Age | Commit message (Collapse) | Author | Files | Lines |
|
decrement a
tdb entry is not the most reliable way to count children correctly.
This increments the number of children after a fork and decrements it upon
SIGCLD. I'm keeping a list of children just for consistency checks, so that we
at least get a debug level 0 message if something goes wrong.
Volker
(This used to be commit eb45de167d24d07a218307ec5a48c0029ec097c6)
|
|
(This used to be commit 2a66abca02b5e95b66ab336f0d0e3977676d4540)
|
|
Thanks to Michael Adam <ma@sernet.de>.
Volker
(This used to be commit c4e10afadb39ff562287ab2294df0a1f83b28908)
|
|
Volker
(This used to be commit ea83001d3ed0b5da67cf367c17fdef662bc01681)
|
|
(This used to be commit 4199b5d2262e1e154f75f609fef20ed8e8c21cf2)
|
|
(This used to be commit 761cbd52f0cff6b864c506ec03c94039b6101ef9)
|
|
(This used to be commit 4a7b06860cd2907eb0e0deb466a613529121b8b7)
|
|
NO_LOGON_SERVERS if no domain controller was found.
Thanks to Michael Adam <ma@sernet.de>.
Volker
(This used to be commit d44599de3a61707a32851f37ddfb2425949622f8)
|
|
pointing them
out.
Volker
(This used to be commit 6bf5e7080a51c416d1d1466b1ca84c8f23a6bf2c)
|
|
bytes returned" is less than the amount we want
to send, return what we can and set STATUS_BUFFER_OVERFLOW
(doserror ERRDOS,ERRbufferoverflow). Required by
OS/2 to handle EA's that are too large. It's hard
to test this in Samba4 smbtorture as the max data
bytes returned is hard coded at 0xffff (as it is
in the Samba3 client libraries also). I used a
custom version of Samba4 smbtorture to test this
out. Might add a "max data bytes" param to make
this testable in the build farm. Confirmed by
"Guenter Kukkukk (sambaos2)" <sambaos2@kukkukk.com>
and Andreas Taegener <atsamba11@eideltown.de>
that this fixes the issue.
Jeremy.
(This used to be commit ff2f1202b76991a404dae8df17c36f8135c8dc51)
|
|
inspired
by Christian M Ambach <CAMBACH1@de.ibm.com>.
Volker
(This used to be commit cf7c83d462dc766fa6f48728d0a4e8d534cc2bd4)
|
|
(This used to be commit 0f483cf66c203d8590998b83cbeeb236ba06ab63)
|
|
(This used to be commit 4fc773080a43cc73906c99a38406706b23e84c3f)
|
|
(This used to be commit 47a462359562eea5d99e1c3965569615c3451397)
|
|
entries to the group mapping db. Ensure this can't happen.
Jeremy.
(This used to be commit 2ba0d93d53868c8b28dccf91dfa26e86817da511)
|
|
Andrew Bartlett
(This used to be commit 199a33ac80977782869b24ce86dcd51cb16d3851)
|
|
Volker
(This used to be commit c0ff2afe0683095401fa7b7654aa3b2fe950f7b3)
|
|
afraid it's
more than 1000 lines of patch, but doing it in smaller pieces is hardly
possible.
Anybody interested please look over this. The patch is not really interesting,
just look at the new groupdb/mapping.c file.
Jerry, one entry for the 3.0.24 release notes: smbd will refuse to start if we
have overlapping mappings in group_mapping.tdb. With the old db a unix gid can
be mapped to two different SIDs. This will be refused with the new code.
Volker
(This used to be commit f0f0e893ca41d35b58b35929de78dcb911b3c7dc)
|
|
(This used to be commit c7d115a7d08ecebe2ba70b3f0efae39a1fd8e42a)
|
|
independently: Change
internal mapping.c functions to return NTSTATUS instead of BOOL.
Volker
(This used to be commit 4ebfc30a28a6f48613098176c5acdfdafbd2941a)
|
|
seemed a
bit pointless to me.
Volker
(This used to be commit 244b25ae49d3c635fc54498dbee29f5b649ea1fa)
|
|
for storing offline hashes.
Jeremy.
(This used to be commit c8e6f7e41c9db436b34dd127d77940d7b43bf13b)
|
|
Remove some unused code: pdb_find_alias is not used anymore, and nobody I
think has ever used the pdb_nop operations for group mapping. smbpasswd and
tdb use the default ones and ldap has its own.
Make the functions pdb_getgr* return NTSTATUS instead of BOOL. Nobody right
now really makes use of it, but it feels wrong to throw away information so
early.
Volker
(This used to be commit f9856f6490fe44fdba97ea86062237d8c74d4bdc)
|
|
error conditions
(This used to be commit 954593bd41ff2475df5d37eae18be08ffa3002eb)
|
|
Found by Whitfield school.
Jeremy.
(This used to be commit f8584a475853bd8937fb0cf1b304c98f96fbd872)
|
|
On Linux,
F_RDLCK is defined to 0, for example NetBSD has it at 1.
Still does not work fully though. Still investigating.
This might also be interesting to Samba4.
Volker
(This used to be commit a1c3774e01710ae0edc89e05f7781d2928ea9319)
|
|
This patch add some missing async functions to
solve UID/GID -> SID requests not just out of the cache,
but down the remote idmap if necessary.
This patch solves the problem of servers not showing users/groups names
for allocated UID/GIDs when joined to a group of servers that share a
prepopulated idmap backend.
Also correctly resolve UID/GIDs to SIDs when looking ACLs from the
windows security tab on teh same situation.
Simo.
(This used to be commit b8578bfab6a04fcd65a2e65f507067459e326077)
|
|
Volker
(This used to be commit 68db058fdf508d5b4d38731ece21f5d92feca00c)
|
|
Guenther
(This used to be commit 8c1198c1592e7c07904b448ed7a54b9b23c941df)
|
|
* Remove "unknown" from dfs_Enum (samba4 dfs IDL updates to follow).
* When encountering an unsupported infolevel the rpc server must reply
with a dfs_info_0 structure and WERR_OK (observed from w2k3 when talking
to nt4).
Guenther
(This used to be commit f9bef1f08f7d2a4c95c28329ac73e8646f033998)
|
|
(This used to be commit e4b8c79a9d6f7323953121887af4f482d04a9228)
|
|
argument.
Volker
(This used to be commit 873a5a1211d185fd50e7167d88cbc869f70dfd3f)
|
|
and 305.
Volker
(This used to be commit 4f6605a4880f54f2c7d1f3c7554408d893bc623c)
|
|
(This used to be commit d44a3228f08b8855e8f3a5a045b4366af24b82f8)
|
|
system provides rpms
(This used to be commit cad3d27e05a8c6e325795ce145b9f2840911f4bb)
|
|
Jeremy.
(This used to be commit 06aea05c52ee770a2dd6465e9e2fcd0ccd8c811d)
|
|
NTcancel doesn't send a reply, so in this case the signing
sequence number is only incremented by 1, not 2.
Jeremy.
(This used to be commit 85841a01987e653a085af00c7c437145686a332b)
|
|
keys,
this can trivially be added later.
Volker
(This used to be commit 6915adb9780052952e4a1d9e1c3e6cac06f48463)
|
|
(This used to be commit c065341d3ffc9125514f563c63d416cf7c40375f)
|
|
Jeremy.
(This used to be commit b5f0b1b6447ac3c77558b32d97ce96d357ce15c0)
|
|
lookup_name_smbconf, otherwise
force user = domain+administrator
can not work. Also attempt to fix the 'valid users = domain+group' bug at the
same time.
Volker
(This used to be commit 255475901c13fde29b1b476560d969cc99712767)
|
|
With lp_workgroup we end up with remote names again...
Volker
(This used to be commit 250b9f353118bee4c080655f57d09011679deaf7)
|
|
(This used to be commit 63325b36872c92d9f9fe04a185d7bd3ac525d84c)
|
|
up names from smb.conf. If the name is unqualified it
causes the lookup to be done in WORKGROUP\name, then
"Unix [users|groups]"\name rather than searching the
domain. Should fix the problems with "force user"
selecting a domain user by preference.
Jeremy.
(This used to be commit 1e1fcb5eb2ac4bd360461b29f85c07dbf460025d)
|
|
(This used to be commit 92ccdec33f8afb01335f9b775b5af11296ba2aa2)
|
|
(This used to be commit d12b08fc619f7b566ef5c4cc7294174e887014fe)
|
|
For guest connection they may well be zero.
This should fix up the buildfarm (fingers
crossed).
Jeremy.
(This used to be commit 16ebccbc5889c3b4c1a20bf3453bd523ddf6f5b0)
|
|
Let's look at the build farm now... :-).
Jeremy.
(This used to be commit 6d822b85676f033a1a2e422e2d5ac92aaf566aef)
|
|
netlogon code uses pdb_get_group_sid() which could
return a S-1-1-22 unix sid. Who knew.... :-(.
I'm going to test Volker's fix instead. Once
3.0.23b is out we *have* to rip out the pdb_set_group_sid()
code....
Jeremy.
(This used to be commit 65003e1b251b4762cef2b3cdcc895269f9319eb8)
|
|
please come in and fix it in a less ugly way once
you have some time. Thanks,
Jeremy.
(This used to be commit 79b1e668e2ce263c84ff8fafaafb3e57b06717ab)
|