Merge branch 'for-linus' into for-3.18/core

A bit of churn on the for-linus side that would be nice to have
in the core bits for 3.18, so pull it in to catch us up and make
forward progress easier.

Signed-off-by: Jens Axboe <axboe@fb.com>

Conflicts:
	block/scsi_ioctl.c

34 files changed, 636 insertions, 364 deletions

diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 5a201d8..fbd76de 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -22,7 +22,6 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/freezer.h>
-#include <linux/workqueue.h>
 #include "async-thread.h"
 #include "ctree.h"
 
@@ -55,8 +54,39 @@ struct btrfs_workqueue {
 	struct __btrfs_workqueue *high;
 };
 
-static inline struct __btrfs_workqueue
-*__btrfs_alloc_workqueue(const char *name, int flags, int max_active,
+static void normal_work_helper(struct btrfs_work *work);
+
+#define BTRFS_WORK_HELPER(name)					\
+void btrfs_##name(struct work_struct *arg)				\
+{									\
+	struct btrfs_work *work = container_of(arg, struct btrfs_work,	\
+					       normal_work);		\
+	normal_work_helper(work);					\
+}
+
+BTRFS_WORK_HELPER(worker_helper);
+BTRFS_WORK_HELPER(delalloc_helper);
+BTRFS_WORK_HELPER(flush_delalloc_helper);
+BTRFS_WORK_HELPER(cache_helper);
+BTRFS_WORK_HELPER(submit_helper);
+BTRFS_WORK_HELPER(fixup_helper);
+BTRFS_WORK_HELPER(endio_helper);
+BTRFS_WORK_HELPER(endio_meta_helper);
+BTRFS_WORK_HELPER(endio_meta_write_helper);
+BTRFS_WORK_HELPER(endio_raid56_helper);
+BTRFS_WORK_HELPER(rmw_helper);
+BTRFS_WORK_HELPER(endio_write_helper);
+BTRFS_WORK_HELPER(freespace_write_helper);
+BTRFS_WORK_HELPER(delayed_meta_helper);
+BTRFS_WORK_HELPER(readahead_helper);
+BTRFS_WORK_HELPER(qgroup_rescan_helper);
+BTRFS_WORK_HELPER(extent_refs_helper);
+BTRFS_WORK_HELPER(scrub_helper);
+BTRFS_WORK_HELPER(scrubwrc_helper);
+BTRFS_WORK_HELPER(scrubnc_helper);
+
+static struct __btrfs_workqueue *
+__btrfs_alloc_workqueue(const char *name, int flags, int max_active,
 			 int thresh)
 {
 	struct __btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_NOFS);
@@ -232,13 +262,11 @@ static void run_ordered_work(struct __btrfs_workqueue *wq)
 	spin_unlock_irqrestore(lock, flags);
 }
 
-static void normal_work_helper(struct work_struct *arg)
+static void normal_work_helper(struct btrfs_work *work)
 {
-	struct btrfs_work *work;
 	struct __btrfs_workqueue *wq;
 	int need_order = 0;
 
-	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
@@ -262,7 +290,7 @@ static void normal_work_helper(struct work_struct *arg)
 		trace_btrfs_all_work_done(work);
 }
 
-void btrfs_init_work(struct btrfs_work *work,
+void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func,
 		     btrfs_func_t func,
 		     btrfs_func_t ordered_func,
 		     btrfs_func_t ordered_free)
@@ -270,7 +298,7 @@ void btrfs_init_work(struct btrfs_work *work,
 	work->func = func;
 	work->ordered_func = ordered_func;
 	work->ordered_free = ordered_free;
-	INIT_WORK(&work->normal_work, normal_work_helper);
+	INIT_WORK(&work->normal_work, uniq_func);
 	INIT_LIST_HEAD(&work->ordered_list);
 	work->flags = 0;
 }
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 9c6b66d1..e9e31c9 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -19,12 +19,14 @@
 
 #ifndef __BTRFS_ASYNC_THREAD_
 #define __BTRFS_ASYNC_THREAD_
+#include <linux/workqueue.h>
 
 struct btrfs_workqueue;
 /* Internal use only */
 struct __btrfs_workqueue;
 struct btrfs_work;
 typedef void (*btrfs_func_t)(struct btrfs_work *arg);
+typedef void (*btrfs_work_func_t)(struct work_struct *arg);
 
 struct btrfs_work {
 	btrfs_func_t func;
@@ -38,11 +40,35 @@ struct btrfs_work {
 	unsigned long flags;
 };
 
+#define BTRFS_WORK_HELPER_PROTO(name)					\
+void btrfs_##name(struct work_struct *arg)
+
+BTRFS_WORK_HELPER_PROTO(worker_helper);
+BTRFS_WORK_HELPER_PROTO(delalloc_helper);
+BTRFS_WORK_HELPER_PROTO(flush_delalloc_helper);
+BTRFS_WORK_HELPER_PROTO(cache_helper);
+BTRFS_WORK_HELPER_PROTO(submit_helper);
+BTRFS_WORK_HELPER_PROTO(fixup_helper);
+BTRFS_WORK_HELPER_PROTO(endio_helper);
+BTRFS_WORK_HELPER_PROTO(endio_meta_helper);
+BTRFS_WORK_HELPER_PROTO(endio_meta_write_helper);
+BTRFS_WORK_HELPER_PROTO(endio_raid56_helper);
+BTRFS_WORK_HELPER_PROTO(rmw_helper);
+BTRFS_WORK_HELPER_PROTO(endio_write_helper);
+BTRFS_WORK_HELPER_PROTO(freespace_write_helper);
+BTRFS_WORK_HELPER_PROTO(delayed_meta_helper);
+BTRFS_WORK_HELPER_PROTO(readahead_helper);
+BTRFS_WORK_HELPER_PROTO(qgroup_rescan_helper);
+BTRFS_WORK_HELPER_PROTO(extent_refs_helper);
+BTRFS_WORK_HELPER_PROTO(scrub_helper);
+BTRFS_WORK_HELPER_PROTO(scrubwrc_helper);
+BTRFS_WORK_HELPER_PROTO(scrubnc_helper);
+
 struct btrfs_workqueue *btrfs_alloc_workqueue(const char *name,
 					      int flags,
 					      int max_active,
 					      int thresh);
-void btrfs_init_work(struct btrfs_work *work,
+void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t helper,
 		     btrfs_func_t func,
 		     btrfs_func_t ordered_func,
 		     btrfs_func_t ordered_free);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index da775bf..a2e90f8 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1395,8 +1395,8 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
 		return -ENOMEM;
 
 	async_work->delayed_root = delayed_root;
-	btrfs_init_work(&async_work->work, btrfs_async_run_delayed_root,
-			NULL, NULL);
+	btrfs_init_work(&async_work->work, btrfs_delayed_meta_helper,
+			btrfs_async_run_delayed_root, NULL, NULL);
 	async_work->nr = nr;
 
 	btrfs_queue_work(root->fs_info->delayed_workers, &async_work->work);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 39ff591..7e221b0 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -39,7 +39,6 @@
 #include "btrfs_inode.h"
 #include "volumes.h"
 #include "print-tree.h"
-#include "async-thread.h"
 #include "locking.h"
 #include "tree-log.h"
 #include "free-space-cache.h"
@@ -693,35 +692,41 @@ static void end_workqueue_bio(struct bio *bio, int err)
 {
 	struct end_io_wq *end_io_wq = bio->bi_private;
 	struct btrfs_fs_info *fs_info;
+	struct btrfs_workqueue *wq;
+	btrfs_work_func_t func;
 
 	fs_info = end_io_wq->info;
 	end_io_wq->error = err;
-	btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);
 
 	if (bio->bi_rw & REQ_WRITE) {
-		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
-			btrfs_queue_work(fs_info->endio_meta_write_workers,
-					 &end_io_wq->work);
-		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
-			btrfs_queue_work(fs_info->endio_freespace_worker,
-					 &end_io_wq->work);
-		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
-			btrfs_queue_work(fs_info->endio_raid56_workers,
-					 &end_io_wq->work);
-		else
-			btrfs_queue_work(fs_info->endio_write_workers,
-					 &end_io_wq->work);
+		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) {
+			wq = fs_info->endio_meta_write_workers;
+			func = btrfs_endio_meta_write_helper;
+		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) {
+			wq = fs_info->endio_freespace_worker;
+			func = btrfs_freespace_write_helper;
+		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+			wq = fs_info->endio_raid56_workers;
+			func = btrfs_endio_raid56_helper;
+		} else {
+			wq = fs_info->endio_write_workers;
+			func = btrfs_endio_write_helper;
+		}
 	} else {
-		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
-			btrfs_queue_work(fs_info->endio_raid56_workers,
-					 &end_io_wq->work);
-		else if (end_io_wq->metadata)
-			btrfs_queue_work(fs_info->endio_meta_workers,
-					 &end_io_wq->work);
-		else
-			btrfs_queue_work(fs_info->endio_workers,
-					 &end_io_wq->work);
+		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+			wq = fs_info->endio_raid56_workers;
+			func = btrfs_endio_raid56_helper;
+		} else if (end_io_wq->metadata) {
+			wq = fs_info->endio_meta_workers;
+			func = btrfs_endio_meta_helper;
+		} else {
+			wq = fs_info->endio_workers;
+			func = btrfs_endio_helper;
+		}
 	}
+
+	btrfs_init_work(&end_io_wq->work, func, end_workqueue_fn, NULL, NULL);
+	btrfs_queue_work(wq, &end_io_wq->work);
 }
 
 /*
@@ -828,7 +833,7 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
 	async->submit_bio_start = submit_bio_start;
 	async->submit_bio_done = submit_bio_done;
 
-	btrfs_init_work(&async->work, run_one_async_start,
+	btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start,
 			run_one_async_done, run_one_async_free);
 
 	async->bio_flags = bio_flags;
@@ -3450,7 +3455,8 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
 		btrfs_set_stack_device_generation(dev_item, 0);
 		btrfs_set_stack_device_type(dev_item, dev->type);
 		btrfs_set_stack_device_id(dev_item, dev->devid);
-		btrfs_set_stack_device_total_bytes(dev_item, dev->total_bytes);
+		btrfs_set_stack_device_total_bytes(dev_item,
+						   dev->disk_total_bytes);
 		btrfs_set_stack_device_bytes_used(dev_item, dev->bytes_used);
 		btrfs_set_stack_device_io_align(dev_item, dev->io_align);
 		btrfs_set_stack_device_io_width(dev_item, dev->io_width);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 102ed31..3efe1c3 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -552,7 +552,8 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 	caching_ctl->block_group = cache;
 	caching_ctl->progress = cache->key.objectid;
 	atomic_set(&caching_ctl->count, 1);
-	btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL);
+	btrfs_init_work(&caching_ctl->work, btrfs_cache_helper,
+			caching_thread, NULL, NULL);
 
 	spin_lock(&cache->lock);
 	/*
@@ -2749,8 +2750,8 @@ int btrfs_async_run_delayed_refs(struct btrfs_root *root,
 		async->sync = 0;
 	init_completion(&async->wait);
 
-	btrfs_init_work(&async->work, delayed_ref_async_start,
-			NULL, NULL);
+	btrfs_init_work(&async->work, btrfs_extent_refs_helper,
+			delayed_ref_async_start, NULL, NULL);
 
 	btrfs_queue_work(root->fs_info->extent_workers, &async->work);
 
@@ -3586,13 +3587,7 @@ static u64 get_restripe_target(struct btrfs_fs_info *fs_info, u64 flags)
  */
 static u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags)
 {
-	/*
-	 * we add in the count of missing devices because we want
-	 * to make sure that any RAID levels on a degraded FS
-	 * continue to be honored.
-	 */
-	u64 num_devices = root->fs_info->fs_devices->rw_devices +
-		root->fs_info->fs_devices->missing_devices;
+	u64 num_devices = root->fs_info->fs_devices->rw_devices;
 	u64 target;
 	u64 tmp;
 
@@ -8440,13 +8435,7 @@ static u64 update_block_group_flags(struct btrfs_root *root, u64 flags)
 	if (stripped)
 		return extended_to_chunk(stripped);
 
-	/*
-	 * we add in the count of missing devices because we want
-	 * to make sure that any RAID levels on a degraded FS
-	 * continue to be honored.
-	 */
-	num_devices = root->fs_info->fs_devices->rw_devices +
-		root->fs_info->fs_devices->missing_devices;
+	num_devices = root->fs_info->fs_devices->rw_devices;
 
 	stripped = BTRFS_BLOCK_GROUP_RAID0 |
 		BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6 |
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3e11aab..af0359d 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2532,6 +2532,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 					test_bit(BIO_UPTODATE, &bio->bi_flags);
 				if (err)
 					uptodate = 0;
+				offset += len;
 				continue;
 			}
 		}
@@ -4207,8 +4208,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		return -ENOMEM;
 	path->leave_spinning = 1;
 
-	start = ALIGN(start, BTRFS_I(inode)->root->sectorsize);
-	len = ALIGN(len, BTRFS_I(inode)->root->sectorsize);
+	start = round_down(start, BTRFS_I(inode)->root->sectorsize);
+	len = round_up(max, BTRFS_I(inode)->root->sectorsize) - start;
 
 	/*
 	 * lookup the last file extent.  We're not using i_size here
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index d3afac2..36861b7 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1840,7 +1840,15 @@ int btrfs_release_file(struct inode *inode, struct file *filp)
 {
 	if (filp->private_data)
 		btrfs_ioctl_trans_end(filp);
-	filemap_flush(inode->i_mapping);
+	/*
+	 * ordered_data_close is set by settattr when we are about to truncate
+	 * a file from a non-zero size to a zero size.  This tries to
+	 * flush down new bytes that may have been written if the
+	 * application were using truncate to replace a file in place.
+	 */
+	if (test_and_clear_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
+			       &BTRFS_I(inode)->runtime_flags))
+			filemap_flush(inode->i_mapping);
 	return 0;
 }
 
@@ -2088,10 +2096,9 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 		goto out;
 	}
 
-	if (hole_mergeable(inode, leaf, path->slots[0]+1, offset, end)) {
+	if (hole_mergeable(inode, leaf, path->slots[0], offset, end)) {
 		u64 num_bytes;
 
-		path->slots[0]++;
 		key.offset = offset;
 		btrfs_set_item_key_safe(root, path, &key);
 		fi = btrfs_item_ptr(leaf, path->slots[0],
@@ -2216,7 +2223,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		goto out_only_mutex;
 	}
 
-	lockstart = round_up(offset , BTRFS_I(inode)->root->sectorsize);
+	lockstart = round_up(offset, BTRFS_I(inode)->root->sectorsize);
 	lockend = round_down(offset + len,
 			     BTRFS_I(inode)->root->sectorsize) - 1;
 	same_page = ((offset >> PAGE_CACHE_SHIFT) ==
@@ -2277,7 +2284,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 						tail_start + tail_len, 0, 1);
 				if (ret)
 					goto out_only_mutex;
-				}
+			}
 		}
 	}
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 03708ef..9c194bd 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1096,8 +1096,10 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 		async_cow->end = cur_end;
 		INIT_LIST_HEAD(&async_cow->extents);
 
-		btrfs_init_work(&async_cow->work, async_cow_start,
-				async_cow_submit, async_cow_free);
+		btrfs_init_work(&async_cow->work,
+				btrfs_delalloc_helper,
+				async_cow_start, async_cow_submit,
+				async_cow_free);
 
 		nr_pages = (cur_end - start + PAGE_CACHE_SIZE) >>
 			PAGE_CACHE_SHIFT;
@@ -1881,7 +1883,8 @@ static int btrfs_writepage_start_hook(struct page *page, u64 start, u64 end)
 
 	SetPageChecked(page);
 	page_cache_get(page);
-	btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL);
+	btrfs_init_work(&fixup->work, btrfs_fixup_helper,
+			btrfs_writepage_fixup_worker, NULL, NULL);
 	fixup->page = page;
 	btrfs_queue_work(root->fs_info->fixup_workers, &fixup->work);
 	return -EBUSY;
@@ -2822,7 +2825,8 @@ 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 *workers;
+	struct btrfs_workqueue *wq;
+	btrfs_work_func_t func;
 
 	trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
 
@@ -2831,13 +2835,17 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
 					    end - start + 1, uptodate))
 		return 0;
 
-	btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL);
+	if (btrfs_is_free_space_inode(inode)) {
+		wq = root->fs_info->endio_freespace_worker;
+		func = btrfs_freespace_write_helper;
+	} else {
+		wq = root->fs_info->endio_write_workers;
+		func = btrfs_endio_write_helper;
+	}
 
-	if (btrfs_is_free_space_inode(inode))
-		workers = root->fs_info->endio_freespace_worker;
-	else
-		workers = root->fs_info->endio_write_workers;
-	btrfs_queue_work(workers, &ordered_extent->work);
+	btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL,
+			NULL);
+	btrfs_queue_work(wq, &ordered_extent->work);
 
 	return 0;
 }
@@ -4674,6 +4682,11 @@ static void evict_inode_truncate_pages(struct inode *inode)
 		clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
 		remove_extent_mapping(map_tree, em);
 		free_extent_map(em);
+		if (need_resched()) {
+			write_unlock(&map_tree->lock);
+			cond_resched();
+			write_lock(&map_tree->lock);
+		}
 	}
 	write_unlock(&map_tree->lock);
 
@@ -4696,6 +4709,7 @@ static void evict_inode_truncate_pages(struct inode *inode)
 				 &cached_state, GFP_NOFS);
 		free_extent_state(state);
 
+		cond_resched();
 		spin_lock(&io_tree->lock);
 	}
 	spin_unlock(&io_tree->lock);
@@ -5181,6 +5195,42 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 			iput(inode);
 			inode = ERR_PTR(ret);
 		}
+		/*
+		 * If orphan cleanup did remove any orphans, it means the tree
+		 * was modified and therefore the commit root is not the same as
+		 * the current root anymore. This is a problem, because send
+		 * uses the commit root and therefore can see inode items that
+		 * don't exist in the current root anymore, and for example make
+		 * calls to btrfs_iget, which will do tree lookups based on the
+		 * current root and not on the commit root. Those lookups will
+		 * fail, returning a -ESTALE error, and making send fail with
+		 * that error. So make sure a send does not see any orphans we
+		 * have just removed, and that it will see the same inodes
+		 * regardless of whether a transaction commit happened before
+		 * it started (meaning that the commit root will be the same as
+		 * the current root) or not.
+		 */
+		if (sub_root->node != sub_root->commit_root) {
+			u64 sub_flags = btrfs_root_flags(&sub_root->root_item);
+
+			if (sub_flags & BTRFS_ROOT_SUBVOL_RDONLY) {
+				struct extent_buffer *eb;
+
+				/*
+				 * Assert we can't have races between dentry
+				 * lookup called through the snapshot creation
+				 * ioctl and the VFS.
+				 */
+				ASSERT(mutex_is_locked(&dir->i_mutex));
+
+				down_write(&root->fs_info->commit_root_sem);
+				eb = sub_root->commit_root;
+				sub_root->commit_root =
+					btrfs_root_node(sub_root);
+				up_write(&root->fs_info->commit_root_sem);
+				free_extent_buffer(eb);
+			}
+		}
 	}
 
 	return inode;
@@ -5606,6 +5656,13 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	}
 
 	/*
+	 * O_TMPFILE, set link count to 0, so that after this point,
+	 * we fill in an inode item with the correct link count.
+	 */
+	if (!name)
+		set_nlink(inode, 0);
+
+	/*
 	 * we have to initialize this early, so we can reclaim the inode
 	 * number if we fail afterwards in this function.
 	 */
@@ -6097,14 +6154,14 @@ out_fail:
 static int merge_extent_mapping(struct extent_map_tree *em_tree,
 				struct extent_map *existing,
 				struct extent_map *em,
-				u64 map_start, u64 map_len)
+				u64 map_start)
 {
 	u64 start_diff;
 
 	BUG_ON(map_start < em->start || map_start >= extent_map_end(em));
 	start_diff = map_start - em->start;
 	em->start = map_start;
-	em->len = map_len;
+	em->len = existing->start - em->start;
 	if (em->block_start < EXTENT_MAP_LAST_BYTE &&
 	    !test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
 		em->block_start += start_diff;
@@ -6275,6 +6332,8 @@ next:
 			goto not_found;
 		if (start + len <= found_key.offset)
 			goto not_found;
+		if (start > found_key.offset)
+			goto next;
 		em->start = start;
 		em->orig_start = start;
 		em->len = found_key.offset - start;
@@ -6390,8 +6449,7 @@ insert:
 							 em->len);
 			if (existing) {
 				err = merge_extent_mapping(em_tree, existing,
-							   em, start,
-							   root->sectorsize);
+							   em, start);
 				free_extent_map(existing);
 				if (err) {
 					free_extent_map(em);
@@ -7158,7 +7216,8 @@ again:
 	if (!ret)
 		goto out_test;
 
-	btrfs_init_work(&ordered->work, finish_ordered_fn, NULL, NULL);
+	btrfs_init_work(&ordered->work, btrfs_endio_write_helper,
+			finish_ordered_fn, NULL, NULL);
 	btrfs_queue_work(root->fs_info->endio_write_workers,
 			 &ordered->work);
 out_test:
@@ -7306,10 +7365,8 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	map_length = orig_bio->bi_iter.bi_size;
 	ret = btrfs_map_block(root->fs_info, rw, start_sector << 9,
 			      &map_length, NULL, 0);
-	if (ret) {
-		bio_put(orig_bio);
+	if (ret)
 		return -EIO;
-	}
 
 	if (map_length >= orig_bio->bi_iter.bi_size) {
 		bio = orig_bio;
@@ -7326,6 +7383,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
 	if (!bio)
 		return -ENOMEM;
+
 	bio->bi_private = dip;
 	bio->bi_end_io = btrfs_end_dio_bio;
 	atomic_inc(&dip->pending_bios);
@@ -7534,7 +7592,8 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 	count = iov_iter_count(iter);
 	if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
 		     &BTRFS_I(inode)->runtime_flags))
-		filemap_fdatawrite_range(inode->i_mapping, offset, count);
+		filemap_fdatawrite_range(inode->i_mapping, offset,
+					 offset + count - 1);
 
 	if (rw & WRITE) {
 		/*
@@ -8495,7 +8554,9 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
 	work->inode = inode;
 	work->wait = wait;
 	work->delay_iput = delay_iput;
-	btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL);
+	WARN_ON_ONCE(!inode);
+	btrfs_init_work(&work->work, btrfs_flush_delalloc_helper,
+			btrfs_run_delalloc_work, NULL, NULL);
 
 	return work;
 }
@@ -8979,6 +9040,14 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 	if (ret)
 		goto out;
 
+	/*
+	 * We set number of links to 0 in btrfs_new_inode(), and here we set
+	 * it to 1 because d_tmpfile() will issue a warning if the count is 0,
+	 * through:
+	 *
+	 *    d_tmpfile() -> inode_dec_link_count() -> drop_nlink()
+	 */
+	set_nlink(inode, 1);
 	d_tmpfile(dentry, inode);
 	mark_inode_dirty(inode);
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 47aceb4..fce6fd0e 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -711,39 +711,6 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	if (ret)
 		goto fail;
 
-	ret = btrfs_orphan_cleanup(pending_snapshot->snap);
-	if (ret)
-		goto fail;
-
-	/*
-	 * If orphan cleanup did remove any orphans, it means the tree was
-	 * modified and therefore the commit root is not the same as the
-	 * current root anymore. This is a problem, because send uses the
-	 * commit root and therefore can see inode items that don't exist
-	 * in the current root anymore, and for example make calls to
-	 * btrfs_iget, which will do tree lookups based on the current root
-	 * and not on the commit root. Those lookups will fail, returning a
-	 * -ESTALE error, and making send fail with that error. So make sure
-	 * a send does not see any orphans we have just removed, and that it
-	 * will see the same inodes regardless of whether a transaction
-	 * commit happened before it started (meaning that the commit root
-	 * will be the same as the current root) or not.
-	 */
-	if (readonly && pending_snapshot->snap->node !=
-	    pending_snapshot->snap->commit_root) {
-		trans = btrfs_join_transaction(pending_snapshot->snap);
-		if (IS_ERR(trans) && PTR_ERR(trans) != -ENOENT) {
-			ret = PTR_ERR(trans);
-			goto fail;
-		}
-		if (!IS_ERR(trans)) {
-			ret = btrfs_commit_transaction(trans,
-						       pending_snapshot->snap);
-			if (ret)
-				goto fail;
-		}
-	}
-
 	inode = btrfs_lookup_dentry(dentry->d_parent->d_inode, dentry);
 	if (IS_ERR(inode)) {
 		ret = PTR_ERR(inode);
@@ -3527,7 +3494,8 @@ process_slot:
 			btrfs_mark_buffer_dirty(leaf);
 			btrfs_release_path(path);
 
-			last_dest_end = new_key.offset + datal;
+			last_dest_end = ALIGN(new_key.offset + datal,
+					      root->sectorsize);
 			ret = clone_finish_inode_update(trans, inode,
 							last_dest_end,
 							destoff, olen);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 963895c..ac734ec 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -615,6 +615,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
 		spin_unlock(&root->ordered_extent_lock);
 
 		btrfs_init_work(&ordered->flush_work,
+				btrfs_flush_delalloc_helper,
 				btrfs_run_ordered_extent_work, NULL, NULL);
 		list_add_tail(&ordered->work_list, &works);
 		btrfs_queue_work(root->fs_info->flush_workers,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index b497498..ded5c60 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1973,7 +1973,7 @@ static int qgroup_subtree_accounting(struct btrfs_trans_handle *trans,
 				   elem.seq, &roots);
 	btrfs_put_tree_mod_seq(fs_info, &elem);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	if (roots->nnodes != 1)
 		goto out;
@@ -2720,6 +2720,7 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 	memset(&fs_info->qgroup_rescan_work, 0,
 	       sizeof(fs_info->qgroup_rescan_work));
 	btrfs_init_work(&fs_info->qgroup_rescan_work,
+			btrfs_qgroup_rescan_helper,
 			btrfs_qgroup_rescan_worker, NULL, NULL);
 
 	if (ret) {
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 4a88f07..0a6b6e4 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1416,7 +1416,8 @@ cleanup:
 
 static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
 {
-	btrfs_init_work(&rbio->work, rmw_work, NULL, NULL);
+	btrfs_init_work(&rbio->work, btrfs_rmw_helper,
+			rmw_work, NULL, NULL);
 
 	btrfs_queue_work(rbio->fs_info->rmw_workers,
 			 &rbio->work);
@@ -1424,7 +1425,8 @@ static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
 
 static void async_read_rebuild(struct btrfs_raid_bio *rbio)
 {
-	btrfs_init_work(&rbio->work, read_rebuild_work, NULL, NULL);
+	btrfs_init_work(&rbio->work, btrfs_rmw_helper,
+			read_rebuild_work, NULL, NULL);
 
 	btrfs_queue_work(rbio->fs_info->rmw_workers,
 			 &rbio->work);
@@ -1665,7 +1667,8 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	plug = container_of(cb, struct btrfs_plug_cb, cb);
 
 	if (from_schedule) {
-		btrfs_init_work(&plug->work, unplug_work, NULL, NULL);
+		btrfs_init_work(&plug->work, btrfs_rmw_helper,
+				unplug_work, NULL, NULL);
 		btrfs_queue_work(plug->info->rmw_workers,
 				 &plug->work);
 		return;
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 09230cf..20408c6 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -798,7 +798,8 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info)
 		/* FIXME we cannot handle this properly right now */
 		BUG();
 	}
-	btrfs_init_work(&rmw->work, reada_start_machine_worker, NULL, NULL);
+	btrfs_init_work(&rmw->work, btrfs_readahead_helper,
+			reada_start_machine_worker, NULL, NULL);
 	rmw->fs_info = fs_info;
 
 	btrfs_queue_work(fs_info->readahead_workers, &rmw->work);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index b6d198f..f4a41f3 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -428,8 +428,8 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
 		sbio->index = i;
 		sbio->sctx = sctx;
 		sbio->page_count = 0;
-		btrfs_init_work(&sbio->work, scrub_bio_end_io_worker,
-				NULL, NULL);
+		btrfs_init_work(&sbio->work, btrfs_scrub_helper,
+				scrub_bio_end_io_worker, NULL, NULL);
 
 		if (i != SCRUB_BIOS_PER_SCTX - 1)
 			sctx->bios[i]->next_free = i + 1;
@@ -999,8 +999,8 @@ nodatasum_case:
 		fixup_nodatasum->root = fs_info->extent_root;
 		fixup_nodatasum->mirror_num = failed_mirror_index + 1;
 		scrub_pending_trans_workers_inc(sctx);
-		btrfs_init_work(&fixup_nodatasum->work, scrub_fixup_nodatasum,
-				NULL, NULL);
+		btrfs_init_work(&fixup_nodatasum->work, btrfs_scrub_helper,
+				scrub_fixup_nodatasum, NULL, NULL);
 		btrfs_queue_work(fs_info->scrub_workers,
 				 &fixup_nodatasum->work);
 		goto out;
@@ -1616,7 +1616,8 @@ static void scrub_wr_bio_end_io(struct bio *bio, int err)
 	sbio->err = err;
 	sbio->bio = bio;
 
-	btrfs_init_work(&sbio->work, scrub_wr_bio_end_io_worker, NULL, NULL);
+	btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper,
+			 scrub_wr_bio_end_io_worker, NULL, NULL);
 	btrfs_queue_work(fs_info->scrub_wr_completion_workers, &sbio->work);
 }
 
@@ -2904,6 +2905,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	struct scrub_ctx *sctx;
 	int ret;
 	struct btrfs_device *dev;
+	struct rcu_string *name;
 
 	if (btrfs_fs_closing(fs_info))
 		return -EINVAL;
@@ -2965,6 +2967,16 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		return -ENODEV;
 	}
 
+	if (!is_dev_replace && !readonly && !dev->writeable) {
+		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+		rcu_read_lock();
+		name = rcu_dereference(dev->name);
+		btrfs_err(fs_info, "scrub: device %s is not writable",
+			  name->str);
+		rcu_read_unlock();
+		return -EROFS;
+	}
+
 	mutex_lock(&fs_info->scrub_lock);
 	if (!dev->in_fs_metadata || dev->is_tgtdev_for_dev_replace) {
 		mutex_unlock(&fs_info->scrub_lock);
@@ -3203,7 +3215,8 @@ static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
 	nocow_ctx->len = len;
 	nocow_ctx->mirror_num = mirror_num;
 	nocow_ctx->physical_for_dev_replace = physical_for_dev_replace;
-	btrfs_init_work(&nocow_ctx->work, copy_nocow_pages_worker, NULL, NULL);
+	btrfs_init_work(&nocow_ctx->work, btrfs_scrubnc_helper,
+			copy_nocow_pages_worker, NULL, NULL);
 	INIT_LIST_HEAD(&nocow_ctx->inodes);
 	btrfs_queue_work(fs_info->scrub_nocow_workers,
 			 &nocow_ctx->work);
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 7869936..12e5355 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -614,7 +614,7 @@ int btrfs_kobj_rm_device(struct btrfs_fs_info *fs_info,
 	if (!fs_info->device_dir_kobj)
 		return -EINVAL;
 
-	if (one_device) {
+	if (one_device && one_device->bdev) {
 		disk = one_device->bdev->bd_part;
 		disk_kobj = &part_to_dev(disk)->kobj;
 
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 9e1f2cd..7e0e6e3 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3298,7 +3298,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 	struct list_head ordered_sums;
 	int skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 	bool has_extents = false;
-	bool need_find_last_extent = (*last_extent == 0);
+	bool need_find_last_extent = true;
 	bool done = false;
 
 	INIT_LIST_HEAD(&ordered_sums);
@@ -3352,8 +3352,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 		 */
 		if (ins_keys[i].type == BTRFS_EXTENT_DATA_KEY) {
 			has_extents = true;
-			if (need_find_last_extent &&
-			    first_key.objectid == (u64)-1)
+			if (first_key.objectid == (u64)-1)
 				first_key = ins_keys[i];
 		} else {
 			need_find_last_extent = false;
@@ -3427,6 +3426,16 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 	if (!has_extents)
 		return ret;
 
+	if (need_find_last_extent && *last_extent == first_key.offset) {
+		/*
+		 * We don't have any leafs between our current one and the one
+		 * we processed before that can have file extent items for our
+		 * inode (and have a generation number smaller than our current
+		 * transaction id).
+		 */
+		need_find_last_extent = false;
+	}
+
 	/*
 	 * Because we use btrfs_search_forward we could skip leaves that were
 	 * not modified and then assume *last_extent is valid when it really
@@ -3537,7 +3546,7 @@ fill_holes:
 					       0, 0);
 		if (ret)
 			break;
-		*last_extent = offset + len;
+		*last_extent = extent_end;
 	}
 	/*
 	 * Need to let the callers know we dropped the path so they should
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 6cb82f6..340a92d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -508,6 +508,44 @@ static noinline int device_list_add(const char *path,
 		ret = 1;
 		device->fs_devices = fs_devices;
 	} else if (!device->name || strcmp(device->name->str, path)) {
+		/*
+		 * When FS is already mounted.
+		 * 1. If you are here and if the device->name is NULL that
+		 *    means this device was missing at time of FS mount.
+		 * 2. If you are here and if the device->name is different
+		 *    from 'path' that means either
+		 *      a. The same device disappeared and reappeared with
+		 *         different name. or
+		 *      b. The missing-disk-which-was-replaced, has
+		 *         reappeared now.
+		 *
+		 * We must allow 1 and 2a above. But 2b would be a spurious
+		 * and unintentional.
+		 *
+		 * Further in case of 1 and 2a above, the disk at 'path'
+		 * would have missed some transaction when it was away and
+		 * in case of 2a the stale bdev has to be updated as well.
+		 * 2b must not be allowed at all time.
+		 */
+
+		/*
+		 * As of now don't allow update to btrfs_fs_device through
+		 * the btrfs dev scan cli, after FS has been mounted.
+		 */
+		if (fs_devices->opened) {
+			return -EBUSY;
+		} else {
+			/*
+			 * That is if the FS is _not_ mounted and if you
+			 * are here, that means there is more than one
+			 * disk with same uuid and devid.We keep the one
+			 * with larger generation number or the last-in if
+			 * generation are equal.
+			 */
+			if (found_transid < device->generation)
+				return -EEXIST;
+		}
+
 		name = rcu_string_strdup(path, GFP_NOFS);
 		if (!name)
 			return -ENOMEM;
@@ -519,6 +557,15 @@ static noinline int device_list_add(const char *path,
 		}
 	}
 
+	/*
+	 * Unmount does not free the btrfs_device struct but would zero
+	 * generation along with most of the other members. So just update
+	 * it back. We need it to pick the disk with largest generation
+	 * (as above).
+	 */
+	if (!fs_devices->opened)
+		device->generation = found_transid;
+
 	if (found_transid > fs_devices->latest_trans) {
 		fs_devices->latest_devid = devid;
 		fs_devices->latest_trans = found_transid;
@@ -1436,7 +1483,7 @@ static int btrfs_add_device(struct btrfs_trans_handle *trans,
 	btrfs_set_device_io_align(leaf, dev_item, device->io_align);
 	btrfs_set_device_io_width(leaf, dev_item, device->io_width);
 	btrfs_set_device_sector_size(leaf, dev_item, device->sector_size);
-	btrfs_set_device_total_bytes(leaf, dev_item, device->total_bytes);
+	btrfs_set_device_total_bytes(leaf, dev_item, device->disk_total_bytes);
 	btrfs_set_device_bytes_used(leaf, dev_item, device->bytes_used);
 	btrfs_set_device_group(leaf, dev_item, 0);
 	btrfs_set_device_seek_speed(leaf, dev_item, 0);
@@ -1671,7 +1718,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	device->fs_devices->total_devices--;
 
 	if (device->missing)
-		root->fs_info->fs_devices->missing_devices--;
+		device->fs_devices->missing_devices--;
 
 	next_device = list_entry(root->fs_info->fs_devices->devices.next,
 				 struct btrfs_device, dev_list);
@@ -1801,8 +1848,12 @@ void btrfs_rm_dev_replace_srcdev(struct btrfs_fs_info *fs_info,
 	if (srcdev->bdev) {
 		fs_info->fs_devices->open_devices--;
 
-		/* zero out the old super */
-		btrfs_scratch_superblock(srcdev);
+		/*
+		 * zero out the old super if it is not writable
+		 * (e.g. seed device)
+		 */
+		if (srcdev->writeable)
+			btrfs_scratch_superblock(srcdev);
 	}
 
 	call_rcu(&srcdev->rcu, free_device);
@@ -1941,6 +1992,9 @@ static int btrfs_prepare_sprout(struct btrfs_root *root)
 	fs_devices->seeding = 0;
 	fs_devices->num_devices = 0;
 	fs_devices->open_devices = 0;
+	fs_devices->missing_devices = 0;
+	fs_devices->num_can_discard = 0;
+	fs_devices->rotating = 0;
 	fs_devices->seed = seed_devices;
 
 	generate_random_uuid(fs_devices->fsid);
@@ -5800,7 +5854,8 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 	else
 		generate_random_uuid(dev->uuid);
 
-	btrfs_init_work(&dev->work, pending_bios_fn, NULL, NULL);
+	btrfs_init_work(&dev->work, btrfs_submit_helper,
+			pending_bios_fn, NULL, NULL);
 
 	return dev;
 }
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 5b19760..b0c225c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1825,7 +1825,7 @@ ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
 /*
  * Special error return code only used by dx_probe() and its callers.
  */
-#define ERR_BAD_DX_DIR	-75000
+#define ERR_BAD_DX_DIR	(-(MAX_ERRNO - 1))
 
 /*
  * Timeout and state flag for lazy initialization inode thread.
@@ -2454,6 +2454,22 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
 	up_write(&EXT4_I(inode)->i_data_sem);
 }
 
+/* Update i_size, i_disksize. Requires i_mutex to avoid races with truncate */
+static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize)
+{
+	int changed = 0;
+
+	if (newsize > inode->i_size) {
+		i_size_write(inode, newsize);
+		changed = 1;
+	}
+	if (newsize > EXT4_I(inode)->i_disksize) {
+		ext4_update_i_disksize(inode, newsize);
+		changed |= 2;
+	}
+	return changed;
+}
+
 struct ext4_group_info {
 	unsigned long   bb_state;
 	struct rb_root  bb_free_root;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 76c2df3..74292a7 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4665,7 +4665,8 @@ retry:
 }
 
 static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
-				  ext4_lblk_t len, int flags, int mode)
+				  ext4_lblk_t len, loff_t new_size,
+				  int flags, int mode)
 {
 	struct inode *inode = file_inode(file);
 	handle_t *handle;
@@ -4674,8 +4675,10 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 	int retries = 0;
 	struct ext4_map_blocks map;
 	unsigned int credits;
+	loff_t epos;
 
 	map.m_lblk = offset;
+	map.m_len = len;
 	/*
 	 * Don't normalize the request if it can fit in one extent so
 	 * that it doesn't get unnecessarily split into multiple
@@ -4690,9 +4693,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 	credits = ext4_chunk_trans_blocks(inode, len);
 
 retry:
-	while (ret >= 0 && ret < len) {
-		map.m_lblk = map.m_lblk + ret;
-		map.m_len = len = len - ret;
+	while (ret >= 0 && len) {
 		handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
 					    credits);
 		if (IS_ERR(handle)) {
@@ -4709,6 +4710,21 @@ retry:
 			ret2 = ext4_journal_stop(handle);
 			break;
 		}
+		map.m_lblk += ret;
+		map.m_len = len = len - ret;
+		epos = (loff_t)map.m_lblk << inode->i_blkbits;
+		inode->i_ctime = ext4_current_time(inode);
+		if (new_size) {
+			if (epos > new_size)
+				epos = new_size;
+			if (ext4_update_inode_size(inode, epos) & 0x1)
+				inode->i_mtime = inode->i_ctime;
+		} else {
+			if (epos > inode->i_size)
+				ext4_set_inode_flag(inode,
+						    EXT4_INODE_EOFBLOCKS);
+		}
+		ext4_mark_inode_dirty(handle, inode);
 		ret2 = ext4_journal_stop(handle);
 		if (ret2)
 			break;
@@ -4731,7 +4747,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	loff_t new_size = 0;
 	int ret = 0;
 	int flags;
-	int partial;
+	int credits;
+	int partial_begin, partial_end;
 	loff_t start, end;
 	ext4_lblk_t lblk;
 	struct address_space *mapping = inode->i_mapping;
@@ -4771,7 +4788,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 
 	if (start < offset || end > offset + len)
 		return -EINVAL;
-	partial = (offset + len) & ((1 << blkbits) - 1);
+	partial_begin = offset & ((1 << blkbits) - 1);
+	partial_end = (offset + len) & ((1 << blkbits) - 1);
 
 	lblk = start >> blkbits;
 	max_blocks = (end >> blkbits);
@@ -4805,7 +4823,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		 * If we have a partial block after EOF we have to allocate
 		 * the entire block.
 		 */
-		if (partial)
+		if (partial_end)
 			max_blocks += 1;
 	}
 
@@ -4813,6 +4831,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 
 		/* Now release the pages and zero block aligned part of pages*/
 		truncate_pagecache_range(inode, start, end - 1);
+		inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 
 		/* Wait all existing dio workers, newcomers will block on i_mutex */
 		ext4_inode_block_unlocked_dio(inode);
@@ -4825,13 +4844,22 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		if (ret)
 			goto out_dio;
 
-		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, flags,
-					     mode);
+		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
+					     flags, mode);
 		if (ret)
 			goto out_dio;
 	}
+	if (!partial_begin && !partial_end)
+		goto out_dio;
 
-	handle = ext4_journal_start(inode, EXT4_HT_MISC, 4);
+	/*
+	 * In worst case we have to writeout two nonadjacent unwritten
+	 * blocks and update the inode
+	 */
+	credits = (2 * ext4_ext_index_trans_blocks(inode, 2)) + 1;
+	if (ext4_should_journal_data(inode))
+		credits += 2;
+	handle = ext4_journal_start(inode, EXT4_HT_MISC, credits);
 	if (IS_ERR(handle)) {
 		ret = PTR_ERR(handle);
 		ext4_std_error(inode->i_sb, ret);
@@ -4839,12 +4867,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	}
 
 	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
-
 	if (new_size) {
-		if (new_size > i_size_read(inode))
-			i_size_write(inode, new_size);
-		if (new_size > EXT4_I(inode)->i_disksize)
-			ext4_update_i_disksize(inode, new_size);
+		ext4_update_inode_size(inode, new_size);
 	} else {
 		/*
 		* Mark that we allocate beyond EOF so the subsequent truncate
@@ -4853,7 +4877,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		if ((offset + len) > i_size_read(inode))
 			ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
 	}
-
 	ext4_mark_inode_dirty(handle, inode);
 
 	/* Zero out partial block at the edges of the range */
@@ -4880,13 +4903,11 @@ out_mutex:
 long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 {
 	struct inode *inode = file_inode(file);
-	handle_t *handle;
 	loff_t new_size = 0;
 	unsigned int max_blocks;
 	int ret = 0;
 	int flags;
 	ext4_lblk_t lblk;
-	struct timespec tv;
 	unsigned int blkbits = inode->i_blkbits;
 
 	/* Return error if mode is not supported */
@@ -4937,36 +4958,15 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 			goto out;
 	}
 
-	ret = ext4_alloc_file_blocks(file, lblk, max_blocks, flags, mode);
+	ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
+				     flags, mode);
 	if (ret)
 		goto out;
 
-	handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
-	if (IS_ERR(handle))
-		goto out;
-
-	tv = inode->i_ctime = ext4_current_time(inode);
-
-	if (new_size) {
-		if (new_size > i_size_read(inode)) {
-			i_size_write(inode, new_size);
-			inode->i_mtime = tv;
-		}
-		if (new_size > EXT4_I(inode)->i_disksize)
-			ext4_update_i_disksize(inode, new_size);
-	} else {
-		/*
-		* Mark that we allocate beyond EOF so the subsequent truncate
-		* can proceed even if the new size is the same as i_size.
-		*/
-		if ((offset + len) > i_size_read(inode))
-			ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
+	if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) {
+		ret = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal,
+						EXT4_I(inode)->i_sync_tid);
 	}
-	ext4_mark_inode_dirty(handle, inode);
-	if (file->f_flags & O_SYNC)
-		ext4_handle_sync(handle);
-
-	ext4_journal_stop(handle);
 out:
 	mutex_unlock(&inode->i_mutex);
 	trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 367a60c..3aa26e9 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1055,27 +1055,11 @@ static int ext4_write_end(struct file *file,
 	} else
 		copied = block_write_end(file, mapping, pos,
 					 len, copied, page, fsdata);
-
 	/*
-	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hole i_mutex.
-	 *
-	 * But it's important to update i_size while still holding page lock:
+	 * it's important to update i_size while still holding page lock:
 	 * page writeout could otherwise come in and zero beyond i_size.
 	 */
-	if (pos + copied > inode->i_size) {
-		i_size_write(inode, pos + copied);
-		i_size_changed = 1;
-	}
-
-	if (pos + copied > EXT4_I(inode)->i_disksize) {
-		/* We need to mark inode dirty even if
-		 * new_i_size is less that inode->i_size
-		 * but greater than i_disksize. (hint delalloc)
-		 */
-		ext4_update_i_disksize(inode, (pos + copied));
-		i_size_changed = 1;
-	}
+	i_size_changed = ext4_update_inode_size(inode, pos + copied);
 	unlock_page(page);
 	page_cache_release(page);
 
@@ -1123,7 +1107,7 @@ static int ext4_journalled_write_end(struct file *file,
 	int ret = 0, ret2;
 	int partial = 0;
 	unsigned from, to;
-	loff_t new_i_size;
+	int size_changed = 0;
 
 	trace_ext4_journalled_write_end(inode, pos, len, copied);
 	from = pos & (PAGE_CACHE_SIZE - 1);
@@ -1146,20 +1130,18 @@ static int ext4_journalled_write_end(struct file *file,
 		if (!partial)
 			SetPageUptodate(page);
 	}
-	new_i_size = pos + copied;
-	if (new_i_size > inode->i_size)
-		i_size_write(inode, pos+copied);
+	size_changed = ext4_update_inode_size(inode, pos + copied);
 	ext4_set_inode_state(inode, EXT4_STATE_JDATA);
 	EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
-	if (new_i_size > EXT4_I(inode)->i_disksize) {
-		ext4_update_i_disksize(inode, new_i_size);
+	unlock_page(page);
+	page_cache_release(page);
+
+	if (size_changed) {
 		ret2 = ext4_mark_inode_dirty(handle, inode);
 		if (!ret)
 			ret = ret2;
 	}
 
-	unlock_page(page);
-	page_cache_release(page);
 	if (pos + len > inode->i_size && ext4_can_truncate(inode))
 		/* if we have allocated more blocks and copied
 		 * less. We will have blocks allocated outside
@@ -2095,6 +2077,7 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 	struct ext4_map_blocks *map = &mpd->map;
 	int err;
 	loff_t disksize;
+	int progress = 0;
 
 	mpd->io_submit.io_end->offset =
 				((loff_t)map->m_lblk) << inode->i_blkbits;
@@ -2111,8 +2094,11 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 			 * is non-zero, a commit should free up blocks.
 			 */
 			if ((err == -ENOMEM) ||
-			    (err == -ENOSPC && ext4_count_free_clusters(sb)))
+			    (err == -ENOSPC && ext4_count_free_clusters(sb))) {
+				if (progress)
+					goto update_disksize;
 				return err;
+			}
 			ext4_msg(sb, KERN_CRIT,
 				 "Delayed block allocation failed for "
 				 "inode %lu at logical offset %llu with"
@@ -2129,15 +2115,17 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 			*give_up_on_write = true;
 			return err;
 		}
+		progress = 1;
 		/*
 		 * Update buffer state, submit mapped pages, and get us new
 		 * extent to map
 		 */
 		err = mpage_map_and_submit_buffers(mpd);
 		if (err < 0)
-			return err;
+			goto update_disksize;
 	} while (map->m_len);
 
+update_disksize:
 	/*
 	 * Update on-disk size after IO is submitted.  Races with
 	 * truncate are avoided by checking i_size under i_data_sem.
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 9560277..8b0f9ef 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1412,6 +1412,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 	int last = first + count - 1;
 	struct super_block *sb = e4b->bd_sb;
 
+	if (WARN_ON(count == 0))
+		return;
 	BUG_ON(last >= (sb->s_blocksize << 3));
 	assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
 	/* Don't bother if the block group is corrupt. */
@@ -3221,6 +3223,8 @@ static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
 	int err;
 
 	if (pa == NULL) {
+		if (ac->ac_f_ex.fe_len == 0)
+			return;
 		err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b);
 		if (err) {
 			/*
@@ -3235,6 +3239,7 @@ static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
 		mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start,
 			       ac->ac_f_ex.fe_len);
 		ext4_unlock_group(ac->ac_sb, ac->ac_f_ex.fe_group);
+		ext4_mb_unload_buddy(&e4b);
 		return;
 	}
 	if (pa->pa_type == MB_INODE_PA)
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index b147a67..90a3cdc 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1227,7 +1227,7 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
 				   buffer */
 	int num = 0;
 	ext4_lblk_t  nblocks;
-	int i, err;
+	int i, err = 0;
 	int namelen;
 
 	*res_dir = NULL;
@@ -1264,7 +1264,11 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
 		 * return.  Otherwise, fall back to doing a search the
 		 * old fashioned way.
 		 */
-		if (bh || (err != ERR_BAD_DX_DIR))
+		if (err == -ENOENT)
+			return NULL;
+		if (err && err != ERR_BAD_DX_DIR)
+			return ERR_PTR(err);
+		if (bh)
 			return bh;
 		dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
 			       "falling back\n"));
@@ -1295,6 +1299,11 @@ restart:
 				}
 				num++;
 				bh = ext4_getblk(NULL, dir, b++, 0, &err);
+				if (unlikely(err)) {
+					if (ra_max == 0)
+						return ERR_PTR(err);
+					break;
+				}
 				bh_use[ra_max] = bh;
 				if (bh)
 					ll_rw_block(READ | REQ_META | REQ_PRIO,
@@ -1417,6 +1426,8 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 		return ERR_PTR(-ENAMETOOLONG);
 
 	bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
+	if (IS_ERR(bh))
+		return (struct dentry *) bh;
 	inode = NULL;
 	if (bh) {
 		__u32 ino = le32_to_cpu(de->inode);
@@ -1450,6 +1461,8 @@ struct dentry *ext4_get_parent(struct dentry *child)
 	struct buffer_head *bh;
 
 	bh = ext4_find_entry(child->d_inode, &dotdot, &de, NULL);
+	if (IS_ERR(bh))
+		return (struct dentry *) bh;
 	if (!bh)
 		return ERR_PTR(-ENOENT);
 	ino = le32_to_cpu(de->inode);
@@ -2727,6 +2740,8 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
 
 	retval = -ENOENT;
 	bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
 	if (!bh)
 		goto end_rmdir;
 
@@ -2794,6 +2809,8 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 
 	retval = -ENOENT;
 	bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
 	if (!bh)
 		goto end_unlink;
 
@@ -3121,6 +3138,8 @@ static int ext4_find_delete_entry(handle_t *handle, struct inode *dir,
 	struct ext4_dir_entry_2 *de;
 
 	bh = ext4_find_entry(dir, d_name, &de, NULL);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
 	if (bh) {
 		retval = ext4_delete_entry(handle, dir, de, bh);
 		brelse(bh);
@@ -3128,7 +3147,8 @@ static int ext4_find_delete_entry(handle_t *handle, struct inode *dir,
 	return retval;
 }
 
-static void ext4_rename_delete(handle_t *handle, struct ext4_renament *ent)
+static void ext4_rename_delete(handle_t *handle, struct ext4_renament *ent,
+			       int force_reread)
 {
 	int retval;
 	/*
@@ -3140,7 +3160,8 @@ static void ext4_rename_delete(handle_t *handle, struct ext4_renament *ent)
 	if (le32_to_cpu(ent->de->inode) != ent->inode->i_ino ||
 	    ent->de->name_len != ent->dentry->d_name.len ||
 	    strncmp(ent->de->name, ent->dentry->d_name.name,
-		    ent->de->name_len)) {
+		    ent->de->name_len) ||
+	    force_reread) {
 		retval = ext4_find_delete_entry(handle, ent->dir,
 						&ent->dentry->d_name);
 	} else {
@@ -3191,6 +3212,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		.dentry = new_dentry,
 		.inode = new_dentry->d_inode,
 	};
+	int force_reread;
 	int retval;
 
 	dquot_initialize(old.dir);
@@ -3202,6 +3224,8 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		dquot_initialize(new.inode);
 
 	old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
+	if (IS_ERR(old.bh))
+		return PTR_ERR(old.bh);
 	/*
 	 *  Check for inode number is _not_ due to possible IO errors.
 	 *  We might rmdir the source, keep it as pwd of some process
@@ -3214,6 +3238,10 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	new.bh = ext4_find_entry(new.dir, &new.dentry->d_name,
 				 &new.de, &new.inlined);
+	if (IS_ERR(new.bh)) {
+		retval = PTR_ERR(new.bh);
+		goto end_rename;
+	}
 	if (new.bh) {
 		if (!new.inode) {
 			brelse(new.bh);
@@ -3246,6 +3274,15 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (retval)
 			goto end_rename;
 	}
+	/*
+	 * If we're renaming a file within an inline_data dir and adding or
+	 * setting the new dirent causes a conversion from inline_data to
+	 * extents/blockmap, we need to force the dirent delete code to
+	 * re-read the directory, or else we end up trying to delete a dirent
+	 * from what is now the extent tree root (or a block map).
+	 */
+	force_reread = (new.dir->i_ino == old.dir->i_ino &&
+			ext4_test_inode_flag(new.dir, EXT4_INODE_INLINE_DATA));
 	if (!new.bh) {
 		retval = ext4_add_entry(handle, new.dentry, old.inode);
 		if (retval)
@@ -3256,6 +3293,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (retval)
 			goto end_rename;
 	}
+	if (force_reread)
+		force_reread = !ext4_test_inode_flag(new.dir,
+						     EXT4_INODE_INLINE_DATA);
 
 	/*
 	 * Like most other Unix systems, set the ctime for inodes on a
@@ -3267,7 +3307,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 	/*
 	 * ok, that's it
 	 */
-	ext4_rename_delete(handle, &old);
+	ext4_rename_delete(handle, &old, force_reread);
 
 	if (new.inode) {
 		ext4_dec_count(handle, new.inode);
@@ -3330,6 +3370,8 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	old.bh = ext4_find_entry(old.dir, &old.dentry->d_name,
 				 &old.de, &old.inlined);
+	if (IS_ERR(old.bh))
+		return PTR_ERR(old.bh);
 	/*
 	 *  Check for inode number is _not_ due to possible IO errors.
 	 *  We might rmdir the source, keep it as pwd of some process
@@ -3342,6 +3384,10 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	new.bh = ext4_find_entry(new.dir, &new.dentry->d_name,
 				 &new.de, &new.inlined);
+	if (IS_ERR(new.bh)) {
+		retval = PTR_ERR(new.bh);
+		goto end_rename;
+	}
 
 	/* RENAME_EXCHANGE case: old *and* new must both exist */
 	if (!new.bh || le32_to_cpu(new.de->inode) != new.inode->i_ino)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 32b43ad..0b28b36 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3181,9 +3181,9 @@ static int set_journal_csum_feature_set(struct super_block *sb)
 
 	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
 				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
-		/* journal checksum v2 */
+		/* journal checksum v3 */
 		compat = 0;
-		incompat = JBD2_FEATURE_INCOMPAT_CSUM_V2;
+		incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3;
 	} else {
 		/* journal checksum v1 */
 		compat = JBD2_FEATURE_COMPAT_CHECKSUM;
@@ -3205,6 +3205,7 @@ static int set_journal_csum_feature_set(struct super_block *sb)
 		jbd2_journal_clear_features(sbi->s_journal,
 				JBD2_FEATURE_COMPAT_CHECKSUM, 0,
 				JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT |
+				JBD2_FEATURE_INCOMPAT_CSUM_V3 |
 				JBD2_FEATURE_INCOMPAT_CSUM_V2);
 	}
 
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 6fac743..b73e021 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -97,7 +97,7 @@ static void jbd2_commit_block_csum_set(journal_t *j, struct buffer_head *bh)
 	struct commit_header *h;
 	__u32 csum;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	h = (struct commit_header *)(bh->b_data);
@@ -313,11 +313,11 @@ static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh)
 	return checksum;
 }
 
-static void write_tag_block(int tag_bytes, journal_block_tag_t *tag,
+static void write_tag_block(journal_t *j, journal_block_tag_t *tag,
 				   unsigned long long block)
 {
 	tag->t_blocknr = cpu_to_be32(block & (u32)~0);
-	if (tag_bytes > JBD2_TAG_SIZE32)
+	if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_64BIT))
 		tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1);
 }
 
@@ -327,7 +327,7 @@ static void jbd2_descr_block_csum_set(journal_t *j,
 	struct jbd2_journal_block_tail *tail;
 	__u32 csum;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize -
@@ -340,12 +340,13 @@ static void jbd2_descr_block_csum_set(journal_t *j,
 static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
 				    struct buffer_head *bh, __u32 sequence)
 {
+	journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag;
 	struct page *page = bh->b_page;
 	__u8 *addr;
 	__u32 csum32;
 	__be32 seq;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	seq = cpu_to_be32(sequence);
@@ -355,8 +356,10 @@ static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
 			     bh->b_size);
 	kunmap_atomic(addr);
 
-	/* We only have space to store the lower 16 bits of the crc32c. */
-	tag->t_checksum = cpu_to_be16(csum32);
+	if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		tag3->t_checksum = cpu_to_be32(csum32);
+	else
+		tag->t_checksum = cpu_to_be16(csum32);
 }
 /*
  * jbd2_journal_commit_transaction
@@ -396,7 +399,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	LIST_HEAD(io_bufs);
 	LIST_HEAD(log_bufs);
 
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		csum_size = sizeof(struct jbd2_journal_block_tail);
 
 	/*
@@ -690,7 +693,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 			tag_flag |= JBD2_FLAG_SAME_UUID;
 
 		tag = (journal_block_tag_t *) tagp;
-		write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr);
+		write_tag_block(journal, tag, jh2bh(jh)->b_blocknr);
 		tag->t_flags = cpu_to_be16(tag_flag);
 		jbd2_block_tag_csum_set(journal, tag, wbuf[bufs],
 					commit_transaction->t_tid);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 67b8e30..19d74d8 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -124,7 +124,7 @@ EXPORT_SYMBOL(__jbd2_debug);
 /* Checksumming functions */
 static int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb)
 {
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	return sb->s_checksum_type == JBD2_CRC32C_CHKSUM;
@@ -145,7 +145,7 @@ static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb)
 
 static int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
 {
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	return sb->s_checksum == jbd2_superblock_csum(j, sb);
@@ -153,7 +153,7 @@ static int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
 
 static void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb)
 {
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	sb->s_checksum = jbd2_superblock_csum(j, sb);
@@ -1522,21 +1522,29 @@ static int journal_get_superblock(journal_t *journal)
 		goto out;
 	}
 
-	if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) &&
-	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+	if (jbd2_journal_has_csum_v2or3(journal) &&
+	    JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM)) {
 		/* Can't have checksum v1 and v2 on at the same time! */
 		printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2 "
 		       "at the same time!\n");
 		goto out;
 	}
 
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) &&
+	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
+		/* Can't have checksum v2 and v3 at the same time! */
+		printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 "
+		       "at the same time!\n");
+		goto out;
+	}
+
 	if (!jbd2_verify_csum_type(journal, sb)) {
 		printk(KERN_ERR "JBD2: Unknown checksum type\n");
 		goto out;
 	}
 
 	/* Load the checksum driver */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+	if (jbd2_journal_has_csum_v2or3(journal)) {
 		journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
 		if (IS_ERR(journal->j_chksum_driver)) {
 			printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n");
@@ -1553,7 +1561,7 @@ static int journal_get_superblock(journal_t *journal)
 	}
 
 	/* Precompute checksum seed for all metadata */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid,
 						   sizeof(sb->s_uuid));
 
@@ -1813,8 +1821,14 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 	if (!jbd2_journal_check_available_features(journal, compat, ro, incompat))
 		return 0;
 
-	/* Asking for checksumming v2 and v1?  Only give them v2. */
-	if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2 &&
+	/* If enabling v2 checksums, turn on v3 instead */
+	if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2) {
+		incompat &= ~JBD2_FEATURE_INCOMPAT_CSUM_V2;
+		incompat |= JBD2_FEATURE_INCOMPAT_CSUM_V3;
+	}
+
+	/* Asking for checksumming v3 and v1?  Only give them v3. */
+	if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V3 &&
 	    compat & JBD2_FEATURE_COMPAT_CHECKSUM)
 		compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM;
 
@@ -1823,8 +1837,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 
 	sb = journal->j_superblock;
 
-	/* If enabling v2 checksums, update superblock */
-	if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+	/* If enabling v3 checksums, update superblock */
+	if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
 		sb->s_checksum_type = JBD2_CRC32C_CHKSUM;
 		sb->s_feature_compat &=
 			~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM);
@@ -1842,8 +1856,7 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 		}
 
 		/* Precompute checksum seed for all metadata */
-		if (JBD2_HAS_INCOMPAT_FEATURE(journal,
-					      JBD2_FEATURE_INCOMPAT_CSUM_V2))
+		if (jbd2_journal_has_csum_v2or3(journal))
 			journal->j_csum_seed = jbd2_chksum(journal, ~0,
 							   sb->s_uuid,
 							   sizeof(sb->s_uuid));
@@ -1852,7 +1865,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 	/* If enabling v1 checksums, downgrade superblock */
 	if (COMPAT_FEATURE_ON(JBD2_FEATURE_COMPAT_CHECKSUM))
 		sb->s_feature_incompat &=
-			~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2);
+			~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2 |
+				     JBD2_FEATURE_INCOMPAT_CSUM_V3);
 
 	sb->s_feature_compat    |= cpu_to_be32(compat);
 	sb->s_feature_ro_compat |= cpu_to_be32(ro);
@@ -2165,16 +2179,20 @@ int jbd2_journal_blocks_per_page(struct inode *inode)
  */
 size_t journal_tag_bytes(journal_t *journal)
 {
-	journal_block_tag_t tag;
-	size_t x = 0;
+	size_t sz;
+
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		return sizeof(journal_block_tag3_t);
+
+	sz = sizeof(journal_block_tag_t);
 
 	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
-		x += sizeof(tag.t_checksum);
+		sz += sizeof(__u16);
 
 	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
-		return x + JBD2_TAG_SIZE64;
+		return sz;
 	else
-		return x + JBD2_TAG_SIZE32;
+		return sz - sizeof(__u32);
 }
 
 /*
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 3b6bb19..9b329b5 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -181,7 +181,7 @@ static int jbd2_descr_block_csum_verify(journal_t *j,
 	__be32 provided;
 	__u32 calculated;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	tail = (struct jbd2_journal_block_tail *)(buf + j->j_blocksize -
@@ -205,7 +205,7 @@ static int count_tags(journal_t *journal, struct buffer_head *bh)
 	int			nr = 0, size = journal->j_blocksize;
 	int			tag_bytes = journal_tag_bytes(journal);
 
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		size -= sizeof(struct jbd2_journal_block_tail);
 
 	tagp = &bh->b_data[sizeof(journal_header_t)];
@@ -338,10 +338,11 @@ int jbd2_journal_skip_recovery(journal_t *journal)
 	return err;
 }
 
-static inline unsigned long long read_tag_block(int tag_bytes, journal_block_tag_t *tag)
+static inline unsigned long long read_tag_block(journal_t *journal,
+						journal_block_tag_t *tag)
 {
 	unsigned long long block = be32_to_cpu(tag->t_blocknr);
-	if (tag_bytes > JBD2_TAG_SIZE32)
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
 		block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32;
 	return block;
 }
@@ -384,7 +385,7 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
 	__be32 provided;
 	__u32 calculated;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	h = buf;
@@ -399,17 +400,21 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
 static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag,
 				      void *buf, __u32 sequence)
 {
+	journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag;
 	__u32 csum32;
 	__be32 seq;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	seq = cpu_to_be32(sequence);
 	csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq));
 	csum32 = jbd2_chksum(j, csum32, buf, j->j_blocksize);
 
-	return tag->t_checksum == cpu_to_be16(csum32);
+	if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		return tag3->t_checksum == cpu_to_be32(csum32);
+	else
+		return tag->t_checksum == cpu_to_be16(csum32);
 }
 
 static int do_one_pass(journal_t *journal,
@@ -426,6 +431,7 @@ static int do_one_pass(journal_t *journal,
 	int			tag_bytes = journal_tag_bytes(journal);
 	__u32			crc32_sum = ~0; /* Transactional Checksums */
 	int			descr_csum_size = 0;
+	int			block_error = 0;
 
 	/*
 	 * First thing is to establish what we expect to find in the log
@@ -512,8 +518,7 @@ static int do_one_pass(journal_t *journal,
 		switch(blocktype) {
 		case JBD2_DESCRIPTOR_BLOCK:
 			/* Verify checksum first */
-			if (JBD2_HAS_INCOMPAT_FEATURE(journal,
-					JBD2_FEATURE_INCOMPAT_CSUM_V2))
+			if (jbd2_journal_has_csum_v2or3(journal))
 				descr_csum_size =
 					sizeof(struct jbd2_journal_block_tail);
 			if (descr_csum_size > 0 &&
@@ -574,7 +579,7 @@ static int do_one_pass(journal_t *journal,
 					unsigned long long blocknr;
 
 					J_ASSERT(obh != NULL);
-					blocknr = read_tag_block(tag_bytes,
+					blocknr = read_tag_block(journal,
 								 tag);
 
 					/* If the block has been
@@ -598,7 +603,8 @@ static int do_one_pass(journal_t *journal,
 						       "checksum recovering "
 						       "block %llu in log\n",
 						       blocknr);
-						continue;
+						block_error = 1;
+						goto skip_write;
 					}
 
 					/* Find a buffer for the new
@@ -797,7 +803,8 @@ static int do_one_pass(journal_t *journal,
 				success = -EIO;
 		}
 	}
-
+	if (block_error && success == 0)
+		success = -EIO;
 	return success;
 
  failed:
@@ -811,7 +818,7 @@ static int jbd2_revoke_block_csum_verify(journal_t *j,
 	__be32 provided;
 	__u32 calculated;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	tail = (struct jbd2_journal_revoke_tail *)(buf + j->j_blocksize -
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 198c9c1..d5e95a1 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -91,8 +91,8 @@
 #include <linux/list.h>
 #include <linux/init.h>
 #include <linux/bio.h>
-#endif
 #include <linux/log2.h>
+#endif
 
 static struct kmem_cache *jbd2_revoke_record_cache;
 static struct kmem_cache *jbd2_revoke_table_cache;
@@ -597,7 +597,7 @@ static void write_one_revoke_record(journal_t *journal,
 	offset = *offsetp;
 
 	/* Do we need to leave space at the end for a checksum? */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		csum_size = sizeof(struct jbd2_journal_revoke_tail);
 
 	/* Make sure we have a descriptor with space left for the record */
@@ -644,7 +644,7 @@ static void jbd2_revoke_csum_set(journal_t *j, struct buffer_head *bh)
 	struct jbd2_journal_revoke_tail *tail;
 	__u32 csum;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	tail = (struct jbd2_journal_revoke_tail *)(bh->b_data + j->j_blocksize -
diff --git a/fs/locks.c b/fs/locks.c
index cb66fb0..bb08857 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1619,7 +1619,7 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 	smp_mb();
 	error = check_conflicting_open(dentry, arg);
 	if (error)
-		locks_unlink_lock(flp);
+		locks_unlink_lock(before);
 out:
 	if (is_deleg)
 		mutex_unlock(&inode->i_mutex);
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index d0fec26..24c6898 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -129,7 +129,10 @@ static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 		.rpc_argp	= &args,
 		.rpc_resp	= &fattr,
 	};
-	int status;
+	int status = 0;
+
+	if (acl == NULL && (!S_ISDIR(inode->i_mode) || dfacl == NULL))
+		goto out;
 
 	status = -EOPNOTSUPP;
 	if (!nfs_server_capable(inode, NFS_CAP_ACLS))
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 75ae8d2..7dd8aca 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2560,6 +2560,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 	struct nfs4_closedata *calldata = data;
 	struct nfs4_state *state = calldata->state;
 	struct nfs_server *server = NFS_SERVER(calldata->inode);
+	nfs4_stateid *res_stateid = NULL;
 
 	dprintk("%s: begin!\n", __func__);
 	if (!nfs4_sequence_done(task, &calldata->res.seq_res))
@@ -2570,12 +2571,12 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 	 */
 	switch (task->tk_status) {
 		case 0:
-			if (calldata->roc)
+			res_stateid = &calldata->res.stateid;
+			if (calldata->arg.fmode == 0 && calldata->roc)
 				pnfs_roc_set_barrier(state->inode,
 						     calldata->roc_barrier);
-			nfs_clear_open_stateid(state, &calldata->res.stateid, 0);
 			renew_lease(server, calldata->timestamp);
-			goto out_release;
+			break;
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_OLD_STATEID:
@@ -2589,7 +2590,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 				goto out_release;
 			}
 	}
-	nfs_clear_open_stateid(state, NULL, calldata->arg.fmode);
+	nfs_clear_open_stateid(state, res_stateid, calldata->arg.fmode);
 out_release:
 	nfs_release_seqid(calldata->arg.seqid);
 	nfs_refresh_inode(calldata->inode, calldata->res.fattr);
@@ -2601,6 +2602,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 	struct nfs4_closedata *calldata = data;
 	struct nfs4_state *state = calldata->state;
 	struct inode *inode = calldata->inode;
+	bool is_rdonly, is_wronly, is_rdwr;
 	int call_close = 0;
 
 	dprintk("%s: begin!\n", __func__);
@@ -2608,18 +2610,24 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 		goto out_wait;
 
 	task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE];
-	calldata->arg.fmode = FMODE_READ|FMODE_WRITE;
 	spin_lock(&state->owner->so_lock);
+	is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags);
+	is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags);
+	is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags);
+	/* Calculate the current open share mode */
+	calldata->arg.fmode = 0;
+	if (is_rdonly || is_rdwr)
+		calldata->arg.fmode |= FMODE_READ;
+	if (is_wronly || is_rdwr)
+		calldata->arg.fmode |= FMODE_WRITE;
 	/* Calculate the change in open mode */
 	if (state->n_rdwr == 0) {
 		if (state->n_rdonly == 0) {
-			call_close |= test_bit(NFS_O_RDONLY_STATE, &state->flags);
-			call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
+			call_close |= is_rdonly || is_rdwr;
 			calldata->arg.fmode &= ~FMODE_READ;
 		}
 		if (state->n_wronly == 0) {
-			call_close |= test_bit(NFS_O_WRONLY_STATE, &state->flags);
-			call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
+			call_close |= is_wronly || is_rdwr;
 			calldata->arg.fmode &= ~FMODE_WRITE;
 		}
 	}
diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c
index 1ec141e..62e8ec6 100644
--- a/fs/ocfs2/cluster/quorum.c
+++ b/fs/ocfs2/cluster/quorum.c
@@ -160,9 +160,18 @@ static void o2quo_make_decision(struct work_struct *work)
 	}
 
 out:
-	spin_unlock(&qs->qs_lock);
-	if (fence)
+	if (fence) {
+		spin_unlock(&qs->qs_lock);
 		o2quo_fence_self();
+	} else {
+		mlog(ML_NOTICE, "not fencing this node, heartbeating: %d, "
+			"connected: %d, lowest: %d (%sreachable)\n",
+			qs->qs_heartbeating, qs->qs_connected, lowest_hb,
+			lowest_reachable ? "" : "un");
+		spin_unlock(&qs->qs_lock);
+
+	}
+
 }
 
 static void o2quo_set_hold(struct o2quo_state *qs, u8 node)
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 681691b..ea34952 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1480,6 +1480,14 @@ static int o2net_set_nodelay(struct socket *sock)
 	return ret;
 }
 
+static int o2net_set_usertimeout(struct socket *sock)
+{
+	int user_timeout = O2NET_TCP_USER_TIMEOUT;
+
+	return kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
+				(char *)&user_timeout, sizeof(user_timeout));
+}
+
 static void o2net_initialize_handshake(void)
 {
 	o2net_hand->o2hb_heartbeat_timeout_ms = cpu_to_be32(
@@ -1536,16 +1544,20 @@ static void o2net_idle_timer(unsigned long data)
 #endif
 
 	printk(KERN_NOTICE "o2net: Connection to " SC_NODEF_FMT " has been "
-	       "idle for %lu.%lu secs, shutting it down.\n", SC_NODEF_ARGS(sc),
-	       msecs / 1000, msecs % 1000);
+	       "idle for %lu.%lu secs.\n",
+	       SC_NODEF_ARGS(sc), msecs / 1000, msecs % 1000);
 
-	/*
-	 * Initialize the nn_timeout so that the next connection attempt
-	 * will continue in o2net_start_connect.
+	/* idle timerout happen, don't shutdown the connection, but
+	 * make fence decision. Maybe the connection can recover before
+	 * the decision is made.
 	 */
 	atomic_set(&nn->nn_timeout, 1);
+	o2quo_conn_err(o2net_num_from_nn(nn));
+	queue_delayed_work(o2net_wq, &nn->nn_still_up,
+			msecs_to_jiffies(O2NET_QUORUM_DELAY_MS));
+
+	o2net_sc_reset_idle_timer(sc);
 
-	o2net_sc_queue_work(sc, &sc->sc_shutdown_work);
 }
 
 static void o2net_sc_reset_idle_timer(struct o2net_sock_container *sc)
@@ -1560,6 +1572,15 @@ static void o2net_sc_reset_idle_timer(struct o2net_sock_container *sc)
 
 static void o2net_sc_postpone_idle(struct o2net_sock_container *sc)
 {
+	struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num);
+
+	/* clear fence decision since the connection recover from timeout*/
+	if (atomic_read(&nn->nn_timeout)) {
+		o2quo_conn_up(o2net_num_from_nn(nn));
+		cancel_delayed_work(&nn->nn_still_up);
+		atomic_set(&nn->nn_timeout, 0);
+	}
+
 	/* Only push out an existing timer */
 	if (timer_pending(&sc->sc_idle_timeout))
 		o2net_sc_reset_idle_timer(sc);
@@ -1650,6 +1671,12 @@ static void o2net_start_connect(struct work_struct *work)
 		goto out;
 	}
 
+	ret = o2net_set_usertimeout(sock);
+	if (ret) {
+		mlog(ML_ERROR, "set TCP_USER_TIMEOUT failed with %d\n", ret);
+		goto out;
+	}
+
 	o2net_register_callbacks(sc->sc_sock->sk, sc);
 
 	spin_lock(&nn->nn_lock);
@@ -1831,6 +1858,12 @@ static int o2net_accept_one(struct socket *sock, int *more)
 		goto out;
 	}
 
+	ret = o2net_set_usertimeout(new_sock);
+	if (ret) {
+		mlog(ML_ERROR, "set TCP_USER_TIMEOUT failed with %d\n", ret);
+		goto out;
+	}
+
 	slen = sizeof(sin);
 	ret = new_sock->ops->getname(new_sock, (struct sockaddr *) &sin,
 				       &slen, 1);
diff --git a/fs/ocfs2/cluster/tcp.h b/fs/ocfs2/cluster/tcp.h
index 5bada2a..c571e84 100644
--- a/fs/ocfs2/cluster/tcp.h
+++ b/fs/ocfs2/cluster/tcp.h
@@ -63,6 +63,7 @@ typedef void (o2net_post_msg_handler_func)(int status, void *data,
 #define O2NET_KEEPALIVE_DELAY_MS_DEFAULT	2000
 #define O2NET_IDLE_TIMEOUT_MS_DEFAULT		30000
 
+#define O2NET_TCP_USER_TIMEOUT			0x7fffffff
 
 /* TODO: figure this out.... */
 static inline int o2net_link_down(int err, struct socket *sock)
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 6f66b37..53e6c40 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -35,9 +35,8 @@
 		copy_to_user((typeof(a) __user *)b, &(a), sizeof(a))
 
 /*
- * This call is void because we are already reporting an error that may
- * be -EFAULT.  The error will be returned from the ioctl(2) call.  It's
- * just a best-effort to tell userspace that this request caused the error.
+ * This is just a best-effort to tell userspace that this request
+ * caused the error.
  */
 static inline void o2info_set_request_error(struct ocfs2_info_request *kreq,
 					struct ocfs2_info_request __user *req)
@@ -146,136 +145,105 @@ bail:
 static int ocfs2_info_handle_blocksize(struct inode *inode,
 				       struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_blocksize oib;
 
 	if (o2info_from_user(oib, req))
-		goto bail;
+		return -EFAULT;
 
 	oib.ib_blocksize = inode->i_sb->s_blocksize;
 
 	o2info_set_request_filled(&oib.ib_req);
 
 	if (o2info_to_user(oib, req))
-		goto bail;
-
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oib.ib_req, req);
+		return -EFAULT;
 
-	return status;
+	return 0;
 }
 
 static int ocfs2_info_handle_clustersize(struct inode *inode,
 					 struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_clustersize oic;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	if (o2info_from_user(oic, req))
-		goto bail;
+		return -EFAULT;
 
 	oic.ic_clustersize = osb->s_clustersize;
 
 	o2info_set_request_filled(&oic.ic_req);
 
 	if (o2info_to_user(oic, req))
-		goto bail;
-
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oic.ic_req, req);
+		return -EFAULT;
 
-	return status;
+	return 0;
 }
 
 static int ocfs2_info_handle_maxslots(struct inode *inode,
 				      struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_maxslots oim;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	if (o2info_from_user(oim, req))
-		goto bail;
+		return -EFAULT;
 
 	oim.im_max_slots = osb->max_slots;
 
 	o2info_set_request_filled(&oim.im_req);
 
 	if (o2info_to_user(oim, req))
-		goto bail;
+		return -EFAULT;
 
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oim.im_req, req);
-
-	return status;
+	return 0;
 }
 
 static int ocfs2_info_handle_label(struct inode *inode,
 				   struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_label oil;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	if (o2info_from_user(oil, req))
-		goto bail;
+		return -EFAULT;
 
 	memcpy(oil.il_label, osb->vol_label, OCFS2_MAX_VOL_LABEL_LEN);
 
 	o2info_set_request_filled(&oil.il_req);
 
 	if (o2info_to_user(oil, req))
-		goto bail;
+		return -EFAULT;
 
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oil.il_req, req);
-
-	return status;
+	return 0;
 }
 
 static int ocfs2_info_handle_uuid(struct inode *inode,
 				  struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_uuid oiu;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	if (o2info_from_user(oiu, req))
-		goto bail;
+		return -EFAULT;
 
 	memcpy(oiu.iu_uuid_str, osb->uuid_str, OCFS2_TEXT_UUID_LEN + 1);
 
 	o2info_set_request_filled(&oiu.iu_req);
 
 	if (o2info_to_user(oiu, req))
-		goto bail;
-
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oiu.iu_req, req);
+		return -EFAULT;
 
-	return status;
+	return 0;
 }
 
 static int ocfs2_info_handle_fs_features(struct inode *inode,
 					 struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_fs_features oif;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	if (o2info_from_user(oif, req))
-		goto bail;
+		return -EFAULT;
 
 	oif.if_compat_features = osb->s_feature_compat;
 	oif.if_incompat_features = osb->s_feature_incompat;
@@ -284,39 +252,28 @@ static int ocfs2_info_handle_fs_features(struct inode *inode,
 	o2info_set_request_filled(&oif.if_req);
 
 	if (o2info_to_user(oif, req))
-		goto bail;
+		return -EFAULT;
 
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oif.if_req, req);
-
-	return status;
+	return 0;
 }
 
 static int ocfs2_info_handle_journal_size(struct inode *inode,
 					  struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_journal_size oij;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	if (o2info_from_user(oij, req))
-		goto bail;
+		return -EFAULT;
 
 	oij.ij_journal_size = i_size_read(osb->journal->j_inode);
 
 	o2info_set_request_filled(&oij.ij_req);
 
 	if (o2info_to_user(oij, req))
-		goto bail;
+		return -EFAULT;
 
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oij.ij_req, req);
-
-	return status;
+	return 0;
 }
 
 static int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb,
@@ -373,7 +330,7 @@ static int ocfs2_info_handle_freeinode(struct inode *inode,
 	u32 i;
 	u64 blkno = -1;
 	char namebuf[40];
-	int status = -EFAULT, type = INODE_ALLOC_SYSTEM_INODE;
+	int status, type = INODE_ALLOC_SYSTEM_INODE;
 	struct ocfs2_info_freeinode *oifi = NULL;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct inode *inode_alloc = NULL;
@@ -385,8 +342,10 @@ static int ocfs2_info_handle_freeinode(struct inode *inode,
 		goto out_err;
 	}
 
-	if (o2info_from_user(*oifi, req))
-		goto bail;
+	if (o2info_from_user(*oifi, req)) {
+		status = -EFAULT;
+		goto out_free;
+	}
 
 	oifi->ifi_slotnum = osb->max_slots;
 
@@ -424,14 +383,16 @@ static int ocfs2_info_handle_freeinode(struct inode *inode,
 
 	o2info_set_request_filled(&oifi->ifi_req);
 
-	if (o2info_to_user(*oifi, req))
-		goto bail;
+	if (o2info_to_user(*oifi, req)) {
+		status = -EFAULT;
+		goto out_free;
+	}
 
 	status = 0;
 bail:
 	if (status)
 		o2info_set_request_error(&oifi->ifi_req, req);
-
+out_free:
 	kfree(oifi);
 out_err:
 	return status;
@@ -658,7 +619,7 @@ static int ocfs2_info_handle_freefrag(struct inode *inode,
 {
 	u64 blkno = -1;
 	char namebuf[40];
-	int status = -EFAULT, type = GLOBAL_BITMAP_SYSTEM_INODE;
+	int status, type = GLOBAL_BITMAP_SYSTEM_INODE;
 
 	struct ocfs2_info_freefrag *oiff;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
@@ -671,8 +632,10 @@ static int ocfs2_info_handle_freefrag(struct inode *inode,
 		goto out_err;
 	}
 
-	if (o2info_from_user(*oiff, req))
-		goto bail;
+	if (o2info_from_user(*oiff, req)) {
+		status = -EFAULT;
+		goto out_free;
+	}
 	/*
 	 * chunksize from userspace should be power of 2.
 	 */
@@ -711,14 +674,14 @@ static int ocfs2_info_handle_freefrag(struct inode *inode,
 
 	if (o2info_to_user(*oiff, req)) {
 		status = -EFAULT;
-		goto bail;
+		goto out_free;
 	}
 
 	status = 0;
 bail:
 	if (status)
 		o2info_set_request_error(&oiff->iff_req, req);
-
+out_free:
 	kfree(oiff);
 out_err:
 	return status;
@@ -727,23 +690,17 @@ out_err:
 static int ocfs2_info_handle_unknown(struct inode *inode,
 				     struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_request oir;
 
 	if (o2info_from_user(oir, req))
-		goto bail;
+		return -EFAULT;
 
 	o2info_clear_request_filled(&oir);
 
 	if (o2info_to_user(oir, req))
-		goto bail;
+		return -EFAULT;
 
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oir, req);
-
-	return status;
+	return 0;
 }
 
 /*