Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs fixes from Chris Mason:
 "The biggest of these comes from Liu Bo, who tracked down a hang we've
  been hitting since moving to kernel workqueues (it's a btrfs bug, not
  in the generic code).  His patch needs backporting to 3.16 and 3.15
  stable, which I'll send once this is in.

  Otherwise these are assorted fixes.  Most were integrated last week
  during KS, but I wanted to give everyone the chance to test the
  result, so I waited for rc2 to come out before sending"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (24 commits)
  Btrfs: fix task hang under heavy compressed write
  Btrfs: fix filemap_flush call in btrfs_file_release
  Btrfs: fix crash on endio of reading corrupted block
  btrfs: fix leak in qgroup_subtree_accounting() error path
  btrfs: Use right extent length when inserting overlap extent map.
  Btrfs: clone, don't create invalid hole extent map
  Btrfs: don't monopolize a core when evicting inode
  Btrfs: fix hole detection during file fsync
  Btrfs: ensure tmpfile inode is always persisted with link count of 0
  Btrfs: race free update of commit root for ro snapshots
  Btrfs: fix regression of btrfs device replace
  Btrfs: don't consider the missing device when allocating new chunks
  Btrfs: Fix wrong device size when we are resizing the device
  Btrfs: don't write any data into a readonly device when scrub
  Btrfs: Fix the problem that the replace destroys the seed filesystem
  btrfs: Return right extent when fiemap gives unaligned offset and len.
  Btrfs: fix wrong extent mapping for DirectIO
  Btrfs: fix wrong write range for filemap_fdatawrite_range()
  Btrfs: fix wrong missing device counter decrease
  Btrfs: fix unzeroed members in fs_devices when creating a fs from seed fs
  ...

17 files changed, 312 insertions, 135 deletions

diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 5a201d81049c..fbd76ded9a34 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 9c6b66d15fb0..e9e31c94758f 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 da775bfdebc9..a2e90f855d7d 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 d0ed9e664f7d..a1d36e62179c 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 102ed3143976..3efe1c3877bf 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 3e11aab9f391..af0359dcf337 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 d3afac292d67..36861b7a6757 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 03708ef3deef..9c194bd74d6e 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 47aceb494d1d..fce6fd0e3f50 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 963895c1f801..ac734ec4cc20 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 b497498484be..ded5c601d916 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 4a88f073fdd7..0a6b6e4bcbb9 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 09230cf3a244..20408c6b665a 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 b6d198f5181e..f4a41f37be22 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 78699364f537..12e53556e214 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 9e1f2cd5e67a..7e0e6e3029dd 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 6cb82f62cb7c..340a92d08e84 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;
 }