| Commit message (Collapse) | Author | Age | Files | Lines |
... | |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
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
|
| |
| |
| |
| |
| |
| |
| |
| | |
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 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
|
| |
| |
| |
| |
| |
| |
| |
| | |
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"
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
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.
|
| |
| |
| |
| | |
tdb as well to make naming consistent.
|
| | |
|
| |
| |
| |
| | |
Jeremy.
|
| |
| |
| |
| | |
Jeremy.
|
| | |
|
| |
| |
| |
| |
| |
| |
| | |
taking 1/5th
the time it used to. Replace strcasecmp with invididual char checks for
"S-" sid prefix.
|
| |
| |
| |
| | |
the need for allocating memory to duplicate the string.
|
| |
| |
| |
| | |
value name
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
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.
|
| |
| |
| |
| | |
Guenther
|
| |
| |
| |
| |
| |
| |
| |
| | |
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.
|
| |
| |
| |
| | |
Guenther
|
| | |
|
| | |
|
| | |
|
| |
| |
| |
| | |
build the library at all. Still needs some more cleanup but this works for now
|
| | |
|
| |
| |
| |
| | |
modulebranches/SAMBA_3_0_RELEASE/source/configure.in
|
| |
| |
| |
| | |
Jeremy.
|
| |
| |
| |
| | |
Jeremy.
|
| |
| |
| |
| | |
Jeremy.
|
| |
| |
| |
| | |
docs with SWAT
|
| |
| |
| |
| | |
got broken
|
| |
| |
| |
| |
| | |
x86_64 box.
Jeremy.
|
| | |
|
| |
| |
| |
| | |
Allocate memory in convert_printer_info() if necessary
|
| | |
|
| | |
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
rewrite. His comments:
I've gotten the libmsrpc code to work with TRUNK.
I've put the patch at:
www.uoguelph.ca/~cnicholl/libmsrpc_trunk_v1.patch.gz
It is from revision 11093.
I also fixed a minor bug in the svcctl code, the timeout
parameter for all the control functions was working
in milliseconds instead of seconds.
Also fixed bug in Makefile when building libmsrpc.a
|
| |
| |
| |
| |
| |
| | |
source keys
* my patches to get registry utility functions linking
with eventlogadm tool
|
| |
| |
| |
| |
| |
| | |
initial NTLMSSP negotiate blob of only 16 bytes - no strings
added ! (So don't try parsing them).
Jeremy.
|
| |
| |
| |
| |
| |
| | |
NTLMSSP client and domain strings as Unicode, even when setting
flags as OEM. Cope with this.
Jeremy.
|
| |
| |
| |
| | |
REG_MULTI_SZ
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| |
| |
| |
| | |
_srv_net_name_validate()
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
added new parameter : map readonly = [yes|no|permissions]
If yes: map inverse of user "w" bit to mean readonly.
If no: never set DOS readonly bit.
If permissions: check file permissions for user and set readonly
bit if the current user cannot write.
If store dos attributes is set to yes then this parameter
is ignored.
Jeremy.
|
| |
| |
| |
| |
| |
| | |
higher.
Guenther
|
| |
| |
| |
| | |
Guenther
|
| |
| |
| |
| |
| | |
set keylen to zero if no spnego.
Jeremy.
|