14 files changed, 121 insertions, 79 deletions

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index d3220d31d3cb..dcd9be32ac57 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -1011,8 +1011,6 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
                 bytes = min(bytes, working_bytes);
                 kaddr = kmap_atomic(page_out);
                 memcpy(kaddr + *pg_offset, buf + buf_offset, bytes);
-                if (*pg_index == (vcnt - 1) && *pg_offset == 0)
-                        memset(kaddr + bytes, 0, PAGE_CACHE_SIZE - bytes);
                 kunmap_atomic(kaddr);
                 flush_dcache_page(page_out);
 
@@ -1054,3 +1052,34 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 
         return 1;
 }
+
+/*
+ * When uncompressing data, we need to make sure and zero any parts of
+ * the biovec that were not filled in by the decompression code.  pg_index
+ * and pg_offset indicate the last page and the last offset of that page
+ * that have been filled in.  This will zero everything remaining in the
+ * biovec.
+ */
+void btrfs_clear_biovec_end(struct bio_vec *bvec, int vcnt,
+                                   unsigned long pg_index,
+                                   unsigned long pg_offset)
+{
+        while (pg_index < vcnt) {
+                struct page *page = bvec[pg_index].bv_page;
+                unsigned long off = bvec[pg_index].bv_offset;
+                unsigned long len = bvec[pg_index].bv_len;
+
+                if (pg_offset < off)
+                        pg_offset = off;
+                if (pg_offset < off + len) {
+                        unsigned long bytes = off + len - pg_offset;
+                        char *kaddr;
+
+                        kaddr = kmap_atomic(page);
+                        memset(kaddr + pg_offset, 0, bytes);
+                        kunmap_atomic(kaddr);
+                }
+                pg_index++;
+                pg_offset = 0;
+        }
+}
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 0c803b4fbf93..d181f70caae0 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -45,7 +45,9 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
                                   unsigned long nr_pages);
 int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
                                  int mirror_num, unsigned long bio_flags);
-
+void btrfs_clear_biovec_end(struct bio_vec *bvec, int vcnt,
+                                   unsigned long pg_index,
+                                   unsigned long pg_offset);
 struct btrfs_compress_op {
         struct list_head *(*alloc_workspace)(void);
 
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 19bc6162fb8e..150822ee0a0b 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -80,13 +80,6 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
 {
         int i;
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-        /* lockdep really cares that we take all of these spinlocks
-         * in the right order.  If any of the locks in the path are not
-         * currently blocking, it is going to complain.  So, make really
-         * really sure by forcing the path to blocking before we clear
-         * the path blocking.
-         */
         if (held) {
                 btrfs_set_lock_blocking_rw(held, held_rw);
                 if (held_rw == BTRFS_WRITE_LOCK)
@@ -95,7 +88,6 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
                         held_rw = BTRFS_READ_LOCK_BLOCKING;
         }
         btrfs_set_path_blocking(p);
-#endif
 
         for (i = BTRFS_MAX_LEVEL - 1; i >= 0; i--) {
                 if (p->nodes[i] && p->locks[i]) {
@@ -107,10 +99,8 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
                 }
         }
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
         if (held)
                 btrfs_clear_lock_blocking_rw(held, held_rw);
-#endif
 }
 
 /* this also releases the path */
@@ -2893,7 +2883,7 @@ cow_done:
                                         }
                                         p->locks[level] = BTRFS_WRITE_LOCK;
                                 } else {
-                                        err = btrfs_try_tree_read_lock(b);
+                                        err = btrfs_tree_read_lock_atomic(b);
                                         if (!err) {
                                                 btrfs_set_path_blocking(p);
                                                 btrfs_tree_read_lock(b);
@@ -3025,7 +3015,7 @@ again:
                         }
 
                         level = btrfs_header_level(b);
-                        err = btrfs_try_tree_read_lock(b);
+                        err = btrfs_tree_read_lock_atomic(b);
                         if (!err) {
                                 btrfs_set_path_blocking(p);
                                 btrfs_tree_read_lock(b);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index d557264ee974..fe69edda11fb 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3276,7 +3276,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
                            struct btrfs_root *root, unsigned long count);
 int btrfs_async_run_delayed_refs(struct btrfs_root *root,
                                  unsigned long count, int wait);
-int btrfs_lookup_extent(struct btrfs_root *root, u64 start, u64 len);
+int btrfs_lookup_data_extent(struct btrfs_root *root, u64 start, u64 len);
 int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
                              struct btrfs_root *root, u64 bytenr,
                              u64 offset, int metadata, u64 *refs, u64 *flags);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1ad0f47ac850..1bf9f897065d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3817,19 +3817,19 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
         struct btrfs_super_block *sb = fs_info->super_copy;
         int ret = 0;
 
-        if (sb->root_level > BTRFS_MAX_LEVEL) {
-                printk(KERN_ERR "BTRFS: tree_root level too big: %d > %d\n",
-                                sb->root_level, BTRFS_MAX_LEVEL);
+        if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
+                printk(KERN_ERR "BTRFS: tree_root level too big: %d >= %d\n",
+                                btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
                 ret = -EINVAL;
         }
-        if (sb->chunk_root_level > BTRFS_MAX_LEVEL) {
-                printk(KERN_ERR "BTRFS: chunk_root level too big: %d > %d\n",
-                                sb->chunk_root_level, BTRFS_MAX_LEVEL);
+        if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) {
+                printk(KERN_ERR "BTRFS: chunk_root level too big: %d >= %d\n",
+                                btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL);
                 ret = -EINVAL;
         }
-        if (sb->log_root_level > BTRFS_MAX_LEVEL) {
-                printk(KERN_ERR "BTRFS: log_root level too big: %d > %d\n",
-                                sb->log_root_level, BTRFS_MAX_LEVEL);
+        if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) {
+                printk(KERN_ERR "BTRFS: log_root level too big: %d >= %d\n",
+                                btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL);
                 ret = -EINVAL;
         }
 
@@ -3837,15 +3837,15 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
          * The common minimum, we don't know if we can trust the nodesize/sectorsize
          * items yet, they'll be verified later. Issue just a warning.
          */
-        if (!IS_ALIGNED(sb->root, 4096))
+        if (!IS_ALIGNED(btrfs_super_root(sb), 4096))
                 printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
                                 sb->root);
-        if (!IS_ALIGNED(sb->chunk_root, 4096))
+        if (!IS_ALIGNED(btrfs_super_chunk_root(sb), 4096))
                 printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
                                 sb->chunk_root);
-        if (!IS_ALIGNED(sb->log_root, 4096))
+        if (!IS_ALIGNED(btrfs_super_log_root(sb), 4096))
                 printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
-                                sb->log_root);
+                                btrfs_super_log_root(sb));
 
         if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_UUID_SIZE) != 0) {
                 printk(KERN_ERR "BTRFS: dev_item UUID does not match fsid: %pU != %pU\n",
@@ -3857,13 +3857,13 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
          * Hint to catch really bogus numbers, bitflips or so, more exact checks are
          * done later
          */
-        if (sb->num_devices > (1UL << 31))
+        if (btrfs_super_num_devices(sb) > (1UL << 31))
                 printk(KERN_WARNING "BTRFS: suspicious number of devices: %llu\n",
-                                sb->num_devices);
+                                btrfs_super_num_devices(sb));
 
-        if (sb->bytenr != BTRFS_SUPER_INFO_OFFSET) {
+        if (btrfs_super_bytenr(sb) != BTRFS_SUPER_INFO_OFFSET) {
                 printk(KERN_ERR "BTRFS: super offset mismatch %llu != %u\n",
-                                sb->bytenr, BTRFS_SUPER_INFO_OFFSET);
+                                btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET);
                 ret = -EINVAL;
         }
 
@@ -3871,14 +3871,15 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
          * The generation is a global counter, we'll trust it more than the others
          * but it's still possible that it's the one that's wrong.
          */
-        if (sb->generation < sb->chunk_root_generation)
+        if (btrfs_super_generation(sb) < btrfs_super_chunk_root_generation(sb))
                 printk(KERN_WARNING
                         "BTRFS: suspicious: generation < chunk_root_generation: %llu < %llu\n",
-                        sb->generation, sb->chunk_root_generation);
-        if (sb->generation < sb->cache_generation && sb->cache_generation != (u64)-1)
+                        btrfs_super_generation(sb), btrfs_super_chunk_root_generation(sb));
+        if (btrfs_super_generation(sb) < btrfs_super_cache_generation(sb)
+            && btrfs_super_cache_generation(sb) != (u64)-1)
                 printk(KERN_WARNING
                         "BTRFS: suspicious: generation < cache_generation: %llu < %llu\n",
-                        sb->generation, sb->cache_generation);
+                        btrfs_super_generation(sb), btrfs_super_cache_generation(sb));
 
         return ret;
 }
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d56589571012..47c1ba141082 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -710,8 +710,8 @@ void btrfs_clear_space_info_full(struct btrfs_fs_info *info)
         rcu_read_unlock();
 }
 
-/* simple helper to search for an existing extent at a given offset */
-int btrfs_lookup_extent(struct btrfs_root *root, u64 start, u64 len)
+/* simple helper to search for an existing data extent at a given offset */
+int btrfs_lookup_data_extent(struct btrfs_root *root, u64 start, u64 len)
 {
         int ret;
         struct btrfs_key key;
@@ -726,12 +726,6 @@ int btrfs_lookup_extent(struct btrfs_root *root, u64 start, u64 len)
         key.type = BTRFS_EXTENT_ITEM_KEY;
         ret = btrfs_search_slot(NULL, root->fs_info->extent_root, &key, path,
                                 0, 0);
-        if (ret > 0) {
-                btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
-                if (key.objectid == start &&
-                    key.type == BTRFS_METADATA_ITEM_KEY)
-                        ret = 0;
-        }
         btrfs_free_path(path);
         return ret;
 }
@@ -786,7 +780,6 @@ search_again:
         else
                 key.type = BTRFS_EXTENT_ITEM_KEY;
 
-again:
         ret = btrfs_search_slot(trans, root->fs_info->extent_root,
                                 &key, path, 0, 0);
         if (ret < 0)
@@ -802,13 +795,6 @@ again:
                             key.offset == root->nodesize)
                                 ret = 0;
                 }
-                if (ret) {
-                        key.objectid = bytenr;
-                        key.type = BTRFS_EXTENT_ITEM_KEY;
-                        key.offset = root->nodesize;
-                        btrfs_release_path(path);
-                        goto again;
-                }
         }
 
         if (ret == 0) {
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 783a94355efd..84a2d1868271 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -413,7 +413,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
         ret = 0;
 fail:
         while (ret < 0 && !list_empty(&tmplist)) {
-                sums = list_entry(&tmplist, struct btrfs_ordered_sum, list);
+                sums = list_entry(tmplist.next, struct btrfs_ordered_sum, list);
                 list_del(&sums->list);
                 kfree(sums);
         }
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 8d2b76e29d3b..4399f0c3a4ce 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -765,23 +765,6 @@ out:
         return ret;
 }
 
-/*  copy of check_sticky in fs/namei.c()
-* It's inline, so penalty for filesystems that don't use sticky bit is
-* minimal.
-*/
-static inline int btrfs_check_sticky(struct inode *dir, struct inode *inode)
-{
-        kuid_t fsuid = current_fsuid();
-
-        if (!(dir->i_mode & S_ISVTX))
-                return 0;
-        if (uid_eq(inode->i_uid, fsuid))
-                return 0;
-        if (uid_eq(dir->i_uid, fsuid))
-                return 0;
-        return !capable(CAP_FOWNER);
-}
-
 /*  copy of may_delete in fs/namei.c()
  *      Check whether we can remove a link victim from directory dir, check
  *  whether the type of victim is right.
@@ -817,8 +800,7 @@ static int btrfs_may_delete(struct inode *dir, struct dentry *victim, int isdir)
                 return error;
         if (IS_APPEND(dir))
                 return -EPERM;
-        if (btrfs_check_sticky(dir, victim->d_inode)||
-                IS_APPEND(victim->d_inode)||
+        if (check_sticky(dir, victim->d_inode) || IS_APPEND(victim->d_inode) ||
             IS_IMMUTABLE(victim->d_inode) || IS_SWAPFILE(victim->d_inode))
                 return -EPERM;
         if (isdir) {
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 5665d2149249..f8229ef1b46d 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -128,6 +128,26 @@ again:
 }
 
 /*
+ * take a spinning read lock.
+ * returns 1 if we get the read lock and 0 if we don't
+ * this won't wait for blocking writers
+ */
+int btrfs_tree_read_lock_atomic(struct extent_buffer *eb)
+{
+        if (atomic_read(&eb->blocking_writers))
+                return 0;
+
+        read_lock(&eb->lock);
+        if (atomic_read(&eb->blocking_writers)) {
+                read_unlock(&eb->lock);
+                return 0;
+        }
+        atomic_inc(&eb->read_locks);
+        atomic_inc(&eb->spinning_readers);
+        return 1;
+}
+
+/*
  * returns 1 if we get the read lock and 0 if we don't
  * this won't wait for blocking writers
  */
@@ -158,9 +178,7 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
             atomic_read(&eb->blocking_readers))
                 return 0;
 
-        if (!write_trylock(&eb->lock))
-                return 0;
-
+        write_lock(&eb->lock);
         if (atomic_read(&eb->blocking_writers) ||
             atomic_read(&eb->blocking_readers)) {
                 write_unlock(&eb->lock);
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index b81e0e9a4894..c44a9d5f5362 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -35,6 +35,8 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw);
 void btrfs_assert_tree_locked(struct extent_buffer *eb);
 int btrfs_try_tree_read_lock(struct extent_buffer *eb);
 int btrfs_try_tree_write_lock(struct extent_buffer *eb);
+int btrfs_tree_read_lock_atomic(struct extent_buffer *eb);
+
 
 static inline void btrfs_tree_unlock_rw(struct extent_buffer *eb, int rw)
 {
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 78285f30909e..617553cdb7d3 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -373,6 +373,8 @@ cont:
         }
 done:
         kunmap(pages_in[page_in_index]);
+        if (!ret)
+                btrfs_clear_biovec_end(bvec, vcnt, page_out_index, pg_offset);
         return ret;
 }
 
@@ -410,10 +412,23 @@ static int lzo_decompress(struct list_head *ws, unsigned char *data_in,
                 goto out;
         }
 
+        /*
+         * the caller is already checking against PAGE_SIZE, but lets
+         * move this check closer to the memcpy/memset
+         */
+        destlen = min_t(unsigned long, destlen, PAGE_SIZE);
         bytes = min_t(unsigned long, destlen, out_len - start_byte);
 
         kaddr = kmap_atomic(dest_page);
         memcpy(kaddr, workspace->buf + start_byte, bytes);
+
+        /*
+         * btrfs_getblock is doing a zero on the tail of the page too,
+         * but this will cover anything missing from the decompressed
+         * data.
+         */
+        if (bytes < destlen)
+                memset(kaddr+bytes, 0, destlen-bytes);
         kunmap_atomic(kaddr);
 out:
         return ret;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index a2b97ef10317..54bd91ece35b 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2151,6 +2151,7 @@ static void __exit exit_btrfs_fs(void)
         extent_map_exit();
         extent_io_exit();
         btrfs_interface_exit();
+        btrfs_end_io_wq_exit();
         unregister_filesystem(&btrfs_fs_type);
         btrfs_exit_sysfs();
         btrfs_cleanup_fs_uuids();
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 1475979e5718..286213cec861 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -672,7 +672,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
                          * is this extent already allocated in the extent
                          * allocation tree?  If so, just add a reference
                          */
-                        ret = btrfs_lookup_extent(root, ins.objectid,
+                        ret = btrfs_lookup_data_extent(root, ins.objectid,
                                                 ins.offset);
                         if (ret == 0) {
                                 ret = btrfs_inc_extent_ref(trans, root,
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 759fa4e2de8f..fb22fd8d8fb8 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -299,6 +299,8 @@ done:
         zlib_inflateEnd(&workspace->strm);
         if (data_in)
                 kunmap(pages_in[page_in_index]);
+        if (!ret)
+                btrfs_clear_biovec_end(bvec, vcnt, page_out_index, pg_offset);
         return ret;
 }
 
@@ -310,10 +312,14 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
         struct workspace *workspace = list_entry(ws, struct workspace, list);
         int ret = 0;
         int wbits = MAX_WBITS;
-        unsigned long bytes_left = destlen;
+        unsigned long bytes_left;
         unsigned long total_out = 0;
+        unsigned long pg_offset = 0;
         char *kaddr;
 
+        destlen = min_t(unsigned long, destlen, PAGE_SIZE);
+        bytes_left = destlen;
+
         workspace->strm.next_in = data_in;
         workspace->strm.avail_in = srclen;
         workspace->strm.total_in = 0;
@@ -341,7 +347,6 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
                 unsigned long buf_start;
                 unsigned long buf_offset;
                 unsigned long bytes;
-                unsigned long pg_offset = 0;
 
                 ret = zlib_inflate(&workspace->strm, Z_NO_FLUSH);
                 if (ret != Z_OK && ret != Z_STREAM_END)
@@ -384,6 +389,17 @@ next:
                 ret = 0;
 
         zlib_inflateEnd(&workspace->strm);
+
+        /*
+         * this should only happen if zlib returned fewer bytes than we
+         * expected.  btrfs_get_block is responsible for zeroing from the
+         * end of the inline extent (destlen) to the end of the page
+         */
+        if (pg_offset < destlen) {
+                kaddr = kmap_atomic(dest_page);
+                memset(kaddr + pg_offset, 0, destlen - pg_offset);
+                kunmap_atomic(kaddr);
+        }
         return ret;
 }