From 827463c49f29111efd22148d24c9ca44d648acfa Mon Sep 17 00:00:00 2001
From: Miao Xie <miaox@cn.fujitsu.com>
Date: Tue, 14 Jan 2014 20:31:51 +0800
Subject: Btrfs: don't mix the ordered extents of all files together during
 logging the inodes

There was a problem in the old code:
If we failed to log the csum, we would free all the ordered extents in the log list
including those ordered extents that were logged successfully, it would make the
log committer not to wait for the completion of the ordered extents.

This patch doesn't insert the ordered extents that is about to be logged into
a global list, instead, we insert them into a local list. If we log the ordered
extents successfully, we splice them with the global list, or we will throw them
away, then do full sync. It can also reduce the lock contention and the traverse
time of list.

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
---
 fs/btrfs/ordered-data.c | 37 +++++++++++++++++++++++++++++--------
 1 file changed, 29 insertions(+), 8 deletions(-)

(limited to 'fs/btrfs/ordered-data.c')

diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index b16450b840e7..138a7d7e9c90 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -424,27 +424,48 @@ out:
 }
 
 /* Needs to either be called under a log transaction or the log_mutex */
-void btrfs_get_logged_extents(struct btrfs_root *log, struct inode *inode)
+void btrfs_get_logged_extents(struct inode *inode,
+			      struct list_head *logged_list)
 {
 	struct btrfs_ordered_inode_tree *tree;
 	struct btrfs_ordered_extent *ordered;
 	struct rb_node *n;
-	int index = log->log_transid % 2;
 
 	tree = &BTRFS_I(inode)->ordered_tree;
 	spin_lock_irq(&tree->lock);
 	for (n = rb_first(&tree->tree); n; n = rb_next(n)) {
 		ordered = rb_entry(n, struct btrfs_ordered_extent, rb_node);
-		spin_lock(&log->log_extents_lock[index]);
-		if (list_empty(&ordered->log_list)) {
-			list_add_tail(&ordered->log_list, &log->logged_list[index]);
-			atomic_inc(&ordered->refs);
-		}
-		spin_unlock(&log->log_extents_lock[index]);
+		if (!list_empty(&ordered->log_list))
+			continue;
+		list_add_tail(&ordered->log_list, logged_list);
+		atomic_inc(&ordered->refs);
 	}
 	spin_unlock_irq(&tree->lock);
 }
 
+void btrfs_put_logged_extents(struct list_head *logged_list)
+{
+	struct btrfs_ordered_extent *ordered;
+
+	while (!list_empty(logged_list)) {
+		ordered = list_first_entry(logged_list,
+					   struct btrfs_ordered_extent,
+					   log_list);
+		list_del_init(&ordered->log_list);
+		btrfs_put_ordered_extent(ordered);
+	}
+}
+
+void btrfs_submit_logged_extents(struct list_head *logged_list,
+				 struct btrfs_root *log)
+{
+	int index = log->log_transid % 2;
+
+	spin_lock_irq(&log->log_extents_lock[index]);
+	list_splice_tail(logged_list, &log->logged_list[index]);
+	spin_unlock_irq(&log->log_extents_lock[index]);
+}
+
 void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid)
 {
 	struct btrfs_ordered_extent *ordered;
-- 
cgit v1.2.3


From a44903abe9dc23ffa305898368a7a910dbae13c5 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <quwenruo@cn.fujitsu.com>
Date: Fri, 28 Feb 2014 10:46:09 +0800
Subject: btrfs: Replace fs_info->flush_workers with btrfs_workqueue.

Replace the fs_info->submit_workers with the newly created
btrfs_workqueue.

Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Tested-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Josef Bacik <jbacik@fb.com>
---
 fs/btrfs/ctree.h        |  4 ++--
 fs/btrfs/disk-io.c      | 10 ++++------
 fs/btrfs/inode.c        |  8 ++++----
 fs/btrfs/ordered-data.c | 13 +++++++------
 fs/btrfs/ordered-data.h |  2 +-
 5 files changed, 18 insertions(+), 19 deletions(-)

(limited to 'fs/btrfs/ordered-data.c')

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index abed94213e6a..c31a102d34de 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1507,7 +1507,7 @@ struct btrfs_fs_info {
 	struct btrfs_workers generic_worker;
 	struct btrfs_workqueue_struct *workers;
 	struct btrfs_workqueue_struct *delalloc_workers;
-	struct btrfs_workers flush_workers;
+	struct btrfs_workqueue_struct *flush_workers;
 	struct btrfs_workers endio_workers;
 	struct btrfs_workers endio_meta_workers;
 	struct btrfs_workers endio_raid56_workers;
@@ -3681,7 +3681,7 @@ struct btrfs_delalloc_work {
 	int delay_iput;
 	struct completion completion;
 	struct list_head list;
-	struct btrfs_work work;
+	struct btrfs_work_struct work;
 };
 
 struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 420328bacf49..5b82b0b31ec8 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2010,7 +2010,7 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 	btrfs_stop_workers(&fs_info->delayed_workers);
 	btrfs_stop_workers(&fs_info->caching_workers);
 	btrfs_stop_workers(&fs_info->readahead_workers);
-	btrfs_stop_workers(&fs_info->flush_workers);
+	btrfs_destroy_workqueue(fs_info->flush_workers);
 	btrfs_stop_workers(&fs_info->qgroup_rescan_workers);
 }
 
@@ -2483,9 +2483,8 @@ int open_ctree(struct super_block *sb,
 	fs_info->delalloc_workers =
 		btrfs_alloc_workqueue("delalloc", flags, max_active, 2);
 
-	btrfs_init_workers(&fs_info->flush_workers, "flush_delalloc",
-			   fs_info->thread_pool_size, NULL);
-
+	fs_info->flush_workers =
+		btrfs_alloc_workqueue("flush_delalloc", flags, max_active, 0);
 
 	btrfs_init_workers(&fs_info->caching_workers, "cache",
 			   fs_info->thread_pool_size, NULL);
@@ -2560,14 +2559,13 @@ int open_ctree(struct super_block *sb,
 	ret |= btrfs_start_workers(&fs_info->delayed_workers);
 	ret |= btrfs_start_workers(&fs_info->caching_workers);
 	ret |= btrfs_start_workers(&fs_info->readahead_workers);
-	ret |= btrfs_start_workers(&fs_info->flush_workers);
 	ret |= btrfs_start_workers(&fs_info->qgroup_rescan_workers);
 	if (ret) {
 		err = -ENOMEM;
 		goto fail_sb_buffer;
 	}
 	if (!(fs_info->workers && fs_info->delalloc_workers &&
-	      fs_info->submit_workers)) {
+	      fs_info->submit_workers && fs_info->flush_workers)) {
 		err = -ENOMEM;
 		goto fail_sb_buffer;
 	}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a41a5a7aa3cb..6c043bed0c32 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8386,7 +8386,7 @@ out_notrans:
 	return ret;
 }
 
-static void btrfs_run_delalloc_work(struct btrfs_work *work)
+static void btrfs_run_delalloc_work(struct btrfs_work_struct *work)
 {
 	struct btrfs_delalloc_work *delalloc_work;
 	struct inode *inode;
@@ -8424,7 +8424,7 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
 	work->inode = inode;
 	work->wait = wait;
 	work->delay_iput = delay_iput;
-	work->work.func = btrfs_run_delalloc_work;
+	btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL);
 
 	return work;
 }
@@ -8476,8 +8476,8 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
 			goto out;
 		}
 		list_add_tail(&work->list, &works);
-		btrfs_queue_worker(&root->fs_info->flush_workers,
-				   &work->work);
+		btrfs_queue_work(root->fs_info->flush_workers,
+				 &work->work);
 
 		cond_resched();
 		spin_lock(&root->delalloc_lock);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 138a7d7e9c90..6fa8219b5d03 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -576,7 +576,7 @@ void btrfs_remove_ordered_extent(struct inode *inode,
 	wake_up(&entry->wait);
 }
 
-static void btrfs_run_ordered_extent_work(struct btrfs_work *work)
+static void btrfs_run_ordered_extent_work(struct btrfs_work_struct *work)
 {
 	struct btrfs_ordered_extent *ordered;
 
@@ -609,10 +609,11 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
 		atomic_inc(&ordered->refs);
 		spin_unlock(&root->ordered_extent_lock);
 
-		ordered->flush_work.func = btrfs_run_ordered_extent_work;
+		btrfs_init_work(&ordered->flush_work,
+				btrfs_run_ordered_extent_work, NULL, NULL);
 		list_add_tail(&ordered->work_list, &works);
-		btrfs_queue_worker(&root->fs_info->flush_workers,
-				   &ordered->flush_work);
+		btrfs_queue_work(root->fs_info->flush_workers,
+				 &ordered->flush_work);
 
 		cond_resched();
 		spin_lock(&root->ordered_extent_lock);
@@ -725,8 +726,8 @@ int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 		list_add_tail(&work->list, &works);
-		btrfs_queue_worker(&root->fs_info->flush_workers,
-				   &work->work);
+		btrfs_queue_work(root->fs_info->flush_workers,
+				 &work->work);
 
 		cond_resched();
 		spin_lock(&root->fs_info->ordered_root_lock);
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 246897058efb..fe9f4dbab09c 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -133,7 +133,7 @@ struct btrfs_ordered_extent {
 	struct btrfs_work work;
 
 	struct completion completion;
-	struct btrfs_work flush_work;
+	struct btrfs_work_struct flush_work;
 	struct list_head work_list;
 };
 
-- 
cgit v1.2.3


From d458b0540ebd728b4d6ef47cc5ef0dbfd4dd361a Mon Sep 17 00:00:00 2001
From: Qu Wenruo <quwenruo@cn.fujitsu.com>
Date: Fri, 28 Feb 2014 10:46:19 +0800
Subject: btrfs: Cleanup the "_struct" suffix in btrfs_workequeue

Since the "_struct" suffix is mainly used for distinguish the differnt
btrfs_work between the original and the newly created one,
there is no need using the suffix since all btrfs_workers are changed
into btrfs_workqueue.

Also this patch fixed some codes whose code style is changed due to the
too long "_struct" suffix.

Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Tested-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Josef Bacik <jbacik@fb.com>
---
 fs/btrfs/async-thread.c  | 66 ++++++++++++++++++++++++------------------------
 fs/btrfs/async-thread.h  | 34 ++++++++++++-------------
 fs/btrfs/ctree.h         | 44 ++++++++++++++++----------------
 fs/btrfs/delayed-inode.c |  4 +--
 fs/btrfs/disk-io.c       | 14 +++++-----
 fs/btrfs/extent-tree.c   |  2 +-
 fs/btrfs/inode.c         | 18 ++++++-------
 fs/btrfs/ordered-data.c  |  2 +-
 fs/btrfs/ordered-data.h  |  4 +--
 fs/btrfs/qgroup.c        |  2 +-
 fs/btrfs/raid56.c        | 14 +++++-----
 fs/btrfs/reada.c         |  5 ++--
 fs/btrfs/scrub.c         | 23 ++++++++---------
 fs/btrfs/volumes.c       |  2 +-
 fs/btrfs/volumes.h       |  2 +-
 15 files changed, 116 insertions(+), 120 deletions(-)

(limited to 'fs/btrfs/ordered-data.c')

diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 2a5f383c3636..a709585e2c97 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -32,7 +32,7 @@
 #define NO_THRESHOLD (-1)
 #define DFT_THRESHOLD (32)
 
-struct __btrfs_workqueue_struct {
+struct __btrfs_workqueue {
 	struct workqueue_struct *normal_wq;
 	/* List head pointing to ordered work list */
 	struct list_head ordered_list;
@@ -49,15 +49,15 @@ struct __btrfs_workqueue_struct {
 	spinlock_t thres_lock;
 };
 
-struct btrfs_workqueue_struct {
-	struct __btrfs_workqueue_struct *normal;
-	struct __btrfs_workqueue_struct *high;
+struct btrfs_workqueue {
+	struct __btrfs_workqueue *normal;
+	struct __btrfs_workqueue *high;
 };
 
-static inline struct __btrfs_workqueue_struct
+static inline struct __btrfs_workqueue
 *__btrfs_alloc_workqueue(char *name, int flags, int max_active, int thresh)
 {
-	struct __btrfs_workqueue_struct *ret = kzalloc(sizeof(*ret), GFP_NOFS);
+	struct __btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_NOFS);
 
 	if (unlikely(!ret))
 		return NULL;
@@ -95,14 +95,14 @@ static inline struct __btrfs_workqueue_struct
 }
 
 static inline void
-__btrfs_destroy_workqueue(struct __btrfs_workqueue_struct *wq);
+__btrfs_destroy_workqueue(struct __btrfs_workqueue *wq);
 
-struct btrfs_workqueue_struct *btrfs_alloc_workqueue(char *name,
-						     int flags,
-						     int max_active,
-						     int thresh)
+struct btrfs_workqueue *btrfs_alloc_workqueue(char *name,
+					      int flags,
+					      int max_active,
+					      int thresh)
 {
-	struct btrfs_workqueue_struct *ret = kzalloc(sizeof(*ret), GFP_NOFS);
+	struct btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_NOFS);
 
 	if (unlikely(!ret))
 		return NULL;
@@ -131,7 +131,7 @@ struct btrfs_workqueue_struct *btrfs_alloc_workqueue(char *name,
  * This hook WILL be called in IRQ handler context,
  * so workqueue_set_max_active MUST NOT be called in this hook
  */
-static inline void thresh_queue_hook(struct __btrfs_workqueue_struct *wq)
+static inline void thresh_queue_hook(struct __btrfs_workqueue *wq)
 {
 	if (wq->thresh == NO_THRESHOLD)
 		return;
@@ -143,7 +143,7 @@ static inline void thresh_queue_hook(struct __btrfs_workqueue_struct *wq)
  * This hook is called in kthread content.
  * So workqueue_set_max_active is called here.
  */
-static inline void thresh_exec_hook(struct __btrfs_workqueue_struct *wq)
+static inline void thresh_exec_hook(struct __btrfs_workqueue *wq)
 {
 	int new_max_active;
 	long pending;
@@ -186,10 +186,10 @@ out:
 	}
 }
 
-static void run_ordered_work(struct __btrfs_workqueue_struct *wq)
+static void run_ordered_work(struct __btrfs_workqueue *wq)
 {
 	struct list_head *list = &wq->ordered_list;
-	struct btrfs_work_struct *work;
+	struct btrfs_work *work;
 	spinlock_t *lock = &wq->list_lock;
 	unsigned long flags;
 
@@ -197,7 +197,7 @@ static void run_ordered_work(struct __btrfs_workqueue_struct *wq)
 		spin_lock_irqsave(lock, flags);
 		if (list_empty(list))
 			break;
-		work = list_entry(list->next, struct btrfs_work_struct,
+		work = list_entry(list->next, struct btrfs_work,
 				  ordered_list);
 		if (!test_bit(WORK_DONE_BIT, &work->flags))
 			break;
@@ -229,11 +229,11 @@ static void run_ordered_work(struct __btrfs_workqueue_struct *wq)
 
 static void normal_work_helper(struct work_struct *arg)
 {
-	struct btrfs_work_struct *work;
-	struct __btrfs_workqueue_struct *wq;
+	struct btrfs_work *work;
+	struct __btrfs_workqueue *wq;
 	int need_order = 0;
 
-	work = container_of(arg, struct btrfs_work_struct, normal_work);
+	work = container_of(arg, struct btrfs_work, normal_work);
 	/*
 	 * We should not touch things inside work in the following cases:
 	 * 1) after work->func() if it has no ordered_free
@@ -254,10 +254,10 @@ static void normal_work_helper(struct work_struct *arg)
 	}
 }
 
-void btrfs_init_work(struct btrfs_work_struct *work,
-		     void (*func)(struct btrfs_work_struct *),
-		     void (*ordered_func)(struct btrfs_work_struct *),
-		     void (*ordered_free)(struct btrfs_work_struct *))
+void btrfs_init_work(struct btrfs_work *work,
+		     void (*func)(struct btrfs_work *),
+		     void (*ordered_func)(struct btrfs_work *),
+		     void (*ordered_free)(struct btrfs_work *))
 {
 	work->func = func;
 	work->ordered_func = ordered_func;
@@ -267,8 +267,8 @@ void btrfs_init_work(struct btrfs_work_struct *work,
 	work->flags = 0;
 }
 
-static inline void __btrfs_queue_work(struct __btrfs_workqueue_struct *wq,
-				      struct btrfs_work_struct *work)
+static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq,
+				      struct btrfs_work *work)
 {
 	unsigned long flags;
 
@@ -282,10 +282,10 @@ static inline void __btrfs_queue_work(struct __btrfs_workqueue_struct *wq,
 	queue_work(wq->normal_wq, &work->normal_work);
 }
 
-void btrfs_queue_work(struct btrfs_workqueue_struct *wq,
-		      struct btrfs_work_struct *work)
+void btrfs_queue_work(struct btrfs_workqueue *wq,
+		      struct btrfs_work *work)
 {
-	struct __btrfs_workqueue_struct *dest_wq;
+	struct __btrfs_workqueue *dest_wq;
 
 	if (test_bit(WORK_HIGH_PRIO_BIT, &work->flags) && wq->high)
 		dest_wq = wq->high;
@@ -295,13 +295,13 @@ void btrfs_queue_work(struct btrfs_workqueue_struct *wq,
 }
 
 static inline void
-__btrfs_destroy_workqueue(struct __btrfs_workqueue_struct *wq)
+__btrfs_destroy_workqueue(struct __btrfs_workqueue *wq)
 {
 	destroy_workqueue(wq->normal_wq);
 	kfree(wq);
 }
 
-void btrfs_destroy_workqueue(struct btrfs_workqueue_struct *wq)
+void btrfs_destroy_workqueue(struct btrfs_workqueue *wq)
 {
 	if (!wq)
 		return;
@@ -310,14 +310,14 @@ void btrfs_destroy_workqueue(struct btrfs_workqueue_struct *wq)
 	__btrfs_destroy_workqueue(wq->normal);
 }
 
-void btrfs_workqueue_set_max(struct btrfs_workqueue_struct *wq, int max)
+void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max)
 {
 	wq->normal->max_active = max;
 	if (wq->high)
 		wq->high->max_active = max;
 }
 
-void btrfs_set_work_high_priority(struct btrfs_work_struct *work)
+void btrfs_set_work_high_priority(struct btrfs_work *work)
 {
 	set_bit(WORK_HIGH_PRIO_BIT, &work->flags);
 }
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index ab05904f791c..08d717476227 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -20,33 +20,33 @@
 #ifndef __BTRFS_ASYNC_THREAD_
 #define __BTRFS_ASYNC_THREAD_
 
-struct btrfs_workqueue_struct;
+struct btrfs_workqueue;
 /* Internal use only */
-struct __btrfs_workqueue_struct;
+struct __btrfs_workqueue;
 
-struct btrfs_work_struct {
-	void (*func)(struct btrfs_work_struct *arg);
-	void (*ordered_func)(struct btrfs_work_struct *arg);
-	void (*ordered_free)(struct btrfs_work_struct *arg);
+struct btrfs_work {
+	void (*func)(struct btrfs_work *arg);
+	void (*ordered_func)(struct btrfs_work *arg);
+	void (*ordered_free)(struct btrfs_work *arg);
 
 	/* Don't touch things below */
 	struct work_struct normal_work;
 	struct list_head ordered_list;
-	struct __btrfs_workqueue_struct *wq;
+	struct __btrfs_workqueue *wq;
 	unsigned long flags;
 };
 
-struct btrfs_workqueue_struct *btrfs_alloc_workqueue(char *name,
+struct btrfs_workqueue *btrfs_alloc_workqueue(char *name,
 						     int flags,
 						     int max_active,
 						     int thresh);
-void btrfs_init_work(struct btrfs_work_struct *work,
-		     void (*func)(struct btrfs_work_struct *),
-		     void (*ordered_func)(struct btrfs_work_struct *),
-		     void (*ordered_free)(struct btrfs_work_struct *));
-void btrfs_queue_work(struct btrfs_workqueue_struct *wq,
-		      struct btrfs_work_struct *work);
-void btrfs_destroy_workqueue(struct btrfs_workqueue_struct *wq);
-void btrfs_workqueue_set_max(struct btrfs_workqueue_struct *wq, int max);
-void btrfs_set_work_high_priority(struct btrfs_work_struct *work);
+void btrfs_init_work(struct btrfs_work *work,
+		     void (*func)(struct btrfs_work *),
+		     void (*ordered_func)(struct btrfs_work *),
+		     void (*ordered_free)(struct btrfs_work *));
+void btrfs_queue_work(struct btrfs_workqueue *wq,
+		      struct btrfs_work *work);
+void btrfs_destroy_workqueue(struct btrfs_workqueue *wq);
+void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max);
+void btrfs_set_work_high_priority(struct btrfs_work *work);
 #endif
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 5a8c77a441ba..b4d2e957b89f 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1221,7 +1221,7 @@ struct btrfs_caching_control {
 	struct list_head list;
 	struct mutex mutex;
 	wait_queue_head_t wait;
-	struct btrfs_work_struct work;
+	struct btrfs_work work;
 	struct btrfs_block_group_cache *block_group;
 	u64 progress;
 	atomic_t count;
@@ -1504,27 +1504,27 @@ struct btrfs_fs_info {
 	 * A third pool does submit_bio to avoid deadlocking with the other
 	 * two
 	 */
-	struct btrfs_workqueue_struct *workers;
-	struct btrfs_workqueue_struct *delalloc_workers;
-	struct btrfs_workqueue_struct *flush_workers;
-	struct btrfs_workqueue_struct *endio_workers;
-	struct btrfs_workqueue_struct *endio_meta_workers;
-	struct btrfs_workqueue_struct *endio_raid56_workers;
-	struct btrfs_workqueue_struct *rmw_workers;
-	struct btrfs_workqueue_struct *endio_meta_write_workers;
-	struct btrfs_workqueue_struct *endio_write_workers;
-	struct btrfs_workqueue_struct *endio_freespace_worker;
-	struct btrfs_workqueue_struct *submit_workers;
-	struct btrfs_workqueue_struct *caching_workers;
-	struct btrfs_workqueue_struct *readahead_workers;
+	struct btrfs_workqueue *workers;
+	struct btrfs_workqueue *delalloc_workers;
+	struct btrfs_workqueue *flush_workers;
+	struct btrfs_workqueue *endio_workers;
+	struct btrfs_workqueue *endio_meta_workers;
+	struct btrfs_workqueue *endio_raid56_workers;
+	struct btrfs_workqueue *rmw_workers;
+	struct btrfs_workqueue *endio_meta_write_workers;
+	struct btrfs_workqueue *endio_write_workers;
+	struct btrfs_workqueue *endio_freespace_worker;
+	struct btrfs_workqueue *submit_workers;
+	struct btrfs_workqueue *caching_workers;
+	struct btrfs_workqueue *readahead_workers;
 
 	/*
 	 * fixup workers take dirty pages that didn't properly go through
 	 * the cow mechanism and make them safe to write.  It happens
 	 * for the sys_munmap function call path
 	 */
-	struct btrfs_workqueue_struct *fixup_workers;
-	struct btrfs_workqueue_struct *delayed_workers;
+	struct btrfs_workqueue *fixup_workers;
+	struct btrfs_workqueue *delayed_workers;
 	struct task_struct *transaction_kthread;
 	struct task_struct *cleaner_kthread;
 	int thread_pool_size;
@@ -1604,9 +1604,9 @@ struct btrfs_fs_info {
 	atomic_t scrub_cancel_req;
 	wait_queue_head_t scrub_pause_wait;
 	int scrub_workers_refcnt;
-	struct btrfs_workqueue_struct *scrub_workers;
-	struct btrfs_workqueue_struct *scrub_wr_completion_workers;
-	struct btrfs_workqueue_struct *scrub_nocow_workers;
+	struct btrfs_workqueue *scrub_workers;
+	struct btrfs_workqueue *scrub_wr_completion_workers;
+	struct btrfs_workqueue *scrub_nocow_workers;
 
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
 	u32 check_integrity_print_mask;
@@ -1647,9 +1647,9 @@ struct btrfs_fs_info {
 	/* qgroup rescan items */
 	struct mutex qgroup_rescan_lock; /* protects the progress item */
 	struct btrfs_key qgroup_rescan_progress;
-	struct btrfs_workqueue_struct *qgroup_rescan_workers;
+	struct btrfs_workqueue *qgroup_rescan_workers;
 	struct completion qgroup_rescan_completion;
-	struct btrfs_work_struct qgroup_rescan_work;
+	struct btrfs_work qgroup_rescan_work;
 
 	/* filesystem state */
 	unsigned long fs_state;
@@ -3680,7 +3680,7 @@ struct btrfs_delalloc_work {
 	int delay_iput;
 	struct completion completion;
 	struct list_head list;
-	struct btrfs_work_struct work;
+	struct btrfs_work work;
 };
 
 struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 76e85d66801f..33e561a84013 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1318,10 +1318,10 @@ void btrfs_remove_delayed_node(struct inode *inode)
 struct btrfs_async_delayed_work {
 	struct btrfs_delayed_root *delayed_root;
 	int nr;
-	struct btrfs_work_struct work;
+	struct btrfs_work work;
 };
 
-static void btrfs_async_run_delayed_root(struct btrfs_work_struct *work)
+static void btrfs_async_run_delayed_root(struct btrfs_work *work)
 {
 	struct btrfs_async_delayed_work *async_work;
 	struct btrfs_delayed_root *delayed_root;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index c80d9507171c..f7d84d955764 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -55,7 +55,7 @@
 #endif
 
 static struct extent_io_ops btree_extent_io_ops;
-static void end_workqueue_fn(struct btrfs_work_struct *work);
+static void end_workqueue_fn(struct btrfs_work *work);
 static void free_fs_root(struct btrfs_root *root);
 static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 				    int read_only);
@@ -86,7 +86,7 @@ struct end_io_wq {
 	int error;
 	int metadata;
 	struct list_head list;
-	struct btrfs_work_struct work;
+	struct btrfs_work work;
 };
 
 /*
@@ -108,7 +108,7 @@ struct async_submit_bio {
 	 * can't tell us where in the file the bio should go
 	 */
 	u64 bio_offset;
-	struct btrfs_work_struct work;
+	struct btrfs_work work;
 	int error;
 };
 
@@ -742,7 +742,7 @@ unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info)
 	return 256 * limit;
 }
 
-static void run_one_async_start(struct btrfs_work_struct *work)
+static void run_one_async_start(struct btrfs_work *work)
 {
 	struct async_submit_bio *async;
 	int ret;
@@ -755,7 +755,7 @@ static void run_one_async_start(struct btrfs_work_struct *work)
 		async->error = ret;
 }
 
-static void run_one_async_done(struct btrfs_work_struct *work)
+static void run_one_async_done(struct btrfs_work *work)
 {
 	struct btrfs_fs_info *fs_info;
 	struct async_submit_bio *async;
@@ -782,7 +782,7 @@ static void run_one_async_done(struct btrfs_work_struct *work)
 			       async->bio_offset);
 }
 
-static void run_one_async_free(struct btrfs_work_struct *work)
+static void run_one_async_free(struct btrfs_work *work)
 {
 	struct async_submit_bio *async;
 
@@ -1668,7 +1668,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
  * called by the kthread helper functions to finally call the bio end_io
  * functions.  This is where read checksum verification actually happens
  */
-static void end_workqueue_fn(struct btrfs_work_struct *work)
+static void end_workqueue_fn(struct btrfs_work *work)
 {
 	struct bio *bio;
 	struct end_io_wq *end_io_wq;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index bb58082f6d61..19ea8ad70c67 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -378,7 +378,7 @@ static u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
 	return total_added;
 }
 
-static noinline void caching_thread(struct btrfs_work_struct *work)
+static noinline void caching_thread(struct btrfs_work *work)
 {
 	struct btrfs_block_group_cache *block_group;
 	struct btrfs_fs_info *fs_info;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0885f333574d..53697a80b849 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -324,7 +324,7 @@ struct async_cow {
 	u64 start;
 	u64 end;
 	struct list_head extents;
-	struct btrfs_work_struct work;
+	struct btrfs_work work;
 };
 
 static noinline int add_async_extent(struct async_cow *cow,
@@ -1000,7 +1000,7 @@ out_unlock:
 /*
  * work queue call back to started compression on a file and pages
  */
-static noinline void async_cow_start(struct btrfs_work_struct *work)
+static noinline void async_cow_start(struct btrfs_work *work)
 {
 	struct async_cow *async_cow;
 	int num_added = 0;
@@ -1018,7 +1018,7 @@ static noinline void async_cow_start(struct btrfs_work_struct *work)
 /*
  * work queue call back to submit previously compressed pages
  */
-static noinline void async_cow_submit(struct btrfs_work_struct *work)
+static noinline void async_cow_submit(struct btrfs_work *work)
 {
 	struct async_cow *async_cow;
 	struct btrfs_root *root;
@@ -1039,7 +1039,7 @@ static noinline void async_cow_submit(struct btrfs_work_struct *work)
 		submit_compressed_extents(async_cow->inode, async_cow);
 }
 
-static noinline void async_cow_free(struct btrfs_work_struct *work)
+static noinline void async_cow_free(struct btrfs_work *work)
 {
 	struct async_cow *async_cow;
 	async_cow = container_of(work, struct async_cow, work);
@@ -1748,10 +1748,10 @@ int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
 /* see btrfs_writepage_start_hook for details on why this is required */
 struct btrfs_writepage_fixup {
 	struct page *page;
-	struct btrfs_work_struct work;
+	struct btrfs_work work;
 };
 
-static void btrfs_writepage_fixup_worker(struct btrfs_work_struct *work)
+static void btrfs_writepage_fixup_worker(struct btrfs_work *work)
 {
 	struct btrfs_writepage_fixup *fixup;
 	struct btrfs_ordered_extent *ordered;
@@ -2750,7 +2750,7 @@ out:
 	return ret;
 }
 
-static void finish_ordered_fn(struct btrfs_work_struct *work)
+static void finish_ordered_fn(struct btrfs_work *work)
 {
 	struct btrfs_ordered_extent *ordered_extent;
 	ordered_extent = container_of(work, struct btrfs_ordered_extent, work);
@@ -2763,7 +2763,7 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
 	struct inode *inode = page->mapping->host;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_ordered_extent *ordered_extent = NULL;
-	struct btrfs_workqueue_struct *workers;
+	struct btrfs_workqueue *workers;
 
 	trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
 
@@ -8384,7 +8384,7 @@ out_notrans:
 	return ret;
 }
 
-static void btrfs_run_delalloc_work(struct btrfs_work_struct *work)
+static void btrfs_run_delalloc_work(struct btrfs_work *work)
 {
 	struct btrfs_delalloc_work *delalloc_work;
 	struct inode *inode;
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 6fa8219b5d03..751ee38083a9 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -576,7 +576,7 @@ void btrfs_remove_ordered_extent(struct inode *inode,
 	wake_up(&entry->wait);
 }
 
-static void btrfs_run_ordered_extent_work(struct btrfs_work_struct *work)
+static void btrfs_run_ordered_extent_work(struct btrfs_work *work)
 {
 	struct btrfs_ordered_extent *ordered;
 
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 84bb236119fe..246897058efb 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -130,10 +130,10 @@ struct btrfs_ordered_extent {
 	/* a per root list of all the pending ordered extents */
 	struct list_head root_extent_list;
 
-	struct btrfs_work_struct work;
+	struct btrfs_work work;
 
 	struct completion completion;
-	struct btrfs_work_struct flush_work;
+	struct btrfs_work flush_work;
 	struct list_head work_list;
 };
 
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 38617cc2fdd5..2cf905877aaf 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1984,7 +1984,7 @@ out:
 	return ret;
 }
 
-static void btrfs_qgroup_rescan_worker(struct btrfs_work_struct *work)
+static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 {
 	struct btrfs_fs_info *fs_info = container_of(work, struct btrfs_fs_info,
 						     qgroup_rescan_work);
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 5afa564201a2..1269fc30b15c 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -87,7 +87,7 @@ struct btrfs_raid_bio {
 	/*
 	 * for scheduling work in the helper threads
 	 */
-	struct btrfs_work_struct work;
+	struct btrfs_work work;
 
 	/*
 	 * bio list and bio_list_lock are used
@@ -166,8 +166,8 @@ struct btrfs_raid_bio {
 
 static int __raid56_parity_recover(struct btrfs_raid_bio *rbio);
 static noinline void finish_rmw(struct btrfs_raid_bio *rbio);
-static void rmw_work(struct btrfs_work_struct *work);
-static void read_rebuild_work(struct btrfs_work_struct *work);
+static void rmw_work(struct btrfs_work *work);
+static void read_rebuild_work(struct btrfs_work *work);
 static void async_rmw_stripe(struct btrfs_raid_bio *rbio);
 static void async_read_rebuild(struct btrfs_raid_bio *rbio);
 static int fail_bio_stripe(struct btrfs_raid_bio *rbio, struct bio *bio);
@@ -1588,7 +1588,7 @@ struct btrfs_plug_cb {
 	struct blk_plug_cb cb;
 	struct btrfs_fs_info *info;
 	struct list_head rbio_list;
-	struct btrfs_work_struct work;
+	struct btrfs_work work;
 };
 
 /*
@@ -1652,7 +1652,7 @@ static void run_plug(struct btrfs_plug_cb *plug)
  * if the unplug comes from schedule, we have to push the
  * work off to a helper thread
  */
-static void unplug_work(struct btrfs_work_struct *work)
+static void unplug_work(struct btrfs_work *work)
 {
 	struct btrfs_plug_cb *plug;
 	plug = container_of(work, struct btrfs_plug_cb, work);
@@ -2079,7 +2079,7 @@ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio,
 
 }
 
-static void rmw_work(struct btrfs_work_struct *work)
+static void rmw_work(struct btrfs_work *work)
 {
 	struct btrfs_raid_bio *rbio;
 
@@ -2087,7 +2087,7 @@ static void rmw_work(struct btrfs_work_struct *work)
 	raid56_rmw_stripe(rbio);
 }
 
-static void read_rebuild_work(struct btrfs_work_struct *work)
+static void read_rebuild_work(struct btrfs_work *work)
 {
 	struct btrfs_raid_bio *rbio;
 
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 9e01d3677355..30947f923620 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -91,8 +91,7 @@ struct reada_zone {
 };
 
 struct reada_machine_work {
-	struct btrfs_work_struct
-				work;
+	struct btrfs_work	work;
 	struct btrfs_fs_info	*fs_info;
 };
 
@@ -734,7 +733,7 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 
 }
 
-static void reada_start_machine_worker(struct btrfs_work_struct *work)
+static void reada_start_machine_worker(struct btrfs_work *work)
 {
 	struct reada_machine_work *rmw;
 	struct btrfs_fs_info *fs_info;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 5a240f5e6ceb..db21a1360e13 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -96,8 +96,7 @@ struct scrub_bio {
 #endif
 	int			page_count;
 	int			next_free;
-	struct btrfs_work_struct
-				work;
+	struct btrfs_work	work;
 };
 
 struct scrub_block {
@@ -155,8 +154,7 @@ struct scrub_fixup_nodatasum {
 	struct btrfs_device	*dev;
 	u64			logical;
 	struct btrfs_root	*root;
-	struct btrfs_work_struct
-				work;
+	struct btrfs_work	work;
 	int			mirror_num;
 };
 
@@ -174,8 +172,7 @@ struct scrub_copy_nocow_ctx {
 	int			mirror_num;
 	u64			physical_for_dev_replace;
 	struct list_head	inodes;
-	struct btrfs_work_struct
-				work;
+	struct btrfs_work	work;
 };
 
 struct scrub_warning {
@@ -234,7 +231,7 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
 		       u64 gen, int mirror_num, u8 *csum, int force,
 		       u64 physical_for_dev_replace);
 static void scrub_bio_end_io(struct bio *bio, int err);
-static void scrub_bio_end_io_worker(struct btrfs_work_struct *work);
+static void scrub_bio_end_io_worker(struct btrfs_work *work);
 static void scrub_block_complete(struct scrub_block *sblock);
 static void scrub_remap_extent(struct btrfs_fs_info *fs_info,
 			       u64 extent_logical, u64 extent_len,
@@ -251,14 +248,14 @@ static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx,
 				    struct scrub_page *spage);
 static void scrub_wr_submit(struct scrub_ctx *sctx);
 static void scrub_wr_bio_end_io(struct bio *bio, int err);
-static void scrub_wr_bio_end_io_worker(struct btrfs_work_struct *work);
+static void scrub_wr_bio_end_io_worker(struct btrfs_work *work);
 static int write_page_nocow(struct scrub_ctx *sctx,
 			    u64 physical_for_dev_replace, struct page *page);
 static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
 				      struct scrub_copy_nocow_ctx *ctx);
 static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
 			    int mirror_num, u64 physical_for_dev_replace);
-static void copy_nocow_pages_worker(struct btrfs_work_struct *work);
+static void copy_nocow_pages_worker(struct btrfs_work *work);
 static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
 static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
 
@@ -737,7 +734,7 @@ out:
 	return -EIO;
 }
 
-static void scrub_fixup_nodatasum(struct btrfs_work_struct *work)
+static void scrub_fixup_nodatasum(struct btrfs_work *work)
 {
 	int ret;
 	struct scrub_fixup_nodatasum *fixup;
@@ -1622,7 +1619,7 @@ static void scrub_wr_bio_end_io(struct bio *bio, int err)
 	btrfs_queue_work(fs_info->scrub_wr_completion_workers, &sbio->work);
 }
 
-static void scrub_wr_bio_end_io_worker(struct btrfs_work_struct *work)
+static void scrub_wr_bio_end_io_worker(struct btrfs_work *work)
 {
 	struct scrub_bio *sbio = container_of(work, struct scrub_bio, work);
 	struct scrub_ctx *sctx = sbio->sctx;
@@ -2090,7 +2087,7 @@ static void scrub_bio_end_io(struct bio *bio, int err)
 	btrfs_queue_work(fs_info->scrub_workers, &sbio->work);
 }
 
-static void scrub_bio_end_io_worker(struct btrfs_work_struct *work)
+static void scrub_bio_end_io_worker(struct btrfs_work *work)
 {
 	struct scrub_bio *sbio = container_of(work, struct scrub_bio, work);
 	struct scrub_ctx *sctx = sbio->sctx;
@@ -3161,7 +3158,7 @@ static int record_inode_for_nocow(u64 inum, u64 offset, u64 root, void *ctx)
 
 #define COPY_COMPLETE 1
 
-static void copy_nocow_pages_worker(struct btrfs_work_struct *work)
+static void copy_nocow_pages_worker(struct btrfs_work *work)
 {
 	struct scrub_copy_nocow_ctx *nocow_ctx =
 		container_of(work, struct scrub_copy_nocow_ctx, work);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 0066cff077ce..b4660c413c73 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -440,7 +440,7 @@ done:
 	blk_finish_plug(&plug);
 }
 
-static void pending_bios_fn(struct btrfs_work_struct *work)
+static void pending_bios_fn(struct btrfs_work *work)
 {
 	struct btrfs_device *device;
 
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 5d9a03773ca6..80754f9dd3df 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -95,7 +95,7 @@ struct btrfs_device {
 	/* per-device scrub information */
 	struct scrub_ctx *scrub_device;
 
-	struct btrfs_work_struct work;
+	struct btrfs_work work;
 	struct rcu_head rcu;
 	struct work_struct rcu_work;
 
-- 
cgit v1.2.3


From 8b9d83cd6bebe10e9965d2cef8053b02663eaad8 Mon Sep 17 00:00:00 2001
From: Miao Xie <miaox@cn.fujitsu.com>
Date: Thu, 6 Mar 2014 13:54:55 +0800
Subject: Btrfs: fix early enospc due to the race of the two ordered extent
 wait

btrfs_wait_ordered_roots() moves all the list entries to a new list,
and then deals with them one by one. But if the other task invokes this
function at that time, it would get a empty list. It makes the enospc
error happens more early. Fix it.

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
---
 fs/btrfs/ordered-data.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

(limited to 'fs/btrfs/ordered-data.c')

diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 751ee38083a9..73de19c37f5a 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -589,7 +589,7 @@ static void btrfs_run_ordered_extent_work(struct btrfs_work *work)
  * wait for all the ordered extents in a root.  This is done when balancing
  * space between drives.
  */
-int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
+static int __btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
 {
 	struct list_head splice, works;
 	struct btrfs_ordered_extent *ordered, *next;
@@ -598,7 +598,6 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
 	INIT_LIST_HEAD(&splice);
 	INIT_LIST_HEAD(&works);
 
-	mutex_lock(&root->fs_info->ordered_operations_mutex);
 	spin_lock(&root->ordered_extent_lock);
 	list_splice_init(&root->ordered_extents, &splice);
 	while (!list_empty(&splice) && nr) {
@@ -630,6 +629,16 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
 		btrfs_put_ordered_extent(ordered);
 		cond_resched();
 	}
+
+	return count;
+}
+
+int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
+{
+	int count;
+
+	mutex_lock(&root->fs_info->ordered_operations_mutex);
+	count = __btrfs_wait_ordered_extents(root, nr);
 	mutex_unlock(&root->fs_info->ordered_operations_mutex);
 
 	return count;
@@ -643,6 +652,7 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
 
 	INIT_LIST_HEAD(&splice);
 
+	mutex_lock(&fs_info->ordered_operations_mutex);
 	spin_lock(&fs_info->ordered_root_lock);
 	list_splice_init(&fs_info->ordered_roots, &splice);
 	while (!list_empty(&splice) && nr) {
@@ -654,7 +664,7 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
 			       &fs_info->ordered_roots);
 		spin_unlock(&fs_info->ordered_root_lock);
 
-		done = btrfs_wait_ordered_extents(root, nr);
+		done = __btrfs_wait_ordered_extents(root, nr);
 		btrfs_put_fs_root(root);
 
 		spin_lock(&fs_info->ordered_root_lock);
@@ -665,6 +675,7 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
 	}
 	list_splice_tail(&splice, &fs_info->ordered_roots);
 	spin_unlock(&fs_info->ordered_root_lock);
+	mutex_unlock(&fs_info->ordered_operations_mutex);
 }
 
 /*
-- 
cgit v1.2.3


From af7a65097b3f0a63caf1755df78d04e1a33588ef Mon Sep 17 00:00:00 2001
From: Miao Xie <miaox@cn.fujitsu.com>
Date: Thu, 6 Mar 2014 13:54:56 +0800
Subject: Btrfs: wake up the tasks that wait for the io earlier

The tasks that wait for the IO_DONE flag just care about the io of the dirty
pages, so it is better to wake up them immediately after all the pages are
written, not the whole process of the io completes.

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
---
 fs/btrfs/ordered-data.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

(limited to 'fs/btrfs/ordered-data.c')

diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 73de19c37f5a..a75eaa286b8a 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -349,10 +349,13 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode,
 	if (!uptodate)
 		set_bit(BTRFS_ORDERED_IOERR, &entry->flags);
 
-	if (entry->bytes_left == 0)
+	if (entry->bytes_left == 0) {
 		ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);
-	else
+		if (waitqueue_active(&entry->wait))
+			wake_up(&entry->wait);
+	} else {
 		ret = 1;
+	}
 out:
 	if (!ret && cached && entry) {
 		*cached = entry;
@@ -410,10 +413,13 @@ have_entry:
 	if (!uptodate)
 		set_bit(BTRFS_ORDERED_IOERR, &entry->flags);
 
-	if (entry->bytes_left == 0)
+	if (entry->bytes_left == 0) {
 		ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);
-	else
+		if (waitqueue_active(&entry->wait))
+			wake_up(&entry->wait);
+	} else {
 		ret = 1;
+	}
 out:
 	if (!ret && cached && entry) {
 		*cached = entry;
-- 
cgit v1.2.3


From 31f3d255c677073f83daa1e0671bbf2157bf8edc Mon Sep 17 00:00:00 2001
From: Miao Xie <miaox@cn.fujitsu.com>
Date: Thu, 6 Mar 2014 13:55:02 +0800
Subject: Btrfs: split the global ordered extents mutex

When we create a snapshot, we just need wait the ordered extents in
the source fs/file root, but because we use the global mutex to protect
this ordered extents list of the source fs/file root to avoid accessing
a empty list, if someone got the mutex to access the ordered extents list
of the other fs/file root, we had to wait.

This patch splits the above global mutex, now every fs/file root has
its own mutex to protect its own list.

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
---
 fs/btrfs/ctree.h        |  2 ++
 fs/btrfs/disk-io.c      |  1 +
 fs/btrfs/ordered-data.c | 17 ++++-------------
 3 files changed, 7 insertions(+), 13 deletions(-)

(limited to 'fs/btrfs/ordered-data.c')

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 5a800986f416..5f4921554f0a 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1814,6 +1814,8 @@ struct btrfs_root {
 	struct list_head delalloc_inodes;
 	struct list_head delalloc_root;
 	u64 nr_delalloc_inodes;
+
+	struct mutex ordered_extent_mutex;
 	/*
 	 * this is used by the balancing code to wait for all the pending
 	 * ordered extents
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 7d09ca48c347..237b5b5a2200 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1220,6 +1220,7 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	spin_lock_init(&root->log_extents_lock[1]);
 	mutex_init(&root->objectid_mutex);
 	mutex_init(&root->log_mutex);
+	mutex_init(&root->ordered_extent_mutex);
 	init_waitqueue_head(&root->log_writer_wait);
 	init_waitqueue_head(&root->log_commit_wait[0]);
 	init_waitqueue_head(&root->log_commit_wait[1]);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index a75eaa286b8a..a94b05f72869 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -595,7 +595,7 @@ static void btrfs_run_ordered_extent_work(struct btrfs_work *work)
  * wait for all the ordered extents in a root.  This is done when balancing
  * space between drives.
  */
-static int __btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
+int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
 {
 	struct list_head splice, works;
 	struct btrfs_ordered_extent *ordered, *next;
@@ -604,6 +604,7 @@ static int __btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
 	INIT_LIST_HEAD(&splice);
 	INIT_LIST_HEAD(&works);
 
+	mutex_lock(&root->ordered_extent_mutex);
 	spin_lock(&root->ordered_extent_lock);
 	list_splice_init(&root->ordered_extents, &splice);
 	while (!list_empty(&splice) && nr) {
@@ -635,17 +636,7 @@ static int __btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
 		btrfs_put_ordered_extent(ordered);
 		cond_resched();
 	}
-
-	return count;
-}
-
-int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
-{
-	int count;
-
-	mutex_lock(&root->fs_info->ordered_operations_mutex);
-	count = __btrfs_wait_ordered_extents(root, nr);
-	mutex_unlock(&root->fs_info->ordered_operations_mutex);
+	mutex_unlock(&root->ordered_extent_mutex);
 
 	return count;
 }
@@ -670,7 +661,7 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
 			       &fs_info->ordered_roots);
 		spin_unlock(&fs_info->ordered_root_lock);
 
-		done = __btrfs_wait_ordered_extents(root, nr);
+		done = btrfs_wait_ordered_extents(root, nr);
 		btrfs_put_fs_root(root);
 
 		spin_lock(&fs_info->ordered_root_lock);
-- 
cgit v1.2.3