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

* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw: (34 commits)
  [GFS2] Uncomment sprintf_symbol calling code
  [DLM] lowcomms style
  [GFS2] printk warning fixes
  [GFS2] Patch to fix mmap of stuffed files
  [GFS2] use lib/parser for parsing mount options
  [DLM] Lowcomms nodeid range & initialisation fixes
  [DLM] Fix dlm_lowcoms_stop hang
  [DLM] fix mode munging
  [GFS2] lockdump improvements
  [GFS2] Patch to detect corrupt number of dir entries in leaf and/or inode blocks
  [GFS2] bz 236008: Kernel gpf doing cat /debugfs/gfs2/xxx (lock dump)
  [DLM] fs/dlm/ast.c should #include "ast.h"
  [DLM] Consolidate transport protocols
  [DLM] Remove redundant assignment
  [GFS2] Fix bz 234168 (ignoring rgrp flags)
  [DLM] change lkid format
  [DLM] interface for purge (2/2)
  [DLM] add orphan purging code (1/2)
  [DLM] split create_message function
  [GFS2] Set drop_count to 0 (off) by default
  ...

fs/dlm/Kconfig

@@ -3,30 +3,13 @@ menu "Distributed Lock Manager"
 
 config DLM
 	tristate "Distributed Lock Manager (DLM)"
-	depends on SYSFS && (IPV6 || IPV6=n)
+	depends on IPV6 || IPV6=n
 	select CONFIGFS_FS
-	select IP_SCTP if DLM_SCTP
+	select IP_SCTP
 	help
 	A general purpose distributed lock manager for kernel or userspace
 	applications.
 
-choice
-	prompt "Select DLM communications protocol"
-	depends on DLM
-	default DLM_TCP
-	help
-	  The DLM Can use TCP or SCTP for it's network communications.
-	  SCTP supports multi-homed operations whereas TCP doesn't.
-	  However, SCTP seems to have stability problems at the moment.
-
-config DLM_TCP
-	bool "TCP/IP"
-
-config DLM_SCTP
-	bool "SCTP"
-
-endchoice
-
 config DLM_DEBUG
 	bool "DLM debugging"
 	depends on DLM

fs/dlm/Makefile

@@ -8,6 +8,7 @@ dlm-y :=			ast.o \
 				member.o \
 				memory.o \
 				midcomms.o \
+				lowcomms.o \
 				rcom.o \
 				recover.o \
 				recoverd.o \
@@ -16,6 +17,3 @@ dlm-y :=			ast.o \
 				util.o 
 dlm-$(CONFIG_DLM_DEBUG) +=	debug_fs.o
 
-dlm-$(CONFIG_DLM_TCP)   += lowcomms-tcp.o
-
-dlm-$(CONFIG_DLM_SCTP)  += lowcomms-sctp.o
\ No newline at end of file

fs/dlm/ast.c

@@ -14,6 +14,7 @@
 #include "dlm_internal.h"
 #include "lock.h"
 #include "user.h"
+#include "ast.h"
 
 #define WAKE_ASTS  0
 

fs/dlm/config.c

@@ -2,7 +2,7 @@
 *******************************************************************************
 **
 **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
-**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
 **
 **  This copyrighted material is made available to anyone wishing to use,
 **  modify, copy, or redistribute it subject to the terms and conditions
@@ -89,6 +89,7 @@ struct cluster {
 	unsigned int cl_toss_secs;
 	unsigned int cl_scan_secs;
 	unsigned int cl_log_debug;
+	unsigned int cl_protocol;
 };
 
 enum {
@@ -101,6 +102,7 @@ enum {
 	CLUSTER_ATTR_TOSS_SECS,
 	CLUSTER_ATTR_SCAN_SECS,
 	CLUSTER_ATTR_LOG_DEBUG,
+	CLUSTER_ATTR_PROTOCOL,
 };
 
 struct cluster_attribute {
@@ -159,6 +161,7 @@ CLUSTER_ATTR(recover_timer, 1);
 CLUSTER_ATTR(toss_secs, 1);
 CLUSTER_ATTR(scan_secs, 1);
 CLUSTER_ATTR(log_debug, 0);
+CLUSTER_ATTR(protocol, 0);
 
 static struct configfs_attribute *cluster_attrs[] = {
 	[CLUSTER_ATTR_TCP_PORT] = &cluster_attr_tcp_port.attr,
@@ -170,6 +173,7 @@ static struct configfs_attribute *cluster_attrs[] = {
 	[CLUSTER_ATTR_TOSS_SECS] = &cluster_attr_toss_secs.attr,
 	[CLUSTER_ATTR_SCAN_SECS] = &cluster_attr_scan_secs.attr,
 	[CLUSTER_ATTR_LOG_DEBUG] = &cluster_attr_log_debug.attr,
+	[CLUSTER_ATTR_PROTOCOL] = &cluster_attr_protocol.attr,
 	NULL,
 };
 
@@ -904,6 +908,7 @@ int dlm_our_addr(struct sockaddr_storage *addr, int num)
 #define DEFAULT_TOSS_SECS         10
 #define DEFAULT_SCAN_SECS          5
 #define DEFAULT_LOG_DEBUG          0
+#define DEFAULT_PROTOCOL           0
 
 struct dlm_config_info dlm_config = {
 	.ci_tcp_port = DEFAULT_TCP_PORT,
@@ -914,6 +919,7 @@ struct dlm_config_info dlm_config = {
 	.ci_recover_timer = DEFAULT_RECOVER_TIMER,
 	.ci_toss_secs = DEFAULT_TOSS_SECS,
 	.ci_scan_secs = DEFAULT_SCAN_SECS,
-	.ci_log_debug = DEFAULT_LOG_DEBUG
+	.ci_log_debug = DEFAULT_LOG_DEBUG,
+	.ci_protocol = DEFAULT_PROTOCOL
 };
 

fs/dlm/config.h

@@ -2,7 +2,7 @@
 *******************************************************************************
 **
 **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
-**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
 **
 **  This copyrighted material is made available to anyone wishing to use,
 **  modify, copy, or redistribute it subject to the terms and conditions
@@ -26,6 +26,7 @@ struct dlm_config_info {
 	int ci_toss_secs;
 	int ci_scan_secs;
 	int ci_log_debug;
+	int ci_protocol;
 };
 
 extern struct dlm_config_info dlm_config;

fs/dlm/dlm_internal.h

@@ -2,7 +2,7 @@
 *******************************************************************************
 **
 **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
-**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
 **
 **  This copyrighted material is made available to anyone wishing to use,
 **  modify, copy, or redistribute it subject to the terms and conditions
@@ -210,6 +210,9 @@ struct dlm_args {
 #define DLM_IFL_MSTCPY		0x00010000
 #define DLM_IFL_RESEND		0x00020000
 #define DLM_IFL_DEAD		0x00040000
+#define DLM_IFL_OVERLAP_UNLOCK  0x00080000
+#define DLM_IFL_OVERLAP_CANCEL  0x00100000
+#define DLM_IFL_ENDOFLIFE	0x00200000
 #define DLM_IFL_USER		0x00000001
 #define DLM_IFL_ORPHAN		0x00000002
 
@@ -230,8 +233,8 @@ struct dlm_lkb {
 	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_wait_count;
 	int8_t			lkb_ast_type;	/* type of ast queued for */
 
 	struct list_head	lkb_idtbl_list;	/* lockspace lkbtbl */
@@ -339,6 +342,7 @@ struct dlm_header {
 #define DLM_MSG_LOOKUP		11
 #define DLM_MSG_REMOVE		12
 #define DLM_MSG_LOOKUP_REPLY	13
+#define DLM_MSG_PURGE		14
 
 struct dlm_message {
 	struct dlm_header	m_header;
@@ -440,6 +444,9 @@ struct dlm_ls {
 	struct mutex		ls_waiters_mutex;
 	struct list_head	ls_waiters;	/* lkbs needing a reply */
 
+	struct mutex		ls_orphans_mutex;
+	struct list_head	ls_orphans;
+
 	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 */

fs/dlm/lock.h

@@ -41,6 +41,8 @@ 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);
+int dlm_user_purge(struct dlm_ls *ls, struct dlm_user_proc *proc,
+	int nodeid, int pid);
 void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc);
 
 static inline int is_master(struct dlm_rsb *r)

fs/dlm/lockspace.c

@@ -2,7 +2,7 @@
 *******************************************************************************
 **
 **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
-**  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
 **
 **  This copyrighted material is made available to anyone wishing to use,
 **  modify, copy, or redistribute it subject to the terms and conditions
@@ -459,6 +459,8 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
 
 	INIT_LIST_HEAD(&ls->ls_waiters);
 	mutex_init(&ls->ls_waiters_mutex);
+	INIT_LIST_HEAD(&ls->ls_orphans);
+	mutex_init(&ls->ls_orphans_mutex);
 
 	INIT_LIST_HEAD(&ls->ls_nodes);
 	INIT_LIST_HEAD(&ls->ls_nodes_gone);

fs/dlm/user.c

 /*
- * Copyright (C) 2006 Red Hat, Inc.  All rights reserved.
+ * Copyright (C) 2006-2007 Red Hat, Inc.  All rights reserved.
  *
  * This copyrighted material is made available to anyone wishing to use,
  * modify, copy, or redistribute it subject to the terms and conditions
@@ -56,6 +56,7 @@ struct dlm_write_request32 {
 	union  {
 		struct dlm_lock_params32 lock;
 		struct dlm_lspace_params lspace;
+		struct dlm_purge_params purge;
 	} i;
 };
 
@@ -92,6 +93,9 @@ static void compat_input(struct dlm_write_request *kb,
 		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 if (kb->cmd == DLM_USER_PURGE) {
+		kb->i.purge.nodeid = kb32->i.purge.nodeid;
+		kb->i.purge.pid = kb32->i.purge.pid;
 	} else {
 		kb->i.lock.mode = kb32->i.lock.mode;
 		kb->i.lock.namelen = kb32->i.lock.namelen;
@@ -111,8 +115,6 @@ static void compat_input(struct dlm_write_request *kb,
 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;
@@ -128,35 +130,30 @@ static void compat_output(struct dlm_lock_result *res,
 }
 #endif
 
+/* we could possibly check if the cancel of an orphan has resulted in the lkb
+   being removed and then remove that lkb from the orphans list and free it */
 
 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;
+	int eol = 0, ast_type;
 
-	/* 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); */
+	if (lkb->lkb_flags & (DLM_IFL_ORPHAN | DLM_IFL_DEAD))
 		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. */
+	   lkb->ua so we can't try to use it.  This second check is necessary
+	   for cases where a completion ast is received for an operation that
+	   began before clear_proc_locks did its cancel/unlock. */
 
-	if (lkb->lkb_flags & (DLM_IFL_ORPHAN | DLM_IFL_DEAD)) {
-		/* log_print("user_add_ast skip2 %x", lkb->lkb_flags); */
+	if (lkb->lkb_flags & (DLM_IFL_ORPHAN | DLM_IFL_DEAD))
 		goto out;
-	}
 
 	DLM_ASSERT(lkb->lkb_astparam, dlm_print_lkb(lkb););
 	ua = (struct dlm_user_args *)lkb->lkb_astparam;
@@ -166,28 +163,42 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, int type)
 		goto out;
 
 	spin_lock(&proc->asts_spin);
-	if (!(lkb->lkb_ast_type & (AST_COMP | AST_BAST))) {
+
+	ast_type = lkb->lkb_ast_type;
+	lkb->lkb_ast_type |= type;
+
+	if (!ast_type) {
 		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;
-
-	/* unlocks or cancels of waiting requests need to be removed from the
-	   proc's unlocking list, again there must be a better way...  */
-
-	if (ua->lksb.sb_status == -DLM_EUNLOCK ||
+	if (type == AST_COMP && (ast_type & AST_COMP))
+		log_debug(ls, "ast overlap %x status %x %x",
+			  lkb->lkb_id, ua->lksb.sb_status, lkb->lkb_flags);
+
+	/* Figure out if this lock is at the end of its life and no longer
+	   available for the application to use.  The lkb still exists until
+	   the final ast is read.  A lock becomes EOL in three situations:
+	     1. a noqueue request fails with EAGAIN
+	     2. an unlock completes with EUNLOCK
+	     3. a cancel of a waiting request completes with ECANCEL
+	   An EOL lock needs to be removed from the process's list of locks.
+	   And we can't allow any new operation on an EOL lock.  This is
+	   not related to the lifetime of the lkb struct which is managed
+	   entirely by refcount. */
+
+	if (type == AST_COMP &&
+	    lkb->lkb_grmode == DLM_LOCK_IV &&
+	    ua->lksb.sb_status == -EAGAIN)
+		eol = 1;
+	else if (ua->lksb.sb_status == -DLM_EUNLOCK ||
 	    (ua->lksb.sb_status == -DLM_ECANCEL &&
 	     lkb->lkb_grmode == DLM_LOCK_IV))
-		remove_ownqueue = 1;
+		eol = 1;
+	if (eol) {
+		lkb->lkb_ast_type &= ~AST_BAST;
+		lkb->lkb_flags |= DLM_IFL_ENDOFLIFE;
+	}
 
 	/* 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
@@ -204,12 +215,14 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, int type)
 
 	spin_unlock(&proc->asts_spin);
 
-	if (remove_ownqueue) {
+	if (eol) {
 		spin_lock(&ua->proc->locks_spin);
+		if (!list_empty(&lkb->lkb_ownqueue)) {
 			list_del_init(&lkb->lkb_ownqueue);
-		spin_unlock(&ua->proc->locks_spin);
 			dlm_put_lkb(lkb);
 		}
+		spin_unlock(&ua->proc->locks_spin);
+	}
  out:
 	mutex_unlock(&ls->ls_clear_proc_locks);
 }
@@ -286,47 +299,71 @@ static int device_user_unlock(struct dlm_user_proc *proc,
 	return error;
 }
 
-static int device_create_lockspace(struct dlm_lspace_params *params)
+static int create_misc_device(struct dlm_ls *ls, char *name)
 {
-	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;
+	len = strlen(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);
+		 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;
 	}
+fail:
+	return error;
+}
+
+static int device_user_purge(struct dlm_user_proc *proc,
+			     struct dlm_purge_params *params)
+{
+	struct dlm_ls *ls;
+	int error;
+
+	ls = dlm_find_lockspace_local(proc->lockspace);
+	if (!ls)
+		return -ENOENT;
+
+	error = dlm_user_purge(ls, proc, params->nodeid, params->pid);
 
-	error = ls->ls_device.minor;
 	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;
+
+	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;
 
- fail:
+	error = create_misc_device(ls, params->name);
 	dlm_put_lockspace(ls);
+
+	if (error)
 		dlm_release_lockspace(lockspace, 0);
+	else
+		error = ls->ls_device.minor;
+
 	return error;
 }
 
@@ -343,6 +380,10 @@ static int device_remove_lockspace(struct dlm_lspace_params *params)
 	if (!ls)
 		return -ENOENT;
 
+	/* Deregister the misc device first, so we don't have
+	 * a device that's not attached to a lockspace. If
+	 * dlm_release_lockspace fails then we can recreate it
+	 */
 	error = misc_deregister(&ls->ls_device);
 	if (error) {
 		dlm_put_lockspace(ls);
@@ -361,6 +402,8 @@ static int device_remove_lockspace(struct dlm_lspace_params *params)
 
 	dlm_put_lockspace(ls);
 	error = dlm_release_lockspace(lockspace, force);
+	if (error)
+		create_misc_device(ls, ls->ls_name);
  out:
 	return error;
 }
@@ -497,6 +540,14 @@ static ssize_t device_write(struct file *file, const char __user *buf,
 		error = device_remove_lockspace(&kbuf->i.lspace);
 		break;
 
+	case DLM_USER_PURGE:
+		if (!proc) {
+			log_print("no locking on control device");
+			goto out_sig;
+		}
+		error = device_user_purge(proc, &kbuf->i.purge);
+		break;
+
 	default:
 		log_print("Unknown command passed to DLM device : %d\n",
 			  kbuf->cmd);

fs/gfs2/dir.c

@@ -1262,9 +1262,10 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
 			      u64 leaf_no)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct buffer_head *bh;
 	struct gfs2_leaf *lf;
-	unsigned entries = 0;
+	unsigned entries = 0, entries2 = 0;
 	unsigned leaves = 0;
 	const struct gfs2_dirent **darr, *dent;
 	struct dirent_gather g;
@@ -1290,7 +1291,13 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
 		return 0;
 
 	error = -ENOMEM;
-	larr = vmalloc((leaves + entries) * sizeof(void *));
+	/*
+	 * The extra 99 entries are not normally used, but are a buffer
+	 * zone in case the number of entries in the leaf is corrupt.
+	 * 99 is the maximum number of entries that can fit in a single
+	 * leaf block.
+	 */
+	larr = vmalloc((leaves + entries + 99) * sizeof(void *));
 	if (!larr)
 		goto out;
 	darr = (const struct gfs2_dirent **)(larr + leaves);
@@ -1305,10 +1312,20 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
 		lf = (struct gfs2_leaf *)bh->b_data;
 		lfn = be64_to_cpu(lf->lf_next);
 		if (lf->lf_entries) {
+			entries2 += be16_to_cpu(lf->lf_entries);
 			dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size,
 						gfs2_dirent_gather, NULL, &g);
 			error = PTR_ERR(dent);
-			if (IS_ERR(dent)) {
+			if (IS_ERR(dent))
+				goto out_kfree;
+			if (entries2 != g.offset) {
+				fs_warn(sdp, "Number of entries corrupt in dir "
+						"leaf %llu, entries2 (%u) != "
+						"g.offset (%u)\n",
+					(unsigned long long)bh->b_blocknr,
+					entries2, g.offset);
+					
+				error = -EIO;
 				goto out_kfree;
 			}
 			error = 0;
@@ -1318,6 +1335,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
 		}
 	} while(lfn);
 
+	BUG_ON(entries2 != entries);
 	error = do_filldir_main(ip, offset, opaque, filldir, darr,
 				entries, copied);
 out_kfree:
@@ -1401,6 +1419,7 @@ int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque,
 		  filldir_t filldir)
 {
 	struct gfs2_inode *dip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct dirent_gather g;
 	const struct gfs2_dirent **darr, *dent;
 	struct buffer_head *dibh;
@@ -1423,8 +1442,8 @@ int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque,
 		return error;
 
 	error = -ENOMEM;
-	darr = kmalloc(dip->i_di.di_entries * sizeof(struct gfs2_dirent *),
-		       GFP_KERNEL);
+	/* 96 is max number of dirents which can be stuffed into an inode */
+	darr = kmalloc(96 * sizeof(struct gfs2_dirent *), GFP_KERNEL);
 	if (darr) {
 		g.pdent = darr;
 		g.offset = 0;
@@ -1434,6 +1453,15 @@ int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque,
 			error = PTR_ERR(dent);
 			goto out;
 		}
+		if (dip->i_di.di_entries != g.offset) {
+			fs_warn(sdp, "Number of entries corrupt in dir %llu, "
+				"ip->i_di.di_entries (%u) != g.offset (%u)\n",
+				(unsigned long long)dip->i_num.no_addr,
+				dip->i_di.di_entries,
+				g.offset);
+			error = -EIO;
+			goto out;
+		}
 		error = do_filldir_main(dip, offset, opaque, filldir, darr,
 					dip->i_di.di_entries, &copied);
 out:

fs/gfs2/glock.h

@@ -38,7 +38,7 @@ static inline int gfs2_glock_is_locked_by_me(struct gfs2_glock *gl)
 	/* 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) {
+		if (gh->gh_owner_pid == current->pid) {
 			locked = 1;
 			break;
 		}
@@ -67,7 +67,7 @@ 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);
+	ret = test_bit(GLF_DEMOTE, &gl->gl_flags) || !list_empty(&gl->gl_waiters3);
 	spin_unlock(&gl->gl_spin);
 	return ret;
 }
@@ -135,5 +135,9 @@ 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);
+int gfs2_create_debugfs_file(struct gfs2_sbd *sdp);
+void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp);
+int gfs2_register_debugfs(void);
+void gfs2_unregister_debugfs(void);
 
 #endif /* __GLOCK_DOT_H__ */

fs/gfs2/incore.h

@@ -115,11 +115,8 @@ enum {
 	/* Actions */
 	HIF_MUTEX		= 0,
 	HIF_PROMOTE		= 1,
-	HIF_DEMOTE		= 2,
 
 	/* States */
-	HIF_ALLOCED		= 4,
-	HIF_DEALLOC		= 5,
 	HIF_HOLDER		= 6,
 	HIF_FIRST		= 7,
 	HIF_ABORTED		= 9,
@@ -130,7 +127,7 @@ struct gfs2_holder {
 	struct list_head gh_list;
 
 	struct gfs2_glock *gh_gl;
-	struct task_struct *gh_owner;
+	pid_t gh_owner_pid;
 	unsigned int gh_state;
 	unsigned gh_flags;
 
@@ -142,8 +139,8 @@ struct gfs2_holder {
 enum {
 	GLF_LOCK		= 1,
 	GLF_STICKY		= 2,
+	GLF_DEMOTE		= 3,
 	GLF_DIRTY		= 5,
-	GLF_SKIP_WAITERS2	= 6,
 };
 
 struct gfs2_glock {
@@ -156,11 +153,12 @@ struct gfs2_glock {
 
 	unsigned int gl_state;
 	unsigned int gl_hash;
-	struct task_struct *gl_owner;
+	unsigned int gl_demote_state; /* state requested by remote node */
+	unsigned long gl_demote_time; /* time of first demote request */
+	pid_t gl_owner_pid;
 	unsigned long gl_ip;
 	struct list_head gl_holders;
 	struct list_head gl_waiters1;	/* HIF_MUTEX */
-	struct list_head gl_waiters2;	/* HIF_DEMOTE */
 	struct list_head gl_waiters3;	/* HIF_PROMOTE */
 
 	const struct gfs2_glock_operations *gl_ops;
@@ -611,6 +609,8 @@ struct gfs2_sbd {
 
 	unsigned long sd_last_warning;
 	struct vfsmount *sd_gfs2mnt;
+	struct dentry *debugfs_dir;    /* debugfs directory */
+	struct dentry *debugfs_dentry_glocks; /* for debugfs */
 };
 
 #endif /* __INCORE_DOT_H__ */

fs/gfs2/locking/dlm/lock.c

@@ -151,7 +151,7 @@ static inline unsigned int make_flags(struct gdlm_lock *lp,
 
 /* make_strname - convert GFS lock numbers to a string */
 
-static inline void make_strname(struct lm_lockname *lockname,
+static inline void make_strname(const struct lm_lockname *lockname,
 				struct gdlm_strname *str)
 {
 	sprintf(str->name, "%8x%16llx", lockname->ln_type,
@@ -169,6 +169,7 @@ static int gdlm_create_lp(struct gdlm_ls *ls, struct lm_lockname *name,
 		return -ENOMEM;
 
 	lp->lockname = *name;
+	make_strname(name, &lp->strname);
 	lp->ls = ls;
 	lp->cur = DLM_LOCK_IV;
 	lp->lvb = NULL;
@@ -227,7 +228,6 @@ void gdlm_put_lock(void *lock)
 unsigned int gdlm_do_lock(struct gdlm_lock *lp)
 {
 	struct gdlm_ls *ls = lp->ls;
-	struct gdlm_strname str;
 	int error, bast = 1;
 
 	/*
@@ -249,8 +249,6 @@ unsigned int gdlm_do_lock(struct gdlm_lock *lp)
 	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,
@@ -258,8 +256,8 @@ unsigned int gdlm_do_lock(struct gdlm_lock *lp)
 		  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);
+			 lp->strname.name, lp->strname.namelen, 0, gdlm_ast,
+			 lp, bast ? gdlm_bast : NULL);
 
 	if ((error == -EAGAIN) && (lp->lkf & DLM_LKF_NOQUEUE)) {
 		lp->lksb.sb_status = -EAGAIN;
@@ -268,7 +266,7 @@ unsigned int gdlm_do_lock(struct gdlm_lock *lp)
 	}
 
 	if (error) {
-		log_debug("%s: gdlm_lock %x,%llx err=%d cur=%d req=%d lkf=%x "
+		log_error("%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);
@@ -296,7 +294,7 @@ static unsigned int gdlm_do_unlock(struct gdlm_lock *lp)
 	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 "
+		log_error("%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);

fs/gfs2/locking/dlm/lock_dlm.h

@@ -36,7 +36,7 @@
 
 #define GDLM_STRNAME_BYTES	24
 #define GDLM_LVB_SIZE		32
-#define GDLM_DROP_COUNT		200000
+#define GDLM_DROP_COUNT		0
 #define GDLM_DROP_PERIOD	60
 #define GDLM_NAME_LEN		128
 
@@ -106,6 +106,7 @@ enum {
 struct gdlm_lock {
 	struct gdlm_ls		*ls;
 	struct lm_lockname	lockname;
+	struct gdlm_strname	strname;
 	char			*lvb;
 	struct dlm_lksb		lksb;
 

fs/gfs2/lops.c

@@ -33,16 +33,17 @@ static void glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 
 	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);
+	if (!list_empty(&le->le_list)){
+		gfs2_log_unlock(sdp);
+		return;
+	}
+	gfs2_glock_hold(gl);
+	set_bit(GLF_DIRTY, &gl->gl_flags);
 	sdp->sd_log_num_gl++;
 	list_add(&le->le_list, &sdp->sd_log_le_gl);
 	gfs2_log_unlock(sdp);
@@ -415,13 +416,14 @@ static void rg_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 
 	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);
+	if (!list_empty(&le->le_list)){
+		gfs2_log_unlock(sdp);
+		return;
+	}
+	gfs2_rgrp_bh_hold(rgd);
 	sdp->sd_log_num_rg++;
 	list_add(&le->le_list, &sdp->sd_log_le_rg);
 	gfs2_log_unlock(sdp);

fs/gfs2/main.c

@@ -43,7 +43,6 @@ static void gfs2_init_glock_once(void *foo, struct kmem_cache *cachep, unsigned
 		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);
@@ -101,6 +100,8 @@ static int __init init_gfs2_fs(void)
 	if (error)
 		goto fail_unregister;
 
+	gfs2_register_debugfs();
+
 	printk("GFS2 (built %s %s) installed\n", __DATE__, __TIME__);
 
 	return 0;
@@ -128,6 +129,7 @@ static int __init init_gfs2_fs(void)
 
 static void __exit exit_gfs2_fs(void)
 {
+	gfs2_unregister_debugfs();
 	unregister_filesystem(&gfs2_fs_type);
 	unregister_filesystem(&gfs2meta_fs_type);
 

fs/gfs2/mount.c

@@ -13,6 +13,7 @@
 #include <linux/buffer_head.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/lm_interface.h>
+#include <linux/parser.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -20,6 +21,52 @@
 #include "sys.h"
 #include "util.h"
 
+enum {
+	Opt_lockproto,
+	Opt_locktable,
+	Opt_hostdata,
+	Opt_spectator,
+	Opt_ignore_local_fs,
+	Opt_localflocks,
+	Opt_localcaching,
+	Opt_debug,
+	Opt_nodebug,
+	Opt_upgrade,
+	Opt_num_glockd,
+	Opt_acl,
+	Opt_noacl,
+	Opt_quota_off,
+	Opt_quota_account,
+	Opt_quota_on,
+	Opt_suiddir,
+	Opt_nosuiddir,
+	Opt_data_writeback,
+	Opt_data_ordered,
+};
+
+static match_table_t tokens = {
+	{Opt_lockproto, "lockproto=%s"},
+	{Opt_locktable, "locktable=%s"},
+	{Opt_hostdata, "hostdata=%s"},
+	{Opt_spectator, "spectator"},
+	{Opt_ignore_local_fs, "ignore_local_fs"},
+	{Opt_localflocks, "localflocks"},
+	{Opt_localcaching, "localcaching"},
+	{Opt_debug, "debug"},
+	{Opt_nodebug, "nodebug"},
+	{Opt_upgrade, "upgrade"},
+	{Opt_num_glockd, "num_glockd=%d"},
+	{Opt_acl, "acl"},
+	{Opt_noacl, "noacl"},
+	{Opt_quota_off, "quota=off"},
+	{Opt_quota_account, "quota=account"},
+	{Opt_quota_on, "quota=on"},
+	{Opt_suiddir, "suiddir"},
+	{Opt_nosuiddir, "nosuiddir"},
+	{Opt_data_writeback, "data=writeback"},
+	{Opt_data_ordered, "data=ordered"}
+};
+
 /**
  * gfs2_mount_args - Parse mount options
  * @sdp:
@@ -54,146 +101,150 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount)
 	   process them */
 
 	for (options = data; (o = strsep(&options, ",")); ) {
+		int token, option;
+		substring_t tmp[MAX_OPT_ARGS];
+
 		if (!*o)
 			continue;
 
-		v = strchr(o, '=');
-		if (v)
-			*v++ = 0;
+		token = match_token(o, tokens, tmp);
+		switch (token) {
+		case Opt_lockproto:
+			v = match_strdup(&tmp[0]);
+			if (!v) {
+				fs_info(sdp, "no memory for lockproto\n");
+				error = -ENOMEM;
+				goto out_error;
+			}
 
-		if (!strcmp(o, "lockproto")) {
-			if (!v)
-				goto need_value;
-			if (remount && strcmp(v, args->ar_lockproto))
+			if (remount && strcmp(v, args->ar_lockproto)) {
+				kfree(v);
 				goto cant_remount;
+			}
+			
 			strncpy(args->ar_lockproto, v, GFS2_LOCKNAME_LEN);
 			args->ar_lockproto[GFS2_LOCKNAME_LEN - 1] = 0;
+			kfree(v);
+			break;
+		case Opt_locktable:
+			v = match_strdup(&tmp[0]);
+			if (!v) {
+				fs_info(sdp, "no memory for locktable\n");
+				error = -ENOMEM;
+				goto out_error;
 			}
 
-		else if (!strcmp(o, "locktable")) {
-			if (!v)
-				goto need_value;
-			if (remount && strcmp(v, args->ar_locktable))
+			if (remount && strcmp(v, args->ar_locktable)) {
+				kfree(v);
 				goto cant_remount;
+			}
+
 			strncpy(args->ar_locktable, v, GFS2_LOCKNAME_LEN);
 			args->ar_locktable[GFS2_LOCKNAME_LEN - 1]  = 0;
+			kfree(v);
+			break;
+		case Opt_hostdata:
+			v = match_strdup(&tmp[0]);
+			if (!v) {
+				fs_info(sdp, "no memory for hostdata\n");
+				error = -ENOMEM;
+				goto out_error;
 			}
 
-		else if (!strcmp(o, "hostdata")) {
-			if (!v)
-				goto need_value;
-			if (remount && strcmp(v, args->ar_hostdata))
+			if (remount && strcmp(v, args->ar_hostdata)) {
+				kfree(v);
 				goto cant_remount;
-			strncpy(args->ar_hostdata, v, GFS2_LOCKNAME_LEN);
-			args->ar_hostdata[GFS2_LOCKNAME_LEN - 1] = 0;
 			}
 
-		else if (!strcmp(o, "spectator")) {
+			strncpy(args->ar_hostdata, v, GFS2_LOCKNAME_LEN);
+			args->ar_hostdata[GFS2_LOCKNAME_LEN - 1] = 0;
+			kfree(v);
+			break;
+		case Opt_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")) {
+			break;
+		case Opt_ignore_local_fs:
 			if (remount && !args->ar_ignore_local_fs)
 				goto cant_remount;
 			args->ar_ignore_local_fs = 1;
-		}
-
-		else if (!strcmp(o, "localflocks")) {
+			break;
+		case Opt_localflocks:
 			if (remount && !args->ar_localflocks)
 				goto cant_remount;
 			args->ar_localflocks = 1;
-		}
-
-		else if (!strcmp(o, "localcaching")) {
+			break;
+		case Opt_localcaching:
 			if (remount && !args->ar_localcaching)
 				goto cant_remount;
 			args->ar_localcaching = 1;
-		}
-
-		else if (!strcmp(o, "debug"))
+			break;
+		case Opt_debug:
 			args->ar_debug = 1;
-
-		else if (!strcmp(o, "nodebug"))
+			break;
+		case Opt_nodebug:
 			args->ar_debug = 0;
-
-		else if (!strcmp(o, "upgrade")) {
+			break;
+		case Opt_upgrade:
 			if (remount && !args->ar_upgrade)
 				goto cant_remount;
 			args->ar_upgrade = 1;
+			break;
+		case Opt_num_glockd:
+			if ((error = match_int(&tmp[0], &option))) {
+				fs_info(sdp, "problem getting num_glockd\n");
+				goto out_error;
 			}
 
-		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)
+			if (remount && option != args->ar_num_glockd)
 				goto cant_remount;
-			if (!x || x > GFS2_GLOCKD_MAX) {
+			if (!option || option > GFS2_GLOCKD_MAX) {
 				fs_info(sdp, "0 < num_glockd <= %u  (not %u)\n",
-				        GFS2_GLOCKD_MAX, x);
+				        GFS2_GLOCKD_MAX, option);
 				error = -EINVAL;
-				break;
+				goto out_error;
 			}
-			args->ar_num_glockd = x;
-		}
-
-		else if (!strcmp(o, "acl")) {
+			args->ar_num_glockd = option;
+			break;
+		case Opt_acl:
 			args->ar_posix_acl = 1;
 			sdp->sd_vfs->s_flags |= MS_POSIXACL;
-		}
-
-		else if (!strcmp(o, "noacl")) {
+			break;
+		case Opt_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"))
+			break;
+		case Opt_quota_off:
 			args->ar_quota = GFS2_QUOTA_OFF;
-			else if (!strcmp(v, "account"))
+			break;
+		case Opt_quota_account:
 			args->ar_quota = GFS2_QUOTA_ACCOUNT;
-			else if (!strcmp(v, "on"))
+			break;
+		case Opt_quota_on:
 			args->ar_quota = GFS2_QUOTA_ON;
-			else {
-				fs_info(sdp, "invalid value for quota\n");
-				error = -EINVAL;
 			break;
-			}
-		}
-
-		else if (!strcmp(o, "suiddir"))
+		case Opt_suiddir:
 			args->ar_suiddir = 1;
-
-		else if (!strcmp(o, "nosuiddir"))
+			break;
+		case Opt_nosuiddir:
 			args->ar_suiddir = 0;
-
-		else if (!strcmp(o, "data")) {
-			if (!v)
-				goto need_value;
-			if (!strcmp(v, "writeback"))
+			break;
+		case Opt_data_writeback:
 			args->ar_data = GFS2_DATA_WRITEBACK;
-			else if (!strcmp(v, "ordered"))
+			break;
+		case Opt_data_ordered:
 			args->ar_data = GFS2_DATA_ORDERED;
-			else {
-				fs_info(sdp, "invalid value for data\n");
-				error = -EINVAL;
 			break;
-			}
-		}
-
-		else {
+		default:
 			fs_info(sdp, "unknown option: %s\n", o);
 			error = -EINVAL;
-			break;
+			goto out_error;
 		}
 	}
 
+out_error:
 	if (error)
 		fs_info(sdp, "invalid mount option(s)\n");
 
@@ -202,10 +253,6 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount)
 
 	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/ops_address.c

@@ -197,7 +197,19 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
 	void *kaddr;
 	int error;
 
-	BUG_ON(page->index);
+	/*
+	 * Due to the order of unstuffing files and ->nopage(), we can be
+	 * asked for a zero page in the case of a stuffed file being extended,
+	 * so we need to supply one here. It doesn't happen often.
+	 */
+	if (unlikely(page->index)) {
+		kaddr = kmap_atomic(page, KM_USER0);
+		memset(kaddr, 0, PAGE_CACHE_SIZE);
+		kunmap_atomic(kaddr, KM_USER0);
+		flush_dcache_page(page);
+		SetPageUptodate(page);
+		return 0;
+	}
 
 	error = gfs2_meta_inode_buffer(ip, &dibh);
 	if (error)
@@ -208,9 +220,8 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
 	       ip->i_di.di_size);
 	memset(kaddr + ip->i_di.di_size, 0, PAGE_CACHE_SIZE - ip->i_di.di_size);
 	kunmap_atomic(kaddr, KM_USER0);
-
+	flush_dcache_page(page);
 	brelse(dibh);
-
 	SetPageUptodate(page);
 
 	return 0;
@@ -507,7 +518,9 @@ static int gfs2_commit_write(struct file *file, struct page *page,
 		gfs2_quota_unlock(ip);
 		gfs2_alloc_put(ip);
 	}
+	unlock_page(page);
 	gfs2_glock_dq_m(1, &ip->i_gh);
+	lock_page(page);
 	gfs2_holder_uninit(&ip->i_gh);
 	return 0;
 
@@ -520,7 +533,9 @@ static int gfs2_commit_write(struct file *file, struct page *page,
 		gfs2_quota_unlock(ip);
 		gfs2_alloc_put(ip);
 	}
+	unlock_page(page);
 	gfs2_glock_dq_m(1, &ip->i_gh);
+	lock_page(page);
 	gfs2_holder_uninit(&ip->i_gh);
 fail_nounlock:
 	ClearPageUptodate(page);

fs/gfs2/ops_fstype.c

@@ -690,6 +690,8 @@ static int fill_super(struct super_block *sb, void *data, int silent)
 	if (error)
 		goto fail;
 
+	gfs2_create_debugfs_file(sdp);
+
 	error = gfs2_sys_fs_add(sdp);
 	if (error)
 		goto fail;
@@ -754,6 +756,7 @@ static int fill_super(struct super_block *sb, void *data, int silent)
 fail_sys:
 	gfs2_sys_fs_del(sdp);
 fail:
+	gfs2_delete_debugfs_file(sdp);
 	kfree(sdp);
 	sb->s_fs_info = NULL;
 	return error;
@@ -896,6 +899,7 @@ static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags,
 
 static void gfs2_kill_sb(struct super_block *sb)
 {
+	gfs2_delete_debugfs_file(sb->s_fs_info);
 	kill_block_super(sb);
 }
 

fs/gfs2/ops_super.c

@@ -283,6 +283,31 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
 	return error;
 }
 
+/**
+ * gfs2_drop_inode - Drop an inode (test for remote unlink)
+ * @inode: The inode to drop
+ *
+ * If we've received a callback on an iopen lock then its because a
+ * remote node tried to deallocate the inode but failed due to this node
+ * still having the inode open. Here we mark the link count zero
+ * since we know that it must have reached zero if the GLF_DEMOTE flag
+ * is set on the iopen glock. If we didn't do a disk read since the
+ * remote node removed the final link then we might otherwise miss
+ * this event. This check ensures that this node will deallocate the
+ * inode's blocks, or alternatively pass the baton on to another
+ * node for later deallocation.
+ */
+static void gfs2_drop_inode(struct inode *inode)
+{
+	if (inode->i_private && inode->i_nlink) {
+		struct gfs2_inode *ip = GFS2_I(inode);
+		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
+		if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags))
+			clear_nlink(inode);
+	}
+	generic_drop_inode(inode);
+}
+
 /**
  * gfs2_clear_inode - Deallocate an inode when VFS is done with it
  * @inode: The VFS inode
@@ -441,7 +466,7 @@ static void gfs2_delete_inode(struct inode *inode)
 out_uninit:
 	gfs2_holder_uninit(&ip->i_iopen_gh);
 	gfs2_glock_dq_uninit(&gh);
-	if (error)
+	if (error && error != GLR_TRYFAILED)
 		fs_warn(sdp, "gfs2_delete_inode: %d\n", error);
 out:
 	truncate_inode_pages(&inode->i_data, 0);
@@ -481,6 +506,7 @@ const struct super_operations gfs2_super_ops = {
 	.statfs			= gfs2_statfs,
 	.remount_fs		= gfs2_remount_fs,
 	.clear_inode		= gfs2_clear_inode,
+	.drop_inode		= gfs2_drop_inode,
 	.show_options		= gfs2_show_options,
 };