Age | Commit message (Collapse) | Author | Files | Lines |
|
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)
|
|
taking 1/5th
the time it used to. Replace strcasecmp with invididual char checks for
"S-" sid prefix.
(This used to be commit de3d0094b78cb20da7ed958e8d3a428583694309)
|
|
the need for allocating memory to duplicate the string.
(This used to be commit e5cc94f13ff2dacb219c8a56fa13853d620ecda6)
|
|
value name
(This used to be commit 34c3fd77b320d4fe5e0f1452aa09ea5ec2797494)
|
|
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)
|
|
Guenther
(This used to be commit 908ac0c9eccd1ba368a6305fee9673770fc74a53)
|
|
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)
|
|
Guenther
(This used to be commit a8d5d6b845efb62e73e281549528376f3ee74211)
|
|
(This used to be commit 4e3ff41e1ee2e3c323814fd8c6aa44ecab412257)
|
|
(This used to be commit 0e60813ed0d5c56c44a371d84275d1944bade770)
|
|
(This used to be commit 056bf816284a473b8419fccf62a54813317043b7)
|
|
build the library at all. Still needs some more cleanup but this works for now
(This used to be commit df998bfa8e00a736250eb5a7b31ed53abd6a4241)
|
|
(This used to be commit 2f94df322232ace14cddc8e24c8949a5ed1fad32)
|
|
modulebranches/SAMBA_3_0_RELEASE/source/configure.in
(This used to be commit 19e0e48ce09eebc21b800b6ecf13c6f42dfe27f3)
|
|
Jeremy.
(This used to be commit de27b0eef2eb021f28e8bf300c4dd524e30fc7ed)
|
|
Jeremy.
(This used to be commit fc9eca51e02022ccffbad2a4f2450f85e558e151)
|
|
Jeremy.
(This used to be commit c7373b39bae6dca8281d45d1ff3f2161465838df)
|
|
docs with SWAT
(This used to be commit e3c68738663701fde21baef03c36de303e7f1636)
|
|
got broken
(This used to be commit 490dbc64f7ae2006624039da6b450ba4aca56dd4)
|
|
x86_64 box.
Jeremy.
(This used to be commit d720867a788c735e56d53d63265255830ec21208)
|
|
(This used to be commit 47b626a8f72629fd1bbabf35b68e24d202df2555)
|
|
Allocate memory in convert_printer_info() if necessary
(This used to be commit 7ada5da8e94a08a9a3e488172fa04ce688882299)
|
|
(This used to be commit 6f32785bcdb99a630e7c94e3f03275c1ca324b11)
|
|
(This used to be commit d404919d926be6bc4e21d7d5aaf2dfe795ba2726)
|
|
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
(This used to be commit d3a52900ec223316779e59a13cea87ecb500bccc)
|
|
source keys
* my patches to get registry utility functions linking
with eventlogadm tool
(This used to be commit 24e7663086f5d15c7e3fd8069667169b91d1acda)
|
|
initial NTLMSSP negotiate blob of only 16 bytes - no strings
added ! (So don't try parsing them).
Jeremy.
(This used to be commit e15b758f5fa6f500214bb60599a89f3c795c9fed)
|
|
NTLMSSP client and domain strings as Unicode, even when setting
flags as OEM. Cope with this.
Jeremy.
(This used to be commit 458da8987e8f406cdfd5bd602b3c3cf315675725)
|
|
REG_MULTI_SZ
(This used to be commit db8d85aa1ec5c486f061f97627b6b18a0e17cd34)
|
|
(This used to be commit e858eed813b5a9a8d57262142c5bbde2951b5590)
|
|
(This used to be commit bfdcbb7572352b3a3b7941249438a927eb91e18d)
|
|
(This used to be commit 9a63b52efaf0b49982d56dc7c301f59bbb076a6e)
|