From 58e9c04a52abe2c4f0995be71117d8e9dbc01a58 Mon Sep 17 00:00:00 2001
From: Sunil Mushran <sunil.mushran@oracle.com>
Date: Tue, 13 May 2008 13:45:14 -0700
Subject: [PATCH 1/2] ocfs2: Add CONFIG_OCFS2_FS_STATS config option

This patch adds config option CONFIG_OCFS2_FS_STATS to allow building
the fs with instrumentation enabled. An upcoming patch will provide
support to instrument cluster locking, which is a crucial overhead in
a cluster file system. This config option allows users to avoid the cpu
and memory overhead that is involved in gathering such statistics.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/Kconfig | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'fs')

diff --git a/fs/Kconfig b/fs/Kconfig
index cf12c403b8c7..c264610ca27c 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -470,6 +470,14 @@ config OCFS2_FS_USERSPACE_CLUSTER
 	  It is safe to say Y, as the clustering method is run-time
 	  selectable.
 
+config OCFS2_FS_STATS
+	bool "OCFS2 statistics"
+	depends on OCFS2_FS
+	default y
+	help
+	  This option allows some fs statistics to be captured. Enabling
+	  this option may increase the memory consumption.
+
 config OCFS2_DEBUG_MASKLOG
 	bool "OCFS2 logging support"
 	depends on OCFS2_FS
-- 
cgit v1.2.3


From 30e2a703701e9163b69732c6aa40a5f98c850acf Mon Sep 17 00:00:00 2001
From: Sunil Mushran <sunil.mushran@oracle.com>
Date: Tue, 13 May 2008 13:45:15 -0700
Subject: [PATCH 2/2] ocfs2: Instrument fs cluster locks

This patch adds code to track the number of times the fs takes
various cluster locks as well as the times associated with it.
The information is made available to users via debugfs.

This patch was originally written by Jan Kara <jack@suse.cz>.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/ocfs2/dlmglue.c | 122 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
 fs/ocfs2/ocfs2.h   |  12 ++++++
 2 files changed, 133 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 394d25a131a5..6d3c78ec0f29 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -31,6 +31,7 @@
 #include <linux/pagemap.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
+#include <linux/time.h>
 
 #define MLOG_MASK_PREFIX ML_DLM_GLUE
 #include <cluster/masklog.h>
@@ -59,6 +60,9 @@ struct ocfs2_mask_waiter {
 	struct completion	mw_complete;
 	unsigned long		mw_mask;
 	unsigned long		mw_goal;
+#ifdef CONFIG_OCFS2_FS_STATS
+	unsigned long long 	mw_lock_start;
+#endif
 };
 
 static struct ocfs2_super *ocfs2_get_dentry_osb(struct ocfs2_lock_res *lockres);
@@ -366,6 +370,75 @@ static void ocfs2_remove_lockres_tracking(struct ocfs2_lock_res *res)
 	spin_unlock(&ocfs2_dlm_tracking_lock);
 }
 
+#ifdef CONFIG_OCFS2_FS_STATS
+static void ocfs2_init_lock_stats(struct ocfs2_lock_res *res)
+{
+	res->l_lock_num_prmode = 0;
+	res->l_lock_num_prmode_failed = 0;
+	res->l_lock_total_prmode = 0;
+	res->l_lock_max_prmode = 0;
+	res->l_lock_num_exmode = 0;
+	res->l_lock_num_exmode_failed = 0;
+	res->l_lock_total_exmode = 0;
+	res->l_lock_max_exmode = 0;
+	res->l_lock_refresh = 0;
+}
+
+static void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, int level,
+				    struct ocfs2_mask_waiter *mw, int ret)
+{
+	unsigned long long *num, *sum;
+	unsigned int *max, *failed;
+	struct timespec ts = current_kernel_time();
+	unsigned long long time = timespec_to_ns(&ts) - mw->mw_lock_start;
+
+	if (level == LKM_PRMODE) {
+		num = &res->l_lock_num_prmode;
+		sum = &res->l_lock_total_prmode;
+		max = &res->l_lock_max_prmode;
+		failed = &res->l_lock_num_prmode_failed;
+	} else if (level == LKM_EXMODE) {
+		num = &res->l_lock_num_exmode;
+		sum = &res->l_lock_total_exmode;
+		max = &res->l_lock_max_exmode;
+		failed = &res->l_lock_num_exmode_failed;
+	} else
+		return;
+
+	(*num)++;
+	(*sum) += time;
+	if (time > *max)
+		*max = time;
+	if (ret)
+		(*failed)++;
+}
+
+static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres)
+{
+	lockres->l_lock_refresh++;
+}
+
+static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw)
+{
+	struct timespec ts = current_kernel_time();
+	mw->mw_lock_start = timespec_to_ns(&ts);
+}
+#else
+static inline void ocfs2_init_lock_stats(struct ocfs2_lock_res *res)
+{
+}
+static inline void ocfs2_update_lock_stats(struct ocfs2_lock_res *res,
+			   int level, struct ocfs2_mask_waiter *mw, int ret)
+{
+}
+static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres)
+{
+}
+static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw)
+{
+}
+#endif
+
 static void ocfs2_lock_res_init_common(struct ocfs2_super *osb,
 				       struct ocfs2_lock_res *res,
 				       enum ocfs2_lock_type type,
@@ -385,6 +458,8 @@ static void ocfs2_lock_res_init_common(struct ocfs2_super *osb,
 	res->l_flags         = OCFS2_LOCK_INITIALIZED;
 
 	ocfs2_add_lockres_tracking(res, osb->osb_dlm_debug);
+
+	ocfs2_init_lock_stats(res);
 }
 
 void ocfs2_lock_res_init_once(struct ocfs2_lock_res *res)
@@ -1048,6 +1123,7 @@ static void ocfs2_init_mask_waiter(struct ocfs2_mask_waiter *mw)
 {
 	INIT_LIST_HEAD(&mw->mw_item);
 	init_completion(&mw->mw_complete);
+	ocfs2_init_start_time(mw);
 }
 
 static int ocfs2_wait_for_mask(struct ocfs2_mask_waiter *mw)
@@ -1254,6 +1330,7 @@ out:
 			goto again;
 		mlog_errno(ret);
 	}
+	ocfs2_update_lock_stats(lockres, level, &mw, ret);
 
 	mlog_exit(ret);
 	return ret;
@@ -1983,6 +2060,7 @@ static int ocfs2_inode_lock_update(struct inode *inode,
 				le32_to_cpu(fe->i_flags));
 
 		ocfs2_refresh_inode(inode, fe);
+		ocfs2_track_lock_refresh(lockres);
 	}
 
 	status = 0;
@@ -2267,6 +2345,7 @@ int ocfs2_super_lock(struct ocfs2_super *osb,
 
 		if (status < 0)
 			mlog_errno(status);
+		ocfs2_track_lock_refresh(lockres);
 	}
 bail:
 	mlog_exit(status);
@@ -2461,7 +2540,7 @@ static void *ocfs2_dlm_seq_next(struct seq_file *m, void *v, loff_t *pos)
 }
 
 /* So that debugfs.ocfs2 can determine which format is being used */
-#define OCFS2_DLM_DEBUG_STR_VERSION 1
+#define OCFS2_DLM_DEBUG_STR_VERSION 2
 static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
 {
 	int i;
@@ -2502,6 +2581,47 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
 	for(i = 0; i < DLM_LVB_LEN; i++)
 		seq_printf(m, "0x%x\t", lvb[i]);
 
+#ifdef CONFIG_OCFS2_FS_STATS
+# define lock_num_prmode(_l)		(_l)->l_lock_num_prmode
+# define lock_num_exmode(_l)		(_l)->l_lock_num_exmode
+# define lock_num_prmode_failed(_l)	(_l)->l_lock_num_prmode_failed
+# define lock_num_exmode_failed(_l)	(_l)->l_lock_num_exmode_failed
+# define lock_total_prmode(_l)		(_l)->l_lock_total_prmode
+# define lock_total_exmode(_l)		(_l)->l_lock_total_exmode
+# define lock_max_prmode(_l)		(_l)->l_lock_max_prmode
+# define lock_max_exmode(_l)		(_l)->l_lock_max_exmode
+# define lock_refresh(_l)		(_l)->l_lock_refresh
+#else
+# define lock_num_prmode(_l)		(0)
+# define lock_num_exmode(_l)		(0)
+# define lock_num_prmode_failed(_l)	(0)
+# define lock_num_exmode_failed(_l)	(0)
+# define lock_total_prmode(_l)		(0)
+# define lock_total_exmode(_l)		(0)
+# define lock_max_prmode(_l)		(0)
+# define lock_max_exmode(_l)		(0)
+# define lock_refresh(_l)		(0)
+#endif
+	/* The following seq_print was added in version 2 of this output */
+	seq_printf(m, "%llu\t"
+		   "%llu\t"
+		   "%u\t"
+		   "%u\t"
+		   "%llu\t"
+		   "%llu\t"
+		   "%u\t"
+		   "%u\t"
+		   "%u\t",
+		   lock_num_prmode(lockres),
+		   lock_num_exmode(lockres),
+		   lock_num_prmode_failed(lockres),
+		   lock_num_exmode_failed(lockres),
+		   lock_total_prmode(lockres),
+		   lock_total_exmode(lockres),
+		   lock_max_prmode(lockres),
+		   lock_max_exmode(lockres),
+		   lock_refresh(lockres));
+
 	/* End the line */
 	seq_printf(m, "\n");
 	return 0;
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 31692379c170..1cb814be8ef1 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -132,6 +132,18 @@ struct ocfs2_lock_res {
 	wait_queue_head_t        l_event;
 
 	struct list_head         l_debug_list;
+
+#ifdef CONFIG_OCFS2_FS_STATS
+	unsigned long long	 l_lock_num_prmode; 	   /* PR acquires */
+	unsigned long long 	 l_lock_num_exmode; 	   /* EX acquires */
+	unsigned int		 l_lock_num_prmode_failed; /* Failed PR gets */
+	unsigned int		 l_lock_num_exmode_failed; /* Failed EX gets */
+	unsigned long long	 l_lock_total_prmode; 	   /* Tot wait for PR */
+	unsigned long long	 l_lock_total_exmode; 	   /* Tot wait for EX */
+	unsigned int		 l_lock_max_prmode; 	   /* Max wait for PR */
+	unsigned int		 l_lock_max_exmode; 	   /* Max wait for EX */
+	unsigned int		 l_lock_refresh;	   /* Disk refreshes */
+#endif
 };
 
 struct ocfs2_dlm_debug {
-- 
cgit v1.2.3


From d625ad4713bce0af0edead557387129dc35edf19 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <randy.dunlap@oracle.com>
Date: Wed, 28 May 2008 14:41:00 -0700
Subject: ocfs2: fix printk format warnings with OCFS2_FS_STATS=n

Fix printk format warnings when OCFS2_FS_STATS=n:

linux-next-20080528/fs/ocfs2/dlmglue.c: In function 'ocfs2_dlm_seq_show':
linux-next-20080528/fs/ocfs2/dlmglue.c:2623: warning: format '%llu' expects type 'long long unsigned int', but argument 3 has type 'int'
linux-next-20080528/fs/ocfs2/dlmglue.c:2623: warning: format '%llu' expects type 'long long unsigned int', but argument 4 has type 'int'
linux-next-20080528/fs/ocfs2/dlmglue.c:2623: warning: format '%llu' expects type 'long long unsigned int', but argument 7 has type 'int'
linux-next-20080528/fs/ocfs2/dlmglue.c:2623: warning: format '%llu' expects type 'long long unsigned int', but argument 8 has type 'int'

Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/ocfs2/dlmglue.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'fs')

diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 6d3c78ec0f29..1c6da696d213 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2592,12 +2592,12 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
 # define lock_max_exmode(_l)		(_l)->l_lock_max_exmode
 # define lock_refresh(_l)		(_l)->l_lock_refresh
 #else
-# define lock_num_prmode(_l)		(0)
-# define lock_num_exmode(_l)		(0)
+# define lock_num_prmode(_l)		(0ULL)
+# define lock_num_exmode(_l)		(0ULL)
 # define lock_num_prmode_failed(_l)	(0)
 # define lock_num_exmode_failed(_l)	(0)
-# define lock_total_prmode(_l)		(0)
-# define lock_total_exmode(_l)		(0)
+# define lock_total_prmode(_l)		(0ULL)
+# define lock_total_exmode(_l)		(0ULL)
 # define lock_max_prmode(_l)		(0)
 # define lock_max_exmode(_l)		(0)
 # define lock_refresh(_l)		(0)
-- 
cgit v1.2.3


From d7e3b0226349a0a756440385c8e72b1668f71bc1 Mon Sep 17 00:00:00 2001
From: Joel Becker <joel.becker@oracle.com>
Date: Fri, 30 May 2008 15:30:49 -0700
Subject: ocfs2: Move the hb_ctl_path sysctl into the stack glue.

ocfs2 needs to call out to the hb_ctl program at unmount for all cluster
stacks.  The first step is to move the hb_ctl_path sysctl out of the
o2cb code and into the generic stack glue.

Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/ocfs2/cluster/nodemanager.c | 74 +-----------------------------------
 fs/ocfs2/cluster/nodemanager.h |  4 --
 fs/ocfs2/stack_o2cb.c          |  2 +-
 fs/ocfs2/stackglue.c           | 85 ++++++++++++++++++++++++++++++++++++++++++
 fs/ocfs2/stackglue.h           |  2 +
 5 files changed, 89 insertions(+), 78 deletions(-)

(limited to 'fs')

diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index cf9401e8cd0b..cfdb08b484ed 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -21,7 +21,6 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/sysctl.h>
 #include <linux/configfs.h>
 
 #include "tcp.h"
@@ -36,65 +35,6 @@
  * cluster references throughout where nodes are looked up */
 struct o2nm_cluster *o2nm_single_cluster = NULL;
 
-#define OCFS2_MAX_HB_CTL_PATH 256
-static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl";
-
-static ctl_table ocfs2_nm_table[] = {
-	{
-		.ctl_name	= 1,
-		.procname	= "hb_ctl_path",
-		.data		= ocfs2_hb_ctl_path,
-		.maxlen		= OCFS2_MAX_HB_CTL_PATH,
-		.mode		= 0644,
-		.proc_handler	= &proc_dostring,
-		.strategy	= &sysctl_string,
-	},
-	{ .ctl_name = 0 }
-};
-
-static ctl_table ocfs2_mod_table[] = {
-	{
-		.ctl_name	= FS_OCFS2_NM,
-		.procname	= "nm",
-		.data		= NULL,
-		.maxlen		= 0,
-		.mode		= 0555,
-		.child		= ocfs2_nm_table
-	},
-	{ .ctl_name = 0}
-};
-
-static ctl_table ocfs2_kern_table[] = {
-	{
-		.ctl_name	= FS_OCFS2,
-		.procname	= "ocfs2",
-		.data		= NULL,
-		.maxlen		= 0,
-		.mode		= 0555,
-		.child		= ocfs2_mod_table
-	},
-	{ .ctl_name = 0}
-};
-
-static ctl_table ocfs2_root_table[] = {
-	{
-		.ctl_name	= CTL_FS,
-		.procname	= "fs",
-		.data		= NULL,
-		.maxlen		= 0,
-		.mode		= 0555,
-		.child		= ocfs2_kern_table
-	},
-	{ .ctl_name = 0 }
-};
-
-static struct ctl_table_header *ocfs2_table_header = NULL;
-
-const char *o2nm_get_hb_ctl_path(void)
-{
-	return ocfs2_hb_ctl_path;
-}
-EXPORT_SYMBOL_GPL(o2nm_get_hb_ctl_path);
 
 struct o2nm_node *o2nm_get_node_by_num(u8 node_num)
 {
@@ -941,9 +881,6 @@ void o2nm_undepend_this_node(void)
 
 static void __exit exit_o2nm(void)
 {
-	if (ocfs2_table_header)
-		unregister_sysctl_table(ocfs2_table_header);
-
 	/* XXX sync with hb callbacks and shut down hb? */
 	o2net_unregister_hb_callbacks();
 	configfs_unregister_subsystem(&o2nm_cluster_group.cs_subsys);
@@ -964,16 +901,9 @@ static int __init init_o2nm(void)
 	if (ret)
 		goto out;
 
-	ocfs2_table_header = register_sysctl_table(ocfs2_root_table);
-	if (!ocfs2_table_header) {
-		printk(KERN_ERR "nodemanager: unable to register sysctl\n");
-		ret = -ENOMEM; /* or something. */
-		goto out_o2net;
-	}
-
 	ret = o2net_register_hb_callbacks();
 	if (ret)
-		goto out_sysctl;
+		goto out_o2net;
 
 	config_group_init(&o2nm_cluster_group.cs_subsys.su_group);
 	mutex_init(&o2nm_cluster_group.cs_subsys.su_mutex);
@@ -990,8 +920,6 @@ static int __init init_o2nm(void)
 	configfs_unregister_subsystem(&o2nm_cluster_group.cs_subsys);
 out_callbacks:
 	o2net_unregister_hb_callbacks();
-out_sysctl:
-	unregister_sysctl_table(ocfs2_table_header);
 out_o2net:
 	o2net_exit();
 out:
diff --git a/fs/ocfs2/cluster/nodemanager.h b/fs/ocfs2/cluster/nodemanager.h
index 7c860361b8dd..c992ea0da4ad 100644
--- a/fs/ocfs2/cluster/nodemanager.h
+++ b/fs/ocfs2/cluster/nodemanager.h
@@ -33,10 +33,6 @@
 #include <linux/configfs.h>
 #include <linux/rbtree.h>
 
-#define FS_OCFS2_NM		1
-
-const char *o2nm_get_hb_ctl_path(void);
-
 struct o2nm_node {
 	spinlock_t		nd_lock;
 	struct config_item	nd_item;
diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c
index bbd1667aa7d3..fb26a7c69c47 100644
--- a/fs/ocfs2/stack_o2cb.c
+++ b/fs/ocfs2/stack_o2cb.c
@@ -338,7 +338,7 @@ static void o2hb_stop(const char *group)
 	int ret;
 	char *argv[5], *envp[3];
 
-	argv[0] = (char *)o2nm_get_hb_ctl_path();
+	argv[0] = (char *)ocfs2_get_hb_ctl_path();
 	argv[1] = "-K";
 	argv[2] = "-u";
 	argv[3] = (char *)group;
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 119f60cea9cc..fb9b8e0db260 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -26,6 +26,7 @@
 #include <linux/fs.h>
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
+#include <linux/sysctl.h>
 
 #include "ocfs2_fs.h"
 
@@ -548,10 +549,92 @@ error:
 	return ret;
 }
 
+/*
+ * Sysctl bits
+ *
+ * The sysctl lives at /proc/sys/fs/ocfs2/nm/hb_ctl_path.  The 'nm' doesn't
+ * make as much sense in a multiple cluster stack world, but it's safer
+ * and easier to preserve the name.
+ */
+
+#define FS_OCFS2_NM		1
+
+#define OCFS2_MAX_HB_CTL_PATH 256
+static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl";
+
+static ctl_table ocfs2_nm_table[] = {
+	{
+		.ctl_name	= 1,
+		.procname	= "hb_ctl_path",
+		.data		= ocfs2_hb_ctl_path,
+		.maxlen		= OCFS2_MAX_HB_CTL_PATH,
+		.mode		= 0644,
+		.proc_handler	= &proc_dostring,
+		.strategy	= &sysctl_string,
+	},
+	{ .ctl_name = 0 }
+};
+
+static ctl_table ocfs2_mod_table[] = {
+	{
+		.ctl_name	= FS_OCFS2_NM,
+		.procname	= "nm",
+		.data		= NULL,
+		.maxlen		= 0,
+		.mode		= 0555,
+		.child		= ocfs2_nm_table
+	},
+	{ .ctl_name = 0}
+};
+
+static ctl_table ocfs2_kern_table[] = {
+	{
+		.ctl_name	= FS_OCFS2,
+		.procname	= "ocfs2",
+		.data		= NULL,
+		.maxlen		= 0,
+		.mode		= 0555,
+		.child		= ocfs2_mod_table
+	},
+	{ .ctl_name = 0}
+};
+
+static ctl_table ocfs2_root_table[] = {
+	{
+		.ctl_name	= CTL_FS,
+		.procname	= "fs",
+		.data		= NULL,
+		.maxlen		= 0,
+		.mode		= 0555,
+		.child		= ocfs2_kern_table
+	},
+	{ .ctl_name = 0 }
+};
+
+static struct ctl_table_header *ocfs2_table_header = NULL;
+
+const char *ocfs2_get_hb_ctl_path(void)
+{
+	return ocfs2_hb_ctl_path;
+}
+EXPORT_SYMBOL_GPL(ocfs2_get_hb_ctl_path);
+
+
+/*
+ * Initialization
+ */
+
 static int __init ocfs2_stack_glue_init(void)
 {
 	strcpy(cluster_stack_name, OCFS2_STACK_PLUGIN_O2CB);
 
+	ocfs2_table_header = register_sysctl_table(ocfs2_root_table);
+	if (!ocfs2_table_header) {
+		printk(KERN_ERR
+		       "ocfs2 stack glue: unable to register sysctl\n");
+		return -ENOMEM; /* or something. */
+	}
+
 	return ocfs2_sysfs_init();
 }
 
@@ -559,6 +642,8 @@ static void __exit ocfs2_stack_glue_exit(void)
 {
 	lproto = NULL;
 	ocfs2_sysfs_exit();
+	if (ocfs2_table_header)
+		unregister_sysctl_table(ocfs2_table_header);
 }
 
 MODULE_AUTHOR("Oracle");
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index 005e4f170e0f..c9fb01ab6347 100644
--- a/fs/ocfs2/stackglue.h
+++ b/fs/ocfs2/stackglue.h
@@ -258,4 +258,6 @@ void ocfs2_stack_glue_set_locking_protocol(struct ocfs2_locking_protocol *proto)
 /* Used by stack plugins */
 int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin);
 void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin);
+const char *ocfs2_get_hb_ctl_path(void);
+
 #endif  /* STACKGLUE_H */
-- 
cgit v1.2.3


From 3dda66cb80cbc67c6f194920e950bdb42c36f8e3 Mon Sep 17 00:00:00 2001
From: Joel Becker <joel.becker@oracle.com>
Date: Fri, 30 May 2008 15:43:58 -0700
Subject: ocfs2: Move the call of ocfs2_hb_ctl into the stack glue.

Take o2hb_stop() out of the o2cb code and make it part of the generic
stack glue as ocfs2_leave_group().  This also allows us to remove the
ocfs2_get_hb_ctl_path() function - everything to do with hb_ctl is now
part of stackglue.c.  o2cb no longer needs a ->hangup() function.

Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/ocfs2/stack_o2cb.c | 38 --------------------------------------
 fs/ocfs2/stackglue.c  | 49 ++++++++++++++++++++++++++++++++++++++++---------
 fs/ocfs2/stackglue.h  |  1 -
 3 files changed, 40 insertions(+), 48 deletions(-)

(limited to 'fs')

diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c
index fb26a7c69c47..765ade5ee84a 100644
--- a/fs/ocfs2/stack_o2cb.c
+++ b/fs/ocfs2/stack_o2cb.c
@@ -333,43 +333,6 @@ static int o2cb_cluster_disconnect(struct ocfs2_cluster_connection *conn,
 	return 0;
 }
 
-static void o2hb_stop(const char *group)
-{
-	int ret;
-	char *argv[5], *envp[3];
-
-	argv[0] = (char *)ocfs2_get_hb_ctl_path();
-	argv[1] = "-K";
-	argv[2] = "-u";
-	argv[3] = (char *)group;
-	argv[4] = NULL;
-
-	mlog(0, "Run: %s %s %s %s\n", argv[0], argv[1], argv[2], argv[3]);
-
-	/* minimal command environment taken from cpu_run_sbin_hotplug */
-	envp[0] = "HOME=/";
-	envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
-	envp[2] = NULL;
-
-	ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
-	if (ret < 0)
-		mlog_errno(ret);
-}
-
-/*
- * Hangup is a hack for tools compatibility.  Older ocfs2-tools software
- * expects the filesystem to call "ocfs2_hb_ctl" during unmount.  This
- * happens regardless of whether the DLM got started, so we can't do it
- * in ocfs2_cluster_disconnect().  We bring the o2hb_stop() function into
- * the glue and provide a "hangup" API for super.c to call.
- *
- * Other stacks will eventually provide a NULL ->hangup() pointer.
- */
-static void o2cb_cluster_hangup(const char *group, int grouplen)
-{
-	o2hb_stop(group);
-}
-
 static int o2cb_cluster_this_node(unsigned int *node)
 {
 	int node_num;
@@ -388,7 +351,6 @@ static int o2cb_cluster_this_node(unsigned int *node)
 static struct ocfs2_stack_operations o2cb_stack_ops = {
 	.connect	= o2cb_cluster_connect,
 	.disconnect	= o2cb_cluster_disconnect,
-	.hangup		= o2cb_cluster_hangup,
 	.this_node	= o2cb_cluster_this_node,
 	.dlm_lock	= o2cb_dlm_lock,
 	.dlm_unlock	= o2cb_dlm_unlock,
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index fb9b8e0db260..5f78ff4c76c7 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -34,11 +34,13 @@
 
 #define OCFS2_STACK_PLUGIN_O2CB		"o2cb"
 #define OCFS2_STACK_PLUGIN_USER		"user"
+#define OCFS2_MAX_HB_CTL_PATH		256
 
 static struct ocfs2_locking_protocol *lproto;
 static DEFINE_SPINLOCK(ocfs2_stack_lock);
 static LIST_HEAD(ocfs2_stack_list);
 static char cluster_stack_name[OCFS2_STACK_LABEL_LEN + 1];
+static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl";
 
 /*
  * The stack currently in use.  If not null, active_stack->sp_count > 0,
@@ -363,6 +365,42 @@ int ocfs2_cluster_disconnect(struct ocfs2_cluster_connection *conn,
 }
 EXPORT_SYMBOL_GPL(ocfs2_cluster_disconnect);
 
+/*
+ * Leave the group for this filesystem.  This is executed by a userspace
+ * program (stored in ocfs2_hb_ctl_path).
+ */
+static void ocfs2_leave_group(const char *group)
+{
+	int ret;
+	char *argv[5], *envp[3];
+
+	argv[0] = ocfs2_hb_ctl_path;
+	argv[1] = "-K";
+	argv[2] = "-u";
+	argv[3] = (char *)group;
+	argv[4] = NULL;
+
+	/* minimal command environment taken from cpu_run_sbin_hotplug */
+	envp[0] = "HOME=/";
+	envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
+	envp[2] = NULL;
+
+	ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
+	if (ret < 0) {
+		printk(KERN_ERR
+		       "ocfs2: Error %d running user helper "
+		       "\"%s %s %s %s\"\n",
+		       ret, argv[0], argv[1], argv[2], argv[3]);
+	}
+}
+
+/*
+ * Hangup is a required post-umount.  ocfs2-tools software expects the
+ * filesystem to call "ocfs2_hb_ctl" during unmount.  This happens
+ * regardless of whether the DLM got started, so we can't do it
+ * in ocfs2_cluster_disconnect().  The ocfs2_leave_group() function does
+ * the actual work.
+ */
 void ocfs2_cluster_hangup(const char *group, int grouplen)
 {
 	BUG_ON(group == NULL);
@@ -371,6 +409,8 @@ void ocfs2_cluster_hangup(const char *group, int grouplen)
 	if (active_stack->sp_ops->hangup)
 		active_stack->sp_ops->hangup(group, grouplen);
 
+	ocfs2_leave_group(group);
+
 	/* cluster_disconnect() was called with hangup_pending==1 */
 	ocfs2_stack_driver_put();
 }
@@ -559,9 +599,6 @@ error:
 
 #define FS_OCFS2_NM		1
 
-#define OCFS2_MAX_HB_CTL_PATH 256
-static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl";
-
 static ctl_table ocfs2_nm_table[] = {
 	{
 		.ctl_name	= 1,
@@ -613,12 +650,6 @@ static ctl_table ocfs2_root_table[] = {
 
 static struct ctl_table_header *ocfs2_table_header = NULL;
 
-const char *ocfs2_get_hb_ctl_path(void)
-{
-	return ocfs2_hb_ctl_path;
-}
-EXPORT_SYMBOL_GPL(ocfs2_get_hb_ctl_path);
-
 
 /*
  * Initialization
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index c9fb01ab6347..fe3fd2a12821 100644
--- a/fs/ocfs2/stackglue.h
+++ b/fs/ocfs2/stackglue.h
@@ -258,6 +258,5 @@ void ocfs2_stack_glue_set_locking_protocol(struct ocfs2_locking_protocol *proto)
 /* Used by stack plugins */
 int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin);
 void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin);
-const char *ocfs2_get_hb_ctl_path(void);
 
 #endif  /* STACKGLUE_H */
-- 
cgit v1.2.3


From 062e7bc725caab324e0cc26232feb819c5f20396 Mon Sep 17 00:00:00 2001
From: Joel Becker <joel.becker@oracle.com>
Date: Fri, 30 May 2008 15:58:26 -0700
Subject: ocfs2: Remove ->hangup() from stack glue operations.

The ->hangup() call was only used to execute ocfs2_hb_ctl.  Now that
the generic stack glue code handles this, the underlying stack drivers
don't need to know about it.

Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/ocfs2/stack_o2cb.c |  3 +--
 fs/ocfs2/stack_user.c |  3 +--
 fs/ocfs2/stackglue.c  |  5 +----
 fs/ocfs2/stackglue.h  | 18 +++---------------
 4 files changed, 6 insertions(+), 23 deletions(-)

(limited to 'fs')

diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c
index 765ade5ee84a..fcd120f1493a 100644
--- a/fs/ocfs2/stack_o2cb.c
+++ b/fs/ocfs2/stack_o2cb.c
@@ -317,8 +317,7 @@ out:
 	return rc;
 }
 
-static int o2cb_cluster_disconnect(struct ocfs2_cluster_connection *conn,
-				   int hangup_pending)
+static int o2cb_cluster_disconnect(struct ocfs2_cluster_connection *conn)
 {
 	struct dlm_ctxt *dlm = conn->cc_lockspace;
 	struct o2dlm_private *priv = conn->cc_private;
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index 6b97d11f6bf8..c021280dd462 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -816,8 +816,7 @@ out:
 	return rc;
 }
 
-static int user_cluster_disconnect(struct ocfs2_cluster_connection *conn,
-				   int hangup_pending)
+static int user_cluster_disconnect(struct ocfs2_cluster_connection *conn)
 {
 	dlm_release_lockspace(conn->cc_lockspace, 2);
 	conn->cc_lockspace = NULL;
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 5f78ff4c76c7..10e149ae5e3a 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -352,7 +352,7 @@ int ocfs2_cluster_disconnect(struct ocfs2_cluster_connection *conn,
 
 	BUG_ON(conn == NULL);
 
-	ret = active_stack->sp_ops->disconnect(conn, hangup_pending);
+	ret = active_stack->sp_ops->disconnect(conn);
 
 	/* XXX Should we free it anyway? */
 	if (!ret) {
@@ -406,9 +406,6 @@ void ocfs2_cluster_hangup(const char *group, int grouplen)
 	BUG_ON(group == NULL);
 	BUG_ON(group[grouplen] != '\0');
 
-	if (active_stack->sp_ops->hangup)
-		active_stack->sp_ops->hangup(group, grouplen);
-
 	ocfs2_leave_group(group);
 
 	/* cluster_disconnect() was called with hangup_pending==1 */
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index fe3fd2a12821..db56281dd1be 100644
--- a/fs/ocfs2/stackglue.h
+++ b/fs/ocfs2/stackglue.h
@@ -134,22 +134,10 @@ struct ocfs2_stack_operations {
 	 * be freed.  Thus, a stack must not return from ->disconnect()
 	 * until it will no longer reference the conn pointer.
 	 *
-	 * If hangup_pending is zero, ocfs2_cluster_disconnect() will also
-	 * be dropping the reference on the module.
+	 * Once this call returns, the stack glue will be dropping this
+	 * connection's reference on the module.
 	 */
-	int (*disconnect)(struct ocfs2_cluster_connection *conn,
-			  int hangup_pending);
-
-	/*
-	 * ocfs2_cluster_hangup() exists for compatibility with older
-	 * ocfs2 tools.  Only the classic stack really needs it.  As such
-	 * ->hangup() is not required of all stacks.  See the comment by
-	 * ocfs2_cluster_hangup() for more details.
-	 *
-	 * Note that ocfs2_cluster_hangup() can only be called if
-	 * hangup_pending was passed to ocfs2_cluster_disconnect().
-	 */
-	void (*hangup)(const char *group, int grouplen);
+	int (*disconnect)(struct ocfs2_cluster_connection *conn);
 
 	/*
 	 * ->this_node() returns the cluster's unique identifier for the
-- 
cgit v1.2.3


From f0b970600a0fc711dc3e5f3f26cd4135b2283745 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Mon, 9 Jun 2008 16:34:23 -0700
Subject: ocfs2: use simple_read_from_buffer()

Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Acked-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/ocfs2/stack_user.c | 19 +++++--------------
 1 file changed, 5 insertions(+), 14 deletions(-)

(limited to 'fs')

diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index 6b97d11f6bf8..ce39072d63f1 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -549,26 +549,17 @@ static ssize_t ocfs2_control_read(struct file *file,
 				  size_t count,
 				  loff_t *ppos)
 {
-	char *proto_string = OCFS2_CONTROL_PROTO;
-	size_t to_write = 0;
-
-	if (*ppos >= OCFS2_CONTROL_PROTO_LEN)
-		return 0;
-
-	to_write = OCFS2_CONTROL_PROTO_LEN - *ppos;
-	if (to_write > count)
-		to_write = count;
-	if (copy_to_user(buf, proto_string + *ppos, to_write))
-		return -EFAULT;
+	ssize_t ret;
 
-	*ppos += to_write;
+	ret = simple_read_from_buffer(buf, count, ppos,
+			OCFS2_CONTROL_PROTO, OCFS2_CONTROL_PROTO_LEN);
 
 	/* Have we read the whole protocol list? */
-	if (*ppos >= OCFS2_CONTROL_PROTO_LEN)
+	if (ret > 0 && *ppos >= OCFS2_CONTROL_PROTO_LEN)
 		ocfs2_control_set_handshake_state(file,
 						  OCFS2_CONTROL_HANDSHAKE_READ);
 
-	return to_write;
+	return ret;
 }
 
 static int ocfs2_control_release(struct inode *inode, struct file *file)
-- 
cgit v1.2.3


From 8213dbe326ce69df2fb195a5cdee21a47039b1eb Mon Sep 17 00:00:00 2001
From: Sunil Mushran <sunil.mushran@oracle.com>
Date: Mon, 9 Jun 2008 11:24:41 -0700
Subject: ocfs2: Silence an error message in ocfs2_file_aio_read()

This patch silences an EINVAL error message in ocfs2_file_aio_read()
that is always due to a user error.

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/ocfs2/file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 57e0d30cde98..e8514e8b6ce8 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2202,7 +2202,7 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
 
 	ret = generic_file_aio_read(iocb, iov, nr_segs, iocb->ki_pos);
 	if (ret == -EINVAL)
-		mlog(ML_ERROR, "generic_file_aio_read returned -EINVAL\n");
+		mlog(0, "generic_file_aio_read returned -EINVAL\n");
 
 	/* buffered aio wouldn't have proper lock coverage today */
 	BUG_ON(ret == -EIOCBQUEUED && !(filp->f_flags & O_DIRECT));
-- 
cgit v1.2.3


From 78fc39248ed6a69c44c378b956715caf51289793 Mon Sep 17 00:00:00 2001
From: Wengang Wang <wen.gang.wang@oracle.com>
Date: Tue, 10 Jun 2008 14:24:48 +0800
Subject: ocfs2: Handle error during journal load

This patch ensures the mount fails if the fs is unable to load the journal.

Signed-off-by: Wengang Wang <wen.gang.wang@oracle.com>
Acked-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/ocfs2/super.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index df63ba20ae90..ccecfe5094fa 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1703,7 +1703,11 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
 	local = ocfs2_mount_local(osb);
 
 	/* will play back anything left in the journal. */
-	ocfs2_journal_load(osb->journal, local);
+	status = ocfs2_journal_load(osb->journal, local);
+	if (status < 0) {
+		mlog(ML_ERROR, "ocfs2 journal load failed! %d\n", status);
+		goto finally;
+	}
 
 	if (dirty) {
 		/* recover my local alloc if we didn't unmount cleanly. */
-- 
cgit v1.2.3


From ffbffbab7b814d8f5d7674a4894c0928e68310bc Mon Sep 17 00:00:00 2001
From: Sunil Mushran <sunil.mushran@oracle.com>
Date: Mon, 19 May 2008 16:23:37 -0700
Subject: ocfs2/net: Silence build warnings on sparc64

suseconds_t is type long on most arches except sparc64 where it is type int.
This patch silences the following warnings that are generated when building
on it.

netdebug.c: In function 'nst_seq_show':
netdebug.c:152: warning: format '%lu' expects type 'long unsigned int', but argument 13 has type 'suseconds_t'
netdebug.c:152: warning: format '%lu' expects type 'long unsigned int', but argument 15 has type 'suseconds_t'
netdebug.c:152: warning: format '%lu' expects type 'long unsigned int', but argument 17 has type 'suseconds_t'
netdebug.c: In function 'sc_seq_show':
netdebug.c:332: warning: format '%lu' expects type 'long unsigned int', but argument 19 has type 'suseconds_t'
netdebug.c:332: warning: format '%lu' expects type 'long unsigned int', but argument 21 has type 'suseconds_t'
netdebug.c:332: warning: format '%lu' expects type 'long unsigned int', but argument 23 has type 'suseconds_t'
netdebug.c:332: warning: format '%lu' expects type 'long unsigned int', but argument 25 has type 'suseconds_t'
netdebug.c:332: warning: format '%lu' expects type 'long unsigned int', but argument 27 has type 'suseconds_t'
netdebug.c:332: warning: format '%lu' expects type 'long unsigned int', but argument 29 has type 'suseconds_t'

Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/ocfs2/cluster/netdebug.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'fs')

diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c
index 7bf3c0ea7bd9..d8bfa0eb41b2 100644
--- a/fs/ocfs2/cluster/netdebug.c
+++ b/fs/ocfs2/cluster/netdebug.c
@@ -146,8 +146,10 @@ static int nst_seq_show(struct seq_file *seq, void *v)
 			   nst->st_task->comm, nst->st_node,
 			   nst->st_sc, nst->st_id, nst->st_msg_type,
 			   nst->st_msg_key,
-			   nst->st_sock_time.tv_sec, nst->st_sock_time.tv_usec,
-			   nst->st_send_time.tv_sec, nst->st_send_time.tv_usec,
+			   nst->st_sock_time.tv_sec,
+			   (unsigned long)nst->st_sock_time.tv_usec,
+			   nst->st_send_time.tv_sec,
+			   (unsigned long)nst->st_send_time.tv_usec,
 			   nst->st_status_time.tv_sec,
 			   nst->st_status_time.tv_usec);
 	}
@@ -274,7 +276,7 @@ static void *sc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	return sc; /* unused, just needs to be null when done */
 }
 
-#define TV_SEC_USEC(TV) TV.tv_sec, TV.tv_usec
+#define TV_SEC_USEC(TV) TV.tv_sec, (unsigned long)TV.tv_usec
 
 static int sc_seq_show(struct seq_file *seq, void *v)
 {
-- 
cgit v1.2.3