vlendec/samba-autobuild/.git
16 years agor20744: Fix the build (I missed some chkpth -> checkpath renames).
Jeremy Allison [Sat, 13 Jan 2007 22:26:46 +0000 (22:26 +0000)]
r20744: Fix the build (I missed some chkpth -> checkpath renames).
Jeremy.
(This used to be commit 89b7a0630de0bd95a56263b36d433b4e73517a70)

16 years agor20743: Remove another BOOL ok from reply_getatr.
Jeremy Allison [Sat, 13 Jan 2007 22:22:32 +0000 (22:22 +0000)]
r20743: Remove another BOOL ok from reply_getatr.
Jeremy.
(This used to be commit c154f430710a4646fac42774817dfed7b936b087)

16 years agor20742: Rename chkpth -> checkpath for sanity's sake :-).
Jeremy Allison [Sat, 13 Jan 2007 22:10:18 +0000 (22:10 +0000)]
r20742: Rename chkpth -> checkpath for sanity's sake :-).
Start removing unneeded "BOOL ok" from this reply.c
(this logic is old, old, old..... :-).
Jeremy.
(This used to be commit 3d52268095c605a80dfcd371769198a332baa0a5)

16 years agor20740: Get rid of some if-statements
Volker Lendecke [Sat, 13 Jan 2007 20:26:53 +0000 (20:26 +0000)]
r20740: Get rid of some if-statements
(This used to be commit db93c1b98d5445071ad0af229afed1f11ab0a862)

16 years agor20738: Remove unused variable
Volker Lendecke [Sat, 13 Jan 2007 19:55:37 +0000 (19:55 +0000)]
r20738: Remove unused variable
(This used to be commit c16ce9ebaab0175e7f1dc13798d5599388fa35d6)

16 years agor20725: Get rid of a bool passed down -- gd, please check
Volker Lendecke [Sat, 13 Jan 2007 10:40:09 +0000 (10:40 +0000)]
r20725: Get rid of a bool passed down -- gd, please check
(This used to be commit 1ef910f423a9ec69af6abf5a4e2137e8a4e81755)

16 years agor20724: Get closer to passing RAW-OPEN. If the client is using
Jeremy Allison [Sat, 13 Jan 2007 02:34:43 +0000 (02:34 +0000)]
r20724: Get closer to passing RAW-OPEN. If the client is using
create disposition of FILE_CREATE then there's no need
to check can_delete_file_in_directory().
Jeremy.
(This used to be commit eb32b60efc4c332295ff6fc7e5d575f4b40e8ff6)

16 years agor20722: RAW-CHKPATH should now pass, build farm should
Jeremy Allison [Sat, 13 Jan 2007 02:13:45 +0000 (02:13 +0000)]
r20722: RAW-CHKPATH should now pass, build farm should
go back to normal. Sorry about that.
Jeremy.
(This used to be commit d4127034fb89185fe7464d57c9f56f7914da6141)

16 years agor20721: Fix the search unix_convert error returns. Only open
Jeremy Allison [Sat, 13 Jan 2007 01:29:10 +0000 (01:29 +0000)]
r20721: Fix the search unix_convert error returns. Only open
to go...
Jeremy.
(This used to be commit 89f03a8db40365f99c6755ff19a4bfbf8d1bd316)

16 years agor20720: Fix the chkpath problem, still looking at findfirst.
Jeremy Allison [Sat, 13 Jan 2007 01:07:39 +0000 (01:07 +0000)]
r20720: Fix the chkpath problem, still looking at findfirst.
Jeremy.
(This used to be commit c5be0082ef60cd041121a9c36f4af934cd60562d)

16 years agor20718: Sync up the filename path parsing changes from SAMBA_3_0_24.
Jeremy Allison [Fri, 12 Jan 2007 23:47:16 +0000 (23:47 +0000)]
r20718: Sync up the filename path parsing changes from SAMBA_3_0_24.
The only difference between the two trees now w.r.t file
serving are the changes to smbd/open.c in this branch I need
to review.
Jeremy.
(This used to be commit f4474edf6a0c71001dbd01429ef70bafad6abd74)

16 years agor20717: Merge sharemode patch from Mathias Dietz <MDIETZ@de.ibm.com>.
Jim McDonough [Fri, 12 Jan 2007 21:56:25 +0000 (21:56 +0000)]
r20717: Merge sharemode patch from Mathias Dietz <MDIETZ@de.ibm.com>.

The patch fixes the behaviour of GPFS sharemodes when
the access mask is no_access.
(This used to be commit 799967c66879b4d6e28f1af6ba27c67f0b1deaeb)

16 years agor20707: Clean up pdb_interface.c a bit -- patch from Michael Adam <ma@sernet.de>
Volker Lendecke [Fri, 12 Jan 2007 14:16:30 +0000 (14:16 +0000)]
r20707: Clean up pdb_interface.c a bit -- patch from Michael Adam <ma@sernet.de>
(This used to be commit d78c18a9fa494a2b3ef48db0abd987c740556e50)

16 years agor20700: In the main processing loop we select() on the fam socket. If it fires, it
Volker Lendecke [Fri, 12 Jan 2007 09:29:44 +0000 (09:29 +0000)]
r20700: In the main processing loop we select() on the fam socket. If it fires, it
might be possible that we hang in the receive_smb() although that socket is
not the reason for the select() to return.

This immediately reacts to the fam socket to become readable, and goes into
the select loop again. This fixes delays in files showing up in Windows.

Jeremy, James please review this and merge to 3_0_24 if appropriate.

Thanks,

Volker
(This used to be commit c846153b2ed2f9aca82491888e391ccbe239e88a)

16 years agor20699: This is an attempt to fix bug 4326.
Volker Lendecke [Fri, 12 Jan 2007 08:49:09 +0000 (08:49 +0000)]
r20699: This is an attempt to fix bug 4326.

James, can you please confirm this and merge it to 3_0_24? For me it fixes the
segfault.

Thanks,

Volker
(This used to be commit a841b7659ba7b76b2da7993e1f4402aa0e11716f)

16 years agor20695: Remove duplication of constants.
Jeremy Allison [Fri, 12 Jan 2007 02:58:01 +0000 (02:58 +0000)]
r20695: Remove duplication of constants.
Jeremy.
(This used to be commit 66cca893e1aa035fa0aa05c0d542848f084fac31)

16 years agor20694: To get this right we need to do signed 64-bit
Jeremy Allison [Fri, 12 Jan 2007 02:48:37 +0000 (02:48 +0000)]
r20694: To get this right we need to do signed 64-bit
comparisons here, not unsigned as we're eventually
casting into what it normall a signed 32 bit
value. Guenther please check (but I think I'm right here).
Jeremy.
(This used to be commit 31f8e0edc0c3e76654728b2c204faa70830e1f1b)

16 years agor20692: Fix bug found by Guenther -
Jeremy Allison [Fri, 12 Jan 2007 02:12:15 +0000 (02:12 +0000)]
r20692: Fix bug found by Guenther -

Just try to log on in offline mode without the fix: all accounts are expired,
although they are set to never expire in the PAC/info3.

NTTIME "Never" needs to get (time_t) -1.

We were casting a uint64 to time_t before
comparing, and we should have been doing it
the other way around.

Guenther please check this fixes things.

Jeremy.
(This used to be commit f4e898b6224fd82d9805da771ef6040065de7b12)

16 years agor20690: fix a bug that causes smbd to 'hang' intermittently.
Andrew Tridgell [Thu, 11 Jan 2007 23:10:16 +0000 (23:10 +0000)]
r20690: fix a bug that causes smbd to 'hang' intermittently.

The problem occurs like this:

  1) running smbd as a domain member without winbindd

  2) client1 connects, during auth smbd-1 calls update_trustdom_cache()

  3) smbd-1 takes the trustdom cache timestamp lock, then starts
     enumerate_domain_trusts

  4) enumerate_domain_trusts hangs for some unknown reason

  5) other clients connect, all block waiting for read lock on trustdom
     cache

  6) samba is now hung

The problem is the lock, and really its just trying to avoid a race
where the cure is worse than the problem. A race in updating the
trutdom cache is not a big issue. So I've just removed the lock.

It is still an open question why enumerate_domain_trusts() can
hang. Unfortunately I've not in a position to get a sniff at the site
that is affected. I suspect a full fix will involve ensuring that all
the rpc code paths have appropriate timeouts.
(This used to be commit ab8d41053347a5b342ed5b59a0b0dd4983ca91e6)

16 years agor20687: Implement grace logons for offline authentications in pam_winbind.
Günther Deschner [Thu, 11 Jan 2007 15:41:02 +0000 (15:41 +0000)]
r20687: Implement grace logons for offline authentications in pam_winbind.

In case a user authenticated sucessfully and his password just expired
while beeing disconnected, we should allow a user to logon (given a
clear warning). We currently forced the user into a password change
dialogue in that scenario; this did not make much sense while offline.

Guenther
(This used to be commit 668b278653acfc4de7807834988f7af557e608a5)

16 years agor20674: Regenerate NDR parsers after pidl changes. This should fix a couple of
Jelmer Vernooij [Thu, 11 Jan 2007 01:47:22 +0000 (01:47 +0000)]
r20674: Regenerate NDR parsers after pidl changes. This should fix a couple of
coverity warnings.
(This used to be commit 5f86d006debd880ec35db4ebe7db0663c5cb220f)

16 years agor20668: Also do not install the smbumount man page if we don't build smbumount.
Lars Müller [Wed, 10 Jan 2007 21:46:39 +0000 (21:46 +0000)]
r20668: Also do not install the smbumount man page if we don't build smbumount.
(This used to be commit 82ce272b2464f06e8bcbed6452621daa05e12b5d)

16 years agor20666: Also do not install the smbmnt man page if SMBMOUNT_PROGS is not set.
Lars Müller [Wed, 10 Jan 2007 20:08:25 +0000 (20:08 +0000)]
r20666: Also do not install the smbmnt man page if SMBMOUNT_PROGS is not set.
(This used to be commit aa122be8f7a33ebceeb43e4f0c5362047560b199)

16 years agor20664: Set the environment variable _before_ calling the shell.
Lars Müller [Wed, 10 Jan 2007 19:54:49 +0000 (19:54 +0000)]
r20664: Set the environment variable _before_ calling the shell.
(This used to be commit 9cecd62654d22b47d938a44a8aed63c558d511ad)

16 years agor20663: Do not install smbmount man page if we didn't called configure
Lars Müller [Wed, 10 Jan 2007 19:16:59 +0000 (19:16 +0000)]
r20663: Do not install smbmount man page if we didn't called configure
--with-smbmount.
(This used to be commit ee12348cf1e93d0e75714f3883bfea6525797dc1)

16 years agor20654: Fix from Karolin Seeger <ks@sernet.de>: Accept "forever", "off" and "never" as
Volker Lendecke [Wed, 10 Jan 2007 15:31:42 +0000 (15:31 +0000)]
r20654: Fix from Karolin Seeger <ks@sernet.de>: Accept "forever", "off" and "never" as
key words for -1 as policy values for net sam policy.

Volker
(This used to be commit b6347751d8f67dcaac5c1bcbc07f03073278f6fb)

16 years agor20651: Fix "password expires soon" warning message for pam_winbind.
Günther Deschner [Wed, 10 Jan 2007 12:34:24 +0000 (12:34 +0000)]
r20651: Fix "password expires soon" warning message for pam_winbind.

We were incorrectly calculating the days until the password expires and
we also need to look at the info3 pass_must_change_time for expiry
calculation.

Guenther
(This used to be commit 22d79237127a064a934928d175182adecc6300de)

16 years agor20644: Make some functions static, thanks to Michael Adam <ma@sernet.de> for the...
Volker Lendecke [Wed, 10 Jan 2007 07:56:43 +0000 (07:56 +0000)]
r20644: Make some functions static, thanks to Michael Adam <ma@sernet.de> for the hint.
(This used to be commit f1f5d035db067b85e55b1c4009407b47dedcf975)

16 years agor20636: Remove notify leftover
Volker Lendecke [Tue, 9 Jan 2007 20:04:46 +0000 (20:04 +0000)]
r20636: Remove notify leftover
(This used to be commit a174b49173e7185abb89e605e667e64e8dd87454)

16 years agor20635: Add placeholder to ensure we don't go into the
Jeremy Allison [Tue, 9 Jan 2007 18:48:38 +0000 (18:48 +0000)]
r20635: Add placeholder to ensure we don't go into the
wcard unlink if bad_path was set. The error
returned here is almost certainly incorrect
and will need testing properly with smbtorture,
but I don't want to forget about this path
(yes Volker I know this is currently incorrect :-).
Jeremy.
(This used to be commit 06e20c287898d21e437ab117eb5eeeaf2420ba78)

16 years agor20634: A *LOT* more work is necessary before touching notify remotely starts to...
Volker Lendecke [Tue, 9 Jan 2007 16:12:54 +0000 (16:12 +0000)]
r20634: A *LOT* more work is necessary before touching notify remotely starts to make
sense. Until then, remove it from the tree to keep the diff between 3_0_24 and
3_0 small.

Volker
(This used to be commit f146a85e74c84e78a11e616a1cbeaeef4693a0e0)

16 years agor20632: The extended RAW-SAMBA3BADPATH test led me to some wrong assumptions, in
Volker Lendecke [Tue, 9 Jan 2007 15:50:40 +0000 (15:50 +0000)]
r20632: The extended RAW-SAMBA3BADPATH test led me to some wrong assumptions, in
particular the NT_STATUS_INVALID_PARAMETER thing was badly wrong. Remove the
changes based on it. Using gentest is much more effective in this respect, but
it will take a while to figure out the wildcard error handling of W2k3.

Volker
(This used to be commit 58b8a242a7f08c1292d24fc73df170dbcd68c10d)

16 years agor20630: Fix some trivial memleaks.
Günther Deschner [Tue, 9 Jan 2007 13:24:33 +0000 (13:24 +0000)]
r20630: Fix some trivial memleaks.

Guenther
(This used to be commit 3bb94a081888eca69796b14057b551b078ee9a77)

16 years agor20628: Looks bigger than it is. This is just re-indenting the if (dirname) that...
Volker Lendecke [Tue, 9 Jan 2007 09:03:33 +0000 (09:03 +0000)]
r20628: Looks bigger than it is. This is just re-indenting the if (dirname) that we've
taken care of above.

Volker
(This used to be commit 5e1da363bb3f2675beb9fd9240301bb432e5239b)

16 years agor20627: orig_name is not needed anymore, and slightly simplify logic by doing early
Volker Lendecke [Tue, 9 Jan 2007 08:56:24 +0000 (08:56 +0000)]
r20627: orig_name is not needed anymore, and slightly simplify logic by doing early
returns.

Volker
(This used to be commit 614651c6a72742173de5fa8723403880acc37c09)

16 years agor20626: Fix a memleak found by the IBM checker -- not on 3.0.24
Volker Lendecke [Tue, 9 Jan 2007 08:19:05 +0000 (08:19 +0000)]
r20626: Fix a memleak found by the IBM checker -- not on 3.0.24
(This used to be commit 9d0a789e32e6a6501421edb25bc8197c9e06846d)

16 years agor20619: bad_path is handled somewhere else, so can_delete does not need it anymore
Volker Lendecke [Mon, 8 Jan 2007 21:13:27 +0000 (21:13 +0000)]
r20619: bad_path is handled somewhere else, so can_delete does not need it anymore
(This used to be commit 1798987128be579a1a4574294a7c3094040ebaf2)

16 years agor20618: Fix a bug in bad_path handling that also exists in 3.0.23: For reply_unlink
Volker Lendecke [Mon, 8 Jan 2007 21:08:31 +0000 (21:08 +0000)]
r20618: Fix a bug in bad_path handling that also exists in 3.0.23: For reply_unlink
under Linux we returned NT_STATUS_NOT_A_DIRECTORY. This is because in the
bad_path==True condition lstat(2) returns ENOTDIR and not ENOENT.

Not sure if we want to necessarily replicate the INVALID_PARAMETER here, but
this is what W2k3 does.

Jeremy, I tried to call you, but you were not around. So I'll leave it up to
you to merge this.

Volker
(This used to be commit b1edc3d053104204b966eed67d070ad5da40f17b)

16 years agor20617: Do not notify if the delete failed
Volker Lendecke [Mon, 8 Jan 2007 20:06:36 +0000 (20:06 +0000)]
r20617: Do not notify if the delete failed
(This used to be commit c86fbdf8cc8f6f17b23e647bd1f4714c6095b860)

16 years agor20614: Dummy-checkin to trigger the build
Volker Lendecke [Mon, 8 Jan 2007 16:52:58 +0000 (16:52 +0000)]
r20614: Dummy-checkin to trigger the build
(This used to be commit 7e444e1612fa49f7db4de3256e6c67025db28806)

16 years agor20612: A checkin I've wanted to do for ages: For bad_path==False set_bad_path_error
Volker Lendecke [Mon, 8 Jan 2007 15:36:33 +0000 (15:36 +0000)]
r20612: A checkin I've wanted to do for ages: For bad_path==False set_bad_path_error
is equivalent to UNIX_ERROR. Expand the last reference. Lets see if I can kill
that as well :-)

Volker
(This used to be commit 794d5d38f19601bb5b30b965b41b844aacf1caeb)

16 years agor20611: All but one callers to set_bad_path_error have had the bad_path==True argument
Volker Lendecke [Mon, 8 Jan 2007 15:26:17 +0000 (15:26 +0000)]
r20611: All but one callers to set_bad_path_error have had the bad_path==True argument
being handled further up.

Volker
(This used to be commit 358673c36697a16aa87f9cebbace34abf16ed28e)

16 years agor20610: Fix a Solaris warning
Volker Lendecke [Mon, 8 Jan 2007 14:16:42 +0000 (14:16 +0000)]
r20610: Fix a Solaris warning
(This used to be commit 60d7b349dbc12288a3da0486b571a1d83401d0b7)

16 years agor20608: ENOENT->NT_STATUS_OBJECT_NAME_NOT_FOUND is covered in the standard unix error...
Volker Lendecke [Mon, 8 Jan 2007 14:08:34 +0000 (14:08 +0000)]
r20608: ENOENT->NT_STATUS_OBJECT_NAME_NOT_FOUND is covered in the standard unix error mapping table
(This used to be commit 816c19aaeb812a94fd5669174c9beec60ce1a73f)

16 years agor20607: Next micro-step for reply_setatr
Volker Lendecke [Mon, 8 Jan 2007 13:21:43 +0000 (13:21 +0000)]
r20607: Next micro-step for reply_setatr
(This used to be commit cea9a01434490fb8a17c3f12db7a092efda21186)

16 years agor20606: bad_path == True has been covered further up in reply_setatr.
Volker Lendecke [Mon, 8 Jan 2007 13:18:23 +0000 (13:18 +0000)]
r20606: bad_path == True has been covered further up in reply_setatr.

I'm checking in micro-steps to make them independently checkable. This code
just very severely needs cleanup, but I don't want to break anything. So, be
patient with me, please :-)

Volker
(This used to be commit c16775486baa89901f0d5126cb926c9e5a807743)

16 years agor20605: Simplify logic in reply_setatr slightly
Volker Lendecke [Mon, 8 Jan 2007 13:05:36 +0000 (13:05 +0000)]
r20605: Simplify logic in reply_setatr slightly
(This used to be commit f19db8f33ed3749f6b72ae3a4cee83574c606e88)

16 years agor20604: Fix two memleaks, Coverity ID 337, merge to 3_0_24
Volker Lendecke [Mon, 8 Jan 2007 08:09:29 +0000 (08:09 +0000)]
r20604: Fix two memleaks, Coverity ID 337, merge to 3_0_24
(This used to be commit 44f9d25a9026df29fcaae8723ef52b1d3101628b)

16 years agor20603: Slightly simplify logic
Volker Lendecke [Mon, 8 Jan 2007 08:05:49 +0000 (08:05 +0000)]
r20603: Slightly simplify logic
(This used to be commit e4dea0e64747912da899e846b944c24804772259)

16 years agor20602: Fix coverity ID 339. SMB_ASSERT does not panic without -DDEVELOPER.
Volker Lendecke [Mon, 8 Jan 2007 08:00:53 +0000 (08:00 +0000)]
r20602: Fix coverity ID 339. SMB_ASSERT does not panic without -DDEVELOPER.

Volker
(This used to be commit 33b5950bec407e295b2c6139e21d062e376df330)

16 years agor20597: Survive some of the notify mask tests.
Volker Lendecke [Sun, 7 Jan 2007 18:08:50 +0000 (18:08 +0000)]
r20597: Survive some of the notify mask tests.
(This used to be commit e4a2e63272dc5b20413597179d06b0185c4a6817)

16 years agor20589: Re-add lost bad_path handling, sorry.
Volker Lendecke [Sat, 6 Jan 2007 18:59:02 +0000 (18:59 +0000)]
r20589: Re-add lost bad_path handling, sorry.
(This used to be commit 244f96388c843fd629478d0069f68550a2006d06)

16 years agor20585: - allocate an OID range for LDB/LDAP extended operations
Stefan Metzmacher [Sat, 6 Jan 2007 10:10:25 +0000 (10:10 +0000)]
r20585: - allocate an OID range for LDB/LDAP extended operations

metze
(This used to be commit 5373897ef54ba5d04d214cd7a32d2c971059314c)

16 years agor20578: - allocate an OID range for samba4 LDB/LDAP Controls
Stefan Metzmacher [Sat, 6 Jan 2007 01:10:20 +0000 (01:10 +0000)]
r20578: - allocate an OID range for samba4 LDB/LDAP Controls
- allocate an OID range for conflicting attributes/classes

metze
(This used to be commit 6fedd69f5e9a647cd50b08dba517e1f27a06a802)

16 years agor20558: Refactor rmdir_internals to use early termination rather
Jeremy Allison [Fri, 5 Jan 2007 17:42:54 +0000 (17:42 +0000)]
r20558: Refactor rmdir_internals to use early termination rather
than lots of indented code. Change recursive_rmdir()
to return the smbd standards of True on success, False
on fail (it was doing the reverse, which was very confusing).
Jeremy.
(This used to be commit 27dc5bebda7ffbdcb2371638f6132063a953fba2)

16 years agor20546: Fix some IBM checker errors
Volker Lendecke [Fri, 5 Jan 2007 14:52:10 +0000 (14:52 +0000)]
r20546: Fix some IBM checker errors
(This used to be commit 8f67efd582655e03fea746eee499f3cab6cbdb4d)

16 years agor20544: Change copy_file() to return NTSTATUS. This is in preparation of turning
Volker Lendecke [Fri, 5 Jan 2007 13:13:15 +0000 (13:13 +0000)]
r20544: Change copy_file() to return NTSTATUS. This is in preparation of turning
close_file() to NTSTATUS as well.

I'm not sure I got all the error codes right, but as I've never come across a
smb_copy() call in all my Samba work, I'm leaving it at that. If I'm
absolutely bored, I will write a thorough torture test.

As far as I can see, Samba4 even does not have a libcli implementation for
it...  :-)

Volker
(This used to be commit 5ebdf02ba166df69e210e6f70c01a44e6205ecc1)

16 years agor20542: Make close_remove_share_mode retun NTSTATUS. Not that anybody cares yet...
Volker Lendecke [Fri, 5 Jan 2007 11:31:28 +0000 (11:31 +0000)]
r20542: Make close_remove_share_mode retun NTSTATUS. Not that anybody cares yet...
(This used to be commit c8995771531caa4ec9bcaef2c29b11ee7d8e49e6)

16 years agor20541: Fix some obvious glitches in wait_for_aio_completion. Hmmm. It seems
Volker Lendecke [Fri, 5 Jan 2007 11:18:59 +0000 (11:18 +0000)]
r20541: Fix some obvious glitches in wait_for_aio_completion. Hmmm. It seems
reply_close() at its heart is going to be an async call :-)

Volker
(This used to be commit 36f60407ae9b430dc5d7f67dd3e7ed8b1dbc93a8)

16 years agor20536: In the offline PAM session close case the attempt to delete a
Günther Deschner [Thu, 4 Jan 2007 23:41:16 +0000 (23:41 +0000)]
r20536: In the offline PAM session close case the attempt to delete a
non-existing krb5 credential cache should not generate an error.

Guenther
(This used to be commit 11c6f573af5c1d3387e60f3fc44b00e28cd87813)

16 years agor20535: Fix make install to work when root doesn't have
Jeremy Allison [Thu, 4 Jan 2007 23:25:04 +0000 (23:25 +0000)]
r20535: Fix make install to work when root doesn't have
write access into the source tree (like when your
directory is nfs mounted for example....).
Jeremy.
(This used to be commit 7dcb61d1b2d08270a8c718328a26ef4866a1c500)

16 years agor20532: From Volker...
Jeremy Allison [Thu, 4 Jan 2007 22:01:36 +0000 (22:01 +0000)]
r20532: From Volker...

"smbcli_setattr("") always returns ACCESS_DENIED, test extension to follow.

Merge to 3.0.24?"

Yep (with slight optimization).

Jeremy.
(This used to be commit dcc7bca1adbc69f348d46291ec2cbfaf5d8486bc)

16 years agor20530: Don't want this call to get inadvertently re-added :-).
Jeremy Allison [Thu, 4 Jan 2007 20:46:13 +0000 (20:46 +0000)]
r20530: Don't want this call to get inadvertently re-added :-).
Jeremy.
(This used to be commit 68c4fbcf3397d6c43a3e5809b20a23116b1f8a31)

16 years agor20525: Closing a dir with del-on-close set requires the same as files: Don't actually
Volker Lendecke [Thu, 4 Jan 2007 16:26:15 +0000 (16:26 +0000)]
r20525: Closing a dir with del-on-close set requires the same as files: Don't actually
unlink/rmdir if another process still has it open.

Jeremy, this is a potential merger to 3.0.24.

Volker
(This used to be commit 8e1e896b02da99b5a48883c5f37fe146ad0fb5ce)

16 years agor20524: Simplify logic of close_remove_share_mode().
Volker Lendecke [Thu, 4 Jan 2007 15:12:22 +0000 (15:12 +0000)]
r20524: Simplify logic of close_remove_share_mode().

Volker
(This used to be commit ade90dbf0c2cbd2cc49a6357f3dd220ea82fd215)

16 years agor20512: Fix typo.
Günther Deschner [Wed, 3 Jan 2007 16:05:00 +0000 (16:05 +0000)]
r20512: Fix typo.

Guenther
(This used to be commit 36bd5cb21bdaf35c7dae47f8b8e93822b3f6188c)

16 years agor20507: smbcli_setattr("") always returns ACCESS_DENIED, test extension to follow.
Volker Lendecke [Wed, 3 Jan 2007 12:01:17 +0000 (12:01 +0000)]
r20507: smbcli_setattr("") always returns ACCESS_DENIED, test extension to follow.

Merge to 3.0.24?

Volker
(This used to be commit f2563ac98f8ec7af8083d2b62186753acba7a9dd)

16 years agor20503: And one more 64-bit warning
Volker Lendecke [Wed, 3 Jan 2007 09:30:55 +0000 (09:30 +0000)]
r20503: And one more 64-bit warning
(This used to be commit 7bcde1069e38d70808d78c408f16821a0bfadcdd)

16 years agor20502: Activate RAW-RENAME, my Linux box passes this
Volker Lendecke [Wed, 3 Jan 2007 09:04:06 +0000 (09:04 +0000)]
r20502: Activate RAW-RENAME, my Linux box passes this
(This used to be commit 56c8d2cfed273655b2c79b3a2c613a7253e05221)

16 years agor20501: Check in config.h fix from Michael Adam <ma@sernet.de>
Volker Lendecke [Wed, 3 Jan 2007 08:55:22 +0000 (08:55 +0000)]
r20501: Check in config.h fix from Michael Adam <ma@sernet.de>
(This used to be commit d10dd47fb8908a4372aa6932e40b23189784522c)

16 years agor20500: Fix compiler warnings.
James Peach [Wed, 3 Jan 2007 06:55:12 +0000 (06:55 +0000)]
r20500: Fix compiler warnings.
(This used to be commit 9a790ee1fcfdaab1c9ee0884694832bd81f512bb)

16 years agor20499: Activate RAW-OPEN in the build farm
Volker Lendecke [Wed, 3 Jan 2007 06:53:13 +0000 (06:53 +0000)]
r20499: Activate RAW-OPEN in the build farm
(This used to be commit a0d5de61a10321ee2edd832dcda611230d796dd6)

16 years agor20498: Two 64-bit warnings
Volker Lendecke [Wed, 3 Jan 2007 06:39:18 +0000 (06:39 +0000)]
r20498: Two 64-bit warnings
(This used to be commit 382827ebac61646ec31fe1d56ccde2ea337e8f9e)

16 years agor20496: Some changes to make Samba3 the RAW-OPEN test. Checking in to both 3_0 and
Volker Lendecke [Wed, 3 Jan 2007 06:19:11 +0000 (06:19 +0000)]
r20496: Some changes to make Samba3 the RAW-OPEN test. Checking in to both 3_0 and
3_0_24 because I was explicitly asked to, although this needs close
review. Jeremy, I'm sure you will check this thoroughly :-)

In reply_open_and_X the separate "size" variable kills the calculation of the
SPARSE flag returned to the client in the attrib field. In getpathinfo we do
it correctly, and RAW-OPEN (correctly) complains about the difference.

Add the "set the write time" to mknew and create.

For trans2open we were missing the "ofun == 0" ->
NT_STATUS_OBJECT_NAME_COLLISION case, and we dropped the status returned in
favor of ACCESS_DENIED once too many.

Last change is a fix to trans2open: We were returning the attributes given by
the client, not the attributes of the new file.

Volker
(This used to be commit 84e6889632c7f98a7cb37036b0acdf538d50d16c)

16 years agor20489: Missed patch ofthe forest_name patch for lookupname
Gerald Carter [Tue, 2 Jan 2007 22:14:26 +0000 (22:14 +0000)]
r20489: Missed patch ofthe forest_name patch for lookupname
(This used to be commit 25c4ebb55f425816e033491138f1216125de6edb)

16 years agor20488: When joined to a child domain in a multi-domain/single domain tree,
Gerald Carter [Tue, 2 Jan 2007 21:48:47 +0000 (21:48 +0000)]
r20488: When joined to a child domain in a multi-domain/single domain tree,
the child domain cannot always resolve SIDs in sibling domains.
Windows tries to contact a DC in its own domain and then the root
domain in the forest.  This async changes makes winbindd's name2sid()
call do the same.
(This used to be commit 7b2bf0e5a6b8d4119657c7a34aa53c9a0c1d5723)

16 years agor20487: Remove the unused dn2ad_canonical() call
Gerald Carter [Tue, 2 Jan 2007 21:45:12 +0000 (21:45 +0000)]
r20487: Remove the unused dn2ad_canonical() call
(This used to be commit 86e6ae6a9fe2a6fdaeeb503653a312662c7f50e9)

16 years agor20486: Always upper case the "host/<sAMAccoutnName>" entry in the keytab file
Gerald Carter [Tue, 2 Jan 2007 21:29:09 +0000 (21:29 +0000)]
r20486: Always upper case the "host/<sAMAccoutnName>" entry in the keytab file
so apps will know which one to look for,
(This used to be commit d4a5dc3ad5f56a5f741424ecc4fffa0ef39bdc67)

16 years agor20485: Add select with a 10 second timeout when reading DSN update responses.
Gerald Carter [Tue, 2 Jan 2007 21:20:40 +0000 (21:20 +0000)]
r20485: Add select with a 10 second timeout when reading DSN update responses.
(This used to be commit cb6c6a49e257d60318101c897e8d2b86de08a846)

16 years agor20482: Make us survive and activate RAW-CLOSE
Volker Lendecke [Tue, 2 Jan 2007 16:40:41 +0000 (16:40 +0000)]
r20482: Make us survive and activate RAW-CLOSE
(This used to be commit 471c6e6a2142afbca36163bcdbb5b6fb4e7ac774)

16 years agor20479: Both remaining calls of can_delete called it with check_is_at_open==False,
Volker Lendecke [Tue, 2 Jan 2007 15:07:27 +0000 (15:07 +0000)]
r20479: Both remaining calls of can_delete called it with check_is_at_open==False,
remove that parameter.

Volker
(This used to be commit e51b7648703f3a85b840501dd4199600a5a7e44f)

16 years agor20478: Make us survive & activate RAW-UNLINK
Volker Lendecke [Tue, 2 Jan 2007 15:01:43 +0000 (15:01 +0000)]
r20478: Make us survive & activate RAW-UNLINK
(This used to be commit 4f0f917b344743e16e8bacf4e72529a2890590fe)

16 years agor20470: Jeremy, another one to check:
Volker Lendecke [Tue, 2 Jan 2007 12:10:46 +0000 (12:10 +0000)]
r20470: Jeremy, another one to check:

The only error path of can_delete() that we're interested in ntcreate&x is the
one of can_delete_file_in_directory(), so call that directly.

The only other one where we might get a NT_STATUS_ACCESS_DENIED is from the
lstat in can_delete, but this is covered later in the open_directory and
open_file_ntcreate calls. open_directory does a stat() in the open case which
also covers the (potential) symlink, and open_file_ntcreate does the open(2)
itself, so this should also work.

This makes can_delete() static to reply.c.

Volker
(This used to be commit d289037fdbc8bd3e0723784888946d5b39ffadef)

16 years agor20465: Get rid of a redundant !NT_STATUS_IS_OK(status)
Volker Lendecke [Tue, 2 Jan 2007 11:16:27 +0000 (11:16 +0000)]
r20465: Get rid of a redundant !NT_STATUS_IS_OK(status)
(This used to be commit ff173995cfeac216ab26faef6553be8f7f439347)

16 years agor20454: Get rid of a bogus variable that was only assigned but never read.
Volker Lendecke [Mon, 1 Jan 2007 21:37:02 +0000 (21:37 +0000)]
r20454: Get rid of a bogus variable that was only assigned but never read.

Jeremy, please check this.

Thanks,

Volker
(This used to be commit 2becbb9e5f7d1b04962178e6f0c97c3ccf2b0f88)

16 years agor20451: Survive the first of the filter-tests (mkdir).
Volker Lendecke [Mon, 1 Jan 2007 18:11:32 +0000 (18:11 +0000)]
r20451: Survive the first of the filter-tests (mkdir).

Add lots of TODOs :-)

Volker
(This used to be commit 0e953884a15873b0962ab1ab064d6b3a436726c0)

16 years agor20448: Happy New Year!
Stefan Metzmacher [Mon, 1 Jan 2007 17:29:20 +0000 (17:29 +0000)]
r20448: Happy New Year!

metze
(This used to be commit 3260d2116358fc64c40d2cbe8bffed4f3e387323)

16 years agor20443: Fix a compiler warning
Volker Lendecke [Sun, 31 Dec 2006 18:10:47 +0000 (18:10 +0000)]
r20443: Fix a compiler warning
(This used to be commit 19781d71fc5a8146109395cd53c04cf13cc48652)

16 years agor20442: Slight rewrite of the change notify infrastructure. This now survives the
Volker Lendecke [Sun, 31 Dec 2006 17:52:24 +0000 (17:52 +0000)]
r20442: Slight rewrite of the change notify infrastructure. This now survives the
first of the raw-notify subtests, the one-level test_notify_dir without any
flags around yet.

The tricky part was getting the data structures right, I hope the next tests
don't let that fall over.

fsp->notify is now by default NULL, meaning that nobody has issued a
changenotify call. This means nobody is interested in changes for this
directory.

If that has happened, notify_change_buf collects the changes if no current
request is outstanding, and it collects the requests if no change has happened
since the last request.

Happy New Year, somewhere on this planet it's already 2007 :-)

Volker

P.S: Jeremy, there's a question for you in smbd/files.c line 367.
(This used to be commit ce0ad24988075465addcac0b9afc872e909135af)

16 years agor20434: Revert an accidential commit
Volker Lendecke [Sun, 31 Dec 2006 10:17:40 +0000 (10:17 +0000)]
r20434: Revert an accidential commit
(This used to be commit fe122b07fa1712c15067ed385d4408206e9beef4)

16 years agor20433: Work in progress: Survive more of RAW-NOTIFY.
Volker Lendecke [Sun, 31 Dec 2006 10:16:03 +0000 (10:16 +0000)]
r20433: Work in progress: Survive more of RAW-NOTIFY.

call_nt_transact_notify_change() is now sync if there are changes around.

A notify_message does a direct reply from within the message, so
process_pending_change_notify_queue is not needed anymore for samba-generated
events. Next step is to restructure the kernel-mechanisms to generate
messages.

Volker
(This used to be commit c813f71d0036ec52c99a97e60fe33ee47d0635fa)

16 years agor20432: Apply some const
Volker Lendecke [Sun, 31 Dec 2006 10:08:52 +0000 (10:08 +0000)]
r20432: Apply some const
(This used to be commit 22163fee595251d4ea92279d88a1e8525188c620)

16 years agor20429: Restructure the libuuid API tests to handle the case where libuuid
James Peach [Sun, 31 Dec 2006 06:53:11 +0000 (06:53 +0000)]
r20429: Restructure the libuuid API tests to handle the case where libuuid
is (effectively) in libc. Convert AC_LIBTESTFUNC to use the mystically
undocumented m4_ifval, which fixes some quoting problems when
providing shell code for the if-true and if-false branches.
(This used to be commit 5e1fbcc403c471ecaaa37e8cd54b719b65dd7495)

16 years agor20428: Rename dns_open. This conflicts with the dns_open symbol in
James Peach [Sun, 31 Dec 2006 06:50:44 +0000 (06:50 +0000)]
r20428: Rename dns_open. This conflicts with the dns_open symbol in
libSystem on Mac OS X.
(This used to be commit 2117904f18869fca0d4770883cf2de5fb00c4f85)

16 years agor20427: Rename dnp_open. This conflicts with the dns_open symbol in
James Peach [Sun, 31 Dec 2006 06:45:24 +0000 (06:45 +0000)]
r20427: Rename dnp_open. This conflicts with the dns_open symbol in
libSystem on Mac OS X.
(This used to be commit 585ee7f31d2fb169e9dc37fd786faa8049be5e52)

16 years agor20424: No, we do not have to do that here :-)
Volker Lendecke [Sat, 30 Dec 2006 17:54:22 +0000 (17:54 +0000)]
r20424: No, we do not have to do that here :-)
(This used to be commit 49a463a97a4f800977ed3a657714e7f3b17bbf21)

16 years agor20412: Placeholder to remind me to write a torture test
Jeremy Allison [Sat, 30 Dec 2006 03:02:59 +0000 (03:02 +0000)]
r20412: Placeholder to remind me to write a torture test
for this error code.
Jeremy.
(This used to be commit 71b868611671a6c9275fce153794a0ccc150551f)

16 years agor20411: Fix originally from SATOH Fumiyasu (slightly
Jeremy Allison [Fri, 29 Dec 2006 20:39:53 +0000 (20:39 +0000)]
r20411: Fix originally from SATOH Fumiyasu (slightly
modified). Ensure "hide unXXX" parameters don't
hide MSDFS links. Bug #3319.
Jeremy.
(This used to be commit e5466fffc286a99fafe0fcfbf70e903e33baa7f9)

16 years agor20403: Cleaning out my Samba 3.0 tree:
Andrew Bartlett [Fri, 29 Dec 2006 09:18:06 +0000 (09:18 +0000)]
r20403: Cleaning out my Samba 3.0 tree:

As discussed with jerry at the CIFS conf: overriding the
administrator's wishes from the krb5.conf has only every given me
segfaults.  We suggest leaving this up to the defaults from the
libraries anyway.

Andrew Bartlett
(This used to be commit 0b72c04906b1c25e80b217a8f34fd3a8e756b9ca)

16 years agor20402: Fix spelling: samba bug #4292 debian #402392
Andrew Bartlett [Fri, 29 Dec 2006 08:25:51 +0000 (08:25 +0000)]
r20402: Fix spelling: samba bug #4292 debian #402392
(This used to be commit e43aa4e03d8d2d3ffa3a0383b0b0835dd1a51cda)