tprouty/samba.git
16 years agor17937: Move the saf_ cache into the tcp ad connection code.
Jeremy Allison [Wed, 30 Aug 2006 18:48:49 +0000 (18:48 +0000)]
r17937: Move the saf_ cache into the tcp ad connection code.
Cause winbindd to set site support before doing the
generic AD server lookup.
Jeremy.

16 years agor17934: allow srcdir != builddir for 'make test'
Gerald Carter [Wed, 30 Aug 2006 16:58:29 +0000 (16:58 +0000)]
r17934: allow srcdir != builddir for 'make test'

16 years agor17933: Don't print a NULL sitename.
Jeremy Allison [Wed, 30 Aug 2006 16:02:08 +0000 (16:02 +0000)]
r17933: Don't print a NULL sitename.
Jeremy.

16 years agor17929: Ok, I think I finally figured out where to put
Jeremy Allison [Wed, 30 Aug 2006 05:52:31 +0000 (05:52 +0000)]
r17929: Ok, I think I finally figured out where to put
the code to redo the CLDAP query to restrict DC
DNS lookups to the sitename. Jerry, please check
to stop me going insane :-).
Jeremy.

16 years agor17928: Implement the basic store for CLDAP sitename
Jeremy Allison [Wed, 30 Aug 2006 04:40:03 +0000 (04:40 +0000)]
r17928: Implement the basic store for CLDAP sitename
support when looking up DC's. On every CLDAP
call store the returned client sitename (if
present, delete store if not) in gencache with
infinate timeout. On AD DNS DC lookup, try looking
for sitename DC's first, only try generic if
sitename DNS lookup failed.
I still haven't figured out yet how to ensure
we fetch the sitename with a CLDAP query before
doing the generic DC list lookup. This code is
difficult to understand. I'll do some experiments
and backtraces tomorrow to try and work out where
to force a CLDAP site query first.
Jeremy.

16 years agor17924: Get rid of warnings now that talloc is merged.
Volker Lendecke [Tue, 29 Aug 2006 19:14:25 +0000 (19:14 +0000)]
r17924: Get rid of warnings now that talloc is merged.

Destructors now take a pointer to the "real" destroyed object as an argument.

Volker

16 years agor17923: turn on null_tracking with the first talloc_init() call,
Stefan Metzmacher [Tue, 29 Aug 2006 17:17:02 +0000 (17:17 +0000)]
r17923: turn on null_tracking with the first talloc_init() call,
(this needs to be moved to a samba3 specific place)

I commit this because I habe no time to test smbcontrol .... pool-usage
and don't want to break it. I'll try to find a better fix tomorrow.

metze

16 years agor17922: sync samba3's talloc with samba4's and move the samba3 specific stuff to...
Stefan Metzmacher [Tue, 29 Aug 2006 16:54:12 +0000 (16:54 +0000)]
r17922: sync samba3's talloc with samba4's and move the samba3 specific stuff to tallocmsg.c

metze

16 years agor17921: Comment is obsolte. This is now implemented in winbindd.
Jeremy Allison [Tue, 29 Aug 2006 16:52:59 +0000 (16:52 +0000)]
r17921: Comment is obsolte. This is now implemented in winbindd.
Jeremy.

16 years agor17910: remove incorrect comment (code has already been fixed)
Gerald Carter [Tue, 29 Aug 2006 15:43:15 +0000 (15:43 +0000)]
r17910: remove incorrect comment (code has already been fixed)

16 years agor17909: ensure we do not call map_username() twice on Krb5 session setups
Gerald Carter [Tue, 29 Aug 2006 15:42:09 +0000 (15:42 +0000)]
r17909: ensure we do not call map_username() twice on Krb5 session setups

16 years agor17906: Port the snprintf bugfix from 4. I wonder why we never hit this....
Volker Lendecke [Tue, 29 Aug 2006 09:49:10 +0000 (09:49 +0000)]
r17906: Port the snprintf bugfix from 4. I wonder why we never hit this....

16 years agor17903: Fix null deref caught by Stanford checker. Don't
Jeremy Allison [Tue, 29 Aug 2006 01:25:57 +0000 (01:25 +0000)]
r17903: Fix null deref caught by Stanford checker. Don't
call ntlmssp_end on a null pointer ! (Doh !).
Jeremy.

16 years agor17902: Fix possible null deref caught by Stanford checker.
Jeremy Allison [Tue, 29 Aug 2006 01:11:02 +0000 (01:11 +0000)]
r17902: Fix possible null deref caught by Stanford checker.
Jeremy.

16 years agor17901: Stanford checker fix. cookie here can't be null or we'd
Jeremy Allison [Tue, 29 Aug 2006 01:04:25 +0000 (01:04 +0000)]
r17901: Stanford checker fix. cookie here can't be null or we'd
deref null. Make interface explicit.
Jeremy.

16 years agor17900: Fix from Michael Adam <ma@sernet.de> - make internal_resolve_name
Jeremy Allison [Tue, 29 Aug 2006 00:56:08 +0000 (00:56 +0000)]
r17900: Fix from Michael Adam <ma@sernet.de> - make internal_resolve_name
do what it's supposed to.
Jeremy.

16 years agor17899: Fix Stanford checker bug - possible null deref.
Jeremy Allison [Tue, 29 Aug 2006 00:53:28 +0000 (00:53 +0000)]
r17899: Fix Stanford checker bug - possible null deref.
Jeremy.

16 years agor17897: Store the uid in the memory creds. Don't request the
Jeremy Allison [Mon, 28 Aug 2006 23:01:30 +0000 (23:01 +0000)]
r17897: Store the uid in the memory creds. Don't request the
krb5 refresh creds when doing cached NTLM auth, request
the memory creds instead.
Jeremy.

16 years agor17896: Reformatting. I did not want to do it anymore, but these ones looked just
Volker Lendecke [Mon, 28 Aug 2006 18:25:55 +0000 (18:25 +0000)]
r17896: Reformatting. I did not want to do it anymore, but these ones looked just
silly :-)

Volker

16 years agor17881: Another microstep towards better error reporting: Make get_sorted_dc_list
Volker Lendecke [Mon, 28 Aug 2006 09:19:30 +0000 (09:19 +0000)]
r17881: Another microstep towards better error reporting: Make get_sorted_dc_list
return NTSTATUS.

If we want to differentiate different name resolution problems we might want
to introduce yet another error class for Samba-internal errors. Things like no
route to host to the WINS server, a DNS server explicitly said host not found
etc might be worth passing up.

Because we can not stash everything into the existing NT_STATUS codes, what
about a Samba-specific error class like NT_STATUS_DOS and NT_STATUS_LDAP?

Volker

16 years agor17880: On host "tridge" in the build farm the tests fail because smbd hangs in in
Volker Lendecke [Mon, 28 Aug 2006 07:56:15 +0000 (07:56 +0000)]
r17880: On host "tridge" in the build farm the tests fail because smbd hangs in in
'connecting to cups server on localhost'. There is no cups on that host, but
the TCP connection hangs in SYN_SENT. Probably some firewall rule.

Work around that.

Volker

16 years agor17879: Make it explicit that we can never pass NULL for buflen or stringlen.
Jeremy Allison [Mon, 28 Aug 2006 05:41:32 +0000 (05:41 +0000)]
r17879: Make it explicit that we can never pass NULL for buflen or stringlen.
Stanford Checker fix.
Jeremy.

16 years agor17878: Fix possible null deref found by Stanford checker.
Jeremy Allison [Mon, 28 Aug 2006 05:35:27 +0000 (05:35 +0000)]
r17878: Fix possible null deref found by Stanford checker.
Jeremy.

16 years agor17877: Make it explicit to the checker that we can never pass
Jeremy Allison [Mon, 28 Aug 2006 05:27:30 +0000 (05:27 +0000)]
r17877: Make it explicit to the checker that we can never pass
in NULL as ctr to a void returning fn.
Jeremy.

16 years agor17875: Fix (rather theoretical, but still...) null deref found by
Jeremy Allison [Mon, 28 Aug 2006 05:22:10 +0000 (05:22 +0000)]
r17875: Fix (rather theoretical, but still...) null deref found by
Stanford checker.
Jeremy.

16 years agor17874: Fix possible null deref found by Stanford checker.
Jeremy Allison [Mon, 28 Aug 2006 05:10:56 +0000 (05:10 +0000)]
r17874: Fix possible null deref found by Stanford checker.
Jeremy.

16 years agor17873: Fix possible null deref found by Stanford checker.
Jeremy Allison [Mon, 28 Aug 2006 04:55:05 +0000 (04:55 +0000)]
r17873: Fix possible null deref found by Stanford checker.
Jeremy.

16 years agor17872: Fix possible null deref found by the Stanford checker.
Jeremy Allison [Mon, 28 Aug 2006 04:52:36 +0000 (04:52 +0000)]
r17872: Fix possible null deref found by the Stanford checker.
Jeremy.

16 years agor17869: More sensible fix for Stanford Checker null deref.
Jeremy Allison [Mon, 28 Aug 2006 03:15:06 +0000 (03:15 +0000)]
r17869: More sensible fix for Stanford Checker null deref.
Jeremy.

16 years agor17867: Fix null deref in error code path. Found by the
Jeremy Allison [Mon, 28 Aug 2006 02:29:36 +0000 (02:29 +0000)]
r17867: Fix null deref in error code path. Found by the
Stanford checker.
Jeremy.

16 years agor17866: Fix possible null deref - found by Stanford checker.
Jeremy Allison [Mon, 28 Aug 2006 02:27:49 +0000 (02:27 +0000)]
r17866: Fix possible null deref - found by Stanford checker.
Jeremy.

16 years agor17865: Fix what the Stanford checker reported as a possible
Jeremy Allison [Mon, 28 Aug 2006 02:24:15 +0000 (02:24 +0000)]
r17865: Fix what the Stanford checker reported as a possible
deref. I think this is a false positive, but it's
an easy extra check to add here.
Jeremy.

16 years agor17864: Fix possible null deref if client doesn't give us
Jeremy Allison [Mon, 28 Aug 2006 02:13:50 +0000 (02:13 +0000)]
r17864: Fix possible null deref if client doesn't give us
an answer record. Found by the Stanford checker.
Jeremy.

16 years agor17863: Fix unneeded NULL check on pointer parameters causing the
Jeremy Allison [Mon, 28 Aug 2006 01:56:17 +0000 (01:56 +0000)]
r17863: Fix unneeded NULL check on pointer parameters causing the
Stanford checker to flag null deref.
Jeremy.

16 years agor17862: Fix possible NULL deref (like rev 17861) found by the
Jeremy Allison [Mon, 28 Aug 2006 01:48:04 +0000 (01:48 +0000)]
r17862: Fix possible NULL deref (like rev 17861) found by the
Stanford group.
Jeremy.

16 years agor17861: Fix inconsistency found in checking for NULL in DLIST_REMOVE
Jeremy Allison [Mon, 28 Aug 2006 01:44:40 +0000 (01:44 +0000)]
r17861: Fix inconsistency found in checking for NULL in DLIST_REMOVE
macro. Don't check for NULL if we would have already derefed.
Jeremy.

16 years agor17855: Fix the build on systems without LDAP
Volker Lendecke [Sun, 27 Aug 2006 17:36:17 +0000 (17:36 +0000)]
r17855: Fix the build on systems without LDAP

16 years agor17854: Steal the LDAP in NTSTATUS trick from Samba4
Volker Lendecke [Sun, 27 Aug 2006 17:24:31 +0000 (17:24 +0000)]
r17854: Steal the LDAP in NTSTATUS trick from Samba4

Thanks to Michael Adam <ma@sernet.de>

Volker

16 years agor17853: Fix an uninitialized variable (m_time2). Jeremy, please check.
Volker Lendecke [Sun, 27 Aug 2006 16:50:10 +0000 (16:50 +0000)]
r17853: Fix an uninitialized variable (m_time2). Jeremy, please check.

Thanks,

Volker

16 years agor17852: Remove a pointless NULL assignment
Volker Lendecke [Sun, 27 Aug 2006 16:24:03 +0000 (16:24 +0000)]
r17852: Remove a pointless NULL assignment

16 years agor17851: Fix a warning & attempt to fix the Tru64 build
Volker Lendecke [Sun, 27 Aug 2006 16:14:31 +0000 (16:14 +0000)]
r17851: Fix a warning & attempt to fix the Tru64 build

16 years agor17850: Another dummy checkin for the build farm to retry
Volker Lendecke [Sun, 27 Aug 2006 14:55:46 +0000 (14:55 +0000)]
r17850: Another dummy checkin for the build farm to retry

16 years agor17847: Dummy commit
Volker Lendecke [Sat, 26 Aug 2006 22:59:58 +0000 (22:59 +0000)]
r17847: Dummy commit

16 years agor17845: Remove a Solaris warning
Volker Lendecke [Sat, 26 Aug 2006 20:56:49 +0000 (20:56 +0000)]
r17845: Remove a Solaris warning

16 years agor17837: Split out the storing of memory cached credentials
Jeremy Allison [Sat, 26 Aug 2006 02:53:45 +0000 (02:53 +0000)]
r17837: Split out the storing of memory cached credentials
from the krb5 ticket renewal code. This allows cached
credentials to be stored for single sign-on via ntlm_auth
for machines in a domain still using NTLM. Also (hopefully)
fixes the reference counting problem with pam_logon/logoff
so multiple logons/logoffs won't lose cached credentials.
This compiles, but I'm intending to test it over the weekend
so don't complain too much :-). I also want it in the tree
so Coverity can scan it for errors. Guenther, check this over
please - I ran through the architecture with Jerry and he's
ok with it, but this is modifying your code a lot.
Jeremy.

16 years agor17836: Don't create zombies in the children, thanks to Jeremy!
Volker Lendecke [Fri, 25 Aug 2006 19:13:37 +0000 (19:13 +0000)]
r17836: Don't create zombies in the children, thanks to Jeremy!

Volker

16 years agor17835: Fix Coverity bugs 306, 309, 310.
Volker Lendecke [Fri, 25 Aug 2006 18:24:43 +0000 (18:24 +0000)]
r17835: Fix Coverity bugs 306, 309, 310.

Jeremy, you might want to look at the trans2 one.

Volker

16 years agor17834: Another bug found by Volker's tests in the build farm !
Jeremy Allison [Fri, 25 Aug 2006 16:25:09 +0000 (16:25 +0000)]
r17834: Another bug found by Volker's tests in the build farm !
Correctly map large nt timevals to TIME_T_MAX.
Jeremy.

16 years agor17833: Next step to fix the build farm.
Volker Lendecke [Fri, 25 Aug 2006 15:08:05 +0000 (15:08 +0000)]
r17833: Next step to fix the build farm.

Jerry, why don't you include "includes.h"?

Thanks,

Volker

16 years agor17832: Fix bug 4050
Volker Lendecke [Fri, 25 Aug 2006 14:52:30 +0000 (14:52 +0000)]
r17832: Fix bug 4050

16 years agor17831: Attempt to fix the build farm: 0x7fffffffffffffff needs special casing too I
Volker Lendecke [Fri, 25 Aug 2006 14:25:06 +0000 (14:25 +0000)]
r17831: Attempt to fix the build farm: 0x7fffffffffffffff needs special casing too I
think. This broke 'make test' because the newly created user was set to be
kicked off Mi, 22 Jan 1975 23:55:33 CET (unix time 159663333) with the
setuserinfo21 call.

I'm not 100% sure that 0x7ff... means max time as I do it here, I vaguely
remember it to mean "don't touch".

Does anybody know that for sure?

Jeremy, please check this.

Thanks,

Volker

16 years agor17819: Add some more ignores.
Jelmer Vernooij [Fri, 25 Aug 2006 03:17:47 +0000 (03:17 +0000)]
r17819: Add some more ignores.

16 years agor17818: Fixup uint64 time calc. NT time is a 64 bit number,
Jeremy Allison [Thu, 24 Aug 2006 23:39:37 +0000 (23:39 +0000)]
r17818: Fixup uint64 time calc. NT time is a 64 bit number,
not high value seconds, low value 100ns units.
Jeremy.

16 years agor17817: Disable compilation of LIBNDR (it uses uint64_t).
Jelmer Vernooij [Thu, 24 Aug 2006 23:21:43 +0000 (23:21 +0000)]
r17817: Disable compilation of LIBNDR (it uses uint64_t).

16 years agor17816: Merge my cupsprot branch. It is now possible to (optionally) specify :port in
Jelmer Vernooij [Thu, 24 Aug 2006 22:10:59 +0000 (22:10 +0000)]
r17816: Merge my cupsprot branch. It is now possible to (optionally) specify :port in
the "cups server" smb.conf parameter.

16 years agor17815: Revert Volker's change in 16014. I really do not believe
Gerald Carter [Thu, 24 Aug 2006 22:10:42 +0000 (22:10 +0000)]
r17815: Revert Volker's change in 16014.  I really do not believe
the this should be necessary.  If there is still a bug,
I believe that setting thr group RID from the passdb is
masking it.  Not fixing it.  It is very likely that
the change was necessary before but is no longer
with the recent changes.  But I'm not taking the chance
of merging it to 3.0.23c. :-)

16 years agor17814: Add .bzrignore file
Jelmer Vernooij [Thu, 24 Aug 2006 22:08:02 +0000 (22:08 +0000)]
r17814: Add .bzrignore file

16 years agor17813: Remove another instance of manually setting the group SID.
Gerald Carter [Thu, 24 Aug 2006 22:05:53 +0000 (22:05 +0000)]
r17813: Remove another instance of manually setting the group SID.
The would have been primaryly used when adding a user to
an smbpasswd file, but could have been introduce to other
backends by using pdbedit -i -e.

The symptom was

[2006/08/09 13:07:43, 0] rpc_parse/parse_samr.c:init_sam_user_info21A(6276)
  init_sam_user_info_21A: User nobody has Primary Group SID S-1-22-2-99,
  which conflicts with the domain sid S-1-5-21-1825997848-4107600307-1754506280.
  Failing operation.

16 years agor17812: Fix bad unsigned comparisons with TIME_T_MIN/TIME_T_MAX.
Jeremy Allison [Thu, 24 Aug 2006 21:37:10 +0000 (21:37 +0000)]
r17812: Fix bad unsigned comparisons with TIME_T_MIN/TIME_T_MAX.
Jeremy.

16 years agor17810: Use datarootdir variable generated by newer autoconf versions. (fixes warning)
Jelmer Vernooij [Thu, 24 Aug 2006 20:52:43 +0000 (20:52 +0000)]
r17810: Use datarootdir variable generated by newer autoconf versions. (fixes warning)

16 years agor17809: Add in 64-bit integer time calculations (taken from
Jeremy Allison [Thu, 24 Aug 2006 20:51:57 +0000 (20:51 +0000)]
r17809: Add in 64-bit integer time calculations (taken from
Samba4) for machines that have 64-bit integers. Leave
the (double) code for machines that don't. Needs
testing.... :-).
Jeremy.

16 years agor17807: Fix a file descriptor leak pointed out by John Malmberg. Thanks!
Volker Lendecke [Thu, 24 Aug 2006 20:42:31 +0000 (20:42 +0000)]
r17807: Fix a file descriptor leak pointed out by John Malmberg. Thanks!

Volker

16 years agor17806: Make NTTIME a UINT64_S rather than a separate structure consisting of
Jelmer Vernooij [Thu, 24 Aug 2006 20:27:42 +0000 (20:27 +0000)]
r17806: Make NTTIME a UINT64_S rather than a separate structure consisting of
two uint32s.

16 years agor17805: Sorry Jerry, I could not stand the warnings... :-)
Volker Lendecke [Thu, 24 Aug 2006 20:17:59 +0000 (20:17 +0000)]
r17805: Sorry Jerry, I could not stand the warnings... :-)

16 years agor17804: Fix a enum/int mixup found by the IRIX compiler.
Volker Lendecke [Thu, 24 Aug 2006 19:56:20 +0000 (19:56 +0000)]
r17804: Fix a enum/int mixup found by the IRIX compiler.

Volker

16 years agor17803: finally get the new libaddns code to build on Solaris 9
Gerald Carter [Thu, 24 Aug 2006 18:48:44 +0000 (18:48 +0000)]
r17803: finally get the new libaddns code to build on Solaris 9

16 years agor17802: trying to fix more build farm hosts
Gerald Carter [Thu, 24 Aug 2006 18:09:05 +0000 (18:09 +0000)]
r17802: trying to fix more build farm hosts

16 years agor17801: bad merge ? No sure how the second half of the LIBNDR_OBJ value got cut...
Gerald Carter [Thu, 24 Aug 2006 16:56:36 +0000 (16:56 +0000)]
r17801: bad merge ?  No sure how the second half of the LIBNDR_OBJ value got cut...

16 years agor17800: Start using struct timespec internally for file times
Jeremy Allison [Thu, 24 Aug 2006 16:44:00 +0000 (16:44 +0000)]
r17800: Start using struct timespec internally for file times
on the wire. This allows us to go to nsec resolution
for systems that support it. It should also now be
easy to add a correct "create time" (birth time)
for systems that support it (*BSD). I'll be watching
the build farm closely after this one for breakage :-).
Jeremy.

16 years agor17799: Start fixing the building carnage. Only include calls to
Gerald Carter [Thu, 24 Aug 2006 16:33:50 +0000 (16:33 +0000)]
r17799: Start fixing the building carnage.  Only include calls to
uuid lib fucntions when WITH_DNS_UPDATES is defined.

16 years agor17798: Beginnings of a standalone libaddns library released under
Gerald Carter [Thu, 24 Aug 2006 15:43:32 +0000 (15:43 +0000)]
r17798: Beginnings of a standalone libaddns library released under
the LGPL.   Original code by Krishna Ganugapati <krishnag@centeris.com>.
Additional work by me.

It's still got some warts, but non-secure updates do
currently work.  There are at least four things left to
really clean up.

1. Change the memory management to use talloc() rather than
   malloc() and cleanup the leaks.
2. Fix the error code reporting (see initial changes to
   dnserr.h)
3. Fix the secure updates
4. Define a public interface in addns.h
5. Move the code in libads/dns.c into the libaddns/ directory
   (and under the LGPL).

A few notes:

* Enable the new code by compiling with --with-dnsupdate
* Also adds the command 'net ads dns register'
* Requires -luuid (included in the e2fsprogs-devel package).
* Has only been tested on Linux platforms so there may be portability
  issues.

16 years agor17797: Just say "ok" when trying to rename a local group to its same name.
Gerald Carter [Thu, 24 Aug 2006 12:49:18 +0000 (12:49 +0000)]
r17797: Just say "ok" when trying to rename a local group to its same name.

16 years agor17795: Finally track down the "ads_connect: Interrupted system call"
Gerald Carter [Thu, 24 Aug 2006 12:13:57 +0000 (12:13 +0000)]
r17795: Finally track down the "ads_connect: Interrupted system call"
error.  Fix our DNS SRV lookup code to deal with multi-homed hosts.
We were noly remembering one IP address per host from the Additional
records section in the SRV response which could have been an unreachable
address.

16 years agor17767: Argggg. Broke the build. Need to fix callers of put_long_date()
Jeremy Allison [Thu, 24 Aug 2006 01:34:33 +0000 (01:34 +0000)]
r17767: Argggg. Broke the build. Need to fix callers of put_long_date()
and interpret_long_date() first. Reverting...
Jeremy.

16 years agor17766: Getting ready to properly expose 100ns times on
Jeremy Allison [Thu, 24 Aug 2006 01:31:00 +0000 (01:31 +0000)]
r17766: Getting ready to properly expose 100ns times on
the wire. Move the internals of nt_time functions
to use struct timespecs.
Jeremy.

16 years agor17761: Handle times consistently across all client utils.
Jeremy Allison [Wed, 23 Aug 2006 22:33:50 +0000 (22:33 +0000)]
r17761: Handle times consistently across all client utils.
Fixes bugs reported in libsmbclient.
Jeremy.

16 years agor17760: The DNS SRV lookup already sorts by priority and weight so don't
Gerald Carter [Wed, 23 Aug 2006 21:04:47 +0000 (21:04 +0000)]
r17760: The DNS SRV lookup already sorts by priority and weight so don't
use the generic IP list sort in get_sorted_dc_list().

16 years agor17736: Apply the Unix group patch when creating the token for a
Gerald Carter [Wed, 23 Aug 2006 02:45:45 +0000 (02:45 +0000)]
r17736: Apply the Unix group patch when creating the token for a
username map.

16 years agor17723: * BUG 3969: Fix unsigned time comparison with expiration policy from AD DC
Gerald Carter [Tue, 22 Aug 2006 22:53:08 +0000 (22:53 +0000)]
r17723: * BUG 3969: Fix unsigned time comparison with expiration policy from AD DC
* Merge patches from SLES10 to make sure we talk to the correct
  winbindd process when performing pam_auth (and pull the password policy info).

16 years agor17710: Thanks to Thomas Bork for testing and continued feedback on this.
Gerald Carter [Tue, 22 Aug 2006 16:01:24 +0000 (16:01 +0000)]
r17710: Thanks to Thomas Bork for testing and continued feedback on this.

Comments from the patch:

/* Add the "Unix Group" SID for each gid to catch mapped groups
   and their Unix equivalent.  This is to solve the backwards
   compatibility problem of 'valid users = +ntadmin' where
   ntadmin has been paired with "Domain Admins" in the group
   mapping table.  Otherwise smb.conf would need to be changed
   to 'valid user = "Domain Admins"'.  --jerry */

16 years agor17709: Fix cut-n-paste error with the name of gid_to_unix_group_sid().
Gerald Carter [Tue, 22 Aug 2006 15:18:13 +0000 (15:18 +0000)]
r17709: Fix cut-n-paste error with the name of gid_to_unix_group_sid().

16 years agor17677: There is no need for a 2nd krb5_to_nt_status function, is there?
Günther Deschner [Tue, 22 Aug 2006 00:36:31 +0000 (00:36 +0000)]
r17677: There is no need for a 2nd krb5_to_nt_status function, is there?

Michael Adam/Volker, please check.

Guenther

16 years agor17676: Fix printing bug found by kukks. Don't copy a return
Jeremy Allison [Mon, 21 Aug 2006 23:30:39 +0000 (23:30 +0000)]
r17676: Fix printing bug found by kukks. Don't copy a return
value into an auto on the stack that gets removed when
we return from the frame :-).
Jeremy.

16 years agor17673: volker's patch for re-adding Getpwnam() lookups to smbpasswd backend (I hate...
Gerald Carter [Mon, 21 Aug 2006 21:53:02 +0000 (21:53 +0000)]
r17673: volker's patch for re-adding Getpwnam() lookups to smbpasswd backend (I hate username level)

16 years agor17672: remove duplicate description on NT_STATUS_INVALID_PARAMETER (from Michael...
Gerald Carter [Mon, 21 Aug 2006 21:25:17 +0000 (21:25 +0000)]
r17672: remove duplicate description on NT_STATUS_INVALID_PARAMETER (from Michael Adam <ma@sernet.de>)

16 years agor17669: Remove RID algorithm support from unmapped users and groups
Gerald Carter [Mon, 21 Aug 2006 20:04:01 +0000 (20:04 +0000)]
r17669: Remove RID algorithm support from unmapped users and groups
when using smbpasswd

16 years agor17668: Fix the miscalculations in pushing announces. Fixes
Jeremy Allison [Mon, 21 Aug 2006 20:03:32 +0000 (20:03 +0000)]
r17668: Fix the miscalculations in pushing announces. Fixes
problems Kukks reported.
Jeremy.

16 years agor17667: Merge snprintf fixes from tridge (Samba4).
Jeremy Allison [Mon, 21 Aug 2006 17:58:41 +0000 (17:58 +0000)]
r17667: Merge snprintf fixes from tridge (Samba4).
Jeremy.

----------
several replacement snprintf() fixes.

1) when running the testsuite, actually test against the system
   sprintf(), not against ourselves (doh!)

2) fix the buffer termination to terminate buf2 as well

3) fix handling of %llu, and add a simple test

This fixes a bug with password expiry on solaris
----------

16 years agor17630: Looks like getpeerid() is a system function on
Jeremy Allison [Sun, 20 Aug 2006 20:05:49 +0000 (20:05 +0000)]
r17630: Looks like getpeerid() is a system function on
FreeBSD. Change to sys_getpeerid(). Thanks to
vl for pointing this out.
Jeremy.

16 years agor17626: Some C++ Warnings
Volker Lendecke [Sun, 20 Aug 2006 17:55:06 +0000 (17:55 +0000)]
r17626: Some C++ Warnings

16 years agor17625: Fix the build
Volker Lendecke [Sun, 20 Aug 2006 17:46:20 +0000 (17:46 +0000)]
r17625: Fix the build

16 years agor17623: Revert accidential commit
Volker Lendecke [Sun, 20 Aug 2006 17:30:27 +0000 (17:30 +0000)]
r17623: Revert accidential commit

16 years agor17622: Add a framework for a printing backend designed to support the build farm. If
Volker Lendecke [Sun, 20 Aug 2006 17:29:00 +0000 (17:29 +0000)]
r17622: Add a framework for a printing backend designed to support the build farm. If
we want to walk more printing code in the build farm I think doing that with a
customized printing backend is much easier than with a set of shell scripts.

Jerry, comments?

Volker

16 years agor17620: Fix two C++ Warnings and a memleak
Volker Lendecke [Sun, 20 Aug 2006 17:08:37 +0000 (17:08 +0000)]
r17620: Fix two C++ Warnings and a memleak

16 years agor17618: Not using a cache version number (yet). We really should...
Jeremy Allison [Sun, 20 Aug 2006 03:56:27 +0000 (03:56 +0000)]
r17618: Not using a cache version number (yet). We really should...
Jeremy

16 years agor17617: Take Andrew Bartletts excellent advice and don't store
Jeremy Allison [Sun, 20 Aug 2006 03:53:42 +0000 (03:53 +0000)]
r17617: Take Andrew Bartletts excellent advice and don't store
the nt hash directly in the winbindd cache, store a
salted version (MD5 of salt + nt_hash). This is what
we do in the LDAP password history code. We store
this salted cache entry under the same name as an old
entry (CRED/<sid>) but detect it on read by checking
if there are 17 bytes of data after the first stored
hash (1 byte len, 16 bytes hash). GD PLEASE CHECK.
Jeremy.

16 years agor17616: Add the lm and nt hashes to the cached credentials
Jeremy Allison [Sun, 20 Aug 2006 01:25:26 +0000 (01:25 +0000)]
r17616: Add the lm and nt hashes to the cached credentials
stored - only store the password if we're going to
be doing a krb5 refresh. GD please review this change !
Now to add code to reference count the cached creds
(to allow multiple pam_logon/pam_logoffs to keep the
creds around), ensure that the cred cache is called
on all successful pam_logons (if we have winbindd cache
pam credentials = true, set this by default) and finally
ensure the creds cache is changed on successful password
change. GD - you *really* need to review this :-).
Jeremy.

16 years agor17612: Modify NTLMSSP session code so that it doesn't store
Jeremy Allison [Sat, 19 Aug 2006 20:42:04 +0000 (20:42 +0000)]
r17612: Modify NTLMSSP session code so that it doesn't store
a copy of the plaintext password, only the NT and LM
hashes (all it needs). Fix smbencrypt to expose hash
verions of plaintext function. Andrew Bartlett, you
might want to look at this for gensec.
This should make it easier for winbindd to store
cached credentials without having to store plaintext
passwords in an NTLM-only environment (non krb5).
Jeremy.

16 years agor17610: Added the ability for firefox to drive the winbindd
Jeremy Allison [Sat, 19 Aug 2006 01:04:54 +0000 (01:04 +0000)]
r17610: Added the ability for firefox to drive the winbindd
ntlm_auth module to allow it to use winbindd cached
credentials.The credentials are currently only stored
in a krb5 MIT environment - we need to add an option to
winbindd to allow passwords to be stored even in an NTLM-only
environment.
Patch from Robert O'Callahan, modified with some fixes
by me.
Jeremy.

16 years agor17607: Adapt the Samba4 directory structure for tdb. Makes it easier to diff.
Volker Lendecke [Fri, 18 Aug 2006 16:25:09 +0000 (16:25 +0000)]
r17607: Adapt the Samba4 directory structure for tdb. Makes it easier to diff.

Let's see what it breaks. For me it works :-)

Volker