diff options
author | Jean-François Micouleau <jfm@samba.org> | 2001-12-21 22:34:49 +0000 |
---|---|---|
committer | Jean-François Micouleau <jfm@samba.org> | 2001-12-21 22:34:49 +0000 |
commit | 0e550b2c11bde9a05167b237fb9910e2beccd14c (patch) | |
tree | 3567569d59bca94f542cf13b7c33c30f026b05fd /source3/auth/auth_rhosts.c | |
parent | 5829284a07463aa560527b38b69570444160e019 (diff) | |
download | samba-0e550b2c11bde9a05167b237fb9910e2beccd14c.tar.gz samba-0e550b2c11bde9a05167b237fb9910e2beccd14c.tar.bz2 samba-0e550b2c11bde9a05167b237fb9910e2beccd14c.zip |
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)
Diffstat (limited to 'source3/auth/auth_rhosts.c')
0 files changed, 0 insertions, 0 deletions