Age | Commit message (Collapse) | Author | Files | Lines |
|
Jeremy.
(This used to be commit cab76c3c33883aad444eefb6562ab1b27d9ca88a)
|
|
Jeremy.
(This used to be commit f22822790cdbbe7d5a237421c1eda73a504e488d)
|
|
Jeremy.
(This used to be commit d202aae3c821f3d78ff063d867bac1f84dca3548)
|
|
up a *lot*.
Jeremy.
(This used to be commit 762fff4ddb505b90ada1ea54348dba1a8b9af631)
|
|
to be set in local.h. Change from the default (131) to
another prime (1049). Should this be an smb.conf tunable parameter
based on the number of open file descriptors available ?
If so what scaling factor ? More tests to follow.
Jeremy.
(This used to be commit 6a902ec49ffea5d0ca0308d5ff51584cece41043)
|
|
any potential lib/smbldap.c calls.
Jeremy.
(This used to be commit 915cfb48f08b3748e22e68ed028eaca6d558cbad)
|
|
function. Oops.
Jeremy.
(This used to be commit 7edb26e7657fc01710abe563b941779749409ef2)
|
|
only tell at parse time from the wire if an incoming name
has wildcards or not. If it's a mangled name and we demangle
the demangled name may contain wildcard characters. Ensure
these are ignored.
Jeremy.
(This used to be commit 4cd8e2a96b98ff711905e8c6f416b22440c16062)
|
|
(This used to be commit 7fc05b79643c93eaf0ef028a7337889ed21c52ba)
|
|
Move form stable to stable distribution names based hives.
(This used to be commit bb13b3482047b6ab6d84ba9e2839cf8a0fac71aa)
|
|
trans2_mkdir/trans2_open/trans2_setfilepathingo.
Jeremy.
(This used to be commit 71c037dfbb0b51e750f2e14533b03d9932778cb0)
|
|
XATTR calls on *BSD systems (bug #3218).
Jeremy.
(This used to be commit 3d8faf42e854a720aca5c2e0a4682c85a3dfd365)
|
|
Volker
(This used to be commit 440e7b3342e6b7b12208b789853962de72a9cac2)
|
|
Jeremy.
(This used to be commit 7fb05872612c9e1816ac24d25a020073e3b41950)
|
|
(This used to be commit eee397ea15d0804d541be9707158a5240996aeae)
|
|
inside a
message handler, the list of messages from retrieve_all_messages is not
properly freed. Not important, just confusing :-)
Volker
(This used to be commit d20388750dcfe7e0680246f7e3e6beb3a6d51a4a)
|
|
the mangle cache is no good (3 letter extension could be wrong
case - so don't demangle in this case - leave as mangled and
allow the mangling of the directory entry read (which is done
case insensitively) to match instead. This will lead to more
false positive matches but we fail completely without it.
Jeremy.
(This used to be commit 238b35d2e6e21d0e07d500d446f08ec128ea7720)
|
|
a directory when you've got permissions. Need to write
a smbtorture test for this.
Jeremy.
(This used to be commit e959a5be393eb59b8987eb6967a2ee5d11978f41)
|
|
can treat them similarly to file opens (delete on
close, share mode violations etc.). This fixes bug
#3216 I will up the default hash size on the locking
db in a later commit as this means more entries.
Jeremy.
(This used to be commit 1134abbbb3fd8e8b88e1a5817aae106476a4c126)
|
|
(this is the way it's been done in other functions). Instead
of moving this into the IDL, I think the best solution would
be to write a wrapper function around any call that needs
this (this is what we already do for many of the calls).
Jeremy.
(This used to be commit aeca4efa11728be53b81967bb5442b5b09d1a975)
|
|
Andrew Bartlett is right - making lsa code do it the
netlogon way, not vica-versa.
Jeremy.
(This used to be commit f313757e36215cb3dd956e4a73de6d30258a6974)
|
|
(This used to be commit f5f40633bc3f641a0fef4934375d0d829899b0d7)
|
|
lsa_openpolicy and fall back appropriately. In particular an ntlmssp bind
failure can not be detected before the first real rpc request, at least
according to abartlet :-)
Works for me against w2k3, w2k and nt4. Sooner or later I should test against
samba4 ... :-)
Volker
(This used to be commit 48a9e35208ae7b6271508085f59833e5def640e8)
|
|
(This used to be commit 37267d5ab018bb6df9e297ea68e57deb9a908f28)
|
|
(This used to be commit 9741818d2c54240ef1f38762396828adceb92b2a)
|
|
here. ;-)
We can only tell if the bind succeeded on the first real RPC call. So we have
to decide according to success of samrconnect whether we have to fall
back. Similarly for lsaopenpolicy.
Volker
(This used to be commit 0603e1c8456ee87b87b051e0303a35fdbfbcf7ca)
|
|
Volker
(This used to be commit 770ad2a8a72ae7bfcdc1b86b72142e11f662d975)
|
|
functions
in cli_netlogon look similarly suspicious.
Volker
(This used to be commit 8d7713431efd80bd358daffcbbc4d715611b8b4b)
|
|
Volker
(This used to be commit 6948f748f689708c396e52097553ff222b1af744)
|
|
(This used to be commit c495059de1675676fe4d9a87ce516a54f16e9c66)
|
|
(This used to be commit 88a33c4cf87ada17637579d9261471c219e88de0)
|
|
name stored in the array was normalized. This was causing
records to not be deleted on a reload. As a result,
I was getting the wrong path for various services.
Seems to be ok after this change.
Also converted canonicalize_servicename() to just
use strupper_m() rather than doing the conversion itself.
Jeremy, i think this should be ok but please check.
also cleaned up some things in the hash service code
and added debug messages for sanity purposes.
(This used to be commit e0bf0581f0aaf1505f653f2101eed61352d03da8)
|
|
Don't count open pipes in the num_files_open on a connection.
conn_idle_all() handles this by looking for open rpc handles
If there are no open handles, we can close the IPC$ share.
(This used to be commit 747fba4dbf06c42495c430cd78c1cded3445f821)
|
|
(This used to be commit f4c310d55624ab726e3cdc49dcc69f9162c797aa)
|
|
Jeremy.
(This used to be commit f68ff32630ee3b06b69bac59674ecc1496880a47)
|
|
the request to winbindd (prevents the WB_RECURSE flags from accidentially getting set
(This used to be commit 8c63d6d8a7f50d9a101117338242a9c8b243b43f)
|
|
with Sun compiler)
(This used to be commit dd28582efbacd02c4134298be000cd2338c822ad)
|
|
MB service names may contain embedded ' ' characters.
Jeremy.
(This used to be commit 83d0cda858de5f40ab652e1f438808a3bfac0f81)
|
|
The problem
was a O(n^2) loop: Whenever a service definition was found, we linearly
searched the already loaded share definitions, the patch adds an internal tdb
for this. For a smb.conf with 2000 shares this speeds up loading by about a
factor of 50.
Might be a fix for bug #1117.
Thanks to Michael Adam <ma@sernet.de>,
Volker
(This used to be commit d07343e0c4022d753f381d368fc0f03972a070f3)
|
|
can't assume long long is always there). Removed unused
var in new a/c rename code.
long long still used in eventlog code but Jerry has promised
to fix that.
Jeremy.
(This used to be commit f46d8470652b8bc5c4b8cac8e96973c6165ab19a)
|
|
(This used to be commit 10fb32ec52b32b72a46a783b73c6dd1f24625d9b)
|
|
(This used to be commit 1ce6d12898c6f24c83e54561862735586b5a41b4)
|
|
This avoids that each time a full-group-dump is requested from ADS; the
bitwise match allows to only query those groups we are interested in.
The ADS LDAP server changed to RFC compliant behaviour when decoding the ldap
filter with extensible match in the latest SPs (fixes). From the patch:
/* Workaround ADS LDAP bug present in MS W2K3 SP0 and W2K SP4 w/o
* rollup-fixes:
*
* According to Section 5.1(4) of RFC 2251 if a value of a type is it's
* default value, it MUST be absent. In case of extensible matching the
* "dnattr" boolean defaults to FALSE and so it must be only be present
* when set to TRUE.
*
* When it is set to FALSE and the OpenLDAP lib (correctly) encodes a
* filter using bitwise matching rule then a buggy AD fails to decode
* the extensible match. As a workaround set it to TRUE and thereby add
* the dnAttributes "dn" field to cope with those older AD versions.
* It should not harm and won't put any additional load on the AD since
* none of the dn components have a bitmask-attribute.
*
* Thanks to Ralf Haferkamp for input and testing */
Guenther
(This used to be commit db38ed6be607d08515920d46fb8a12f8cb4ddd6e)
|
|
spoolss backchannel connection by rewriting
spoolss_connect_to_client(). Ensure that we
save the cli_state* in the rpc_pipe_client struct.
* fix typo in debug message in cli_start_connection"
(This used to be commit 18400f96628ffdd332c2fb2aa52b5e9aee5cb3ce)
|
|
We should only check the S_IWGRP permissions if we haven't already
seen an owning group SMB_ACL_GROUP_OBJ ace entry. If there is an
SMB_ACL_GROUP_OBJ ace entry then the group bits in st_gid are
the same as the SMB_ACL_MASK bits, not the SMB_ACL_GROUP_OBJ
bits. Thanks to Marc Cousin <mcousin@sigma.fr> for pointing
this out.
Jeremy.
(This used to be commit 7e1318e09bd4b155707020142b08776a546a646e)
|
|
tdb as well to make naming consistent.
(This used to be commit ee91eb9a39cc5e3edd9e97eb040e7557930e4e62)
|
|
(This used to be commit f6f78877b485be5efd5cf1f3147b2e9fee647e52)
|
|
Jeremy.
(This used to be commit 797b9f47e98bed500dc3dd6ec8de51a0ec3e2bd7)
|
|
Jeremy.
(This used to be commit af8545806770a7530eecc184bdd230ca14999884)
|
|
(This used to be commit cda5a81bbe52308a81a79eb0354aea63027a9701)
|