doesn't keep track of the struct's size we enumerate. W2K doesn't

calculate them and always reply a size of 32 bytes whereas NT4 did the
maths. Anyway, it looks like the clients don't complain.

in query_dom_info() at level 2, return the real number of users and
groups. That's the fix to the W95/98 userlist bug !

as W95/98 does a query_dom_info(2) followed by a query_disp_info(4) on
the SAME context handle (err we call it an lsa policy handle ! plain
wrong name), I was tempted to keep the snapshoot in memory, to prevent
2 full user db enumerations in a row and just have one shared. But if some
client does the 2 calls on two different handles, we would have 2 copies
in memory not free'ed before the samr_close().

We still have too many fixed constant and too many magic values in that
code. And btw, I really hates how the sequence number is generated !

        J.F.
(This used to be commit c0178e1a03f8225e5b350feb8fcbfb02f43327b4)

1 files changed, 0 insertions, 2 deletions

diff --git a/source3/include/rpc_samr.h b/source3/include/rpc_samr.h
index 777dfa1e46..8b1a2b6ab8 100644
--- a/source3/include/rpc_samr.h
+++ b/source3/include/rpc_samr.h
@@ -148,12 +148,10 @@ SamrTestPrivateFunctionsUser
 
 typedef struct _DISP_USER_INFO {
 	SAM_ACCOUNT *sam;
-	uint32 size;
 } DISP_USER_INFO;
 
 typedef struct _DISP_GROUP_INFO {
 	DOMAIN_GRP *grp;
-	uint32 size;
 } DISP_GROUP_INFO;