1 files changed, 1132 insertions, 307 deletions

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d39a9895d93..8e16bca69c5 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -39,25 +39,38 @@
 #include <linux/miscdevice.h>
 #include <linux/magic.h>
 #include <linux/slab.h>
-#include "compat.h"
+#include <linux/cleancache.h>
+#include <linux/ratelimit.h>
+#include <linux/btrfs.h>
+#include "delayed-inode.h"
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
-#include "ioctl.h"
 #include "print-tree.h"
+#include "hash.h"
+#include "props.h"
 #include "xattr.h"
 #include "volumes.h"
-#include "version.h"
 #include "export.h"
 #include "compression.h"
+#include "rcu-string.h"
+#include "dev-replace.h"
+#include "free-space-cache.h"
+#include "backref.h"
+#include "tests/btrfs-tests.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/btrfs.h>
 
 static const struct super_operations btrfs_super_ops;
+static struct file_system_type btrfs_fs_type;
+
+static int btrfs_remount(struct super_block *sb, int *flags, char *data);
 
-static const char *btrfs_decode_error(struct btrfs_fs_info *fs_info, int errno,
-				      char nbuf[16])
+static const char *btrfs_decode_error(int errno)
 {
-	char *errstr = NULL;
+	char *errstr = "unknown";
 
 	switch (errno) {
 	case -EIO:
@@ -69,33 +82,27 @@ static const char *btrfs_decode_error(struct btrfs_fs_info *fs_info, int errno,
 	case -EROFS:
 		errstr = "Readonly filesystem";
 		break;
-	default:
-		if (nbuf) {
-			if (snprintf(nbuf, 16, "error %d", -errno) >= 0)
-				errstr = nbuf;
-		}
+	case -EEXIST:
+		errstr = "Object already exists";
+		break;
+	case -ENOSPC:
+		errstr = "No space left";
+		break;
+	case -ENOENT:
+		errstr = "No such entry";
 		break;
 	}
 
 	return errstr;
 }
 
-static void __save_error_info(struct btrfs_fs_info *fs_info)
+static void save_error_info(struct btrfs_fs_info *fs_info)
 {
 	/*
 	 * today we only save the error info into ram.  Long term we'll
 	 * also send it down to the disk
 	 */
-	fs_info->fs_state = BTRFS_SUPER_FLAG_ERROR;
-}
-
-/* NOTE:
- *	We move write_super stuff at umount in order to avoid deadlock
- *	for umount hold all lock.
- */
-static void save_error_info(struct btrfs_fs_info *fs_info)
-{
-	__save_error_info(fs_info);
+	set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
 }
 
 /* btrfs handle error by forcing the filesystem readonly */
@@ -106,21 +113,31 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
 	if (sb->s_flags & MS_RDONLY)
 		return;
 
-	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
 		sb->s_flags |= MS_RDONLY;
-		printk(KERN_INFO "btrfs is forced readonly\n");
+		btrfs_info(fs_info, "forced readonly");
+		/*
+		 * Note that a running device replace operation is not
+		 * canceled here although there is no way to update
+		 * the progress. It would add the risk of a deadlock,
+		 * therefore the canceling is ommited. The only penalty
+		 * is that some I/O remains active until the procedure
+		 * completes. The next time when the filesystem is
+		 * mounted writeable again, the device replace
+		 * operation continues.
+		 */
 	}
 }
 
+#ifdef CONFIG_PRINTK
 /*
  * __btrfs_std_error decodes expected errors from the caller and
  * invokes the approciate error response.
  */
 void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
-		     unsigned int line, int errno)
+		       unsigned int line, int errno, const char *fmt, ...)
 {
 	struct super_block *sb = fs_info->sb;
-	char nbuf[16];
 	const char *errstr;
 
 	/*
@@ -128,25 +145,175 @@ void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
 	 * under MS_RDONLY, then it is safe here.
 	 */
 	if (errno == -EROFS && (sb->s_flags & MS_RDONLY))
-		return;
+  		return;
+
+	errstr = btrfs_decode_error(errno);
+	if (fmt) {
+		struct va_format vaf;
+		va_list args;
+
+		va_start(args, fmt);
+		vaf.fmt = fmt;
+		vaf.va = &args;
+
+		printk(KERN_CRIT
+			"BTRFS: error (device %s) in %s:%d: errno=%d %s (%pV)\n",
+			sb->s_id, function, line, errno, errstr, &vaf);
+		va_end(args);
+	} else {
+		printk(KERN_CRIT "BTRFS: error (device %s) in %s:%d: errno=%d %s\n",
+			sb->s_id, function, line, errno, errstr);
+	}
 
-	errstr = btrfs_decode_error(fs_info, errno, nbuf);
-	printk(KERN_CRIT "BTRFS error (device %s) in %s:%d: %s\n",
-		sb->s_id, function, line, errstr);
+	/* Don't go through full error handling during mount */
 	save_error_info(fs_info);
+	if (sb->s_flags & MS_BORN)
+		btrfs_handle_error(fs_info);
+}
+
+static const char * const logtypes[] = {
+	"emergency",
+	"alert",
+	"critical",
+	"error",
+	"warning",
+	"notice",
+	"info",
+	"debug",
+};
 
-	btrfs_handle_error(fs_info);
+void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...)
+{
+	struct super_block *sb = fs_info->sb;
+	char lvl[4];
+	struct va_format vaf;
+	va_list args;
+	const char *type = logtypes[4];
+	int kern_level;
+
+	va_start(args, fmt);
+
+	kern_level = printk_get_level(fmt);
+	if (kern_level) {
+		size_t size = printk_skip_level(fmt) - fmt;
+		memcpy(lvl, fmt,  size);
+		lvl[size] = '\0';
+		fmt += size;
+		type = logtypes[kern_level - '0'];
+	} else
+		*lvl = '\0';
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	printk("%sBTRFS %s (device %s): %pV\n", lvl, type, sb->s_id, &vaf);
+
+	va_end(args);
 }
 
-static void btrfs_put_super(struct super_block *sb)
+#else
+
+void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
+		       unsigned int line, int errno, const char *fmt, ...)
 {
-	struct btrfs_root *root = btrfs_sb(sb);
-	int ret;
+	struct super_block *sb = fs_info->sb;
 
-	ret = close_ctree(root);
-	sb->s_fs_info = NULL;
+	/*
+	 * Special case: if the error is EROFS, and we're already
+	 * under MS_RDONLY, then it is safe here.
+	 */
+	if (errno == -EROFS && (sb->s_flags & MS_RDONLY))
+		return;
 
-	(void)ret; /* FIXME: need to fix VFS to return error? */
+	/* Don't go through full error handling during mount */
+	if (sb->s_flags & MS_BORN) {
+		save_error_info(fs_info);
+		btrfs_handle_error(fs_info);
+	}
+}
+#endif
+
+/*
+ * We only mark the transaction aborted and then set the file system read-only.
+ * This will prevent new transactions from starting or trying to join this
+ * one.
+ *
+ * This means that error recovery at the call site is limited to freeing
+ * any local memory allocations and passing the error code up without
+ * further cleanup. The transaction should complete as it normally would
+ * in the call path but will return -EIO.
+ *
+ * We'll complete the cleanup in btrfs_end_transaction and
+ * btrfs_commit_transaction.
+ */
+void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *root, const char *function,
+			       unsigned int line, int errno)
+{
+	/*
+	 * Report first abort since mount
+	 */
+	if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED,
+				&root->fs_info->fs_state)) {
+		WARN(1, KERN_DEBUG "BTRFS: Transaction aborted (error %d)\n",
+				errno);
+	}
+	trans->aborted = errno;
+	/* Nothing used. The other threads that have joined this
+	 * transaction may be able to continue. */
+	if (!trans->blocks_used) {
+		const char *errstr;
+
+		errstr = btrfs_decode_error(errno);
+		btrfs_warn(root->fs_info,
+		           "%s:%d: Aborting unused transaction(%s).",
+		           function, line, errstr);
+		return;
+	}
+	ACCESS_ONCE(trans->transaction->aborted) = errno;
+	/* Wake up anybody who may be waiting on this transaction */
+	wake_up(&root->fs_info->transaction_wait);
+	wake_up(&root->fs_info->transaction_blocked_wait);
+	__btrfs_std_error(root->fs_info, function, line, errno, NULL);
+}
+/*
+ * __btrfs_panic decodes unexpected, fatal errors from the caller,
+ * issues an alert, and either panics or BUGs, depending on mount options.
+ */
+void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
+		   unsigned int line, int errno, const char *fmt, ...)
+{
+	char *s_id = "<unknown>";
+	const char *errstr;
+	struct va_format vaf = { .fmt = fmt };
+	va_list args;
+
+	if (fs_info)
+		s_id = fs_info->sb->s_id;
+
+	va_start(args, fmt);
+	vaf.va = &args;
+
+	errstr = btrfs_decode_error(errno);
+	if (fs_info && (fs_info->mount_opt & BTRFS_MOUNT_PANIC_ON_FATAL_ERROR))
+		panic(KERN_CRIT "BTRFS panic (device %s) in %s:%d: %pV (errno=%d %s)\n",
+			s_id, function, line, &vaf, errno, errstr);
+
+	btrfs_crit(fs_info, "panic in %s:%d: %pV (errno=%d %s)",
+		   function, line, &vaf, errno, errstr);
+	va_end(args);
+	/* Caller calls BUG() */
+}
+
+static void btrfs_put_super(struct super_block *sb)
+{
+	(void)close_ctree(btrfs_sb(sb)->tree_root);
+	/* FIXME: need to fix VFS to return error? */
+	/* AV: return it _where_?  ->put_super() can be triggered by any number
+	 * of async events, up to and including delivery of SIGKILL to the
+	 * last process that kept it busy.  Or segfault in the aforementioned
+	 * process...  Whom would you report that to?
+	 */
 }
 
 enum {
@@ -156,17 +323,27 @@ enum {
 	Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
 	Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
 	Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed,
-	Opt_enospc_debug, Opt_err,
+	Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, Opt_inode_cache,
+	Opt_no_space_cache, Opt_recovery, Opt_skip_balance,
+	Opt_check_integrity, Opt_check_integrity_including_extent_data,
+	Opt_check_integrity_print_mask, Opt_fatal_errors, Opt_rescan_uuid_tree,
+	Opt_commit_interval, Opt_barrier, Opt_nodefrag, Opt_nodiscard,
+	Opt_noenospc_debug, Opt_noflushoncommit, Opt_acl, Opt_datacow,
+	Opt_datasum, Opt_treelog, Opt_noinode_cache,
+	Opt_err,
 };
 
 static match_table_t tokens = {
 	{Opt_degraded, "degraded"},
 	{Opt_subvol, "subvol=%s"},
-	{Opt_subvolid, "subvolid=%d"},
+	{Opt_subvolid, "subvolid=%s"},
 	{Opt_device, "device=%s"},
 	{Opt_nodatasum, "nodatasum"},
+	{Opt_datasum, "datasum"},
 	{Opt_nodatacow, "nodatacow"},
+	{Opt_datacow, "datacow"},
 	{Opt_nobarrier, "nobarrier"},
+	{Opt_barrier, "barrier"},
 	{Opt_max_inline, "max_inline=%s"},
 	{Opt_alloc_start, "alloc_start=%s"},
 	{Opt_thread_pool, "thread_pool=%d"},
@@ -177,34 +354,60 @@ static match_table_t tokens = {
 	{Opt_ssd, "ssd"},
 	{Opt_ssd_spread, "ssd_spread"},
 	{Opt_nossd, "nossd"},
+	{Opt_acl, "acl"},
 	{Opt_noacl, "noacl"},
 	{Opt_notreelog, "notreelog"},
+	{Opt_treelog, "treelog"},
 	{Opt_flushoncommit, "flushoncommit"},
+	{Opt_noflushoncommit, "noflushoncommit"},
 	{Opt_ratio, "metadata_ratio=%d"},
 	{Opt_discard, "discard"},
+	{Opt_nodiscard, "nodiscard"},
 	{Opt_space_cache, "space_cache"},
 	{Opt_clear_cache, "clear_cache"},
 	{Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"},
 	{Opt_enospc_debug, "enospc_debug"},
+	{Opt_noenospc_debug, "noenospc_debug"},
+	{Opt_subvolrootid, "subvolrootid=%d"},
+	{Opt_defrag, "autodefrag"},
+	{Opt_nodefrag, "noautodefrag"},
+	{Opt_inode_cache, "inode_cache"},
+	{Opt_noinode_cache, "noinode_cache"},
+	{Opt_no_space_cache, "nospace_cache"},
+	{Opt_recovery, "recovery"},
+	{Opt_skip_balance, "skip_balance"},
+	{Opt_check_integrity, "check_int"},
+	{Opt_check_integrity_including_extent_data, "check_int_data"},
+	{Opt_check_integrity_print_mask, "check_int_print_mask=%d"},
+	{Opt_rescan_uuid_tree, "rescan_uuid_tree"},
+	{Opt_fatal_errors, "fatal_errors=%s"},
+	{Opt_commit_interval, "commit=%d"},
 	{Opt_err, NULL},
 };
 
 /*
  * Regular mount options parser.  Everything that is needed only when
  * reading in a new superblock is parsed here.
+ * XXX JDM: This needs to be cleaned up for remount.
  */
 int btrfs_parse_options(struct btrfs_root *root, char *options)
 {
 	struct btrfs_fs_info *info = root->fs_info;
 	substring_t args[MAX_OPT_ARGS];
-	char *p, *num, *orig;
+	char *p, *num, *orig = NULL;
+	u64 cache_gen;
 	int intarg;
 	int ret = 0;
 	char *compress_type;
 	bool compress_force = false;
+	bool compress = false;
+
+	cache_gen = btrfs_super_cache_generation(root->fs_info->super_copy);
+	if (cache_gen)
+		btrfs_set_opt(info->mount_opt, SPACE_CACHE);
 
 	if (!options)
-		return 0;
+		goto out;
 
 	/*
 	 * strsep changes the string, duplicate it because parse_options
@@ -224,11 +427,12 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 		token = match_token(p, tokens, args);
 		switch (token) {
 		case Opt_degraded:
-			printk(KERN_INFO "btrfs: allowing degraded mounts\n");
+			btrfs_info(root->fs_info, "allowing degraded mounts");
 			btrfs_set_opt(info->mount_opt, DEGRADED);
 			break;
 		case Opt_subvol:
 		case Opt_subvolid:
+		case Opt_subvolrootid:
 		case Opt_device:
 			/*
 			 * These are parsed by btrfs_parse_early_options
@@ -236,69 +440,112 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			 */
 			break;
 		case Opt_nodatasum:
-			printk(KERN_INFO "btrfs: setting nodatasum\n");
-			btrfs_set_opt(info->mount_opt, NODATASUM);
+			btrfs_set_and_info(root, NODATASUM,
+					   "setting nodatasum");
+			break;
+		case Opt_datasum:
+			if (btrfs_test_opt(root, NODATASUM)) {
+				if (btrfs_test_opt(root, NODATACOW))
+					btrfs_info(root->fs_info, "setting datasum, datacow enabled");
+				else
+					btrfs_info(root->fs_info, "setting datasum");
+			}
+			btrfs_clear_opt(info->mount_opt, NODATACOW);
+			btrfs_clear_opt(info->mount_opt, NODATASUM);
 			break;
 		case Opt_nodatacow:
-			printk(KERN_INFO "btrfs: setting nodatacow\n");
+			if (!btrfs_test_opt(root, NODATACOW)) {
+				if (!btrfs_test_opt(root, COMPRESS) ||
+				    !btrfs_test_opt(root, FORCE_COMPRESS)) {
+					btrfs_info(root->fs_info,
+						   "setting nodatacow, compression disabled");
+				} else {
+					btrfs_info(root->fs_info, "setting nodatacow");
+				}
+			}
+			btrfs_clear_opt(info->mount_opt, COMPRESS);
+			btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
 			btrfs_set_opt(info->mount_opt, NODATACOW);
 			btrfs_set_opt(info->mount_opt, NODATASUM);
 			break;
+		case Opt_datacow:
+			btrfs_clear_and_info(root, NODATACOW,
+					     "setting datacow");
+			break;
 		case Opt_compress_force:
 		case Opt_compress_force_type:
 			compress_force = true;
+			/* Fallthrough */
 		case Opt_compress:
 		case Opt_compress_type:
+			compress = true;
 			if (token == Opt_compress ||
 			    token == Opt_compress_force ||
 			    strcmp(args[0].from, "zlib") == 0) {
 				compress_type = "zlib";
 				info->compress_type = BTRFS_COMPRESS_ZLIB;
+				btrfs_set_opt(info->mount_opt, COMPRESS);
+				btrfs_clear_opt(info->mount_opt, NODATACOW);
+				btrfs_clear_opt(info->mount_opt, NODATASUM);
 			} else if (strcmp(args[0].from, "lzo") == 0) {
 				compress_type = "lzo";
 				info->compress_type = BTRFS_COMPRESS_LZO;
+				btrfs_set_opt(info->mount_opt, COMPRESS);
+				btrfs_clear_opt(info->mount_opt, NODATACOW);
+				btrfs_clear_opt(info->mount_opt, NODATASUM);
+				btrfs_set_fs_incompat(info, COMPRESS_LZO);
+			} else if (strncmp(args[0].from, "no", 2) == 0) {
+				compress_type = "no";
+				btrfs_clear_opt(info->mount_opt, COMPRESS);
+				btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
+				compress_force = false;
 			} else {
 				ret = -EINVAL;
 				goto out;
 			}
 
-			btrfs_set_opt(info->mount_opt, COMPRESS);
 			if (compress_force) {
-				btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
-				pr_info("btrfs: force %s compression\n",
-					compress_type);
-			} else
-				pr_info("btrfs: use %s compression\n",
-					compress_type);
+				btrfs_set_and_info(root, FORCE_COMPRESS,
+						   "force %s compression",
+						   compress_type);
+			} else if (compress) {
+				if (!btrfs_test_opt(root, COMPRESS))
+					btrfs_info(root->fs_info,
+						   "btrfs: use %s compression",
+						   compress_type);
+			}
 			break;
 		case Opt_ssd:
-			printk(KERN_INFO "btrfs: use ssd allocation scheme\n");
-			btrfs_set_opt(info->mount_opt, SSD);
+			btrfs_set_and_info(root, SSD,
+					   "use ssd allocation scheme");
 			break;
 		case Opt_ssd_spread:
-			printk(KERN_INFO "btrfs: use spread ssd "
-			       "allocation scheme\n");
+			btrfs_set_and_info(root, SSD_SPREAD,
+					   "use spread ssd allocation scheme");
 			btrfs_set_opt(info->mount_opt, SSD);
-			btrfs_set_opt(info->mount_opt, SSD_SPREAD);
 			break;
 		case Opt_nossd:
-			printk(KERN_INFO "btrfs: not using ssd allocation "
-			       "scheme\n");
-			btrfs_set_opt(info->mount_opt, NOSSD);
+			btrfs_set_and_info(root, NOSSD,
+					     "not using ssd allocation scheme");
 			btrfs_clear_opt(info->mount_opt, SSD);
-			btrfs_clear_opt(info->mount_opt, SSD_SPREAD);
+			break;
+		case Opt_barrier:
+			btrfs_clear_and_info(root, NOBARRIER,
+					     "turning on barriers");
 			break;
 		case Opt_nobarrier:
-			printk(KERN_INFO "btrfs: turning off barriers\n");
-			btrfs_set_opt(info->mount_opt, NOBARRIER);
+			btrfs_set_and_info(root, NOBARRIER,
+					   "turning off barriers");
 			break;
 		case Opt_thread_pool:
-			intarg = 0;
-			match_int(&args[0], &intarg);
-			if (intarg) {
+			ret = match_int(&args[0], &intarg);
+			if (ret) {
+				goto out;
+			} else if (intarg > 0) {
 				info->thread_pool_size = intarg;
-				printk(KERN_INFO "btrfs: thread pool %d\n",
-				       info->thread_pool_size);
+			} else {
+				ret = -EINVAL;
+				goto out;
 			}
 			break;
 		case Opt_max_inline:
@@ -308,54 +555,103 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 				kfree(num);
 
 				if (info->max_inline) {
-					info->max_inline = max_t(u64,
+					info->max_inline = min_t(u64,
 						info->max_inline,
 						root->sectorsize);
 				}
-				printk(KERN_INFO "btrfs: max_inline at %llu\n",
-					(unsigned long long)info->max_inline);
+				btrfs_info(root->fs_info, "max_inline at %llu",
+					info->max_inline);
+			} else {
+				ret = -ENOMEM;
+				goto out;
 			}
 			break;
 		case Opt_alloc_start:
 			num = match_strdup(&args[0]);
 			if (num) {
+				mutex_lock(&info->chunk_mutex);
 				info->alloc_start = memparse(num, NULL);
+				mutex_unlock(&info->chunk_mutex);
 				kfree(num);
-				printk(KERN_INFO
-					"btrfs: allocations start at %llu\n",
-					(unsigned long long)info->alloc_start);
+				btrfs_info(root->fs_info, "allocations start at %llu",
+					info->alloc_start);
+			} else {
+				ret = -ENOMEM;
+				goto out;
 			}
 			break;
+		case Opt_acl:
+#ifdef CONFIG_BTRFS_FS_POSIX_ACL
+			root->fs_info->sb->s_flags |= MS_POSIXACL;
+			break;
+#else
+			btrfs_err(root->fs_info,
+				"support for ACL not compiled in!");
+			ret = -EINVAL;
+			goto out;
+#endif
 		case Opt_noacl:
 			root->fs_info->sb->s_flags &= ~MS_POSIXACL;
 			break;
 		case Opt_notreelog:
-			printk(KERN_INFO "btrfs: disabling tree log\n");
-			btrfs_set_opt(info->mount_opt, NOTREELOG);
+			btrfs_set_and_info(root, NOTREELOG,
+					   "disabling tree log");
+			break;
+		case Opt_treelog:
+			btrfs_clear_and_info(root, NOTREELOG,
+					     "enabling tree log");
 			break;
 		case Opt_flushoncommit:
-			printk(KERN_INFO "btrfs: turning on flush-on-commit\n");
-			btrfs_set_opt(info->mount_opt, FLUSHONCOMMIT);
+			btrfs_set_and_info(root, FLUSHONCOMMIT,
+					   "turning on flush-on-commit");
+			break;
+		case Opt_noflushoncommit:
+			btrfs_clear_and_info(root, FLUSHONCOMMIT,
+					     "turning off flush-on-commit");
 			break;
 		case Opt_ratio:
-			intarg = 0;
-			match_int(&args[0], &intarg);
-			if (intarg) {
+			ret = match_int(&args[0], &intarg);
+			if (ret) {
+				goto out;
+			} else if (intarg >= 0) {
 				info->metadata_ratio = intarg;
-				printk(KERN_INFO "btrfs: metadata ratio %d\n",
+				btrfs_info(root->fs_info, "metadata ratio %d",
 				       info->metadata_ratio);
+			} else {
+				ret = -EINVAL;
+				goto out;
 			}
 			break;
 		case Opt_discard:
-			btrfs_set_opt(info->mount_opt, DISCARD);
+			btrfs_set_and_info(root, DISCARD,
+					   "turning on discard");
+			break;
+		case Opt_nodiscard:
+			btrfs_clear_and_info(root, DISCARD,
+					     "turning off discard");
 			break;
 		case Opt_space_cache:
-			printk(KERN_INFO "btrfs: enabling disk space caching\n");
-			btrfs_set_opt(info->mount_opt, SPACE_CACHE);
+			btrfs_set_and_info(root, SPACE_CACHE,
+					   "enabling disk space caching");
+			break;
+		case Opt_rescan_uuid_tree:
+			btrfs_set_opt(info->mount_opt, RESCAN_UUID_TREE);
+			break;
+		case Opt_no_space_cache:
+			btrfs_clear_and_info(root, SPACE_CACHE,
+					     "disabling disk space caching");
+			break;
+		case Opt_inode_cache:
+			btrfs_set_and_info(root, CHANGE_INODE_CACHE,
+					   "enabling inode map caching");
+			break;
+		case Opt_noinode_cache:
+			btrfs_clear_and_info(root, CHANGE_INODE_CACHE,
+					     "disabling inode map caching");
 			break;
 		case Opt_clear_cache:
-			printk(KERN_INFO "btrfs: force clearing of disk cache\n");
-			btrfs_set_opt(info->mount_opt, CLEAR_CACHE);
+			btrfs_set_and_info(root, CLEAR_CACHE,
+					   "force clearing of disk cache");
 			break;
 		case Opt_user_subvol_rm_allowed:
 			btrfs_set_opt(info->mount_opt, USER_SUBVOL_RM_ALLOWED);
@@ -363,9 +659,92 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 		case Opt_enospc_debug:
 			btrfs_set_opt(info->mount_opt, ENOSPC_DEBUG);
 			break;
+		case Opt_noenospc_debug:
+			btrfs_clear_opt(info->mount_opt, ENOSPC_DEBUG);
+			break;
+		case Opt_defrag:
+			btrfs_set_and_info(root, AUTO_DEFRAG,
+					   "enabling auto defrag");
+			break;
+		case Opt_nodefrag:
+			btrfs_clear_and_info(root, AUTO_DEFRAG,
+					     "disabling auto defrag");
+			break;
+		case Opt_recovery:
+			btrfs_info(root->fs_info, "enabling auto recovery");
+			btrfs_set_opt(info->mount_opt, RECOVERY);
+			break;
+		case Opt_skip_balance:
+			btrfs_set_opt(info->mount_opt, SKIP_BALANCE);
+			break;
+#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
+		case Opt_check_integrity_including_extent_data:
+			btrfs_info(root->fs_info,
+				   "enabling check integrity including extent data");
+			btrfs_set_opt(info->mount_opt,
+				      CHECK_INTEGRITY_INCLUDING_EXTENT_DATA);
+			btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY);
+			break;
+		case Opt_check_integrity:
+			btrfs_info(root->fs_info, "enabling check integrity");
+			btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY);
+			break;
+		case Opt_check_integrity_print_mask:
+			ret = match_int(&args[0], &intarg);
+			if (ret) {
+				goto out;
+			} else if (intarg >= 0) {
+				info->check_integrity_print_mask = intarg;
+				btrfs_info(root->fs_info, "check_integrity_print_mask 0x%x",
+				       info->check_integrity_print_mask);
+			} else {
+				ret = -EINVAL;
+				goto out;
+			}
+			break;
+#else
+		case Opt_check_integrity_including_extent_data:
+		case Opt_check_integrity:
+		case Opt_check_integrity_print_mask:
+			btrfs_err(root->fs_info,
+				"support for check_integrity* not compiled in!");
+			ret = -EINVAL;
+			goto out;
+#endif
+		case Opt_fatal_errors:
+			if (strcmp(args[0].from, "panic") == 0)
+				btrfs_set_opt(info->mount_opt,
+					      PANIC_ON_FATAL_ERROR);
+			else if (strcmp(args[0].from, "bug") == 0)
+				btrfs_clear_opt(info->mount_opt,
+					      PANIC_ON_FATAL_ERROR);
+			else {
+				ret = -EINVAL;
+				goto out;
+			}
+			break;
+		case Opt_commit_interval:
+			intarg = 0;
+			ret = match_int(&args[0], &intarg);
+			if (ret < 0) {
+				btrfs_err(root->fs_info, "invalid commit interval");
+				ret = -EINVAL;
+				goto out;
+			}
+			if (intarg > 0) {
+				if (intarg > 300) {
+					btrfs_warn(root->fs_info, "excessive commit interval %d",
+							intarg);
+				}
+				info->commit_interval = intarg;
+			} else {
+				btrfs_info(root->fs_info, "using default commit interval %ds",
+				    BTRFS_DEFAULT_COMMIT_INTERVAL);
+				info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
+			}
+			break;
 		case Opt_err:
-			printk(KERN_INFO "btrfs: unrecognized mount option "
-			       "'%s'\n", p);
+			btrfs_info(root->fs_info, "unrecognized mount option '%s'", p);
 			ret = -EINVAL;
 			goto out;
 		default:
@@ -373,6 +752,8 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 		}
 	}
 out:
+	if (!ret && btrfs_test_opt(root, SPACE_CACHE))
+		btrfs_info(root->fs_info, "disk space caching is enabled");
 	kfree(orig);
 	return ret;
 }
@@ -388,12 +769,12 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 		struct btrfs_fs_devices **fs_devices)
 {
 	substring_t args[MAX_OPT_ARGS];
-	char *opts, *orig, *p;
+	char *device_name, *opts, *orig, *p;
+	char *num = NULL;
 	int error = 0;
-	int intarg;
 
 	if (!options)
-		goto out;
+		return 0;
 
 	/*
 	 * strsep changes the string, duplicate it because parse_options
@@ -412,51 +793,59 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 		token = match_token(p, tokens, args);
 		switch (token) {
 		case Opt_subvol:
+			kfree(*subvol_name);
 			*subvol_name = match_strdup(&args[0]);
+			if (!*subvol_name) {
+				error = -ENOMEM;
+				goto out;
+			}
 			break;
 		case Opt_subvolid:
-			intarg = 0;
-			error = match_int(&args[0], &intarg);
-			if (!error) {
+			num = match_strdup(&args[0]);
+			if (num) {
+				*subvol_objectid = memparse(num, NULL);
+				kfree(num);
 				/* we want the original fs_tree */
-				if (!intarg)
+				if (!*subvol_objectid)
 					*subvol_objectid =
 						BTRFS_FS_TREE_OBJECTID;
-				else
-					*subvol_objectid = intarg;
+			} else {
+				error = -EINVAL;
+				goto out;
 			}
 			break;
+		case Opt_subvolrootid:
+			printk(KERN_WARNING
+				"BTRFS: 'subvolrootid' mount option is deprecated and has "
+				"no effect\n");
+			break;
 		case Opt_device:
-			error = btrfs_scan_one_device(match_strdup(&args[0]),
+			device_name = match_strdup(&args[0]);
+			if (!device_name) {
+				error = -ENOMEM;
+				goto out;
+			}
+			error = btrfs_scan_one_device(device_name,
 					flags, holder, fs_devices);
+			kfree(device_name);
 			if (error)
-				goto out_free_opts;
+				goto out;
 			break;
 		default:
 			break;
 		}
 	}
 
- out_free_opts:
+out:
 	kfree(orig);
- out:
-	/*
-	 * If no subvolume name is specified we use the default one.  Allocate
-	 * a copy of the string "." here so that code later in the
-	 * mount path doesn't care if it's the default volume or another one.
-	 */
-	if (!*subvol_name) {
-		*subvol_name = kstrdup(".", GFP_KERNEL);
-		if (!*subvol_name)
-			return -ENOMEM;
-	}
 	return error;
 }
 
 static struct dentry *get_default_root(struct super_block *sb,
 				       u64 subvol_objectid)
 {
-	struct btrfs_root *root = sb->s_fs_info;
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+	struct btrfs_root *root = fs_info->tree_root;
 	struct btrfs_root *new_root;
 	struct btrfs_dir_item *di;
 	struct btrfs_path *path;
@@ -487,10 +876,12 @@ static struct dentry *get_default_root(struct super_block *sb,
 	 * will mount by default if we haven't been given a specific subvolume
 	 * to mount.
 	 */
-	dir_id = btrfs_super_root_dir(&root->fs_info->super_copy);
+	dir_id = btrfs_super_root_dir(fs_info->super_copy);
 	di = btrfs_lookup_dir_item(NULL, root, path, dir_id, "default", 7, 0);
-	if (IS_ERR(di))
+	if (IS_ERR(di)) {
+		btrfs_free_path(path);
 		return ERR_CAST(di);
+	}
 	if (!di) {
 		/*
 		 * Ok the default dir item isn't there.  This is weird since
@@ -499,7 +890,7 @@ static struct dentry *get_default_root(struct super_block *sb,
 		 */
 		btrfs_free_path(path);
 		dir_id = BTRFS_FIRST_FREE_OBJECTID;
-		new_root = root->fs_info->fs_root;
+		new_root = fs_info->fs_root;
 		goto setup_root;
 	}
 
@@ -507,13 +898,10 @@ static struct dentry *get_default_root(struct super_block *sb,
 	btrfs_free_path(path);
 
 find_root:
-	new_root = btrfs_read_fs_root_no_name(root->fs_info, &location);
+	new_root = btrfs_read_fs_root_no_name(fs_info, &location);
 	if (IS_ERR(new_root))
 		return ERR_CAST(new_root);
 
-	if (btrfs_root_refs(&new_root->root_item) == 0)
-		return ERR_PTR(-ENOENT);
-
 	dir_id = btrfs_root_dirid(&new_root->root_item);
 setup_root:
 	location.objectid = dir_id;
@@ -534,28 +922,12 @@ setup_root:
 		return dget(sb->s_root);
 	}
 
-	if (new) {
-		const struct qstr name = { .name = "/", .len = 1 };
-
-		/*
-		 * New inode, we need to make the dentry a sibling of s_root so
-		 * everything gets cleaned up properly on unmount.
-		 */
-		dentry = d_alloc(sb->s_root, &name);
-		if (!dentry) {
-			iput(inode);
-			return ERR_PTR(-ENOMEM);
-		}
-		d_splice_alias(inode, dentry);
-	} else {
-		/*
-		 * We found the inode in cache, just find a dentry for it and
-		 * put the reference to the inode we just got.
-		 */
-		dentry = d_find_alias(inode);
-		iput(inode);
+	dentry = d_obtain_alias(inode);
+	if (!IS_ERR(dentry)) {
+		spin_lock(&dentry->d_lock);
+		dentry->d_flags &= ~DCACHE_DISCONNECTED;
+		spin_unlock(&dentry->d_lock);
 	}
-
 	return dentry;
 }
 
@@ -564,8 +936,7 @@ static int btrfs_fill_super(struct super_block *sb,
 			    void *data, int silent)
 {
 	struct inode *inode;
-	struct dentry *root_dentry;
-	struct btrfs_root *tree_root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
 	struct btrfs_key key;
 	int err;
 
@@ -579,66 +950,68 @@ static int btrfs_fill_super(struct super_block *sb,
 #ifdef CONFIG_BTRFS_FS_POSIX_ACL
 	sb->s_flags |= MS_POSIXACL;
 #endif
-
-	tree_root = open_ctree(sb, fs_devices, (char *)data);
-
-	if (IS_ERR(tree_root)) {
-		printk("btrfs: open_ctree failed\n");
-		return PTR_ERR(tree_root);
+	sb->s_flags |= MS_I_VERSION;
+	err = open_ctree(sb, fs_devices, (char *)data);
+	if (err) {
+		printk(KERN_ERR "BTRFS: open_ctree failed\n");
+		return err;
 	}
-	sb->s_fs_info = tree_root;
 
 	key.objectid = BTRFS_FIRST_FREE_OBJECTID;
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
-	inode = btrfs_iget(sb, &key, tree_root->fs_info->fs_root, NULL);
+	inode = btrfs_iget(sb, &key, fs_info->fs_root, NULL);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto fail_close;
 	}
 
-	root_dentry = d_alloc_root(inode);
-	if (!root_dentry) {
-		iput(inode);
+	sb->s_root = d_make_root(inode);
+	if (!sb->s_root) {
 		err = -ENOMEM;
 		goto fail_close;
 	}
 
-	sb->s_root = root_dentry;
-
 	save_mount_options(sb, data);
+	cleancache_init_fs(sb);
+	sb->s_flags |= MS_ACTIVE;
 	return 0;
 
 fail_close:
-	close_ctree(tree_root);
+	close_ctree(fs_info->tree_root);
 	return err;
 }
 
 int btrfs_sync_fs(struct super_block *sb, int wait)
 {
 	struct btrfs_trans_handle *trans;
-	struct btrfs_root *root = btrfs_sb(sb);
-	int ret;
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+	struct btrfs_root *root = fs_info->tree_root;
+
+	trace_btrfs_sync_fs(wait);
 
 	if (!wait) {
-		filemap_flush(root->fs_info->btree_inode->i_mapping);
+		filemap_flush(fs_info->btree_inode->i_mapping);
 		return 0;
 	}
 
-	btrfs_start_delalloc_inodes(root, 0);
-	btrfs_wait_ordered_extents(root, 0, 0);
+	btrfs_wait_ordered_roots(fs_info, -1);
 
-	trans = btrfs_start_transaction(root, 0);
-	if (IS_ERR(trans))
+	trans = btrfs_attach_transaction_barrier(root);
+	if (IS_ERR(trans)) {
+		/* no transaction, don't bother */
+		if (PTR_ERR(trans) == -ENOENT)
+			return 0;
 		return PTR_ERR(trans);
-	ret = btrfs_commit_transaction(trans, root);
-	return ret;
+	}
+	return btrfs_commit_transaction(trans, root);
 }
 
-static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
+static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 {
-	struct btrfs_root *root = btrfs_sb(vfs->mnt_sb);
-	struct btrfs_fs_info *info = root->fs_info;
+	struct btrfs_fs_info *info = btrfs_sb(dentry->d_sb);
+	struct btrfs_root *root = info->tree_root;
+	char *compress_type;
 
 	if (btrfs_test_opt(root, DEGRADED))
 		seq_puts(seq, ",degraded");
@@ -649,16 +1022,22 @@ static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	if (btrfs_test_opt(root, NOBARRIER))
 		seq_puts(seq, ",nobarrier");
 	if (info->max_inline != 8192 * 1024)
-		seq_printf(seq, ",max_inline=%llu",
-			   (unsigned long long)info->max_inline);
+		seq_printf(seq, ",max_inline=%llu", info->max_inline);
 	if (info->alloc_start != 0)
-		seq_printf(seq, ",alloc_start=%llu",
-			   (unsigned long long)info->alloc_start);
+		seq_printf(seq, ",alloc_start=%llu", info->alloc_start);
 	if (info->thread_pool_size !=  min_t(unsigned long,
 					     num_online_cpus() + 2, 8))
 		seq_printf(seq, ",thread_pool=%d", info->thread_pool_size);
-	if (btrfs_test_opt(root, COMPRESS))
-		seq_puts(seq, ",compress");
+	if (btrfs_test_opt(root, COMPRESS)) {
+		if (info->compress_type == BTRFS_COMPRESS_ZLIB)
+			compress_type = "zlib";
+		else
+			compress_type = "lzo";
+		if (btrfs_test_opt(root, FORCE_COMPRESS))
+			seq_printf(seq, ",compress-force=%s", compress_type);
+		else
+			seq_printf(seq, ",compress=%s", compress_type);
+	}
 	if (btrfs_test_opt(root, NOSSD))
 		seq_puts(seq, ",nossd");
 	if (btrfs_test_opt(root, SSD_SPREAD))
@@ -673,30 +1052,175 @@ static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",discard");
 	if (!(root->fs_info->sb->s_flags & MS_POSIXACL))
 		seq_puts(seq, ",noacl");
+	if (btrfs_test_opt(root, SPACE_CACHE))
+		seq_puts(seq, ",space_cache");
+	else
+		seq_puts(seq, ",nospace_cache");
+	if (btrfs_test_opt(root, RESCAN_UUID_TREE))
+		seq_puts(seq, ",rescan_uuid_tree");
+	if (btrfs_test_opt(root, CLEAR_CACHE))
+		seq_puts(seq, ",clear_cache");
+	if (btrfs_test_opt(root, USER_SUBVOL_RM_ALLOWED))
+		seq_puts(seq, ",user_subvol_rm_allowed");
+	if (btrfs_test_opt(root, ENOSPC_DEBUG))
+		seq_puts(seq, ",enospc_debug");
+	if (btrfs_test_opt(root, AUTO_DEFRAG))
+		seq_puts(seq, ",autodefrag");
+	if (btrfs_test_opt(root, INODE_MAP_CACHE))
+		seq_puts(seq, ",inode_cache");
+	if (btrfs_test_opt(root, SKIP_BALANCE))
+		seq_puts(seq, ",skip_balance");
+	if (btrfs_test_opt(root, RECOVERY))
+		seq_puts(seq, ",recovery");
+#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
+	if (btrfs_test_opt(root, CHECK_INTEGRITY_INCLUDING_EXTENT_DATA))
+		seq_puts(seq, ",check_int_data");
+	else if (btrfs_test_opt(root, CHECK_INTEGRITY))
+		seq_puts(seq, ",check_int");
+	if (info->check_integrity_print_mask)
+		seq_printf(seq, ",check_int_print_mask=%d",
+				info->check_integrity_print_mask);
+#endif
+	if (info->metadata_ratio)
+		seq_printf(seq, ",metadata_ratio=%d",
+				info->metadata_ratio);
+	if (btrfs_test_opt(root, PANIC_ON_FATAL_ERROR))
+		seq_puts(seq, ",fatal_errors=panic");
+	if (info->commit_interval != BTRFS_DEFAULT_COMMIT_INTERVAL)
+		seq_printf(seq, ",commit=%d", info->commit_interval);
 	return 0;
 }
 
 static int btrfs_test_super(struct super_block *s, void *data)
 {
-	struct btrfs_root *test_root = data;
-	struct btrfs_root *root = btrfs_sb(s);
+	struct btrfs_fs_info *p = data;
+	struct btrfs_fs_info *fs_info = btrfs_sb(s);
 
-	/*
-	 * If this super block is going away, return false as it
-	 * can't match as an existing super block.
-	 */
-	if (!atomic_read(&s->s_active))
-		return 0;
-	return root->fs_info->fs_devices == test_root->fs_info->fs_devices;
+	return fs_info->fs_devices == p->fs_devices;
 }
 
 static int btrfs_set_super(struct super_block *s, void *data)
 {
-	s->s_fs_info = data;
+	int err = set_anon_super(s, data);
+	if (!err)
+		s->s_fs_info = data;
+	return err;
+}
+
+/*
+ * subvolumes are identified by ino 256
+ */
+static inline int is_subvolume_inode(struct inode *inode)
+{
+	if (inode && inode->i_ino == BTRFS_FIRST_FREE_OBJECTID)
+		return 1;
+	return 0;
+}
+
+/*
+ * This will strip out the subvol=%s argument for an argument string and add
+ * subvolid=0 to make sure we get the actual tree root for path walking to the
+ * subvol we want.
+ */
+static char *setup_root_args(char *args)
+{
+	unsigned len = strlen(args) + 2 + 1;
+	char *src, *dst, *buf;
 
-	return set_anon_super(s, data);
+	/*
+	 * We need the same args as before, but with this substitution:
+	 * s!subvol=[^,]+!subvolid=0!
+	 *
+	 * Since the replacement string is up to 2 bytes longer than the
+	 * original, allocate strlen(args) + 2 + 1 bytes.
+	 */
+
+	src = strstr(args, "subvol=");
+	/* This shouldn't happen, but just in case.. */
+	if (!src)
+		return NULL;
+
+	buf = dst = kmalloc(len, GFP_NOFS);
+	if (!buf)
+		return NULL;
+
+	/*
+	 * If the subvol= arg is not at the start of the string,
+	 * copy whatever precedes it into buf.
+	 */
+	if (src != args) {
+		*src++ = '\0';
+		strcpy(buf, args);
+		dst += strlen(args);
+	}
+
+	strcpy(dst, "subvolid=0");
+	dst += strlen("subvolid=0");
+
+	/*
+	 * If there is a "," after the original subvol=... string,
+	 * copy that suffix into our buffer.  Otherwise, we're done.
+	 */
+	src = strchr(src, ',');
+	if (src)
+		strcpy(dst, src);
+
+	return buf;
 }
 
+static struct dentry *mount_subvol(const char *subvol_name, int flags,
+				   const char *device_name, char *data)
+{
+	struct dentry *root;
+	struct vfsmount *mnt;
+	char *newargs;
+
+	newargs = setup_root_args(data);
+	if (!newargs)
+		return ERR_PTR(-ENOMEM);
+	mnt = vfs_kern_mount(&btrfs_fs_type, flags, device_name,
+			     newargs);
+
+	if (PTR_RET(mnt) == -EBUSY) {
+		if (flags & MS_RDONLY) {
+			mnt = vfs_kern_mount(&btrfs_fs_type, flags & ~MS_RDONLY, device_name,
+					     newargs);
+		} else {
+			int r;
+			mnt = vfs_kern_mount(&btrfs_fs_type, flags | MS_RDONLY, device_name,
+					     newargs);
+			if (IS_ERR(mnt)) {
+				kfree(newargs);
+				return ERR_CAST(mnt);
+			}
+
+			r = btrfs_remount(mnt->mnt_sb, &flags, NULL);
+			if (r < 0) {
+				/* FIXME: release vfsmount mnt ??*/
+				kfree(newargs);
+				return ERR_PTR(r);
+			}
+		}
+	}
+
+	kfree(newargs);
+
+	if (IS_ERR(mnt))
+		return ERR_CAST(mnt);
+
+	root = mount_subtree(mnt, subvol_name);
+
+	if (!IS_ERR(root) && !is_subvolume_inode(root->d_inode)) {
+		struct super_block *s = root->d_sb;
+		dput(root);
+		root = ERR_PTR(-EINVAL);
+		deactivate_locked_super(s);
+		printk(KERN_ERR "BTRFS: '%s' is not a valid subvolume\n",
+				subvol_name);
+	}
+
+	return root;
+}
 
 /*
  * Find a superblock for the given device / mount point.
@@ -705,13 +1229,12 @@ static int btrfs_set_super(struct super_block *s, void *data)
  *	  for multiple device setup.  Make sure to keep it in sync.
  */
 static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
-		const char *dev_name, void *data)
+		const char *device_name, void *data)
 {
 	struct block_device *bdev = NULL;
 	struct super_block *s;
 	struct dentry *root;
 	struct btrfs_fs_devices *fs_devices = NULL;
-	struct btrfs_root *tree_root = NULL;
 	struct btrfs_fs_info *fs_info = NULL;
 	fmode_t mode = FMODE_READ;
 	char *subvol_name = NULL;
@@ -724,21 +1247,20 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	error = btrfs_parse_early_options(data, mode, fs_type,
 					  &subvol_name, &subvol_objectid,
 					  &fs_devices);
-	if (error)
+	if (error) {
+		kfree(subvol_name);
 		return ERR_PTR(error);
+	}
 
-	error = btrfs_scan_one_device(dev_name, mode, fs_type, &fs_devices);
-	if (error)
-		goto error_free_subvol_name;
+	if (subvol_name) {
+		root = mount_subvol(subvol_name, flags, device_name, data);
+		kfree(subvol_name);
+		return root;
+	}
 
-	error = btrfs_open_devices(fs_devices, mode, fs_type);
+	error = btrfs_scan_one_device(device_name, mode, fs_type, &fs_devices);
 	if (error)
-		goto error_free_subvol_name;
-
-	if (!(flags & MS_RDONLY) && fs_devices->rw_devices == 0) {
-		error = -EACCES;
-		goto error_close_devices;
-	}
+		return ERR_PTR(error);
 
 	/*
 	 * Setup a dummy root and fs_info for test/set super.  This is because
@@ -747,129 +1269,281 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	 * then open_ctree will properly initialize everything later.
 	 */
 	fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_NOFS);
-	tree_root = kzalloc(sizeof(struct btrfs_root), GFP_NOFS);
-	if (!fs_info || !tree_root) {
+	if (!fs_info)
+		return ERR_PTR(-ENOMEM);
+
+	fs_info->fs_devices = fs_devices;
+
+	fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS);
+	fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS);
+	if (!fs_info->super_copy || !fs_info->super_for_commit) {
 		error = -ENOMEM;
+		goto error_fs_info;
+	}
+
+	error = btrfs_open_devices(fs_devices, mode, fs_type);
+	if (error)
+		goto error_fs_info;
+
+	if (!(flags & MS_RDONLY) && fs_devices->rw_devices == 0) {
+		error = -EACCES;
 		goto error_close_devices;
 	}
-	fs_info->tree_root = tree_root;
-	fs_info->fs_devices = fs_devices;
-	tree_root->fs_info = fs_info;
 
 	bdev = fs_devices->latest_bdev;
-	s = sget(fs_type, btrfs_test_super, btrfs_set_super, tree_root);
-	if (IS_ERR(s))
-		goto error_s;
+	s = sget(fs_type, btrfs_test_super, btrfs_set_super, flags | MS_NOSEC,
+		 fs_info);
+	if (IS_ERR(s)) {
+		error = PTR_ERR(s);
+		goto error_close_devices;
+	}
 
 	if (s->s_root) {
-		if ((flags ^ s->s_flags) & MS_RDONLY) {
-			deactivate_locked_super(s);
-			error = -EBUSY;
-			goto error_close_devices;
-		}
-
 		btrfs_close_devices(fs_devices);
-		kfree(fs_info);
-		kfree(tree_root);
+		free_fs_info(fs_info);
+		if ((flags ^ s->s_flags) & MS_RDONLY)
+			error = -EBUSY;
 	} else {
 		char b[BDEVNAME_SIZE];
 
-		s->s_flags = flags;
 		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
+		btrfs_sb(s)->bdev_holder = fs_type;
 		error = btrfs_fill_super(s, fs_devices, data,
 					 flags & MS_SILENT ? 1 : 0);
-		if (error) {
-			deactivate_locked_super(s);
-			goto error_free_subvol_name;
-		}
-
-		btrfs_sb(s)->fs_info->bdev_holder = fs_type;
-		s->s_flags |= MS_ACTIVE;
 	}
 
-	root = get_default_root(s, subvol_objectid);
-	if (IS_ERR(root)) {
-		error = PTR_ERR(root);
+	root = !error ? get_default_root(s, subvol_objectid) : ERR_PTR(error);
+	if (IS_ERR(root))
 		deactivate_locked_super(s);
-		goto error_free_subvol_name;
-	}
-	/* if they gave us a subvolume name bind mount into that */
-	if (strcmp(subvol_name, ".")) {
-		struct dentry *new_root;
-		mutex_lock(&root->d_inode->i_mutex);
-		new_root = lookup_one_len(subvol_name, root,
-				      strlen(subvol_name));
-		mutex_unlock(&root->d_inode->i_mutex);
-
-		if (IS_ERR(new_root)) {
-			dput(root);
-			deactivate_locked_super(s);
-			error = PTR_ERR(new_root);
-			goto error_free_subvol_name;
-		}
-		if (!new_root->d_inode) {
-			dput(root);
-			dput(new_root);
-			deactivate_locked_super(s);
-			error = -ENXIO;
-			goto error_free_subvol_name;
-		}
-		dput(root);
-		root = new_root;
-	}
 
-	kfree(subvol_name);
 	return root;
 
-error_s:
-	error = PTR_ERR(s);
 error_close_devices:
 	btrfs_close_devices(fs_devices);
-	kfree(fs_info);
-	kfree(tree_root);
-error_free_subvol_name:
-	kfree(subvol_name);
+error_fs_info:
+	free_fs_info(fs_info);
 	return ERR_PTR(error);
 }
 
+static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info,
+				     int new_pool_size, int old_pool_size)
+{
+	if (new_pool_size == old_pool_size)
+		return;
+
+	fs_info->thread_pool_size = new_pool_size;
+
+	btrfs_info(fs_info, "resize thread pool %d -> %d",
+	       old_pool_size, new_pool_size);
+
+	btrfs_workqueue_set_max(fs_info->workers, new_pool_size);
+	btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size);
+	btrfs_workqueue_set_max(fs_info->submit_workers, new_pool_size);
+	btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size);
+	btrfs_workqueue_set_max(fs_info->endio_workers, new_pool_size);
+	btrfs_workqueue_set_max(fs_info->endio_meta_workers, new_pool_size);
+	btrfs_workqueue_set_max(fs_info->endio_meta_write_workers,
+				new_pool_size);
+	btrfs_workqueue_set_max(fs_info->endio_write_workers, new_pool_size);
+	btrfs_workqueue_set_max(fs_info->endio_freespace_worker, new_pool_size);
+	btrfs_workqueue_set_max(fs_info->delayed_workers, new_pool_size);
+	btrfs_workqueue_set_max(fs_info->readahead_workers, new_pool_size);
+	btrfs_workqueue_set_max(fs_info->scrub_wr_completion_workers,
+				new_pool_size);
+}
+
+static inline void btrfs_remount_prepare(struct btrfs_fs_info *fs_info)
+{
+	set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
+}
+
+static inline void btrfs_remount_begin(struct btrfs_fs_info *fs_info,
+				       unsigned long old_opts, int flags)
+{
+	if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) &&
+	    (!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) ||
+	     (flags & MS_RDONLY))) {
+		/* wait for any defraggers to finish */
+		wait_event(fs_info->transaction_wait,
+			   (atomic_read(&fs_info->defrag_running) == 0));
+		if (flags & MS_RDONLY)
+			sync_filesystem(fs_info->sb);
+	}
+}
+
+static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info,
+					 unsigned long old_opts)
+{
+	/*
+	 * We need cleanup all defragable inodes if the autodefragment is
+	 * close or the fs is R/O.
+	 */
+	if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) &&
+	    (!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) ||
+	     (fs_info->sb->s_flags & MS_RDONLY))) {
+		btrfs_cleanup_defrag_inodes(fs_info);
+	}
+
+	clear_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
+}
+
 static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 {
-	struct btrfs_root *root = btrfs_sb(sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+	struct btrfs_root *root = fs_info->tree_root;
+	unsigned old_flags = sb->s_flags;
+	unsigned long old_opts = fs_info->mount_opt;
+	unsigned long old_compress_type = fs_info->compress_type;
+	u64 old_max_inline = fs_info->max_inline;
+	u64 old_alloc_start = fs_info->alloc_start;
+	int old_thread_pool_size = fs_info->thread_pool_size;
+	unsigned int old_metadata_ratio = fs_info->metadata_ratio;
 	int ret;
 
+	sync_filesystem(sb);
+	btrfs_remount_prepare(fs_info);
+
 	ret = btrfs_parse_options(root, data);
-	if (ret)
-		return -EINVAL;
+	if (ret) {
+		ret = -EINVAL;
+		goto restore;
+	}
+
+	btrfs_remount_begin(fs_info, old_opts, *flags);
+	btrfs_resize_thread_pool(fs_info,
+		fs_info->thread_pool_size, old_thread_pool_size);
 
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
-		return 0;
+		goto out;
 
 	if (*flags & MS_RDONLY) {
+		/*
+		 * this also happens on 'umount -rf' or on shutdown, when
+		 * the filesystem is busy.
+		 */
+		cancel_work_sync(&fs_info->async_reclaim_work);
+
+		/* wait for the uuid_scan task to finish */
+		down(&fs_info->uuid_tree_rescan_sem);
+		/* avoid complains from lockdep et al. */
+		up(&fs_info->uuid_tree_rescan_sem);
+
 		sb->s_flags |= MS_RDONLY;
 
-		ret =  btrfs_commit_super(root);
-		WARN_ON(ret);
+		btrfs_dev_replace_suspend_for_unmount(fs_info);
+		btrfs_scrub_cancel(fs_info);
+		btrfs_pause_balance(fs_info);
+
+		ret = btrfs_commit_super(root);
+		if (ret)
+			goto restore;
 	} else {
-		if (root->fs_info->fs_devices->rw_devices == 0)
-			return -EACCES;
+		if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) {
+			btrfs_err(fs_info,
+				"Remounting read-write after error is not allowed");
+			ret = -EINVAL;
+			goto restore;
+		}
+		if (fs_info->fs_devices->rw_devices == 0) {
+			ret = -EACCES;
+			goto restore;
+		}
+
+		if (fs_info->fs_devices->missing_devices >
+		     fs_info->num_tolerated_disk_barrier_failures &&
+		    !(*flags & MS_RDONLY)) {
+			btrfs_warn(fs_info,
+				"too many missing devices, writeable remount is not allowed");
+			ret = -EACCES;
+			goto restore;
+		}
 
-		if (btrfs_super_log_root(&root->fs_info->super_copy) != 0)
-			return -EINVAL;
+		if (btrfs_super_log_root(fs_info->super_copy) != 0) {
+			ret = -EINVAL;
+			goto restore;
+		}
 
-		ret = btrfs_cleanup_fs_roots(root->fs_info);
-		WARN_ON(ret);
+		ret = btrfs_cleanup_fs_roots(fs_info);
+		if (ret)
+			goto restore;
 
 		/* recover relocation */
+		mutex_lock(&fs_info->cleaner_mutex);
 		ret = btrfs_recover_relocation(root);
-		WARN_ON(ret);
+		mutex_unlock(&fs_info->cleaner_mutex);
+		if (ret)
+			goto restore;
+
+		ret = btrfs_resume_balance_async(fs_info);
+		if (ret)
+			goto restore;
+
+		ret = btrfs_resume_dev_replace_async(fs_info);
+		if (ret) {
+			btrfs_warn(fs_info, "failed to resume dev_replace");
+			goto restore;
+		}
 
+		if (!fs_info->uuid_root) {
+			btrfs_info(fs_info, "creating UUID tree");
+			ret = btrfs_create_uuid_tree(fs_info);
+			if (ret) {
+				btrfs_warn(fs_info, "failed to create the UUID tree %d", ret);
+				goto restore;
+			}
+		}
 		sb->s_flags &= ~MS_RDONLY;
 	}
+out:
+	wake_up_process(fs_info->transaction_kthread);
+	btrfs_remount_cleanup(fs_info, old_opts);
+	return 0;
+
+restore:
+	/* We've hit an error - don't reset MS_RDONLY */
+	if (sb->s_flags & MS_RDONLY)
+		old_flags |= MS_RDONLY;
+	sb->s_flags = old_flags;
+	fs_info->mount_opt = old_opts;
+	fs_info->compress_type = old_compress_type;
+	fs_info->max_inline = old_max_inline;
+	mutex_lock(&fs_info->chunk_mutex);
+	fs_info->alloc_start = old_alloc_start;
+	mutex_unlock(&fs_info->chunk_mutex);
+	btrfs_resize_thread_pool(fs_info,
+		old_thread_pool_size, fs_info->thread_pool_size);
+	fs_info->metadata_ratio = old_metadata_ratio;
+	btrfs_remount_cleanup(fs_info, old_opts);
+	return ret;
+}
 
+/* Used to sort the devices by max_avail(descending sort) */
+static int btrfs_cmp_device_free_bytes(const void *dev_info1,
+				       const void *dev_info2)
+{
+	if (((struct btrfs_device_info *)dev_info1)->max_avail >
+	    ((struct btrfs_device_info *)dev_info2)->max_avail)
+		return -1;
+	else if (((struct btrfs_device_info *)dev_info1)->max_avail <
+		 ((struct btrfs_device_info *)dev_info2)->max_avail)
+		return 1;
+	else
 	return 0;
 }
 
 /*
+ * 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);
+}
+
+/*
  * The helper to calc the free space on the devices that can be used to store
  * file data.
  */
@@ -884,34 +1558,39 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 	u64 avail_space;
 	u64 used_space;
 	u64 min_stripe_size;
-	int min_stripes = 1;
+	int min_stripes = 1, num_stripes = 1;
 	int i = 0, nr_devices;
 	int ret;
 
-	nr_devices = fs_info->fs_devices->rw_devices;
+	nr_devices = fs_info->fs_devices->open_devices;
 	BUG_ON(!nr_devices);
 
-	devices_info = kmalloc(sizeof(*devices_info) * nr_devices,
+	devices_info = kmalloc_array(nr_devices, sizeof(*devices_info),
 			       GFP_NOFS);
 	if (!devices_info)
 		return -ENOMEM;
 
 	/* calc min stripe number for data space alloction */
 	type = btrfs_get_alloc_profile(root, 1);
-	if (type & BTRFS_BLOCK_GROUP_RAID0)
+	if (type & BTRFS_BLOCK_GROUP_RAID0) {
 		min_stripes = 2;
-	else if (type & BTRFS_BLOCK_GROUP_RAID1)
+		num_stripes = nr_devices;
+	} else if (type & BTRFS_BLOCK_GROUP_RAID1) {
 		min_stripes = 2;
-	else if (type & BTRFS_BLOCK_GROUP_RAID10)
+		num_stripes = 2;
+	} else if (type & BTRFS_BLOCK_GROUP_RAID10) {
 		min_stripes = 4;
+		num_stripes = 4;
+	}
 
 	if (type & BTRFS_BLOCK_GROUP_DUP)
 		min_stripe_size = 2 * BTRFS_STRIPE_LEN;
 	else
 		min_stripe_size = BTRFS_STRIPE_LEN;
 
-	list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
-		if (!device->in_fs_metadata)
+	list_for_each_entry(device, &fs_devices->devices, dev_list) {
+		if (!device->in_fs_metadata || !device->bdev ||
+		    device->is_tgtdev_for_dev_replace)
 			continue;
 
 		avail_space = device->total_bytes - device->bytes_used;
@@ -972,13 +1651,16 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 	i = nr_devices - 1;
 	avail_space = 0;
 	while (nr_devices >= min_stripes) {
+		if (num_stripes > nr_devices)
+			num_stripes = nr_devices;
+
 		if (devices_info[i].max_avail >= min_stripe_size) {
 			int j;
 			u64 alloc_size;
 
-			avail_space += devices_info[i].max_avail * min_stripes;
+			avail_space += devices_info[i].max_avail * num_stripes;
 			alloc_size = devices_info[i].max_avail;
-			for (j = i + 1 - min_stripes; j <= i; j++)
+			for (j = i + 1 - num_stripes; j <= i; j++)
 				devices_info[j].max_avail -= alloc_size;
 		}
 		i--;
@@ -992,18 +1674,18 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 
 static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
-	struct btrfs_root *root = btrfs_sb(dentry->d_sb);
-	struct btrfs_super_block *disk_super = &root->fs_info->super_copy;
-	struct list_head *head = &root->fs_info->space_info;
+	struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb);
+	struct btrfs_super_block *disk_super = fs_info->super_copy;
+	struct list_head *head = &fs_info->space_info;
 	struct btrfs_space_info *found;
 	u64 total_used = 0;
 	u64 total_free_data = 0;
 	int bits = dentry->d_sb->s_blocksize_bits;
-	__be32 *fsid = (__be32 *)root->fs_info->fsid;
+	__be32 *fsid = (__be32 *)fs_info->fsid;
 	int ret;
 
 	/* holding chunk_muext to avoid allocating new chunks */
-	mutex_lock(&root->fs_info->chunk_mutex);
+	mutex_lock(&fs_info->chunk_mutex);
 	rcu_read_lock();
 	list_for_each_entry_rcu(found, head, list) {
 		if (found->flags & BTRFS_BLOCK_GROUP_DATA) {
@@ -1022,14 +1704,14 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bsize = dentry->d_sb->s_blocksize;
 	buf->f_type = BTRFS_SUPER_MAGIC;
 	buf->f_bavail = total_free_data;
-	ret = btrfs_calc_avail_data_space(root, &total_free_data);
+	ret = btrfs_calc_avail_data_space(fs_info->tree_root, &total_free_data);
 	if (ret) {
-		mutex_unlock(&root->fs_info->chunk_mutex);
+		mutex_unlock(&fs_info->chunk_mutex);
 		return ret;
 	}
 	buf->f_bavail += total_free_data;
 	buf->f_bavail = buf->f_bavail >> bits;
-	mutex_unlock(&root->fs_info->chunk_mutex);
+	mutex_unlock(&fs_info->chunk_mutex);
 
 	/* We treat it as constant endianness (it doesn't matter _which_)
 	   because we want the fsid to come out the same whether mounted
@@ -1043,13 +1725,21 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	return 0;
 }
 
+static void btrfs_kill_super(struct super_block *sb)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+	kill_anon_super(sb);
+	free_fs_info(fs_info);
+}
+
 static struct file_system_type btrfs_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "btrfs",
 	.mount		= btrfs_mount,
-	.kill_sb	= kill_anon_super,
+	.kill_sb	= btrfs_kill_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("btrfs");
 
 /*
  * used by btrfsctl to scan devices when no FS is mounted
@@ -1073,6 +1763,13 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
 					    &btrfs_fs_type, &fs_devices);
 		break;
+	case BTRFS_IOC_DEVICES_READY:
+		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
+					    &btrfs_fs_type, &fs_devices);
+		if (ret)
+			break;
+		ret = !(fs_devices->num_devices == fs_devices->total_devices);
+		break;
 	}
 
 	kfree(vol);
@@ -1081,17 +1778,56 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 
 static int btrfs_freeze(struct super_block *sb)
 {
-	struct btrfs_root *root = btrfs_sb(sb);
-	mutex_lock(&root->fs_info->transaction_kthread_mutex);
-	mutex_lock(&root->fs_info->cleaner_mutex);
-	return 0;
+	struct btrfs_trans_handle *trans;
+	struct btrfs_root *root = btrfs_sb(sb)->tree_root;
+
+	trans = btrfs_attach_transaction_barrier(root);
+	if (IS_ERR(trans)) {
+		/* no transaction, don't bother */
+		if (PTR_ERR(trans) == -ENOENT)
+			return 0;
+		return PTR_ERR(trans);
+	}
+	return btrfs_commit_transaction(trans, root);
 }
 
 static int btrfs_unfreeze(struct super_block *sb)
 {
-	struct btrfs_root *root = btrfs_sb(sb);
-	mutex_unlock(&root->fs_info->cleaner_mutex);
-	mutex_unlock(&root->fs_info->transaction_kthread_mutex);
+	return 0;
+}
+
+static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb);
+	struct btrfs_fs_devices *cur_devices;
+	struct btrfs_device *dev, *first_dev = NULL;
+	struct list_head *head;
+	struct rcu_string *name;
+
+	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	cur_devices = fs_info->fs_devices;
+	while (cur_devices) {
+		head = &cur_devices->devices;
+		list_for_each_entry(dev, head, dev_list) {
+			if (dev->missing)
+				continue;
+			if (!dev->name)
+				continue;
+			if (!first_dev || dev->devid < first_dev->devid)
+				first_dev = dev;
+		}
+		cur_devices = cur_devices->seed;
+	}
+
+	if (first_dev) {
+		rcu_read_lock();
+		name = rcu_dereference(first_dev->name);
+		seq_escape(m, name->str, " \t\n\\");
+		rcu_read_unlock();
+	} else {
+		WARN_ON(1);
+	}
+	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 	return 0;
 }
 
@@ -1101,8 +1837,8 @@ static const struct super_operations btrfs_super_ops = {
 	.put_super	= btrfs_put_super,
 	.sync_fs	= btrfs_sync_fs,
 	.show_options	= btrfs_show_options,
+	.show_devname	= btrfs_show_devname,
 	.write_inode	= btrfs_write_inode,
-	.dirty_inode	= btrfs_dirty_inode,
 	.alloc_inode	= btrfs_alloc_inode,
 	.destroy_inode	= btrfs_destroy_inode,
 	.statfs		= btrfs_statfs,
@@ -1135,20 +1871,65 @@ static int btrfs_interface_init(void)
 static void btrfs_interface_exit(void)
 {
 	if (misc_deregister(&btrfs_misc) < 0)
-		printk(KERN_INFO "misc_deregister failed for control device");
+		printk(KERN_INFO "BTRFS: misc_deregister failed for control device\n");
+}
+
+static void btrfs_print_info(void)
+{
+	printk(KERN_INFO "Btrfs loaded"
+#ifdef CONFIG_BTRFS_DEBUG
+			", debug=on"
+#endif
+#ifdef CONFIG_BTRFS_ASSERT
+			", assert=on"
+#endif
+#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
+			", integrity-checker=on"
+#endif
+			"\n");
+}
+
+static int btrfs_run_sanity_tests(void)
+{
+	int ret;
+
+	ret = btrfs_init_test_fs();
+	if (ret)
+		return ret;
+
+	ret = btrfs_test_free_space_cache();
+	if (ret)
+		goto out;
+	ret = btrfs_test_extent_buffer_operations();
+	if (ret)
+		goto out;
+	ret = btrfs_test_extent_io();
+	if (ret)
+		goto out;
+	ret = btrfs_test_inodes();
+	if (ret)
+		goto out;
+	ret = btrfs_test_qgroups();
+out:
+	btrfs_destroy_test_fs();
+	return ret;
 }
 
 static int __init init_btrfs_fs(void)
 {
 	int err;
 
-	err = btrfs_init_sysfs();
+	err = btrfs_hash_init();
 	if (err)
 		return err;
 
-	err = btrfs_init_compress();
+	btrfs_props_init();
+
+	err = btrfs_init_sysfs();
 	if (err)
-		goto free_sysfs;
+		goto free_hash;
+
+	btrfs_init_compress();
 
 	err = btrfs_init_cachep();
 	if (err)
@@ -1162,19 +1943,56 @@ static int __init init_btrfs_fs(void)
 	if (err)
 		goto free_extent_io;
 
-	err = btrfs_interface_init();
+	err = ordered_data_init();
 	if (err)
 		goto free_extent_map;
 
+	err = btrfs_delayed_inode_init();
+	if (err)
+		goto free_ordered_data;
+
+	err = btrfs_auto_defrag_init();
+	if (err)
+		goto free_delayed_inode;
+
+	err = btrfs_delayed_ref_init();
+	if (err)
+		goto free_auto_defrag;
+
+	err = btrfs_prelim_ref_init();
+	if (err)
+		goto free_prelim_ref;
+
+	err = btrfs_interface_init();
+	if (err)
+		goto free_delayed_ref;
+
+	btrfs_init_lockdep();
+
+	btrfs_print_info();
+
+	err = btrfs_run_sanity_tests();
+	if (err)
+		goto unregister_ioctl;
+
 	err = register_filesystem(&btrfs_fs_type);
 	if (err)
 		goto unregister_ioctl;
 
-	printk(KERN_INFO "%s loaded\n", BTRFS_BUILD_VERSION);
 	return 0;
 
 unregister_ioctl:
 	btrfs_interface_exit();
+free_prelim_ref:
+	btrfs_prelim_ref_exit();
+free_delayed_ref:
+	btrfs_delayed_ref_exit();
+free_auto_defrag:
+	btrfs_auto_defrag_exit();
+free_delayed_inode:
+	btrfs_delayed_inode_exit();
+free_ordered_data:
+	ordered_data_exit();
 free_extent_map:
 	extent_map_exit();
 free_extent_io:
@@ -1183,14 +2001,20 @@ free_cachep:
 	btrfs_destroy_cachep();
 free_compress:
 	btrfs_exit_compress();
-free_sysfs:
 	btrfs_exit_sysfs();
+free_hash:
+	btrfs_hash_exit();
 	return err;
 }
 
 static void __exit exit_btrfs_fs(void)
 {
 	btrfs_destroy_cachep();
+	btrfs_delayed_ref_exit();
+	btrfs_auto_defrag_exit();
+	btrfs_delayed_inode_exit();
+	btrfs_prelim_ref_exit();
+	ordered_data_exit();
 	extent_map_exit();
 	extent_io_exit();
 	btrfs_interface_exit();
@@ -1198,9 +2022,10 @@ static void __exit exit_btrfs_fs(void)
 	btrfs_exit_sysfs();
 	btrfs_cleanup_fs_uuids();
 	btrfs_exit_compress();
+	btrfs_hash_exit();
 }
 
-module_init(init_btrfs_fs)
+late_initcall(init_btrfs_fs);
 module_exit(exit_btrfs_fs)
 
 MODULE_LICENSE("GPL");