Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "Improvements to ext4's block allocator performance for very large file
  systems, especially when the file system or files which are highly
  fragmented. There is a new mount option, prefetch_block_bitmaps which
  will pull in the block bitmaps and set up the in-memory buddy bitmaps
  when the file system is initially mounted.

  Beyond that, a lot of bug fixes and cleanups. In particular, a number
  of changes to make ext4 more robust in the face of write errors or
  file system corruptions"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (46 commits)
  ext4: limit the length of per-inode prealloc list
  ext4: reorganize if statement of ext4_mb_release_context()
  ext4: add mb_debug logging when there are lost chunks
  ext4: Fix comment typo "the the".
  jbd2: clean up checksum verification in do_one_pass()
  ext4: change to use fallthrough macro
  ext4: remove unused parameter of ext4_generic_delete_entry function
  mballoc: replace seq_printf with seq_puts
  ext4: optimize the implementation of ext4_mb_good_group()
  ext4: delete invalid comments near ext4_mb_check_limits()
  ext4: fix typos in ext4_mb_regular_allocator() comment
  ext4: fix checking of directory entry validity for inline directories
  fs: prevent BUG_ON in submit_bh_wbc()
  ext4: correctly restore system zone info when remount fails
  ext4: handle add_system_zone() failure in ext4_setup_system_zone()
  ext4: fold ext4_data_block_valid_rcu() into the caller
  ext4: check journal inode extents more carefully
  ext4: don't allow overlapping system zones
  ext4: handle error of ext4_setup_system_zone() on remount
  ext4: delete the invalid BUGON in ext4_mb_load_buddy_gfp()
  ...

3 files changed, 48 insertions, 47 deletions

diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index e4944436e733..17fdc482f554 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1285,7 +1285,7 @@ journal_t *jbd2_journal_init_inode(struct inode *inode)
  * superblock as being NULL to prevent the journal destroy from writing
  * back a bogus superblock.
  */
-static void journal_fail_superblock (journal_t *journal)
+static void journal_fail_superblock(journal_t *journal)
 {
 	struct buffer_head *bh = journal->j_sb_buffer;
 	brelse(bh);
@@ -1367,8 +1367,10 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags)
 	int ret;
 
 	/* Buffer got discarded which means block device got invalidated */
-	if (!buffer_mapped(bh))
+	if (!buffer_mapped(bh)) {
+		unlock_buffer(bh);
 		return -EIO;
+	}
 
 	trace_jbd2_write_superblock(journal, write_flags);
 	if (!(journal->j_flags & JBD2_BARRIER))
@@ -1815,7 +1817,7 @@ int jbd2_journal_destroy(journal_t *journal)
 
 
 /**
- *int jbd2_journal_check_used_features () - Check if features specified are used.
+ *int jbd2_journal_check_used_features() - Check if features specified are used.
  * @journal: Journal to check.
  * @compat: bitmask of compatible features
  * @ro: bitmask of features that force read-only mount
@@ -1825,7 +1827,7 @@ int jbd2_journal_destroy(journal_t *journal)
  * features.  Return true (non-zero) if it does.
  **/
 
-int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat,
+int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat,
 				 unsigned long ro, unsigned long incompat)
 {
 	journal_superblock_t *sb;
@@ -1860,7 +1862,7 @@ int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat,
  * all of a given set of features on this journal.  Return true
  * (non-zero) if it can. */
 
-int jbd2_journal_check_available_features (journal_t *journal, unsigned long compat,
+int jbd2_journal_check_available_features(journal_t *journal, unsigned long compat,
 				      unsigned long ro, unsigned long incompat)
 {
 	if (!compat && !ro && !incompat)
@@ -1882,7 +1884,7 @@ int jbd2_journal_check_available_features (journal_t *journal, unsigned long com
 }
 
 /**
- * int jbd2_journal_set_features () - Mark a given journal feature in the superblock
+ * int jbd2_journal_set_features() - Mark a given journal feature in the superblock
  * @journal: Journal to act on.
  * @compat: bitmask of compatible features
  * @ro: bitmask of features that force read-only mount
@@ -1893,7 +1895,7 @@ int jbd2_journal_check_available_features (journal_t *journal, unsigned long com
  *
  */
 
-int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
+int jbd2_journal_set_features(journal_t *journal, unsigned long compat,
 			  unsigned long ro, unsigned long incompat)
 {
 #define INCOMPAT_FEATURE_ON(f) \
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 2ed278f0dced..faa97d748474 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -690,14 +690,11 @@ static int do_one_pass(journal_t *journal,
 			 * number. */
 			if (pass == PASS_SCAN &&
 			    jbd2_has_feature_checksum(journal)) {
-				int chksum_err, chksum_seen;
 				struct commit_header *cbh =
 					(struct commit_header *)bh->b_data;
 				unsigned found_chksum =
 					be32_to_cpu(cbh->h_chksum[0]);
 
-				chksum_err = chksum_seen = 0;
-
 				if (info->end_transaction) {
 					journal->j_failed_commit =
 						info->end_transaction;
@@ -705,42 +702,23 @@ static int do_one_pass(journal_t *journal,
 					break;
 				}
 
-				if (crc32_sum == found_chksum &&
-				    cbh->h_chksum_type == JBD2_CRC32_CHKSUM &&
-				    cbh->h_chksum_size ==
-						JBD2_CRC32_CHKSUM_SIZE)
-				       chksum_seen = 1;
-				else if (!(cbh->h_chksum_type == 0 &&
-					     cbh->h_chksum_size == 0 &&
-					     found_chksum == 0 &&
-					     !chksum_seen))
-				/*
-				 * If fs is mounted using an old kernel and then
-				 * kernel with journal_chksum is used then we
-				 * get a situation where the journal flag has
-				 * checksum flag set but checksums are not
-				 * present i.e chksum = 0, in the individual
-				 * commit blocks.
-				 * Hence to avoid checksum failures, in this
-				 * situation, this extra check is added.
-				 */
-						chksum_err = 1;
-
-				if (chksum_err) {
-					info->end_transaction = next_commit_ID;
-
-					if (!jbd2_has_feature_async_commit(journal)) {
-						journal->j_failed_commit =
-							next_commit_ID;
-						brelse(bh);
-						break;
-					}
-				}
+				/* Neither checksum match nor unused? */
+				if (!((crc32_sum == found_chksum &&
+				       cbh->h_chksum_type ==
+						JBD2_CRC32_CHKSUM &&
+				       cbh->h_chksum_size ==
+						JBD2_CRC32_CHKSUM_SIZE) ||
+				      (cbh->h_chksum_type == 0 &&
+				       cbh->h_chksum_size == 0 &&
+				       found_chksum == 0)))
+					goto chksum_error;
+
 				crc32_sum = ~0;
 			}
 			if (pass == PASS_SCAN &&
 			    !jbd2_commit_block_csum_verify(journal,
 							   bh->b_data)) {
+			chksum_error:
 				info->end_transaction = next_commit_ID;
 
 				if (!jbd2_has_feature_async_commit(journal)) {
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index e91aad3637a2..43985738aa86 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2026,6 +2026,9 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
  */
 static void __jbd2_journal_unfile_buffer(struct journal_head *jh)
 {
+	J_ASSERT_JH(jh, jh->b_transaction != NULL);
+	J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
+
 	__jbd2_journal_temp_unlink_buffer(jh);
 	jh->b_transaction = NULL;
 }
@@ -2078,10 +2081,6 @@ out:
  * int jbd2_journal_try_to_free_buffers() - try to free page buffers.
  * @journal: journal for operation
  * @page: to try and free
- * @gfp_mask: we use the mask to detect how hard should we try to release
- * buffers. If __GFP_DIRECT_RECLAIM and __GFP_FS is set, we wait for commit
- * code to release the buffers.
- *
  *
  * For all the buffers on this page,
  * if they are fully written out ordered data, move them onto BUF_CLEAN
@@ -2112,11 +2111,11 @@ out:
  *
  * Return 0 on failure, 1 on success
  */
-int jbd2_journal_try_to_free_buffers(journal_t *journal,
-				struct page *page, gfp_t gfp_mask)
+int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page)
 {
 	struct buffer_head *head;
 	struct buffer_head *bh;
+	bool has_write_io_error = false;
 	int ret = 0;
 
 	J_ASSERT(PageLocked(page));
@@ -2141,11 +2140,26 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal,
 		jbd2_journal_put_journal_head(jh);
 		if (buffer_jbd(bh))
 			goto busy;
+
+		/*
+		 * If we free a metadata buffer which has been failed to
+		 * write out, the jbd2 checkpoint procedure will not detect
+		 * this failure and may lead to filesystem inconsistency
+		 * after cleanup journal tail.
+		 */
+		if (buffer_write_io_error(bh)) {
+			pr_err("JBD2: Error while async write back metadata bh %llu.",
+			       (unsigned long long)bh->b_blocknr);
+			has_write_io_error = true;
+		}
 	} while ((bh = bh->b_this_page) != head);
 
 	ret = try_to_free_buffers(page);
 
 busy:
+	if (has_write_io_error)
+		jbd2_journal_abort(journal, -EIO);
+
 	return ret;
 }
 
@@ -2572,6 +2586,13 @@ bool __jbd2_journal_refile_buffer(struct journal_head *jh)
 
 	was_dirty = test_clear_buffer_jbddirty(bh);
 	__jbd2_journal_temp_unlink_buffer(jh);
+
+	/*
+	 * b_transaction must be set, otherwise the new b_transaction won't
+	 * be holding jh reference
+	 */
+	J_ASSERT_JH(jh, jh->b_transaction != NULL);
+
 	/*
 	 * We set b_transaction here because b_next_transaction will inherit
 	 * our jh reference and thus __jbd2_journal_file_buffer() must not