Merge branch 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2

* 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2:
  [PATCH] ocfs2: fix oops in mmap_truncate testing
  configfs: call drop_link() to cleanup after create_link() failure
  configfs: Allow ->make_item() and ->make_group() to return detailed errors.
  configfs: Fix failing mkdir() making racing rmdir() fail
  configfs: Fix deadlock with racing rmdir() and rename()
  configfs: Make configfs_new_dirent() return error code instead of NULL
  configfs: Protect configfs_dirent s_links list mutations
  configfs: Introduce configfs_dirent_lock
  ocfs2: Don't snprintf() without a format.
  ocfs2: Fix CONFIG_OCFS2_DEBUG_FS #ifdefs
  ocfs2/net: Silence build warnings on sparc64
  ocfs2: Handle error during journal load
  ocfs2: Silence an error message in ocfs2_file_aio_read()
  ocfs2: use simple_read_from_buffer()
  ocfs2: fix printk format warnings with OCFS2_FS_STATS=n
  [PATCH 2/2] ocfs2: Instrument fs cluster locks
  [PATCH 1/2] ocfs2: Add CONFIG_OCFS2_FS_STATS config option

12 files changed, 200 insertions, 50 deletions

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 17964c0505a9..1db080135c6d 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -174,10 +174,17 @@ static int ocfs2_get_block(struct inode *inode, sector_t iblock,
 	 * need to use BH_New is when we're extending i_size on a file
 	 * system which doesn't support holes, in which case BH_New
 	 * allows block_prepare_write() to zero.
+	 *
+	 * If we see this on a sparse file system, then a truncate has
+	 * raced us and removed the cluster. In this case, we clear
+	 * the buffers dirty and uptodate bits and let the buffer code
+	 * ignore it as a hole.
 	 */
-	mlog_bug_on_msg(create && p_blkno == 0 && ocfs2_sparse_alloc(osb),
-			"ino %lu, iblock %llu\n", inode->i_ino,
-			(unsigned long long)iblock);
+	if (create && p_blkno == 0 && ocfs2_sparse_alloc(osb)) {
+		clear_buffer_dirty(bh_result);
+		clear_buffer_uptodate(bh_result);
+		goto bail;
+	}
 
 	/* Treat the unwritten extent as a hole for zeroing purposes. */
 	if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index f02ccb34604d..443d108211ab 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1489,25 +1489,28 @@ static struct o2hb_heartbeat_group *to_o2hb_heartbeat_group(struct config_group
 		: NULL;
 }
 
-static struct config_item *o2hb_heartbeat_group_make_item(struct config_group *group,
-							  const char *name)
+static int o2hb_heartbeat_group_make_item(struct config_group *group,
+					  const char *name,
+					  struct config_item **new_item)
 {
 	struct o2hb_region *reg = NULL;
-	struct config_item *ret = NULL;
+	int ret = 0;
 
 	reg = kzalloc(sizeof(struct o2hb_region), GFP_KERNEL);
-	if (reg == NULL)
-		goto out; /* ENOMEM */
+	if (reg == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	config_item_init_type_name(&reg->hr_item, name, &o2hb_region_type);
 
-	ret = &reg->hr_item;
+	*new_item = &reg->hr_item;
 
 	spin_lock(&o2hb_live_lock);
 	list_add_tail(&reg->hr_all_item, &o2hb_all_regions);
 	spin_unlock(&o2hb_live_lock);
 out:
-	if (ret == NULL)
+	if (ret)
 		kfree(reg);
 
 	return ret;
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)
 {
diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index cfdb08b484ed..b364b7052e46 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -644,27 +644,32 @@ out:
 	return ret;
 }
 
-static struct config_item *o2nm_node_group_make_item(struct config_group *group,
-						     const char *name)
+static int o2nm_node_group_make_item(struct config_group *group,
+				     const char *name,
+				     struct config_item **new_item)
 {
 	struct o2nm_node *node = NULL;
-	struct config_item *ret = NULL;
+	int ret = 0;
 
-	if (strlen(name) > O2NM_MAX_NAME_LEN)
-		goto out; /* ENAMETOOLONG */
+	if (strlen(name) > O2NM_MAX_NAME_LEN) {
+		ret = -ENAMETOOLONG;
+		goto out;
+	}
 
 	node = kzalloc(sizeof(struct o2nm_node), GFP_KERNEL);
-	if (node == NULL)
-		goto out; /* ENOMEM */
+	if (node == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	strcpy(node->nd_name, name); /* use item.ci_namebuf instead? */
 	config_item_init_type_name(&node->nd_item, name, &o2nm_node_type);
 	spin_lock_init(&node->nd_lock);
 
-	ret = &node->nd_item;
+	*new_item = &node->nd_item;
 
 out:
-	if (ret == NULL)
+	if (ret)
 		kfree(node);
 
 	return ret;
@@ -751,25 +756,31 @@ static struct o2nm_cluster_group *to_o2nm_cluster_group(struct config_group *gro
 }
 #endif
 
-static struct config_group *o2nm_cluster_group_make_group(struct config_group *group,
-							  const char *name)
+static int o2nm_cluster_group_make_group(struct config_group *group,
+					 const char *name,
+					 struct config_group **new_group)
 {
 	struct o2nm_cluster *cluster = NULL;
 	struct o2nm_node_group *ns = NULL;
-	struct config_group *o2hb_group = NULL, *ret = NULL;
+	struct config_group *o2hb_group = NULL;
 	void *defs = NULL;
+	int ret = 0;
 
 	/* this runs under the parent dir's i_mutex; there can be only
 	 * one caller in here at a time */
-	if (o2nm_single_cluster)
-		goto out; /* ENOSPC */
+	if (o2nm_single_cluster) {
+		ret = -ENOSPC;
+		goto out;
+	}
 
 	cluster = kzalloc(sizeof(struct o2nm_cluster), GFP_KERNEL);
 	ns = kzalloc(sizeof(struct o2nm_node_group), GFP_KERNEL);
 	defs = kcalloc(3, sizeof(struct config_group *), GFP_KERNEL);
 	o2hb_group = o2hb_alloc_hb_set();
-	if (cluster == NULL || ns == NULL || o2hb_group == NULL || defs == NULL)
+	if (cluster == NULL || ns == NULL || o2hb_group == NULL || defs == NULL) {
+		ret = -ENOMEM;
 		goto out;
+	}
 
 	config_group_init_type_name(&cluster->cl_group, name,
 				    &o2nm_cluster_type);
@@ -786,11 +797,11 @@ static struct config_group *o2nm_cluster_group_make_group(struct config_group *g
 	cluster->cl_idle_timeout_ms    = O2NET_IDLE_TIMEOUT_MS_DEFAULT;
 	cluster->cl_keepalive_delay_ms = O2NET_KEEPALIVE_DELAY_MS_DEFAULT;
 
-	ret = &cluster->cl_group;
+	*new_group = &cluster->cl_group;
 	o2nm_single_cluster = cluster;
 
 out:
-	if (ret == NULL) {
+	if (ret) {
 		kfree(cluster);
 		kfree(ns);
 		o2hb_free_hb_set(o2hb_group);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 80e20d9f2780..eae3d643a5e4 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)		(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)		(0ULL)
+# define lock_total_exmode(_l)		(0ULL)
+# 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/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));
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 9698338adc39..a8c19cb3cfdd 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -329,7 +329,7 @@ int ocfs2_extend_trans(handle_t *handle, int nblocks)
 
 	mlog(0, "Trying to extend transaction by %d blocks\n", nblocks);
 
-#ifdef OCFS2_DEBUG_FS
+#ifdef CONFIG_OCFS2_DEBUG_FS
 	status = 1;
 #else
 	status = journal_extend(handle, nblocks);
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index be774bdc8b36..28e492e4ec88 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -498,7 +498,7 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
 
 	alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data;
 
-#ifdef OCFS2_DEBUG_FS
+#ifdef CONFIG_OCFS2_DEBUG_FS
 	if (le32_to_cpu(alloc->id1.bitmap1.i_used) !=
 	    ocfs2_local_alloc_count_bits(alloc)) {
 		ocfs2_error(osb->sb, "local alloc inode %llu says it has "
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 {
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 52c426665154..3f1945177629 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -901,7 +901,7 @@ static inline int ocfs2_sprintf_system_inode_name(char *buf, int len,
          * list has a copy per slot.
          */
 	if (type <= OCFS2_LAST_GLOBAL_SYSTEM_INODE)
-		chars = snprintf(buf, len,
+		chars = snprintf(buf, len, "%s",
 				 ocfs2_system_inodes[type].si_name);
 	else
 		chars = snprintf(buf, len,
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index bd7e0f3acfc7..353fc35c6748 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -550,26 +550,17 @@ 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)
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. */