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

Pull btrfs fixes and features from Chris Mason:
 "We've merged in the error handling patches from SuSE.  These are
  already shipping in the sles kernel, and they give btrfs the ability
  to abort transactions and go readonly on errors.  It involves a lot of
  churn as they clarify BUG_ONs, and remove the ones we now properly
  deal with.

  Josef reworked the way our metadata interacts with the page cache.
  page->private now points to the btrfs extent_buffer object, which
  makes everything faster.  He changed it so we write an whole extent
  buffer at a time instead of allowing individual pages to go down,,
  which will be important for the raid5/6 code (for the 3.5 merge
  window ;)

  Josef also made us more aggressive about dropping pages for metadata
  blocks that were freed due to COW.  Overall, our metadata caching is
  much faster now.

  We've integrated my patch for metadata bigger than the page size.
  This allows metadata blocks up to 64KB in size.  In practice 16K and
  32K seem to work best.  For workloads with lots of metadata, this cuts
  down the size of the extent allocation tree dramatically and fragments
  much less.

  Scrub was updated to support the larger block sizes, which ended up
  being a fairly large change (thanks Stefan Behrens).

  We also have an assortment of fixes and updates, especially to the
  balancing code (Ilya Dryomov), the back ref walker (Jan Schmidt) and
  the defragging code (Liu Bo)."

Fixed up trivial conflicts in fs/btrfs/scrub.c that were just due to
removal of the second argument to k[un]map_atomic() in commit
7ac687d9e047.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (75 commits)
  Btrfs: update the checks for mixed block groups with big metadata blocks
  Btrfs: update to the right index of defragment
  Btrfs: do not bother to defrag an extent if it is a big real extent
  Btrfs: add a check to decide if we should defrag the range
  Btrfs: fix recursive defragment with autodefrag option
  Btrfs: fix the mismatch of page->mapping
  Btrfs: fix race between direct io and autodefrag
  Btrfs: fix deadlock during allocating chunks
  Btrfs: show useful info in space reservation tracepoint
  Btrfs: don't use crc items bigger than 4KB
  Btrfs: flush out and clean up any block device pages during mount
  btrfs: disallow unequal data/metadata blocksize for mixed block groups
  Btrfs: enhance superblock sanity checks
  Btrfs: change scrub to support big blocks
  Btrfs: minor cleanup in scrub
  Btrfs: introduce common define for max number of mirrors
  Btrfs: fix infinite loop in btrfs_shrink_device()
  Btrfs: fix memory leak in resolver code
  Btrfs: allow dup for data chunks in mixed mode
  Btrfs: validate target profiles only if we are going to use them
  ...

1 files changed, 173 insertions, 19 deletions

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 81df3fec6a6d..8d5d380f7bdb 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -76,6 +76,9 @@ static const char *btrfs_decode_error(struct btrfs_fs_info *fs_info, int errno,
 	case -EROFS:
 		errstr = "Readonly filesystem";
 		break;
+	case -EEXIST:
+		errstr = "Object already exists";
+		break;
 	default:
 		if (nbuf) {
 			if (snprintf(nbuf, 16, "error %d", -errno) >= 0)
@@ -116,6 +119,8 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
 	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
 		sb->s_flags |= MS_RDONLY;
 		printk(KERN_INFO "btrfs is forced readonly\n");
+		__btrfs_scrub_cancel(fs_info);
+//		WARN_ON(1);
 	}
 }
 
@@ -124,25 +129,132 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
  * 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;
+	va_list args;
+	va_start(args, fmt);
 
 	/*
 	 * 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;
+
+  	errstr = btrfs_decode_error(fs_info, errno, nbuf);
+	if (fmt) {
+		struct va_format vaf = {
+			.fmt = fmt,
+			.va = &args,
+		};
+
+		printk(KERN_CRIT "BTRFS error (device %s) in %s:%d: %s (%pV)\n",
+			sb->s_id, function, line, errstr, &vaf);
+	} else {
+		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 */
+	if (sb->s_flags & MS_BORN) {
+		save_error_info(fs_info);
+		btrfs_handle_error(fs_info);
+	}
+	va_end(args);
+}
+
+const char *logtypes[] = {
+	"emergency",
+	"alert",
+	"critical",
+	"error",
+	"warning",
+	"notice",
+	"info",
+	"debug",
+};
+
+void btrfs_printk(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];
+
+	va_start(args, fmt);
+
+	if (fmt[0] == '<' && isdigit(fmt[1]) && fmt[2] == '>') {
+		strncpy(lvl, fmt, 3);
+		fmt += 3;
+		type = logtypes[fmt[1] - '0'];
+	} else
+		*lvl = '\0';
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	printk("%sBTRFS %s (device %s): %pV", lvl, type, sb->s_id, &vaf);
+}
+
+/*
+ * 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)
+{
+	WARN_ONCE(1, KERN_DEBUG "btrfs: Transaction aborted");
+	trans->aborted = errno;
+	/* Nothing used. The other threads that have joined this
+	 * transaction may be able to continue. */
+	if (!trans->blocks_used) {
+		btrfs_printk(root->fs_info, "Aborting unused transaction.\n");
 		return;
+	}
+	trans->transaction->aborted = errno;
+	__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 nbuf[16];
+	char *s_id = "<unknown>";
+	const char *errstr;
+	struct va_format vaf = { .fmt = fmt };
+	va_list args;
 
-	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);
-	save_error_info(fs_info);
+	if (fs_info)
+		s_id = fs_info->sb->s_id;
 
-	btrfs_handle_error(fs_info);
+	va_start(args, fmt);
+	vaf.va = &args;
+
+	errstr = btrfs_decode_error(fs_info, errno, nbuf);
+	if (fs_info->mount_opt & BTRFS_MOUNT_PANIC_ON_FATAL_ERROR)
+		panic(KERN_CRIT "BTRFS panic (device %s) in %s:%d: %pV (%s)\n",
+			s_id, function, line, &vaf, errstr);
+
+	printk(KERN_CRIT "BTRFS panic (device %s) in %s:%d: %pV (%s)\n",
+	       s_id, function, line, &vaf, errstr);
+	va_end(args);
+	/* Caller calls BUG() */
 }
 
 static void btrfs_put_super(struct super_block *sb)
@@ -166,7 +278,7 @@ enum {
 	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_check_integrity_print_mask, Opt_fatal_errors,
 	Opt_err,
 };
 
@@ -206,12 +318,14 @@ static match_table_t tokens = {
 	{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_fatal_errors, "fatal_errors=%s"},
 	{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)
 {
@@ -438,6 +552,18 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			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_err:
 			printk(KERN_INFO "btrfs: unrecognized mount option "
 			       "'%s'\n", p);
@@ -762,6 +888,8 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",inode_cache");
 	if (btrfs_test_opt(root, SKIP_BALANCE))
 		seq_puts(seq, ",skip_balance");
+	if (btrfs_test_opt(root, PANIC_ON_FATAL_ERROR))
+		seq_puts(seq, ",fatal_errors=panic");
 	return 0;
 }
 
@@ -995,11 +1123,20 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 {
 	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;
 
 	ret = btrfs_parse_options(root, data);
-	if (ret)
-		return -EINVAL;
+	if (ret) {
+		ret = -EINVAL;
+		goto restore;
+	}
 
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
 		return 0;
@@ -1007,26 +1144,44 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 	if (*flags & MS_RDONLY) {
 		sb->s_flags |= MS_RDONLY;
 
-		ret =  btrfs_commit_super(root);
-		WARN_ON(ret);
+		ret = btrfs_commit_super(root);
+		if (ret)
+			goto restore;
 	} else {
 		if (fs_info->fs_devices->rw_devices == 0)
-			return -EACCES;
+			ret = -EACCES;
+			goto restore;
 
 		if (btrfs_super_log_root(fs_info->super_copy) != 0)
-			return -EINVAL;
+			ret = -EINVAL;
+			goto restore;
 
 		ret = btrfs_cleanup_fs_roots(fs_info);
-		WARN_ON(ret);
+		if (ret)
+			goto restore;
 
 		/* recover relocation */
 		ret = btrfs_recover_relocation(root);
-		WARN_ON(ret);
+		if (ret)
+			goto restore;
 
 		sb->s_flags &= ~MS_RDONLY;
 	}
 
 	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;
+	fs_info->alloc_start = old_alloc_start;
+	fs_info->thread_pool_size = old_thread_pool_size;
+	fs_info->metadata_ratio = old_metadata_ratio;
+	return ret;
 }
 
 /* Used to sort the devices by max_avail(descending sort) */
@@ -1356,9 +1511,7 @@ static int __init init_btrfs_fs(void)
 	if (err)
 		return err;
 
-	err = btrfs_init_compress();
-	if (err)
-		goto free_sysfs;
+	btrfs_init_compress();
 
 	err = btrfs_init_cachep();
 	if (err)
@@ -1384,6 +1537,8 @@ static int __init init_btrfs_fs(void)
 	if (err)
 		goto unregister_ioctl;
 
+	btrfs_init_lockdep();
+
 	printk(KERN_INFO "%s loaded\n", BTRFS_BUILD_VERSION);
 	return 0;
 
@@ -1399,7 +1554,6 @@ free_cachep:
 	btrfs_destroy_cachep();
 free_compress:
 	btrfs_exit_compress();
-free_sysfs:
 	btrfs_exit_sysfs();
 	return err;
 }