IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an
email to Administrator. User accounts are meant only to access repo
and report issues and/or generate pull requests.
This is a purpose-specific Git hosting for
BaseALT
projects. Thank you for your understanding!
Только зарегистрированные пользователи имеют доступ к сервису!
Для получения аккаунта, обратитесь к администратору.
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)
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)
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)
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)
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 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)
the time it used to. Replace strcasecmp with invididual char checks for
"S-" sid prefix.
(This used to be commit de3d0094b78cb20da7ed958e8d3a428583694309)
This allows us to install for example smbsh.1 only if SMBWRAPPER is set.
Removed also one rm call as we copy and do not append to the same file
in the next step. There is no file permission risk as we chmod 0644 in
any case later.
Replaced one basename call by shell substitution.
(This used to be commit 3944dfbff4f7f951d35e7893f7ab56ed2e9d76b0)
This does 2 things.
1). Makes dfree command a per-share parameter (it should be anyway IMHO).
2). Adds a "dfree cache time" parameter in seconds that specifies how long a
dfree command output should be cached for. Default is zero (no caching).
Jeremy.
(This used to be commit 49ef8b88a3e12883148eb28d8e86fb07dbc3d12d)
