summaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2007-10-10r11395: Update the Debian packaging.Simo Sorce178-26/+10794
Move form stable to stable distribution names based hives. (This used to be commit bb13b3482047b6ab6d84ba9e2839cf8a0fac71aa)
2007-10-10r11389: Attempt to fix bug #3212 - ignore bogus OS/2 EA set values onJeremy Allison1-4/+25
trans2_mkdir/trans2_open/trans2_setfilepathingo. Jeremy. (This used to be commit 71c037dfbb0b51e750f2e14533b03d9932778cb0)
2007-10-10r11383: Patch from Alex Masterov <alex@infobit.ru> to fixJeremy Allison1-3/+83
XATTR calls on *BSD systems (bug #3218). Jeremy. (This used to be commit 3d8faf42e854a720aca5c2e0a4682c85a3dfd365)
2007-10-10r11381: Correctly connect to 445 and 139 after a successful getdcname.Volker Lendecke1-3/+10
Volker (This used to be commit 440e7b3342e6b7b12208b789853962de72a9cac2)
2007-10-10r11379: Remove external dependencies from sharemodes library.Jeremy Allison1-4/+20
Jeremy. (This used to be commit 7fb05872612c9e1816ac24d25a020073e3b41950)
2007-10-10r11375: Update to the latest config.guess and config.sub files.Paul Green2-328/+364
(This used to be commit eee397ea15d0804d541be9707158a5240996aeae)
2007-10-10r11368: Remove a memleak that just cost me half an hour: If we terminate ↵Volker Lendecke1-1/+1
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)
2007-10-10r11346: Fix for bug found by Dina Fine. If in case sensitive mode thenJeremy Allison1-1/+10
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)
2007-10-10r11344: I don't think share mode conflicts occur on deletingJeremy Allison2-20/+10
a directory when you've got permissions. Need to write a smbtorture test for this. Jeremy. (This used to be commit e959a5be393eb59b8987eb6967a2ee5d11978f41)
2007-10-10r11341: Put directory opens into the share mode db so weJeremy Allison3-8/+70
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)
2007-10-10r11338: Move knowledge of \\ needed into rpc_client/cli_netlogonJeremy Allison2-8/+4
(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)
2007-10-10r11336: Start to get my control back :-). Volker, I thinkJeremy Allison2-22/+62
Andrew Bartlett is right - making lsa code do it the netlogon way, not vica-versa. Jeremy. (This used to be commit f313757e36215cb3dd956e4a73de6d30258a6974)
2007-10-10r11332: eventlog API uses NTSTATUS, not WERROR for return codesGerald Carter3-46/+45
(This used to be commit f5f40633bc3f641a0fef4934375d0d829899b0d7)
2007-10-10r11328: Actually verify that the bind on a pipe succeeded with a samr_connect orVolker Lendecke1-167/+196
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)
2007-10-10r11327: Make user domain settable by pdbeditVolker Lendecke1-2/+9
(This used to be commit 37267d5ab018bb6df9e297ea68e57deb9a908f28)
2007-10-10r11326: Fix alignment in getdc responseVolker Lendecke1-0/+3
(This used to be commit 9741818d2c54240ef1f38762396828adceb92b2a)
2007-10-10r11324: Re-formatting before I can get a very *narrow* focus on the bugs in ↵Volker Lendecke1-59/+61
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)
2007-10-10r11323: Fix usage of rpccli_netlogon_getdcname. Add some debug messages.Volker Lendecke1-3/+18
Volker (This used to be commit 770ad2a8a72ae7bfcdc1b86b72142e11f662d975)
2007-10-10r11320: Fix error handling for rpccli_netlogon_getdcname. Jeremy, the other ↵Volker Lendecke1-2/+2
functions in cli_netlogon look similarly suspicious. Volker (This used to be commit 8d7713431efd80bd358daffcbbc4d715611b8b4b)
2007-10-10r11319: read_buf_len and write_buf_len are no longer used, remove them.Volker Lendecke2-6/+3
Volker (This used to be commit 6948f748f689708c396e52097553ff222b1af744)
2007-10-10r11301: why would you look for printf in -lnsl[_s]? Fixing configure checksGerald Carter1-2/+2
(This used to be commit c495059de1675676fe4d9a87ce516a54f16e9c66)
2007-10-10r11296: removing unused variable and ifdef'd out codeGerald Carter1-14/+0
(This used to be commit 88a33c4cf87ada17637579d9261471c219e88de0)
2007-10-10r11295: new service hashing code has assumign that the serviceGerald Carter1-12/+40
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)
2007-10-10r11292: Missed merge from Samba 2.2 many years ago....Gerald Carter1-5/+0
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)
2007-10-10r11286: Fix a potential segfaultVolker Lendecke1-7/+10
(This used to be commit f4c310d55624ab726e3cdc49dcc69f9162c797aa)
2007-10-10r11283: Move to using sival_int from sival_ptr. Part of bug #2922.Jeremy Allison1-4/+10
Jeremy. (This used to be commit f68ff32630ee3b06b69bac59674ecc1496880a47)
2007-10-10r11280: BUG 3201: make sure request structure is cleared prior to sending ↵Gerald Carter1-0/+3
the request to winbindd (prevents the WB_RECURSE flags from accidentially getting set (This used to be commit 8c63d6d8a7f50d9a101117338242a9c8b243b43f)
2007-10-10r11275: patch from Chris to remove the empty struct in libmsrpc.h (fix build ↵Gerald Carter1-4/+0
with Sun compiler) (This used to be commit dd28582efbacd02c4134298be000cd2338c822ad)
2007-10-10r11269: Ensure the new canonicalize_servicename() is mb safe.Jeremy Allison1-1/+1
MB service names may contain embedded ' ' characters. Jeremy. (This used to be commit 83d0cda858de5f40ab652e1f438808a3bfac0f81)
2007-10-10r11266: Speed up loading smb.conf for large numbers of share definitions. ↵Volker Lendecke1-26/+111
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)
2007-10-10r11256: Remove use of long long and strtoll in libsmbclient (weJeremy Allison2-32/+30
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)
2007-10-10r11253: Fix an annoying timeout when no nmbd is aroundVolker Lendecke1-8/+8
(This used to be commit 10fb32ec52b32b72a46a783b73c6dd1f24625d9b)
2007-10-10r11251: Fix a commentVolker Lendecke1-7/+5
(This used to be commit 1ce6d12898c6f24c83e54561862735586b5a41b4)
2007-10-10r11242: use LDAP bitwise machting rule when searching for groups in ADS.Günther Deschner2-20/+61
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)
2007-10-10r11240: * fix invalid read reported by valgrind in theGerald Carter2-69/+35
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)
2007-10-10r11237: Fix acl evaluation bug found by Marc Cousin <mcousin@sigma.fr>Jeremy Allison1-14/+34
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)
2007-10-10r11236: Implement user rename for smbpasswd and ldap backends. Some cleanup onJim McDonough4-4/+130
tdb as well to make naming consistent. (This used to be commit ee91eb9a39cc5e3edd9e97eb040e7557930e4e62)
2007-10-10r11235: fix segfault in addprinter due to mixing talloc() and malloc()'d memoryGerald Carter1-3/+1
(This used to be commit f6f78877b485be5efd5cf1f3147b2e9fee647e52)
2007-10-10r11233: Forgot to add the statvfs file. Oops.Jeremy Allison1-0/+65
Jeremy. (This used to be commit 797b9f47e98bed500dc3dd6ec8de51a0ec3e2bd7)
2007-10-10r11232: Added ab's POSIX statvfs vfs call. Sorry for the delay ab.Jeremy Allison11-7/+115
Jeremy. (This used to be commit af8545806770a7530eecc184bdd230ca14999884)
2007-10-10r11230: Remove the '//' i was using to test something...oopsJim McDonough1-1/+1
(This used to be commit cda5a81bbe52308a81a79eb0354aea63027a9701)
2007-10-10r11229: an even bigger speedup spotted by Volker. string_to_sid() is now ↵Jim McDonough1-2/+2
taking 1/5th the time it used to. Replace strcasecmp with invididual char checks for "S-" sid prefix. (This used to be commit de3d0094b78cb20da7ed958e8d3a428583694309)
2007-10-10r11228: Speed up string_to_sid by removing next_token calls, thus eliminatingJim McDonough1-34/+27
the need for allocating memory to duplicate the string. (This used to be commit e5cc94f13ff2dacb219c8a56fa13853d620ecda6)
2007-10-10r11227: patch from brian moran to fix typo in eventlog message file registry ↵Gerald Carter2-4/+4
value name (This used to be commit 34c3fd77b320d4fe5e0f1452aa09ea5ec2797494)
2007-10-10r11224: Add feature to get our configuration from config.log into installman.sh.Lars Müller1-3/+14
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)
2007-10-10r11213: Fix the buildGünther Deschner2-1/+1
Guenther (This used to be commit 908ac0c9eccd1ba368a6305fee9673770fc74a53)
2007-10-10r11190: Fix enhancement request #3192.Jeremy Allison4-16/+72
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)
2007-10-10r11183: add small helper function to return a PAC_LOGON_INFO.Günther Deschner2-10/+17
Guenther (This used to be commit a8d5d6b845efb62e73e281549528376f3ee74211)
2007-10-10r11170: root free pass on eventlog open access checkGerald Carter2-0/+8
(This used to be commit 4e3ff41e1ee2e3c323814fd8c6aa44ecab412257)
2007-10-10r11169: removing duplicate 'map read only' entryGerald Carter1-1/+0
(This used to be commit 0e60813ed0d5c56c44a371d84275d1944bade770)
generated by cgit (git 2.34.1) at 2024-07-18 06:37:53 +0000