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.
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.
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.
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 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.
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
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
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.
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.
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.
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 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.
