commit
b37b452cb8c1f56b37b04abe7bffdede371ca361
Author: Rusty Russell <rusty@rustcorp.com.au>
Date: Thu Feb 4 23:59:54 2010 +1030
tdb: fix recovery reuse after crash
If a process (or the machine) dies after just after writing the
recovery head (pointing at the end of file), the recovery record will filled
with 0x42. This will not invoke a recovery on open, since rec.magic
!= TDB_RECOVERY_MAGIC.
Unfortunately, the first transaction commit will happily reuse that
area: tdb_recovery_allocate() doesn't check the magic. The recovery
record has length 0x42424242, and it writes that back into the
now-valid-looking transaction header) for the next comer (which
happens to be tdb_wipe_all in my tests).
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
rec.rec_len = 0;
- if (recovery_head != 0 &&
- methods->tdb_read(tdb, recovery_head, &rec, sizeof(rec), DOCONV()) == -1) {
- TDB_LOG((tdb, TDB_DEBUG_FATAL, "tdb_recovery_allocate: failed to read recovery record\n"));
- return -1;
+ if (recovery_head != 0) {
+ if (methods->tdb_read(tdb, recovery_head, &rec, sizeof(rec), DOCONV()) == -1) {
+ TDB_LOG((tdb, TDB_DEBUG_FATAL, "tdb_recovery_allocate: failed to read recovery record\n"));
+ return -1;
+ }
+ /* ignore invalid recovery regions: can happen in crash */
+ if (rec.magic != TDB_RECOVERY_MAGIC &&
+ rec.magic != TDB_RECOVERY_INVALID_MAGIC) {
+ recovery_head = 0;
+ }
}
*recovery_size = tdb_recovery_size(tdb);