IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an
email to Administrator. User accounts are meant only to access repo
and report issues and/or generate pull requests.
This is a purpose-specific Git hosting for
BaseALT
projects. Thank you for your understanding!
Только зарегистрированные пользователи имеют доступ к сервису!
Для получения аккаунта, обратитесь к администратору.
I have some problems resolving the last 3 ones in attrib_handlers.c. In line
251 the function ldb_dn_explode_casefold is called with mem_ctx as the first
argument. Looking at ldb_dn_explode_casefold I see that the first argument it
expects is a struct ldb_context. I could certainly add a cast to (struct
ldb_context *) to that call, but I would assume that this is the wrong fix. Is
it possible that attrib_handlers.c:251 and :254 should have ldb and not
mem_ctx as the first argument?
Can anybody from Samba4 clarify this for me and apply the correct fix?
Thanks a lot.
Volker
the moment) but winbindd isn't run in the build farm
so hopefully won't break anything too badly - I don't
want to lose this.
If winbindd starts offline then it falls back to using
MS-RPC backend. On going online it needs to reset the
backend and try and go to using the AD backend code if
possible, as the MS-RPC sequence number fetch just returns
1 as the sequence number if run against an AD DC.
In addition, the winbindd async child may end up
with the AD backend whilst the main winbindd - which
still contacts the DC for some non-async calls, is
left using MS-RPC. This can cause some trouble (as
you can imagine :-).
Attempt to ensure both main winbindd and async children
us AD backends on going online.
Jeremy.
The attached patch cleans up pam_winbind a tiny bit. Instead of making
exceptions for all pam implementations except for Linux' it's better
to make an exception for the only pam implementation which is
different from all the others. This is equivalent to what pam_smb_auth
does already.
-----------------
Jeremy
including SOCKET_WRAPPER_PCAP_FILE support
but I just noticed that samba don't use recv()/send()
on the socket, so the capture only contain connect()/close()
metze
we now don't compile mostly each .c file twice.
- we use PICFLAG for all object files
- PICFLAG defaults to PIE_CFLAGS and is then overwritten
if the system supports shared libraries
as we currently always use -fPIE if available
(and at least on linux -fPIE produces the same code as -fPIC)
it doesn't change anything in the resulting code.
"high performance" binaries can be build with
"--disable-pie --disable-shared" if someone really needs to...
metze
password at next logon" code. The "password last set time" of zero now
means "user must change password", because that's how windows seems to
use it. The "can change" and "must change" times are now calculated
based on the "last set" time and policies.
We use the "can change" field now to indicate that a user cannot change
a password by putting MAX_TIME_T in it (so long as "last set" time isn't
zero). Based on this, we set the password-can-change bit in the
faked secdesc.
