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

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable: (25 commits)
  Btrfs: forced readonly mounts on errors
  btrfs: Require CAP_SYS_ADMIN for filesystem rebalance
  Btrfs: don't warn if we get ENOSPC in btrfs_block_rsv_check
  btrfs: Fix memory leak in btrfs_read_fs_root_no_radix()
  btrfs: check NULL or not
  btrfs: Don't pass NULL ptr to func that may deref it.
  btrfs: mount failure return value fix
  btrfs: Mem leak in btrfs_get_acl()
  btrfs: fix wrong free space information of btrfs
  btrfs: make the chunk allocator utilize the devices better
  btrfs: restructure find_free_dev_extent()
  btrfs: fix wrong calculation of stripe size
  btrfs: try to reclaim some space when chunk allocation fails
  btrfs: fix wrong data space statistics
  fs/btrfs: Fix build of ctree
  Btrfs: fix off by one while setting block groups readonly
  Btrfs: Add BTRFS_IOC_SUBVOL_GETFLAGS/SETFLAGS ioctls
  Btrfs: Add readonly snapshots support
  Btrfs: Refactor btrfs_ioctl_snap_create()
  btrfs: Extract duplicate decompress code
  ...

29 files changed, 2490 insertions, 623 deletions

diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index 7bb3c020e57..ecb9fd3be14 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -4,6 +4,8 @@ config BTRFS_FS
 	select LIBCRC32C
 	select ZLIB_INFLATE
 	select ZLIB_DEFLATE
+	select LZO_COMPRESS
+	select LZO_DECOMPRESS
 	help
 	  Btrfs is a new filesystem with extents, writable snapshotting,
 	  support for multiple devices and many more features.
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index a35eb36b32f..31610ea73ae 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -6,5 +6,5 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   transaction.o inode.o file.o tree-defrag.o \
 	   extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \
 	   extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
-	   export.o tree-log.o acl.o free-space-cache.o zlib.o \
+	   export.o tree-log.o acl.o free-space-cache.o zlib.o lzo.o \
 	   compression.o delayed-ref.o relocation.o
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 6ae2c8cac9d..15b5ca2a260 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -60,8 +60,10 @@ static struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 		size = __btrfs_getxattr(inode, name, value, size);
 		if (size > 0) {
 			acl = posix_acl_from_xattr(value, size);
-			if (IS_ERR(acl))
+			if (IS_ERR(acl)) {
+				kfree(value);
 				return acl;
+			}
 			set_cached_acl(inode, type, acl);
 		}
 		kfree(value);
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 6ad63f17eca..ccc991c542d 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -157,7 +157,7 @@ struct btrfs_inode {
 	/*
 	 * always compress this one file
 	 */
-	unsigned force_compress:1;
+	unsigned force_compress:4;
 
 	struct inode vfs_inode;
 };
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b50bc4bd5c5..f745287fbf2 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -62,6 +62,9 @@ struct compressed_bio {
 	/* number of bytes on disk */
 	unsigned long compressed_len;
 
+	/* the compression algorithm for this bio */
+	int compress_type;
+
 	/* number of compressed pages in the array */
 	unsigned long nr_pages;
 
@@ -173,11 +176,12 @@ static void end_compressed_bio_read(struct bio *bio, int err)
 	/* ok, we're the last bio for this extent, lets start
 	 * the decompression.
 	 */
-	ret = btrfs_zlib_decompress_biovec(cb->compressed_pages,
-					cb->start,
-					cb->orig_bio->bi_io_vec,
-					cb->orig_bio->bi_vcnt,
-					cb->compressed_len);
+	ret = btrfs_decompress_biovec(cb->compress_type,
+				      cb->compressed_pages,
+				      cb->start,
+				      cb->orig_bio->bi_io_vec,
+				      cb->orig_bio->bi_vcnt,
+				      cb->compressed_len);
 csum_failed:
 	if (ret)
 		cb->errors = 1;
@@ -588,6 +592,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 
 	cb->len = uncompressed_len;
 	cb->compressed_len = compressed_len;
+	cb->compress_type = extent_compress_type(bio_flags);
 	cb->orig_bio = bio;
 
 	nr_pages = (compressed_len + PAGE_CACHE_SIZE - 1) /
@@ -677,3 +682,317 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	bio_put(comp_bio);
 	return 0;
 }
+
+static struct list_head comp_idle_workspace[BTRFS_COMPRESS_TYPES];
+static spinlock_t comp_workspace_lock[BTRFS_COMPRESS_TYPES];
+static int comp_num_workspace[BTRFS_COMPRESS_TYPES];
+static atomic_t comp_alloc_workspace[BTRFS_COMPRESS_TYPES];
+static wait_queue_head_t comp_workspace_wait[BTRFS_COMPRESS_TYPES];
+
+struct btrfs_compress_op *btrfs_compress_op[] = {
+	&btrfs_zlib_compress,
+	&btrfs_lzo_compress,
+};
+
+int __init btrfs_init_compress(void)
+{
+	int i;
+
+	for (i = 0; i < BTRFS_COMPRESS_TYPES; i++) {
+		INIT_LIST_HEAD(&comp_idle_workspace[i]);
+		spin_lock_init(&comp_workspace_lock[i]);
+		atomic_set(&comp_alloc_workspace[i], 0);
+		init_waitqueue_head(&comp_workspace_wait[i]);
+	}
+	return 0;
+}
+
+/*
+ * this finds an available workspace or allocates a new one
+ * ERR_PTR is returned if things go bad.
+ */
+static struct list_head *find_workspace(int type)
+{
+	struct list_head *workspace;
+	int cpus = num_online_cpus();
+	int idx = type - 1;
+
+	struct list_head *idle_workspace	= &comp_idle_workspace[idx];
+	spinlock_t *workspace_lock		= &comp_workspace_lock[idx];
+	atomic_t *alloc_workspace		= &comp_alloc_workspace[idx];
+	wait_queue_head_t *workspace_wait	= &comp_workspace_wait[idx];
+	int *num_workspace			= &comp_num_workspace[idx];
+again:
+	spin_lock(workspace_lock);
+	if (!list_empty(idle_workspace)) {
+		workspace = idle_workspace->next;
+		list_del(workspace);
+		(*num_workspace)--;
+		spin_unlock(workspace_lock);
+		return workspace;
+
+	}
+	if (atomic_read(alloc_workspace) > cpus) {
+		DEFINE_WAIT(wait);
+
+		spin_unlock(workspace_lock);
+		prepare_to_wait(workspace_wait, &wait, TASK_UNINTERRUPTIBLE);
+		if (atomic_read(alloc_workspace) > cpus && !*num_workspace)
+			schedule();
+		finish_wait(workspace_wait, &wait);
+		goto again;
+	}
+	atomic_inc(alloc_workspace);
+	spin_unlock(workspace_lock);
+
+	workspace = btrfs_compress_op[idx]->alloc_workspace();
+	if (IS_ERR(workspace)) {
+		atomic_dec(alloc_workspace);
+		wake_up(workspace_wait);
+	}
+	return workspace;
+}
+
+/*
+ * put a workspace struct back on the list or free it if we have enough
+ * idle ones sitting around
+ */
+static void free_workspace(int type, struct list_head *workspace)
+{
+	int idx = type - 1;
+	struct list_head *idle_workspace	= &comp_idle_workspace[idx];
+	spinlock_t *workspace_lock		= &comp_workspace_lock[idx];
+	atomic_t *alloc_workspace		= &comp_alloc_workspace[idx];
+	wait_queue_head_t *workspace_wait	= &comp_workspace_wait[idx];
+	int *num_workspace			= &comp_num_workspace[idx];
+
+	spin_lock(workspace_lock);
+	if (*num_workspace < num_online_cpus()) {
+		list_add_tail(workspace, idle_workspace);
+		(*num_workspace)++;
+		spin_unlock(workspace_lock);
+		goto wake;
+	}
+	spin_unlock(workspace_lock);
+
+	btrfs_compress_op[idx]->free_workspace(workspace);
+	atomic_dec(alloc_workspace);
+wake:
+	if (waitqueue_active(workspace_wait))
+		wake_up(workspace_wait);
+}
+
+/*
+ * cleanup function for module exit
+ */
+static void free_workspaces(void)
+{
+	struct list_head *workspace;
+	int i;
+
+	for (i = 0; i < BTRFS_COMPRESS_TYPES; i++) {
+		while (!list_empty(&comp_idle_workspace[i])) {
+			workspace = comp_idle_workspace[i].next;
+			list_del(workspace);
+			btrfs_compress_op[i]->free_workspace(workspace);
+			atomic_dec(&comp_alloc_workspace[i]);
+		}
+	}
+}
+
+/*
+ * given an address space and start/len, compress the bytes.
+ *
+ * pages are allocated to hold the compressed result and stored
+ * in 'pages'
+ *
+ * out_pages is used to return the number of pages allocated.  There
+ * may be pages allocated even if we return an error
+ *
+ * total_in is used to return the number of bytes actually read.  It
+ * may be smaller then len if we had to exit early because we
+ * ran out of room in the pages array or because we cross the
+ * max_out threshold.
+ *
+ * total_out is used to return the total number of compressed bytes
+ *
+ * max_out tells us the max number of bytes that we're allowed to
+ * stuff into pages
+ */
+int btrfs_compress_pages(int type, struct address_space *mapping,
+			 u64 start, unsigned long len,
+			 struct page **pages,
+			 unsigned long nr_dest_pages,
+			 unsigned long *out_pages,
+			 unsigned long *total_in,
+			 unsigned long *total_out,
+			 unsigned long max_out)
+{
+	struct list_head *workspace;
+	int ret;
+
+	workspace = find_workspace(type);
+	if (IS_ERR(workspace))
+		return -1;
+
+	ret = btrfs_compress_op[type-1]->compress_pages(workspace, mapping,
+						      start, len, pages,
+						      nr_dest_pages, out_pages,
+						      total_in, total_out,
+						      max_out);
+	free_workspace(type, workspace);
+	return ret;
+}
+
+/*
+ * pages_in is an array of pages with compressed data.
+ *
+ * disk_start is the starting logical offset of this array in the file
+ *
+ * bvec is a bio_vec of pages from the file that we want to decompress into
+ *
+ * vcnt is the count of pages in the biovec
+ *
+ * srclen is the number of bytes in pages_in
+ *
+ * The basic idea is that we have a bio that was created by readpages.
+ * The pages in the bio are for the uncompressed data, and they may not
+ * be contiguous.  They all correspond to the range of bytes covered by
+ * the compressed extent.
+ */
+int btrfs_decompress_biovec(int type, struct page **pages_in, u64 disk_start,
+			    struct bio_vec *bvec, int vcnt, size_t srclen)
+{
+	struct list_head *workspace;
+	int ret;
+
+	workspace = find_workspace(type);
+	if (IS_ERR(workspace))
+		return -ENOMEM;
+
+	ret = btrfs_compress_op[type-1]->decompress_biovec(workspace, pages_in,
+							 disk_start,
+							 bvec, vcnt, srclen);
+	free_workspace(type, workspace);
+	return ret;
+}
+
+/*
+ * a less complex decompression routine.  Our compressed data fits in a
+ * single page, and we want to read a single page out of it.
+ * start_byte tells us the offset into the compressed data we're interested in
+ */
+int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
+		     unsigned long start_byte, size_t srclen, size_t destlen)
+{
+	struct list_head *workspace;
+	int ret;
+
+	workspace = find_workspace(type);
+	if (IS_ERR(workspace))
+		return -ENOMEM;
+
+	ret = btrfs_compress_op[type-1]->decompress(workspace, data_in,
+						  dest_page, start_byte,
+						  srclen, destlen);
+
+	free_workspace(type, workspace);
+	return ret;
+}
+
+void __exit btrfs_exit_compress(void)
+{
+	free_workspaces();
+}
+
+/*
+ * Copy uncompressed data from working buffer to pages.
+ *
+ * buf_start is the byte offset we're of the start of our workspace buffer.
+ *
+ * total_out is the last byte of the buffer
+ */
+int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
+			      unsigned long total_out, u64 disk_start,
+			      struct bio_vec *bvec, int vcnt,
+			      unsigned long *page_index,
+			      unsigned long *pg_offset)
+{
+	unsigned long buf_offset;
+	unsigned long current_buf_start;
+	unsigned long start_byte;
+	unsigned long working_bytes = total_out - buf_start;
+	unsigned long bytes;
+	char *kaddr;
+	struct page *page_out = bvec[*page_index].bv_page;
+
+	/*
+	 * start byte is the first byte of the page we're currently
+	 * copying into relative to the start of the compressed data.
+	 */
+	start_byte = page_offset(page_out) - disk_start;
+
+	/* we haven't yet hit data corresponding to this page */
+	if (total_out <= start_byte)
+		return 1;
+
+	/*
+	 * the start of the data we care about is offset into
+	 * the middle of our working buffer
+	 */
+	if (total_out > start_byte && buf_start < start_byte) {
+		buf_offset = start_byte - buf_start;
+		working_bytes -= buf_offset;
+	} else {
+		buf_offset = 0;
+	}
+	current_buf_start = buf_start;
+
+	/* copy bytes from the working buffer into the pages */
+	while (working_bytes > 0) {
+		bytes = min(PAGE_CACHE_SIZE - *pg_offset,
+			    PAGE_CACHE_SIZE - buf_offset);
+		bytes = min(bytes, working_bytes);
+		kaddr = kmap_atomic(page_out, KM_USER0);
+		memcpy(kaddr + *pg_offset, buf + buf_offset, bytes);
+		kunmap_atomic(kaddr, KM_USER0);
+		flush_dcache_page(page_out);
+
+		*pg_offset += bytes;
+		buf_offset += bytes;
+		working_bytes -= bytes;
+		current_buf_start += bytes;
+
+		/* check if we need to pick another page */
+		if (*pg_offset == PAGE_CACHE_SIZE) {
+			(*page_index)++;
+			if (*page_index >= vcnt)
+				return 0;
+
+			page_out = bvec[*page_index].bv_page;
+			*pg_offset = 0;
+			start_byte = page_offset(page_out) - disk_start;
+
+			/*
+			 * make sure our new page is covered by this
+			 * working buffer
+			 */
+			if (total_out <= start_byte)
+				return 1;
+
+			/*
+			 * the next page in the biovec might not be adjacent
+			 * to the last page, but it might still be found
+			 * inside this working buffer. bump our offset pointer
+			 */
+			if (total_out > start_byte &&
+			    current_buf_start < start_byte) {
+				buf_offset = start_byte - buf_start;
+				working_bytes = total_out - start_byte;
+				current_buf_start = buf_start + buf_offset;
+			}
+		}
+	}
+
+	return 1;
+}
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 421f5b4aa71..51000174b9d 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -19,24 +19,27 @@
 #ifndef __BTRFS_COMPRESSION_
 #define __BTRFS_COMPRESSION_
 
-int btrfs_zlib_decompress(unsigned char *data_in,
-			  struct page *dest_page,
-			  unsigned long start_byte,
-			  size_t srclen, size_t destlen);
-int btrfs_zlib_compress_pages(struct address_space *mapping,
-			      u64 start, unsigned long len,
-			      struct page **pages,
-			      unsigned long nr_dest_pages,
-			      unsigned long *out_pages,
-			      unsigned long *total_in,
-			      unsigned long *total_out,
-			      unsigned long max_out);
-int btrfs_zlib_decompress_biovec(struct page **pages_in,
-			      u64 disk_start,
-			      struct bio_vec *bvec,
-			      int vcnt,
-			      size_t srclen);
-void btrfs_zlib_exit(void);
+int btrfs_init_compress(void);
+void btrfs_exit_compress(void);
+
+int btrfs_compress_pages(int type, struct address_space *mapping,
+			 u64 start, unsigned long len,
+			 struct page **pages,
+			 unsigned long nr_dest_pages,
+			 unsigned long *out_pages,
+			 unsigned long *total_in,
+			 unsigned long *total_out,
+			 unsigned long max_out);
+int btrfs_decompress_biovec(int type, struct page **pages_in, u64 disk_start,
+			    struct bio_vec *bvec, int vcnt, size_t srclen);
+int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
+		     unsigned long start_byte, size_t srclen, size_t destlen);
+int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
+			      unsigned long total_out, u64 disk_start,
+			      struct bio_vec *bvec, int vcnt,
+			      unsigned long *page_index,
+			      unsigned long *pg_offset);
+
 int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				  unsigned long len, u64 disk_start,
 				  unsigned long compressed_len,
@@ -44,4 +47,37 @@ 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);
+
+struct btrfs_compress_op {
+	struct list_head *(*alloc_workspace)(void);
+
+	void (*free_workspace)(struct list_head *workspace);
+
+	int (*compress_pages)(struct list_head *workspace,
+			      struct address_space *mapping,
+			      u64 start, unsigned long len,
+			      struct page **pages,
+			      unsigned long nr_dest_pages,
+			      unsigned long *out_pages,
+			      unsigned long *total_in,
+			      unsigned long *total_out,
+			      unsigned long max_out);
+
+	int (*decompress_biovec)(struct list_head *workspace,
+				 struct page **pages_in,
+				 u64 disk_start,
+				 struct bio_vec *bvec,
+				 int vcnt,
+				 size_t srclen);
+
+	int (*decompress)(struct list_head *workspace,
+			  unsigned char *data_in,
+			  struct page *dest_page,
+			  unsigned long start_byte,
+			  size_t srclen, size_t destlen);
+};
+
+extern struct btrfs_compress_op btrfs_zlib_compress;
+extern struct btrfs_compress_op btrfs_lzo_compress;
+
 #endif
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 9ac17159925..b5baff0dccf 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -105,6 +105,8 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
 /* this also releases the path */
 void btrfs_free_path(struct btrfs_path *p)
 {
+	if (!p)
+		return;
 	btrfs_release_path(NULL, p);
 	kmem_cache_free(btrfs_path_cachep, p);
 }
@@ -2514,6 +2516,9 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root
 	btrfs_assert_tree_locked(path->nodes[1]);
 
 	right = read_node_slot(root, upper, slot + 1);
+	if (right == NULL)
+		return 1;
+
 	btrfs_tree_lock(right);
 	btrfs_set_lock_blocking(right);
 
@@ -2764,6 +2769,9 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root
 	btrfs_assert_tree_locked(path->nodes[1]);
 
 	left = read_node_slot(root, path->nodes[1], slot - 1);
+	if (left == NULL)
+		return 1;
+
 	btrfs_tree_lock(left);
 	btrfs_set_lock_blocking(left);
 
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index b875d445ea8..2c98b3af605 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -295,6 +295,14 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes)
 #define BTRFS_FSID_SIZE 16
 #define BTRFS_HEADER_FLAG_WRITTEN	(1ULL << 0)
 #define BTRFS_HEADER_FLAG_RELOC		(1ULL << 1)
+
+/*
+ * File system states
+ */
+
+/* Errors detected */
+#define BTRFS_SUPER_FLAG_ERROR		(1ULL << 2)
+
 #define BTRFS_SUPER_FLAG_SEEDING	(1ULL << 32)
 #define BTRFS_SUPER_FLAG_METADUMP	(1ULL << 33)
 
@@ -399,13 +407,15 @@ struct btrfs_super_block {
 #define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF	(1ULL << 0)
 #define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL	(1ULL << 1)
 #define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS	(1ULL << 2)
+#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO	(1ULL << 3)
 
 #define BTRFS_FEATURE_COMPAT_SUPP		0ULL
 #define BTRFS_FEATURE_COMPAT_RO_SUPP		0ULL
 #define BTRFS_FEATURE_INCOMPAT_SUPP			\
 	(BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF |		\
 	 BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL |	\
-	 BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
+	 BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS |		\
+	 BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO)
 
 /*
  * A leaf is full of items. offset and size tell us where to find
@@ -552,9 +562,11 @@ struct btrfs_timespec {
 } __attribute__ ((__packed__));
 
 enum btrfs_compression_type {
-	BTRFS_COMPRESS_NONE = 0,
-	BTRFS_COMPRESS_ZLIB = 1,
-	BTRFS_COMPRESS_LAST = 2,
+	BTRFS_COMPRESS_NONE  = 0,
+	BTRFS_COMPRESS_ZLIB  = 1,
+	BTRFS_COMPRESS_LZO   = 2,
+	BTRFS_COMPRESS_TYPES = 2,
+	BTRFS_COMPRESS_LAST  = 3,
 };
 
 struct btrfs_inode_item {
@@ -598,6 +610,8 @@ struct btrfs_dir_item {
 	u8 type;
 } __attribute__ ((__packed__));
 
+#define BTRFS_ROOT_SUBVOL_RDONLY	(1ULL << 0)
+
 struct btrfs_root_item {
 	struct btrfs_inode_item inode;
 	__le64 generation;
@@ -896,7 +910,8 @@ struct btrfs_fs_info {
 	 */
 	u64 last_trans_log_full_commit;
 	u64 open_ioctl_trans;
-	unsigned long mount_opt;
+	unsigned long mount_opt:20;
+	unsigned long compress_type:4;
 	u64 max_inline;
 	u64 alloc_start;
 	struct btrfs_transaction *running_transaction;
@@ -1051,6 +1066,9 @@ struct btrfs_fs_info {
 	unsigned metadata_ratio;
 
 	void *bdev_holder;
+
+	/* filesystem state */
+	u64 fs_state;
 };
 
 /*
@@ -1894,6 +1912,11 @@ BTRFS_SETGET_STACK_FUNCS(root_limit, struct btrfs_root_item, byte_limit, 64);
 BTRFS_SETGET_STACK_FUNCS(root_last_snapshot, struct btrfs_root_item,
 			 last_snapshot, 64);
 
+static inline bool btrfs_root_readonly(struct btrfs_root *root)
+{
+	return root->root_item.flags & BTRFS_ROOT_SUBVOL_RDONLY;
+}
+
 /* struct btrfs_super_block */
 
 BTRFS_SETGET_STACK_FUNCS(super_bytenr, struct btrfs_super_block, bytenr, 64);
@@ -2146,6 +2169,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 group_start);
 u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags);
+u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data);
 void btrfs_set_inode_space_info(struct btrfs_root *root, struct inode *ionde);
 void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
 int btrfs_check_data_free_space(struct inode *inode, u64 bytes);
@@ -2189,6 +2213,12 @@ int btrfs_set_block_group_ro(struct btrfs_root *root,
 int btrfs_set_block_group_rw(struct btrfs_root *root,
 			     struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
+u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
+int btrfs_error_unpin_extent_range(struct btrfs_root *root,
+				   u64 start, u64 end);
+int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
+			       u64 num_bytes);
+
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key,
 		     int level, int *slot);
@@ -2542,6 +2572,14 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
 /* super.c */
 int btrfs_parse_options(struct btrfs_root *root, char *options);
 int btrfs_sync_fs(struct super_block *sb, int wait);
+void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
+		     unsigned int line, int errno);
+
+#define btrfs_std_error(fs_info, errno)				\
+do {								\
+	if ((errno))						\
+		__btrfs_std_error((fs_info), __func__, __LINE__, (errno));\
+} while (0)
 
 /* acl.c */
 #ifdef CONFIG_BTRFS_FS_POSIX_ACL
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 51d2e4de34e..b531c36455d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -44,6 +44,20 @@
 static struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
 static void free_fs_root(struct btrfs_root *root);
+static void btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
+				    int read_only);
+static int btrfs_destroy_ordered_operations(struct btrfs_root *root);
+static int btrfs_destroy_ordered_extents(struct btrfs_root *root);
+static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
+				      struct btrfs_root *root);
+static int btrfs_destroy_pending_snapshots(struct btrfs_transaction *t);
+static int btrfs_destroy_delalloc_inodes(struct btrfs_root *root);
+static int btrfs_destroy_marked_extents(struct btrfs_root *root,
+					struct extent_io_tree *dirty_pages,
+					int mark);
+static int btrfs_destroy_pinned_extent(struct btrfs_root *root,
+				       struct extent_io_tree *pinned_extents);
+static int btrfs_cleanup_transaction(struct btrfs_root *root);
 
 /*
  * end_io_wq structs are used to do processing in task context when an IO is
@@ -353,6 +367,10 @@ static int csum_dirty_buffer(struct btrfs_root *root, struct page *page)
 	WARN_ON(len == 0);
 
 	eb = alloc_extent_buffer(tree, start, len, page, GFP_NOFS);
+	if (eb == NULL) {
+		WARN_ON(1);
+		goto out;
+	}
 	ret = btree_read_extent_buffer_pages(root, eb, start + PAGE_CACHE_SIZE,
 					     btrfs_header_generation(eb));
 	BUG_ON(ret);
@@ -427,6 +445,10 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 	WARN_ON(len == 0);
 
 	eb = alloc_extent_buffer(tree, start, len, page, GFP_NOFS);
+	if (eb == NULL) {
+		ret = -EIO;
+		goto out;
+	}
 
 	found_start = btrfs_header_bytenr(eb);
 	if (found_start != start) {
@@ -1145,6 +1167,7 @@ struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root,
 	}
 	btrfs_free_path(path);
 	if (ret) {
+		kfree(root);
 		if (ret > 0)
 			ret = -ENOENT;
 		return ERR_PTR(ret);
@@ -1713,8 +1736,10 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 		     fs_info, BTRFS_ROOT_TREE_OBJECTID);
 
 	bh = btrfs_read_dev_super(fs_devices->latest_bdev);
-	if (!bh)
+	if (!bh) {
+		err = -EINVAL;
 		goto fail_iput;
+	}
 
 	memcpy(&fs_info->super_copy, bh->b_data, sizeof(fs_info->super_copy));
 	memcpy(&fs_info->super_for_commit, &fs_info->super_copy,
@@ -1727,6 +1752,11 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	if (!btrfs_super_root(disk_super))
 		goto fail_iput;
 
+	/* check FS state, whether FS is broken. */
+	fs_info->fs_state |= btrfs_super_flags(disk_super);
+
+	btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
+
 	ret = btrfs_parse_options(tree_root, options);
 	if (ret) {
 		err = ret;
@@ -1744,10 +1774,10 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	}
 
 	features = btrfs_super_incompat_flags(disk_super);
-	if (!(features & BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF)) {
-		features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
-		btrfs_set_super_incompat_flags(disk_super, features);
-	}
+	features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
+	if (tree_root->fs_info->compress_type & BTRFS_COMPRESS_LZO)
+		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
+	btrfs_set_super_incompat_flags(disk_super, features);
 
 	features = btrfs_super_compat_ro_flags(disk_super) &
 		~BTRFS_FEATURE_COMPAT_RO_SUPP;
@@ -1957,7 +1987,9 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 		btrfs_set_opt(fs_info->mount_opt, SSD);
 	}
 
-	if (btrfs_super_log_root(disk_super) != 0) {
+	/* do not make disk changes in broken FS */
+	if (btrfs_super_log_root(disk_super) != 0 &&
+	    !(fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)) {
 		u64 bytenr = btrfs_super_log_root(disk_super);
 
 		if (fs_devices->rw_devices == 0) {
@@ -2442,8 +2474,28 @@ int close_ctree(struct btrfs_root *root)
 	smp_mb();
 
 	btrfs_put_block_group_cache(fs_info);
+
+	/*
+	 * Here come 2 situations when btrfs is broken to flip readonly:
+	 *
+	 * 1. when btrfs flips readonly somewhere else before
+	 * btrfs_commit_super, sb->s_flags has MS_RDONLY flag,
+	 * and btrfs will skip to write sb directly to keep
+	 * ERROR state on disk.
+	 *
+	 * 2. when btrfs flips readonly just in btrfs_commit_super,
+	 * and in such case, btrfs cannnot write sb via btrfs_commit_super,
+	 * and since fs_state has been set BTRFS_SUPER_FLAG_ERROR flag,
+	 * btrfs will cleanup all FS resources first and write sb then.
+	 */
 	if (!(fs_info->sb->s_flags & MS_RDONLY)) {
-		ret =  btrfs_commit_super(root);
+		ret = btrfs_commit_super(root);
+		if (ret)
+			printk(KERN_ERR "btrfs: commit super ret %d\n", ret);
+	}
+
+	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+		ret = btrfs_error_commit_super(root);
 		if (ret)
 			printk(KERN_ERR "btrfs: commit super ret %d\n", ret);
 	}
@@ -2619,6 +2671,352 @@ out:
 	return 0;
 }
 
+static void btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
+			      int read_only)
+{
+	if (read_only)
+		return;
+
+	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
+		printk(KERN_WARNING "warning: mount fs with errors, "
+		       "running btrfsck is recommended\n");
+}
+
+int btrfs_error_commit_super(struct btrfs_root *root)
+{
+	int ret;
+
+	mutex_lock(&root->fs_info->cleaner_mutex);
+	btrfs_run_delayed_iputs(root);
+	mutex_unlock(&root->fs_info->cleaner_mutex);
+
+	down_write(&root->fs_info->cleanup_work_sem);
+	up_write(&root->fs_info->cleanup_work_sem);
+
+	/* cleanup FS via transaction */
+	btrfs_cleanup_transaction(root);
+
+	ret = write_ctree_super(NULL, root, 0);
+
+	return ret;
+}
+
+static int btrfs_destroy_ordered_operations(struct btrfs_root *root)
+{
+	struct btrfs_inode *btrfs_inode;
+	struct list_head splice;
+