Don't just loop indefinitely when an obfuscated name comes up as a
duplicate. Count the number of times we've found a duplicate and if
if it gets excessive despite choosing names at random, just give up
and use the original name without obfuscation.
Technically, a typical 5-character name has 255 other names that can
have the same hash value. But the algorithm doesn't hit all
possible names (far from it) so duplicates are still possible.
Signed-off-by: Alex Elder <aelder@xxxxxxx>
The only change worth mentioning from the last version posted is
that the duplicate count is now updated inside the loop that
searches the name table.
---
db/metadump.c | 32 ++++++++++++++++++++++++--------
1 file changed, 24 insertions(+), 8 deletions(-)
Index: b/db/metadump.c
===================================================================
--- a/db/metadump.c
+++ b/db/metadump.c
@@ -29,6 +29,14 @@
#define DEFAULT_MAX_EXT_SIZE 1000
+/*
+ * It's possible that multiple files in a directory (or attributes
+ * in a file) produce the same obfuscated name. If that happens, we
+ * try to create another one. After several rounds of this though,
+ * we just give up and leave the original name as-is.
+ */
+#define DUP_MAX 5 /* Max duplicates before we give up */
+
/* copy all metadata structures to/from a file */
static int metadump_f(int argc, char **argv);
@@ -437,8 +445,9 @@ generate_obfuscated_name(
{
xfs_dahash_t hash;
name_ent_t *p;
- int dup;
+ int dup = 0;
uchar_t newname[NAME_MAX];
+ uchar_t *newp;
/*
* Our obfuscation algorithm requires at least 5-character
@@ -471,19 +480,17 @@ generate_obfuscated_name(
do {
int i;
xfs_dahash_t newhash = 0;
- uchar_t *newp = &newname[0];
uchar_t *first;
uchar_t high_bit;
int shift;
- dup = 0;
-
/*
* The beginning of the obfuscated name can be
* pretty much anything, so fill it in with random
* characters. Accumulate its new hash value as we
* go.
*/
+ newp = &newname[0];
for (i = 0; i < namelen - 5; i++) {
*newp = random_filename_char();
newhash = *newp ^ rol32(newhash, 7);
@@ -531,14 +538,22 @@ generate_obfuscated_name(
ASSERT(libxfs_da_hashname(newname, namelen) == hash);
+ /*
+ * Search the name table to be sure we don't produce
+ * a name that's already been used.
+ */
for (p = nametable[hash % NAME_TABLE_SIZE]; p; p = p->next) {
if (p->hash == hash && p->namelen == namelen &&
!memcmp(p->name, newname, namelen)) {
- dup = 1;
+ dup++;
break;
}
}
- } while (dup);
+ } while (dup && dup < DUP_MAX);
+
+ /* Use the original name if we got too many dups. */
+
+ newp = dup < DUP_MAX ? newname : name;
/* Create an entry for the name in the name table */
@@ -547,7 +562,7 @@ generate_obfuscated_name(
return;
p->namelen = namelen;
- memcpy(p->name, newname, namelen);
+ memcpy(p->name, newp, namelen);
p->hash = hash;
p->next = nametable[hash % NAME_TABLE_SIZE];
@@ -555,7 +570,8 @@ generate_obfuscated_name(
/* Update the caller's copy with the obfuscated name */
- memcpy(name, newname, namelen);
+ if (newp != name)
+ memcpy(name, newp, namelen);
}
static void
_______________________________________________
xfs mailing list
xfs@xxxxxxxxxxx
http://oss.sgi.com/mailman/listinfo/xfs
