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
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 00e9703..9b329b5 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -181,7 +181,7 @@
__be32 provided;
__u32 calculated;
- if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (!jbd2_journal_has_csum_v2or3(j))
return 1;
tail = (struct jbd2_journal_block_tail *)(buf + j->j_blocksize -
@@ -205,7 +205,7 @@
int nr = 0, size = journal->j_blocksize;
int tag_bytes = journal_tag_bytes(journal);
- if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (jbd2_journal_has_csum_v2or3(journal))
size -= sizeof(struct jbd2_journal_block_tail);
tagp = &bh->b_data[sizeof(journal_header_t)];
@@ -338,10 +338,11 @@
return err;
}
-static inline unsigned long long read_tag_block(int tag_bytes, journal_block_tag_t *tag)
+static inline unsigned long long read_tag_block(journal_t *journal,
+ journal_block_tag_t *tag)
{
unsigned long long block = be32_to_cpu(tag->t_blocknr);
- if (tag_bytes > JBD2_TAG_SIZE32)
+ if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32;
return block;
}
@@ -384,7 +385,7 @@
__be32 provided;
__u32 calculated;
- if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (!jbd2_journal_has_csum_v2or3(j))
return 1;
h = buf;
@@ -399,17 +400,21 @@
static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag,
void *buf, __u32 sequence)
{
+ journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag;
__u32 csum32;
__be32 seq;
- if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (!jbd2_journal_has_csum_v2or3(j))
return 1;
seq = cpu_to_be32(sequence);
csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq));
csum32 = jbd2_chksum(j, csum32, buf, j->j_blocksize);
- return tag->t_checksum == cpu_to_be16(csum32);
+ if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+ return tag3->t_checksum == cpu_to_be32(csum32);
+ else
+ return tag->t_checksum == cpu_to_be16(csum32);
}
static int do_one_pass(journal_t *journal,
@@ -513,8 +518,7 @@
switch(blocktype) {
case JBD2_DESCRIPTOR_BLOCK:
/* Verify checksum first */
- if (JBD2_HAS_INCOMPAT_FEATURE(journal,
- JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (jbd2_journal_has_csum_v2or3(journal))
descr_csum_size =
sizeof(struct jbd2_journal_block_tail);
if (descr_csum_size > 0 &&
@@ -575,7 +579,7 @@
unsigned long long blocknr;
J_ASSERT(obh != NULL);
- blocknr = read_tag_block(tag_bytes,
+ blocknr = read_tag_block(journal,
tag);
/* If the block has been
@@ -814,7 +818,7 @@
__be32 provided;
__u32 calculated;
- if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (!jbd2_journal_has_csum_v2or3(j))
return 1;
tail = (struct jbd2_journal_revoke_tail *)(buf + j->j_blocksize -
