ira/wip.git
16 years agor21900: Token exchange now seems to work, now why does the
Jeremy Allison [Wed, 21 Mar 2007 01:04:56 +0000 (01:04 +0000)]
r21900: Token exchange now seems to work, now why does the
client encrypt fail ?
Jeremy.

16 years agor21899: At least we're getting to stage 2 of the blob
Jeremy Allison [Wed, 21 Mar 2007 00:56:40 +0000 (00:56 +0000)]
r21899: At least we're getting to stage 2 of the blob
exchange. Still not working but closer.
Jeremy.

16 years agor21898: Added test command, fixed first valgrind bugs.
Jeremy Allison [Wed, 21 Mar 2007 00:44:15 +0000 (00:44 +0000)]
r21898: Added test command, fixed first valgrind bugs.
Now to investigate why it doesn't work :-).
Jeremy.

16 years agor21897: Add in a basic raw NTLM encrypt request. Now
Jeremy Allison [Wed, 21 Mar 2007 00:25:08 +0000 (00:25 +0000)]
r21897: Add in a basic raw NTLM encrypt request. Now
for testing.
Jeremy.

16 years agor21894: Some refactoring of server side encryption context. Support
Jeremy Allison [Tue, 20 Mar 2007 22:01:02 +0000 (22:01 +0000)]
r21894: Some refactoring of server side encryption context. Support
"raw" NTLM auth (no spnego).
Jeremy.

16 years agor21893: Update comments so they actually reflect reality...
Rafal Szczesniak [Tue, 20 Mar 2007 21:21:04 +0000 (21:21 +0000)]
r21893: Update comments so they actually reflect reality...

rafal

16 years agor21892: Mini-Patch from Michael
Volker Lendecke [Tue, 20 Mar 2007 20:47:17 +0000 (20:47 +0000)]
r21892: Mini-Patch from Michael

16 years agor21891: Finish server-side NTLM-SPNEGO negotiation support.
Jeremy Allison [Tue, 20 Mar 2007 18:11:48 +0000 (18:11 +0000)]
r21891: Finish server-side NTLM-SPNEGO negotiation support.
Now for the client part, and testing.
Jeremy.

16 years agor21888: Add the osname and osver options to 'net ads join' as discussed
Gerald Carter [Tue, 20 Mar 2007 15:29:33 +0000 (15:29 +0000)]
r21888: Add the osname and osver options to 'net ads join' as discussed
on the samba-technical ml.

I'll add a 'net ads set attribute=value' utility later
rather than the original 'net ads setmachineupn' patch that
was also posted to the tech ml.

16 years agor21887: Fix annoying bug where in a pam_close_session (or a pam_setcred with the
Günther Deschner [Tue, 20 Mar 2007 12:44:40 +0000 (12:44 +0000)]
r21887: Fix annoying bug where in a pam_close_session (or a pam_setcred with the
PAM_DELETE_CREDS flag set) any user could delete krb5 credential caches.
Make sure that only root can do this.

Jerry, Jeremy, please check.

Guenther

16 years agor21885: Chown logic should be activated only if nfs4:chown=yes
Alexander Bokovoy [Tue, 20 Mar 2007 08:17:27 +0000 (08:17 +0000)]
r21885: Chown logic should be activated only if nfs4:chown=yes

16 years agor21884: * Blacklist BUILTIN and MACHINE domains from the
Gerald Carter [Tue, 20 Mar 2007 02:43:20 +0000 (02:43 +0000)]
r21884: * Blacklist BUILTIN and MACHINE domains from the
  idmap domains as these should only be handled by the
  winbindd_passdb.c backend

* Allow the alloc init to fail for backwards compatible
  configurations like

     idmap backend = ad
     idmap uid = 1000-100000
....

* Remove the deprecated flags from idmap backend, et. al.
  These are mutually exclusive with the new configuration
  options (idmap domains).  Logging annoying messages
  about deprecated parameters is confusing.  So we'll try
  this apprpach for now.

16 years agor21883: Try and fix the build by removing the prototypes for
Jeremy Allison [Tue, 20 Mar 2007 02:20:16 +0000 (02:20 +0000)]
r21883: Try and fix the build by removing the prototypes for
functions that take a gss context handle in includes.h
Jeremy.

16 years agor21882: The server part of the code has to use an AUTH_NTLMSSP struct,
Jeremy Allison [Tue, 20 Mar 2007 01:17:47 +0000 (01:17 +0000)]
r21882: The server part of the code has to use an AUTH_NTLMSSP struct,
not just an NTLMSSP - grr. This complicates the re-use of
common client and server code but I think I've got it right.
Not turned on of valgrinded yet, but you can see it start
to take shape !
Jeremy.

16 years agor21881: Make sure we are very specific when testing whether a backand can handle a
James Peach [Tue, 20 Mar 2007 00:13:42 +0000 (00:13 +0000)]
r21881: Make sure we are very specific when testing whether a backand can handle a
particular SID. Make sure that the passdb backend will accept the same set
range of local SIDs that the idmap system sends it.

Simo, Jerry - this is a 3_0_25 candidate. Can you please review?

16 years agor21880: Make client and server calls into encryption code symetrical,
Jeremy Allison [Mon, 19 Mar 2007 22:45:35 +0000 (22:45 +0000)]
r21880: Make client and server calls into encryption code symetrical,
depending on encryption context pointer.
Jeremy.

16 years agor21879: Move process_blocking_lock_queue to a timed event.
Volker Lendecke [Mon, 19 Mar 2007 21:52:27 +0000 (21:52 +0000)]
r21879: Move process_blocking_lock_queue to a timed event.

The idea is that we have blocking.c:brl_timeout as a timed
event that is present whenever we do have a blocking lock
pending. It fires brl_timeout_fn() which calls
process_blocking_lock_queue().

Whenever we make changes to blocking_lock_queue, we trigger
a recalc_brl_timeout() which sets a new brl_timout event if
necessary. This makes the call to
blocking_locks_timeout_ms() in setup_select_timeout()
unnecessary, this is implicitly done in
event_add_to_select_args() from the timed events.

Volker

16 years agor21878: Fix a bug with smbd serving a windows terminal server: If winbind decides...
Volker Lendecke [Mon, 19 Mar 2007 21:04:56 +0000 (21:04 +0000)]
r21878: Fix a bug with smbd serving a windows terminal server: If winbind decides smbd
to be idle it might happen that smbd needs to do a winbind operation (for
example sid2name) as non-root. This then fails to get the privileged
pipe. When later on on the same connection another authentication request
comes in, we try to do the CRAP auth via the non-privileged pipe.

This adds a winbindd_priv_request_response() request that kills the existing
winbind pipe connection if it's not privileged.

Volker

16 years agor21877: Missed one line.
Jeremy Allison [Mon, 19 Mar 2007 21:03:30 +0000 (21:03 +0000)]
r21877: Missed one line.
Jeremy.

16 years agor21876: Start adding in the seal implementation - prototype code
Jeremy Allison [Mon, 19 Mar 2007 20:39:58 +0000 (20:39 +0000)]
r21876: Start adding in the seal implementation - prototype code
for the server side enc. (doesn't break anything).
I'll keep updating this until I've got NTLM seal working
on both client and server, then add in the gss level
seal.
Jeremy.

16 years agor21875: BUG 3275: Patch from Andy Polyakov <appro@fy.chalmers.se>
Gerald Carter [Mon, 19 Mar 2007 17:45:13 +0000 (17:45 +0000)]
r21875: BUG 3275: Patch from Andy Polyakov <appro@fy.chalmers.se>
Relax check for i386 header checks in the PE header of printer
driver files.  Thus allowing uploading of x64 print drivers
from 64bit Windows clients.

16 years agor21874: Fix missing notify function. Thanks to Thomas Bork <tombork@web.de>
Jeremy Allison [Mon, 19 Mar 2007 17:02:15 +0000 (17:02 +0000)]
r21874: Fix missing notify function. Thanks to Thomas Bork <tombork@web.de>
for pointing this out !
Jeremy.

16 years agor21873: This is winbindd_pam.c, not pam_winbind.c :-)
Volker Lendecke [Mon, 19 Mar 2007 12:54:39 +0000 (12:54 +0000)]
r21873: This is winbindd_pam.c, not pam_winbind.c :-)

16 years agor21872: Fix a debug message
Volker Lendecke [Mon, 19 Mar 2007 12:51:13 +0000 (12:51 +0000)]
r21872: Fix a debug message

16 years agor21871: Move deadtime processing into an idle event. While there, simplify
Volker Lendecke [Sun, 18 Mar 2007 13:19:40 +0000 (13:19 +0000)]
r21871: Move deadtime processing into an idle event. While there, simplify
conn_idle_all() a bit.

Volker

16 years agor21870: Move sending auth_server keepalives out of the main loop into an idle event.
Volker Lendecke [Sun, 18 Mar 2007 11:24:10 +0000 (11:24 +0000)]
r21870: Move sending auth_server keepalives out of the main loop into an idle event.

Volker

16 years agor21869: Move sending keepalives out of the main processing loop into idle event.
Volker Lendecke [Sun, 18 Mar 2007 10:57:46 +0000 (10:57 +0000)]
r21869: Move sending keepalives out of the main processing loop into idle event.

On the way, make lp_keepalive() a proper parameter.

Volker

16 years agor21868: Remove check_log_size from the central smbd processing loop. This can be...
Volker Lendecke [Sun, 18 Mar 2007 10:13:35 +0000 (10:13 +0000)]
r21868: Remove check_log_size from the central smbd processing loop. This can be done
with a become_root/unbecome_root in debug.c.

16 years agor21867: Simplify calling convention of timeout_processing. lp_deadtime is only
Volker Lendecke [Sun, 18 Mar 2007 10:09:16 +0000 (10:09 +0000)]
r21867: Simplify calling convention of timeout_processing. lp_deadtime is only
referenced in conn_idle_all().

16 years agor21866: Remove unused "lock spin count" parameter
Volker Lendecke [Sun, 18 Mar 2007 09:54:18 +0000 (09:54 +0000)]
r21866: Remove unused "lock spin count" parameter

16 years agor21865: Add in the stubs for SMB transport encryption. Will flesh
Jeremy Allison [Sat, 17 Mar 2007 00:32:54 +0000 (00:32 +0000)]
r21865: Add in the stubs for SMB transport encryption. Will flesh
these out as I implement. Don't add to SAMBA_3_0_25, this
is experimental code.
NFSv4 you're now officially on notice... :-).
Jeremy.

16 years agor21864: Reformatting.
Jeremy Allison [Sat, 17 Mar 2007 00:15:18 +0000 (00:15 +0000)]
r21864: Reformatting.
Jeremy.

16 years agor21863: Fix debug messages with incorrect function name.
Jeremy Allison [Fri, 16 Mar 2007 22:40:51 +0000 (22:40 +0000)]
r21863: Fix debug messages with incorrect function name.
Jeremy.

16 years agor21862: add the cups comment and location lookup to get_a_printer_2_default() as...
Gerald Carter [Fri, 16 Mar 2007 21:52:21 +0000 (21:52 +0000)]
r21862: add the cups comment and location lookup to get_a_printer_2_default() as well

16 years agor21861: Pull the comment and location from CUPS if we don't have one
Gerald Carter [Fri, 16 Mar 2007 21:46:58 +0000 (21:46 +0000)]
r21861: Pull the comment and location from CUPS if we don't have one
when fetching a printer from ntprinters.tdb.

Slightly modified from original version submitted on
samba-technical ml by Andy Polyakov <appro@fy.chalmers.se>

16 years agor21860: Fixes for "winbind normalize names" functionality:
Gerald Carter [Fri, 16 Mar 2007 17:54:10 +0000 (17:54 +0000)]
r21860: Fixes for "winbind normalize names" functionality:

* Fix getgroups() call called using a normalized name
* Fix some more name mappings that could cause for example
  a user to be unable to unlock the screen as the username
  would not match in the PAM authenticate call.

16 years agor21858: Fix typo.
Günther Deschner [Fri, 16 Mar 2007 16:21:38 +0000 (16:21 +0000)]
r21858: Fix typo.

Guenther

16 years agor21857: Stop pretending to be Vista in the %a macro towards Samba clients.
Günther Deschner [Fri, 16 Mar 2007 16:20:47 +0000 (16:20 +0000)]
r21857: Stop pretending to be Vista in the %a macro towards Samba clients.

Guenther

16 years agor21855: Fix a memleak in the krb5 locator and comment out gfree_all() which doesn't
Günther Deschner [Fri, 16 Mar 2007 15:48:07 +0000 (15:48 +0000)]
r21855: Fix a memleak in the krb5 locator and comment out gfree_all() which doesn't
make sense as long as it doesn't work as an lp_unload().

Guenther

16 years agor21854: Add gfree_interfaces() to gfree_all().
Günther Deschner [Fri, 16 Mar 2007 14:13:46 +0000 (14:13 +0000)]
r21854: Add gfree_interfaces() to gfree_all().

Guenther

16 years agor21853: Fix a valgrind error
Volker Lendecke [Fri, 16 Mar 2007 13:09:09 +0000 (13:09 +0000)]
r21853: Fix a valgrind error

16 years agor21851: Obvious typos...
Volker Lendecke [Thu, 15 Mar 2007 22:48:30 +0000 (22:48 +0000)]
r21851: Obvious typos...

16 years agor21850: After Jerry explained to me the HORRIBLE way in which
Jeremy Allison [Thu, 15 Mar 2007 22:11:13 +0000 (22:11 +0000)]
r21850: After Jerry explained to me the HORRIBLE way in which
the MIT gss libraries *SUCK*, move the frees to the end
of the function so MIT doesn't segfault.....
Add a comment so that another engineer knows why I did
this.
Jeremy.

16 years agor21848: add a comment about gss_import_name() and when to free the krb5 principal...
Gerald Carter [Thu, 15 Mar 2007 22:09:03 +0000 (22:09 +0000)]
r21848: add a comment about gss_import_name() and when to free the krb5 principal data

16 years agor21847: Fix memory leaks in error paths (and in main code path in one case...)
Jeremy Allison [Thu, 15 Mar 2007 21:53:53 +0000 (21:53 +0000)]
r21847: Fix memory leaks in error paths (and in main code path in one case...)
in sasl bind. Wonder why coverity didn't find these ?
Jeremy.

16 years agor21846: Try and fix the Darwin build which seems to have a strange krb5.
Jeremy Allison [Thu, 15 Mar 2007 20:45:27 +0000 (20:45 +0000)]
r21846: Try and fix the Darwin build which seems to have a strange krb5.
Jeremy.

16 years agor21845: Refactor the sessionsetupX code a little to allow us
Jeremy Allison [Thu, 15 Mar 2007 19:18:18 +0000 (19:18 +0000)]
r21845: Refactor the sessionsetupX code a little to allow us
to return a NT_STATUS_TIME_DIFFERENCE_AT_DC error to
a client when there's clock skew. Will help people
debug this. Prepare us for being able to return the
correct sessionsetupX "NT_STATUS_MORE_PROCESSING_REQUIRED"
error with associated krb5 clock skew error to allow
clients to re-sync time with us when we're eventually
able to be a KDC.
Jeremy.

16 years agor21840: mount.cifs compile on old libc missing bind mount #define
Steve French [Wed, 14 Mar 2007 22:15:21 +0000 (22:15 +0000)]
r21840: mount.cifs compile on old libc missing bind mount #define

Thanks to Thomas Jarosch for pointing this out.

16 years agor21831: Back out r21823 for a while, this is going into a bzr tree first.
Volker Lendecke [Tue, 13 Mar 2007 20:53:38 +0000 (20:53 +0000)]
r21831: Back out r21823 for a while, this is going into a bzr tree first.

Volker

16 years agor21825: add debug prefix timestamp to allow "short timestamps" to be
Herb Lewis [Tue, 13 Mar 2007 17:39:06 +0000 (17:39 +0000)]
r21825: add debug prefix timestamp to allow "short timestamps" to be
added to debug messages

16 years agor21823: Let secrets_store_machine_password() also store the account name. Not used
Volker Lendecke [Tue, 13 Mar 2007 16:13:24 +0000 (16:13 +0000)]
r21823: Let secrets_store_machine_password() also store the account name. Not used
yet, the next step will be a secrets_fetch_machine_account() function that
also pulls the account name to be used in the appropriate places.

Volker

16 years agor21822: Adding experimental krb5 lib locator plugin.
Günther Deschner [Tue, 13 Mar 2007 16:04:17 +0000 (16:04 +0000)]
r21822: Adding experimental krb5 lib locator plugin.

This is a starting point and may get changed. Basically we need follow the
exact same path to detect (K)DCs like other Samba tools/winbind do. In
particular with regard to the server affinity cache and the site-awarness for
DNS SRV lookups.

To compile just call "make bin/smb_krb5_locator.so", copy to
/usr/lib/plugin/krb5/ (Heimdal HEAD) or /usr/lib/krb5/plugins/libkrb5/ (MIT)
and you should immediately be able to kinit to your AD domain without having
your REALM with kdc or kpasswd directives defined in /etc/krb5.conf at all.

Tested with todays Heimdal HEAD and MIT krb5 1.5.

Guenther

16 years agor21819: Wrap all steps in secrets_store_machine_password into one single
Volker Lendecke [Tue, 13 Mar 2007 14:05:38 +0000 (14:05 +0000)]
r21819: Wrap all steps in secrets_store_machine_password into one single
transaction. Succeed all or store nothing.

Volker

16 years agor21818: Remove some unused code
Volker Lendecke [Tue, 13 Mar 2007 12:45:20 +0000 (12:45 +0000)]
r21818: Remove some unused code

16 years agor21814: use ndr_push_error in the ndr layer, not just a NTSTATUS failure
Andrew Tridgell [Tue, 13 Mar 2007 04:42:49 +0000 (04:42 +0000)]
r21814: use ndr_push_error in the ndr layer, not just a NTSTATUS failure

16 years agor21813: fixed an integer overflow error in the ndr push code.
Andrew Tridgell [Tue, 13 Mar 2007 04:37:09 +0000 (04:37 +0000)]
r21813: fixed an integer overflow error in the ndr push code.

Jerry, you might like to consider this for 3.0.25

16 years agor21804: Create a reference after proto_exits was called once. Else we link the
Lars Müller [Mon, 12 Mar 2007 20:57:49 +0000 (20:57 +0000)]
r21804: Create a reference after proto_exits was called once.  Else we link the
binaries again with each make.  Thx Volker to point my chesty at this.

16 years agor21803: Missed part of patch to make self-referrals work.
Jeremy Allison [Mon, 12 Mar 2007 20:10:12 +0000 (20:10 +0000)]
r21803: Missed part of patch to make self-referrals work.
Jeremy.

16 years agor21801: Fix Coverity ID # 342
Volker Lendecke [Mon, 12 Mar 2007 18:19:48 +0000 (18:19 +0000)]
r21801: Fix Coverity ID # 342

16 years agor21800: Check-in the DFS rewrite. I am still testing this but it
Jeremy Allison [Mon, 12 Mar 2007 17:55:24 +0000 (17:55 +0000)]
r21800: Check-in the DFS rewrite. I am still testing this but it
works from smbclient and Windows, and I am promising to
support and fix both client and server code moving forward.
Still need to test the RPC admin support but I haven't
changed that code.
Jeremy.

16 years agor21792: Fix crash bug triggered by Excel reported by Jerry.
Jeremy Allison [Mon, 12 Mar 2007 05:54:14 +0000 (05:54 +0000)]
r21792: Fix crash bug triggered by Excel reported by Jerry.
Bad cut-n-paste on rewrite of timestamps.
Jeremy.

16 years agor21785: Avoid an unnecessary gettimeofday() call
Volker Lendecke [Sun, 11 Mar 2007 18:32:26 +0000 (18:32 +0000)]
r21785: Avoid an unnecessary gettimeofday() call

Volker

16 years agor21784: Replace smb_register_idle_event() with event_add_timed(). This fixes winbind
Volker Lendecke [Sun, 11 Mar 2007 16:49:16 +0000 (16:49 +0000)]
r21784: Replace smb_register_idle_event() with event_add_timed(). This fixes winbind
who did not run the idle events to drop ldap connections.

Volker

16 years agor21783: Add in the "create info" field to the reply
Jeremy Allison [Sun, 11 Mar 2007 02:33:17 +0000 (02:33 +0000)]
r21783: Add in the "create info" field to the reply
from POSIX_OPEN and POSIX_MKDIR as specified
by Stevef in the wikki (extra 4 byte field).

Also fix horrible bug in James's code (James
you should review this for your Apple patch
tree) where he failed to allocate the correct
return memory size when returning a INFO2
struct. Added #define for the size of the
INFO2 struct and made sure we allocate the
correct size for return.

Jeremy.

16 years agor21782: Fix a memleak
Volker Lendecke [Sat, 10 Mar 2007 18:04:47 +0000 (18:04 +0000)]
r21782: Fix a memleak

16 years agor21780: let smbcontrol use POPT_COMMON_SAMBA options to allow setting debug
Herb Lewis [Fri, 9 Mar 2007 19:48:50 +0000 (19:48 +0000)]
r21780: let smbcontrol use POPT_COMMON_SAMBA options to allow setting debug
level. Fix calculation of argc after options are stripped. I couldn't
find a popt function that returned this.

16 years agor21779: I missd a call to krb5_get_init_creds_opt_alloc in r21778.
James Peach [Fri, 9 Mar 2007 19:28:35 +0000 (19:28 +0000)]
r21779: I missd a call to krb5_get_init_creds_opt_alloc in r21778.

16 years agor21778: Wrap calls to krb5_get_init_creds_opt_free to handle the different
James Peach [Fri, 9 Mar 2007 18:51:48 +0000 (18:51 +0000)]
r21778: Wrap calls to krb5_get_init_creds_opt_free to handle the different
calling convention in the latest MIT changes.  Apparantly Heimdal
is also changing to this calling convention.

16 years agor21777: As Stevef requested and the Apple guys agreed, make
Jeremy Allison [Fri, 9 Mar 2007 18:33:16 +0000 (18:33 +0000)]
r21777: As Stevef requested and the Apple guys agreed, make
mode_t in posix_open/posix_mkdir -> 8 bytes to match
the SET_UNIX_INFO_BASIC call. Steve is updating the
Wikki.
Jeremy.

16 years agor21776: fix bugs #4438 #4440
Simo Sorce [Fri, 9 Mar 2007 16:55:56 +0000 (16:55 +0000)]
r21776: fix bugs #4438 #4440

16 years agor21775: make messages more understandable - don't leave part dangling after newline
Herb Lewis [Fri, 9 Mar 2007 15:34:12 +0000 (15:34 +0000)]
r21775: make messages more understandable - don't leave part dangling after newline

16 years agor21774: Fix the build with Fedora Core 6.
Günther Deschner [Fri, 9 Mar 2007 11:34:24 +0000 (11:34 +0000)]
r21774: Fix the build with Fedora Core 6.
tridge/vl: please check.

Guenther

16 years agor21770: For old DOS style searches we must remember if
Jeremy Allison [Fri, 9 Mar 2007 02:40:49 +0000 (02:40 +0000)]
r21770: For old DOS style searches we must remember if
the initial search had a wildcard in order to
correctly return no error on end of search.
Found by Samba4 torture tester.
Jeremy.

16 years agor21769: Attempt to fix bug #4384 in old search code.
Jeremy Allison [Fri, 9 Mar 2007 02:16:03 +0000 (02:16 +0000)]
r21769: Attempt to fix bug #4384 in old search code.
We were accessing a pathname that hadn't gone
through unix_convert ! That's a big no-no...
Jeremy.

16 years agor21768: Fix the client dfs code such that smbclient can
Jeremy Allison [Thu, 8 Mar 2007 23:54:57 +0000 (23:54 +0000)]
r21768: Fix the client dfs code such that smbclient can
process deep dfs links (ie. links that go to non root
parts of a share). Make the directory handling conanonical
in POSIX and Windows pathname processing.
dfs should not be fully working in client tools. Please
bug me if not.
Jeremy.

16 years agor21767: Revert all the bits I accidentally committed in r21766.
James Peach [Thu, 8 Mar 2007 21:30:15 +0000 (21:30 +0000)]
r21767: Revert all the bits I accidentally committed in r21766.

16 years agor21766: Fix compiler warning.
James Peach [Thu, 8 Mar 2007 20:54:13 +0000 (20:54 +0000)]
r21766: Fix compiler warning.

16 years agor21765: Fix the build for HP-UX.
James Peach [Thu, 8 Mar 2007 18:45:44 +0000 (18:45 +0000)]
r21765: Fix the build for HP-UX.

16 years agor21764: Fix warning in debug comment.
Jeremy Allison [Thu, 8 Mar 2007 18:43:39 +0000 (18:43 +0000)]
r21764: Fix warning in debug comment.
Jeremy.

16 years agor21763: Add support for the UNIX_INFO2 infolevel.
James Peach [Thu, 8 Mar 2007 18:05:55 +0000 (18:05 +0000)]
r21763: Add support for the UNIX_INFO2 infolevel.

16 years agor21762: Fix the build by enabling shared modules and adding the config.*
James Peach [Thu, 8 Mar 2007 17:06:16 +0000 (17:06 +0000)]
r21762: Fix the build by enabling shared modules and adding the config.*
files. Add norify_watch and chflags operations. Fix a bunch of
warnings.

16 years agor21759: Fix the same bug in a more elegant way, strrchr_m
Jeremy Allison [Thu, 8 Mar 2007 03:00:42 +0000 (03:00 +0000)]
r21759: Fix the same bug in a more elegant way, strrchr_m
is an expensive call....
Jeremy.

16 years agor21758: Fix a very specific dfs bug when passing in POSIX
Jeremy Allison [Thu, 8 Mar 2007 02:51:41 +0000 (02:51 +0000)]
r21758: Fix a very specific dfs bug when passing in POSIX
pathnames. When we're working out how much we've
consumed we need to backtrack by either a '/' or '\\'
component, as both are valid separators.
Jeremy.

16 years agor21757: Add SMB_VFS_CHFLAGS operation.
James Peach [Thu, 8 Mar 2007 01:40:49 +0000 (01:40 +0000)]
r21757: Add SMB_VFS_CHFLAGS operation.

16 years agor21756: An invarient the dfs code depended on for POSIX paths
Jeremy Allison [Wed, 7 Mar 2007 23:58:40 +0000 (23:58 +0000)]
r21756: An invarient the dfs code depended on for POSIX paths
is no longer true, so fix it.
Jeremy.

16 years agor21755: Memory leak fixes from Zack Kirsch <zack.kirsch@isilon.com>.
Jeremy Allison [Wed, 7 Mar 2007 22:29:21 +0000 (22:29 +0000)]
r21755: Memory leak fixes from Zack Kirsch <zack.kirsch@isilon.com>.
Jeremy.

16 years agor21754: Volker is completely correct. There's no need for
Jeremy Allison [Wed, 7 Mar 2007 22:12:58 +0000 (22:12 +0000)]
r21754: Volker is completely correct. There's no need for
the RESOLVE_DFSPATH macros and their varients
any more. Fix reporting profile bug with all
error returns.
Jeremy.

16 years agor21753: Enable building ndrdump with the builtin popt. Jelmer, please check!
Volker Lendecke [Wed, 7 Mar 2007 21:13:51 +0000 (21:13 +0000)]
r21753: Enable building ndrdump with the builtin popt. Jelmer, please check!

16 years agor21750: Sync up with SAMBA_3_0_25. Only client changes are in libsmbclient
Jeremy Allison [Wed, 7 Mar 2007 19:45:22 +0000 (19:45 +0000)]
r21750: Sync up with SAMBA_3_0_25. Only client changes are in libsmbclient
right now.
Jeremy.

16 years agor21748: More cosmetic alignment. One change to call_nt_transact_create(): We were
Volker Lendecke [Wed, 7 Mar 2007 14:25:07 +0000 (14:25 +0000)]
r21748: More cosmetic alignment. One change to call_nt_transact_create(): We were
asking open_file_ntcreate for a batch oplock if the client asked us to do so,
even if it did not ask for an oplock in the first place. Did not test it, but
I think this is bogus anyway.

Volker

16 years agor21747: Cosmetic checkin to bring ntcreate and nttranscreate closer together
Volker Lendecke [Wed, 7 Mar 2007 13:57:32 +0000 (13:57 +0000)]
r21747: Cosmetic checkin to bring ntcreate and nttranscreate closer together

16 years agor21738: Remove unused file.
James Peach [Wed, 7 Mar 2007 05:09:37 +0000 (05:09 +0000)]
r21738: Remove unused file.

16 years agor21734: Fix bug #4369. Patch from David Leonard <dleonard@vintela.com>.
Jeremy Allison [Wed, 7 Mar 2007 02:27:54 +0000 (02:27 +0000)]
r21734: Fix bug #4369. Patch from David Leonard <dleonard@vintela.com>.
Jeremy.

16 years agor21731: Fix long-standing bug in our chain processing code.
Jeremy Allison [Wed, 7 Mar 2007 01:28:19 +0000 (01:28 +0000)]
r21731: Fix long-standing bug in our chain processing code.
Should fix a bug with WinPE. Probably a candidate
for the Vista patchset.
Jeremy.

16 years agor21726: Fix stupid cut-n-paste typo. Thanks to volker for
Jeremy Allison [Tue, 6 Mar 2007 22:14:09 +0000 (22:14 +0000)]
r21726: Fix stupid cut-n-paste typo. Thanks to volker for
being on the ball..... :-).
Jeremy.

16 years agor21725: Fix for memalign used without test guards. Was
Jeremy Allison [Tue, 6 Mar 2007 22:01:03 +0000 (22:01 +0000)]
r21725: Fix for memalign used without test guards. Was
breaking the build on *BSD's. Tested by Herb.
Jeremy.

16 years agor21724: Optimization pointed out by Volker. If we don't
Jeremy Allison [Tue, 6 Mar 2007 21:59:51 +0000 (21:59 +0000)]
r21724: Optimization pointed out by Volker. If we don't
have any outstanding locks or blocking locks then
we don't need to read the lock db. on close.
Jeremy.

16 years agor21723: Make use of the per-hashchain "freelists"
Volker Lendecke [Tue, 6 Mar 2007 10:40:18 +0000 (10:40 +0000)]
r21723: Make use of the per-hashchain "freelists"

16 years agor21722: Add the dead record functionality presented on samba-technical@samba.org. If
Volker Lendecke [Tue, 6 Mar 2007 10:11:15 +0000 (10:11 +0000)]
r21722: Add the dead record functionality presented on samba-technical@samba.org. If
you do a tdb_set_max_dead(tdb, n), then for this tdb a delete operation will
only mark a record as dead and re-use it if a new record is created. The
parameter n allows for at most n dead records per hash chain. If this number
is exceeded, all dead records are put on the central freelist.

Volker

16 years agor21717: Support the SMB_QUERY_POSIX_WHOAMI info level on QueryFsInfo.
James Peach [Tue, 6 Mar 2007 00:54:05 +0000 (00:54 +0000)]
r21717: Support the SMB_QUERY_POSIX_WHOAMI info level on QueryFsInfo.