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
  ...

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.

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

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);

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;
 };

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

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);
 

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

fs/btrfs/disk-io.h

@@ -52,6 +52,7 @@ int write_ctree_super(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root, int max_mirrors);
 struct buffer_head *btrfs_read_dev_super(struct block_device *bdev);
 int btrfs_commit_super(struct btrfs_root *root);
+int btrfs_error_commit_super(struct btrfs_root *root);
 struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
 					    u64 bytenr, u32 blocksize);
 struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,

fs/btrfs/extent-tree.c

@@ -3089,7 +3089,7 @@ static u64 get_alloc_profile(struct btrfs_root *root, u64 flags)
 	return btrfs_reduce_alloc_profile(root, flags);
 }
 
-static u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data)
+u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data)
 {
 	u64 flags;
 
@@ -3161,8 +3161,12 @@ int btrfs_check_data_free_space(struct inode *inode, u64 bytes)
 					     bytes + 2 * 1024 * 1024,
 					     alloc_target, 0);
 			btrfs_end_transaction(trans, root);
-			if (ret < 0)
-				return ret;
+			if (ret < 0) {
+				if (ret != -ENOSPC)
+					return ret;
+				else
+					goto commit_trans;
+			}
 
 			if (!data_sinfo) {
 				btrfs_set_inode_space_info(root, inode);
@@ -3173,6 +3177,7 @@ int btrfs_check_data_free_space(struct inode *inode, u64 bytes)
 		spin_unlock(&data_sinfo->lock);
 
 		/* commit the current transaction and try again */
+commit_trans:
 		if (!committed && !root->fs_info->open_ioctl_trans) {
 			committed = 1;
 			trans = btrfs_join_transaction(root, 1);
@@ -3721,11 +3726,6 @@ int btrfs_block_rsv_check(struct btrfs_trans_handle *trans,
 		return 0;
 	}
 
-	WARN_ON(1);
-	printk(KERN_INFO"block_rsv size %llu reserved %llu freed %llu %llu\n",
-		block_rsv->size, block_rsv->reserved,
-		block_rsv->freed[0], block_rsv->freed[1]);
-
 	return -ENOSPC;
 }
 
@@ -7970,13 +7970,14 @@ static int set_block_group_ro(struct btrfs_block_group_cache *cache)
 
 	if (sinfo->bytes_used + sinfo->bytes_reserved + sinfo->bytes_pinned +
 	    sinfo->bytes_may_use + sinfo->bytes_readonly +
-	    cache->reserved_pinned + num_bytes < sinfo->total_bytes) {
+	    cache->reserved_pinned + num_bytes <= sinfo->total_bytes) {
 		sinfo->bytes_readonly += num_bytes;
 		sinfo->bytes_reserved += cache->reserved_pinned;
 		cache->reserved_pinned = 0;
 		cache->ro = 1;
 		ret = 0;
 	}
+
 	spin_unlock(&cache->lock);
 	spin_unlock(&sinfo->lock);
 	return ret;
@@ -8012,6 +8013,62 @@ int btrfs_set_block_group_ro(struct btrfs_root *root,
 	return ret;
 }
 
+/*
+ * helper to account the unused space of all the readonly block group in the
+ * list. takes mirrors into account.
+ */
+static u64 __btrfs_get_ro_block_group_free_space(struct list_head *groups_list)
+{
+	struct btrfs_block_group_cache *block_group;
+	u64 free_bytes = 0;
+	int factor;
+
+	list_for_each_entry(block_group, groups_list, list) {
+		spin_lock(&block_group->lock);
+
+		if (!block_group->ro) {
+			spin_unlock(&block_group->lock);
+			continue;
+		}
+
+		if (block_group->flags & (BTRFS_BLOCK_GROUP_RAID1 |
+					  BTRFS_BLOCK_GROUP_RAID10 |
+					  BTRFS_BLOCK_GROUP_DUP))
+			factor = 2;
+		else
+			factor = 1;
+
+		free_bytes += (block_group->key.offset -
+			       btrfs_block_group_used(&block_group->item)) *
+			       factor;
+
+		spin_unlock(&block_group->lock);
+	}
+
+	return free_bytes;
+}
+
+/*
+ * helper to account the unused space of all the readonly block group in the
+ * space_info. takes mirrors into account.
+ */
+u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
+{
+	int i;
+	u64 free_bytes = 0;
+
+	spin_lock(&sinfo->lock);
+
+	for(i = 0; i < BTRFS_NR_RAID_TYPES; i++)
+		if (!list_empty(&sinfo->block_groups[i]))
+			free_bytes += __btrfs_get_ro_block_group_free_space(
+						&sinfo->block_groups[i]);
+
+	spin_unlock(&sinfo->lock);
+
+	return free_bytes;
+}
+
 int btrfs_set_block_group_rw(struct btrfs_root *root,
 			      struct btrfs_block_group_cache *cache)
 {
@@ -8092,7 +8149,7 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 	mutex_lock(&root->fs_info->chunk_mutex);
 	list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
 		u64 min_free = btrfs_block_group_used(&block_group->item);
-		u64 dev_offset, max_avail;
+		u64 dev_offset;
 
 		/*
 		 * check to make sure we can actually find a chunk with enough
@@ -8100,7 +8157,7 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 		 */
 		if (device->total_bytes > device->bytes_used + min_free) {
 			ret = find_free_dev_extent(NULL, device, min_free,
-						   &dev_offset, &max_avail);
+						   &dev_offset, NULL);
 			if (!ret)
 				break;
 			ret = -1;
@@ -8584,3 +8641,14 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	btrfs_free_path(path);
 	return ret;
 }
+
+int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
+{
+	return unpin_extent_range(root, start, end);
+}
+
+int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
+			       u64 num_bytes)
+{
+	return btrfs_discard_extent(root, bytenr, num_bytes);
+}

fs/btrfs/extent_io.c

@@ -2028,8 +2028,11 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 		BUG_ON(extent_map_end(em) <= cur);
 		BUG_ON(end < cur);
 
-		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
+		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
 			this_bio_flag = EXTENT_BIO_COMPRESSED;
+			extent_set_compress_type(&this_bio_flag,
+						 em->compress_type);
+		}
 
 		iosize = min(extent_map_end(em) - cur, end - cur + 1);
 		cur_end = min(extent_map_end(em) - 1, end);
@@ -3072,6 +3075,8 @@ static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree,
 #endif
 
 	eb = kmem_cache_zalloc(extent_buffer_cache, mask);
+	if (eb == NULL)
+		return NULL;
 	eb->start = start;
 	eb->len = len;
 	spin_lock_init(&eb->lock);

fs/btrfs/extent_io.h

@@ -20,8 +20,12 @@
 #define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK)
 #define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC)
 
-/* flags for bio submission */
+/*
+ * flags for bio submission. The high bits indicate the compression
+ * type for this bio
+ */
 #define EXTENT_BIO_COMPRESSED 1
+#define EXTENT_BIO_FLAG_SHIFT 16
 
 /* these are bit numbers for test/set bit */
 #define EXTENT_BUFFER_UPTODATE 0
@@ -135,6 +139,17 @@ struct extent_buffer {
 	wait_queue_head_t lock_wq;
 };
 
+static inline void extent_set_compress_type(unsigned long *bio_flags,
+					    int compress_type)
+{
+	*bio_flags |= compress_type << EXTENT_BIO_FLAG_SHIFT;
+}
+
+static inline int extent_compress_type(unsigned long bio_flags)
+{
+	return bio_flags >> EXTENT_BIO_FLAG_SHIFT;
+}
+
 struct extent_map_tree;
 
 static inline struct extent_state *extent_state_next(struct extent_state *state)

fs/btrfs/extent_map.c

@@ -3,6 +3,7 @@
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
+#include "ctree.h"
 #include "extent_map.h"
 
 
@@ -54,6 +55,7 @@ struct extent_map *alloc_extent_map(gfp_t mask)
 		return em;
 	em->in_tree = 0;
 	em->flags = 0;
+	em->compress_type = BTRFS_COMPRESS_NONE;
 	atomic_set(&em->refs, 1);
 	return em;
 }

fs/btrfs/extent_map.h

@@ -26,7 +26,8 @@ struct extent_map {
 	unsigned long flags;
 	struct block_device *bdev;
 	atomic_t refs;
-	int in_tree;
+	unsigned int in_tree:1;
+	unsigned int compress_type:4;
 };
 
 struct extent_map_tree {

fs/btrfs/file.c

@@ -225,6 +225,7 @@ int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 
 			split->bdev = em->bdev;
 			split->flags = flags;
+			split->compress_type = em->compress_type;
 			ret = add_extent_mapping(em_tree, split);
 			BUG_ON(ret);
 			free_extent_map(split);
@@ -239,6 +240,7 @@ int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 			split->len = em->start + em->len - (start + len);
 			split->bdev = em->bdev;
 			split->flags = flags;
+			split->compress_type = em->compress_type;
 
 			if (compressed) {
 				split->block_len = em->block_len;
@@ -891,6 +893,17 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	if (err)
 		goto out;
 
+	/*
+	 * If BTRFS flips readonly due to some impossible error
+	 * (fs_info->fs_state now has BTRFS_SUPER_FLAG_ERROR),
+	 * although we have opened a file as writable, we have
+	 * to stop this write operation to ensure FS consistency.
+	 */
+	if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+		err = -EROFS;
+		goto out;
+	}
+
 	file_update_time(file);
 	BTRFS_I(inode)->sequence++;
 

fs/btrfs/inode.c

@@ -122,10 +122,10 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
 	size_t cur_size = size;
 	size_t datasize;
 	unsigned long offset;
-	int use_compress = 0;
+	int compress_type = BTRFS_COMPRESS_NONE;
 
 	if (compressed_size && compressed_pages) {
-		use_compress = 1;
+		compress_type = root->fs_info->compress_type;
 		cur_size = compressed_size;
 	}
 
@@ -159,7 +159,7 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
 	btrfs_set_file_extent_ram_bytes(leaf, ei, size);
 	ptr = btrfs_file_extent_inline_start(ei);
 
-	if (use_compress) {
+	if (compress_type != BTRFS_COMPRESS_NONE) {
 		struct page *cpage;
 		int i = 0;
 		while (compressed_size > 0) {
@@ -176,7 +176,7 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
 			compressed_size -= cur_size;
 		}
 		btrfs_set_file_extent_compression(leaf, ei,
-						  BTRFS_COMPRESS_ZLIB);
+						  compress_type);
 	} else {
 		page = find_get_page(inode->i_mapping,
 				     start >> PAGE_CACHE_SHIFT);
@@ -263,6 +263,7 @@ struct async_extent {
 	u64 compressed_size;
 	struct page **pages;
 	unsigned long nr_pages;
+	int compress_type;
 	struct list_head list;
 };
 
@@ -280,7 +281,8 @@ static noinline int add_async_extent(struct async_cow *cow,
 				     u64 start, u64 ram_size,
 				     u64 compressed_size,
 				     struct page **pages,
-				     unsigned long nr_pages)
+				     unsigned long nr_pages,
+				     int compress_type)
 {
 	struct async_extent *async_extent;
 
@@ -290,6 +292,7 @@ static noinline int add_async_extent(struct async_cow *cow,
 	async_extent->compressed_size = compressed_size;
 	async_extent->pages = pages;
 	async_extent->nr_pages = nr_pages;
+	async_extent->compress_type = compress_type;
 	list_add_tail(&async_extent->list, &cow->extents);
 	return 0;
 }
@@ -332,6 +335,7 @@ static noinline int compress_file_range(struct inode *inode,
 	unsigned long max_uncompressed = 128 * 1024;
 	int i;
 	int will_compress;
+	int compress_type = root->fs_info->compress_type;
 
 	actual_end = min_t(u64, isize, end + 1);
 again:
@@ -381,12 +385,16 @@ static noinline int compress_file_range(struct inode *inode,
 		WARN_ON(pages);
 		pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
 
-		ret = btrfs_zlib_compress_pages(inode->i_mapping, start,
-						total_compressed, pages,
-						nr_pages, &nr_pages_ret,
-						&total_in,
-						&total_compressed,
-						max_compressed);
+		if (BTRFS_I(inode)->force_compress)
+			compress_type = BTRFS_I(inode)->force_compress;
+
+		ret = btrfs_compress_pages(compress_type,
+					   inode->i_mapping, start,
+					   total_compressed, pages,
+					   nr_pages, &nr_pages_ret,
+					   &total_in,
+					   &total_compressed,
+					   max_compressed);
 
 		if (!ret) {
 			unsigned long offset = total_compressed &
@@ -493,7 +501,8 @@ static noinline int compress_file_range(struct inode *inode,
 		 * and will submit them to the elevator.
 		 */
 		add_async_extent(async_cow, start, num_bytes,
-				 total_compressed, pages, nr_pages_ret);
+				 total_compressed, pages, nr_pages_ret,
+				 compress_type);
 
 		if (start + num_bytes < end) {
 			start += num_bytes;
@@ -515,7 +524,8 @@ static noinline int compress_file_range(struct inode *inode,
 			__set_page_dirty_nobuffers(locked_page);
 			/* unlocked later on in the async handlers */
 		}
-		add_async_extent(async_cow, start, end - start + 1, 0, NULL, 0);
+		add_async_extent(async_cow, start, end - start + 1,
+				 0, NULL, 0, BTRFS_COMPRESS_NONE);
 		*num_added += 1;
 	}
 
@@ -640,6 +650,7 @@ static noinline int submit_compressed_extents(struct inode *inode,
 		em->block_start = ins.objectid;
 		em->block_len = ins.offset;
 		em->bdev = root->fs_info->fs_devices->latest_bdev;
+		em->compress_type = async_extent->compress_type;
 		set_bit(EXTENT_FLAG_PINNED, &em->flags);
 		set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
 
@@ -656,11 +667,13 @@ static noinline int submit_compressed_extents(struct inode *inode,
 						async_extent->ram_size - 1, 0);
 		}
 
-		ret = btrfs_add_ordered_extent(inode, async_extent->start,
-					       ins.objectid,
-					       async_extent->ram_size,
-					       ins.offset,
-					       BTRFS_ORDERED_COMPRESSED);
+		ret = btrfs_add_ordered_extent_compress(inode,
+						async_extent->start,
+						ins.objectid,
+						async_extent->ram_size,
+						ins.offset,
+						BTRFS_ORDERED_COMPRESSED,
+						async_extent->compress_type);
 		BUG_ON(ret);
 
 		/*
@@ -1670,7 +1683,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 	struct btrfs_ordered_extent *ordered_extent = NULL;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct extent_state *cached_state = NULL;
-	int compressed = 0;
+	int compress_type = 0;
 	int ret;
 	bool nolock = false;
 
@@ -1711,9 +1724,9 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 	if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags))
-		compressed = 1;
+		compress_type = ordered_extent->compress_type;
 	if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) {
-		BUG_ON(compressed);
+		BUG_ON(compress_type);
 		ret = btrfs_mark_extent_written(trans, inode,
 						ordered_extent->file_offset,
 						ordered_extent->file_offset +
@@ -1727,7 +1740,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 						ordered_extent->disk_len,
 						ordered_extent->len,
 						ordered_extent->len,
-						compressed, 0, 0,
+						compress_type, 0, 0,
 						BTRFS_FILE_EXTENT_REG);
 		unpin_extent_cache(&BTRFS_I(inode)->extent_tree,
 				   ordered_extent->file_offset,
@@ -1829,6 +1842,8 @@ static int btrfs_io_failed_hook(struct bio *failed_bio,
 		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
 			logical = em->block_start;
 			failrec->bio_flags = EXTENT_BIO_COMPRESSED;
+			extent_set_compress_type(&failrec->bio_flags,
+						 em->compress_type);
 		}
 		failrec->logical = logical;
 		free_extent_map(em);
@@ -3671,8 +3686,12 @@ static int btrfs_setattr_size(struct inode *inode, struct iattr *attr)
 static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = dentry->d_inode;
+	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int err;
 
+	if (btrfs_root_readonly(root))
+		return -EROFS;
+
 	err = inode_change_ok(inode, attr);
 	if (err)
 		return err;
@@ -4928,8 +4947,10 @@ static noinline int uncompress_inline(struct btrfs_path *path,
 	size_t max_size;
 	unsigned long inline_size;
 	unsigned long ptr;
+	int compress_type;
 
 	WARN_ON(pg_offset != 0);
+	compress_type = btrfs_file_extent_compression(leaf, item);
 	max_size = btrfs_file_extent_ram_bytes(leaf, item);
 	inline_size = btrfs_file_extent_inline_item_len(leaf,
 					btrfs_item_nr(leaf, path->slots[0]));
@@ -4939,8 +4960,8 @@ static noinline int uncompress_inline(struct btrfs_path *path,
 	read_extent_buffer(leaf, tmp, ptr, inline_size);
 
 	max_size = min_t(unsigned long, PAGE_CACHE_SIZE, max_size);
-	ret = btrfs_zlib_decompress(tmp, page, extent_offset,
-				    inline_size, max_size);
+	ret = btrfs_decompress(compress_type, tmp, page,
+			       extent_offset, inline_size, max_size);
 	if (ret) {
 		char *kaddr = kmap_atomic(page, KM_USER0);
 		unsigned long copy_size = min_t(u64,
@@ -4982,7 +5003,7 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_trans_handle *trans = NULL;
-	int compressed;
+	int compress_type;
 
 again:
 	read_lock(&em_tree->lock);
@@ -5041,7 +5062,7 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 
 	found_type = btrfs_file_extent_type(leaf, item);
 	extent_start = found_key.offset;
-	compressed = btrfs_file_extent_compression(leaf, item);
+	compress_type = btrfs_file_extent_compression(leaf, item);
 	if (found_type == BTRFS_FILE_EXTENT_REG ||
 	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
 		extent_end = extent_start +
@@ -5087,8 +5108,9 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 			em->block_start = EXTENT_MAP_HOLE;
 			goto insert;
 		}
-		if (compressed) {
+		if (compress_type != BTRFS_COMPRESS_NONE) {
 			set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
+			em->compress_type = compress_type;
 			em->block_start = bytenr;
 			em->block_len = btrfs_file_extent_disk_num_bytes(leaf,
 									 item);
@@ -5122,12 +5144,14 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 		em->len = (copy_size + root->sectorsize - 1) &
 			~((u64)root->sectorsize - 1);
 		em->orig_start = EXTENT_MAP_INLINE;
-		if (compressed)
+		if (compress_type) {
 			set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
+			em->compress_type = compress_type;
+		}
 		ptr = btrfs_file_extent_inline_start(item) + extent_offset;
 		if (create == 0 && !PageUptodate(page)) {
-			if (btrfs_file_extent_compression(leaf, item) ==
-			    BTRFS_COMPRESS_ZLIB) {
+			if (btrfs_file_extent_compression(leaf, item) !=
+			    BTRFS_COMPRESS_NONE) {
 				ret = uncompress_inline(path, inode, page,
 							pg_offset,
 							extent_offset, item);
@@ -6477,7 +6501,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->ordered_data_close = 0;
 	ei->orphan_meta_reserved = 0;
 	ei->dummy_inode = 0;
-	ei->force_compress = 0;
+	ei->force_compress = BTRFS_COMPRESS_NONE;
 
 	inode = &ei->vfs_inode;
 	extent_map_tree_init(&ei->extent_tree, GFP_NOFS);
@@ -7105,6 +7129,10 @@ static int btrfs_set_page_dirty(struct page *page)
 
 static int btrfs_permission(struct inode *inode, int mask, unsigned int flags)
 {
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+
+	if (btrfs_root_readonly(root) && (mask & MAY_WRITE))
+		return -EROFS;
 	if ((BTRFS_I(inode)->flags & BTRFS_INODE_READONLY) && (mask & MAY_WRITE))
 		return -EACCES;
 	return generic_permission(inode, mask, flags, btrfs_check_acl);

fs/btrfs/ioctl.h

@@ -31,6 +31,7 @@ struct btrfs_ioctl_vol_args {
 };
 
 #define BTRFS_SUBVOL_CREATE_ASYNC	(1ULL << 0)
+#define BTRFS_SUBVOL_RDONLY		(1ULL << 1)
 
 #define BTRFS_SUBVOL_NAME_MAX 4039
 struct btrfs_ioctl_vol_args_v2 {
@@ -133,8 +134,15 @@ struct btrfs_ioctl_defrag_range_args {
 	 */
 	__u32 extent_thresh;
 
+	/*
+	 * which compression method to use if turning on compression
+	 * for this defrag operation.  If unspecified, zlib will
+	 * be used
+	 */
+	__u32 compress_type;
+
 	/* spare for later */
-	__u32 unused[5];
+	__u32 unused[4];
 };
 
 struct btrfs_ioctl_space_info {
@@ -193,4 +201,6 @@ struct btrfs_ioctl_space_args {
 #define BTRFS_IOC_WAIT_SYNC  _IOW(BTRFS_IOCTL_MAGIC, 22, __u64)
 #define BTRFS_IOC_SNAP_CREATE_V2 _IOW(BTRFS_IOCTL_MAGIC, 23, \
 				   struct btrfs_ioctl_vol_args_v2)
+#define BTRFS_IOC_SUBVOL_GETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 25, __u64)
+#define BTRFS_IOC_SUBVOL_SETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 26, __u64)
 #endif

fs/btrfs/ordered-data.c

@@ -172,7 +172,7 @@ static inline struct rb_node *tree_search(struct btrfs_ordered_inode_tree *tree,
  */
 static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 				      u64 start, u64 len, u64 disk_len,
-				      int type, int dio)
+				      int type, int dio, int compress_type)
 {
 	struct btrfs_ordered_inode_tree *tree;
 	struct rb_node *node;
@@ -189,6 +189,7 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 	entry->disk_len = disk_len;
 	entry->bytes_left = len;
 	entry->inode = inode;
+	entry->compress_type = compress_type;
 	if (type != BTRFS_ORDERED_IO_DONE && type != BTRFS_ORDERED_COMPLETE)
 		set_bit(type, &entry->flags);
 
@@ -220,14 +221,25 @@ int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 			     u64 start, u64 len, u64 disk_len, int type)
 {
 	return __btrfs_add_ordered_extent(inode, file_offset, start, len,
-					  disk_len, type, 0);
+					  disk_len, type, 0,
+					  BTRFS_COMPRESS_NONE);
 }
 
 int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset,
 				 u64 start, u64 len, u64 disk_len, int type)
 {
 	return __btrfs_add_ordered_extent(inode, file_offset, start, len,
-					  disk_len, type, 1);
+					  disk_len, type, 1,
+					  BTRFS_COMPRESS_NONE);
+}
+
+int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset,
+				      u64 start, u64 len, u64 disk_len,
+				      int type, int compress_type)
+{
+	return __btrfs_add_ordered_extent(inode, file_offset, start, len,
+					  disk_len, type, 0,
+					  compress_type);
 }
 
 /*

fs/btrfs/ordered-data.h

@@ -68,7 +68,7 @@ struct btrfs_ordered_sum {
 
 #define BTRFS_ORDERED_NOCOW 2 /* set when we want to write in place */
 
-#define BTRFS_ORDERED_COMPRESSED 3 /* writing a compressed extent */
+#define BTRFS_ORDERED_COMPRESSED 3 /* writing a zlib compressed extent */
 
 #define BTRFS_ORDERED_PREALLOC 4 /* set when writing to prealloced extent */
 
@@ -93,6 +93,9 @@ struct btrfs_ordered_extent {
 	/* flags (described above) */
 	unsigned long flags;
 
+	/* compression algorithm */
+	int compress_type;
+
 	/* reference count */
 	atomic_t refs;
 
@@ -148,6 +151,9 @@ int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 			     u64 start, u64 len, u64 disk_len, int type);
 int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset,
 				 u64 start, u64 len, u64 disk_len, int type);
+int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset,
+				      u64 start, u64 len, u64 disk_len,
+				      int type, int compress_type);
 int btrfs_add_ordered_sum(struct inode *inode,
 			  struct btrfs_ordered_extent *entry,
 			  struct btrfs_ordered_sum *sum);

fs/btrfs/transaction.c

@@ -181,6 +181,9 @@ static struct btrfs_trans_handle *start_transaction(struct btrfs_root *root,
 	struct btrfs_trans_handle *h;
 	struct btrfs_transaction *cur_trans;
 	int ret;
+
+	if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
+		return ERR_PTR(-EROFS);
 again:
 	h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS);
 	if (!h)
@@ -910,6 +913,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	u64 to_reserve = 0;
 	u64 index = 0;
 	u64 objectid;
+	u64 root_flags;
 
 	new_root_item = kmalloc(sizeof(*new_root_item), GFP_NOFS);
 	if (!new_root_item) {
@@ -967,6 +971,13 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
 	memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
 
+	root_flags = btrfs_root_flags(new_root_item);
+	if (pending->readonly)
+		root_flags |= BTRFS_ROOT_SUBVOL_RDONLY;
+	else
+		root_flags &= ~BTRFS_ROOT_SUBVOL_RDONLY;
+	btrfs_set_root_flags(new_root_item, root_flags);
+
 	old = btrfs_lock_root_node(root);
 	btrfs_cow_block(trans, root, old, NULL, 0, &old);
 	btrfs_set_lock_blocking(old);

fs/btrfs/transaction.h

@@ -62,6 +62,7 @@ struct btrfs_pending_snapshot {
 	struct btrfs_block_rsv block_rsv;
 	/* extra metadata reseration for relocation */
 	int error;
+	bool readonly;
 	struct list_head list;
 };
 

fs/btrfs/volumes.h

@@ -20,8 +20,11 @@
 #define __BTRFS_VOLUMES_
 
 #include <linux/bio.h>
+#include <linux/sort.h>
 #include "async-thread.h"
 
+#define BTRFS_STRIPE_LEN	(64 * 1024)
+
 struct buffer_head;
 struct btrfs_pending_bios {
 	struct bio *head;
@@ -136,6 +139,30 @@ struct btrfs_multi_bio {
 	struct btrfs_bio_stripe stripes[];
 };
 
+struct btrfs_device_info {
+	struct btrfs_device *dev;
+	u64 dev_offset;
+	u64 max_avail;
+};
+
+/* Used to sort the devices by max_avail(descending sort) */
+int btrfs_cmp_device_free_bytes(const void *dev_info1, const void *dev_info2);
+
+/*
+ * sort the devices by max_avail, in which max free extent size of each device
+ * is stored.(Descending Sort)
+ */
+static inline void btrfs_descending_sort_devices(
+					struct btrfs_device_info *devices,
+					size_t nr_devices)
+{
+	sort(devices, nr_devices, sizeof(struct btrfs_device_info),
+	     btrfs_cmp_device_free_bytes, NULL);
+}
+
+int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
+				   u64 end, u64 *length);
+
 #define btrfs_multi_bio_size(n) (sizeof(struct btrfs_multi_bio) + \
 			    (sizeof(struct btrfs_bio_stripe) * (n)))
 

fs/btrfs/xattr.c

@@ -316,6 +316,15 @@ ssize_t btrfs_getxattr(struct dentry *dentry, const char *name,
 int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 		   size_t size, int flags)
 {
+	struct btrfs_root *root = BTRFS_I(dentry->d_inode)->root;
+
+	/*
+	 * The permission on security.* and system.* is not checked
+	 * in permission().
+	 */
+	if (btrfs_root_readonly(root))
+		return -EROFS;
+
 	/*
 	 * If this is a request for a synthetic attribute in the system.*
 	 * namespace use the generic infrastructure to resolve a handler
@@ -336,6 +345,15 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 
 int btrfs_removexattr(struct dentry *dentry, const char *name)
 {
+	struct btrfs_root *root = BTRFS_I(dentry->d_inode)->root;
+
+	/*
+	 * The permission on security.* and system.* is not checked
+	 * in permission().
+	 */
+	if (btrfs_root_readonly(root))
+		return -EROFS;
+
 	/*
 	 * If this is a request for a synthetic attribute in the system.*
 	 * namespace use the generic infrastructure to resolve a handler