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
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
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.
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().
Volker Lendecke [Sun, 18 Mar 2007 09:54:18 +0000 (09:54 +0000)]
r21866: Remove unused "lock spin count" parameter
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.
Jeremy Allison [Sat, 17 Mar 2007 00:15:18 +0000 (00:15 +0000)]
r21864: Reformatting.
Jeremy.
Jeremy Allison [Fri, 16 Mar 2007 22:40:51 +0000 (22:40 +0000)]
r21863: Fix debug messages with incorrect function name.
Jeremy.
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
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>
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.
Günther Deschner [Fri, 16 Mar 2007 16:21:38 +0000 (16:21 +0000)]
r21858: Fix typo.
Guenther
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
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
Günther Deschner [Fri, 16 Mar 2007 14:13:46 +0000 (14:13 +0000)]
r21854: Add gfree_interfaces() to gfree_all().
Guenther
Volker Lendecke [Fri, 16 Mar 2007 13:09:09 +0000 (13:09 +0000)]
r21853: Fix a valgrind error
Volker Lendecke [Thu, 15 Mar 2007 22:48:30 +0000 (22:48 +0000)]
r21851: Obvious typos...
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.
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
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.
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.
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.
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.
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
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
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
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
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
Volker Lendecke [Tue, 13 Mar 2007 12:45:20 +0000 (12:45 +0000)]
r21818: Remove some unused code
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
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
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.
Jeremy Allison [Mon, 12 Mar 2007 20:10:12 +0000 (20:10 +0000)]
r21803: Missed part of patch to make self-referrals work.
Jeremy.
Volker Lendecke [Mon, 12 Mar 2007 18:19:48 +0000 (18:19 +0000)]
r21801: Fix Coverity ID # 342
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.
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.
Volker Lendecke [Sun, 11 Mar 2007 18:32:26 +0000 (18:32 +0000)]
r21785: Avoid an unnecessary gettimeofday() call
Volker
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
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.
Volker Lendecke [Sat, 10 Mar 2007 18:04:47 +0000 (18:04 +0000)]
r21782: Fix a memleak
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.
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.
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.
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.
Simo Sorce [Fri, 9 Mar 2007 16:55:56 +0000 (16:55 +0000)]
r21776: fix bugs #4438 #4440
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
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
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.
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.
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.
James Peach [Thu, 8 Mar 2007 21:30:15 +0000 (21:30 +0000)]
r21767: Revert all the bits I accidentally committed in r21766.
James Peach [Thu, 8 Mar 2007 20:54:13 +0000 (20:54 +0000)]
r21766: Fix compiler warning.
James Peach [Thu, 8 Mar 2007 18:45:44 +0000 (18:45 +0000)]
r21765: Fix the build for HP-UX.
Jeremy Allison [Thu, 8 Mar 2007 18:43:39 +0000 (18:43 +0000)]
r21764: Fix warning in debug comment.
Jeremy.
James Peach [Thu, 8 Mar 2007 18:05:55 +0000 (18:05 +0000)]
r21763: Add support for the UNIX_INFO2 infolevel.
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.
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.
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.
James Peach [Thu, 8 Mar 2007 01:40:49 +0000 (01:40 +0000)]
r21757: Add SMB_VFS_CHFLAGS operation.
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.
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.
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.
Volker Lendecke [Wed, 7 Mar 2007 21:13:51 +0000 (21:13 +0000)]
r21753: Enable building ndrdump with the builtin popt. Jelmer, please check!
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.
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
Volker Lendecke [Wed, 7 Mar 2007 13:57:32 +0000 (13:57 +0000)]
r21747: Cosmetic checkin to bring ntcreate and nttranscreate closer together
James Peach [Wed, 7 Mar 2007 05:09:37 +0000 (05:09 +0000)]
r21738: Remove unused file.
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.
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.
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.
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.
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.
Volker Lendecke [Tue, 6 Mar 2007 10:40:18 +0000 (10:40 +0000)]
r21723: Make use of the per-hashchain "freelists"
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
James Peach [Tue, 6 Mar 2007 00:54:05 +0000 (00:54 +0000)]
r21717: Support the SMB_QUERY_POSIX_WHOAMI info level on QueryFsInfo.
Jeremy Allison [Tue, 6 Mar 2007 00:20:32 +0000 (00:20 +0000)]
r21715: Fix torture utime code.
Jeremy.
Jeremy Allison [Mon, 5 Mar 2007 23:40:03 +0000 (23:40 +0000)]
r21714: Change the VFS interface to use struct timespec
for utimes - change the call to ntimes. This preserves
nsec timestamps we get from stat (if the system supports
it) and only maps back down to usec or sec resolution
on time set. Looks bigger than it is as I had to move
lots of internal code from using time_t and struct utimebuf
to struct timespec.
Jeremy.
Volker Lendecke [Mon, 5 Mar 2007 20:09:27 +0000 (20:09 +0000)]
r21706: get_delete_on_close_flag() is the perfect candidate for tdb_parse_record()
Herb Lewis [Mon, 5 Mar 2007 18:27:20 +0000 (18:27 +0000)]
r21705: add modify rights defines
Herb Lewis [Mon, 5 Mar 2007 18:20:36 +0000 (18:20 +0000)]
r21704: open sockets immediately in process_loop
Herb Lewis [Mon, 5 Mar 2007 17:02:20 +0000 (17:02 +0000)]
r21703: fix build when O_SYNC not defined
Jeremy Allison [Sat, 3 Mar 2007 01:35:58 +0000 (01:35 +0000)]
r21672: The cannonical file access pattern should look like this :
srvstr_get_path(inbuf, name, smb_buf(inbuf) + 1, sizeof(name), 0, STR_TERMINATE, &status);
if (!NT_STATUS_IS_OK(status)) {
return ERROR_NT(status);
}
RESOLVE_DFSPATH(name, conn, inbuf, outbuf);
status = unix_convert(conn, name, False, NULL, &sbuf);
if (!NT_STATUS_IS_OK(status)) {
return ERROR_NT(status);
}
status = check_name(conn, name);
if (!NT_STATUS_IS_OK(status)) {
return ERROR_NT(status);
}
Make sure that every access pattern (including the
wildcard generated paths from unlink, rename, and copy)
do the same. Tidy things up a bit....
Jeremy.
Jeremy Allison [Fri, 2 Mar 2007 23:06:53 +0000 (23:06 +0000)]
r21667: posix_unlink should break existing oplocks.
Jeremy.
Jeremy Allison [Fri, 2 Mar 2007 23:04:44 +0000 (23:04 +0000)]
r21666: (only in 3.0, not 3.0.25). Fix bad parameter to call.
Jeremy.
Jeremy Allison [Fri, 2 Mar 2007 22:19:53 +0000 (22:19 +0000)]
r21665: Fix bug #4428 reported by Jason Mader <jason@ncac.gwu.edu>.
Jeremy.
Jeremy Allison [Fri, 2 Mar 2007 20:56:18 +0000 (20:56 +0000)]
r21664: Fix #4425 - patch from Jason Mader <jason@ncac.gwu.edu>.
Jeremy
Jeremy Allison [Fri, 2 Mar 2007 20:15:11 +0000 (20:15 +0000)]
r21663: Fix from the Wine guys: Robert Shearman <rob@codeweavers.com>
The background behind this patch is that we're using ntlm_auth with
Wine. Windows allows us to pass in a NULL domain and a username of the
form of "user@domain" and this is converted into an NTLMSSP_AUTH packet
with a NULL domain name and a username of the same form.
Jeremy.
Herb Lewis [Fri, 2 Mar 2007 15:08:09 +0000 (15:08 +0000)]
r21657: get rid of warning - not everyone understands %F
Jelmer Vernooij [Fri, 2 Mar 2007 14:26:19 +0000 (14:26 +0000)]
r21655: Regenerate after pidl bugfix.
Jelmer Vernooij [Fri, 2 Mar 2007 13:10:12 +0000 (13:10 +0000)]
r21652: Fix samba3-specific initialization
Jelmer Vernooij [Fri, 2 Mar 2007 12:54:37 +0000 (12:54 +0000)]
r21651: Add ndrdump to samba 3. This only works from external source at the
moment. To use, use something like:
./bin/ndrdump -l bin/smbd winreg winreg_EnumValue in <filename>
or to see what functions are available:
./bin/ndrdump -l bin/smbd winreg
James Peach [Fri, 2 Mar 2007 03:51:22 +0000 (03:51 +0000)]
r21647: Allow unit on for size parameters.
Jeremy Allison [Thu, 1 Mar 2007 23:57:37 +0000 (23:57 +0000)]
r21646: Patch from SATOH Fumiyasu <fumiyas@osstech.co.jp>
- add minsize parameter. Bug #4409.
Jeremy.
Jeremy Allison [Thu, 1 Mar 2007 23:03:46 +0000 (23:03 +0000)]
r21645: Make posix_unlink work - on open files too !
Jeremy.
Jeremy Allison [Thu, 1 Mar 2007 22:44:02 +0000 (22:44 +0000)]
r21644: Allow mkdir on platforms with no O_DIRECTORY.
Add proper debug to all possible setfilepathinfo
functions.
Jeremy.
Jeremy Allison [Thu, 1 Mar 2007 22:15:30 +0000 (22:15 +0000)]
r21643: Put the correct bits on the wire for posix_mkdir.
We're not yet deleting open files on unlink. Investigating...
Jeremy.
Volker Lendecke [Thu, 1 Mar 2007 22:12:49 +0000 (22:12 +0000)]
r21642: Fix bug 4365. Please note that this was only tested with Vista so far, it
needs testing with other clients as well. I'm afraid I'm visiting a conference
tomorrow and saturday, so I'd be happy to get support in this.
Thanks,
Volker
Jeremy Allison [Thu, 1 Mar 2007 21:56:54 +0000 (21:56 +0000)]
r21641: Add test code for POSIX pathname calls into smbclient.
Jeremy.
Jeremy Allison [Thu, 1 Mar 2007 21:36:05 +0000 (21:36 +0000)]
r21640: Fix the build for broken platoforms without O_DIRECT or O_DIRECTORY.
Jeremy.
Jeremy Allison [Thu, 1 Mar 2007 21:05:29 +0000 (21:05 +0000)]
r21639: Add in implementations of POSIX open/mkdir/unlink/rmdir.
Jeremy.