Volker Lendecke [Fri, 6 Oct 2006 14:39:47 +0000 (14:39 +0000)]
r19132: Fix some C++ warnings. Is there interest to have them in Samba4 as well?
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?
Jeremy Allison [Fri, 6 Oct 2006 02:04:57 +0000 (02:04 +0000)]
r19105: Ok - this is currently untested (but I'm testing it at
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 Allison [Thu, 5 Oct 2006 20:05:09 +0000 (20:05 +0000)]
r19103: From "Björn JACKE <bjoern@j3e.DE>":
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
(This used to be commit 8e5596470822d20740f86585a6cf67240f2face4)
r19093: speed up the samba3 build from 8mins to 5mins:-)
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...
Jim McDonough [Tue, 3 Oct 2006 17:14:18 +0000 (17:14 +0000)]
r19058: Implement "user cannot change password", and complete "user must change
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.
(This used to be commit 21abbeaee9b7f7cff1d34d048463c30cda44a2e3)
Jeremy Allison [Mon, 2 Oct 2006 23:34:03 +0000 (23:34 +0000)]
r19054: Callers of gencache may not have the rights to
open read/write. Allow them to fallback to read-only.
Jeremy
(This used to be commit ec526e1b882e3ade23f90c5e3d637c72b6839da5)
Volker Lendecke [Mon, 2 Oct 2006 13:30:05 +0000 (13:30 +0000)]
r19043: There's no point in #ifdef'ing the detection whether we were offered KRB5 in
SPNEGO, as long as we don't make use of it without krb libs. Makes the code a
bit simpler.
Volker Lendecke [Mon, 2 Oct 2006 08:38:54 +0000 (08:38 +0000)]
r19028: Implement getprinterinfo level 6 (only the status) and get rid of snum in the
getprinter calls. Survives the RPC-SAMBA3-SPOOLSS test which I will activate
when the Samba4 build farm has picked it up.
r19011: Attempt to fix the BSD RAW-CHKPATH failures: In Samba3 we rely on opendir
returning ENOTDIR when the file opened is not a directory. Can we merge this
back into Samba4?
Gerald Carter [Fri, 29 Sep 2006 20:31:09 +0000 (20:31 +0000)]
r19006: Final cleanups for the winreg libmsrpc functions.
Needs thorough testing but the code has been adapted
to the new rpccli_winreg_XX() API.
(This used to be commit c3d1c3ca4d9b23bdbba131563c751b8e0dc4c01f)
to get your machine related GPOs downloaded to /var/lib/samba/gpo_cache.
Detailed information about GPOs is currently only printed when setting a
higher debuglevel then 0.
- fix bug 4078
- talloc_free(talloc_autofree_context()); should not result
in a SIGABORT on exit
- add a test for this, but this test can also pass in the standalone build
and samba3, as samba4 uses talloc_autofree_context()
Gerald Carter [Thu, 28 Sep 2006 21:19:08 +0000 (21:19 +0000)]
r18981: * cleanup some vestiges of old cli_reg.c code and mark some TODO
items in cac_winreg.c
* Get 'net rpc registry enumerate' to list values again
* Fix winreg.idl QueryInfoKey(). The max_subkeysize is the
max_classlen (we previously had this correct in Samba3")
* fix valgrind error about uninitialized memory and use-before-set
on size value inmemset() call
* Fix key enumeration in 'net rpc registry enumerate'
* regenerate gen_dir files based on local pidl patches
Please note that the generated ndr files are from my local
copy of pidl. If you need to regenerate, please apply the
patch that I posted to the samba-technical list earlier today.
(This used to be commit 5d843612a1b9d92022f76626f1c7473faebec4ba)
Jeremy Allison [Thu, 28 Sep 2006 18:08:03 +0000 (18:08 +0000)]
r18980: Be a little more intelligent about "startup_time",
move into the domain struct. Allow message to go online
to set this state and cope with removing it.
Jeremy.
(This used to be commit 51f0e60cc3a652b0ff1658d4c07bfc9493fbc51a)
Andrew Tridgell [Wed, 27 Sep 2006 23:31:53 +0000 (23:31 +0000)]
r18966: this bug affects Samba3 too. I'm actually surprised nobody has
reported that Samba3 on Solaris Sparc with the native compiler can't
join Windows domains. If it worked we were just lucky. I suspect it
just didn't work.
(This used to be commit 9df1e7d98973ac1ec6ba25d528591216e568f2f3)
Gerald Carter [Wed, 27 Sep 2006 19:03:54 +0000 (19:03 +0000)]
r18963: * Move parts of registry headers that were still in
use to reg_objects.h
* Remove unused rpc headers
(This used to be commit 4f79d8c83db5af80078114e9fb39171380d040b1)
Gerald Carter [Wed, 27 Sep 2006 16:05:25 +0000 (16:05 +0000)]
r18962: * Add IDL for SaveKey() and RestoreKey() and regenerated
* Tested RegSaveKey() using win32 app. Apparently
this code has been brokne for a really long time.
(This used to be commit 5381dcbde34206462562bdfc7639f488820a5a64)
we need to include unistd.h in system/network.h because
it contains the ioctl() prototype on some systems
and we need to make sure it gets included before socket_wrapper
defines ioctl swrap_ioctl