60 files changed, 843 insertions, 393 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index cfe512fd1caf..780725a463b1 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -68,16 +68,6 @@ source "fs/quota/Kconfig"
 source "fs/autofs4/Kconfig"
 source "fs/fuse/Kconfig"
 
-config CUSE
-        tristate "Character device in Userspace support"
-        depends on FUSE_FS
-        help
-          This FUSE extension allows character devices to be
-          implemented in userspace.
-
-          If you want to develop or use userspace character device
-          based on CUSE, answer Y or M.
-
 config GENERIC_ACL
         bool
         select FS_POSIX_ACL
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 0c42cdbabecf..49d0b43458b7 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -33,6 +33,7 @@
 #include <linux/elf.h>
 #include <linux/utsname.h>
 #include <linux/coredump.h>
+#include <linux/sched.h>
 #include <asm/uaccess.h>
 #include <asm/param.h>
 #include <asm/page.h>
@@ -1320,8 +1321,11 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
                 cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
                 cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
         } else {
-                cputime_to_timeval(p->utime, &prstatus->pr_utime);
-                cputime_to_timeval(p->stime, &prstatus->pr_stime);
+                cputime_t utime, stime;
+
+                task_cputime(p, &utime, &stime);
+                cputime_to_timeval(utime, &prstatus->pr_utime);
+                cputime_to_timeval(stime, &prstatus->pr_stime);
         }
         cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime);
         cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime);
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index dc84732e554f..cb240dd3b402 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1375,8 +1375,11 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
                 cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
                 cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
         } else {
-                cputime_to_timeval(p->utime, &prstatus->pr_utime);
-                cputime_to_timeval(p->stime, &prstatus->pr_stime);
+                cputime_t utime, stime;
+
+                task_cputime(p, &utime, &stime);
+                cputime_to_timeval(utime, &prstatus->pr_utime);
+                cputime_to_timeval(stime, &prstatus->pr_stime);
         }
         cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime);
         cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 521e9d4424f6..5a3327b8f90d 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3997,7 +3997,7 @@ again:
          * We make the other tasks wait for the flush only when we can flush
          * all things.
          */
-        if (ret && flush == BTRFS_RESERVE_FLUSH_ALL) {
+        if (ret && flush != BTRFS_RESERVE_NO_FLUSH) {
                 flushing = true;
                 space_info->flush = 1;
         }
@@ -4534,7 +4534,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
         unsigned nr_extents = 0;
         int extra_reserve = 0;
         enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL;
-        int ret;
+        int ret = 0;
         bool delalloc_lock = true;
 
         /* If we are a free space inode we need to not flush since we will be in
@@ -4579,20 +4579,18 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
         csum_bytes = BTRFS_I(inode)->csum_bytes;
         spin_unlock(&BTRFS_I(inode)->lock);
 
-        if (root->fs_info->quota_enabled) {
+        if (root->fs_info->quota_enabled)
                 ret = btrfs_qgroup_reserve(root, num_bytes +
                                            nr_extents * root->leafsize);
-                if (ret) {
-                        spin_lock(&BTRFS_I(inode)->lock);
-                        calc_csum_metadata_size(inode, num_bytes, 0);
-                        spin_unlock(&BTRFS_I(inode)->lock);
-                        if (delalloc_lock)
-                                mutex_unlock(&BTRFS_I(inode)->delalloc_mutex);
-                        return ret;
-                }
-        }
 
-        ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush);
+        /*
+         * ret != 0 here means the qgroup reservation failed, we go straight to
+         * the shared error handling then.
+         */
+        if (ret == 0)
+                ret = reserve_metadata_bytes(root, block_rsv,
+                                             to_reserve, flush);
+
         if (ret) {
                 u64 to_free = 0;
                 unsigned dropped;
@@ -5560,7 +5558,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
         int empty_cluster = 2 * 1024 * 1024;
         struct btrfs_space_info *space_info;
         int loop = 0;
-        int index = 0;
+        int index = __get_raid_index(data);
         int alloc_type = (data & BTRFS_BLOCK_GROUP_DATA) ?
                 RESERVE_ALLOC_NO_ACCOUNT : RESERVE_ALLOC;
         bool found_uncached_bg = false;
@@ -6788,11 +6786,13 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
                                                        &wc->flags[level]);
                         if (ret < 0) {
                                 btrfs_tree_unlock_rw(eb, path->locks[level]);
+                                path->locks[level] = 0;
                                 return ret;
                         }
                         BUG_ON(wc->refs[level] == 0);
                         if (wc->refs[level] == 1) {
                                 btrfs_tree_unlock_rw(eb, path->locks[level]);
+                                path->locks[level] = 0;
                                 return 1;
                         }
                 }
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index f169d6b11d7f..fdb7a8db3b57 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -171,6 +171,10 @@ static int mergable_maps(struct extent_map *prev, struct extent_map *next)
         if (test_bit(EXTENT_FLAG_COMPRESSED, &prev->flags))
                 return 0;
 
+        if (test_bit(EXTENT_FLAG_LOGGING, &prev->flags) ||
+            test_bit(EXTENT_FLAG_LOGGING, &next->flags))
+                return 0;
+
         if (extent_map_end(prev) == next->start &&
             prev->flags == next->flags &&
             prev->bdev == next->bdev &&
@@ -255,7 +259,8 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
         if (!em)
                 goto out;
 
-        list_move(&em->list, &tree->modified_extents);
+        if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
+                list_move(&em->list, &tree->modified_extents);
         em->generation = gen;
         clear_bit(EXTENT_FLAG_PINNED, &em->flags);
         em->mod_start = em->start;
@@ -280,6 +285,13 @@ out:
 
 }
 
+void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em)
+{
+        clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
+        if (em->in_tree)
+                try_merge_map(tree, em);
+}
+
 /**
  * add_extent_mapping - add new extent map to the extent tree
  * @tree:       tree to insert new map in
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index 922943ce29e8..c6598c89cff8 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -69,6 +69,7 @@ void free_extent_map(struct extent_map *em);
 int __init extent_map_init(void);
 void extent_map_exit(void);
 int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len, u64 gen);
+void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em);
 struct extent_map *search_extent_mapping(struct extent_map_tree *tree,
                                          u64 start, u64 len);
 #endif
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index bd38cef42358..94aa53b38721 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -460,8 +460,8 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
                 if (!contig)
                         offset = page_offset(bvec->bv_page) + bvec->bv_offset;
 
-                if (!contig && (offset >= ordered->file_offset + ordered->len ||
-                    offset < ordered->file_offset)) {
+                if (offset >= ordered->file_offset + ordered->len ||
+                    offset < ordered->file_offset) {
                         unsigned long bytes_left;
                         sums->len = this_sum_bytes;
                         this_sum_bytes = 0;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 77061bf43edb..aeb84469d2c4 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -293,15 +293,24 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
         struct btrfs_key key;
         struct btrfs_ioctl_defrag_range_args range;
         int num_defrag;
+        int index;
+        int ret;
 
         /* get the inode */
         key.objectid = defrag->root;
         btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
         key.offset = (u64)-1;
+
+        index = srcu_read_lock(&fs_info->subvol_srcu);
+
         inode_root = btrfs_read_fs_root_no_name(fs_info, &key);
         if (IS_ERR(inode_root)) {
-                kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
-                return PTR_ERR(inode_root);
+                ret = PTR_ERR(inode_root);
+                goto cleanup;
+        }
+        if (btrfs_root_refs(&inode_root->root_item) == 0) {
+                ret = -ENOENT;
+                goto cleanup;
         }
 
         key.objectid = defrag->ino;
@@ -309,9 +318,10 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
         key.offset = 0;
         inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL);
         if (IS_ERR(inode)) {
-                kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
-                return PTR_ERR(inode);
+                ret = PTR_ERR(inode);
+                goto cleanup;
         }
+        srcu_read_unlock(&fs_info->subvol_srcu, index);
 
         /* do a chunk of defrag */
         clear_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags);
@@ -346,6 +356,10 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 
         iput(inode);
         return 0;
+cleanup:
+        srcu_read_unlock(&fs_info->subvol_srcu, index);
+        kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
+        return ret;
 }
 
 /*
@@ -1594,9 +1608,10 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
                 if (err < 0 && num_written > 0)
                         num_written = err;
         }
-out:
+
         if (sync)
                 atomic_dec(&BTRFS_I(inode)->sync_writers);
+out:
         sb_end_write(inode->i_sb);
         current->backing_dev_info = NULL;
         return num_written ? num_written : err;
@@ -2241,6 +2256,7 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
         if (lockend <= lockstart)
                 lockend = lockstart + root->sectorsize;
 
+        lockend--;
         len = lockend - lockstart + 1;
 
         len = max_t(u64, len, root->sectorsize);
@@ -2307,9 +2323,12 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
                                         }
                                 }
 
-                                *offset = start;
-                                free_extent_map(em);
-                                break;
+                                if (!test_bit(EXTENT_FLAG_PREALLOC,
+                                              &em->flags)) {
+                                        *offset = start;
+                                        free_extent_map(em);
+                                        break;
+                                }
                         }
                 }
 
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 59ea2e4349c9..0be7a8742a43 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1862,11 +1862,13 @@ int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
 {
         struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
         struct btrfs_free_space *info;
-        int ret = 0;
+        int ret;
+        bool re_search = false;
 
         spin_lock(&ctl->tree_lock);
 
 again:
+        ret = 0;
         if (!bytes)
                 goto out_lock;
 
@@ -1879,17 +1881,17 @@ again:
                 info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset),
                                           1, 0);
                 if (!info) {
-                        /* the tree logging code might be calling us before we
-                         * have fully loaded the free space rbtree for this
-                         * block group.  So it is possible the entry won't
-                         * be in the rbtree yet at all.  The caching code
-                         * will make sure not to put it in the rbtree if
-                         * the logging code has pinned it.
+                        /*
+                         * If we found a partial bit of our free space in a
+                         * bitmap but then couldn't find the other part this may
+                         * be a problem, so WARN about it.
                          */
+                        WARN_ON(re_search);
                         goto out_lock;
                 }
         }
 
+        re_search = false;
         if (!info->bitmap) {
                 unlink_free_space(ctl, info);
                 if (offset == info->offset) {
@@ -1935,8 +1937,10 @@ again:
         }
 
         ret = remove_from_bitmap(ctl, info, &offset, &bytes);
-        if (ret == -EAGAIN)
+        if (ret == -EAGAIN) {
+                re_search = true;
                 goto again;
+        }
         BUG_ON(ret); /* logic error */
 out_lock:
         spin_unlock(&ctl->tree_lock);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 16d9e8e191e6..cc93b23ca352 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -88,7 +88,7 @@ static unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
         [S_IFLNK >> S_SHIFT]    = BTRFS_FT_SYMLINK,
 };
 
-static int btrfs_setsize(struct inode *inode, loff_t newsize);
+static int btrfs_setsize(struct inode *inode, struct iattr *attr);
 static int btrfs_truncate(struct inode *inode);
 static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent);
 static noinline int cow_file_range(struct inode *inode,
@@ -2478,6 +2478,18 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
                                 continue;
                         }
                         nr_truncate++;
+
+                        /* 1 for the orphan item deletion. */
+                        trans = btrfs_start_transaction(root, 1);
+                        if (IS_ERR(trans)) {
+                                ret = PTR_ERR(trans);
+                                goto out;
+                        }
+                        ret = btrfs_orphan_add(trans, inode);
+                        btrfs_end_transaction(trans, root);
+                        if (ret)
+                                goto out;
+
                         ret = btrfs_truncate(inode);
                 } else {
                         nr_unlink++;
@@ -3665,6 +3677,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
                                 block_end - cur_offset, 0);
                 if (IS_ERR(em)) {
                         err = PTR_ERR(em);
+                        em = NULL;
                         break;
                 }
                 last_byte = min(extent_map_end(em), block_end);
@@ -3748,16 +3761,27 @@ next:
         return err;
 }
 
-static int btrfs_setsize(struct inode *inode, loff_t newsize)
+static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 {
         struct btrfs_root *root = BTRFS_I(inode)->root;
         struct btrfs_trans_handle *trans;
         loff_t oldsize = i_size_read(inode);
+        loff_t newsize = attr->ia_size;
+        int mask = attr->ia_valid;
         int ret;
 
         if (newsize == oldsize)
                 return 0;
 
+        /*
+         * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
+         * special case where we need to update the times despite not having
+         * these flags set.  For all other operations the VFS set these flags
+         * explicitly if it wants a timestamp update.
+         */
+        if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME))))
+                inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb);
+
         if (newsize > oldsize) {
                 truncate_pagecache(inode, oldsize, newsize);
                 ret = btrfs_cont_expand(inode, oldsize, newsize);
@@ -3783,9 +3807,34 @@ static int btrfs_setsize(struct inode *inode, loff_t newsize)
                         set_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
                                 &BTRFS_I(inode)->runtime_flags);
 
+                /*
+                 * 1 for the orphan item we're going to add
+                 * 1 for the orphan item deletion.
+                 */
+                trans = btrfs_start_transaction(root, 2);
+                if (IS_ERR(trans))
+                        return PTR_ERR(trans);
+
+                /*
+                 * We need to do this in case we fail at _any_ point during the
+                 * actual truncate.  Once we do the truncate_setsize we could
+                 * invalidate pages which forces any outstanding ordered io to
+                 * be instantly completed which will give us extents that need
+                 * to be truncated.  If we fail to get an orphan inode down we
+                 * could have left over extents that were never meant to live,
+                 * so we need to garuntee from this point on that everything
+                 * will be consistent.
+                 */
+                ret = btrfs_orphan_add(trans, inode);
+                btrfs_end_transaction(trans, root);
+                if (ret)
+                        return ret;
+
                 /* we don't support swapfiles, so vmtruncate shouldn't fail */
                 truncate_setsize(inode, newsize);
                 ret = btrfs_truncate(inode);
+                if (ret && inode->i_nlink)
+                        btrfs_orphan_del(NULL, inode);
         }
 
         return ret;
@@ -3805,7 +3854,7 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
                 return err;
 
         if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
-                err = btrfs_setsize(inode, attr->ia_size);
+                err = btrfs_setsize(inode, attr);
                 if (err)
                         return err;
         }
@@ -5572,10 +5621,13 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag
                 return em;
         if (em) {
                 /*
-                 * if our em maps to a hole, there might
-                 * actually be delalloc bytes behind it
+                 * if our em maps to
+                 * -  a hole or
+                 * -  a pre-alloc extent,
+                 * there might actually be delalloc bytes behind it.
                  */
-                if (em->block_start != EXTENT_MAP_HOLE)
+                if (em->block_start != EXTENT_MAP_HOLE &&
+                    !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
                         return em;
                 else
                         hole_em = em;
@@ -5657,6 +5709,8 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag
                          */
                         em->block_start = hole_em->block_start;
                         em->block_len = hole_len;
+                        if (test_bit(EXTENT_FLAG_PREALLOC, &hole_em->flags))
+                                set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
                 } else {
                         em->start = range_start;
                         em->len = found;
@@ -6915,11 +6969,9 @@ static int btrfs_truncate(struct inode *inode)
 
         /*
          * 1 for the truncate slack space
-         * 1 for the orphan item we're going to add
-         * 1 for the orphan item deletion
          * 1 for updating the inode.
          */
-        trans = btrfs_start_transaction(root, 4);
+        trans = btrfs_start_transaction(root, 2);
         if (IS_ERR(trans)) {
                 err = PTR_ERR(trans);
                 goto out;
@@ -6930,12 +6982,6 @@ static int btrfs_truncate(struct inode *inode)
                                       min_size);
         BUG_ON(ret);
 
-        ret = btrfs_orphan_add(trans, inode);
-        if (ret) {
-                btrfs_end_transaction(trans, root);
-                goto out;
-        }
-
         /*
          * setattr is responsible for setting the ordered_data_close flag,
          * but that is only tested during the last file release.  That
@@ -7004,12 +7050,6 @@ static int btrfs_truncate(struct inode *inode)
                 ret = btrfs_orphan_del(trans, inode);
                 if (ret)
                         err = ret;
-        } else if (ret && inode->i_nlink > 0) {
-                /*
-                 * Failed to do the truncate, remove us from the in memory
-                 * orphan list.
-                 */
-                ret = btrfs_orphan_del(NULL, inode);
         }
 
         if (trans) {
@@ -7531,41 +7571,61 @@ void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work)
  */
 int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
 {
-        struct list_head *head = &root->fs_info->delalloc_inodes;
         struct btrfs_inode *binode;
         struct inode *inode;
         struct btrfs_delalloc_work *work, *next;
         struct list_head works;
+        struct list_head splice;
         int ret = 0;
 
         if (root->fs_info->sb->s_flags & MS_RDONLY)
                 return -EROFS;
 
         INIT_LIST_HEAD(&works);
-
+        INIT_LIST_HEAD(&splice);
+again:
         spin_lock(&root->fs_info->delalloc_lock);
-        while (!list_empty(head)) {
-                binode = list_entry(head->next, struct btrfs_inode,
+        list_splice_init(&root->fs_info->delalloc_inodes, &splice);
+        while (!list_empty(&splice)) {
+                binode = list_entry(splice.next, struct btrfs_inode,
                                     delalloc_inodes);
+
+                list_del_init(&binode->delalloc_inodes);
+
                 inode = igrab(&binode->vfs_inode);
                 if (!inode)
-                        list_del_init(&binode->delalloc_inodes);
+                        continue;
+
+                list_add_tail(&binode->delalloc_inodes,
+                              &root->fs_info->delalloc_inodes);
                 spin_unlock(&root->fs_info->delalloc_lock);
-                if (inode) {
-                        work = btrfs_alloc_delalloc_work(inode, 0, delay_iput);
-                        if (!work) {
-                                ret = -ENOMEM;
-                                goto out;
-                        }
-                        list_add_tail(&work->list, &works);
-                        btrfs_queue_worker(&root->fs_info->flush_workers,
-                                           &work->work);
+
+                work = btrfs_alloc_delalloc_work(inode, 0, delay_iput);
+                if (unlikely(!work)) {
+                        ret = -ENOMEM;
+                        goto out;
                 }
+                list_add_tail(&work->list, &works);
+                btrfs_queue_worker(&root->fs_info->flush_workers,
+                                   &work->work);
+
                 cond_resched();
                 spin_lock(&root->fs_info->delalloc_lock);
         }
         spin_unlock(&root->fs_info->delalloc_lock);
 
+        list_for_each_entry_safe(work, next, &works, list) {
+                list_del_init(&work->list);
+                btrfs_wait_and_free_delalloc_work(work);
+        }
+
+        spin_lock(&root->fs_info->delalloc_lock);
+        if (!list_empty(&root->fs_info->delalloc_inodes)) {
+                spin_unlock(&root->fs_info->delalloc_lock);
+                goto again;
+        }
+        spin_unlock(&root->fs_info->delalloc_lock);
+
         /* the filemap_flush will queue IO into the worker threads, but
          * we have to make sure the IO is actually started and that
          * ordered extents get created before we return
@@ -7578,11 +7638,18 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
                     atomic_read(&root->fs_info->async_delalloc_pages) == 0));
         }
         atomic_dec(&root->fs_info->async_submit_draining);
+        return 0;
 out:
         list_for_each_entry_safe(work, next, &works, list) {
                 list_del_init(&work->list);
                 btrfs_wait_and_free_delalloc_work(work);
         }
+
+        if (!list_empty_careful(&splice)) {
+                spin_lock(&root->fs_info->delalloc_lock);
+                list_splice_tail(&splice, &root->fs_info->delalloc_inodes);
+                spin_unlock(&root->fs_info->delalloc_lock);
+        }
         return ret;
 }
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 4b4516770f05..338f2597bf7f 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -515,7 +515,6 @@ static noinline int create_subvol(struct btrfs_root *root,
 
         BUG_ON(ret);
 
-        d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry));
 fail:
         if (async_transid) {
                 *async_transid = trans->transid;
@@ -525,6 +524,10 @@ fail:
         }
         if (err && !ret)
                 ret = err;
+
+        if (!ret)
+                d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry));
+
         return ret;
 }
 
@@ -1339,7 +1342,8 @@ static noinline int btrfs_ioctl_resize(struct file *file,
         if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
                         1)) {
                 pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
-                return -EINPROGRESS;
+                mnt_drop_write_file(file);
+                return -EINVAL;
         }
 
         mutex_lock(&root->fs_info->volume_mutex);
@@ -1362,6 +1366,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
                 printk(KERN_INFO "btrfs: resizing devid %llu\n",
                        (unsigned long long)devid);
         }
+
         device = btrfs_find_device(root->fs_info, devid, NULL, NULL);
         if (!device) {
                 printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
@@ -1369,9 +1374,10 @@ static noinline int btrfs_ioctl_resize(struct file *file,
                 ret = -EINVAL;
                 goto out_free;
         }
-        if (device->fs_devices && device->fs_devices->seeding) {
+
+        if (!device->writeable) {
                 printk(KERN_INFO "btrfs: resizer unable to apply on "
-                       "seeding device %llu\n",
+                       "readonly device %llu\n",
                        (unsigned long long)devid);
                 ret = -EINVAL;
                 goto out_free;
@@ -1443,8 +1449,8 @@ out_free:
         kfree(vol_args);
 out:
         mutex_unlock(&root->fs_info->volume_mutex);
-        mnt_drop_write_file(file);
         atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
+        mnt_drop_write_file(file);
         return ret;
 }
 
@@ -2095,13 +2101,13 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
                 err = inode_permission(inode, MAY_WRITE | MAY_EXEC);
                 if (err)
                         goto out_dput;
-
-                /* check if subvolume may be deleted by a non-root user */
-                err = btrfs_may_delete(dir, dentry, 1);
-                if (err)
-                        goto out_dput;
         }
 
+        /* check if subvolume may be deleted by a user */
+        err = btrfs_may_delete(dir, dentry, 1);
+        if (err)
+                goto out_dput;
+
         if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
                 err = -EINVAL;
                 goto out_dput;
@@ -2183,19 +2189,20 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
         struct btrfs_ioctl_defrag_range_args *range;
         int ret;
 
-        if (btrfs_root_readonly(root))
-                return -EROFS;
+        ret = mnt_want_write_file(file);
+        if (ret)
+                return ret;
 
         if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
                         1)) {
                 pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
-                return -EINPROGRESS;
+                mnt_drop_write_file(file);
+                return -EINVAL;
         }
-        ret = mnt_want_write_file(file);
-        if (ret) {
-                atomic_set(&root->fs_info->mutually_exclusive_operation_running,
-                           0);
-                return ret;
+
+        if (btrfs_root_readonly(root)) {
+                ret = -EROFS;
+                goto out;
         }
 
         switch (inode->i_mode & S_IFMT) {
@@ -2247,8 +2254,8 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
                 ret = -EINVAL;
         }
 out:
-        mnt_drop_write_file(file);
         atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
+        mnt_drop_write_file(file);
         return ret;
 }
 
@@ -2263,7 +2270,7 @@ static long btrfs_ioctl_add_dev(struct btrfs_root *root, void __user *arg)
         if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
                         1)) {
                 pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
-                return -EINPROGRESS;
+                return -EINVAL;
         }
 
         mutex_lock(&root->fs_info->volume_mutex);
@@ -2300,7 +2307,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
                         1)) {
                 pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
                 mnt_drop_write_file(file);
-                return -EINPROGRESS;
+                return -EINVAL;
         }
 
         mutex_lock(&root->fs_info->volume_mutex);
@@ -2316,8 +2323,8 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
         kfree(vol_args);
 out:
         mutex_unlock(&root->fs_info->volume_mutex);
-        mnt_drop_write_file(file);
         atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
+        mnt_drop_write_file(file);
         return ret;
 }
 
@@ -3437,8 +3444,8 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
         struct btrfs_fs_info *fs_info = root->fs_info;
         struct btrfs_ioctl_balance_args *bargs;
         struct btrfs_balance_control *bctl;
+        bool need_unlock; /* for mut. excl. ops lock */
         int ret;
-        int need_to_clear_lock = 0;
 
         if (!capable(CAP_SYS_ADMIN))
                 return -EPERM;
@@ -3447,14 +3454,61 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
         if (ret)
                 return ret;
 
-        mutex_lock(&fs_info->volume_mutex);
+again:
+        if (!atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1)) {
+                mutex_lock(&fs_info->volume_mutex);
+                mutex_lock(&fs_info->balance_mutex);
+                need_unlock = true;
+                goto locked;
+        }
+
+        /*
+         * mut. excl. ops lock is locked.  Three possibilites:
+         *   (1) some other op is running
+         *   (2) balance is running
+         *   (3) balance is paused -- special case (think resume)
+         */
         mutex_lock(&fs_info->balance_mutex);
+        if (fs_info->balance_ctl) {
+                /* this is either (2) or (3) */
+                if (!atomic_read(&fs_info->balance_running)) {
+                        mutex_unlock(&fs_info->balance_mutex);
+                        if (!mutex_trylock(&fs_info->volume_mutex))
+                                goto again;
+                        mutex_lock(&fs_info->balance_mutex);
+
+                        if (fs_info->balance_ctl &&
+                            !atomic_read(&fs_info->balance_running)) {
+                                /* this is (3) */
+                                need_unlock = false;
+                                goto locked;
+                        }
+
+                        mutex_unlock(&fs_info->balance_mutex);
+                        mutex_unlock(&fs_info->volume_mutex);
+                        goto again;
+                } else {
+                        /* this is (2) */
+                        mutex_unlock(&fs_info->balance_mutex);
+                        ret = -EINPROGRESS;
+                        goto out;
+                }
+        } else {
+                /* this is (1) */
+                mutex_unlock(&fs_info->balance_mutex);
+                pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
+                ret = -EINVAL;
+                goto out;
+        }
+
+locked:
+        BUG_ON(!atomic_read(&fs_info->mutually_exclusive_operation_running));
 
         if (arg) {
                 bargs = memdup_user(arg, sizeof(*bargs));
                 if (IS_ERR(bargs)) {
                         ret = PTR_ERR(bargs);
-                        goto out;
+                        goto out_unlock;
                 }
 
                 if (bargs->flags & BTRFS_BALANCE_RESUME) {
@@ -3474,13 +3528,10 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
                 bargs = NULL;
         }
 
-        if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
-                        1)) {
-                pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
+        if (fs_info->balance_ctl) {
                 ret = -EINPROGRESS;
                 goto out_bargs;
         }
-        need_to_clear_lock = 1;
 
         bctl = kzalloc(sizeof(*bctl), GFP_NOFS);
         if (!bctl) {
@@ -3501,11 +3552,17 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
         }
 
 do_balance:
-        ret = btrfs_balance(bctl, bargs);
         /*
-         * bctl is freed in __cancel_balance or in free_fs_info if
-         * restriper was paused all the way until unmount
+         * Ownership of bctl and mutually_exclusive_operation_running
+         * goes to to btrfs_balance.  bctl is freed in __cancel_balance,
+         * or, if restriper was paused all the way until unmount, in
+         * free_fs_info.  mutually_exclusive_operation_running is
+         * cleared in __cancel_balance.
          */
+        need_unlock = false;
+
+        ret = btrfs_balance(bctl, bargs);
+
         if (arg) {
                 if (copy_to_user(arg, bargs, sizeof(*bargs)))
                         ret = -EFAULT;
@@ -3513,12 +3570,12 @@ do_balance:
 
 out_bargs:
         kfree(bargs);
-out:
-        if (need_to_clear_lock)
-                atomic_set(&root->fs_info->mutually_exclusive_operation_running,
-                           0);
+out_unlock:
         mutex_unlock(&fs_info->balance_mutex);
         mutex_unlock(&fs_info->volume_mutex);
+        if (need_unlock)
+                atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+out:
         mnt_drop_write_file(file);
         return ret;
 }
@@ -3698,6 +3755,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
                 goto drop_write;
         }
 
+        if (!sa->qgroupid) {
+                ret = -EINVAL;
+                goto out;
+        }
+
         trans = btrfs_join_transaction(root);
         if (IS_ERR(trans)) {
                 ret = PTR_ERR(trans);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index f10731297040..e5ed56729607 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -836,9 +836,16 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
          * if the disk i_size is already at the inode->i_size, or
          * this ordered extent is inside the disk i_size, we're done
          */
-        if (disk_i_size == i_size || offset <= disk_i_size) {
+        if (disk_i_size == i_size)
+                goto out;
+
+        /*
+         * We still need to update disk_i_size if outstanding_isize is greater
+         * than disk_i_size.
+         */
+        if (offset <= disk_i_size &&
+            (!ordered || ordered->outstanding_isize <= disk_i_size))
                 goto out;
-        }
 
         /*
          * walk backward from this ordered extent to disk_i_size.
@@ -870,7 +877,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
                         break;
                 if (test->file_offset >= i_size)
                         break;
-                if (test->file_offset >= disk_i_size) {
+                if (entry_end(test) > disk_i_size) {
                         /*
                          * we don't update disk_i_size now, so record this
                          * undealt i_size. Or we will not know the real
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index fe9d02c45f8e..a5c856234323 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -379,6 +379,13 @@ next1:
 
                 ret = add_relation_rb(fs_info, found_key.objectid,
                                       found_key.offset);
+                if (ret == -ENOENT) {
+                        printk(KERN_WARNING
+                                "btrfs: orphan qgroup relation 0x%llx->0x%llx\n",
+                                (unsigned long long)found_key.objectid,
+                                (unsigned long long)found_key.offset);
+                        ret = 0;        /* ignore the error */
+                }
                 if (ret)
                         goto out;
 next2:
@@ -956,17 +963,28 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
                         struct btrfs_fs_info *fs_info, u64 qgroupid)
 {
         struct btrfs_root *quota_root;
+        struct btrfs_qgroup *qgroup;
         int ret = 0;
 
         quota_root = fs_info->quota_root;
         if (!quota_root)
                 return -EINVAL;
 
+        /* check if there are no relations to this qgroup */
+        spin_lock(&fs_info->qgroup_lock);
+        qgroup = find_qgroup_rb(fs_info, qgroupid);
+        if (qgroup) {
+                if (!list_empty(&qgroup->groups) || !list_empty(&qgroup->members)) {
+                        spin_unlock(&fs_info->qgroup_lock);
+                        return -EBUSY;
+                }
+        }
+        spin_unlock(&fs_info->qgroup_lock);
+
         ret = del_qgroup_item(trans, quota_root, qgroupid);
 
         spin_lock(&fs_info->qgroup_lock);
         del_qgroup_rb(quota_root->fs_info, qgroupid);
-
         spin_unlock(&fs_info->qgroup_lock);
 
         return ret;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index bdbb94f245c9..67783e03d121 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -580,20 +580,29 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
         int corrected = 0;
         struct btrfs_key key;
         struct inode *inode = NULL;
+        struct btrfs_fs_info *fs_info;
         u64 end = offset + PAGE_SIZE - 1;
         struct btrfs_root *local_root;
+        int srcu_index;
 
         key.objectid = root;
         key.type = BTRFS_ROOT_ITEM_KEY;
         key.offset = (u64)-1;
-        local_root = btrfs_read_fs_root_no_name(fixup->root->fs_info, &key);
-        if (IS_ERR(local_root))
+
+        fs_info = fixup->root->fs_info;
+        srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
+
+        local_root = btrfs_read_fs_root_no_name(fs_info, &key);
+        if (IS_ERR(local_root)) {
+                srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
                 return PTR_ERR(local_root);
+        }
 
         key.type = BTRFS_INODE_ITEM_KEY;
         key.objectid = inum;
         key.offset = 0;
-        inode = btrfs_iget(fixup->root->fs_info->sb, &key, local_root, NULL);
+        inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
+        srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
         if (IS_ERR(inode))
                 return PTR_ERR(inode);
 
@@ -606,7 +615,6 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
         }
 
         if (PageUptodate(page)) {
-                struct btrfs_fs_info *fs_info;
                 if (PageDirty(page)) {
                         /*
                          * we need to write the data to the defect sector. the
@@ -3180,18 +3188,25 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, void *ctx)
         u64 physical_for_dev_replace;
         u64 len;
         struct btrfs_fs_info *fs_info = nocow_ctx->sctx->dev_root->fs_info;
+        int srcu_index;
 
         key.objectid = root;
         key.type = BTRFS_ROOT_ITEM_KEY;
         key.offset = (u64)-1;
+
+        srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
+
         local_root = btrfs_read_fs_root_no_name(fs_info, &key);
-        if (IS_ERR(local_root))
+        if (IS_ERR(local_root)) {
+                srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
                 return PTR_ERR(local_root);
+        }
 
         key.type = BTRFS_INODE_ITEM_KEY;
         key.objectid = inum;
         key.offset = 0;
         inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
+        srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
         if (IS_ERR(inode))
                 return PTR_ERR(inode);
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 54454542ad40..321b7fb4e441 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1814,8 +1814,10 @@ static int name_cache_insert(struct send_ctx *sctx,
                         (unsigned long)nce->ino);
         if (!nce_head) {
                 nce_head = kmalloc(sizeof(*nce_head), GFP_NOFS);
-                if (!nce_head)
+                if (!nce_head) {
+                        kfree(nce);
                         return -ENOMEM;
+                }
                 INIT_LIST_HEAD(nce_head);
 
                 ret = radix_tree_insert(&sctx->name_cache, nce->ino, nce_head);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 99545df1b86c..d8982e9601d3 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -267,7 +267,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
                              function, line, errstr);
                 return;
         }
-        trans->transaction->aborted = errno;
+        ACCESS_ONCE(trans->transaction->aborted) = errno;
         __btrfs_std_error(root->fs_info, function, line, errno, NULL);
 }
 /*
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 87fac9a21ea5..fc03aa60b684 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -333,12 +333,14 @@ start_transaction(struct btrfs_root *root, u64 num_items, int type,
                                           &root->fs_info->trans_block_rsv,
                                           num_bytes, flush);
                 if (ret)
-                        return ERR_PTR(ret);
+                        goto reserve_fail;
         }
 again:
         h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS);
-        if (!h)
-                return ERR_PTR(-ENOMEM);
+        if (!h) {
+                ret = -ENOMEM;
+                goto alloc_fail;
+        }
 
         /*
          * If we are JOIN_NOLOCK we're already committing a transaction and
@@ -365,11 +367,7 @@ again:
         if (ret < 0) {
                 /* We must get the transaction if we are JOIN_NOLOCK. */
                 BUG_ON(type == TRANS_JOIN_NOLOCK);
-
-                if (type < TRANS_JOIN_NOLOCK)
-                        sb_end_intwrite(root->fs_info->sb);
-                kmem_cache_free(btrfs_trans_handle_cachep, h);
-                return ERR_PTR(ret);
+                goto join_fail;
         }
 
         cur_trans = root->fs_info->running_transaction;
@@ -410,6 +408,19 @@ got_it:
         if (!current->journal_info && type != TRANS_USERSPACE)
                 current->journal_info = h;
         return h;
+
+join_fail:
+        if (type < TRANS_JOIN_NOLOCK)
+                sb_end_intwrite(root->fs_info->sb);
+        kmem_cache_free(btrfs_trans_handle_cachep, h);
+alloc_fail:
+        if (num_bytes)
+                btrfs_block_rsv_release(root, &root->fs_info->trans_block_rsv,
+                                        num_bytes);
+reserve_fail:
+        if (qgroup_reserved)
+                btrfs_qgroup_free(root, qgroup_reserved);
+        return ERR_PTR(ret);
 }
 
 struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
@@ -1468,7 +1479,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
                 goto cleanup_transaction;
         }
 
-        if (cur_trans->aborted) {
+        /* Stop the commit early if ->aborted is set */
+        if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
                 ret = cur_trans->aborted;
                 goto cleanup_transaction;
         }
@@ -1574,6 +1586,11 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
         wait_event(cur_trans->writer_wait,
                    atomic_read(&cur_trans->num_writers) == 1);
 
+        /* ->aborted might be set after the previous check, so check it */
+        if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
+                ret = cur_trans->aborted;
+                goto cleanup_transaction;
+        }
         /*
          * the reloc mutex makes sure that we stop
          * the balancing code from coming in and moving
@@ -1657,6 +1674,17 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
                 goto cleanup_transaction;
         }
 
+        /*
+         * The tasks which save the space cache and inode cache may also
+         * update ->aborted, check it.
+         */
+        if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
+                ret = cur_trans->aborted;
+                mutex_unlock(&root->fs_info->tree_log_mutex);
+                mutex_unlock(&root->fs_info->reloc_mutex);
+                goto cleanup_transaction;
+        }
+
         btrfs_prepare_extent_commit(trans, root);
 
         cur_trans = root->fs_info->running_transaction;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 83186c7e45d4..9027bb1e7466 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3357,6 +3357,11 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
         if (skip_csum)
                 return 0;
 
+        if (em->compress_type) {
+                csum_offset = 0;
+                csum_len = block_len;
+        }
+
         /* block start is already adjusted for the file extent offset. */
         ret = btrfs_lookup_csums_range(log->fs_info->csum_root,
                                        em->block_start + csum_offset,
@@ -3410,13 +3415,13 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
                 em = list_entry(extents.next, struct extent_map, list);
 
                 list_del_init(&em->list);
-                clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
 
                 /*
                  * If we had an error we just need to delete everybody from our
                  * private list.
                  */
                 if (ret) {
+                        clear_em_logging(tree, em);
                         free_extent_map(em);
                         continue;
                 }
@@ -3424,8 +3429,9 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
                 write_unlock(&tree->lock);
 
                 ret = log_one_extent(trans, inode, root, em, path);
-                free_extent_map(em);
                 write_lock(&tree->lock);
+                clear_em_logging(tree, em);
+                free_extent_map(em);
         }
         WARN_ON(!list_empty(&extents));
         write_unlock(&tree->lock);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 5cce6aa74012..5cbb7f4b1672 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1431,7 +1431,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
                 }
         } else {
                 ret = btrfs_get_bdev_and_sb(device_path,
-                                            FMODE_READ | FMODE_EXCL,
+                                            FMODE_WRITE | FMODE_EXCL,
                                             root->fs_info->bdev_holder, 0,
                                             &bdev, &bh);
                 if (ret)
@@ -1556,7 +1556,8 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
         ret = 0;
 
         /* Notify udev that device has changed */
-        btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
+        if (bdev)
+                btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
 
 error_brelse:
         brelse(bh);
@@ -2614,7 +2615,14 @@ static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
         cache = btrfs_lookup_block_group(fs_info, chunk_offset);
         chunk_used = btrfs_block_group_used(&cache->item);
 
-        user_thresh = div_factor_fine(cache->key.offset, bargs->usage);
+        if (bargs->usage == 0)
+                user_thresh = 0;
+        else if (bargs->usage > 100)
+                user_thresh = cache->key.offset;
+        else
+                user_thresh = div_factor_fine(cache->key.offset,
+                                              bargs->usage);
+
         if (chunk_used < user_thresh)
                 ret = 0;
 
@@ -2959,6 +2967,8 @@ static void __cancel_balance(struct btrfs_fs_info *fs_info)
         unset_balance_control(fs_info);
         ret = del_balance_item(fs_info->tree_root);
         BUG_ON(ret);
+
+        atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
 }
 
 void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
@@ -3138,8 +3148,10 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 out:
         if (bctl->flags & BTRFS_BALANCE_RESUME)
                 __cancel_balance(fs_info);
-        else
+        else {
                 kfree(bctl);
+                atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+        }
         return ret;
 }
 
@@ -3156,7 +3168,6 @@ static int balance_kthread(void *data)
                 ret = btrfs_balance(fs_info->balance_ctl, NULL);
         }
 
-        atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
         mutex_unlock(&fs_info->balance_mutex);
         mutex_unlock(&fs_info->volume_mutex);
 
@@ -3179,7 +3190,6 @@ int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info)
                 return 0;
         }
 
-        WARN_ON(atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1));
         tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance");
         if (IS_ERR(tsk))
                 return PTR_ERR(tsk);
@@ -3233,6 +3243,8 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info)
         btrfs_balance_sys(leaf, item, &disk_bargs);
         btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs);
 
+        WARN_ON(atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1));
+
         mutex_lock(&fs_info->volume_mutex);
         mutex_lock(&fs_info->balance_mutex);
 
@@ -3496,7 +3508,7 @@ struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
         { 1, 1, 2, 2, 2, 2 /* raid1 */ },
         { 1, 2, 1, 1, 1, 2 /* dup */ },
         { 1, 1, 0, 2, 1, 1 /* raid0 */ },
-        { 1, 1, 0, 1, 1, 1 /* single */ },
+        { 1, 1, 1, 1, 1, 1 /* single */ },
 };
 
 static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index ce5cbd717bfc..210fce2df308 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -226,6 +226,8 @@ compose_mount_options_out:
 compose_mount_options_err:
         kfree(mountdata);
         mountdata = ERR_PTR(rc);
+        kfree(*devname);
+        *devname = NULL;
         goto compose_mount_options_out;
 }
 
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 17c3643e5950..12b3da39733b 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1917,7 +1917,7 @@ srcip_matches(struct sockaddr *srcaddr, struct sockaddr *rhs)
         }
         case AF_INET6: {
                 struct sockaddr_in6 *saddr6 = (struct sockaddr_in6 *)srcaddr;
-                struct sockaddr_in6 *vaddr6 = (struct sockaddr_in6 *)&rhs;
+                struct sockaddr_in6 *vaddr6 = (struct sockaddr_in6 *)rhs;
                 return ipv6_addr_equal(&saddr6->sin6_addr, &vaddr6->sin6_addr);
         }
         default:
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 7ff49852b0cb..911649a47dd5 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -503,11 +503,11 @@ static ssize_t device_write(struct file *file, const char __user *buf,
 #endif
                 return -EINVAL;
 
-#ifdef CONFIG_COMPAT
-        if (count > sizeof(struct dlm_write_request32) + DLM_RESNAME_MAXLEN)
-#else
+        /*
+         * can't compare against COMPAT/dlm_write_request32 because
+         * we don't yet know if is64bit is zero
+         */
         if (count > sizeof(struct dlm_write_request) + DLM_RESNAME_MAXLEN)
-#endif
                 return -EINVAL;
 
         kbuf = kzalloc(count + 1, GFP_NOFS);
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index e95b94945d5f..137af4255da6 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -191,15 +191,14 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
                 retval = f2fs_getxattr(inode, name_index, "", value, retval);
         }
 
-        if (retval < 0) {
-                if (retval == -ENODATA)
-                        acl = NULL;
-                else
-                        acl = ERR_PTR(retval);
-        } else {
+        if (retval > 0)
                 acl = f2fs_acl_from_disk(value, retval);
-        }
+        else if (retval == -ENODATA)
+                acl = NULL;
+        else
+                acl = ERR_PTR(retval);
         kfree(value);
+
         if (!IS_ERR(acl))
                 set_cached_acl(inode, type, acl);
 
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 6ef36c37e2be..ff3c8439af87 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -214,7 +214,6 @@ retry:
                 goto retry;
         }
         new->ino = ino;
-        INIT_LIST_HEAD(&new->list);
 
         /* add new_oentry into list which is sorted by inode number */
         if (orphan) {
@@ -772,7 +771,7 @@ void init_orphan_info(struct f2fs_sb_info *sbi)
         sbi->n_orphans = 0;
 }
 
-int create_checkpoint_caches(void)
+int __init create_checkpoint_caches(void)
 {
         orphan_entry_slab = f2fs_kmem_cache_create("f2fs_orphan_entry",
                         sizeof(struct orphan_inode_entry), NULL);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 3aa5ce7cab83..7bd22a201125 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -547,6 +547,15 @@ redirty_out:
 
 #define MAX_DESIRED_PAGES_WP    4096
 
+static int __f2fs_writepage(struct page *page, struct writeback_control *wbc,
+                        void *data)
+{
+        struct address_space *mapping = data;
+        int ret = mapping->a_ops->writepage(page, wbc);
+        mapping_set_error(mapping, ret);
+        return ret;
+}
+
 static int f2fs_write_data_pages(struct address_space *mapping,
                             struct writeback_control *wbc)
 {
@@ -563,7 +572,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 
         if (!S_ISDIR(inode->i_mode))
                 mutex_lock(&sbi->writepages);
-        ret = generic_writepages(mapping, wbc);
+        ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
         if (!S_ISDIR(inode->i_mode))
                 mutex_unlock(&sbi->writepages);
         f2fs_submit_bio(sbi, DATA, (wbc->sync_mode == WB_SYNC_ALL));
@@ -689,6 +698,11 @@ static int f2fs_set_data_page_dirty(struct page *page)
         return 0;
 }
 
+static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
+{
+        return generic_block_bmap(mapping, block, get_data_block_ro);
+}
+
 const struct address_space_operations f2fs_dblock_aops = {
         .readpage       = f2fs_read_data_page,
         .readpages      = f2fs_read_data_pages,
@@ -700,4 +714,5 @@ const struct address_space_operations f2fs_dblock_aops = {
         .invalidatepage = f2fs_invalidate_data_page,
         .releasepage    = f2fs_release_data_page,
         .direct_IO      = f2fs_direct_IO,
+        .bmap           = f2fs_bmap,
 };
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 0e0380a588ad..c8c37307b326 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -26,6 +26,7 @@
 
 static LIST_HEAD(f2fs_stat_list);
 static struct dentry *debugfs_root;
+static DEFINE_MUTEX(f2fs_stat_mutex);
 
 static void update_general_status(struct f2fs_sb_info *sbi)
 {
@@ -180,18 +181,14 @@ static int stat_show(struct seq_file *s, void *v)
         int i = 0;
         int j;
 
+        mutex_lock(&f2fs_stat_mutex);
         list_for_each_entry_safe(si, next, &f2fs_stat_list, stat_list) {
 
-                mutex_lock(&si->stat_lock);
-                if (!si->sbi) {
-                        mutex_unlock(&si->stat_lock);
-                        continue;
-                }
                 update_general_status(si->sbi);
 
                 seq_printf(s, "\n=====[ partition info. #%d ]=====\n", i++);
-                seq_printf(s, "[SB: 1] [CP: 2] [NAT: %d] [SIT: %d] ",
-                           si->nat_area_segs, si->sit_area_segs);
+                seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
+                           si->sit_area_segs, si->nat_area_segs);
                 seq_printf(s, "[SSA: %d] [MAIN: %d",
                            si->ssa_area_segs, si->main_area_segs);
                 seq_printf(s, "(OverProv:%d Resv:%d)]\n\n",
@@ -286,8 +283,8 @@ static int stat_show(struct seq_file *s, void *v)
                 seq_printf(s, "\nMemory: %u KB = static: %u + cached: %u\n",
                                 (si->base_mem + si->cache_mem) >> 10,
                                 si->base_mem >> 10, si->cache_mem >> 10);
-                mutex_unlock(&si->stat_lock);
         }
+        mutex_unlock(&f2fs_stat_mutex);
         return 0;
 }
 
@@ -303,7 +300,7 @@ static const struct file_operations stat_fops = {
         .release = single_release,
 };
 
-static int init_stats(struct f2fs_sb_info *sbi)
+int f2fs_build_stats(struct f2fs_sb_info *sbi)
 {
         struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
         struct f2fs_stat_info *si;
@@ -313,9 +310,6 @@ static int init_stats(struct f2fs_sb_info *sbi)
                 return -ENOMEM;
 
         si = sbi->stat_info;
-        mutex_init(&si->stat_lock);
-        list_add_tail(&si->stat_list, &f2fs_stat_list);
-
         si->all_area_segs = le32_to_cpu(raw_super->segment_count);
         si->sit_area_segs = le32_to_cpu(raw_super->segment_count_sit);
         si->nat_area_segs = le32_to_cpu(raw_super->segment_count_nat);
@@ -325,21 +319,11 @@ static int init_stats(struct f2fs_sb_info *sbi)
         si->main_area_zones = si->main_area_sections /
                                 le32_to_cpu(raw_super->secs_per_zone);
         si->sbi = sbi;
-        return 0;
-}
 
-int f2fs_build_stats(struct f2fs_sb_info *sbi)
-{
-        int retval;
-
-        retval = init_stats(sbi);
-        if (retval)
-                return retval;
-
-        if (!debugfs_root)
-                debugfs_root = debugfs_create_dir("f2fs", NULL);
+        mutex_lock(&f2fs_stat_mutex);
+        list_add_tail(&si->stat_list, &f2fs_stat_list);
+        mutex_unlock(&f2fs_stat_mutex);
 
-        debugfs_create_file("status", S_IRUGO, debugfs_root, NULL, &stat_fops);
         return 0;
 }
 
@@ -347,14 +331,22 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
 {
         struct f2fs_stat_info *si = sbi->stat_info;
 
+        mutex_lock(&f2fs_stat_mutex);
         list_del(&si->stat_list);
-        mutex_lock(&si->stat_lock);
-        si->sbi = NULL;
-        mutex_unlock(&si->stat_lock);
+        mutex_unlock(&f2fs_stat_mutex);
+
         kfree(sbi->stat_info);
 }
 
-void destroy_root_stats(void)
+void __init f2fs_create_root_stats(void)
+{
+        debugfs_root = debugfs_create_dir("f2fs", NULL);
+        if (debugfs_root)
+                debugfs_create_file("status", S_IRUGO, debugfs_root,
+                                         NULL, &stat_fops);
+}
+
+void f2fs_destroy_root_stats(void)
 {
         debugfs_remove_recursive(debugfs_root);
         debugfs_root = NULL;
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 951ed52748f6..989980e16d0b 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -503,7 +503,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
         }
 
         if (inode) {
-                inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+                inode->i_ctime = CURRENT_TIME;
                 drop_nlink(inode);
                 if (S_ISDIR(inode->i_mode)) {
                         drop_nlink(inode);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 13c6dfbb7183..c8e2d751ef9c 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -211,11 +211,11 @@ struct dnode_of_data {
 static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode,
                 struct page *ipage, struct page *npage, nid_t nid)
 {
+        memset(dn, 0, sizeof(*dn));
         dn->inode = inode;
         dn->inode_page = ipage;
         dn->node_page = npage;
         dn->nid = nid;
-        dn->inode_page_locked = 0;
 }
 
 /*
@@ -877,6 +877,8 @@ bool f2fs_empty_dir(struct inode *);
  * super.c
  */
 int f2fs_sync_fs(struct super_block *, int);
+extern __printf(3, 4)
+void f2fs_msg(struct super_block *, const char *, const char *, ...);
 
 /*
  * hash.c
@@ -912,7 +914,7 @@ int restore_node_summary(struct f2fs_sb_info *, unsigned int,
 void flush_nat_entries(struct f2fs_sb_info *);
 int build_node_manager(struct f2fs_sb_info *);
 void destroy_node_manager(struct f2fs_sb_info *);
-int create_node_manager_caches(void);
+int __init create_node_manager_caches(void);
 void destroy_node_manager_caches(void);
 
 /*
@@ -964,7 +966,7 @@ void sync_dirty_dir_inodes(struct f2fs_sb_info *);
 void block_operations(struct f2fs_sb_info *);
 void write_checkpoint(struct f2fs_sb_info *, bool, bool);
 void init_orphan_info(struct f2fs_sb_info *);
-int create_checkpoint_caches(void);
+int __init create_checkpoint_caches(void);
 void destroy_checkpoint_caches(void);
 
 /*
@@ -984,9 +986,9 @@ int do_write_data_page(struct page *);
 int start_gc_thread(struct f2fs_sb_info *);
 void stop_gc_thread(struct f2fs_sb_info *);
 block_t start_bidx_of_node(unsigned int);
-int f2fs_gc(struct f2fs_sb_info *, int);
+int f2fs_gc(struct f2fs_sb_info *);
 void build_gc_manager(struct f2fs_sb_info *);
-int create_gc_caches(void);
+int __init create_gc_caches(void);
 void destroy_gc_caches(void);
 
 /*
@@ -1058,7 +1060,8 @@ struct f2fs_stat_info {
 
 int f2fs_build_stats(struct f2fs_sb_info *);
 void f2fs_destroy_stats(struct f2fs_sb_info *);
-void destroy_root_stats(void);
+void __init f2fs_create_root_stats(void);
+void f2fs_destroy_root_stats(void);
 #else
 #define stat_inc_call_count(si)
 #define stat_inc_seg_count(si, type)
@@ -1068,7 +1071,8 @@ void destroy_root_stats(void);
 
 static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
 static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
-static inline void destroy_root_stats(void) { }
+static inline void __init f2fs_create_root_stats(void) { }
+static inline void f2fs_destroy_root_stats(void) { }
 #endif
 
 extern const struct file_operations f2fs_dir_operations;
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 7f9ea9271ebe..3191b52aafb0 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -96,8 +96,9 @@ out:
 }
 
 static const struct vm_operations_struct f2fs_file_vm_ops = {
-        .fault        = filemap_fault,
-        .page_mkwrite = f2fs_vm_page_mkwrite,
+        .fault          = filemap_fault,
+        .page_mkwrite   = f2fs_vm_page_mkwrite,
+        .remap_pages    = generic_file_remap_pages,
 };
 
 static int need_to_sync_dir(struct f2fs_sb_info *sbi, struct inode *inode)
@@ -137,6 +138,9 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
         if (ret)
                 return ret;
 
+        /* guarantee free sections for fsync */
+        f2fs_balance_fs(sbi);
+
         mutex_lock(&inode->i_mutex);
 
         if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
@@ -407,6 +411,8 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
                 struct dnode_of_data dn;
                 struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 
+                f2fs_balance_fs(sbi);
+
                 mutex_lock_op(sbi, DATA_TRUNC);
                 set_new_dnode(&dn, inode, NULL, NULL, 0);
                 err = get_dnode_of_data(&dn, index, RDONLY_NODE);
@@ -534,7 +540,6 @@ static long f2fs_fallocate(struct file *file, int mode,
                                 loff_t offset, loff_t len)
 {
         struct inode *inode = file->f_path.dentry->d_inode;
-        struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
         long ret;
 
         if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
@@ -545,7 +550,10 @@ static long f2fs_fallocate(struct file *file, int mode,
         else
                 ret = expand_inode_data(inode, offset, len, mode);
 
-        f2fs_balance_fs(sbi);
+        if (!ret) {
+                inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+                mark_inode_dirty(inode);
+        }
         return ret;
 }
 
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index b0ec721e984a..c386910dacc5 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -78,7 +78,7 @@ static int gc_thread_func(void *data)
 
                 sbi->bg_gc++;
 
-                if (f2fs_gc(sbi, 1) == GC_NONE)
+                if (f2fs_gc(sbi) == GC_NONE)
                         wait_ms = GC_THREAD_NOGC_SLEEP_TIME;
                 else if (wait_ms == GC_THREAD_NOGC_SLEEP_TIME)
                         wait_ms = GC_THREAD_MAX_SLEEP_TIME;
@@ -424,7 +424,11 @@ next_step:
 }
 
 /*
- * Calculate start block index that this node page contains
+ * Calculate start block index indicating the given node offset.
+ * Be careful, caller should give this node offset only indicating direct node
+ * blocks. If any node offsets, which point the other types of node blocks such
+ * as indirect or double indirect node blocks, are given, it must be a caller's
+ * bug.
  */
 block_t start_bidx_of_node(unsigned int node_ofs)
 {
@@ -651,62 +655,44 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
         return ret;
 }
 
-int f2fs_gc(struct f2fs_sb_info *sbi, int nGC)
+int f2fs_gc(struct f2fs_sb_info *sbi)
 {
-        unsigned int segno;
-        int old_free_secs, cur_free_secs;
-        int gc_status, nfree;
         struct list_head ilist;
+        unsigned int segno, i;
         int gc_type = BG_GC;
+        int gc_status = GC_NONE;
 
         INIT_LIST_HEAD(&ilist);
 gc_more:
-        nfree = 0;
-        gc_status = GC_NONE;
+        if (!(sbi->sb->s_flags & MS_ACTIVE))
+                goto stop;
 
         if (has_not_enough_free_secs(sbi))
-                old_free_secs = reserved_sections(sbi);
-        else
-                old_free_secs = free_sections(sbi);
-
-        while (sbi->sb->s_flags & MS_ACTIVE) {
-                int i;
-                if (has_not_enough_free_secs(sbi))
-                        gc_type = FG_GC;
+                gc_type = FG_GC;
 
-                cur_free_secs = free_sections(sbi) + nfree;
+        if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE))
+                goto stop;
 
-                /* We got free space successfully. */
-                if (nGC < cur_free_secs - old_free_secs)
-                        break;
-
-                if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE))
+        for (i = 0; i < sbi->segs_per_sec; i++) {
+                /*
+                 * do_garbage_collect will give us three gc_status:
+                 * GC_ERROR, GC_DONE, and GC_BLOCKED.
+                 * If GC is finished uncleanly, we have to return
+                 * the victim to dirty segment list.
+                 */
+                gc_status = do_garbage_collect(sbi, segno + i, &ilist, gc_type);
+                if (gc_status != GC_DONE)
                         break;
-
-                for (i = 0; i < sbi->segs_per_sec; i++) {
-                        /*
-                         * do_garbage_collect will give us three gc_status:
-                         * GC_ERROR, GC_DONE, and GC_BLOCKED.
-                         * If GC is finished uncleanly, we have to return
-                         * the victim to dirty segment list.
-                         */
-                        gc_status = do_garbage_collect(sbi, segno + i,
-                                        &ilist, gc_type);
-                        if (gc_status != GC_DONE)
-                                goto stop;
-                        nfree++;
-                }
         }
-stop:
-        if (has_not_enough_free_secs(sbi) || gc_status == GC_BLOCKED) {
+        if (has_not_enough_free_secs(sbi)) {
                 write_checkpoint(sbi, (gc_status == GC_BLOCKED), false);
-                if (nfree)
+                if (has_not_enough_free_secs(sbi))
                         goto gc_more;
         }
+stop:
         mutex_unlock(&sbi->gc_mutex);
 
         put_gc_inode(&ilist);
-        BUG_ON(!list_empty(&ilist));
         return gc_status;
 }
 
@@ -715,7 +701,7 @@ void build_gc_manager(struct f2fs_sb_info *sbi)
         DIRTY_I(sbi)->v_ops = &default_v_ops;
 }
 
-int create_gc_caches(void)
+int __init create_gc_caches(void)
 {
         winode_slab = f2fs_kmem_cache_create("f2fs_gc_inodes",
                         sizeof(struct inode_entry), NULL);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index bf20b4d03214..794241777322 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -217,6 +217,9 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
                         inode->i_ino == F2FS_META_INO(sbi))
                 return 0;
 
+        if (wbc)
+                f2fs_balance_fs(sbi);
+
         node_page = get_node_page(sbi, inode->i_ino);
         if (IS_ERR(node_page))
                 return PTR_ERR(node_page);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 5066bfd256c9..9bda63c9c166 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1124,6 +1124,12 @@ static int f2fs_write_node_page(struct page *page,
         return 0;
 }
 
+/*
+ * It is very important to gather dirty pages and write at once, so that we can
+ * submit a big bio without interfering other data writes.
+ * Be default, 512 pages (2MB), a segment size, is quite reasonable.
+ */
+#define COLLECT_DIRTY_NODES     512
 static int f2fs_write_node_pages(struct address_space *mapping,
                             struct writeback_control *wbc)
 {
@@ -1131,17 +1137,16 @@ static int f2fs_write_node_pages(struct address_space *mapping,
         struct block_device *bdev = sbi->sb->s_bdev;
         long nr_to_write = wbc->nr_to_write;
 
-        if (wbc->for_kupdate)
-                return 0;
-
-        if (get_pages(sbi, F2FS_DIRTY_NODES) == 0)
-                return 0;
-
+        /* First check balancing cached NAT entries */
         if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK)) {
                 write_checkpoint(sbi, false, false);
                 return 0;
         }
 
+        /* collect a number of dirty node pages and write together */
+        if (get_pages(sbi, F2FS_DIRTY_NODES) < COLLECT_DIRTY_NODES)
+                return 0;
+
         /* if mounting is failed, skip writing node pages */
         wbc->nr_to_write = bio_get_nr_vecs(bdev);
         sync_node_pages(sbi, 0, wbc);
@@ -1732,7 +1737,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
         kfree(nm_i);
 }
 
-int create_node_manager_caches(void)
+int __init create_node_manager_caches(void)
 {
         nat_entry_slab = f2fs_kmem_cache_create("nat_entry",
                         sizeof(struct nat_entry), NULL);
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index b571fee677d5..f42e4060b399 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -67,7 +67,7 @@ static int recover_dentry(struct page *ipage, struct inode *inode)
                 kunmap(page);
                 f2fs_put_page(page, 0);
         } else {
-                f2fs_add_link(&dent, inode);
+                err = f2fs_add_link(&dent, inode);
         }
         iput(dir);
 out:
@@ -151,7 +151,6 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
                                 goto out;
                         }
 
-                        INIT_LIST_HEAD(&entry->list);
                         list_add_tail(&entry->list, head);
                         entry->blkaddr = blkaddr;
                 }
@@ -174,10 +173,9 @@ out:
 static void destroy_fsync_dnodes(struct f2fs_sb_info *sbi,
                                         struct list_head *head)
 {
-        struct list_head *this;
-        struct fsync_inode_entry *entry;
-        list_for_each(this, head) {
-                entry = list_entry(this, struct fsync_inode_entry, list);
+        struct fsync_inode_entry *entry, *tmp;
+
+        list_for_each_entry_safe(entry, tmp, head, list) {
                 iput(entry->inode);
                 list_del(&entry->list);
                 kmem_cache_free(fsync_entry_slab, entry);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index de6240922b0a..4b0099066582 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -31,7 +31,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi)
          */
         if (has_not_enough_free_secs(sbi)) {
                 mutex_lock(&sbi->gc_mutex);
-                f2fs_gc(sbi, 1);
+                f2fs_gc(sbi);
         }
 }
 
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 08a94c814bdc..37fad04c8669 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -53,6 +53,18 @@ static match_table_t f2fs_tokens = {
         {Opt_err, NULL},
 };
 
+void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
+{
+        struct va_format vaf;
+        va_list args;
+
+        va_start(args, fmt);
+        vaf.fmt = fmt;
+        vaf.va = &args;
+        printk("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf);
+        va_end(args);
+}
+
 static void init_once(void *foo)
 {
         struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo;
@@ -125,6 +137,8 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
 
         if (sync)
                 write_checkpoint(sbi, false, false);
+        else
+                f2fs_balance_fs(sbi);
 
         return 0;
 }
@@ -247,7 +261,8 @@ static const struct export_operations f2fs_export_ops = {
         .get_parent = f2fs_get_parent,
 };
 
-static int parse_options(struct f2fs_sb_info *sbi, char *options)
+static int parse_options(struct super_block *sb, struct f2fs_sb_info *sbi,
+                                char *options)
 {
         substring_t args[MAX_OPT_ARGS];
         char *p;
@@ -286,7 +301,8 @@ static int parse_options(struct f2fs_sb_info *sbi, char *options)
                         break;
 #else
                 case Opt_nouser_xattr:
-                        pr_info("nouser_xattr options not supported\n");
+                        f2fs_msg(sb, KERN_INFO,
+                                "nouser_xattr options not supported");
                         break;
 #endif
 #ifdef CONFIG_F2FS_FS_POSIX_ACL
@@ -295,7 +311,7 @@ static int parse_options(struct f2fs_sb_info *sbi, char *options)
                         break;
 #else
                 case Opt_noacl:
-                        pr_info("noacl options not supported\n");
+                        f2fs_msg(sb, KERN_INFO, "noacl options not supported");
                         break;
 #endif
                 case Opt_active_logs:
@@ -309,8 +325,9 @@ static int parse_options(struct f2fs_sb_info *sbi, char *options)
                         set_opt(sbi, DISABLE_EXT_IDENTIFY);
                         break;
                 default:
-                        pr_err("Unrecognized mount option \"%s\" or missing value\n",
-                                        p);
+                        f2fs_msg(sb, KERN_ERR,
+                                "Unrecognized mount option \"%s\" or missing value",
+                                p);
                         return -EINVAL;
                 }
         }
@@ -337,23 +354,36 @@ static loff_t max_file_size(unsigned bits)
         return result;
 }
 
-static int sanity_check_raw_super(struct f2fs_super_block *raw_super)
+static int sanity_check_raw_super(struct super_block *sb,
+                        struct f2fs_super_block *raw_super)
 {
         unsigned int blocksize;
 
-        if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic))
+        if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
+                f2fs_msg(sb, KERN_INFO,
+                        "Magic Mismatch, valid(0x%x) - read(0x%x)",
+                        F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic));
                 return 1;
+        }
 
         /* Currently, support only 4KB block size */
         blocksize = 1 << le32_to_cpu(raw_super->log_blocksize);
-        if (blocksize != PAGE_CACHE_SIZE)
+        if (blocksize != PAGE_CACHE_SIZE) {
+                f2fs_msg(sb, KERN_INFO,
+                        "Invalid blocksize (%u), supports only 4KB\n",
+                        blocksize);
                 return 1;
+        }
         if (le32_to_cpu(raw_super->log_sectorsize) !=
-                                        F2FS_LOG_SECTOR_SIZE)
+                                        F2FS_LOG_SECTOR_SIZE) {
+                f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize");
                 return 1;
+        }
         if (le32_to_cpu(raw_super->log_sectors_per_block) !=
-                                        F2FS_LOG_SECTORS_PER_BLOCK)
+                                        F2FS_LOG_SECTORS_PER_BLOCK) {
+                f2fs_msg(sb, KERN_INFO, "Invalid log sectors per block");
                 return 1;
+        }
         return 0;
 }
 
@@ -413,14 +443,17 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
         if (!sbi)
                 return -ENOMEM;
 
-        /* set a temporary block size */
-        if (!sb_set_blocksize(sb, F2FS_BLKSIZE))
+        /* set a block size */
+        if (!sb_set_blocksize(sb, F2FS_BLKSIZE)) {
+                f2fs_msg(sb, KERN_ERR, "unable to set blocksize");
                 goto free_sbi;
+        }
 
         /* read f2fs raw super block */
         raw_super_buf = sb_bread(sb, 0);
         if (!raw_super_buf) {
                 err = -EIO;
+                f2fs_msg(sb, KERN_ERR, "unable to read superblock");
                 goto free_sbi;
         }
         raw_super = (struct f2fs_super_block *)
@@ -438,12 +471,14 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
         set_opt(sbi, POSIX_ACL);
 #endif
         /* parse mount options */
-        if (parse_options(sbi, (char *)data))
+        if (parse_options(sb, sbi, (char *)data))
                 goto free_sb_buf;
 
         /* sanity checking of raw super */
-        if (sanity_check_raw_super(raw_super))
+        if (sanity_check_raw_super(sb, raw_super)) {
+                f2fs_msg(sb, KERN_ERR, "Can't find a valid F2FS filesystem");
                 goto free_sb_buf;
+        }
 
         sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
         sb->s_max_links = F2FS_LINK_MAX;
@@ -477,18 +512,23 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
         /* get an inode for meta space */
         sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
         if (IS_ERR(sbi->meta_inode)) {
+                f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
                 err = PTR_ERR(sbi->meta_inode);
                 goto free_sb_buf;
         }
 
         err = get_valid_checkpoint(sbi);
-        if (err)
+        if (err) {
+                f2fs_msg(sb, KERN_ERR, "Failed to get valid F2FS checkpoint");
                 goto free_meta_inode;
+        }
 
         /* sanity checking of checkpoint */
         err = -EINVAL;
-        if (sanity_check_ckpt(raw_super, sbi->ckpt))
+        if (sanity_check_ckpt(raw_super, sbi->ckpt)) {
+                f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
                 goto free_cp;
+        }
 
         sbi->total_valid_node_count =
                                 le32_to_cpu(sbi->ckpt->valid_node_count);
@@ -502,25 +542,28 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
         INIT_LIST_HEAD(&sbi->dir_inode_list);
         spin_lock_init(&sbi->dir_inode_lock);
 
-        /* init super block */
-        if (!sb_set_blocksize(sb, sbi->blocksize))
-                goto free_cp;
-
         init_orphan_info(sbi);
 
         /* setup f2fs internal modules */
         err = build_segment_manager(sbi);
-        if (err)
+        if (err) {
+                f2fs_msg(sb, KERN_ERR,
+                        "Failed to initialize F2FS segment manager");
                 goto free_sm;
+        }
         err = build_node_manager(sbi);
-        if (err)
+        if (err) {
+                f2fs_msg(sb, KERN_ERR,
+                        "Failed to initialize F2FS node manager");
                 goto free_nm;
+        }
 
         build_gc_manager(sbi);
 
         /* get an inode for node space */
         sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi));
         if (IS_ERR(sbi->node_inode)) {
+                f2fs_msg(sb, KERN_ERR, "Failed to read node inode");
                 err = PTR_ERR(sbi->node_inode);
                 goto free_nm;
         }
@@ -533,6 +576,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
         /* read root inode and dentry */
         root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
         if (IS_ERR(root)) {
+                f2fs_msg(sb, KERN_ERR, "Failed to read root inode");
                 err = PTR_ERR(root);
                 goto free_node_inode;
         }
@@ -596,7 +640,7 @@ static struct file_system_type f2fs_fs_type = {
         .fs_flags       = FS_REQUIRES_DEV,
 };
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
         f2fs_inode_cachep = f2fs_kmem_cache_create("f2fs_inode_cache",
                         sizeof(struct f2fs_inode_info), NULL);
@@ -631,14 +675,17 @@ static int __init init_f2fs_fs(void)
         err = create_checkpoint_caches();
         if (err)
                 goto fail;
-        return register_filesystem(&f2fs_fs_type);
+        err = register_filesystem(&f2fs_fs_type);
+        if (err)
+                goto fail;
+        f2fs_create_root_stats();
 fail:
         return err;
 }
 
 static void __exit exit_f2fs_fs(void)
 {
-        destroy_root_stats();
+        f2fs_destroy_root_stats();
         unregister_filesystem(&f2fs_fs_type);
         destroy_checkpoint_caches();
         destroy_gc_caches();
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 940136a3d3a6..8038c0496504 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -318,6 +318,8 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
         if (name_len > 255 || value_len > MAX_VALUE_LEN)
                 return -ERANGE;
 
+        f2fs_balance_fs(sbi);
+
         mutex_lock_op(sbi, NODE_NEW);
         if (!fi->i_xattr_nid) {
                 /* Allocate new attribute block */
diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig
index 0cf160a94eda..1b2f6c2c3aaf 100644
--- a/fs/fuse/Kconfig
+++ b/fs/fuse/Kconfig
@@ -4,12 +4,24 @@ config FUSE_FS
           With FUSE it is possible to implement a fully functional filesystem
           in a userspace program.
 
-          There's also companion library: libfuse.  This library along with
-          utilities is available from the FUSE homepage:
+          There's also a companion library: libfuse2.  This library is available
+          from the FUSE homepage:
           <http://fuse.sourceforge.net/>
+          although chances are your distribution already has that library
+          installed if you've installed the "fuse" package itself.
 
           See <file:Documentation/filesystems/fuse.txt> for more information.
           See <file:Documentation/Changes> for needed library/utility version.
 
           If you want to develop a userspace FS, or if you want to use
           a filesystem based on FUSE, answer Y or M.
+
+config CUSE
+        tristate "Character device in Userspace support"
+        depends on FUSE_FS
+        help
+          This FUSE extension allows character devices to be
+          implemented in userspace.
+
+          If you want to develop or use a userspace character device
+          based on CUSE, answer Y or M.
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index ee8d55042298..e397b675b029 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -45,7 +45,6 @@
 #include <linux/miscdevice.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
-#include <linux/spinlock.h>
 #include <linux/stat.h>
 #include <linux/module.h>
 
@@ -63,7 +62,7 @@ struct cuse_conn {
         bool                    unrestricted_ioctl;
 };
 
-static DEFINE_SPINLOCK(cuse_lock);              /* protects cuse_conntbl */
+static DEFINE_MUTEX(cuse_lock);         /* protects registration */
 static struct list_head cuse_conntbl[CUSE_CONNTBL_LEN];
 static struct class *cuse_class;
 
@@ -114,14 +113,14 @@ static int cuse_open(struct inode *inode, struct file *file)
         int rc;
 
         /* look up and get the connection */
-        spin_lock(&cuse_lock);
+        mutex_lock(&cuse_lock);
         list_for_each_entry(pos, cuse_conntbl_head(devt), list)
                 if (pos->dev->devt == devt) {
                         fuse_conn_get(&pos->fc);
                         cc = pos;
                         break;
                 }
-        spin_unlock(&cuse_lock);
+        mutex_unlock(&cuse_lock);
 
         /* dead? */
         if (!cc)
@@ -267,7 +266,7 @@ static int cuse_parse_one(char **pp, char *end, char **keyp, char **valp)
 static int cuse_parse_devinfo(char *p, size_t len, struct cuse_devinfo *devinfo)
 {
         char *end = p + len;
-        char *key, *val;
+        char *uninitialized_var(key), *uninitialized_var(val);
         int rc;
 
         while (true) {
@@ -305,14 +304,14 @@ static void cuse_gendev_release(struct device *dev)
  */
 static void cuse_process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 {
-        struct cuse_conn *cc = fc_to_cc(fc);
+        struct cuse_conn *cc = fc_to_cc(fc), *pos;
         struct cuse_init_out *arg = req->out.args[0].value;
         struct page *page = req->pages[0];
         struct cuse_devinfo devinfo = { };
         struct device *dev;
         struct cdev *cdev;
         dev_t devt;
-        int rc;
+        int rc, i;
 
         if (req->out.h.error ||
             arg->major != FUSE_KERNEL_VERSION || arg->minor < 11) {
@@ -356,15 +355,24 @@ static void cuse_process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
         dev_set_drvdata(dev, cc);
         dev_set_name(dev, "%s", devinfo.name);
 
+        mutex_lock(&cuse_lock);
+
+        /* make sure the device-name is unique */
+        for (i = 0; i < CUSE_CONNTBL_LEN; ++i) {
+                list_for_each_entry(pos, &cuse_conntbl[i], list)
+                        if (!strcmp(dev_name(pos->dev), dev_name(dev)))
+                                goto err_unlock;
+        }
+
         rc = device_add(dev);
         if (rc)
-                goto err_device;
+                goto err_unlock;
 
         /* register cdev */
         rc = -ENOMEM;
         cdev = cdev_alloc();
         if (!cdev)
-                goto err_device;
+                goto err_unlock;
 
         cdev->owner = THIS_MODULE;
         cdev->ops = &cuse_frontend_fops;
@@ -377,9 +385,8 @@ static void cuse_process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
         cc->cdev = cdev;
 
         /* make the device available */
-        spin_lock(&cuse_lock);
         list_add(&cc->list, cuse_conntbl_head(devt));
-        spin_unlock(&cuse_lock);
+        mutex_unlock(&cuse_lock);
 
         /* announce device availability */
         dev_set_uevent_suppress(dev, 0);
@@ -391,7 +398,8 @@ out:
 
 err_cdev:
         cdev_del(cdev);
-err_device:
+err_unlock:
+        mutex_unlock(&cuse_lock);
         put_device(dev);
 err_region:
         unregister_chrdev_region(devt, 1);
@@ -520,9 +528,9 @@ static int cuse_channel_release(struct inode *inode, struct file *file)
         int rc;
 
         /* remove from the conntbl, no more access from this point on */
-        spin_lock(&cuse_lock);
+        mutex_lock(&cuse_lock);
         list_del_init(&cc->list);
-        spin_unlock(&cuse_lock);
+        mutex_unlock(&cuse_lock);
 
         /* remove device */
         if (cc->dev)
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index c16335315e5d..e83351aa5bad 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -692,8 +692,6 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
         struct page *oldpage = *pagep;
         struct page *newpage;
         struct pipe_buffer *buf = cs->pipebufs;
-        struct address_space *mapping;
-        pgoff_t index;
 
         unlock_request(cs->fc, cs->req);
         fuse_copy_finish(cs);
@@ -724,9 +722,6 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
         if (fuse_check_page(newpage) != 0)
                 goto out_fallback_unlock;
 
-        mapping = oldpage->mapping;
-        index = oldpage->index;
-
         /*
          * This is a new and locked page, it shouldn't be mapped or
          * have any special flags on it
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index e21d4d8f87e3..f3ab824fa302 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2177,8 +2177,8 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
         return ret;
 }
 
-long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
-                            loff_t length)
+static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
+                                loff_t length)
 {
         struct fuse_file *ff = file->private_data;
         struct fuse_conn *fc = ff->fc;
@@ -2213,7 +2213,6 @@ long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
 
         return err;
 }
-EXPORT_SYMBOL_GPL(fuse_file_fallocate);
 
 static const struct file_operations fuse_file_operations = {
         .llseek         = fuse_file_llseek,
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index b906ed17a839..9802de0f85e6 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -281,6 +281,7 @@ static void gdlm_put_lock(struct gfs2_glock *gl)
 {
         struct gfs2_sbd *sdp = gl->gl_sbd;
         struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+        int lvb_needs_unlock = 0;
         int error;
 
         if (gl->gl_lksb.sb_lkid == 0) {
@@ -294,8 +295,12 @@ static void gdlm_put_lock(struct gfs2_glock *gl)
         gfs2_update_request_times(gl);
 
         /* don't want to skip dlm_unlock writing the lvb when lock is ex */
+
+        if (gl->gl_lksb.sb_lvbptr && (gl->gl_state == LM_ST_EXCLUSIVE))
+                lvb_needs_unlock = 1;
+
         if (test_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags) &&
-            gl->gl_lksb.sb_lvbptr && (gl->gl_state != LM_ST_EXCLUSIVE)) {
+            !lvb_needs_unlock) {
                 gfs2_glock_free(gl);
                 return;
         }
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index dd057bc6b65b..fc8dc20fdeb9 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -177,11 +177,31 @@ out_nofree:
         return mnt;
 }
 
+static int
+nfs_namespace_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+{
+        if (NFS_FH(dentry->d_inode)->size != 0)
+                return nfs_getattr(mnt, dentry, stat);
+        generic_fillattr(dentry->d_inode, stat);
+        return 0;
+}
+
+static int
+nfs_namespace_setattr(struct dentry *dentry, struct iattr *attr)
+{
+        if (NFS_FH(dentry->d_inode)->size != 0)
+                return nfs_setattr(dentry, attr);
+        return -EACCES;
+}
+
 const struct inode_operations nfs_mountpoint_inode_operations = {
         .getattr        = nfs_getattr,
+        .setattr        = nfs_setattr,
 };
 
 const struct inode_operations nfs_referral_inode_operations = {
+        .getattr        = nfs_namespace_getattr,
+        .setattr        = nfs_namespace_setattr,
 };
 
 static void nfs_expire_automounts(struct work_struct *work)
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index acc347268124..2e9779b58b7a 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -236,11 +236,10 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
         error = nfs4_discover_server_trunking(clp, &old);
         if (error < 0)
                 goto error;
+        nfs_put_client(clp);
         if (clp != old) {
                 clp->cl_preserve_clid = true;
-                nfs_put_client(clp);
                 clp = old;
-                atomic_inc(&clp->cl_count);
         }
 
         return clp;
@@ -306,7 +305,7 @@ int nfs40_walk_client_list(struct nfs_client *new,
                 .clientid       = new->cl_clientid,
                 .confirm        = new->cl_confirm,
         };
-        int status;
+        int status = -NFS4ERR_STALE_CLIENTID;
 
         spin_lock(&nn->nfs_client_lock);
         list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
@@ -332,40 +331,33 @@ int nfs40_walk_client_list(struct nfs_client *new,
 
                 if (prev)
                         nfs_put_client(prev);
+                prev = pos;
 
                 status = nfs4_proc_setclientid_confirm(pos, &clid, cred);
-                if (status == 0) {
+                switch (status) {
+                case -NFS4ERR_STALE_CLIENTID:
+                        break;
+                case 0:
                         nfs4_swap_callback_idents(pos, new);
 
-                        nfs_put_client(pos);
+                        prev = NULL;
                         *result = pos;
                         dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
                                 __func__, pos, atomic_read(&pos->cl_count));
-                        return 0;
-                }
-                if (status != -NFS4ERR_STALE_CLIENTID) {
-                        nfs_put_client(pos);
-                        dprintk("NFS: <-- %s status = %d, no result\n",
-                                __func__, status);
-                        return status;
+                default:
+                        goto out;
                 }
 
                 spin_lock(&nn->nfs_client_lock);
-                prev = pos;
         }
+        spin_unlock(&nn->nfs_client_lock);
 
-        /*
-         * No matching nfs_client found.  This should be impossible,
-         * because the new nfs_client has already been added to
-         * nfs_client_list by nfs_get_client().
-         *
-         * Don't BUG(), since the caller is holding a mutex.
-         */
+        /* No match found. The server lost our clientid */
+out:
         if (prev)
                 nfs_put_client(prev);
-        spin_unlock(&nn->nfs_client_lock);
-        pr_err("NFS: %s Error: no matching nfs_client found\n", __func__);
-        return -NFS4ERR_STALE_CLIENTID;
+        dprintk("NFS: <-- %s status = %d\n", __func__, status);
+        return status;
 }
 
 #ifdef CONFIG_NFS_V4_1
@@ -432,7 +424,7 @@ int nfs41_walk_client_list(struct nfs_client *new,
 {
         struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
         struct nfs_client *pos, *n, *prev = NULL;
-        int error;
+        int status = -NFS4ERR_STALE_CLIENTID;
 
         spin_lock(&nn->nfs_client_lock);
         list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
@@ -448,14 +440,17 @@ int nfs41_walk_client_list(struct nfs_client *new,
                                 nfs_put_client(prev);
                         prev = pos;
 
-                        error = nfs_wait_client_init_complete(pos);
-                        if (error < 0) {
+                        nfs4_schedule_lease_recovery(pos);
+                        status = nfs_wait_client_init_complete(pos);
+                        if (status < 0) {
                                 nfs_put_client(pos);
                                 spin_lock(&nn->nfs_client_lock);
                                 continue;
                         }
-
+                        status = pos->cl_cons_state;
                         spin_lock(&nn->nfs_client_lock);
+                        if (status < 0)
+                                continue;
                 }
 
                 if (pos->rpc_ops != new->rpc_ops)
@@ -473,6 +468,7 @@ int nfs41_walk_client_list(struct nfs_client *new,
                 if (!nfs4_match_serverowners(pos, new))
                         continue;
 
+                atomic_inc(&pos->cl_count);
                 spin_unlock(&nn->nfs_client_lock);
                 dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
                         __func__, pos, atomic_read(&pos->cl_count));
@@ -481,16 +477,10 @@ int nfs41_walk_client_list(struct nfs_client *new,
                 return 0;
         }
 
-        /*
-         * No matching nfs_client found.  This should be impossible,
-         * because the new nfs_client has already been added to
-         * nfs_client_list by nfs_get_client().
-         *
-         * Don't BUG(), since the caller is holding a mutex.
-         */
+        /* No matching nfs_client found. */
         spin_unlock(&nn->nfs_client_lock);
-        pr_err("NFS: %s Error: no matching nfs_client found\n", __func__);
-        return -NFS4ERR_STALE_CLIENTID;
+        dprintk("NFS: <-- %s status = %d\n", __func__, status);
+        return status;
 }
 #endif  /* CONFIG_NFS_V4_1 */
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 9448c579d41a..e61f68d5ef21 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -136,16 +136,11 @@ int nfs40_discover_server_trunking(struct nfs_client *clp,
         clp->cl_confirm = clid.confirm;
 
         status = nfs40_walk_client_list(clp, result, cred);
-        switch (status) {
-        case -NFS4ERR_STALE_CLIENTID:
-                set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
-        case 0:
+        if (status == 0) {
                 /* Sustain the lease, even if it's empty.  If the clientid4
                  * goes stale it's of no use for trunking discovery. */
                 nfs4_schedule_state_renewal(*result);
-                break;
         }
-
 out:
         return status;
 }
@@ -1863,6 +1858,7 @@ again:
         case -ETIMEDOUT:
         case -EAGAIN:
                 ssleep(1);
+        case -NFS4ERR_STALE_CLIENTID:
                 dprintk("NFS: %s after status %d, retrying\n",
                         __func__, status);
                 goto again;
@@ -2022,8 +2018,18 @@ static int nfs4_reset_session(struct nfs_client *clp)
         nfs4_begin_drain_session(clp);
         cred = nfs4_get_exchange_id_cred(clp);
         status = nfs4_proc_destroy_session(clp->cl_session, cred);
-        if (status && status != -NFS4ERR_BADSESSION &&
-            status != -NFS4ERR_DEADSESSION) {
+        switch (status) {
+        case 0:
+        case -NFS4ERR_BADSESSION:
+        case -NFS4ERR_DEADSESSION:
+                break;
+        case -NFS4ERR_BACK_CHAN_BUSY:
+        case -NFS4ERR_DELAY:
+                set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+                status = 0;
+                ssleep(1);
+                goto out;
+        default:
                 status = nfs4_recovery_handle_error(clp, status);
                 goto out;
         }
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 2e7e8c878e5d..b056b1628722 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2589,27 +2589,23 @@ nfs_xdev_mount(struct file_system_type *fs_type, int flags,
         struct nfs_server *server;
         struct dentry *mntroot = ERR_PTR(-ENOMEM);
         struct nfs_subversion *nfs_mod = NFS_SB(data->sb)->nfs_client->cl_nfs_mod;
-        int error;
 
-        dprintk("--> nfs_xdev_mount_common()\n");
+        dprintk("--> nfs_xdev_mount()\n");
 
         mount_info.mntfh = mount_info.cloned->fh;
 
         /* create a new volume representation */
         server = nfs_mod->rpc_ops->clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor);
-        if (IS_ERR(server)) {
-                error = PTR_ERR(server);
-                goto out_err;
-        }
 
-        mntroot = nfs_fs_mount_common(server, flags, dev_name, &mount_info, nfs_mod);
-        dprintk("<-- nfs_xdev_mount_common() = 0\n");
-out:
-        return mntroot;
+        if (IS_ERR(server))
+                mntroot = ERR_CAST(server);
+        else
+                mntroot = nfs_fs_mount_common(server, flags,
+                                dev_name, &mount_info, nfs_mod);
 
-out_err:
-        dprintk("<-- nfs_xdev_mount_common() = %d [error]\n", error);
-        goto out;
+        dprintk("<-- nfs_xdev_mount() = %ld\n",
+                        IS_ERR(mntroot) ? PTR_ERR(mntroot) : 0L);
+        return mntroot;
 }
 
 #if IS_ENABLED(CONFIG_NFS_V4)
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index fdb180769485..f3859354e41a 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -664,8 +664,11 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp,
         if (ret < 0)
                 printk(KERN_ERR "NILFS: GC failed during preparation: "
                         "cannot read source blocks: err=%d\n", ret);
-        else
+        else {
+                if (nilfs_sb_need_update(nilfs))
+                        set_nilfs_discontinued(nilfs);
                 ret = nilfs_clean_segments(inode->i_sb, argv, kbufs);
+        }
 
         nilfs_remove_all_gcinodes(nilfs);
         clear_nilfs_gc_running(nilfs);
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 6a91e6ffbcbd..f7ed9ee46eb9 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -449,7 +449,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
                         do {
                                 min_flt += t->min_flt;
                                 maj_flt += t->maj_flt;
-                                gtime += t->gtime;
+                                gtime += task_gtime(t);
                                 t = next_thread(t);
                         } while (t != task);
 
@@ -472,7 +472,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
                 min_flt = task->min_flt;
                 maj_flt = task->maj_flt;
                 task_cputime_adjusted(task, &utime, &stime);
-                gtime = task->gtime;
+                gtime = task_gtime(task);
         }
 
         /* scale priority and nice values from timeslices to -20..20 */
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 7003e5266f25..288f068740f6 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -167,12 +167,16 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz)
 {
         char *hdr;
-        struct timeval timestamp;
+        struct timespec timestamp;
         size_t len;
 
-        do_gettimeofday(&timestamp);
+        /* Report zeroed timestamp if called before timekeeping has resumed. */
+        if (__getnstimeofday(&timestamp)) {
+                timestamp.tv_sec = 0;
+                timestamp.tv_nsec = 0;
+        }
         hdr = kasprintf(GFP_ATOMIC, RAMOOPS_KERNMSG_HDR "%lu.%lu\n",
-                (long)timestamp.tv_sec, (long)timestamp.tv_usec);
+                (long)timestamp.tv_sec, (long)(timestamp.tv_nsec / 1000));
         WARN_ON_ONCE(!hdr);
         len = hdr ? strlen(hdr) : 0;
         persistent_ram_write(prz, hdr, len);
diff --git a/fs/select.c b/fs/select.c
index 2ef72d965036..8c1c96c27062 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -26,6 +26,7 @@
 #include <linux/fs.h>
 #include <linux/rcupdate.h>
 #include <linux/hrtimer.h>
+#include <linux/sched/rt.h>
 
 #include <asm/uaccess.h>
 
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index 2df555c66d57..aec3d5c98c94 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -205,6 +205,48 @@ void sysfs_unmerge_group(struct kobject *kobj,
 }
 EXPORT_SYMBOL_GPL(sysfs_unmerge_group);
 
+/**
+ * sysfs_add_link_to_group - add a symlink to an attribute group.
+ * @kobj:       The kobject containing the group.
+ * @group_name: The name of the group.
+ * @target:     The target kobject of the symlink to create.
+ * @link_name:  The name of the symlink to create.
+ */
+int sysfs_add_link_to_group(struct kobject *kobj, const char *group_name,
+                            struct kobject *target, const char *link_name)
+{
+        struct sysfs_dirent *dir_sd;
+        int error = 0;
+
+        dir_sd = sysfs_get_dirent(kobj->sd, NULL, group_name);
+        if (!dir_sd)
+                return -ENOENT;
+
+        error = sysfs_create_link_sd(dir_sd, target, link_name);
+        sysfs_put(dir_sd);
+
+        return error;
+}
+EXPORT_SYMBOL_GPL(sysfs_add_link_to_group);
+
+/**
+ * sysfs_remove_link_from_group - remove a symlink from an attribute group.
+ * @kobj:       The kobject containing the group.
+ * @group_name: The name of the group.
+ * @link_name:  The name of the symlink to remove.
+ */
+void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name,
+                                  const char *link_name)
+{
+        struct sysfs_dirent *dir_sd;
+
+        dir_sd = sysfs_get_dirent(kobj->sd, NULL, group_name);
+        if (dir_sd) {
+                sysfs_hash_and_remove(dir_sd, NULL, link_name);
+                sysfs_put(dir_sd);
+        }
+}
+EXPORT_SYMBOL_GPL(sysfs_remove_link_from_group);
 
 EXPORT_SYMBOL_GPL(sysfs_create_group);
 EXPORT_SYMBOL_GPL(sysfs_update_group);
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index 3c9eb5624f5e..8c940df97a52 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -21,26 +21,17 @@
 
 #include "sysfs.h"
 
-static int sysfs_do_create_link(struct kobject *kobj, struct kobject *target,
-                                const char *name, int warn)
+static int sysfs_do_create_link_sd(struct sysfs_dirent *parent_sd,
+                                   struct kobject *target,
+                                   const char *name, int warn)
 {
-        struct sysfs_dirent *parent_sd = NULL;
         struct sysfs_dirent *target_sd = NULL;
         struct sysfs_dirent *sd = NULL;
         struct sysfs_addrm_cxt acxt;
         enum kobj_ns_type ns_type;
         int error;
 
-        BUG_ON(!name);
-
-        if (!kobj)
-                parent_sd = &sysfs_root;
-        else
-                parent_sd = kobj->sd;
-
-        error = -EFAULT;
-        if (!parent_sd)
-                goto out_put;
+        BUG_ON(!name || !parent_sd);
 
         /* target->sd can go away beneath us but is protected with
          * sysfs_assoc_lock.  Fetch target_sd from it.
@@ -96,6 +87,34 @@ static int sysfs_do_create_link(struct kobject *kobj, struct kobject *target,
 }
 
 /**
+ *      sysfs_create_link_sd - create symlink to a given object.
+ *      @sd:            directory we're creating the link in.
+ *      @target:        object we're pointing to.
+ *      @name:          name of the symlink.
+ */
+int sysfs_create_link_sd(struct sysfs_dirent *sd, struct kobject *target,
+                         const char *name)
+{
+        return sysfs_do_create_link_sd(sd, target, name, 1);
+}
+
+static int sysfs_do_create_link(struct kobject *kobj, struct kobject *target,
+                                const char *name, int warn)
+{
+        struct sysfs_dirent *parent_sd = NULL;
+
+        if (!kobj)
+                parent_sd = &sysfs_root;
+        else
+                parent_sd = kobj->sd;
+
+        if (!parent_sd)
+                return -EFAULT;
+
+        return sysfs_do_create_link_sd(parent_sd, target, name, warn);
+}
+
+/**
  *      sysfs_create_link - create symlink between two objects.
  *      @kobj:  object whose directory we're creating the link in.
  *      @target:        object we're pointing to.
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index d73c0932bbd6..d1e4043eb0c3 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -240,3 +240,5 @@ void unmap_bin_file(struct sysfs_dirent *attr_sd);
  * symlink.c
  */
 extern const struct inode_operations sysfs_symlink_inode_operations;
+int sysfs_create_link_sd(struct sysfs_dirent *sd, struct kobject *target,
+                         const char *name);
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 4111a40ebe1a..5f707e537171 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -86,11 +86,11 @@ xfs_destroy_ioend(
         }
 
         if (ioend->io_iocb) {
+                inode_dio_done(ioend->io_inode);
                 if (ioend->io_isasync) {
                         aio_complete(ioend->io_iocb, ioend->io_error ?
                                         ioend->io_error : ioend->io_result, 0);
                 }
-                inode_dio_done(ioend->io_inode);
         }
 
         mempool_free(ioend, xfs_ioend_pool);
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 0e92d12765d2..cdb2d3348583 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -4680,9 +4680,6 @@ __xfs_bmapi_allocate(
                         return error;
         }
 
-        if (bma->flags & XFS_BMAPI_STACK_SWITCH)
-                bma->stack_switch = 1;
-
         error = xfs_bmap_alloc(bma);
         if (error)
                 return error;
@@ -4956,6 +4953,9 @@ xfs_bmapi_write(
         bma.flist = flist;
         bma.firstblock = firstblock;
 
+        if (flags & XFS_BMAPI_STACK_SWITCH)
+                bma.stack_switch = 1;
+
         while (bno < end && n < *nmap) {
                 inhole = eof || bma.got.br_startoff > bno;
                 wasdelay = !inhole && isnullstartblock(bma.got.br_startblock);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 56d1614760cf..fbbb9eb92e32 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -487,6 +487,7 @@ _xfs_buf_find(
         struct rb_node          *parent;
         xfs_buf_t               *bp;
         xfs_daddr_t             blkno = map[0].bm_bn;
+        xfs_daddr_t             eofs;
         int                     numblks = 0;
         int                     i;
 
@@ -498,6 +499,23 @@ _xfs_buf_find(
         ASSERT(!(numbytes < (1 << btp->bt_sshift)));
         ASSERT(!(BBTOB(blkno) & (xfs_off_t)btp->bt_smask));
 
+        /*
+         * Corrupted block numbers can get through to here, unfortunately, so we
+         * have to check that the buffer falls within the filesystem bounds.
+         */
+        eofs = XFS_FSB_TO_BB(btp->bt_mount, btp->bt_mount->m_sb.sb_dblocks);
+        if (blkno >= eofs) {
+                /*
+                 * XXX (dgc): we should really be returning EFSCORRUPTED here,
+                 * but none of the higher level infrastructure supports
+                 * returning a specific error on buffer lookup failures.
+                 */
+                xfs_alert(btp->bt_mount,
+                          "%s: Block out of range: block 0x%llx, EOFS 0x%llx ",
+                          __func__, blkno, eofs);
+                return NULL;
+        }
+
         /* get tree root */
         pag = xfs_perag_get(btp->bt_mount,
                                 xfs_daddr_to_agno(btp->bt_mount, blkno));
@@ -1487,6 +1505,8 @@ restart:
         while (!list_empty(&btp->bt_lru)) {
                 bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru);
                 if (atomic_read(&bp->b_hold) > 1) {
+                        trace_xfs_buf_wait_buftarg(bp, _RET_IP_);
+                        list_move_tail(&bp->b_lru, &btp->bt_lru);
                         spin_unlock(&btp->bt_lru_lock);
                         delay(100);
                         goto restart;
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 77b09750e92c..3f9949fee391 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -652,7 +652,10 @@ xfs_buf_item_unlock(
 
         /*
          * If the buf item isn't tracking any data, free it, otherwise drop the
-         * reference we hold to it.
+         * reference we hold to it. If we are aborting the transaction, this may
+         * be the only reference to the buf item, so we free it anyway
+         * regardless of whether it is dirty or not. A dirty abort implies a
+         * shutdown, anyway.
          */
         clean = 1;
         for (i = 0; i < bip->bli_format_count; i++) {
@@ -664,7 +667,12 @@ xfs_buf_item_unlock(
         }
         if (clean)
                 xfs_buf_item_relse(bp);
-        else
+        else if (aborted) {
+                if (atomic_dec_and_test(&bip->bli_refcount)) {
+                        ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
+                        xfs_buf_item_relse(bp);
+                }
+        } else
                 atomic_dec(&bip->bli_refcount);
 
         if (!hold)
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index d0e9c74d3d96..a8bd26b82ecb 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -246,10 +246,10 @@ xfs_swap_extents(
                 goto out_unlock;
         }
 
-        error = -filemap_write_and_wait(VFS_I(ip)->i_mapping);
+        error = -filemap_write_and_wait(VFS_I(tip)->i_mapping);
         if (error)
                 goto out_unlock;
-        truncate_pagecache_range(VFS_I(ip), 0, -1);
+        truncate_pagecache_range(VFS_I(tip), 0, -1);
 
         /* Verify O_DIRECT for ftmp */
         if (VN_CACHED(VFS_I(tip)) != 0) {
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index add06b4e9a63..364818eef40e 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -351,6 +351,15 @@ xfs_iomap_prealloc_size(
                 }
                 if (shift)
                         alloc_blocks >>= shift;
+
+                /*
+                 * If we are still trying to allocate more space than is
+                 * available, squash the prealloc hard. This can happen if we
+                 * have a large file on a small filesystem and the above
+                 * lowspace thresholds are smaller than MAXEXTLEN.
+                 */
+                while (alloc_blocks >= freesp)
+                        alloc_blocks >>= 4;
         }
 
         if (alloc_blocks < mp->m_writeio_blocks)
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index da508463ff10..7d6df7c00c36 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -658,7 +658,7 @@ xfs_sb_quiet_read_verify(
                 return;
         }
         /* quietly fail */
-        xfs_buf_ioerror(bp, EFSCORRUPTED);
+        xfs_buf_ioerror(bp, EWRONGFS);
 }
 
 static void
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 2e137d4a85ae..16a812977eab 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -341,6 +341,7 @@ DEFINE_BUF_EVENT(xfs_buf_item_relse);
 DEFINE_BUF_EVENT(xfs_buf_item_iodone);
 DEFINE_BUF_EVENT(xfs_buf_item_iodone_async);
 DEFINE_BUF_EVENT(xfs_buf_error_relse);
+DEFINE_BUF_EVENT(xfs_buf_wait_buftarg);
 DEFINE_BUF_EVENT(xfs_trans_read_buf_io);
 DEFINE_BUF_EVENT(xfs_trans_read_buf_shut);