From 0e550b2c11bde9a05167b237fb9910e2beccd14c Mon Sep 17 00:00:00 2001 From: Jean-François Micouleau Date: Fri, 21 Dec 2001 22:34:49 +0000 Subject: 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) --- source3/include/rpc_samr.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'source3/include') 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; -- cgit