Merge commit 'v2.6.33' into perf/core

Merge reason:
	__percpu annotations need the corresponding sparse address
space definition upstream.

Conflicts:
	tools/perf/util/probe-event.c (trivial)

11 files changed, 59 insertions, 86 deletions

diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 54f4798ab46a..6df6d6ed74fd 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -244,6 +244,7 @@ int btrfs_init_acl(struct btrfs_trans_handle *trans,
                                                     ACL_TYPE_ACCESS);
                         }
                 }
+                posix_acl_release(clone);
         }
 failed:
         posix_acl_release(acl);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9f806dd04c27..2aa8ec6a0981 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1161,6 +1161,7 @@ struct btrfs_root {
 #define BTRFS_MOUNT_SSD_SPREAD          (1 << 8)
 #define BTRFS_MOUNT_NOSSD               (1 << 9)
 #define BTRFS_MOUNT_DISCARD             (1 << 10)
+#define BTRFS_MOUNT_FORCE_COMPRESS      (1 << 11)
 
 #define btrfs_clear_opt(o, opt)         ((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)           ((o) |= BTRFS_MOUNT_##opt)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 009e3bd18f23..2b59201b955c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1982,7 +1982,12 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 
         if (!(sb->s_flags & MS_RDONLY)) {
                 ret = btrfs_recover_relocation(tree_root);
-                BUG_ON(ret);
+                if (ret < 0) {
+                        printk(KERN_WARNING
+                               "btrfs: failed to recover relocation\n");
+                        err = -EINVAL;
+                        goto fail_trans_kthread;
+                }
         }
 
         location.objectid = BTRFS_FS_TREE_OBJECTID;
@@ -1993,6 +1998,12 @@ struct btrfs_root *open_ctree(struct super_block *sb,
         if (!fs_info->fs_root)
                 goto fail_trans_kthread;
 
+        if (!(sb->s_flags & MS_RDONLY)) {
+                down_read(&fs_info->cleanup_work_sem);
+                btrfs_orphan_cleanup(fs_info->fs_root);
+                up_read(&fs_info->cleanup_work_sem);
+        }
+
         return tree_root;
 
 fail_trans_kthread:
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 432a2da4641e..559f72489b3b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5402,10 +5402,6 @@ static noinline int walk_down_tree(struct btrfs_trans_handle *trans,
         int ret;
 
         while (level >= 0) {
-                if (path->slots[level] >=
-                    btrfs_header_nritems(path->nodes[level]))
-                        break;
-
                 ret = walk_down_proc(trans, root, path, wc, lookup_info);
                 if (ret > 0)
                         break;
@@ -5413,6 +5409,10 @@ static noinline int walk_down_tree(struct btrfs_trans_handle *trans,
                 if (level == 0)
                         break;
 
+                if (path->slots[level] >=
+                    btrfs_header_nritems(path->nodes[level]))
+                        break;
+
                 ret = do_walk_down(trans, root, path, wc, &lookup_info);
                 if (ret > 0) {
                         path->slots[level]++;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 96577e8bf9fd..b177ed319612 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3165,10 +3165,9 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
                 spin_unlock(&tree->buffer_lock);
                 goto free_eb;
         }
-        spin_unlock(&tree->buffer_lock);
-
         /* add one reference for the tree */
         atomic_inc(&eb->refs);
+        spin_unlock(&tree->buffer_lock);
         return eb;
 
 free_eb:
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 46bea0f4dc7b..428fcac45f90 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -155,20 +155,6 @@ static struct rb_node *__tree_search(struct rb_root *root, u64 offset,
         return NULL;
 }
 
-/*
- * look for an offset in the tree, and if it can't be found, return
- * the first offset we can find smaller than 'offset'.
- */
-static inline struct rb_node *tree_search(struct rb_root *root, u64 offset)
-{
-        struct rb_node *prev;
-        struct rb_node *ret;
-        ret = __tree_search(root, offset, &prev, NULL);
-        if (!ret)
-                return prev;
-        return ret;
-}
-
 /* check to see if two extent_map structs are adjacent and safe to merge */
 static int mergable_maps(struct extent_map *prev, struct extent_map *next)
 {
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index c02033596f02..6ed434ac037f 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -720,13 +720,15 @@ again:
                                         inode->i_ino, orig_offset);
                 BUG_ON(ret);
         }
-        fi = btrfs_item_ptr(leaf, path->slots[0],
-                           struct btrfs_file_extent_item);
         if (del_nr == 0) {
+                fi = btrfs_item_ptr(leaf, path->slots[0],
+                           struct btrfs_file_extent_item);
                 btrfs_set_file_extent_type(leaf, fi,
                                            BTRFS_FILE_EXTENT_REG);
                 btrfs_mark_buffer_dirty(leaf);
         } else {
+                fi = btrfs_item_ptr(leaf, del_slot - 1,
+                           struct btrfs_file_extent_item);
                 btrfs_set_file_extent_type(leaf, fi,
                                            BTRFS_FILE_EXTENT_REG);
                 btrfs_set_file_extent_num_bytes(leaf, fi,
@@ -1133,7 +1135,7 @@ int btrfs_sync_file(struct file *file, struct dentry *dentry, int datasync)
         }
         mutex_lock(&dentry->d_inode->i_mutex);
 out:
-        return ret > 0 ? EIO : ret;
+        return ret > 0 ? -EIO : ret;
 }
 
 static const struct vm_operations_struct btrfs_file_vm_ops = {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b330e27c2d8b..4deb280f8969 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -483,7 +483,8 @@ again:
                 nr_pages_ret = 0;
 
                 /* flag the file so we don't compress in the future */
-                BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS;
+                if (!btrfs_test_opt(root, FORCE_COMPRESS))
+                        BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS;
         }
         if (will_compress) {
                 *num_added += 1;
@@ -1680,24 +1681,6 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
  * before we start the transaction.  It limits the amount of btree
  * reads required while inside the transaction.
  */
-static noinline void reada_csum(struct btrfs_root *root,
-                                struct btrfs_path *path,
-                                struct btrfs_ordered_extent *ordered_extent)
-{
-        struct btrfs_ordered_sum *sum;
-        u64 bytenr;
-
-        sum = list_entry(ordered_extent->list.next, struct btrfs_ordered_sum,
-                         list);
-        bytenr = sum->sums[0].bytenr;
-
-        /*
-         * we don't care about the results, the point of this search is
-         * just to get the btree leaves into ram
-         */
-        btrfs_lookup_csum(NULL, root->fs_info->csum_root, path, bytenr, 0);
-}
-
 /* as ordered data IO finishes, this gets called so we can finish
  * an ordered extent if the range of bytes in the file it covers are
  * fully written.
@@ -1708,7 +1691,6 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
         struct btrfs_trans_handle *trans;
         struct btrfs_ordered_extent *ordered_extent = NULL;
         struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
-        struct btrfs_path *path;
         int compressed = 0;
         int ret;
 
@@ -1716,32 +1698,9 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
         if (!ret)
                 return 0;
 
-        /*
-         * before we join the transaction, try to do some of our IO.
-         * This will limit the amount of IO that we have to do with
-         * the transaction running.  We're unlikely to need to do any
-         * IO if the file extents are new, the disk_i_size checks
-         * covers the most common case.
-         */
-        if (start < BTRFS_I(inode)->disk_i_size) {
-                path = btrfs_alloc_path();
-                if (path) {
-                        ret = btrfs_lookup_file_extent(NULL, root, path,
-                                                       inode->i_ino,
-                                                       start, 0);
-                        ordered_extent = btrfs_lookup_ordered_extent(inode,
-                                                                     start);
-                        if (!list_empty(&ordered_extent->list)) {
-                                btrfs_release_path(root, path);
-                                reada_csum(root, path, ordered_extent);
-                        }
-                        btrfs_free_path(path);
-                }
-        }
-
-        if (!ordered_extent)
-                ordered_extent = btrfs_lookup_ordered_extent(inode, start);
+        ordered_extent = btrfs_lookup_ordered_extent(inode, start);
         BUG_ON(!ordered_extent);
+
         if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) {
                 BUG_ON(!list_empty(&ordered_extent->list));
                 ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent);
@@ -3796,12 +3755,6 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 
         if (location.type == BTRFS_INODE_ITEM_KEY) {
                 inode = btrfs_iget(dir->i_sb, &location, root);
-                if (unlikely(root->clean_orphans) &&
-                    !(inode->i_sb->s_flags & MS_RDONLY)) {
-                        down_read(&root->fs_info->cleanup_work_sem);
-                        btrfs_orphan_cleanup(root);
-                        up_read(&root->fs_info->cleanup_work_sem);
-                }
                 return inode;
         }
 
@@ -5799,7 +5752,7 @@ out_fail:
 }
 
 static int prealloc_file_range(struct inode *inode, u64 start, u64 end,
-                               u64 alloc_hint, int mode)
+                        u64 alloc_hint, int mode, loff_t actual_len)
 {
         struct btrfs_trans_handle *trans;
         struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -5808,6 +5761,7 @@ static int prealloc_file_range(struct inode *inode, u64 start, u64 end,
         u64 cur_offset = start;
         u64 num_bytes = end - start;
         int ret = 0;
+        u64 i_size;
 
         while (num_bytes > 0) {
                 alloc_size = min(num_bytes, root->fs_info->max_extent);
@@ -5845,9 +5799,15 @@ static int prealloc_file_range(struct inode *inode, u64 start, u64 end,
                 inode->i_ctime = CURRENT_TIME;
                 BTRFS_I(inode)->flags |= BTRFS_INODE_PREALLOC;
                 if (!(mode & FALLOC_FL_KEEP_SIZE) &&
-                    cur_offset > inode->i_size) {
-                        i_size_write(inode, cur_offset);
-                        btrfs_ordered_update_i_size(inode, cur_offset, NULL);
+                        (actual_len > inode->i_size) &&
+                        (cur_offset > inode->i_size)) {
+
+                        if (cur_offset > actual_len)
+                                i_size  = actual_len;
+                        else
+                                i_size = cur_offset;
+                        i_size_write(inode, i_size);
+                        btrfs_ordered_update_i_size(inode, i_size, NULL);
                 }
 
                 ret = btrfs_update_inode(trans, root, inode);
@@ -5940,7 +5900,7 @@ static long btrfs_fallocate(struct inode *inode, int mode,
                      !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
                         ret = prealloc_file_range(inode,
                                                   cur_offset, last_byte,
-                                                  alloc_hint, mode);
+                                                alloc_hint, mode, offset+len);
                         if (ret < 0) {
                                 free_extent_map(em);
                                 break;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index ed3e4a2ec2c8..ab7ab5318745 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3764,7 +3764,8 @@ out:
                                        BTRFS_DATA_RELOC_TREE_OBJECTID);
                 if (IS_ERR(fs_root))
                         err = PTR_ERR(fs_root);
-                btrfs_orphan_cleanup(fs_root);
+                else
+                        btrfs_orphan_cleanup(fs_root);
         }
         return err;
 }
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 3f9b45704fcd..8a1ea6e64575 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -66,7 +66,8 @@ enum {
         Opt_degraded, Opt_subvol, Opt_device, Opt_nodatasum, Opt_nodatacow,
         Opt_max_extent, Opt_max_inline, Opt_alloc_start, Opt_nobarrier,
         Opt_ssd, Opt_nossd, Opt_ssd_spread, Opt_thread_pool, Opt_noacl,
-        Opt_compress, Opt_notreelog, Opt_ratio, Opt_flushoncommit,
+        Opt_compress, Opt_compress_force, Opt_notreelog, Opt_ratio,
+        Opt_flushoncommit,
         Opt_discard, Opt_err,
 };
 
@@ -82,6 +83,7 @@ static match_table_t tokens = {
         {Opt_alloc_start, "alloc_start=%s"},
         {Opt_thread_pool, "thread_pool=%d"},
         {Opt_compress, "compress"},
+        {Opt_compress_force, "compress-force"},
         {Opt_ssd, "ssd"},
         {Opt_ssd_spread, "ssd_spread"},
         {Opt_nossd, "nossd"},
@@ -173,6 +175,11 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
                         printk(KERN_INFO "btrfs: use compression\n");
                         btrfs_set_opt(info->mount_opt, COMPRESS);
                         break;
+                case Opt_compress_force:
+                        printk(KERN_INFO "btrfs: forcing compression\n");
+                        btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
+                        btrfs_set_opt(info->mount_opt, COMPRESS);
+                        break;
                 case Opt_ssd:
                         printk(KERN_INFO "btrfs: use ssd allocation scheme\n");
                         btrfs_set_opt(info->mount_opt, SSD);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 220dad5db017..41ecbb2347f2 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1135,7 +1135,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
                 root->fs_info->avail_metadata_alloc_bits;
 
         if ((all_avail & BTRFS_BLOCK_GROUP_RAID10) &&
-            root->fs_info->fs_devices->rw_devices <= 4) {
+            root->fs_info->fs_devices->num_devices <= 4) {
                 printk(KERN_ERR "btrfs: unable to go below four devices "
                        "on raid10\n");
                 ret = -EINVAL;
@@ -1143,7 +1143,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
         }
 
         if ((all_avail & BTRFS_BLOCK_GROUP_RAID1) &&
-            root->fs_info->fs_devices->rw_devices <= 2) {
+            root->fs_info->fs_devices->num_devices <= 2) {
                 printk(KERN_ERR "btrfs: unable to go below two "
                        "devices on raid1\n");
                 ret = -EINVAL;
@@ -1434,8 +1434,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
                 return -EINVAL;
 
         bdev = open_bdev_exclusive(device_path, 0, root->fs_info->bdev_holder);
-        if (!bdev)
-                return -EIO;
+        if (IS_ERR(bdev))
+                return PTR_ERR(bdev);
 
         if (root->fs_info->fs_devices->seeding) {
                 seeding_dev = 1;
@@ -2538,6 +2538,11 @@ int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset)
         if (!em)
                 return 1;
 
+        if (btrfs_test_opt(root, DEGRADED)) {
+                free_extent_map(em);
+                return 0;
+        }
+
         map = (struct map_lookup *)em->bdev;
         for (i = 0; i < map->num_stripes; i++) {
                 if (!map->stripes[i].dev->writeable) {