jbd2: fix descriptor block size handling errors with journal_csum

It turns out that there are some serious problems with the on-disk
format of journal checksum v2.  The foremost is that the function to
calculate descriptor tag size returns sizes that are too big.  This
causes alignment issues on some architectures and is compounded by the
fact that some parts of jbd2 use the structure size (incorrectly) to
determine the presence of a 64bit journal instead of checking the
feature flags.

Therefore, introduce journal checksum v3, which enlarges the
descriptor block tag format to allow for full 32-bit checksums of
journal blocks, fix the journal tag function to return the correct
sizes, and fix the jbd2 recovery code to use feature flags to
determine 64bitness.

Add a few function helpers so we don't have to open-code quite so
many pieces.

Switching to a 16-byte block size was found to increase journal size
overhead by a maximum of 0.1%, to convert a 32-bit journal with no
checksumming to a 32-bit journal with checksum v3 enabled.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reported-by: TR Reardon <thomas_reardon@hotmail.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@vger.kernel.org

1 files changed, 25 insertions, 5 deletions

diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index d5b50a19463c..0dae71e9971c 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -159,7 +159,11 @@ typedef struct journal_header_s
  * journal_block_tag (in the descriptor).  The other h_chksum* fields are
  * not used.
  *
- * Checksum v1 and v2 are mutually exclusive features.
+ * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses
+ * journal_block_tag3_t to store a full 32-bit checksum.  Everything else
+ * is the same as v2.
+ *
+ * Checksum v1, v2, and v3 are mutually exclusive features.
  */
 struct commit_header {
 	__be32		h_magic;
@@ -179,6 +183,14 @@ struct commit_header {
  * raw struct shouldn't be used for pointer math or sizeof() - use
  * journal_tag_bytes(journal) instead to compute this.
  */
+typedef struct journal_block_tag3_s
+{
+	__be32		t_blocknr;	/* The on-disk block number */
+	__be32		t_flags;	/* See below */
+	__be32		t_blocknr_high; /* most-significant high 32bits. */
+	__be32		t_checksum;	/* crc32c(uuid+seq+block) */
+} journal_block_tag3_t;
+
 typedef struct journal_block_tag_s
 {
 	__be32		t_blocknr;	/* The on-disk block number */
@@ -187,9 +199,6 @@ typedef struct journal_block_tag_s
 	__be32		t_blocknr_high; /* most-significant high 32bits. */
 } journal_block_tag_t;
 
-#define JBD2_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high))
-#define JBD2_TAG_SIZE64 (sizeof(journal_block_tag_t))
-
 /* Tail of descriptor block, for checksumming */
 struct jbd2_journal_block_tail {
 	__be32		t_checksum;	/* crc32c(uuid+descr_block) */
@@ -284,6 +293,7 @@ typedef struct journal_superblock_s
 #define JBD2_FEATURE_INCOMPAT_64BIT		0x00000002
 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT	0x00000004
 #define JBD2_FEATURE_INCOMPAT_CSUM_V2		0x00000008
+#define JBD2_FEATURE_INCOMPAT_CSUM_V3		0x00000010
 
 /* Features known to this kernel version: */
 #define JBD2_KNOWN_COMPAT_FEATURES	JBD2_FEATURE_COMPAT_CHECKSUM
@@ -291,7 +301,8 @@ typedef struct journal_superblock_s
 #define JBD2_KNOWN_INCOMPAT_FEATURES	(JBD2_FEATURE_INCOMPAT_REVOKE | \
 					JBD2_FEATURE_INCOMPAT_64BIT | \
 					JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \
-					JBD2_FEATURE_INCOMPAT_CSUM_V2)
+					JBD2_FEATURE_INCOMPAT_CSUM_V2 | \
+					JBD2_FEATURE_INCOMPAT_CSUM_V3)
 
 #ifdef __KERNEL__
 
@@ -1296,6 +1307,15 @@ static inline int tid_geq(tid_t x, tid_t y)
 extern int jbd2_journal_blocks_per_page(struct inode *inode);
 extern size_t journal_tag_bytes(journal_t *journal);
 
+static inline int jbd2_journal_has_csum_v2or3(journal_t *journal)
+{
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) ||
+	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		return 1;
+
+	return 0;
+}
+
 /*
  * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for
  * transaction control blocks.