Merge branch 'master' into percpu

11 files changed, 155 insertions, 65 deletions

diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 2e9e69987a82..6df6d6ed74fd 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -112,12 +112,14 @@ static int btrfs_set_acl(struct btrfs_trans_handle *trans,
         switch (type) {
         case ACL_TYPE_ACCESS:
                 mode = inode->i_mode;
-                ret = posix_acl_equiv_mode(acl, &mode);
-                if (ret < 0)
-                        return ret;
-                ret = 0;
-                inode->i_mode = mode;
                 name = POSIX_ACL_XATTR_ACCESS;
+                if (acl) {
+                        ret = posix_acl_equiv_mode(acl, &mode);
+                        if (ret < 0)
+                                return ret;
+                        inode->i_mode = mode;
+                }
+                ret = 0;
                 break;
         case ACL_TYPE_DEFAULT:
                 if (!S_ISDIR(inode->i_mode))
@@ -242,6 +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..87b25543d7d1 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1993,6 +1993,12 @@ 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 56e50137d0e6..432a2da4641e 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -83,6 +83,17 @@ static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits)
         return (cache->flags & bits) == bits;
 }
 
+void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
+{
+        atomic_inc(&cache->count);
+}
+
+void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
+{
+        if (atomic_dec_and_test(&cache->count))
+                kfree(cache);
+}
+
 /*
  * this adds the block group to the fs_info rb tree for the block group
  * cache
@@ -156,7 +167,7 @@ block_group_cache_tree_search(struct btrfs_fs_info *info, u64 bytenr,
                 }
         }
         if (ret)
-                atomic_inc(&ret->count);
+                btrfs_get_block_group(ret);
         spin_unlock(&info->block_group_cache_lock);
 
         return ret;
@@ -407,6 +418,8 @@ err:
 
         put_caching_control(caching_ctl);
         atomic_dec(&block_group->space_info->caching_threads);
+        btrfs_put_block_group(block_group);
+
         return 0;
 }
 
@@ -447,6 +460,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache)
         up_write(&fs_info->extent_commit_sem);
 
         atomic_inc(&cache->space_info->caching_threads);
+        btrfs_get_block_group(cache);
 
         tsk = kthread_run(caching_kthread, cache, "btrfs-cache-%llu\n",
                           cache->key.objectid);
@@ -486,12 +500,6 @@ struct btrfs_block_group_cache *btrfs_lookup_block_group(
         return cache;
 }
 
-void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
-{
-        if (atomic_dec_and_test(&cache->count))
-                kfree(cache);
-}
-
 static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info,
                                                   u64 flags)
 {
@@ -2582,7 +2590,7 @@ next_block_group(struct btrfs_root *root,
         if (node) {
                 cache = rb_entry(node, struct btrfs_block_group_cache,
                                  cache_node);
-                atomic_inc(&cache->count);
+                btrfs_get_block_group(cache);
         } else
                 cache = NULL;
         spin_unlock(&root->fs_info->block_group_cache_lock);
@@ -4227,7 +4235,7 @@ search:
                 u64 offset;
                 int cached;
 
-                atomic_inc(&block_group->count);
+                btrfs_get_block_group(block_group);
                 search_start = block_group->key.objectid;
 
 have_block_group:
@@ -4315,7 +4323,7 @@ have_block_group:
 
                                 btrfs_put_block_group(block_group);
                                 block_group = last_ptr->block_group;
-                                atomic_inc(&block_group->count);
+                                btrfs_get_block_group(block_group);
                                 spin_unlock(&last_ptr->lock);
                                 spin_unlock(&last_ptr->refill_lock);
 
@@ -7395,9 +7403,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
                         wait_block_group_cache_done(block_group);
 
                 btrfs_remove_free_space_cache(block_group);
-
-                WARN_ON(atomic_read(&block_group->count) != 1);
-                kfree(block_group);
+                btrfs_put_block_group(block_group);
 
                 spin_lock(&info->block_group_cache_lock);
         }
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 feaa13b105d9..c02033596f02 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -506,7 +506,8 @@ next_slot:
 }
 
 static int extent_mergeable(struct extent_buffer *leaf, int slot,
-                            u64 objectid, u64 bytenr, u64 *start, u64 *end)
+                            u64 objectid, u64 bytenr, u64 orig_offset,
+                            u64 *start, u64 *end)
 {
         struct btrfs_file_extent_item *fi;
         struct btrfs_key key;
@@ -522,6 +523,7 @@ static int extent_mergeable(struct extent_buffer *leaf, int slot,
         fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
         if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG ||
             btrfs_file_extent_disk_bytenr(leaf, fi) != bytenr ||
+            btrfs_file_extent_offset(leaf, fi) != key.offset - orig_offset ||
             btrfs_file_extent_compression(leaf, fi) ||
             btrfs_file_extent_encryption(leaf, fi) ||
             btrfs_file_extent_other_encoding(leaf, fi))
@@ -561,6 +563,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
         u64 split;
         int del_nr = 0;
         int del_slot = 0;
+        int recow;
         int ret;
 
         btrfs_drop_extent_cache(inode, start, end - 1, 0);
@@ -568,6 +571,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
         path = btrfs_alloc_path();
         BUG_ON(!path);
 again:
+        recow = 0;
         split = start;
         key.objectid = inode->i_ino;
         key.type = BTRFS_EXTENT_DATA_KEY;
@@ -591,12 +595,60 @@ again:
         bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
         num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
         orig_offset = key.offset - btrfs_file_extent_offset(leaf, fi);
+        memcpy(&new_key, &key, sizeof(new_key));
+
+        if (start == key.offset && end < extent_end) {
+                other_start = 0;
+                other_end = start;
+                if (extent_mergeable(leaf, path->slots[0] - 1,
+                                     inode->i_ino, bytenr, orig_offset,
+                                     &other_start, &other_end)) {
+                        new_key.offset = end;
+                        btrfs_set_item_key_safe(trans, root, path, &new_key);
+                        fi = btrfs_item_ptr(leaf, path->slots[0],
+                                            struct btrfs_file_extent_item);
+                        btrfs_set_file_extent_num_bytes(leaf, fi,
+                                                        extent_end - end);
+                        btrfs_set_file_extent_offset(leaf, fi,
+                                                     end - orig_offset);
+                        fi = btrfs_item_ptr(leaf, path->slots[0] - 1,
+                                            struct btrfs_file_extent_item);
+                        btrfs_set_file_extent_num_bytes(leaf, fi,
+                                                        end - other_start);
+                        btrfs_mark_buffer_dirty(leaf);
+                        goto out;
+                }
+        }
+
+        if (start > key.offset && end == extent_end) {
+                other_start = end;
+                other_end = 0;
+                if (extent_mergeable(leaf, path->slots[0] + 1,
+                                     inode->i_ino, bytenr, orig_offset,
+                                     &other_start, &other_end)) {
+                        fi = btrfs_item_ptr(leaf, path->slots[0],
+                                            struct btrfs_file_extent_item);
+                        btrfs_set_file_extent_num_bytes(leaf, fi,
+                                                        start - key.offset);
+                        path->slots[0]++;
+                        new_key.offset = start;
+                        btrfs_set_item_key_safe(trans, root, path, &new_key);
+
+                        fi = btrfs_item_ptr(leaf, path->slots[0],
+                                            struct btrfs_file_extent_item);
+                        btrfs_set_file_extent_num_bytes(leaf, fi,
+                                                        other_end - start);
+                        btrfs_set_file_extent_offset(leaf, fi,
+                                                     start - orig_offset);
+                        btrfs_mark_buffer_dirty(leaf);
+                        goto out;
+                }
+        }
 
         while (start > key.offset || end < extent_end) {
                 if (key.offset == start)
                         split = end;
 
-                memcpy(&new_key, &key, sizeof(new_key));
                 new_key.offset = split;
                 ret = btrfs_duplicate_item(trans, root, path, &new_key);
                 if (ret == -EAGAIN) {
@@ -631,15 +683,18 @@ again:
                         path->slots[0]--;
                         extent_end = end;
                 }
+                recow = 1;
         }
 
-        fi = btrfs_item_ptr(leaf, path->slots[0],
-                            struct btrfs_file_extent_item);
-
         other_start = end;
         other_end = 0;
-        if (extent_mergeable(leaf, path->slots[0] + 1, inode->i_ino,
-                             bytenr, &other_start, &other_end)) {
+        if (extent_mergeable(leaf, path->slots[0] + 1,
+                             inode->i_ino, bytenr, orig_offset,
+                             &other_start, &other_end)) {
+                if (recow) {
+                        btrfs_release_path(root, path);
+                        goto again;
+                }
                 extent_end = other_end;
                 del_slot = path->slots[0] + 1;
                 del_nr++;
@@ -650,8 +705,13 @@ again:
         }
         other_start = 0;
         other_end = start;
-        if (extent_mergeable(leaf, path->slots[0] - 1, inode->i_ino,
-                             bytenr, &other_start, &other_end)) {
+        if (extent_mergeable(leaf, path->slots[0] - 1,
+                             inode->i_ino, bytenr, orig_offset,
+                             &other_start, &other_end)) {
+                if (recow) {
+                        btrfs_release_path(root, path);
+                        goto again;
+                }
                 key.offset = other_start;
                 del_slot = path->slots[0];
                 del_nr++;
@@ -660,22 +720,22 @@ 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) {
                 btrfs_set_file_extent_type(leaf, fi,
                                            BTRFS_FILE_EXTENT_REG);
                 btrfs_mark_buffer_dirty(leaf);
-                goto out;
-        }
-
-        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,
-                                        extent_end - key.offset);
-        btrfs_mark_buffer_dirty(leaf);
+        } else {
+                btrfs_set_file_extent_type(leaf, fi,
+                                           BTRFS_FILE_EXTENT_REG);
+                btrfs_set_file_extent_num_bytes(leaf, fi,
+                                                extent_end - key.offset);
+                btrfs_mark_buffer_dirty(leaf);
 
-        ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
-        BUG_ON(ret);
+                ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
+                BUG_ON(ret);
+        }
 out:
         btrfs_free_path(path);
         return 0;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5440bab23635..8cd109972fa6 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;
@@ -3995,7 +3996,11 @@ skip:
 
         /* Reached end of directory/root. Bump pos past the last item. */
         if (key_type == BTRFS_DIR_INDEX_KEY)
-                filp->f_pos = INT_LIMIT(off_t);
+                /*
+                 * 32-bit glibc will use getdents64, but then strtol -
+                 * so the last number we can serve is this.
+                 */
+                filp->f_pos = 0x7fffffff;
         else
                 filp->f_pos++;
 nopos:
@@ -5789,7 +5794,7 @@ 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;
@@ -5798,6 +5803,7 @@ 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);
@@ -5836,8 +5842,12 @@ static int prealloc_file_range(struct inode *inode, u64 start, u64 end,
                 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);
+                        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);
@@ -5930,7 +5940,7 @@ 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/ordered-data.c b/fs/btrfs/ordered-data.c
index b10a49d4bc6a..5c2a9e78a949 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -626,6 +626,8 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 
         if (ordered)
                 offset = entry_end(ordered);
+        else
+                offset = ALIGN(offset, BTRFS_I(inode)->root->sectorsize);
 
         mutex_lock(&tree->mutex);
         disk_i_size = BTRFS_I(inode)->disk_i_size;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index a9728680eca8..ed3e4a2ec2c8 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3281,8 +3281,10 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
                 return -ENOMEM;
 
         path = btrfs_alloc_path();
-        if (!path)
+        if (!path) {
+                kfree(cluster);
                 return -ENOMEM;
+        }
 
         rc->extents_found = 0;
         rc->extents_skipped = 0;
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 198cff28766d..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) {
@@ -2649,8 +2654,10 @@ again:
         em = lookup_extent_mapping(em_tree, logical, *length);
         read_unlock(&em_tree->lock);
 
-        if (!em && unplug_page)
+        if (!em && unplug_page) {
+                kfree(multi);
                 return 0;
+        }
 
         if (!em) {
                 printk(KERN_CRIT "unable to find logical %llu len %llu\n",