goto errout;
}
- journal->j_maxlen = EXT2_I_SIZE(&j_inode->i_ext2) /
+ journal->j_total_len = EXT2_I_SIZE(&j_inode->i_ext2) /
journal->j_blocksize;
#ifdef USE_INODE_IO
brelse(bh);
maxlen = ext2fs_blocks_count(&jsuper);
- journal->j_maxlen = (maxlen < 1ULL << 32) ? maxlen : (1ULL << 32) - 1;
+ journal->j_total_len = (maxlen < 1ULL << 32) ? maxlen : (1ULL << 32) - 1;
start++;
}
return EXT2_ET_CORRUPT_JOURNAL_SB;
}
- if (ntohl(jsb->s_maxlen) < journal->j_maxlen)
- journal->j_maxlen = ntohl(jsb->s_maxlen);
- else if (ntohl(jsb->s_maxlen) > journal->j_maxlen) {
+ if (ntohl(jsb->s_maxlen) < journal->j_total_len)
+ journal->j_total_len = ntohl(jsb->s_maxlen);
+ else if (ntohl(jsb->s_maxlen) > journal->j_total_len) {
com_err(ctx->program_name, EXT2_ET_CORRUPT_JOURNAL_SB,
_("%s: journal too short\n"),
ctx->device_name);
journal->j_transaction_sequence = journal->j_tail_sequence;
journal->j_tail = ntohl(jsb->s_start);
journal->j_first = ntohl(jsb->s_first);
- journal->j_last = ntohl(jsb->s_maxlen);
+ if (jbd2_has_feature_fast_commit(journal)) {
+ if (ntohl(jsb->s_maxlen) - jbd_get_num_fc_blks(jsb)
+ < JBD2_MIN_JOURNAL_BLOCKS) {
+ com_err(ctx->program_name, EXT2_ET_CORRUPT_JOURNAL_SB,
+ _("%s: incorrect fast commit blocks\n"),
+ ctx->device_name);
+ return EXT2_ET_CORRUPT_JOURNAL_SB;
+ }
+ journal->j_fc_last = ntohl(jsb->s_maxlen);
+ journal->j_last = journal->j_fc_last -
+ jbd_get_num_fc_blks(jsb);
+ journal->j_fc_first = journal->j_last + 1;
+ } else {
+ journal->j_last = ntohl(jsb->s_maxlen);
+ }
return 0;
}
memset (p, 0, ctx->fs->blocksize-sizeof(journal_header_t));
jsb->s_blocksize = htonl(ctx->fs->blocksize);
- jsb->s_maxlen = htonl(journal->j_maxlen);
+ jsb->s_maxlen = htonl(journal->j_total_len);
jsb->s_first = htonl(1);
/* Initialize the journal sequence number so that there is "no"
int nr_revoke_hits;
};
-enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY};
static int do_one_pass(journal_t *journal,
struct recovery_info *info, enum passtype pass);
static int scan_revoke_records(journal_t *, struct buffer_head *,
/* Do up to 128K of readahead */
max = start + (128 * 1024 / journal->j_blocksize);
- if (max > journal->j_maxlen)
- max = journal->j_maxlen;
+ if (max > journal->j_total_len)
+ max = journal->j_total_len;
/* Do the readahead itself. We'll submit MAXBUF buffer_heads at
* a time to the block device IO layer. */
*bhp = NULL;
- if (offset >= journal->j_maxlen) {
+ if (offset >= journal->j_total_len) {
printk(KERN_ERR "JBD2: corrupted journal superblock\n");
return -EFSCORRUPTED;
}
if (!jbd2_journal_has_csum_v2or3(j))
return 1;
- tail = (struct jbd2_journal_block_tail *)((char *)buf + j->j_blocksize -
+ tail = (struct jbd2_journal_block_tail *)(buf + j->j_blocksize -
sizeof(struct jbd2_journal_block_tail));
provided = tail->t_checksum;
tail->t_checksum = 0;
/* Make sure we wrap around the log correctly! */
#define wrap(journal, var) \
do { \
- if (var >= (journal)->j_last) \
- var -= ((journal)->j_last - (journal)->j_first); \
+ unsigned long _wrap_last = \
+ jbd2_has_feature_fast_commit(journal) ? \
+ (journal)->j_fc_last : (journal)->j_last; \
+ \
+ if (var >= _wrap_last) \
+ var -= (_wrap_last - (journal)->j_first); \
} while (0)
+static int fc_do_one_pass(journal_t *journal,
+ struct recovery_info *info, enum passtype pass)
+{
+ unsigned int expected_commit_id = info->end_transaction;
+ unsigned long next_fc_block;
+ struct buffer_head *bh;
+ int err = 0;
+
+ next_fc_block = journal->j_fc_first;
+ if (!journal->j_fc_replay_callback)
+ return 0;
+
+ while (next_fc_block <= journal->j_fc_last) {
+ jbd_debug(3, "Fast commit replay: next block %ld",
+ next_fc_block);
+ err = jread(&bh, journal, next_fc_block);
+ if (err) {
+ jbd_debug(3, "Fast commit replay: read error");
+ break;
+ }
+
+ jbd_debug(3, "Processing fast commit blk with seq %d");
+ err = journal->j_fc_replay_callback(journal, bh, pass,
+ next_fc_block - journal->j_fc_first,
+ expected_commit_id);
+ next_fc_block++;
+ if (err < 0 || err == JBD2_FC_REPLAY_STOP)
+ break;
+ err = 0;
+ }
+
+ if (err)
+ jbd_debug(3, "Fast commit replay failed, err = %d\n", err);
+
+ return err;
+}
+
/**
* jbd2_journal_recover - recovers a on-disk journal
* @journal: the journal to recover
err = err2;
/* Make sure all replayed data is on permanent storage */
if (journal->j_flags & JBD2_BARRIER) {
- err2 = blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
+ err2 = blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL);
if (!err)
err = err2;
}
__u32 crc32_sum = ~0; /* Transactional Checksums */
int descr_csum_size = 0;
int block_error = 0;
+ bool need_check_commit_time = false;
+ __u64 last_trans_commit_time = 0, commit_time;
/*
* First thing is to establish what we expect to find in the log
break;
jbd_debug(2, "Scanning for sequence ID %u at %lu/%lu\n",
- next_commit_ID, next_log_block, journal->j_last);
+ next_commit_ID, next_log_block,
+ jbd2_has_feature_fast_commit(journal) ?
+ journal->j_fc_last : journal->j_last);
/* Skip over each chunk of the transaction looking
* either the next descriptor block or the final commit
if (descr_csum_size > 0 &&
!jbd2_descriptor_block_csum_verify(journal,
bh->b_data)) {
- err = -EFSBADCRC;
- brelse(bh);
- goto failed;
+ /*
+ * PASS_SCAN can see stale blocks due to lazy
+ * journal init. Don't error out on those yet.
+ */
+ if (pass != PASS_SCAN) {
+ pr_err("JBD2: Invalid checksum recovering block %lu in log\n",
+ next_log_block);
+ err = -EFSBADCRC;
+ brelse(bh);
+ goto failed;
+ }
+ need_check_commit_time = true;
+ jbd_debug(1,
+ "invalid descriptor block found in %lu\n",
+ next_log_block);
}
/* If it is a valid descriptor block, replay it
if (pass != PASS_REPLAY) {
if (pass == PASS_SCAN &&
jbd2_has_feature_checksum(journal) &&
+ !need_check_commit_time &&
!info->end_transaction) {
if (calc_chksums(journal, bh,
&next_log_block,
* | GO TO NEXT "Journal Corruption"
* | TRANSACTION
* |
- * {(n+1)th transaction}
+ * {(n+1)th transanction}
* |
* _______|______________
* | |
* mentioned conditions. Hence assume
* "Interrupted Commit".)
*/
+ commit_time = be64_to_cpu(
+ ((struct commit_header *)bh->b_data)->h_commit_sec);
+ /*
+ * If need_check_commit_time is set, it means we are in
+ * PASS_SCAN and csum verify failed before. If
+ * commit_time is increasing, it's the same journal,
+ * otherwise it is stale journal block, just end this
+ * recovery.
+ */
+ if (need_check_commit_time) {
+ if (commit_time >= last_trans_commit_time) {
+ pr_err("JBD2: Invalid checksum found in transaction %u\n",
+ next_commit_ID);
+ err = -EFSBADCRC;
+ brelse(bh);
+ goto failed;
+ }
+ ignore_crc_mismatch:
+ /*
+ * It likely does not belong to same journal,
+ * just end this recovery with success.
+ */
+ jbd_debug(1, "JBD2: Invalid checksum ignored in transaction %u, likely stale data\n",
+ next_commit_ID);
+ err = 0;
+ brelse(bh);
+ goto done;
+ }
- /* Found an expected commit block: if checksums
- * are present verify them in PASS_SCAN; else not
+ /*
+ * Found an expected commit block: if checksums
+ * are present, verify them in PASS_SCAN; else not
* much to do other than move on to the next sequence
- * number. */
+ * 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;
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;
+ /* 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;
- if (!jbd2_has_feature_async_commit(journal)) {
- journal->j_failed_commit =
- next_commit_ID;
- brelse(bh);
- break;
- }
- }
crc32_sum = ~0;
}
if (pass == PASS_SCAN &&
!jbd2_commit_block_csum_verify(journal,
bh->b_data)) {
+ chksum_error:
+ if (commit_time < last_trans_commit_time)
+ goto ignore_crc_mismatch;
info->end_transaction = next_commit_ID;
if (!jbd2_has_feature_async_commit(journal)) {
break;
}
}
+ if (pass == PASS_SCAN)
+ last_trans_commit_time = commit_time;
brelse(bh);
next_commit_ID++;
continue;
case JBD2_REVOKE_BLOCK:
+ /*
+ * Check revoke block crc in pass_scan, if csum verify
+ * failed, check commit block time later.
+ */
+ if (pass == PASS_SCAN &&
+ !jbd2_descriptor_block_csum_verify(journal,
+ bh->b_data)) {
+ jbd_debug(1, "JBD2: invalid revoke block found in %lu\n",
+ next_log_block);
+ need_check_commit_time = true;
+ }
/* If we aren't in the REVOKE pass, then we can
* just skip over this block. */
if (pass != PASS_REVOKE) {
success = -EIO;
}
}
+
+ if (jbd2_has_feature_fast_commit(journal) && pass != PASS_REVOKE) {
+ err = fc_do_one_pass(journal, info, pass);
+ if (err)
+ success = err;
+ }
+
if (block_error && success == 0)
success = -EIO;
return success;
{
jbd2_journal_revoke_header_t *header;
int offset, max;
- unsigned csum_size = 0;
+ int csum_size = 0;
__u32 rcount;
int record_len = 4;
offset = sizeof(jbd2_journal_revoke_header_t);
rcount = be32_to_cpu(header->r_count);
- if (!jbd2_descriptor_block_csum_verify(journal, header))
- return -EFSBADCRC;
-
if (jbd2_journal_has_csum_v2or3(journal))
csum_size = sizeof(struct jbd2_journal_block_tail);
if (rcount > journal->j_blocksize - csum_size)
__jbd_kmalloc(__FUNCTION__, (size), (flags), journal_oom_retry)
#define jbd_rep_kmalloc(size, flags) \
__jbd_kmalloc(__FUNCTION__, (size), (flags), 1)
+#define jbd_get_num_fc_blks(jsb) \
+ (be32_to_cpu((jsb)->s_num_fc_blks) ? \
+ be32_to_cpu((jsb)->s_num_fc_blks) : JBD2_DEFAULT_FAST_COMMIT_BLOCKS)
+
#define JBD2_MIN_JOURNAL_BLOCKS 1024
+#define JBD2_DEFAULT_FAST_COMMIT_BLOCKS 256
/*
* Internal structures used by the logging mechanism:
#define JBD2_SUPERBLOCK_V1 3
#define JBD2_SUPERBLOCK_V2 4
#define JBD2_REVOKE_BLOCK 5
+#define JBD2_FC_BLOCK 6
/*
* Standard header for all descriptor blocks:
/* 0x0050 */
__u8 s_checksum_type; /* checksum type */
__u8 s_padding2[3];
- __be32 s_padding[42];
+/* 0x0054 */
+ __be32 s_num_fc_blks; /* Number of fast commit blocks */
+/* 0x0058 */
+ __be32 s_padding[41];
__be32 s_checksum; /* crc32c(superblock) */
/* 0x0100 */
#define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004
#define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008
#define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010
+#define JBD2_FEATURE_INCOMPAT_FAST_COMMIT 0x00000020
/* Features known to this kernel version: */
#define JBD2_KNOWN_COMPAT_FEATURES 0
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT| \
JBD2_FEATURE_INCOMPAT_64BIT|\
JBD2_FEATURE_INCOMPAT_CSUM_V2| \
- JBD2_FEATURE_INCOMPAT_CSUM_V3)
+ JBD2_FEATURE_INCOMPAT_CSUM_V3 | \
+ JBD2_FEATURE_INCOMPAT_FAST_COMMIT)
#ifdef NO_INLINE_FUNCS
extern size_t journal_tag_bytes(journal_t *journal);
JBD2_FEATURE_INCOMPAT_FUNCS(async_commit, ASYNC_COMMIT)
JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2)
JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3)
+JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT)
#if (defined(E2FSCK_INCLUDE_INLINE_FUNCS) || !defined(NO_INLINE_FUNCS))
/*
git://git.whamcloud.com / tools / e2fsprogs.git / commitdiff