data, bh_log->b_data, bh_log->b_size);
+
+		if (gfs2_meta_check(sdp, bh_ip))
+			error = -EIO;
+		else
+			mark_buffer_dirty(bh_ip);
+
+		brelse(bh_log);
+		brelse(bh_ip);
+
+		if (error)
+			break;
+
+		sdp->sd_replayed_blocks++;
+	}
+
+	return error;
+}
+
+static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (error) {
+		gfs2_meta_sync(ip->i_gl);
+		return;
+	}
+	if (pass != 1)
+		return;
+
+	gfs2_meta_sync(ip->i_gl);
+
+	fs_info(sdp, "jid=%u: Replayed %u of %u blocks\n",
+	        jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks);
+}
+
+static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+{
+	struct gfs2_trans *tr;
+
+	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 gfs2_log_descriptor *ld;
+	struct gfs2_meta_header *mh;
+	struct buffer_head *bh;
+	unsigned int offset;
+	struct list_head *head = &sdp->sd_log_le_revoke;
+	struct gfs2_revoke *rv;
+
+	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);
+	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);
+		sdp->sd_log_num_revoke--;
+
+		if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) {
+			set_buffer_dirty(bh);
+			ll_rw_block(WRITE, 1, &bh);
+
+			bh = gfs2_log_get_buf(sdp);
+			mh = (struct gfs2_meta_header *)bh->b_data;
+			mh->mh_magic = cpu_to_be32(GFS2_MAGIC);
+			mh->mh_type = cpu_to_be32(GFS2_METATYPE_LB);
+			mh->mh_format = cpu_to_be32(GFS2_FORMAT_LB);
+			offset = sizeof(struct gfs2_meta_header);
+		}
+
+		*(__be64 *)(bh->b_data + offset) = cpu_to_be64(rv->rv_blkno);
+		kfree(rv);
+
+		offset += sizeof(u64);
+	}
+	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
+
+	set_buffer_dirty(bh);
+	ll_rw_block(WRITE, 1, &bh);
+}
+
+static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
+				  struct gfs2_log_header *head, int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (pass != 0)
+		return;
+
+	sdp->sd_found_revokes = 0;
+	sdp->sd_replay_tail = head->lh_tail;
+}
+
+static int revoke_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				   struct gfs2_log_descriptor *ld, __be64 *ptr,
+				   int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	unsigned int blks = be32_to_cpu(ld->ld_length);
+	unsigned int revokes = be32_to_cpu(ld->ld_data1);
+	struct buffer_head *bh;
+	unsigned int offset;
+	u64 blkno;
+	int first = 1;
+	int error;
+
+	if (pass != 0 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_REVOKE)
+		return 0;
+
+	offset = sizeof(struct gfs2_log_descriptor);
+
+	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
+		error = gfs2_replay_read_block(jd, start, &bh);
+		if (error)
+			return error;
+
+		if (!first)
+			gfs2_metatype_check(sdp, bh, GFS2_METATYPE_LB);
+
+		while (offset + sizeof(u64) <= sdp->sd_sb.sb_bsize) {
+			blkno = be64_to_cpu(*(__be64 *)(bh->b_data + offset));
+
+			error = gfs2_revoke_add(sdp, blkno, start);
+			if (error < 0)
+				return error;
+			else if (error)
+				sdp->sd_found_revokes++;
+
+			if (!--revokes)
+				break;
+			offset += sizeof(u64);
+		}
+
+		brelse(bh);
+		offset = sizeof(struct gfs2_meta_header);
+		first = 0;
+	}
+
+	return 0;
+}
+
+static void revoke_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (error) {
+		gfs2_revoke_clean(sdp);
+		return;
+	}
+	if (pass != 1)
+		return;
+
+	fs_info(sdp, "jid=%u: Found %u revoke tags\n",
+	        jd->jd_jid, sdp->sd_found_revokes);
+
+	gfs2_revoke_clean(sdp);
+}
+
+static void rg_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+{
+	struct gfs2_rgrpd *rgd;
+	struct gfs2_trans *tr = current->journal_info;
+
+	tr->tr_touched = 1;
+
+	if (!list_empty(&le->le_list))
+		return;
+
+	rgd = container_of(le, struct gfs2_rgrpd, rd_le);
+	gfs2_rgrp_bh_hold(rgd);
+
+	gfs2_log_lock(sdp);
+	sdp->sd_log_num_rg++;
+	list_add(&le->le_list, &sdp->sd_log_le_rg);
+	gfs2_log_unlock(sdp);
+}
+
+static void rg_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct list_head *head = &sdp->sd_log_le_rg;
+	struct gfs2_rgrpd *rgd;
+
+	while (!list_empty(head)) {
+		rgd = list_entry(head->next, struct gfs2_rgrpd, rd_le.le_list);
+		list_del_init(&rgd->rd_le.le_list);
+		sdp->sd_log_num_rg--;
+
+		gfs2_rgrp_repolish_clones(rgd);
+		gfs2_rgrp_bh_put(rgd);
+	}
+	gfs2_assert_warn(sdp, !sdp->sd_log_num_rg);
+}
+
+/**
+ * databuf_lo_add - Add a databuf to the transaction.
+ *
+ * This is used in two distinct cases:
+ * i) In ordered write mode
+ *    We put the data buffer on a list so that we can ensure that its
+ *    synced to disk at the right time
+ * ii) In journaled data mode
+ *    We need to journal the data block in the same way as metadata in
+ *    the functions above. The difference is that here we have a tag
+ *    which is two __be64's being the block number (as per meta data)
+ *    and a flag which says whether the data block needs escaping or
+ *    not. This means we need a new log entry for each 251 or so data
+ *    blocks, which isn't an enormous overhead but twice as much as
+ *    for normal metadata blocks.
+ */
+static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+{
+	struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le);
+	struct gfs2_trans *tr = current->journal_info;
+	struct address_space *mapping = bd->bd_bh->b_page->mapping;
+	struct gfs2_inode *ip = GFS2_I(mapping->host);
+
+	tr->tr_touched = 1;
+	if (list_empty(&bd->bd_list_tr) &&
+	    (ip->i_di.di_flags & GFS2_DIF_JDATA)) {
+		tr->tr_num_buf++;
+		list_add(&bd->bd_list_tr, &tr->tr_list_buf);
+		gfs2_pin(sdp, bd->bd_bh);
+		tr->tr_num_buf_new++;
+	}
+	gfs2_trans_add_gl(bd->bd_gl);
+	gfs2_log_lock(sdp);
+	if (list_empty(&le->le_list)) {
+		if (ip->i_di.di_flags & GFS2_DIF_JDATA)
+			sdp->sd_log_num_jdata++;
+		sdp->sd_log_num_databuf++;
+		list_add(&le->le_list, &sdp->sd_log_le_databuf);
+	}
+	gfs2_log_unlock(sdp);
+}
+
+static int 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);
+	ptr = kaddr + bh_offset(bh);
+	if (*ptr == cpu_to_be32(GFS2_MAGIC))
+		rv = 1;
+	kunmap_atomic(page, KM_USER0);
+
+	return rv;
+}
+
+/**
+ * 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;
+	unsigned int offset = sizeof(struct gfs2_log_descriptor);
+	struct gfs2_log_descriptor *ld;
+	unsigned int limit;
+	unsigned int total_dbuf = sdp->sd_log_num_databuf;
+	unsigned int total_jdata = sdp->sd_log_num_jdata;
+	unsigned int num, n;
+	__be64 *ptr = NULL;
+
+	offset += 2*sizeof(__be64) - 1;
+	offset &= ~(2*sizeof(__be64) - 1);
+	limit = (sdp->sd_sb.sb_bsize - offset)/sizeof(__be64);
+
+	/*
+	 * Start writing ordered buffers, write journaled buffers
+	 * into the log along with a header
+	 */
+	gfs2_log_lock(sdp);
+	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) {
+			/* An ordered write buffer */
+			if (bd1->bd_bh && !buffer_pinned(bd1->bd_bh)) {
+				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 (bd1->bd_bh) {
+					get_bh(bd1->bd_bh);
+					if (buffer_dirty(bd1->bd_bh)) {
+						gfs2_log_unlock(sdp);
+						wait_on_buffer(bd1->bd_bh);
+						ll_rw_block(WRITE, 1,
+							    &bd1->bd_bh);
+						gfs2_log_lock(sdp);
+					}
+					brelse(bd1->bd_bh);
+					continue;
+				}
+				continue;
+			} else if (bd1->bd_bh) { /* A journaled buffer */
+				int magic;
+				gfs2_log_unlock(sdp);
+				if (!bh) {
+					bh = gfs2_log_get_buf(sdp);
+					sdp->sd_log_num_hdrs++;
+					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_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(bd1->bd_bh);
+				*ptr++ = cpu_to_be64(bd1->bd_bh->b_blocknr);
+				*ptr++ = cpu_to_be64((__u64)magic);
+				clear_buffer_escaped(bd1->bd_bh);
+				if (unlikely(magic != 0))
+					set_buffer_escaped(bd1->bd_bh);
+				gfs2_log_lock(sdp);
+				if (n++ > num)
+					break;
+			} else if (!bd1->bd_bh) {
+				total_dbuf--;
+				sdp->sd_log_num_databuf--;
+				list_del_init(&bd1->bd_le.le_list);
+				if (bd1 == bd2) {
+					bd2 = NULL;
+					bd2 = list_prepare_entry(bd2,
+						&sdp->sd_log_le_databuf,
+						bd_le.le_list);
+                                }
+				kmem_cache_free(gfs2_bufdata_cachep, bd1);
+			}
+		}
+		gfs2_log_unlock(sdp);
+		if (bh) {
+			set_buffer_dirty(bh);
+			ll_rw_block(WRITE, 1, &bh);
+			bh = NULL;
+		}
+		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 */
+			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(page, 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_log_lock(sdp);
+			if (++n >= num)
+				break;
+		}
+		bh = NULL;
+		total_dbuf -= num;
+		total_jdata -= num;
+	}
+	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);
+}
+
+static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				    struct gfs2_log_descriptor *ld,
+				    __be64 *ptr, int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	unsigned int blks = be32_to_cpu(ld->ld_data1);
+	struct buffer_head *bh_log, *bh_ip;
+	u64 blkno;
+	u64 esc;
+	int error = 0;
+
+	if (pass != 1 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_JDATA)
+		return 0;
+
+	gfs2_replay_incr_blk(sdp, &start);
+	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
+		blkno = be64_to_cpu(*ptr++);
+		esc = be64_to_cpu(*ptr++);
+
+		sdp->sd_found_blocks++;
+
+		if (gfs2_revoke_check(sdp, blkno, start))
+			continue;
+
+		error = gfs2_replay_read_block(jd, start, &bh_log);
+		if (error)
+			return error;
+
+		bh_ip = gfs2_meta_new(gl, blkno);
+		memcpy(bh_ip->b_data, bh_log->b_data, bh_log->b_size);
+
+		/* Unescape */
+		if (esc) {
+			__be32 *eptr = (__be32 *)bh_ip->b_data;
+			*eptr = cpu_to_be32(GFS2_MAGIC);
+		}
+		mark_buffer_dirty(bh_ip);
+
+		brelse(bh_log);
+		brelse(bh_ip);
+		if (error)
+			break;
+
+		sdp->sd_replayed_blocks++;
+	}
+
+	return error;
+}
+
+/* FIXME: sort out accounting for log blocks etc. */
+
+static void databuf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (error) {
+		gfs2_meta_sync(ip->i_gl);
+		return;
+	}
+	if (pass != 1)
+		return;
+
+	/* data sync? */
+	gfs2_meta_sync(ip->i_gl);
+
+	fs_info(sdp, "jid=%u: Replayed %u of %u data blocks\n",
+		jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks);
+}
+
+static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	struct list_head *head = &sdp->sd_log_le_databuf;
+	struct gfs2_bufdata *bd;
+
+	while (!list_empty(head)) {
+		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_glock_lops = {
+	.lo_add = glock_lo_add,
+	.lo_after_commit = glock_lo_after_commit,
+	.lo_name = "glock",
+};
+
+const struct gfs2_log_operations gfs2_buf_lops = {
+	.lo_add = buf_lo_add,
+	.lo_incore_commit = buf_lo_incore_commit,
+	.lo_before_commit = buf_lo_before_commit,
+	.lo_after_commit = buf_lo_after_commit,
+	.lo_before_scan = buf_lo_before_scan,
+	.lo_scan_elements = buf_lo_scan_elements,
+	.lo_after_scan = buf_lo_after_scan,
+	.lo_name = "buf",
+};
+
+const struct gfs2_log_operations gfs2_revoke_lops = {
+	.lo_add = revoke_lo_add,
+	.lo_before_commit = revoke_lo_before_commit,
+	.lo_before_scan = revoke_lo_before_scan,
+	.lo_scan_elements = revoke_lo_scan_elements,
+	.lo_after_scan = revoke_lo_after_scan,
+	.lo_name = "revoke",
+};
+
+const struct gfs2_log_operations gfs2_rg_lops = {
+	.lo_add = rg_lo_add,
+	.lo_after_commit = rg_lo_after_commit,
+	.lo_name = "rg",
+};
+
+const struct gfs2_log_operations gfs2_databuf_lops = {
+	.lo_add = databuf_lo_add,
+	.lo_incore_commit = buf_lo_incore_commit,
+	.lo_before_commit = databuf_lo_before_commit,
+	.lo_after_commit = databuf_lo_after_commit,
+	.lo_scan_elements = databuf_lo_scan_elements,
+	.lo_after_scan = databuf_lo_after_scan,
+	.lo_name = "databuf",
+};
+
+const struct gfs2_log_operations *gfs2_log_ops[] = {
+	&gfs2_glock_lops,
+	&gfs2_buf_lops,
+	&gfs2_revoke_lops,
+	&gfs2_rg_lops,
+	&gfs2_databuf_lops,
+	NULL,
+};
+

fs/gfs2/lops.h

@@ -0,0 +1,99 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __LOPS_DOT_H__
+#define __LOPS_DOT_H__
+
+#include <linux/list.h>
+#include "incore.h"
+
+extern const struct gfs2_log_operations gfs2_glock_lops;
+extern const struct gfs2_log_operations gfs2_buf_lops;
+extern const struct gfs2_log_operations gfs2_revoke_lops;
+extern const struct gfs2_log_operations gfs2_rg_lops;
+extern const struct gfs2_log_operations gfs2_databuf_lops;
+
+extern const struct gfs2_log_operations *gfs2_log_ops[];
+
+static inline void lops_init_le(struct gfs2_log_element *le,
+				const struct gfs2_log_operations *lops)
+{
+	INIT_LIST_HEAD(&le->le_list);
+	le->le_ops = lops;
+}
+
+static inline void lops_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+{
+	if (le->le_ops->lo_add)
+		le->le_ops->lo_add(sdp, le);
+}
+
+static inline void lops_incore_commit(struct gfs2_sbd *sdp,
+				      struct gfs2_trans *tr)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_incore_commit)
+			gfs2_log_ops[x]->lo_incore_commit(sdp, tr);
+}
+
+static inline void lops_before_commit(struct gfs2_sbd *sdp)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_before_commit)
+			gfs2_log_ops[x]->lo_before_commit(sdp);
+}
+
+static inline void lops_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_after_commit)
+			gfs2_log_ops[x]->lo_after_commit(sdp, ai);
+}
+
+static inline void lops_before_scan(struct gfs2_jdesc *jd,
+				    struct gfs2_log_header *head,
+				    unsigned int pass)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_before_scan)
+			gfs2_log_ops[x]->lo_before_scan(jd, head, pass);
+}
+
+static inline int lops_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				     struct gfs2_log_descriptor *ld,
+				     __be64 *ptr,
+				     unsigned int pass)
+{
+	int x, error;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_scan_elements) {
+			error = gfs2_log_ops[x]->lo_scan_elements(jd, start,
+								  ld, ptr, pass);
+			if (error)
+				return error;
+		}
+
+	return 0;
+}
+
+static inline void lops_after_scan(struct gfs2_jdesc *jd, int error,
+				   unsigned int pass)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_before_scan)
+			gfs2_log_ops[x]->lo_after_scan(jd, error, pass);
+}
+
+#endif /* __LOPS_DOT_H__ */
+

fs/gfs2/main.c

@@ -0,0 +1,150 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+#include <asm/atomic.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "ops_fstype.h"
+#include "sys.h"
+#include "util.h"
+#include "glock.h"
+
+static void gfs2_init_inode_once(void *foo, kmem_cache_t *cachep, unsigned long flags)
+{
+	struct gfs2_inode *ip = foo;
+	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
+	    SLAB_CTOR_CONSTRUCTOR) {
+		inode_init_once(&ip->i_inode);
+		spin_lock_init(&ip->i_spin);
+		init_rwsem(&ip->i_rw_mutex);
+		memset(ip->i_cache, 0, sizeof(ip->i_cache));
+	}
+}
+
+static void gfs2_init_glock_once(void *foo, kmem_cache_t *cachep, unsigned long flags)
+{
+	struct gfs2_glock *gl = foo;
+	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
+	    SLAB_CTOR_CONSTRUCTOR) {
+		INIT_HLIST_NODE(&gl->gl_list);
+		spin_lock_init(&gl->gl_spin);
+		INIT_LIST_HEAD(&gl->gl_holders);
+		INIT_LIST_HEAD(&gl->gl_waiters1);
+		INIT_LIST_HEAD(&gl->gl_waiters2);
+		INIT_LIST_HEAD(&gl->gl_waiters3);
+		gl->gl_lvb = NULL;
+		atomic_set(&gl->gl_lvb_count, 0);
+		INIT_LIST_HEAD(&gl->gl_reclaim);
+		INIT_LIST_HEAD(&gl->gl_ail_list);
+		atomic_set(&gl->gl_ail_count, 0);
+	}
+}
+
+/**
+ * init_gfs2_fs - Register GFS2 as a filesystem
+ *
+ * Returns: 0 on success, error code on failure
+ */
+
+static int __init init_gfs2_fs(void)
+{
+	int error;
+
+	error = gfs2_sys_init();
+	if (error)
+		return error;
+
+	error = gfs2_glock_init();
+	if (error)
+		goto fail;
+
+	error = -ENOMEM;
+	gfs2_glock_cachep = kmem_cache_create("gfs2_glock",
+					      sizeof(struct gfs2_glock),
+					      0, 0,
+					      gfs2_init_glock_once, NULL);
+	if (!gfs2_glock_cachep)
+		goto fail;
+
+	gfs2_inode_cachep = kmem_cache_create("gfs2_inode",
+					      sizeof(struct gfs2_inode),
+					      0, (SLAB_RECLAIM_ACCOUNT|
+					      SLAB_PANIC|SLAB_MEM_SPREAD),
+					      gfs2_init_inode_once, NULL);
+	if (!gfs2_inode_cachep)
+		goto fail;
+
+	gfs2_bufdata_cachep = kmem_cache_create("gfs2_bufdata",
+						sizeof(struct gfs2_bufdata),
+					        0, 0, NULL, NULL);
+	if (!gfs2_bufdata_cachep)
+		goto fail;
+
+	error = register_filesystem(&gfs2_fs_type);
+	if (error)
+		goto fail;
+
+	error = register_filesystem(&gfs2meta_fs_type);
+	if (error)
+		goto fail_unregister;
+
+	printk("GFS2 (built %s %s) installed\n", __DATE__, __TIME__);
+
+	return 0;
+
+fail_unregister:
+	unregister_filesystem(&gfs2_fs_type);
+fail:
+	if (gfs2_bufdata_cachep)
+		kmem_cache_destroy(gfs2_bufdata_cachep);
+
+	if (gfs2_inode_cachep)
+		kmem_cache_destroy(gfs2_inode_cachep);
+
+	if (gfs2_glock_cachep)
+		kmem_cache_destroy(gfs2_glock_cachep);
+
+	gfs2_sys_uninit();
+	return error;
+}
+
+/**
+ * exit_gfs2_fs - Unregister the file system
+ *
+ */
+
+static void __exit exit_gfs2_fs(void)
+{
+	unregister_filesystem(&gfs2_fs_type);
+	unregister_filesystem(&gfs2meta_fs_type);
+
+	kmem_cache_destroy(gfs2_bufdata_cachep);
+	kmem_cache_destroy(gfs2_inode_cachep);
+	kmem_cache_destroy(gfs2_glock_cachep);
+
+	gfs2_sys_uninit();
+}
+
+MODULE_DESCRIPTION("Global File System");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+module_init(init_gfs2_fs);
+module_exit(exit_gfs2_fs);
+

fs/gfs2/meta_io.c

@@ -0,0 +1,590 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/writeback.h>
+#include <linux/swap.h>
+#include <linux/delay.h>
+#include <linux/bio.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "log.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+#include "ops_address.h"
+
+static int aspace_get_block(struct inode *inode, sector_t lblock,
+			    struct buffer_head *bh_result, int create)
+{
+	gfs2_assert_warn(inode->i_sb->s_fs_info, 0);
+	return -EOPNOTSUPP;
+}
+
+static int gfs2_aspace_writepage(struct page *page,
+				 struct writeback_control *wbc)
+{
+	return block_write_full_page(page, aspace_get_block, wbc);
+}
+
+static const struct address_space_operations aspace_aops = {
+	.writepage = gfs2_aspace_writepage,
+	.releasepage = gfs2_releasepage,
+};
+
+/**
+ * gfs2_aspace_get - Create and initialize a struct inode structure
+ * @sdp: the filesystem the aspace is in
+ *
+ * Right now a struct inode is just a struct inode.  Maybe Linux
+ * will supply a more lightweight address space construct (that works)
+ * in the future.
+ *
+ * Make sure pages/buffers in this aspace aren't in high memory.
+ *
+ * Returns: the aspace
+ */
+
+struct inode *gfs2_aspace_get(struct gfs2_sbd *sdp)
+{
+	struct inode *aspace;
+
+	aspace = new_inode(sdp->sd_vfs);
+	if (aspace) {
+		mapping_set_gfp_mask(aspace->i_mapping, GFP_NOFS);
+		aspace->i_mapping->a_ops = &aspace_aops;
+		aspace->i_size = ~0ULL;
+		aspace->i_private = NULL;
+		insert_inode_hash(aspace);
+	}
+	return aspace;
+}
+
+void gfs2_aspace_put(struct inode *aspace)
+{
+	remove_inode_hash(aspace);
+	iput(aspace);
+}
+
+/**
+ * gfs2_meta_inval - Invalidate all buffers associated with a glock
+ * @gl: the glock
+ *
+ */
+
+void gfs2_meta_inval(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct inode *aspace = gl->gl_aspace;
+	struct address_space *mapping = gl->gl_aspace->i_mapping;
+
+	gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
+
+	atomic_inc(&aspace->i_writecount);
+	truncate_inode_pages(mapping, 0);
+	atomic_dec(&aspace->i_writecount);
+
+	gfs2_assert_withdraw(sdp, !mapping->nrpages);
+}
+
+/**
+ * gfs2_meta_sync - Sync all buffers associated with a glock
+ * @gl: The glock
+ *
+ */
+
+void gfs2_meta_sync(struct gfs2_glock *gl)
+{
+	struct address_space *mapping = gl->gl_aspace->i_mapping;
+	int error;
+
+	filemap_fdatawrite(mapping);
+	error = filemap_fdatawait(mapping);
+
+	if (error)
+		gfs2_io_error(gl->gl_sbd);
+}
+
+/**
+ * getbuf - Get a buffer with a given address space
+ * @sdp: the filesystem
+ * @aspace: the address space
+ * @blkno: the block number (filesystem scope)
+ * @create: 1 if the buffer should be created
+ *
+ * Returns: the buffer
+ */
+
+static struct buffer_head *getbuf(struct gfs2_sbd *sdp, struct inode *aspace,
+				  u64 blkno, int create)
+{
+	struct page *page;
+	struct buffer_head *bh;
+	unsigned int shift;
+	unsigned long index;
+	unsigned int bufnum;
+
+	shift = PAGE_CACHE_SHIFT - sdp->sd_sb.sb_bsize_shift;
+	index = blkno >> shift;             /* convert block to page */
+	bufnum = blkno - (index << shift);  /* block buf index within page */
+
+	if (create) {
+		for (;;) {
+			page = grab_cache_page(aspace->i_mapping, index);
+			if (page)
+				break;
+			yield();
+		}
+	} else {
+		page = find_lock_page(aspace->i_mapping, index);
+		if (!page)
+			return NULL;
+	}
+
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, sdp->sd_sb.sb_bsize, 0);
+
+	/* Locate header for our buffer within our page */
+	for (bh = page_buffers(page); bufnum--; bh = bh->b_this_page)
+		/* Do nothing */;
+	get_bh(bh);
+
+	if (!buffer_mapped(bh))
+		map_bh(bh, sdp->sd_vfs, blkno);
+
+	unlock_page(page);
+	mark_page_accessed(page);
+	page_cache_release(page);
+
+	return bh;
+}
+
+static void meta_prep_new(struct buffer_head *bh)
+{
+	struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;
+
+	lock_buffer(bh);
+	clear_buffer_dirty(bh);
+	set_buffer_uptodate(bh);
+	unlock_buffer(bh);
+
+	mh->mh_magic = cpu_to_be32(GFS2_MAGIC);
+}
+
+/**
+ * gfs2_meta_new - Get a block
+ * @gl: The glock associated with this block
+ * @blkno: The block number
+ *
+ * Returns: The buffer
+ */
+
+struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
+{
+	struct buffer_head *bh;
+	bh = getbuf(gl->gl_sbd, gl->gl_aspace, blkno, CREATE);
+	meta_prep_new(bh);
+	return bh;
+}
+
+/**
+ * gfs2_meta_read - Read a block from disk
+ * @gl: The glock covering the block
+ * @blkno: The block number
+ * @flags: flags
+ * @bhp: the place where the buffer is returned (NULL on failure)
+ *
+ * Returns: errno
+ */
+
+int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
+		   struct buffer_head **bhp)
+{
+	*bhp = getbuf(gl->gl_sbd, gl->gl_aspace, blkno, CREATE);
+	if (!buffer_uptodate(*bhp))
+		ll_rw_block(READ_META, 1, bhp);
+	if (flags & DIO_WAIT) {
+		int error = gfs2_meta_wait(gl->gl_sbd, *bhp);
+		if (error) {
+			brelse(*bhp);
+			return error;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_meta_wait - Reread a block from disk
+ * @sdp: the filesystem
+ * @bh: The block to wait for
+ *
+ * Returns: errno
+ */
+
+int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
+{
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+
+	wait_on_buffer(bh);
+
+	if (!buffer_uptodate(bh)) {
+		struct gfs2_trans *tr = current->journal_info;
+		if (tr && tr->tr_touched)
+			gfs2_io_error_bh(sdp, bh);
+		return -EIO;
+	}
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * gfs2_attach_bufdata - attach a struct gfs2_bufdata structure to a buffer
+ * @gl: the glock the buffer belongs to
+ * @bh: The buffer to be attached to
+ * @meta: Flag to indicate whether its metadata or not
+ */
+
+void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
+			 int meta)
+{
+	struct gfs2_bufdata *bd;
+
+	if (meta)
+		lock_page(bh->b_page);
+
+	if (bh->b_private) {
+		if (meta)
+			unlock_page(bh->b_page);
+		return;
+	}
+
+	bd = kmem_cache_alloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL),
+	memset(bd, 0, sizeof(struct gfs2_bufdata));
+	bd->bd_bh = bh;
+	bd->bd_gl = gl;
+
+	INIT_LIST_HEAD(&bd->bd_list_tr);
+	if (meta)
+		lops_init_le(&bd->bd_le, &gfs2_buf_lops);
+	else
+		lops_init_le(&bd->bd_le, &gfs2_databuf_lops);
+	bh->b_private = bd;
+
+	if (meta)
+		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)
+{
+	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);
+		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);
+}
+
+/**
+ * gfs2_meta_wipe - make inode's buffers so they aren't dirty/pinned anymore
+ * @ip: the inode who owns the buffers
+ * @bstart: the first buffer in the run
+ * @blen: the number of buffers in the run
+ *
+ */
+
+void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct inode *aspace = ip->i_gl->gl_aspace;
+	struct buffer_head *bh;
+
+	while (blen) {
+		bh = getbuf(sdp, aspace, 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;
+				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);
+				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);
+			unlock_buffer(bh);
+
+			brelse(bh);
+		}
+
+		bstart++;
+		blen--;
+	}
+}
+
+/**
+ * gfs2_meta_cache_flush - get rid of any references on buffers for this inode
+ * @ip: The GFS2 inode
+ *
+ * This releases buffers that are in the most-recently-used array of
+ * blocks used for indirect block addressing for this inode.
+ */
+
+void gfs2_meta_cache_flush(struct gfs2_inode *ip)
+{
+	struct buffer_head **bh_slot;
+	unsigned int x;
+
+	spin_lock(&ip->i_spin);
+
+	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;
+	}
+
+	spin_unlock(&ip->i_spin);
+}
+
+/**
+ * gfs2_meta_indirect_buffer - Get a metadata buffer
+ * @ip: The GFS2 inode
+ * @height: The level of this buf in the metadata (indir addr) tree (if any)
+ * @num: The block number (device relative) of the buffer
+ * @new: Non-zero if we may create a new buffer
+ * @bhp: the buffer is returned here
+ *
+ * Try to use the gfs2_inode's MRU metadata tree cache.
+ *
+ * Returns: errno
+ */
+
+int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
+			      int new, struct buffer_head **bhp)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	struct buffer_head *bh = NULL, **bh_slot = ip->i_cache + height;
+	int in_cache = 0;
+
+	spin_lock(&ip->i_spin);
+	if (*bh_slot && (*bh_slot)->b_blocknr == num) {
+		bh = *bh_slot;
+		get_bh(bh);
+		in_cache = 1;
+	}
+	spin_unlock(&ip->i_spin);
+
+	if (!bh)
+		bh = getbuf(gl->gl_sbd, gl->gl_aspace, num, CREATE);
+
+	if (!bh)
+		return -ENOBUFS;
+
+	if (new) {
+		if (gfs2_assert_warn(sdp, height))
+			goto err;
+		meta_prep_new(bh);
+		gfs2_trans_add_bh(ip->i_gl, bh, 1);
+		gfs2_metatype_set(bh, GFS2_METATYPE_IN, GFS2_FORMAT_IN);
+		gfs2_buffer_clear_tail(bh, sizeof(struct gfs2_meta_header));
+	} else {
+		u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI;
+		if (!buffer_uptodate(bh)) {
+			ll_rw_block(READ_META, 1, &bh);
+			if (gfs2_meta_wait(sdp, bh))
+				goto err;
+		}
+		if (gfs2_metatype_check(sdp, bh, mtype))
+			goto err;
+	}
+
+	if (!in_cache) {
+		spin_lock(&ip->i_spin);
+		if (*bh_slot)
+			brelse(*bh_slot);
+		*bh_slot = bh;
+		get_bh(bh);
+		spin_unlock(&ip->i_spin);
+	}
+
+	*bhp = bh;
+	return 0;
+err:
+	brelse(bh);
+	return -EIO;
+}
+
+/**
+ * gfs2_meta_ra - start readahead on an extent of a file
+ * @gl: the glock the blocks belong to
+ * @dblock: the starting disk block
+ * @extlen: the number of blocks in the extent
+ *
+ * returns: the first buffer in the extent
+ */
+
+struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct inode *aspace = gl->gl_aspace;
+	struct buffer_head *first_bh, *bh;
+	u32 max_ra = gfs2_tune_get(sdp, gt_max_readahead) >>
+			  sdp->sd_sb.sb_bsize_shift;
+
+	BUG_ON(!extlen);
+
+	if (max_ra < 1)
+		max_ra = 1;
+	if (extlen > max_ra)
+		extlen = max_ra;
+
+	first_bh = getbuf(sdp, aspace, dblock, CREATE);
+
+	if (buffer_uptodate(first_bh))
+		goto out;
+	if (!buffer_locked(first_bh))
+		ll_rw_block(READ_META, 1, &first_bh);
+
+	dblock++;
+	extlen--;
+
+	while (extlen) {
+		bh = getbuf(sdp, aspace, dblock, CREATE);
+
+		if (!buffer_uptodate(bh) && !buffer_locked(bh))
+			ll_rw_block(READA, 1, &bh);
+		brelse(bh);
+		dblock++;
+		extlen--;
+		if (!buffer_locked(first_bh) && buffer_uptodate(first_bh))
+			goto out;
+	}
+
+	wait_on_buffer(first_bh);
+out:
+	return first_bh;
+}
+
+/**
+ * gfs2_meta_syncfs - sync all the buffers in a filesystem
+ * @sdp: the filesystem
+ *
+ */
+
+void gfs2_meta_syncfs(struct gfs2_sbd *sdp)
+{
+	gfs2_log_flush(sdp, NULL);
+	for (;;) {
+		gfs2_ail1_start(sdp, DIO_ALL);
+		if (gfs2_ail1_empty(sdp, DIO_ALL))
+			break;
+		msleep(10);
+	}
+}
+

fs/gfs2/meta_io.h

@@ -0,0 +1,78 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __DIO_DOT_H__
+#define __DIO_DOT_H__
+
+#include <linux/buffer_head.h>
+#include <linux/string.h>
+#include "incore.h"
+
+static inline void gfs2_buffer_clear(struct buffer_head *bh)
+{
+	memset(bh->b_data, 0, bh->b_size);
+}
+
+static inline void gfs2_buffer_clear_tail(struct buffer_head *bh, int head)
+{
+	BUG_ON(head > bh->b_size);
+	memset(bh->b_data + head, 0, bh->b_size - head);
+}
+
+static inline void gfs2_buffer_copy_tail(struct buffer_head *to_bh,
+					 int to_head,
+					 struct buffer_head *from_bh,
+					 int from_head)
+{
+	BUG_ON(from_head < to_head);
+	memcpy(to_bh->b_data + to_head, from_bh->b_data + from_head,
+	       from_bh->b_size - from_head);
+	memset(to_bh->b_data + to_bh->b_size + to_head - from_head,
+	       0, from_head - to_head);
+}
+
+struct inode *gfs2_aspace_get(struct gfs2_sbd *sdp);
+void gfs2_aspace_put(struct inode *aspace);
+
+void gfs2_meta_inval(struct gfs2_glock *gl);
+void gfs2_meta_sync(struct gfs2_glock *gl);
+
+struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno);
+int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno,
+		   int flags, struct buffer_head **bhp);
+int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh);
+
+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_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen);
+
+void gfs2_meta_cache_flush(struct gfs2_inode *ip);
+int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
+			      int new, struct buffer_head **bhp);
+
+static inline int gfs2_meta_inode_buffer(struct gfs2_inode *ip,
+					 struct buffer_head **bhp)
+{
+	return gfs2_meta_indirect_buffer(ip, 0, ip->i_num.no_addr, 0, bhp);
+}
+
+struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen);
+void gfs2_meta_syncfs(struct gfs2_sbd *sdp);
+
+#define buffer_busy(bh) \
+((bh)->b_state & ((1ul << BH_Dirty) | (1ul << BH_Lock) | (1ul << BH_Pinned)))
+#define buffer_in_io(bh) \
+((bh)->b_state & ((1ul << BH_Dirty) | (1ul << BH_Lock)))
+
+#endif /* __DIO_DOT_H__ */
+

fs/gfs2/mount.c

@@ -0,0 +1,214 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "mount.h"
+#include "sys.h"
+#include "util.h"
+
+/**
+ * gfs2_mount_args - Parse mount options
+ * @sdp:
+ * @data:
+ *
+ * Return: errno
+ */
+
+int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount)
+{
+	struct gfs2_args *args = &sdp->sd_args;
+	char *data = data_arg;
+	char *options, *o, *v;
+	int error = 0;
+
+	if (!remount) {
+		/*  If someone preloaded options, use those instead  */
+		spin_lock(&gfs2_sys_margs_lock);
+		if (gfs2_sys_margs) {
+			data = gfs2_sys_margs;
+			gfs2_sys_margs = NULL;
+		}
+		spin_unlock(&gfs2_sys_margs_lock);
+
+		/*  Set some defaults  */
+		args->ar_num_glockd = GFS2_GLOCKD_DEFAULT;
+		args->ar_quota = GFS2_QUOTA_DEFAULT;
+		args->ar_data = GFS2_DATA_DEFAULT;
+	}
+
+	/* Split the options into tokens with the "," character and
+	   process them */
+
+	for (options = data; (o = strsep(&options, ",")); ) {
+		if (!*o)
+			continue;
+
+		v = strchr(o, '=');
+		if (v)
+			*v++ = 0;
+
+		if (!strcmp(o, "lockproto")) {
+			if (!v)
+				goto need_value;
+			if (remount && strcmp(v, args->ar_lockproto))
+				goto cant_remount;
+			strncpy(args->ar_lockproto, v, GFS2_LOCKNAME_LEN);
+			args->ar_lockproto[GFS2_LOCKNAME_LEN - 1] = 0;
+		}
+
+		else if (!strcmp(o, "locktable")) {
+			if (!v)
+				goto need_value;
+			if (remount && strcmp(v, args->ar_locktable))
+				goto cant_remount;
+			strncpy(args->ar_locktable, v, GFS2_LOCKNAME_LEN);
+			args->ar_locktable[GFS2_LOCKNAME_LEN - 1] = 0;
+		}
+
+		else if (!strcmp(o, "hostdata")) {
+			if (!v)
+				goto need_value;
+			if (remount && strcmp(v, args->ar_hostdata))
+				goto cant_remount;
+			strncpy(args->ar_hostdata, v, GFS2_LOCKNAME_LEN);
+			args->ar_hostdata[GFS2_LOCKNAME_LEN - 1] = 0;
+		}
+
+		else if (!strcmp(o, "spectator")) {
+			if (remount && !args->ar_spectator)
+				goto cant_remount;
+			args->ar_spectator = 1;
+			sdp->sd_vfs->s_flags |= MS_RDONLY;
+		}
+
+		else if (!strcmp(o, "ignore_local_fs")) {
+			if (remount && !args->ar_ignore_local_fs)
+				goto cant_remount;
+			args->ar_ignore_local_fs = 1;
+		}
+
+		else if (!strcmp(o, "localflocks")) {
+			if (remount && !args->ar_localflocks)
+				goto cant_remount;
+			args->ar_localflocks = 1;
+		}
+
+		else if (!strcmp(o, "localcaching")) {
+			if (remount && !args->ar_localcaching)
+				goto cant_remount;
+			args->ar_localcaching = 1;
+		}
+
+		else if (!strcmp(o, "debug"))
+			args->ar_debug = 1;
+
+		else if (!strcmp(o, "nodebug"))
+			args->ar_debug = 0;
+
+		else if (!strcmp(o, "upgrade")) {
+			if (remount && !args->ar_upgrade)
+				goto cant_remount;
+			args->ar_upgrade = 1;
+		}
+
+		else if (!strcmp(o, "num_glockd")) {
+			unsigned int x;
+			if (!v)
+				goto need_value;
+			sscanf(v, "%u", &x);
+			if (remount && x != args->ar_num_glockd)
+				goto cant_remount;
+			if (!x || x > GFS2_GLOCKD_MAX) {
+				fs_info(sdp, "0 < num_glockd <= %u  (not %u)\n",
+				        GFS2_GLOCKD_MAX, x);
+				error = -EINVAL;
+				break;
+			}
+			args->ar_num_glockd = x;
+		}
+
+		else if (!strcmp(o, "acl")) {
+			args->ar_posix_acl = 1;
+			sdp->sd_vfs->s_flags |= MS_POSIXACL;
+		}
+
+		else if (!strcmp(o, "noacl")) {
+			args->ar_posix_acl = 0;
+			sdp->sd_vfs->s_flags &= ~MS_POSIXACL;
+		}
+
+		else if (!strcmp(o, "quota")) {
+			if (!v)
+				goto need_value;
+			if (!strcmp(v, "off"))
+				args->ar_quota = GFS2_QUOTA_OFF;
+			else if (!strcmp(v, "account"))
+				args->ar_quota = GFS2_QUOTA_ACCOUNT;
+			else if (!strcmp(v, "on"))
+				args->ar_quota = GFS2_QUOTA_ON;
+			else {
+				fs_info(sdp, "invalid value for quota\n");
+				error = -EINVAL;
+				break;
+			}
+		}
+
+		else if (!strcmp(o, "suiddir"))
+			args->ar_suiddir = 1;
+
+		else if (!strcmp(o, "nosuiddir"))
+			args->ar_suiddir = 0;
+
+		else if (!strcmp(o, "data")) {
+			if (!v)
+				goto need_value;
+			if (!strcmp(v, "writeback"))
+				args->ar_data = GFS2_DATA_WRITEBACK;
+			else if (!strcmp(v, "ordered"))
+				args->ar_data = GFS2_DATA_ORDERED;
+			else {
+				fs_info(sdp, "invalid value for data\n");
+				error = -EINVAL;
+				break;
+			}
+		}
+
+		else {
+			fs_info(sdp, "unknown option: %s\n", o);
+			error = -EINVAL;
+			break;
+		}
+	}
+
+	if (error)
+		fs_info(sdp, "invalid mount option(s)\n");
+
+	if (data != data_arg)
+		kfree(data);
+
+	return error;
+
+need_value:
+	fs_info(sdp, "need value for option %s\n", o);
+	return -EINVAL;
+
+cant_remount:
+	fs_info(sdp, "can't remount with option %s\n", o);
+	return -EINVAL;
+}
+

fs/gfs2/mount.h

@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __MOUNT_DOT_H__
+#define __MOUNT_DOT_H__
+
+struct gfs2_sbd;
+
+int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount);
+
+#endif /* __MOUNT_DOT_H__ */

fs/gfs2/ondisk.c

@@ -0,0 +1,308 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+
+#include "gfs2.h"
+#include <linux/gfs2_ondisk.h>
+
+#define pv(struct, member, fmt) printk(KERN_INFO "  "#member" = "fmt"\n", \
+				       struct->member);
+
+/*
+ * gfs2_xxx_in - read in an xxx struct
+ * first arg: the cpu-order structure
+ * buf: the disk-order buffer
+ *
+ * gfs2_xxx_out - write out an xxx struct
+ * first arg: the cpu-order structure
+ * buf: the disk-order buffer
+ *
+ * gfs2_xxx_print - print out an xxx struct
+ * first arg: the cpu-order structure
+ */
+
+void gfs2_inum_in(struct gfs2_inum *no, const void *buf)
+{
+	const struct gfs2_inum *str = buf;
+
+	no->no_formal_ino = be64_to_cpu(str->no_formal_ino);
+	no->no_addr = be64_to_cpu(str->no_addr);
+}
+
+void gfs2_inum_out(const struct gfs2_inum *no, void *buf)
+{
+	struct gfs2_inum *str = buf;
+
+	str->no_formal_ino = cpu_to_be64(no->no_formal_ino);
+	str->no_addr = cpu_to_be64(no->no_addr);
+}
+
+static void gfs2_inum_print(const struct gfs2_inum *no)
+{
+	printk(KERN_INFO "  no_formal_ino = %llu\n", (unsigned long long)no->no_formal_ino);
+	printk(KERN_INFO "  no_addr = %llu\n", (unsigned long long)no->no_addr);
+}
+
+static void gfs2_meta_header_in(struct gfs2_meta_header *mh, const void *buf)
+{
+	const struct gfs2_meta_header *str = buf;
+
+	mh->mh_magic = be32_to_cpu(str->mh_magic);
+	mh->mh_type = be32_to_cpu(str->mh_type);
+	mh->mh_format = be32_to_cpu(str->mh_format);
+}
+
+static void gfs2_meta_header_out(const struct gfs2_meta_header *mh, void *buf)
+{
+	struct gfs2_meta_header *str = buf;
+
+	str->mh_magic = cpu_to_be32(mh->mh_magic);
+	str->mh_type = cpu_to_be32(mh->mh_type);
+	str->mh_format = cpu_to_be32(mh->mh_format);
+}
+
+static void gfs2_meta_header_print(const struct gfs2_meta_header *mh)
+{
+	pv(mh, mh_magic, "0x%.8X");
+	pv(mh, mh_type, "%u");
+	pv(mh, mh_format, "%u");
+}
+
+void gfs2_sb_in(struct gfs2_sb *sb, const void *buf)
+{
+	const struct gfs2_sb *str = buf;
+
+	gfs2_meta_header_in(&sb->sb_header, buf);
+
+	sb->sb_fs_format = be32_to_cpu(str->sb_fs_format);
+	sb->sb_multihost_format = be32_to_cpu(str->sb_multihost_format);
+	sb->sb_bsize = be32_to_cpu(str->sb_bsize);
+	sb->sb_bsize_shift = be32_to_cpu(str->sb_bsize_shift);
+
+	gfs2_inum_in(&sb->sb_master_dir, (char *)&str->sb_master_dir);
+	gfs2_inum_in(&sb->sb_root_dir, (char *)&str->sb_root_dir);
+
+	memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN);
+	memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN);
+}
+
+void gfs2_rindex_in(struct gfs2_rindex *ri, const void *buf)
+{
+	const struct gfs2_rindex *str = buf;
+
+	ri->ri_addr = be64_to_cpu(str->ri_addr);
+	ri->ri_length = be32_to_cpu(str->ri_length);
+	ri->ri_data0 = be64_to_cpu(str->ri_data0);
+	ri->ri_data = be32_to_cpu(str->ri_data);
+	ri->ri_bitbytes = be32_to_cpu(str->ri_bitbytes);
+
+}
+
+void gfs2_rindex_print(const struct gfs2_rindex *ri)
+{
+	printk(KERN_INFO "  ri_addr = %llu\n", (unsigned long long)ri->ri_addr);
+	pv(ri, ri_length, "%u");
+
+	printk(KERN_INFO "  ri_data0 = %llu\n", (unsigned long long)ri->ri_data0);
+	pv(ri, ri_data, "%u");
+
+	pv(ri, ri_bitbytes, "%u");
+}
+
+void gfs2_rgrp_in(struct gfs2_rgrp *rg, const void *buf)
+{
+	const struct gfs2_rgrp *str = buf;
+
+	gfs2_meta_header_in(&rg->rg_header, buf);
+	rg->rg_flags = be32_to_cpu(str->rg_flags);
+	rg->rg_free = be32_to_cpu(str->rg_free);
+	rg->rg_dinodes = be32_to_cpu(str->rg_dinodes);
+	rg->rg_igeneration = be64_to_cpu(str->rg_igeneration);
+}
+
+void gfs2_rgrp_out(const struct gfs2_rgrp *rg, void *buf)
+{
+	struct gfs2_rgrp *str = buf;
+
+	gfs2_meta_header_out(&rg->rg_header, buf);
+	str->rg_flags = cpu_to_be32(rg->rg_flags);
+	str->rg_free = cpu_to_be32(rg->rg_free);
+	str->rg_dinodes = cpu_to_be32(rg->rg_dinodes);
+	str->__pad = cpu_to_be32(0);
+	str->rg_igeneration = cpu_to_be64(rg->rg_igeneration);
+	memset(&str->rg_reserved, 0, sizeof(str->rg_reserved));
+}
+
+void gfs2_quota_in(struct gfs2_quota *qu, const void *buf)
+{
+	const struct gfs2_quota *str = buf;
+
+	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);
+}
+
+void gfs2_dinode_in(struct gfs2_dinode *di, const void *buf)
+{
+	const struct gfs2_dinode *str = buf;
+
+	gfs2_meta_header_in(&di->di_header, buf);
+	gfs2_inum_in(&di->di_num, &str->di_num);
+
+	di->di_mode = be32_to_cpu(str->di_mode);
+	di->di_uid = be32_to_cpu(str->di_uid);
+	di->di_gid = be32_to_cpu(str->di_gid);
+	di->di_nlink = be32_to_cpu(str->di_nlink);
+	di->di_size = be64_to_cpu(str->di_size);
+	di->di_blocks = be64_to_cpu(str->di_blocks);
+	di->di_atime = be64_to_cpu(str->di_atime);
+	di->di_mtime = be64_to_cpu(str->di_mtime);
+	di->di_ctime = be64_to_cpu(str->di_ctime);
+	di->di_major = be32_to_cpu(str->di_major);
+	di->di_minor = be32_to_cpu(str->di_minor);
+
+	di->di_goal_meta = be64_to_cpu(str->di_goal_meta);
+	di->di_goal_data = be64_to_cpu(str->di_goal_data);
+	di->di_generation = be64_to_cpu(str->di_generation);
+
+	di->di_flags = be32_to_cpu(str->di_flags);
+	di->di_payload_format = be32_to_cpu(str->di_payload_format);
+	di->di_height = be16_to_cpu(str->di_height);
+
+	di->di_depth = be16_to_cpu(str->di_depth);
+	di->di_entries = be32_to_cpu(str->di_entries);
+
+	di->di_eattr = be64_to_cpu(str->di_eattr);
+
+}
+
+void gfs2_dinode_out(const struct gfs2_dinode *di, void *buf)
+{
+	struct gfs2_dinode *str = buf;
+
+	gfs2_meta_header_out(&di->di_header, buf);
+	gfs2_inum_out(&di->di_num, (char *)&str->di_num);
+
+	str->di_mode = cpu_to_be32(di->di_mode);
+	str->di_uid = cpu_to_be32(di->di_uid);
+	str->di_gid = cpu_to_be32(di->di_gid);
+	str->di_nlink = cpu_to_be32(di->di_nlink);
+	str->di_size = cpu_to_be64(di->di_size);
+	str->di_blocks = cpu_to_be64(di->di_blocks);
+	str->di_atime = cpu_to_be64(di->di_atime);
+	str->di_mtime = cpu_to_be64(di->di_mtime);
+	str->di_ctime = cpu_to_be64(di->di_ctime);
+	str->di_major = cpu_to_be32(di->di_major);
+	str->di_minor = cpu_to_be32(di->di_minor);
+
+	str->di_goal_meta = cpu_to_be64(di->di_goal_meta);
+	str->di_goal_data = cpu_to_be64(di->di_goal_data);
+	str->di_generation = cpu_to_be64(di->di_generation);
+
+	str->di_flags = cpu_to_be32(di->di_flags);
+	str->di_payload_format = cpu_to_be32(di->di_payload_format);
+	str->di_height = cpu_to_be16(di->di_height);
+
+	str->di_depth = cpu_to_be16(di->di_depth);
+	str->di_entries = cpu_to_be32(di->di_entries);
+
+	str->di_eattr = cpu_to_be64(di->di_eattr);
+
+}
+
+void gfs2_dinode_print(const struct gfs2_dinode *di)
+{
+	gfs2_meta_header_print(&di->di_header);
+	gfs2_inum_print(&di->di_num);
+
+	pv(di, di_mode, "0%o");
+	pv(di, di_uid, "%u");
+	pv(di, di_gid, "%u");
+	pv(di, di_nlink, "%u");
+	printk(KERN_INFO "  di_size = %llu\n", (unsigned long long)di->di_size);
+	printk(KERN_INFO "  di_blocks = %llu\n", (unsigned long long)di->di_blocks);
+	printk(KERN_INFO "  di_atime = %lld\n", (long long)di->di_atime);
+	printk(KERN_INFO "  di_mtime = %lld\n", (long long)di->di_mtime);
+	printk(KERN_INFO "  di_ctime = %lld\n", (long long)di->di_ctime);
+	pv(di, di_major, "%u");
+	pv(di, di_minor, "%u");
+
+	printk(KERN_INFO "  di_goal_meta = %llu\n", (unsigned long long)di->di_goal_meta);
+	printk(KERN_INFO "  di_goal_data = %llu\n", (unsigned long long)di->di_goal_data);
+
+	pv(di, di_flags, "0x%.8X");
+	pv(di, di_payload_format, "%u");
+	pv(di, di_height, "%u");
+
+	pv(di, di_depth, "%u");
+	pv(di, di_entries, "%u");
+
+	printk(KERN_INFO "  di_eattr = %llu\n", (unsigned long long)di->di_eattr);
+}
+
+void gfs2_log_header_in(struct gfs2_log_header *lh, const void *buf)
+{
+	const struct gfs2_log_header *str = buf;
+
+	gfs2_meta_header_in(&lh->lh_header, buf);
+	lh->lh_sequence = be64_to_cpu(str->lh_sequence);
+	lh->lh_flags = be32_to_cpu(str->lh_flags);
+	lh->lh_tail = be32_to_cpu(str->lh_tail);
+	lh->lh_blkno = be32_to_cpu(str->lh_blkno);
+	lh->lh_hash = be32_to_cpu(str->lh_hash);
+}
+
+void gfs2_inum_range_in(struct gfs2_inum_range *ir, const void *buf)
+{
+	const struct gfs2_inum_range *str = buf;
+
+	ir->ir_start = be64_to_cpu(str->ir_start);
+	ir->ir_length = be64_to_cpu(str->ir_length);
+}
+
+void gfs2_inum_range_out(const struct gfs2_inum_range *ir, void *buf)
+{
+	struct gfs2_inum_range *str = buf;
+
+	str->ir_start = cpu_to_be64(ir->ir_start);
+	str->ir_length = cpu_to_be64(ir->ir_length);
+}
+
+void gfs2_statfs_change_in(struct gfs2_statfs_change *sc, const void *buf)
+{
+	const struct gfs2_statfs_change *str = buf;
+
+	sc->sc_total = be64_to_cpu(str->sc_total);
+	sc->sc_free = be64_to_cpu(str->sc_free);
+	sc->sc_dinodes = be64_to_cpu(str->sc_dinodes);
+}
+
+void gfs2_statfs_change_out(const struct gfs2_statfs_change *sc, void *buf)
+{
+	struct gfs2_statfs_change *str = buf;
+
+	str->sc_total = cpu_to_be64(sc->sc_total);
+	str->sc_free = cpu_to_be64(sc->sc_free);
+	str->sc_dinodes = cpu_to_be64(sc->sc_dinodes);
+}
+
+void gfs2_quota_change_in(struct gfs2_quota_change *qc, const void *buf)
+{
+	const struct gfs2_quota_change *str = buf;
+
+	qc->qc_change = be64_to_cpu(str->qc_change);
+	qc->qc_flags = be32_to_cpu(str->qc_flags);
+	qc->qc_id = be32_to_cpu(str->qc_id);
+}
+

fs/gfs2/ops_address.c

@@ -0,0 +1,790 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/pagemap.h>
+#include <linux/pagevec.h>
+#include <linux/mpage.h>
+#include <linux/fs.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "inode.h"
+#include "log.h"
+#include "meta_io.h"
+#include "ops_address.h"
+#include "quota.h"
+#include "trans.h"
+#include "rgrp.h"
+#include "ops_file.h"
+#include "util.h"
+#include "glops.h"
+
+
+static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
+				   unsigned int from, unsigned int to)
+{
+	struct buffer_head *head = page_buffers(page);
+	unsigned int bsize = head->b_size;
+	struct buffer_head *bh;
+	unsigned int start, end;
+
+	for (bh = head, start = 0; bh != head || !start;
+	     bh = bh->b_this_page, start = end) {
+		end = start + bsize;
+		if (end <= from || start >= to)
+			continue;
+		gfs2_trans_add_bh(ip->i_gl, bh, 0);
+	}
+}
+
+/**
+ * gfs2_get_block - Fills in a buffer head with details about a block
+ * @inode: The inode
+ * @lblock: The block number to look up
+ * @bh_result: The buffer head to return the result in
+ * @create: Non-zero if we may add block to the file
+ *
+ * Returns: errno
+ */
+
+int gfs2_get_block(struct inode *inode, sector_t lblock,
+	           struct buffer_head *bh_result, int create)
+{
+	return gfs2_block_map(inode, lblock, create, bh_result, 32);
+}
+
+/**
+ * gfs2_get_block_noalloc - Fills in a buffer head with details about a block
+ * @inode: The inode
+ * @lblock: The block number to look up
+ * @bh_result: The buffer head to return the result in
+ * @create: Non-zero if we may add block to the file
+ *
+ * Returns: errno
+ */
+
+static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
+				  struct buffer_head *bh_result, int create)
+{
+	int error;
+
+	error = gfs2_block_map(inode, lblock, 0, bh_result, 1);
+	if (error)
+		return error;
+	if (bh_result->b_blocknr == 0)
+		return -EIO;
+	return 0;
+}
+
+static int gfs2_get_block_direct(struct inode *inode, sector_t lblock,
+				 struct buffer_head *bh_result, int create)
+{
+	return gfs2_block_map(inode, lblock, 0, bh_result, 32);
+}
+
+/**
+ * gfs2_writepage - Write complete page
+ * @page: Page to write
+ *
+ * Returns: errno
+ *
+ * Some of this is copied from block_write_full_page() although we still
+ * call it to do most of the work.
+ */
+
+static int gfs2_writepage(struct page *page, struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	loff_t i_size = i_size_read(inode);
+	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	unsigned offset;
+	int error;
+	int done_trans = 0;
+
+	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl))) {
+		unlock_page(page);
+		return -EIO;
+	}
+	if (current->journal_info)
+		goto out_ignore;
+
+	/* Is the page fully outside i_size? (truncate in progress) */
+        offset = i_size & (PAGE_CACHE_SIZE-1);
+	if (page->index > end_index || (page->index == end_index && !offset)) {
+		page->mapping->a_ops->invalidatepage(page, 0);
+		unlock_page(page);
+		return 0; /* don't care */
+	}
+
+	if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) {
+		error = gfs2_trans_begin(sdp, RES_DINODE + 1, 0);
+		if (error)
+			goto out_ignore;
+		if (!page_has_buffers(page)) {
+			create_empty_buffers(page, inode->i_sb->s_blocksize,
+					     (1 << BH_Dirty)|(1 << BH_Uptodate));
+		}
+		gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize-1);
+		done_trans = 1;
+	}
+	error = block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+	if (done_trans)
+		gfs2_trans_end(sdp);
+	gfs2_meta_cache_flush(ip);
+	return error;
+
+out_ignore:
+	redirty_page_for_writepage(wbc, page);
+	unlock_page(page);
+	return 0;
+}
+
+static int zero_readpage(struct page *page)
+{
+	void *kaddr;
+
+	kaddr = kmap_atomic(page, KM_USER0);
+	memset(kaddr, 0, PAGE_CACHE_SIZE);
+	kunmap_atomic(page, KM_USER0);
+
+	SetPageUptodate(page);
+
+	return 0;
+}
+
+/**
+ * stuffed_readpage - Fill in a Linux page with stuffed file data
+ * @ip: the inode
+ * @page: the page
+ *
+ * Returns: errno
+ */
+
+static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
+{
+	struct buffer_head *dibh;
+	void *kaddr;
+	int error;
+
+	/* Only the first page of a stuffed file might contain data */
+	if (unlikely(page->index))
+		return zero_readpage(page);
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		return error;
+
+	kaddr = kmap_atomic(page, KM_USER0);
+	memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode),
+	       ip->i_di.di_size);
+	memset(kaddr + ip->i_di.di_size, 0, PAGE_CACHE_SIZE - ip->i_di.di_size);
+	kunmap_atomic(page, KM_USER0);
+
+	brelse(dibh);
+
+	SetPageUptodate(page);
+
+	return 0;
+}
+
+
+/**
+ * gfs2_readpage - readpage with locking
+ * @file: The file to read a page for. N.B. This may be NULL if we are
+ * reading an internal file.
+ * @page: The page to read
+ *
+ * Returns: errno
+ */
+
+static int gfs2_readpage(struct file *file, struct page *page)
+{
+	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
+	struct gfs2_file *gf = NULL;
+	struct gfs2_holder gh;
+	int error;
+	int do_unlock = 0;
+
+	if (likely(file != &gfs2_internal_file_sentinel)) {
+		if (file) {
+			gf = file->private_data;
+			if (test_bit(GFF_EXLOCK, &gf->f_flags))
+				/* gfs2_sharewrite_nopage has grabbed the ip->i_gl already */
+				goto skip_lock;
+		}
+		gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME|GL_AOP, &gh);
+		do_unlock = 1;
+		error = gfs2_glock_nq_m_atime(1, &gh);
+		if (unlikely(error))
+			goto out_unlock;
+	}
+
+skip_lock:
+	if (gfs2_is_stuffed(ip)) {
+		error = stuffed_readpage(ip, page);
+		unlock_page(page);
+	} else
+		error = mpage_readpage(page, gfs2_get_block);
+
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		error = -EIO;
+
+	if (do_unlock) {
+		gfs2_glock_dq_m(1, &gh);
+		gfs2_holder_uninit(&gh);
+	}
+out:
+	return error;
+out_unlock:
+	unlock_page(page);
+	if (do_unlock)
+		gfs2_holder_uninit(&gh);
+	goto out;
+}
+
+/**
+ * gfs2_readpages - Read a bunch of pages at once
+ *
+ * Some notes:
+ * 1. This is only for readahead, so we can simply ignore any things
+ *    which are slightly inconvenient (such as locking conflicts between
+ *    the page lock and the glock) and return having done no I/O. Its
+ *    obviously not something we'd want to do on too regular a basis.
+ *    Any I/O we ignore at this time will be done via readpage later.
+ * 2. We have to handle stuffed files here too.
+ * 3. mpage_readpages() does most of the heavy lifting in the common case.
+ * 4. gfs2_get_block() is relied upon to set BH_Boundary in the right places.
+ * 5. We use LM_FLAG_TRY_1CB here, effectively we then have lock-ahead as
+ *    well as read-ahead.
+ */
+static int gfs2_readpages(struct file *file, struct address_space *mapping,
+			  struct list_head *pages, unsigned nr_pages)
+{
+	struct inode *inode = mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_holder gh;
+	unsigned page_idx;
+	int ret;
+	int do_unlock = 0;
+
+	if (likely(file != &gfs2_internal_file_sentinel)) {
+		if (file) {
+			struct gfs2_file *gf = file->private_data;
+			if (test_bit(GFF_EXLOCK, &gf->f_flags))
+				goto skip_lock;
+		}
+		gfs2_holder_init(ip->i_gl, LM_ST_SHARED,
+				 LM_FLAG_TRY_1CB|GL_ATIME|GL_AOP, &gh);
+		do_unlock = 1;
+		ret = gfs2_glock_nq_m_atime(1, &gh);
+		if (ret == GLR_TRYFAILED)
+			goto out_noerror;
+		if (unlikely(ret))
+			goto out_unlock;
+	}
+skip_lock:
+	if (gfs2_is_stuffed(ip)) {
+		struct pagevec lru_pvec;
+		pagevec_init(&lru_pvec, 0);
+		for (page_idx = 0; page_idx < nr_pages; page_idx++) {
+			struct page *page = list_entry(pages->prev, struct page, lru);
+			prefetchw(&page->flags);
+			list_del(&page->lru);
+			if (!add_to_page_cache(page, mapping,
+					       page->index, GFP_KERNEL)) {
+				ret = stuffed_readpage(ip, page);
+				unlock_page(page);
+				if (!pagevec_add(&lru_pvec, page))
+					 __pagevec_lru_add(&lru_pvec);
+			} else {
+				page_cache_release(page);
+			}
+		}
+		pagevec_lru_add(&lru_pvec);
+		ret = 0;
+	} else {
+		/* What we really want to do .... */
+		ret = mpage_readpages(mapping, pages, nr_pages, gfs2_get_block);
+	}
+
+	if (do_unlock) {
+		gfs2_glock_dq_m(1, &gh);
+		gfs2_holder_uninit(&gh);
+	}
+out:
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		ret = -EIO;
+	return ret;
+out_noerror:
+	ret = 0;
+out_unlock:
+	/* unlock all pages, we can't do any I/O right now */
+	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
+		struct page *page = list_entry(pages->prev, struct page, lru);
+		list_del(&page->lru);
+		unlock_page(page);
+		page_cache_release(page);
+	}
+	if (do_unlock)
+		gfs2_holder_uninit(&gh);
+	goto out;
+}
+
+/**
+ * gfs2_prepare_write - Prepare to write a page to a file
+ * @file: The file to write to
+ * @page: The page which is to be prepared for writing
+ * @from: From (byte range within page)
+ * @to: To (byte range within page)
+ *
+ * Returns: errno
+ */
+
+static int gfs2_prepare_write(struct file *file, struct page *page,
+			      unsigned from, unsigned to)
+{
+	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
+	unsigned int data_blocks, ind_blocks, rblocks;
+	int alloc_required;
+	int error = 0;
+	loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + from;
+	loff_t end = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+	struct gfs2_alloc *al;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME|GL_AOP, &ip->i_gh);
+	error = gfs2_glock_nq_m_atime(1, &ip->i_gh);
+	if (error)
+		goto out_uninit;
+
+	gfs2_write_calc_reserv(ip, to - from, &data_blocks, &ind_blocks);
+
+	error = gfs2_write_alloc_required(ip, pos, from - to, &alloc_required);
+	if (error)
+		goto out_unlock;
+
+
+	if (alloc_required) {
+		al = gfs2_alloc_get(ip);
+
+		error = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+		if (error)
+			goto out_alloc_put;
+
+		error = gfs2_quota_check(ip, ip->i_di.di_uid, ip->i_di.di_gid);
+		if (error)
+			goto out_qunlock;
+
+		al->al_requested = data_blocks + ind_blocks;
+		error = gfs2_inplace_reserve(ip);
+		if (error)
+			goto out_qunlock;
+	}
+
+	rblocks = RES_DINODE + ind_blocks;
+	if (gfs2_is_jdata(ip))
+		rblocks += data_blocks ? data_blocks : 1;
+	if (ind_blocks || data_blocks)
+		rblocks += RES_STATFS + RES_QUOTA;
+
+	error = gfs2_trans_begin(sdp, rblocks, 0);
+	if (error)
+		goto out;
+
+	if (gfs2_is_stuffed(ip)) {
+		if (end > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) {
+			error = gfs2_unstuff_dinode(ip, page);
+			if (error == 0)
+				goto prepare_write;
+		} else if (!PageUptodate(page))
+			error = stuffed_readpage(ip, page);
+		goto out;
+	}
+
+prepare_write:
+	error = block_prepare_write(page, from, to, gfs2_get_block);
+
+out:
+	if (error) {
+		gfs2_trans_end(sdp);
+		if (alloc_required) {
+			gfs2_inplace_release(ip);
+out_qunlock:
+			gfs2_quota_unlock(ip);
+out_alloc_put:
+			gfs2_alloc_put(ip);
+		}
+out_unlock:
+		gfs2_glock_dq_m(1, &ip->i_gh);
+out_uninit:
+		gfs2_holder_uninit(&ip->i_gh);
+	}
+
+	return error;
+}
+
+/**
+ * gfs2_commit_write - Commit write to a file
+ * @file: The file to write to
+ * @page: The page containing the data
+ * @from: From (byte range within page)
+ * @to: To (byte range within page)
+ *
+ * Returns: errno
+ */
+
+static int gfs2_commit_write(struct file *file, struct page *page,
+			     unsigned from, unsigned to)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	int error = -EOPNOTSUPP;
+	struct buffer_head *dibh;
+	struct gfs2_alloc *al = &ip->i_alloc;
+	struct gfs2_dinode *di;
+
+	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_locked_by_me(ip->i_gl)))
+                goto fail_nounlock;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		goto fail_endtrans;
+
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	di = (struct gfs2_dinode *)dibh->b_data;
+
+	if (gfs2_is_stuffed(ip)) {
+		u64 file_size;
+		void *kaddr;
+
+		file_size = ((u64)page->index << PAGE_CACHE_SHIFT) + to;
+
+		kaddr = kmap_atomic(page, KM_USER0);
+		memcpy(dibh->b_data + sizeof(struct gfs2_dinode) + from,
+		       kaddr + from, to - from);
+		kunmap_atomic(page, KM_USER0);
+
+		SetPageUptodate(page);
+
+		if (inode->i_size < file_size)
+			i_size_write(inode, file_size);
+	} else {
+		if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED ||
+		    gfs2_is_jdata(ip))
+			gfs2_page_add_databufs(ip, page, from, to);
+		error = generic_commit_write(file, page, from, to);
+		if (error)
+			goto fail;
+	}
+
+	if (ip->i_di.di_size < inode->i_size) {
+		ip->i_di.di_size = inode->i_size;
+		di->di_size = cpu_to_be64(inode->i_size);
+	}
+
+	di->di_mode = cpu_to_be32(inode->i_mode);
+	di->di_atime = cpu_to_be64(inode->i_atime.tv_sec);
+	di->di_mtime = cpu_to_be64(inode->i_mtime.tv_sec);
+	di->di_ctime = cpu_to_be64(inode->i_ctime.tv_sec);
+
+	brelse(dibh);
+	gfs2_trans_end(sdp);
+	if (al->al_requested) {
+		gfs2_inplace_release(ip);
+		gfs2_quota_unlock(ip);
+		gfs2_alloc_put(ip);
+	}
+	gfs2_glock_dq_m(1, &ip->i_gh);
+	gfs2_holder_uninit(&ip->i_gh);
+	return 0;
+
+fail:
+	brelse(dibh);
+fail_endtrans:
+	gfs2_trans_end(sdp);
+	if (al->al_requested) {
+		gfs2_inplace_release(ip);
+		gfs2_quota_unlock(ip);
+		gfs2_alloc_put(ip);
+	}
+	gfs2_glock_dq_m(1, &ip->i_gh);
+	gfs2_holder_uninit(&ip->i_gh);
+fail_nounlock:
+	ClearPageUptodate(page);
+	return error;
+}
+
+/**
+ * gfs2_bmap - Block map function
+ * @mapping: Address space info
+ * @lblock: The block to map
+ *
+ * Returns: The disk address for the block or 0 on hole or error
+ */
+
+static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock)
+{
+	struct gfs2_inode *ip = GFS2_I(mapping->host);
+	struct gfs2_holder i_gh;
+	sector_t dblock = 0;
+	int error;
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+	if (error)
+		return 0;
+
+	if (!gfs2_is_stuffed(ip))
+		dblock = generic_block_bmap(mapping, lblock, gfs2_get_block);
+
+	gfs2_glock_dq_uninit(&i_gh);
+
+	return dblock;
+}
+
+static void discard_buffer(struct gfs2_sbd *sdp, struct buffer_head *bh)
+{
+	struct gfs2_bufdata *bd;
+
+	gfs2_log_lock(sdp);
+	bd = bh->b_private;
+	if (bd) {
+		bd->bd_bh = NULL;
+		bh->b_private = NULL;
+	}
+	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);
+	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;
+
+	BUG_ON(!PageLocked(page));
+	if (!page_has_buffers(page))
+		return;
+
+	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;
+	} while (bh != head);
+
+	if (!offset)
+		try_to_release_page(page, 0);
+
+	return;
+}
+
+static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
+			      const struct iovec *iov, loff_t offset,
+			      unsigned long nr_segs)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int rv;
+
+	if (rw == READ)
+		mutex_lock(&inode->i_mutex);
+	/*
+	 * Shared lock, even if its a write, since we do no allocation
+	 * on this path. All we need change is atime.
+	 */
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
+	rv = gfs2_glock_nq_m_atime(1, &gh);
+	if (rv)
+		goto out;
+
+	if (offset > i_size_read(inode))
+		goto out;
+
+	/*
+	 * Should we return an error here? I can't see that O_DIRECT for
+	 * a journaled file makes any sense. For now we'll silently fall
+	 * back to buffered I/O, likewise we do the same for stuffed
+	 * files since they are (a) small and (b) unaligned.
+	 */
+	if (gfs2_is_jdata(ip))
+		goto out;
+
+	if (gfs2_is_stuffed(ip))
+		goto out;
+
+	rv = blockdev_direct_IO_own_locking(rw, iocb, inode,
+					    inode->i_sb->s_bdev,
+					    iov, offset, nr_segs,
+					    gfs2_get_block_direct, NULL);
+out:
+	gfs2_glock_dq_m(1, &gh);
+	gfs2_holder_uninit(&gh);
+	if (rw == READ)
+		mutex_unlock(&inode->i_mutex);
+
+	return rv;
+}
+
+/**
+ * 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_num.no_formal_ino,
+			(unsigned long long)ip->i_num.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
+ *
+ * Call try_to_free_buffers() if the buffers in this page can be
+ * released.
+ *
+ * Returns: 0
+ */
+
+int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
+{
+	struct inode *aspace = page->mapping->host;
+	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;
+
+	head = bh = page_buffers(page);
+	do {
+		while (atomic_read(&bh->b_count)) {
+			if (!atomic_read(&aspace->i_writecount))
+				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;
+			bh->b_private = NULL;
+		}
+		gfs2_log_unlock(sdp);
+		if (bd)
+			kmem_cache_free(gfs2_bufdata_cachep, bd);
+
+		bh = bh->b_this_page;
+	} while (bh != head);
+
+out:
+	return try_to_free_buffers(page);
+}
+
+const struct address_space_operations gfs2_file_aops = {
+	.writepage = gfs2_writepage,
+	.readpage = gfs2_readpage,
+	.readpages = gfs2_readpages,
+	.sync_page = block_sync_page,
+	.prepare_write = gfs2_prepare_write,
+	.commit_write = gfs2_commit_write,
+	.bmap = gfs2_bmap,
+	.invalidatepage = gfs2_invalidatepage,
+	.releasepage = gfs2_releasepage,
+	.direct_IO = gfs2_direct_IO,
+};
+

fs/gfs2/ops_address.h

@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __OPS_ADDRESS_DOT_H__
+#define __OPS_ADDRESS_DOT_H__
+
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/mm.h>
+
+extern const struct address_space_operations gfs2_file_aops;
+extern int gfs2_get_block(struct inode *inode, sector_t lblock,
+			  struct buffer_head *bh_result, int create);
+extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask);
+
+#endif /* __OPS_ADDRESS_DOT_H__ */

fs/gfs2/ops_dentry.c

@@ -0,0 +1,119 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/smp_lock.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "dir.h"
+#include "glock.h"
+#include "ops_dentry.h"
+#include "util.h"
+
+/**
+ * gfs2_drevalidate - Check directory lookup consistency
+ * @dentry: the mapping to check
+ * @nd:
+ *
+ * Check to make sure the lookup necessary to arrive at this inode from its
+ * parent is still good.
+ *
+ * Returns: 1 if the dentry is ok, 0 if it isn't
+ */
+
+static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd)
+{
+	struct dentry *parent = dget_parent(dentry);
+	struct gfs2_sbd *sdp = GFS2_SB(parent->d_inode);
+	struct gfs2_inode *dip = GFS2_I(parent->d_inode);
+	struct inode *inode = dentry->d_inode;
+	struct gfs2_holder d_gh;
+	struct gfs2_inode *ip;
+	struct gfs2_inum inum;
+	unsigned int type;
+	int error;
+
+	if (inode && is_bad_inode(inode))
+		goto invalid;
+
+	if (sdp->sd_args.ar_localcaching)
+		goto valid;
+
+	error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
+	if (error)
+		goto fail;
+
+	error = gfs2_dir_search(parent->d_inode, &dentry->d_name, &inum, &type);
+	switch (error) {
+	case 0:
+		if (!inode)
+			goto invalid_gunlock;
+		break;
+	case -ENOENT:
+		if (!inode)
+			goto valid_gunlock;
+		goto invalid_gunlock;
+	default:
+		goto fail_gunlock;
+	}
+
+	ip = GFS2_I(inode);
+
+	if (!gfs2_inum_equal(&ip->i_num, &inum))
+		goto invalid_gunlock;
+
+	if (IF2DT(ip->i_di.di_mode) != type) {
+		gfs2_consist_inode(dip);
+		goto fail_gunlock;
+	}
+
+valid_gunlock:
+	gfs2_glock_dq_uninit(&d_gh);
+valid:
+	dput(parent);
+	return 1;
+
+invalid_gunlock:
+	gfs2_glock_dq_uninit(&d_gh);
+invalid:
+	if (inode && S_ISDIR(inode->i_mode)) {
+		if (have_submounts(dentry))
+			goto valid;
+		shrink_dcache_parent(dentry);
+	}
+	d_drop(dentry);
+	dput(parent);
+	return 0;
+
+fail_gunlock:
+	gfs2_glock_dq_uninit(&d_gh);
+fail:
+	dput(parent);
+	return 0;
+}
+
+static int gfs2_dhash(struct dentry *dentry, struct qstr *str)
+{
+	str->hash = gfs2_disk_hash(str->name, str->len);
+	return 0;
+}
+
+struct dentry_operations gfs2_dops = {
+	.d_revalidate = gfs2_drevalidate,
+	.d_hash = gfs2_dhash,
+};
+

fs/gfs2/ops_dentry.h

@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __OPS_DENTRY_DOT_H__
+#define __OPS_DENTRY_DOT_H__
+
+#include <linux/dcache.h>
+
+extern struct dentry_operations gfs2_dops;
+
+#endif /* __OPS_DENTRY_DOT_H__ */

fs/gfs2/ops_export.c

@@ -0,0 +1,298 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "dir.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "ops_export.h"
+#include "rgrp.h"
+#include "util.h"
+
+static struct dentry *gfs2_decode_fh(struct super_block *sb,
+				     __u32 *fh,
+				     int fh_len,
+				     int fh_type,
+				     int (*acceptable)(void *context,
+						       struct dentry *dentry),
+				     void *context)
+{
+	struct gfs2_fh_obj fh_obj;
+	struct gfs2_inum *this, parent;
+
+	if (fh_type != fh_len)
+		return NULL;
+
+	this 		= &fh_obj.this;
+	fh_obj.imode 	= DT_UNKNOWN;
+	memset(&parent, 0, sizeof(struct gfs2_inum));
+
+	switch (fh_type) {
+	case GFS2_LARGE_FH_SIZE:
+		parent.no_formal_ino = ((u64)be32_to_cpu(fh[4])) << 32;
+		parent.no_formal_ino |= be32_to_cpu(fh[5]);
+		parent.no_addr = ((u64)be32_to_cpu(fh[6])) << 32;
+		parent.no_addr |= be32_to_cpu(fh[7]);
+		fh_obj.imode = be32_to_cpu(fh[8]);
+	case GFS2_SMALL_FH_SIZE:
+		this->no_formal_ino = ((u64)be32_to_cpu(fh[0])) << 32;
+		this->no_formal_ino |= be32_to_cpu(fh[1]);
+		this->no_addr = ((u64)be32_to_cpu(fh[2])) << 32;
+		this->no_addr |= be32_to_cpu(fh[3]);
+		break;
+	default:
+		return NULL;
+	}
+
+	return gfs2_export_ops.find_exported_dentry(sb, &fh_obj, &parent,
+						    acceptable, context);
+}
+
+static int gfs2_encode_fh(struct dentry *dentry, __u32 *fh, int *len,
+			  int connectable)
+{
+	struct inode *inode = dentry->d_inode;
+	struct super_block *sb = inode->i_sb;
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	if (*len < GFS2_SMALL_FH_SIZE ||
+	    (connectable && *len < GFS2_LARGE_FH_SIZE))
+		return 255;
+
+	fh[0] = ip->i_num.no_formal_ino >> 32;
+	fh[0] = cpu_to_be32(fh[0]);
+	fh[1] = ip->i_num.no_formal_ino & 0xFFFFFFFF;
+	fh[1] = cpu_to_be32(fh[1]);
+	fh[2] = ip->i_num.no_addr >> 32;
+	fh[2] = cpu_to_be32(fh[2]);
+	fh[3] = ip->i_num.no_addr & 0xFFFFFFFF;
+	fh[3] = cpu_to_be32(fh[3]);
+	*len = GFS2_SMALL_FH_SIZE;
+
+	if (!connectable || inode == sb->s_root->d_inode)
+		return *len;
+
+	spin_lock(&dentry->d_lock);
+	inode = dentry->d_parent->d_inode;
+	ip = GFS2_I(inode);
+	igrab(inode);
+	spin_unlock(&dentry->d_lock);
+
+	fh[4] = ip->i_num.no_formal_ino >> 32;
+	fh[4] = cpu_to_be32(fh[4]);
+	fh[5] = ip->i_num.no_formal_ino & 0xFFFFFFFF;
+	fh[5] = cpu_to_be32(fh[5]);
+	fh[6] = ip->i_num.no_addr >> 32;
+	fh[6] = cpu_to_be32(fh[6]);
+	fh[7] = ip->i_num.no_addr & 0xFFFFFFFF;
+	fh[7] = cpu_to_be32(fh[7]);
+
+	fh[8]  = cpu_to_be32(inode->i_mode);
+	fh[9]  = 0;	/* pad to double word */
+	*len = GFS2_LARGE_FH_SIZE;
+
+	iput(inode);
+
+	return *len;
+}
+
+struct get_name_filldir {
+	struct gfs2_inum inum;
+	char *name;
+};
+
+static int get_name_filldir(void *opaque, const char *name, unsigned int length,
+			    u64 offset, struct gfs2_inum *inum,
+			    unsigned int type)
+{
+	struct get_name_filldir *gnfd = (struct get_name_filldir *)opaque;
+
+	if (!gfs2_inum_equal(inum, &gnfd->inum))
+		return 0;
+
+	memcpy(gnfd->name, name, length);
+	gnfd->name[length] = 0;
+
+	return 1;
+}
+
+static int gfs2_get_name(struct dentry *parent, char *name,
+			 struct dentry *child)
+{
+	struct inode *dir = parent->d_inode;
+	struct inode *inode = child->d_inode;
+	struct gfs2_inode *dip, *ip;
+	struct get_name_filldir gnfd;
+	struct gfs2_holder gh;
+	u64 offset = 0;
+	int error;
+
+	if (!dir)
+		return -EINVAL;
+
+	if (!S_ISDIR(dir->i_mode) || !inode)
+		return -EINVAL;
+
+	dip = GFS2_I(dir);
+	ip = GFS2_I(inode);
+
+	*name = 0;
+	gnfd.inum = ip->i_num;
+	gnfd.name = name;
+
+	error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &gh);
+	if (error)
+		return error;
+
+	error = gfs2_dir_read(dir, &offset, &gnfd, get_name_filldir);
+
+	gfs2_glock_dq_uninit(&gh);
+
+	if (!error && !*name)
+		error = -ENOENT;
+
+	return error;
+}
+
+static struct dentry *gfs2_get_parent(struct dentry *child)
+{
+	struct qstr dotdot;
+	struct inode *inode;
+	struct dentry *dentry;
+
+	gfs2_str2qstr(&dotdot, "..");
+	inode = gfs2_lookupi(child->d_inode, &dotdot, 1, NULL);
+
+	if (!inode)
+		return ERR_PTR(-ENOENT);
+	/*
+	 * In case of an error, @inode carries the error value, and we
+	 * have to return that as a(n invalid) pointer to dentry.
+	 */
+	if (IS_ERR(inode))
+		return ERR_PTR(PTR_ERR(inode));
+
+	dentry = d_alloc_anon(inode);
+	if (!dentry) {
+		iput(inode);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return dentry;
+}
+
+static struct dentry *gfs2_get_dentry(struct super_block *sb, void *inum_obj)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_fh_obj *fh_obj = (struct gfs2_fh_obj *)inum_obj;
+	struct gfs2_inum *inum = &fh_obj->this;
+	struct gfs2_holder i_gh, ri_gh, rgd_gh;
+	struct gfs2_rgrpd *rgd;
+	struct inode *inode;
+	struct dentry *dentry;
+	int error;
+
+	/* System files? */
+
+	inode = gfs2_ilookup(sb, inum);
+	if (inode) {
+		if (GFS2_I(inode)->i_num.no_formal_ino != inum->no_formal_ino) {
+			iput(inode);
+			return ERR_PTR(-ESTALE);
+		}
+		goto out_inode;
+	}
+
+	error = gfs2_glock_nq_num(sdp, inum->no_addr, &gfs2_inode_glops,
+				  LM_ST_SHARED, LM_FLAG_ANY | GL_LOCAL_EXCL,
+				  &i_gh);
+	if (error)
+		return ERR_PTR(error);
+
+	error = gfs2_rindex_hold(sdp, &ri_gh);
+	if (error)
+		goto fail;
+
+	error = -EINVAL;
+	rgd = gfs2_blk2rgrpd(sdp, inum->no_addr);
+	if (!rgd)
+		goto fail_rindex;
+
+	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_SHARED, 0, &rgd_gh);
+	if (error)
+		goto fail_rindex;
+
+	error = -ESTALE;
+	if (gfs2_get_block_type(rgd, inum->no_addr) != GFS2_BLKST_DINODE)
+		goto fail_rgd;
+
+	gfs2_glock_dq_uninit(&rgd_gh);
+	gfs2_glock_dq_uninit(&ri_gh);
+
+	inode = gfs2_inode_lookup(sb, inum, fh_obj->imode);
+	if (!inode)
+		goto fail;
+	if (IS_ERR(inode)) {
+		error = PTR_ERR(inode);
+		goto fail;
+	}
+
+	error = gfs2_inode_refresh(GFS2_I(inode));
+	if (error) {
+		iput(inode);
+		goto fail;
+	}
+
+	error = -EIO;
+	if (GFS2_I(inode)->i_di.di_flags & GFS2_DIF_SYSTEM) {
+		iput(inode);
+		goto fail;
+	}
+
+	gfs2_glock_dq_uninit(&i_gh);
+
+out_inode:
+	dentry = d_alloc_anon(inode);
+	if (!dentry) {
+		iput(inode);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return dentry;
+
+fail_rgd:
+	gfs2_glock_dq_uninit(&rgd_gh);
+
+fail_rindex:
+	gfs2_glock_dq_uninit(&ri_gh);
+
+fail:
+	gfs2_glock_dq_uninit(&i_gh);
+	return ERR_PTR(error);
+}
+
+struct export_operations gfs2_export_ops = {
+	.decode_fh = gfs2_decode_fh,
+	.encode_fh = gfs2_encode_fh,
+	.get_name = gfs2_get_name,
+	.get_parent = gfs2_get_parent,
+	.get_dentry = gfs2_get_dentry,
+};
+

fs/gfs2/ops_export.h

@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __OPS_EXPORT_DOT_H__
+#define __OPS_EXPORT_DOT_H__
+
+#define GFS2_SMALL_FH_SIZE 4
+#define GFS2_LARGE_FH_SIZE 10
+
+extern struct export_operations gfs2_export_ops;
+struct gfs2_fh_obj {
+	struct gfs2_inum this;
+	__u32            imode;
+};
+
+#endif /* __OPS_EXPORT_DOT_H__ */

fs/gfs2/ops_file.c

@@ -0,0 +1,661 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/pagemap.h>
+#include <linux/uio.h>
+#include <linux/blkdev.h>
+#include <linux/mm.h>
+#include <linux/smp_lock.h>
+#include <linux/fs.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/ext2_fs.h>
+#include <linux/crc32.h>
+#include <linux/lm_interface.h>
+#include <asm/uaccess.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "dir.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "lm.h"
+#include "log.h"
+#include "meta_io.h"
+#include "ops_file.h"
+#include "ops_vm.h"
+#include "quota.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+#include "eaops.h"
+
+/* For regular, non-NFS */
+struct filldir_reg {
+	struct gfs2_sbd *fdr_sbd;
+	int fdr_prefetch;
+
+	filldir_t fdr_filldir;
+	void *fdr_opaque;
+};
+
+/*
+ * Most fields left uninitialised to catch anybody who tries to
+ * use them. f_flags set to prevent file_accessed() from touching
+ * any other part of this. Its use is purely as a flag so that we
+ * know (in readpage()) whether or not do to locking.
+ */
+struct file gfs2_internal_file_sentinel = {
+	.f_flags = O_NOATIME|O_RDONLY,
+};
+
+static int gfs2_read_actor(read_descriptor_t *desc, struct page *page,
+			   unsigned long offset, unsigned long size)
+{
+	char *kaddr;
+	unsigned long count = desc->count;
+
+	if (size > count)
+		size = count;
+
+	kaddr = kmap(page);
+	memcpy(desc->arg.buf, kaddr + offset, size);
+	kunmap(page);
+
+	desc->count = count - size;
+	desc->written += size;
+	desc->arg.buf += size;
+	return size;
+}
+
+int gfs2_internal_read(struct gfs2_inode *ip, struct file_ra_state *ra_state,
+		       char *buf, loff_t *pos, unsigned size)
+{
+	struct inode *inode = &ip->i_inode;
+	read_descriptor_t desc;
+	desc.written = 0;
+	desc.arg.buf = buf;
+	desc.count = size;
+	desc.error = 0;
+	do_generic_mapping_read(inode->i_mapping, ra_state,
+				&gfs2_internal_file_sentinel, pos, &desc,
+				gfs2_read_actor);
+	return desc.written ? desc.written : desc.error;
+}
+
+/**
+ * gfs2_llseek - seek to a location in a file
+ * @file: the file
+ * @offset: the offset
+ * @origin: Where to seek from (SEEK_SET, SEEK_CUR, or SEEK_END)
+ *
+ * SEEK_END requires the glock for the file because it references the
+ * file's size.
+ *
+ * Returns: The new offset, or errno
+ */
+
+static loff_t gfs2_llseek(struct file *file, loff_t offset, int origin)
+{
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+	struct gfs2_holder i_gh;
+	loff_t error;
+
+	if (origin == 2) {
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
+					   &i_gh);
+		if (!error) {
+			error = remote_llseek(file, offset, origin);
+			gfs2_glock_dq_uninit(&i_gh);
+		}
+	} else
+		error = remote_llseek(file, offset, origin);
+
+	return error;
+}
+
+/**
+ * filldir_func - Report a directory entry to the caller of gfs2_dir_read()
+ * @opaque: opaque data used by the function
+ * @name: the name of the directory entry
+ * @length: the length of the name
+ * @offset: the entry's offset in the directory
+ * @inum: the inode number the entry points to
+ * @type: the type of inode the entry points to
+ *
+ * Returns: 0 on success, 1 if buffer full
+ */
+
+static int filldir_func(void *opaque, const char *name, unsigned int length,
+			u64 offset, struct gfs2_inum *inum,
+			unsigned int type)
+{
+	struct filldir_reg *fdr = (struct filldir_reg *)opaque;
+	struct gfs2_sbd *sdp = fdr->fdr_sbd;
+	int error;
+
+	error = fdr->fdr_filldir(fdr->fdr_opaque, name, length, offset,
+				 inum->no_addr, type);
+	if (error)
+		return 1;
+
+	if (fdr->fdr_prefetch && !(length == 1 && *name == '.')) {
+		gfs2_glock_prefetch_num(sdp, inum->no_addr, &gfs2_inode_glops,
+				       LM_ST_SHARED, LM_FLAG_TRY | LM_FLAG_ANY);
+		gfs2_glock_prefetch_num(sdp, inum->no_addr, &gfs2_iopen_glops,
+				       LM_ST_SHARED, LM_FLAG_TRY);
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_readdir - Read directory entries from a directory
+ * @file: The directory to read from
+ * @dirent: Buffer for dirents
+ * @filldir: Function used to do the copying
+ *
+ * Returns: errno
+ */
+
+static int gfs2_readdir(struct file *file, void *dirent, filldir_t filldir)
+{
+	struct inode *dir = file->f_mapping->host;
+	struct gfs2_inode *dip = GFS2_I(dir);
+	struct filldir_reg fdr;
+	struct gfs2_holder d_gh;
+	u64 offset = file->f_pos;
+	int error;
+
+	fdr.fdr_sbd = GFS2_SB(dir);
+	fdr.fdr_prefetch = 1;
+	fdr.fdr_filldir = filldir;
+	fdr.fdr_opaque = dirent;
+
+	gfs2_holder_init(dip->i_gl, LM_ST_SHARED, GL_ATIME, &d_gh);
+	error = gfs2_glock_nq_atime(&d_gh);
+	if (error) {
+		gfs2_holder_uninit(&d_gh);
+		return error;
+	}
+
+	error = gfs2_dir_read(dir, &offset, &fdr, filldir_func);
+
+	gfs2_glock_dq_uninit(&d_gh);
+
+	file->f_pos = offset;
+
+	return error;
+}
+
+/**
+ * fsflags_cvt
+ * @table: A table of 32 u32 flags
+ * @val: a 32 bit value to convert
+ *
+ * This function can be used to convert between fsflags values and
+ * GFS2's own flags values.
+ *
+ * Returns: the converted flags
+ */
+static u32 fsflags_cvt(const u32 *table, u32 val)
+{
+	u32 res = 0;
+	while(val) {
+		if (val & 1)
+			res |= *table;
+		table++;
+		val >>= 1;
+	}
+	return res;
+}
+
+static const u32 fsflags_to_gfs2[32] = {
+	[3] = GFS2_DIF_SYNC,
+	[4] = GFS2_DIF_IMMUTABLE,
+	[5] = GFS2_DIF_APPENDONLY,
+	[7] = GFS2_DIF_NOATIME,
+	[12] = GFS2_DIF_EXHASH,
+	[14] = GFS2_DIF_JDATA,
+	[20] = GFS2_DIF_DIRECTIO,
+};
+
+static const u32 gfs2_to_fsflags[32] = {
+	[gfs2fl_Sync] = FS_SYNC_FL,
+	[gfs2fl_Immutable] = FS_IMMUTABLE_FL,
+	[gfs2fl_AppendOnly] = FS_APPEND_FL,
+	[gfs2fl_NoAtime] = FS_NOATIME_FL,
+	[gfs2fl_ExHash] = FS_INDEX_FL,
+	[gfs2fl_Jdata] = FS_JOURNAL_DATA_FL,
+	[gfs2fl_Directio] = FS_DIRECTIO_FL,
+	[gfs2fl_InheritDirectio] = FS_DIRECTIO_FL,
+	[gfs2fl_InheritJdata] = FS_JOURNAL_DATA_FL,
+};
+
+static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
+{
+	struct inode *inode = filp->f_dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int error;
+	u32 fsflags;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
+	error = gfs2_glock_nq_m_atime(1, &gh);
+	if (error)
+		return error;
+
+	fsflags = fsflags_cvt(gfs2_to_fsflags, ip->i_di.di_flags);
+	if (put_user(fsflags, ptr))
+		error = -EFAULT;
+
+	gfs2_glock_dq_m(1, &gh);
+	gfs2_holder_uninit(&gh);
+	return error;
+}
+
+/* Flags that can be set by user space */
+#define GFS2_FLAGS_USER_SET (GFS2_DIF_JDATA|			\
+			     GFS2_DIF_DIRECTIO|			\
+			     GFS2_DIF_IMMUTABLE|		\
+			     GFS2_DIF_APPENDONLY|		\
+			     GFS2_DIF_NOATIME|			\
+			     GFS2_DIF_SYNC|			\
+			     GFS2_DIF_SYSTEM|			\
+			     GFS2_DIF_INHERIT_DIRECTIO|		\
+			     GFS2_DIF_INHERIT_JDATA)
+
+/**
+ * gfs2_set_flags - set flags on an inode
+ * @inode: The inode
+ * @flags: The flags to set
+ * @mask: Indicates which flags are valid
+ *
+ */
+static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
+{
+	struct inode *inode = filp->f_dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct buffer_head *bh;
+	struct gfs2_holder gh;
+	int error;
+	u32 new_flags, flags;
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	if (error)
+		return error;
+
+	flags = ip->i_di.di_flags;
+	new_flags = (flags & ~mask) | (reqflags & mask);
+	if ((new_flags ^ flags) == 0)
+		goto out;
+
+	if (S_ISDIR(inode->i_mode)) {
+		if ((new_flags ^ flags) & GFS2_DIF_JDATA)
+			new_flags ^= (GFS2_DIF_JDATA|GFS2_DIF_INHERIT_JDATA);
+		if ((new_flags ^ flags) & GFS2_DIF_DIRECTIO)
+			new_flags ^= (GFS2_DIF_DIRECTIO|GFS2_DIF_INHERIT_DIRECTIO);
+	}
+
+	error = -EINVAL;
+	if ((new_flags ^ flags) & ~GFS2_FLAGS_USER_SET)
+		goto out;
+
+	error = -EPERM;
+	if (IS_IMMUTABLE(inode) && (new_flags & GFS2_DIF_IMMUTABLE))
+		goto out;
+	if (IS_APPEND(inode) && (new_flags & GFS2_DIF_APPENDONLY))
+		goto out;
+	if (((new_flags ^ flags) & GFS2_DIF_IMMUTABLE) &&
+	    !capable(CAP_LINUX_IMMUTABLE))
+		goto out;
+	if (!IS_IMMUTABLE(inode)) {
+		error = permission(inode, MAY_WRITE, NULL);
+		if (error)
+			goto out;
+	}
+
+	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
+	if (error)
+		goto out;
+	error = gfs2_meta_inode_buffer(ip, &bh);
+	if (error)
+		goto out_trans_end;
+	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+	ip->i_di.di_flags = new_flags;
+	gfs2_dinode_out(&ip->i_di, bh->b_data);
+	brelse(bh);
+out_trans_end:
+	gfs2_trans_end(sdp);
+out:
+	gfs2_glock_dq_uninit(&gh);
+	return error;
+}
+
+static int gfs2_set_flags(struct file *filp, u32 __user *ptr)
+{
+	u32 fsflags, gfsflags;
+	if (get_user(fsflags, ptr))
+		return -EFAULT;
+	gfsflags = fsflags_cvt(fsflags_to_gfs2, fsflags);
+	return do_gfs2_set_flags(filp, gfsflags, ~0);
+}
+
+static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	switch(cmd) {
+	case FS_IOC_GETFLAGS:
+		return gfs2_get_flags(filp, (u32 __user *)arg);
+	case FS_IOC_SETFLAGS:
+		return gfs2_set_flags(filp, (u32 __user *)arg);
+	}
+	return -ENOTTY;
+}
+
+
+/**
+ * gfs2_mmap -
+ * @file: The file to map
+ * @vma: The VMA which described the mapping
+ *
+ * Returns: 0 or error code
+ */
+
+static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+	struct gfs2_holder i_gh;
+	int error;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &i_gh);
+	error = gfs2_glock_nq_atime(&i_gh);
+	if (error) {
+		gfs2_holder_uninit(&i_gh);
+		return error;
+	}
+
+	/* This is VM_MAYWRITE instead of VM_WRITE because a call
+	   to mprotect() can turn on VM_WRITE later. */
+
+	if ((vma->vm_flags & (VM_MAYSHARE | VM_MAYWRITE)) ==
+	    (VM_MAYSHARE | VM_MAYWRITE))
+		vma->vm_ops = &gfs2_vm_ops_sharewrite;
+	else
+		vma->vm_ops = &gfs2_vm_ops_private;
+
+	gfs2_glock_dq_uninit(&i_gh);
+
+	return error;
+}
+
+/**
+ * gfs2_open - open a file
+ * @inode: the inode to open
+ * @file: the struct file for this opening
+ *
+ * Returns: errno
+ */
+
+static int gfs2_open(struct inode *inode, struct file *file)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder i_gh;
+	struct gfs2_file *fp;
+	int error;
+
+	fp = kzalloc(sizeof(struct gfs2_file), GFP_KERNEL);
+	if (!fp)
+		return -ENOMEM;
+
+	mutex_init(&fp->f_fl_mutex);
+
+	gfs2_assert_warn(GFS2_SB(inode), !file->private_data);
+	file->private_data = fp;
+
+	if (S_ISREG(ip->i_di.di_mode)) {
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
+					   &i_gh);
+		if (error)
+			goto fail;
+
+		if (!(file->f_flags & O_LARGEFILE) &&
+		    ip->i_di.di_size > MAX_NON_LFS) {
+			error = -EFBIG;
+			goto fail_gunlock;
+		}
+
+		/* Listen to the Direct I/O flag */
+
+		if (ip->i_di.di_flags & GFS2_DIF_DIRECTIO)
+			file->f_flags |= O_DIRECT;
+
+		gfs2_glock_dq_uninit(&i_gh);
+	}
+
+	return 0;
+
+fail_gunlock:
+	gfs2_glock_dq_uninit(&i_gh);
+fail:
+	file->private_data = NULL;
+	kfree(fp);
+	return error;
+}
+
+/**
+ * gfs2_close - called to close a struct file
+ * @inode: the inode the struct file belongs to
+ * @file: the struct file being closed
+ *
+ * Returns: errno
+ */
+
+static int gfs2_close(struct inode *inode, struct file *file)
+{
+	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+	struct gfs2_file *fp;
+
+	fp = file->private_data;
+	file->private_data = NULL;
+
+	if (gfs2_assert_warn(sdp, fp))
+		return -EIO;
+
+	kfree(fp);
+
+	return 0;
+}
+
+/**
+ * gfs2_fsync - sync the dirty data for a file (across the cluster)
+ * @file: the file that points to the dentry (we ignore this)
+ * @dentry: the dentry that points to the inode to sync
+ *
+ * Returns: errno
+ */
+
+static int gfs2_fsync(struct file *file, struct dentry *dentry, int datasync)
+{
+	struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
+
+	gfs2_log_flush(ip->i_gl->gl_sbd, ip->i_gl);
+
+	return 0;
+}
+
+/**
+ * gfs2_lock - acquire/release a posix lock on a file
+ * @file: the file pointer
+ * @cmd: either modify or retrieve lock state, possibly wait
+ * @fl: type and range of lock
+ *
+ * Returns: errno
+ */
+
+static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
+{
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host);
+	struct lm_lockname name =
+		{ .ln_number = ip->i_num.no_addr,
+		  .ln_type = LM_TYPE_PLOCK };
+
+	if (!(fl->fl_flags & FL_POSIX))
+		return -ENOLCK;
+	if ((ip->i_di.di_mode & (S_ISGID | S_IXGRP)) == S_ISGID)
+		return -ENOLCK;
+
+	if (sdp->sd_args.ar_localflocks) {
+		if (IS_GETLK(cmd)) {
+			struct file_lock tmp;
+			int ret;
+			ret = posix_test_lock(file, fl, &tmp);
+			fl->fl_type = F_UNLCK;
+			if (ret)
+				memcpy(fl, &tmp, sizeof(struct file_lock));
+			return 0;
+		} else {
+			return posix_lock_file_wait(file, fl);
+		}
+	}
+
+	if (IS_GETLK(cmd))
+		return gfs2_lm_plock_get(sdp, &name, file, fl);
+	else if (fl->fl_type == F_UNLCK)
+		return gfs2_lm_punlock(sdp, &name, file, fl);
+	else
+		return gfs2_lm_plock(sdp, &name, file, cmd, fl);
+}
+
+static int do_flock(struct file *file, int cmd, struct file_lock *fl)
+{
+	struct gfs2_file *fp = file->private_data;
+	struct gfs2_holder *fl_gh = &fp->f_fl_gh;
+	struct gfs2_inode *ip = GFS2_I(file->f_dentry->d_inode);
+	struct gfs2_glock *gl;
+	unsigned int state;
+	int flags;
+	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;
+
+	mutex_lock(&fp->f_fl_mutex);
+
+	gl = fl_gh->gh_gl;
+	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);
+	} else {
+		error = gfs2_glock_get(GFS2_SB(&ip->i_inode),
+				      ip->i_num.no_addr, &gfs2_flock_glops,
+				      CREATE, &gl);
+		if (error)
+			goto out;
+	}
+
+	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);
+		if (error == GLR_TRYFAILED)
+			error = -EAGAIN;
+	} else {
+		error = flock_lock_file_wait(file, fl);
+		gfs2_assert_warn(GFS2_SB(&ip->i_inode), !error);
+	}
+
+out:
+	mutex_unlock(&fp->f_fl_mutex);
+	return error;
+}
+
+static void do_unflock(struct file *file, struct file_lock *fl)
+{
+	struct gfs2_file *fp = file->private_data;
+	struct gfs2_holder *fl_gh = &fp->f_fl_gh;
+
+	mutex_lock(&fp->f_fl_mutex);
+	flock_lock_file_wait(file, fl);
+	if (fl_gh->gh_gl)
+		gfs2_glock_dq_uninit(fl_gh);
+	mutex_unlock(&fp->f_fl_mutex);
+}
+
+/**
+ * gfs2_flock - acquire/release a flock lock on a file
+ * @file: the file pointer
+ * @cmd: either modify or retrieve lock state, possibly wait
+ * @fl: type and range of lock
+ *
+ * Returns: errno
+ */
+
+static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
+{
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host);
+
+	if (!(fl->fl_flags & FL_FLOCK))
+		return -ENOLCK;
+	if ((ip->i_di.di_mode & (S_ISGID | S_IXGRP)) == S_ISGID)
+		return -ENOLCK;
+
+	if (sdp->sd_args.ar_localflocks)
+		return flock_lock_file_wait(file, fl);
+
+	if (fl->fl_type == F_UNLCK) {
+		do_unflock(file, fl);
+		return 0;
+	} else {
+		return do_flock(file, cmd, fl);
+	}
+}
+
+const struct file_operations gfs2_file_fops = {
+	.llseek		= gfs2_llseek,
+	.read		= do_sync_read,
+	.aio_read	= generic_file_aio_read,
+	.write		= do_sync_write,
+	.aio_write	= generic_file_aio_write,
+	.unlocked_ioctl	= gfs2_ioctl,
+	.mmap		= gfs2_mmap,
+	.open		= gfs2_open,
+	.release	= gfs2_close,
+	.fsync		= gfs2_fsync,
+	.lock		= gfs2_lock,
+	.sendfile	= generic_file_sendfile,
+	.flock		= gfs2_flock,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= generic_file_splice_write,
+};
+
+const struct file_operations gfs2_dir_fops = {
+	.readdir	= gfs2_readdir,
+	.unlocked_ioctl	= gfs2_ioctl,
+	.open		= gfs2_open,
+	.release	= gfs2_close,
+	.fsync		= gfs2_fsync,
+	.lock		= gfs2_lock,
+	.flock		= gfs2_flock,
+};
+

fs/gfs2/ops_file.h

@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __OPS_FILE_DOT_H__
+#define __OPS_FILE_DOT_H__
+
+#include <linux/fs.h>
+struct gfs2_inode;
+
+extern struct file gfs2_internal_file_sentinel;
+extern int gfs2_internal_read(struct gfs2_inode *ip,
+			      struct file_ra_state *ra_state,
+			      char *buf, loff_t *pos, unsigned size);
+
+extern const struct file_operations gfs2_file_fops;
+extern const struct file_operations gfs2_dir_fops;
+
+#endif /* __OPS_FILE_DOT_H__ */

fs/gfs2/ops_fstype.c

@@ -0,0 +1,928 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/blkdev.h>
+#include <linux/kthread.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "daemon.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "lm.h"
+#include "mount.h"
+#include "ops_export.h"
+#include "ops_fstype.h"
+#include "ops_super.h"
+#include "recovery.h"
+#include "rgrp.h"
+#include "super.h"
+#include "sys.h"
+#include "util.h"
+
+#define DO 0
+#define UNDO 1
+
+extern struct dentry_operations gfs2_dops;
+
+static struct gfs2_sbd *init_sbd(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp;
+
+	sdp = kzalloc(sizeof(struct gfs2_sbd), GFP_KERNEL);
+	if (!sdp)
+		return NULL;
+
+	sb->s_fs_info = sdp;
+	sdp->sd_vfs = sb;
+
+	gfs2_tune_init(&sdp->sd_tune);
+
+	INIT_LIST_HEAD(&sdp->sd_reclaim_list);
+	spin_lock_init(&sdp->sd_reclaim_lock);
+	init_waitqueue_head(&sdp->sd_reclaim_wq);
+
+	mutex_init(&sdp->sd_inum_mutex);
+	spin_lock_init(&sdp->sd_statfs_spin);
+	mutex_init(&sdp->sd_statfs_mutex);
+
+	spin_lock_init(&sdp->sd_rindex_spin);
+	mutex_init(&sdp->sd_rindex_mutex);
+	INIT_LIST_HEAD(&sdp->sd_rindex_list);
+	INIT_LIST_HEAD(&sdp->sd_rindex_mru_list);
+	INIT_LIST_HEAD(&sdp->sd_rindex_recent_list);
+
+	INIT_LIST_HEAD(&sdp->sd_jindex_list);
+	spin_lock_init(&sdp->sd_jindex_spin);
+	mutex_init(&sdp->sd_jindex_mutex);
+
+	INIT_LIST_HEAD(&sdp->sd_quota_list);
+	spin_lock_init(&sdp->sd_quota_spin);
+	mutex_init(&sdp->sd_quota_mutex);
+
+	spin_lock_init(&sdp->sd_log_lock);
+
+	INIT_LIST_HEAD(&sdp->sd_log_le_gl);
+	INIT_LIST_HEAD(&sdp->sd_log_le_buf);
+	INIT_LIST_HEAD(&sdp->sd_log_le_revoke);
+	INIT_LIST_HEAD(&sdp->sd_log_le_rg);
+	INIT_LIST_HEAD(&sdp->sd_log_le_databuf);
+
+	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);
+
+	INIT_LIST_HEAD(&sdp->sd_revoke_list);
+
+	mutex_init(&sdp->sd_freeze_lock);
+
+	return sdp;
+}
+
+static void init_vfs(struct super_block *sb, unsigned noatime)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+
+	sb->s_magic = GFS2_MAGIC;
+	sb->s_op = &gfs2_super_ops;
+	sb->s_export_op = &gfs2_export_ops;
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+
+	if (sb->s_flags & (MS_NOATIME | MS_NODIRATIME))
+		set_bit(noatime, &sdp->sd_flags);
+
+	/* Don't let the VFS update atimes.  GFS2 handles this itself. */
+	sb->s_flags |= MS_NOATIME | MS_NODIRATIME;
+}
+
+static int init_names(struct gfs2_sbd *sdp, int silent)
+{
+	struct page *page;
+	char *proto, *table;
+	int error = 0;
+
+	proto = sdp->sd_args.ar_lockproto;
+	table = sdp->sd_args.ar_locktable;
+
+	/*  Try to autodetect  */
+
+	if (!proto[0] || !table[0]) {
+		struct gfs2_sb *sb;
+		page = gfs2_read_super(sdp->sd_vfs, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
+		if (!page)
+			return -ENOBUFS;
+		sb = kmap(page);
+		gfs2_sb_in(&sdp->sd_sb, sb);
+		kunmap(page);
+		__free_page(page);
+
+		error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
+		if (error)
+			goto out;
+
+		if (!proto[0])
+			proto = sdp->sd_sb.sb_lockproto;
+		if (!table[0])
+			table = sdp->sd_sb.sb_locktable;
+	}
+
+	if (!table[0])
+		table = sdp->sd_vfs->s_id;
+
+	snprintf(sdp->sd_proto_name, GFS2_FSNAME_LEN, "%s", proto);
+	snprintf(sdp->sd_table_name, GFS2_FSNAME_LEN, "%s", table);
+
+out:
+	return error;
+}
+
+static int init_locking(struct gfs2_sbd *sdp, struct gfs2_holder *mount_gh,
+			int undo)
+{
+	struct task_struct *p;
+	int error = 0;
+
+	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;
+	     sdp->sd_glockd_num++) {
+		p = kthread_run(gfs2_glockd, sdp, "gfs2_glockd");
+		error = IS_ERR(p);
+		if (error) {
+			fs_err(sdp, "can't start glockd thread: %d\n", error);
+			goto fail;
+		}
+		sdp->sd_glockd_process[sdp->sd_glockd_num] = p;
+	}
+
+	error = gfs2_glock_nq_num(sdp,
+				  GFS2_MOUNT_LOCK, &gfs2_nondisk_glops,
+				  LM_ST_EXCLUSIVE, LM_FLAG_NOEXP | GL_NOCACHE,
+				  mount_gh);
+	if (error) {
+		fs_err(sdp, "can't acquire mount glock: %d\n", error);
+		goto fail;
+	}
+
+	error = gfs2_glock_nq_num(sdp,
+				  GFS2_LIVE_LOCK, &gfs2_nondisk_glops,
+				  LM_ST_SHARED,
+				  LM_FLAG_NOEXP | GL_EXACT,
+				  &sdp->sd_live_gh);
+	if (error) {
+		fs_err(sdp, "can't acquire live glock: %d\n", error);
+		goto fail_mount;
+	}
+
+	error = gfs2_glock_get(sdp, GFS2_RENAME_LOCK, &gfs2_nondisk_glops,
+			       CREATE, &sdp->sd_rename_gl);
+	if (error) {
+		fs_err(sdp, "can't create rename glock: %d\n", error);
+		goto fail_live;
+	}
+
+	error = gfs2_glock_get(sdp, GFS2_TRANS_LOCK, &gfs2_trans_glops,
+			       CREATE, &sdp->sd_trans_gl);
+	if (error) {
+		fs_err(sdp, "can't create transaction glock: %d\n", error);
+		goto fail_rename;
+	}
+	set_bit(GLF_STICKY, &sdp->sd_trans_gl->gl_flags);
+
+	return 0;
+
+fail_trans:
+	gfs2_glock_put(sdp->sd_trans_gl);
+fail_rename:
+	gfs2_glock_put(sdp->sd_rename_gl);
+fail_live:
+	gfs2_glock_dq_uninit(&sdp->sd_live_gh);
+fail_mount:
+	gfs2_glock_dq_uninit(mount_gh);
+fail:
+	while (sdp->sd_glockd_num--)
+		kthread_stop(sdp->sd_glockd_process[sdp->sd_glockd_num]);
+
+	kthread_stop(sdp->sd_scand_process);
+	return error;
+}
+
+static struct inode *gfs2_lookup_root(struct super_block *sb,
+				      struct gfs2_inum *inum)
+{
+	return gfs2_inode_lookup(sb, inum, DT_DIR);
+}
+
+static int init_sb(struct gfs2_sbd *sdp, int silent, int undo)
+{
+	struct super_block *sb = sdp->sd_vfs;
+	struct gfs2_holder sb_gh;
+	struct gfs2_inum *inum;
+	struct inode *inode;
+	int error = 0;
+
+	if (undo) {
+		if (sb->s_root) {
+			dput(sb->s_root);
+			sb->s_root = NULL;
+		}
+		return 0;
+	}
+
+	error = gfs2_glock_nq_num(sdp, GFS2_SB_LOCK, &gfs2_meta_glops,
+				 LM_ST_SHARED, 0, &sb_gh);
+	if (error) {
+		fs_err(sdp, "can't acquire superblock glock: %d\n", error);
+		return error;
+	}
+
+	error = gfs2_read_sb(sdp, sb_gh.gh_gl, silent);
+	if (error) {
+		fs_err(sdp, "can't read superblock: %d\n", error);
+		goto out;
+	}
+
+	/* Set up the buffer cache and SB for real */
+	if (sdp->sd_sb.sb_bsize < bdev_hardsect_size(sb->s_bdev)) {
+		error = -EINVAL;
+		fs_err(sdp, "FS block size (%u) is too small for device "
+		       "block size (%u)\n",
+		       sdp->sd_sb.sb_bsize, bdev_hardsect_size(sb->s_bdev));
+		goto out;
+	}
+	if (sdp->sd_sb.sb_bsize > PAGE_SIZE) {
+		error = -EINVAL;
+		fs_err(sdp, "FS block size (%u) is too big for machine "
+		       "page size (%u)\n",
+		       sdp->sd_sb.sb_bsize, (unsigned int)PAGE_SIZE);
+		goto out;
+	}
+	sb_set_blocksize(sb, sdp->sd_sb.sb_bsize);
+
+	/* Get the root inode */
+	inum = &sdp->sd_sb.sb_root_dir;
+	if (sb->s_type == &gfs2meta_fs_type)
+		inum = &sdp->sd_sb.sb_master_dir;
+	inode = gfs2_lookup_root(sb, inum);
+	if (IS_ERR(inode)) {
+		error = PTR_ERR(inode);
+		fs_err(sdp, "can't read in root inode: %d\n", error);
+		goto out;
+	}
+
+	sb->s_root = d_alloc_root(inode);
+	if (!sb->s_root) {
+		fs_err(sdp, "can't get root dentry\n");
+		error = -ENOMEM;
+		iput(inode);
+	}
+	sb->s_root->d_op = &gfs2_dops;
+out:
+	gfs2_glock_dq_uninit(&sb_gh);
+	return error;
+}
+
+static int init_journal(struct gfs2_sbd *sdp, int undo)
+{
+	struct gfs2_holder ji_gh;
+	struct task_struct *p;
+	struct gfs2_inode *ip;
+	int jindex = 1;
+	int error = 0;
+
+	if (undo) {
+		jindex = 0;
+		goto fail_recoverd;
+	}
+
+	sdp->sd_jindex = gfs2_lookup_simple(sdp->sd_master_dir, "jindex");
+	if (IS_ERR(sdp->sd_jindex)) {
+		fs_err(sdp, "can't lookup journal index: %d\n", error);
+		return PTR_ERR(sdp->sd_jindex);
+	}
+	ip = GFS2_I(sdp->sd_jindex);
+	set_bit(GLF_STICKY, &ip->i_gl->gl_flags);
+
+	/* Load in the journal index special file */
+
+	error = gfs2_jindex_hold(sdp, &ji_gh);
+	if (error) {
+		fs_err(sdp, "can't read journal index: %d\n", error);
+		goto fail;
+	}
+
+	error = -EINVAL;
+	if (!gfs2_jindex_size(sdp)) {
+		fs_err(sdp, "no journals!\n");
+		goto fail_jindex;
+	}
+
+	if (sdp->sd_args.ar_spectator) {
+		sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0);
+		sdp->sd_log_blks_free = sdp->sd_jdesc->jd_blocks;
+	} else {
+		if (sdp->sd_lockstruct.ls_jid >= gfs2_jindex_size(sdp)) {
+			fs_err(sdp, "can't mount journal #%u\n",
+			       sdp->sd_lockstruct.ls_jid);
+			fs_err(sdp, "there are only %u journals (0 - %u)\n",
+			       gfs2_jindex_size(sdp),
+			       gfs2_jindex_size(sdp) - 1);
+			goto fail_jindex;
+		}
+		sdp->sd_jdesc = gfs2_jdesc_find(sdp, sdp->sd_lockstruct.ls_jid);
+
+		error = gfs2_glock_nq_num(sdp, sdp->sd_lockstruct.ls_jid,
+					  &gfs2_journal_glops,
+					  LM_ST_EXCLUSIVE, LM_FLAG_NOEXP,
+					  &sdp->sd_journal_gh);
+		if (error) {
+			fs_err(sdp, "can't acquire journal glock: %d\n", error);
+			goto fail_jindex;
+		}
+
+		ip = GFS2_I(sdp->sd_jdesc->jd_inode);
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
+					   LM_FLAG_NOEXP | GL_EXACT,
+					   &sdp->sd_jinode_gh);
+		if (error) {
+			fs_err(sdp, "can't acquire journal inode glock: %d\n",
+			       error);
+			goto fail_journal_gh;
+		}
+
+		error = gfs2_jdesc_check(sdp->sd_jdesc);
+		if (error) {
+			fs_err(sdp, "my journal (%u) is bad: %d\n",
+			       sdp->sd_jdesc->jd_jid, error);
+			goto fail_jinode_gh;
+		}
+		sdp->sd_log_blks_free = sdp->sd_jdesc->jd_blocks;
+	}
+
+	if (sdp->sd_lockstruct.ls_first) {
+		unsigned int x;
+		for (x = 0; x < sdp->sd_journals; x++) {
+			error = gfs2_recover_journal(gfs2_jdesc_find(sdp, x));
+			if (error) {
+				fs_err(sdp, "error recovering journal %u: %d\n",
+				       x, error);
+				goto fail_jinode_gh;
+			}
+		}
+
+		gfs2_lm_others_may_mount(sdp);
+	} else if (!sdp->sd_args.ar_spectator) {
+		error = gfs2_recover_journal(sdp->sd_jdesc);
+		if (error) {
+			fs_err(sdp, "error recovering my journal: %d\n", error);
+			goto fail_jinode_gh;
+		}
+	}
+
+	set_bit(SDF_JOURNAL_CHECKED, &sdp->sd_flags);
+	gfs2_glock_dq_uninit(&ji_gh);
+	jindex = 0;
+
+	p = kthread_run(gfs2_recoverd, sdp, "gfs2_recoverd");
+	error = IS_ERR(p);
+	if (error) {
+		fs_err(sdp, "can't start recoverd thread: %d\n", error);
+		goto fail_jinode_gh;
+	}
+	sdp->sd_recoverd_process = p;
+
+	return 0;
+
+fail_recoverd:
+	kthread_stop(sdp->sd_recoverd_process);
+fail_jinode_gh:
+	if (!sdp->sd_args.ar_spectator)
+		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
+fail_journal_gh:
+	if (!sdp->sd_args.ar_spectator)
+		gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
+fail_jindex:
+	gfs2_jindex_free(sdp);
+	if (jindex)
+		gfs2_glock_dq_uninit(&ji_gh);
+fail:
+	iput(sdp->sd_jindex);
+	return error;
+}
+
+
+static int init_inodes(struct gfs2_sbd *sdp, int undo)
+{
+	int error = 0;
+	struct gfs2_inode *ip;
+	struct inode *inode;
+
+	if (undo)
+		goto fail_qinode;
+
+	inode = gfs2_lookup_root(sdp->sd_vfs, &sdp->sd_sb.sb_master_dir);
+	if (IS_ERR(inode)) {
+		error = PTR_ERR(inode);
+		fs_err(sdp, "can't read in master directory: %d\n", error);
+		goto fail;
+	}
+	sdp->sd_master_dir = inode;
+
+	error = init_journal(sdp, undo);
+	if (error)
+		goto fail_master;
+
+	/* Read in the master inode number inode */
+	sdp->sd_inum_inode = gfs2_lookup_simple(sdp->sd_master_dir, "inum");
+	if (IS_ERR(sdp->sd_inum_inode)) {
+		error = PTR_ERR(sdp->sd_inum_inode);
+		fs_err(sdp, "can't read in inum inode: %d\n", error);
+		goto fail_journal;
+	}
+
+
+	/* Read in the master statfs inode */
+	sdp->sd_statfs_inode = gfs2_lookup_simple(sdp->sd_master_dir, "statfs");
+	if (IS_ERR(sdp->sd_statfs_inode)) {
+		error = PTR_ERR(sdp->sd_statfs_inode);
+		fs_err(sdp, "can't read in statfs inode: %d\n", error);
+		goto fail_inum;
+	}
+
+	/* Read in the resource index inode */
+	sdp->sd_rindex = gfs2_lookup_simple(sdp->sd_master_dir, "rindex");
+	if (IS_ERR(sdp->sd_rindex)) {
+		error = PTR_ERR(sdp->sd_rindex);
+		fs_err(sdp, "can't get resource index inode: %d\n", error);
+		goto fail_statfs;
+	}
+	ip = GFS2_I(sdp->sd_rindex);
+	set_bit(GLF_STICKY, &ip->i_gl->gl_flags);
+	sdp->sd_rindex_vn = ip->i_gl->gl_vn - 1;
+
+	/* Read in the quota inode */
+	sdp->sd_quota_inode = gfs2_lookup_simple(sdp->sd_master_dir, "quota");
+	if (IS_ERR(sdp->sd_quota_inode)) {
+		error = PTR_ERR(sdp->sd_quota_inode);
+		fs_err(sdp, "can't get quota file inode: %d\n", error);
+		goto fail_rindex;
+	}
+	return 0;
+
+fail_qinode:
+	iput(sdp->sd_quota_inode);
+fail_rindex:
+	gfs2_clear_rgrpd(sdp);
+	iput(sdp->sd_rindex);
+fail_statfs:
+	iput(sdp->sd_statfs_inode);
+fail_inum:
+	iput(sdp->sd_inum_inode);
+fail_journal:
+	init_journal(sdp, UNDO);
+fail_master:
+	iput(sdp->sd_master_dir);
+fail:
+	return error;
+}
+
+static int init_per_node(struct gfs2_sbd *sdp, int undo)
+{
+	struct inode *pn = NULL;
+	char buf[30];
+	int error = 0;
+	struct gfs2_inode *ip;
+
+	if (sdp->sd_args.ar_spectator)
+		return 0;
+
+	if (undo)
+		goto fail_qc_gh;
+
+	pn = gfs2_lookup_simple(sdp->sd_master_dir, "per_node");
+	if (IS_ERR(pn)) {
+		error = PTR_ERR(pn);
+		fs_err(sdp, "can't find per_node directory: %d\n", error);
+		return error;
+	}
+
+	sprintf(buf, "inum_range%u", sdp->sd_jdesc->jd_jid);
+	sdp->sd_ir_inode = gfs2_lookup_simple(pn, buf);
+	if (IS_ERR(sdp->sd_ir_inode)) {
+		error = PTR_ERR(sdp->sd_ir_inode);
+		fs_err(sdp, "can't find local \"ir\" file: %d\n", error);
+		goto fail;
+	}
+
+	sprintf(buf, "statfs_change%u", sdp->sd_jdesc->jd_jid);
+	sdp->sd_sc_inode = gfs2_lookup_simple(pn, buf);
+	if (IS_ERR(sdp->sd_sc_inode)) {
+		error = PTR_ERR(sdp->sd_sc_inode);
+		fs_err(sdp, "can't find local \"sc\" file: %d\n", error);
+		goto fail_ir_i;
+	}
+
+	sprintf(buf, "quota_change%u", sdp->sd_jdesc->jd_jid);
+	sdp->sd_qc_inode = gfs2_lookup_simple(pn, buf);
+	if (IS_ERR(sdp->sd_qc_inode)) {
+		error = PTR_ERR(sdp->sd_qc_inode);
+		fs_err(sdp, "can't find local \"qc\" file: %d\n", error);
+		goto fail_ut_i;
+	}
+
+	iput(pn);
+	pn = NULL;
+
+	ip = GFS2_I(sdp->sd_ir_inode);
+	error = gfs2_glock_nq_init(ip->i_gl,
+				   LM_ST_EXCLUSIVE, 0,
+				   &sdp->sd_ir_gh);
+	if (error) {
+		fs_err(sdp, "can't lock local \"ir\" file: %d\n", error);
+		goto fail_qc_i;
+	}
+
+	ip = GFS2_I(sdp->sd_sc_inode);
+	error = gfs2_glock_nq_init(ip->i_gl,
+				   LM_ST_EXCLUSIVE, 0,
+				   &sdp->sd_sc_gh);
+	if (error) {
+		fs_err(sdp, "can't lock local \"sc\" file: %d\n", error);
+		goto fail_ir_gh;
+	}
+
+	ip = GFS2_I(sdp->sd_qc_inode);
+	error = gfs2_glock_nq_init(ip->i_gl,
+				   LM_ST_EXCLUSIVE, 0,
+				   &sdp->sd_qc_gh);
+	if (error) {
+		fs_err(sdp, "can't lock local \"qc\" file: %d\n", error);
+		goto fail_ut_gh;
+	}
+
+	return 0;
+
+fail_qc_gh:
+	gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
+fail_ut_gh:
+	gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
+fail_ir_gh:
+	gfs2_glock_dq_uninit(&sdp->sd_ir_gh);
+fail_qc_i:
+	iput(sdp->sd_qc_inode);
+fail_ut_i:
+	iput(sdp->sd_sc_inode);
+fail_ir_i:
+	iput(sdp->sd_ir_inode);
+fail:
+	if (pn)
+		iput(pn);
+	return error;
+}
+
+static int init_threads(struct gfs2_sbd *sdp, int undo)
+{
+	struct task_struct *p;
+	int error = 0;
+
+	if (undo)
+		goto fail_quotad;
+
+	sdp->sd_log_flush_time = jiffies;
+	sdp->sd_jindex_refresh_time = jiffies;
+
+	p = kthread_run(gfs2_logd, sdp, "gfs2_logd");
+	error = IS_ERR(p);
+	if (error) {
+		fs_err(sdp, "can't start logd thread: %d\n", error);
+		return error;
+	}
+	sdp->sd_logd_process = p;
+
+	sdp->sd_statfs_sync_time = jiffies;
+	sdp->sd_quota_sync_time = jiffies;
+
+	p = kthread_run(gfs2_quotad, sdp, "gfs2_quotad");
+	error = IS_ERR(p);
+	if (error) {
+		fs_err(sdp, "can't start quotad thread: %d\n", error);
+		goto fail;
+	}
+	sdp->sd_quotad_process = p;
+
+	return 0;
+
+
+fail_quotad:
+	kthread_stop(sdp->sd_quotad_process);
+fail:
+	kthread_stop(sdp->sd_logd_process);
+	return error;
+}
+
+/**
+ * fill_super - Read in superblock
+ * @sb: The VFS superblock
+ * @data: Mount options
+ * @silent: Don't complain if it's not a GFS2 filesystem
+ *
+ * Returns: errno
+ */
+
+static int fill_super(struct super_block *sb, void *data, int silent)
+{
+	struct gfs2_sbd *sdp;
+	struct gfs2_holder mount_gh;
+	int error;
+
+	sdp = init_sbd(sb);
+	if (!sdp) {
+		printk(KERN_WARNING "GFS2: can't alloc struct gfs2_sbd\n");
+		return -ENOMEM;
+	}
+
+	error = gfs2_mount_args(sdp, (char *)data, 0);
+	if (error) {
+		printk(KERN_WARNING "GFS2: can't parse mount arguments\n");
+		goto fail;
+	}
+
+	init_vfs(sb, SDF_NOATIME);
+
+	/* Set up the buffer cache and fill in some fake block size values
+	   to allow us to read-in the on-disk superblock. */
+	sdp->sd_sb.sb_bsize = sb_min_blocksize(sb, GFS2_BASIC_BLOCK);
+	sdp->sd_sb.sb_bsize_shift = sb->s_blocksize_bits;
+	sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
+                               GFS2_BASIC_BLOCK_SHIFT;
+	sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
+
+	error = init_names(sdp, silent);
+	if (error)
+		goto fail;
+
+	error = gfs2_sys_fs_add(sdp);
+	if (error)
+		goto fail;
+
+	error = gfs2_lm_mount(sdp, silent);
+	if (error)
+		goto fail_sys;
+
+	error = init_locking(sdp, &mount_gh, DO);
+	if (error)
+		goto fail_lm;
+
+	error = init_sb(sdp, silent, DO);
+	if (error)
+		goto fail_locking;
+
+	error = init_inodes(sdp, DO);
+	if (error)
+		goto fail_sb;
+
+	error = init_per_node(sdp, DO);
+	if (error)
+		goto fail_inodes;
+
+	error = gfs2_statfs_init(sdp);
+	if (error) {
+		fs_err(sdp, "can't initialize statfs subsystem: %d\n", error);
+		goto fail_per_node;
+	}
+
+	error = init_threads(sdp, DO);
+	if (error)
+		goto fail_per_node;
+
+	if (!(sb->s_flags & MS_RDONLY)) {
+		error = gfs2_make_fs_rw(sdp);
+		if (error) {
+			fs_err(sdp, "can't make FS RW: %d\n", error);
+			goto fail_threads;
+		}
+	}
+
+	gfs2_glock_dq_uninit(&mount_gh);
+
+	return 0;
+
+fail_threads:
+	init_threads(sdp, UNDO);
+fail_per_node:
+	init_per_node(sdp, UNDO);
+fail_inodes:
+	init_inodes(sdp, UNDO);
+fail_sb:
+	init_sb(sdp, 0, UNDO);
+fail_locking:
+	init_locking(sdp, &mount_gh, UNDO);
+fail_lm:
+	gfs2_gl_hash_clear(sdp, WAIT);
+	gfs2_lm_unmount(sdp);
+	while (invalidate_inodes(sb))
+		yield();
+fail_sys:
+	gfs2_sys_fs_del(sdp);
+fail:
+	kfree(sdp);
+	sb->s_fs_info = NULL;
+	return error;
+}
+
+static int gfs2_get_sb(struct file_system_type *fs_type, int flags,
+		const char *dev_name, void *data, struct vfsmount *mnt)
+{
+	struct super_block *sb;
+	struct gfs2_sbd *sdp;
+	int error = get_sb_bdev(fs_type, flags, dev_name, data, fill_super, mnt);
+	if (error)
+		goto out;
+	sb = mnt->mnt_sb;
+	sdp = sb->s_fs_info;
+	sdp->sd_gfs2mnt = mnt;
+out:
+	return error;
+}
+
+static int fill_super_meta(struct super_block *sb, struct super_block *new,
+			   void *data, int silent)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct inode *inode;
+	int error = 0;
+
+	new->s_fs_info = sdp;
+	sdp->sd_vfs_meta = sb;
+
+	init_vfs(new, SDF_NOATIME);
+
+        /* Get the master inode */
+	inode = igrab(sdp->sd_master_dir);
+
+	new->s_root = d_alloc_root(inode);
+	if (!new->s_root) {
+		fs_err(sdp, "can't get root dentry\n");
+		error = -ENOMEM;
+		iput(inode);
+	}
+	new->s_root->d_op = &gfs2_dops;
+
+	return error;
+}
+
+static int set_bdev_super(struct super_block *s, void *data)
+{
+	s->s_bdev = data;
+	s->s_dev = s->s_bdev->bd_dev;
+	return 0;
+}
+
+static int test_bdev_super(struct super_block *s, void *data)
+{
+	return s->s_bdev == data;
+}
+
+static struct super_block* get_gfs2_sb(const char *dev_name)
+{
+	struct kstat stat;
+	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);
+	if (error) {
+		printk(KERN_WARNING "GFS2: path_lookup on %s returned error\n",
+		       dev_name);
+		goto out;
+	}
+	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);
+		if ((S_ISBLK(stat.mode) && s->s_dev == stat.rdev) ||
+		    (S_ISDIR(stat.mode) && s == nd.dentry->d_inode->i_sb)) {
+			sb = s;
+			goto free_nd;
+		}
+	}
+
+	printk(KERN_WARNING "GFS2: Unrecognized block device or "
+	       "mount point %s", dev_name);
+
+free_nd:
+	path_release(&nd);
+out:
+	return sb;
+}
+
+static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags,
+			    const char *dev_name, void *data, struct vfsmount *mnt)
+{
+	int error = 0;
+	struct super_block *sb = NULL, *new;
+	struct gfs2_sbd *sdp;
+	char *gfs2mnt = NULL;
+
+	sb = get_gfs2_sb(dev_name);
+	if (!sb) {
+		printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n");
+		error = -ENOENT;
+		goto error;
+	}
+	sdp = (struct gfs2_sbd*) sb->s_fs_info;
+	if (sdp->sd_vfs_meta) {
+		printk(KERN_WARNING "GFS2: gfs2meta mount already exists\n");
+		error = -EBUSY;
+		goto error;
+	}
+	mutex_lock(&sb->s_bdev->bd_mount_mutex);
+	new = sget(fs_type, test_bdev_super, set_bdev_super, sb->s_bdev);
+	mutex_unlock(&sb->s_bdev->bd_mount_mutex);
+	if (IS_ERR(new)) {
+		error = PTR_ERR(new);
+		goto error;
+	}
+	module_put(fs_type->owner);
+	new->s_flags = flags;
+	strlcpy(new->s_id, sb->s_id, sizeof(new->s_id));
+	sb_set_blocksize(new, sb->s_blocksize);
+	error = fill_super_meta(sb, new, data, flags & MS_SILENT ? 1 : 0);
+	if (error) {
+		up_write(&new->s_umount);
+		deactivate_super(new);
+		goto error;
+	}
+
+	new->s_flags |= MS_ACTIVE;
+
+	/* Grab a reference to the gfs2 mount point */
+	atomic_inc(&sdp->sd_gfs2mnt->mnt_count);
+	return simple_set_mnt(mnt, new);
+error:
+	if (gfs2mnt)
+		kfree(gfs2mnt);
+	return error;
+}
+
+static void gfs2_kill_sb(struct super_block *sb)
+{
+	kill_block_super(sb);
+}
+
+static void gfs2_kill_sb_meta(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	generic_shutdown_super(sb);
+	sdp->sd_vfs_meta = NULL;
+	atomic_dec(&sdp->sd_gfs2mnt->mnt_count);
+}
+
+struct file_system_type gfs2_fs_type = {
+	.name = "gfs2",
+	.fs_flags = FS_REQUIRES_DEV,
+	.get_sb = gfs2_get_sb,
+	.kill_sb = gfs2_kill_sb,
+	.owner = THIS_MODULE,
+};
+
+struct file_system_type gfs2meta_fs_type = {
+	.name = "gfs2meta",
+	.fs_flags = FS_REQUIRES_DEV,
+	.get_sb = gfs2_get_sb_meta,
+	.kill_sb = gfs2_kill_sb_meta,
+	.owner = THIS_MODULE,
+};
+

fs/gfs2/ops_fstype.h

@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __OPS_FSTYPE_DOT_H__
+#define __OPS_FSTYPE_DOT_H__
+
+#include <linux/fs.h>
+
+extern struct file_system_type gfs2_fs_type;
+extern struct file_system_type gfs2meta_fs_type;
+
+#endif /* __OPS_FSTYPE_DOT_H__ */

fs/gfs2/ops_inode.h

@@ -0,0 +1,20 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#ifndef __OPS_INODE_DOT_H__
+#define __OPS_INODE_DOT_H__
+
+#include <linux/fs.h>
+
+extern struct inode_operations gfs2_file_iops;
+extern struct inode_operations gfs2_dir_iops;
+extern struct inode_operations gfs2_symlink_iops;
+extern struct inode_operations gfs2_dev_iops;
+
+#endif /* __OPS_INODE_DOT_H__ */

fs/gfs2/ops_super.c

@@ -0,0 +1,468 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/statfs.h>
+#include <linux/seq_file.h>
+#include <linux/mount.h>
+#include <linux/kthread.h>
+#include <linux/delay.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+#include <linux/lm_interface.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "inode.h"
+#include "lm.h"
+#include "log.h"
+#include "mount.h"
+#include "ops_super.h"
+#include "quota.h"
+#include "recovery.h"
+#include "rgrp.h"
+#include "super.h"
+#include "sys.h"
+#include "util.h"
+#include "trans.h"
+#include "dir.h"
+#include "eattr.h"
+#include "bmap.h"
+
+/**
+ * gfs2_write_inode - Make sure the inode is stable on the disk
+ * @inode: The inode
+ * @sync: synchronous write flag
+ *
+ * Returns: errno
+ */
+
+static int gfs2_write_inode(struct inode *inode, int sync)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	/* Check this is a "normal" inode */
+	if (inode->i_private) {
+		if (current->flags & PF_MEMALLOC)
+			return 0;
+		if (sync)
+			gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_put_super - Unmount the filesystem
+ * @sb: The VFS superblock
+ *
+ */
+
+static void gfs2_put_super(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	int error;
+
+	if (!sdp)
+		return;
+
+	if (!strncmp(sb->s_type->name, "gfs2meta", 8))
+		return; /* Nothing to do */
+
+	/*  Unfreeze the filesystem, if we need to  */
+
+	mutex_lock(&sdp->sd_freeze_lock);
+	if (sdp->sd_freeze_count)
+		gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
+	mutex_unlock(&sdp->sd_freeze_lock);
+
+	kthread_stop(sdp->sd_quotad_process);
+	kthread_stop(sdp->sd_logd_process);
+	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);
+		if (error)
+			gfs2_io_error(sdp);
+	}
+	/*  At this point, we're through modifying the disk  */
+
+	/*  Release stuff  */
+
+	iput(sdp->sd_master_dir);
+	iput(sdp->sd_jindex);
+	iput(sdp->sd_inum_inode);
+	iput(sdp->sd_statfs_inode);
+	iput(sdp->sd_rindex);
+	iput(sdp->sd_quota_inode);
+
+	gfs2_glock_put(sdp->sd_rename_gl);
+	gfs2_glock_put(sdp->sd_trans_gl);
+
+	if (!sdp->sd_args.ar_spectator) {
+		gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_ir_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
+		iput(sdp->sd_ir_inode);
+		iput(sdp->sd_sc_inode);
+		iput(sdp->sd_qc_inode);
+	}
+
+	gfs2_glock_dq_uninit(&sdp->sd_live_gh);
+	gfs2_clear_rgrpd(sdp);
+	gfs2_jindex_free(sdp);
+	/*  Take apart glock structures and buffer lists  */
+	gfs2_gl_hash_clear(sdp, WAIT);
+	/*  Unmount the locking protocol  */
+	gfs2_lm_unmount(sdp);
+
+	/*  At this point, we're through participating in the lockspace  */
+	gfs2_sys_fs_del(sdp);
+	kfree(sdp);
+}
+
+/**
+ * gfs2_write_super - disk commit all incore transactions
+ * @sb: the filesystem
+ *
+ * This function is called every time sync(2) is called.
+ * After this exits, all dirty buffers are synced.
+ */
+
+static void gfs2_write_super(struct super_block *sb)
+{
+	gfs2_log_flush(sb->s_fs_info, NULL);
+}
+
+/**
+ * gfs2_write_super_lockfs - prevent further writes to the filesystem
+ * @sb: the VFS structure for the filesystem
+ *
+ */
+
+static void gfs2_write_super_lockfs(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	int error;
+
+	for (;;) {
+		error = gfs2_freeze_fs(sdp);
+		if (!error)
+			break;
+
+		switch (error) {
+		case -EBUSY:
+			fs_err(sdp, "waiting for recovery before freeze\n");
+			break;
+
+		default:
+			fs_err(sdp, "error freezing FS: %d\n", error);
+			break;
+		}
+
+		fs_err(sdp, "retrying...\n");
+		msleep(1000);
+	}
+}
+
+/**
+ * gfs2_unlockfs - reallow writes to the filesystem
+ * @sb: the VFS structure for the filesystem
+ *
+ */
+
+static void gfs2_unlockfs(struct super_block *sb)
+{
+	gfs2_unfreeze_fs(sb->s_fs_info);
+}
+
+/**
+ * gfs2_statfs - Gather and return stats about the filesystem
+ * @sb: The superblock
+ * @statfsbuf: The buffer
+ *
+ * Returns: 0 on success or error code
+ */
+
+static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	struct super_block *sb = dentry->d_inode->i_sb;
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_statfs_change sc;
+	int error;
+
+	if (gfs2_tune_get(sdp, gt_statfs_slow))
+		error = gfs2_statfs_slow(sdp, &sc);
+	else
+		error = gfs2_statfs_i(sdp, &sc);
+
+	if (error)
+		return error;
+
+	buf->f_type = GFS2_MAGIC;
+	buf->f_bsize = sdp->sd_sb.sb_bsize;
+	buf->f_blocks = sc.sc_total;
+	buf->f_bfree = sc.sc_free;
+	buf->f_bavail = sc.sc_free;
+	buf->f_files = sc.sc_dinodes + sc.sc_free;
+	buf->f_ffree = sc.sc_free;
+	buf->f_namelen = GFS2_FNAMESIZE;
+
+	return 0;
+}
+
+/**
+ * gfs2_remount_fs - called when the FS is remounted
+ * @sb:  the filesystem
+ * @flags:  the remount flags
+ * @data:  extra data passed in (not used right now)
+ *
+ * Returns: errno
+ */
+
+static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	int error;
+
+	error = gfs2_mount_args(sdp, data, 1);
+	if (error)
+		return error;
+
+	if (sdp->sd_args.ar_spectator)
+		*flags |= MS_RDONLY;
+	else {
+		if (*flags & MS_RDONLY) {
+			if (!(sb->s_flags & MS_RDONLY))
+				error = gfs2_make_fs_ro(sdp);
+		} else if (!(*flags & MS_RDONLY) &&
+			   (sb->s_flags & MS_RDONLY)) {
+			error = gfs2_make_fs_rw(sdp);
+		}
+	}
+
+	if (*flags & (MS_NOATIME | MS_NODIRATIME))
+		set_bit(SDF_NOATIME, &sdp->sd_flags);
+	else
+		clear_bit(SDF_NOATIME, &sdp->sd_flags);
+
+	/* Don't let the VFS update atimes.  GFS2 handles this itself. */
+	*flags |= MS_NOATIME | MS_NODIRATIME;
+
+	return error;
+}
+
+/**
+ * gfs2_clear_inode - Deallocate an inode when VFS is done with it
+ * @inode: The VFS inode
+ *
+ */
+
+static void gfs2_clear_inode(struct inode *inode)
+{
+	/* This tells us its a "real" inode and not one which only
+	 * serves to contain an address space (see rgrp.c, meta_io.c)
+	 * which therefore doesn't have its own glocks.
+	 */
+	if (inode->i_private) {
+		struct gfs2_inode *ip = GFS2_I(inode);
+		gfs2_glock_inode_squish(inode);
+		gfs2_assert(inode->i_sb->s_fs_info, ip->i_gl->gl_state == LM_ST_UNLOCKED);
+		ip->i_gl->gl_object = NULL;
+		gfs2_glock_schedule_for_reclaim(ip->i_gl);
+		gfs2_glock_put(ip->i_gl);
+		ip->i_gl = NULL;
+		if (ip->i_iopen_gh.gh_gl)
+			gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+	}
+}
+
+/**
+ * gfs2_show_options - Show mount options for /proc/mounts
+ * @s: seq_file structure
+ * @mnt: vfsmount
+ *
+ * Returns: 0 on success or error code
+ */
+
+static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
+{
+	struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info;
+	struct gfs2_args *args = &sdp->sd_args;
+
+	if (args->ar_lockproto[0])
+		seq_printf(s, ",lockproto=%s", args->ar_lockproto);
+	if (args->ar_locktable[0])
+		seq_printf(s, ",locktable=%s", args->ar_locktable);
+	if (args->ar_hostdata[0])
+		seq_printf(s, ",hostdata=%s", args->ar_hostdata);
+	if (args->ar_spectator)
+		seq_printf(s, ",spectator");
+	if (args->ar_ignore_local_fs)
+		seq_printf(s, ",ignore_local_fs");
+	if (args->ar_localflocks)
+		seq_printf(s, ",localflocks");
+	if (args->ar_localcaching)
+		seq_printf(s, ",localcaching");
+	if (args->ar_debug)
+		seq_printf(s, ",debug");
+	if (args->ar_upgrade)
+		seq_printf(s, ",upgrade");
+	if (args->ar_num_glockd != GFS2_GLOCKD_DEFAULT)
+		seq_printf(s, ",num_glockd=%u", args->ar_num_glockd);
+	if (args->ar_posix_acl)
+		seq_printf(s, ",acl");
+	if (args->ar_quota != GFS2_QUOTA_DEFAULT) {
+		char *state;
+		switch (args->ar_quota) {
+		case GFS2_QUOTA_OFF:
+			state = "off";
+			break;
+		case GFS2_QUOTA_ACCOUNT:
+			state = "account";
+			break;
+		case GFS2_QUOTA_ON:
+			state = "on";
+			break;
+		default:
+			state = "unknown";
+			break;
+		}
+		seq_printf(s, ",quota=%s", state);
+	}
+	if (args->ar_suiddir)
+		seq_printf(s, ",suiddir");
+	if (args->ar_data != GFS2_DATA_DEFAULT) {
+		char *state;
+		switch (args->ar_data) {
+		case GFS2_DATA_WRITEBACK:
+			state = "writeback";
+			break;
+		case GFS2_DATA_ORDERED:
+			state = "ordered";
+			break;
+		default:
+			state = "unknown";
+			break;
+		}
+		seq_printf(s, ",data=%s", state);
+	}
+
+	return 0;
+}
+
+/*
+ * We have to (at the moment) hold the inodes main lock to cover
+ * the gap between unlocking the shared lock on the iopen lock and
+ * taking the exclusive lock. I'd rather do a shared -> exclusive
+ * conversion on the iopen lock, but we can change that later. This
+ * is safe, just less efficient.
+ */
+static void gfs2_delete_inode(struct inode *inode)
+{
+	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int error;
+
+	if (!inode->i_private)
+		goto out;
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &gh);
+	if (unlikely(error)) {
+		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+		goto out;
+	}
+
+	gfs2_glock_dq(&ip->i_iopen_gh);
+	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
+	error = gfs2_glock_nq(&ip->i_iopen_gh);
+	if (error)
+		goto out_uninit;
+
+	if (S_ISDIR(ip->i_di.di_mode) &&
+	    (ip->i_di.di_flags & GFS2_DIF_EXHASH)) {
+		error = gfs2_dir_exhash_dealloc(ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	if (ip->i_di.di_eattr) {
+		error = gfs2_ea_dealloc(ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	if (!gfs2_is_stuffed(ip)) {
+		error = gfs2_file_dealloc(ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	error = gfs2_dinode_dealloc(ip);
+
+out_unlock:
+	gfs2_glock_dq(&ip->i_iopen_gh);
+out_uninit:
+	gfs2_holder_uninit(&ip->i_iopen_gh);
+	gfs2_glock_dq_uninit(&gh);
+	if (error)
+		fs_warn(sdp, "gfs2_delete_inode: %d\n", error);
+out:
+	truncate_inode_pages(&inode->i_data, 0);
+	clear_inode(inode);
+}
+
+
+
+static struct inode *gfs2_alloc_inode(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_inode *ip;
+
+	ip = kmem_cache_alloc(gfs2_inode_cachep, GFP_KERNEL);
+	if (ip) {
+		ip->i_flags = 0;
+		ip->i_gl = NULL;
+		ip->i_greedy = gfs2_tune_get(sdp, gt_greedy_default);
+		ip->i_last_pfault = jiffies;
+	}
+	return &ip->i_inode;
+}
+
+static void gfs2_destroy_inode(struct inode *inode)
+{
+	kmem_cache_free(gfs2_inode_cachep, inode);
+}
+
+struct super_operations gfs2_super_ops = {
+	.alloc_inode = gfs2_alloc_inode,
+	.destroy_inode = gfs2_destroy_inode,
+	.write_inode = gfs2_write_inode,
+	.delete_inode = gfs2_delete_inode,
+	.put_super = gfs2_put_super,
+	.write_super = gfs2_write_super,
+	.write_super_lockfs = gfs2_write_super_lockfs,
+	.unlockfs = gfs2_unlockfs,
+	.statfs = gfs2_statfs,
+	.remount_fs = gfs2_remount_fs,
+	.clear_inode = gfs2_clear_inode,
+	.show_options = gfs2_show_options,
+};
+