Age | Commit message (Collapse) | Author | Files | Lines |
|
moment. To use, use something like:
./bin/ndrdump -l bin/smbd winreg winreg_EnumValue in <filename>
or to see what functions are available:
./bin/ndrdump -l bin/smbd winreg
(This used to be commit 0db258c6004922ce444b4a3ecdf669f7e4600ef0)
|
|
(This used to be commit 4d5654a8ab491364be5fd83e9894e9a46401f0f4)
|
|
- add minsize parameter. Bug #4409.
Jeremy.
(This used to be commit b9408304db9a64d9b8ad56f53532825a02fdb150)
|
|
Jeremy.
(This used to be commit 98f4b64574ef205ec87401b4bf5eed89f2933fa1)
|
|
Add proper debug to all possible setfilepathinfo
functions.
Jeremy.
(This used to be commit 3c47a5ef258d536504759a02f6d84c0ab0af7224)
|
|
We're not yet deleting open files on unlink. Investigating...
Jeremy.
(This used to be commit 334b34f131578c2a889caa90aa2425f41883cafd)
|
|
far, it
needs testing with other clients as well. I'm afraid I'm visiting a conference
tomorrow and saturday, so I'd be happy to get support in this.
Thanks,
Volker
(This used to be commit 2186e276a0f15457ee6b29ecf2d109d812628ff9)
|
|
Jeremy.
(This used to be commit 9858e5b72526360fc415b848a84042e09d9b2453)
|
|
Jeremy.
(This used to be commit 6a0f6fde0a19bfb4af4c7fa6f29d7015e884d86e)
|
|
Jeremy.
(This used to be commit 6457d66b9a04c421fc43e131c825c7555c16a1ea)
|
|
between unlink/rmdir calls.
Jeremy.
(This used to be commit f0c8488d382ada32fabe79399f64ba1c6486d009)
|
|
0x8000000000000000LL is "infinity" to NT and should
not be converted numerically to time_t.
(This used to be commit f3a8048a628753990f9c5401b2bb50c19d4f66e3)
|
|
to get the
Krb5 config stuff to work in the server affinity settings.
(This used to be commit 518052be38385ad089c0cb092d07ccd210a27ef3)
|
|
when changing how memory is allocated.
(This used to be commit 78bf4042dd22bf063846c58729d5b64be3fce8a8)
|
|
ads_cached_connection() does not call get_dc_name()
before ads_connect() and therefore does not setup
the environment to look at krb5.conf.DOMAIN file
before sending the TGT request. The failure I'm seeing
occurs ni a multi-DC domain where we get back preuath
failed after we just joined the domain.
(This used to be commit 256f36dce3e3a39798b2ad38fa3123669d670597)
|
|
(This used to be commit 82dc19f844af65a8815c629e4ec1f354d208a53f)
|
|
SATOH Fumiyasu <fumiya@samba.gr.jp>
(This used to be commit d68b2910c8ba97a42b8bccc0af1341fc301a76d0)
|
|
(This used to be commit 0de74724289f2b78719f6675664d7376446650d0)
|
|
(This used to be commit 05886edb3559355e8cd3e3eb8999f24b64ddb3eb)
|
|
so they can honor the offline logon state.
(This used to be commit 15b13dfe81e861b94077c94b80117a85a5ffb999)
|
|
is took late
(This used to be commit 5575845952171aaeae81cf65fe32be33cc1b45ba)
|
|
on x86_64 Linux boxes. Since it is not needed, just use malloc()
on Linux.
(This used to be commit 3644bd999621e04b3fae262f172e93ea8fdcd47e)
|
|
by the nss_info backend
(This used to be commit a9028612a3f614579b28f9560cc67aef90b31cf8)
|
|
LAM module does to work around a system that does not support
>8 character usernames. Without the change, pam_winbind tries
to authenticate _#uid in the domain.
(This used to be commit 7f0ba72e05acbd958fbf768a04d16c29189dc8f7)
|
|
su - DOM\user was unable to set the process crendentials
without listing the "id" and other attributes in the attrlist[].
More fixes to come, but I didn't want this to get lost.
(This used to be commit 4c53d300fa3516a4c5113bc94dfd07413c46b038)
|
|
ends up commenting out the remainder of the line and we have missing libraries in the link
(This used to be commit c4621de39bb9ad8d366d776b27df45dc07f782ba)
|
|
Patch from Zack Kirsch <zack.kirsch@isilon.com>.
Jeremy.
(This used to be commit df07a662e32367a52c1e8473475423db2ff5bc51)
|
|
Coverity finds them :-)
Jeremy.
(This used to be commit cbe725f1b09f3d0edbdf823e0862edf21e16d336)
|
|
(This used to be commit 51d296f25152ce9d719cec777bb306ca246fc3be)
|
|
Fix escaping of DN components and filters around the code
Add some notes to commandline help messages about how to pass DNs
revert jra's "concistency" commit to nsswitch/winbindd_ads.c, as it was
incorrect.
The 2 functions use DNs in different ways.
- lookup_usergroups_member() uses the DN in a search filter,
and must use the filter escaping function to escape it
Escaping filters that include escaped DNs ("\," becomes "\5c,") is the
correct way to do it (tested against W2k3).
- lookup_usergroups_memberof() instead uses the DN ultimately as a base dn.
Both functions do NOT need any DN escaping function as DNs can't be reliably
escaped when in a string form, intead each single RDN value must be escaped
separately.
DNs coming from other ldap calls (like ads_get_dn()), do not need escaping as
they come already escaped on the wire and passed as is by the ldap libraries
DN filtering has been tested.
For example now it is possible to do something like:
'net ads add user joe#5' as now the '#' character is correctly escaped when
building the DN, previously such a call failed with Invalid DN Syntax.
Simo.
(This used to be commit 5b4838f62ab1a92bfe02626ef40d7f94c2598322)
|
|
Jeremy.
(This used to be commit 5ed61d5af6fe56e22135406256f5d1f7ccd6a376)
|
|
Jeremy.
(This used to be commit 4a04555e23b5fa53fbeb5b65a7c83cff1b0f9640)
|
|
allowed a CIFS client bug to remain unnoticed :-(.
I suck.
Jeremy.
(This used to be commit 29761173ee26b4713c9a12166a935c066fc3321b)
|
|
(This used to be commit 5ef0286b56b368abd4da2cbe3d826a3438f3acc3)
|
|
removed).
Jeremy.
(This used to be commit 645b0438dde0dad26e950b3184cc412d3d87560a)
|
|
to allow client to fragment large SPNEGO blobs (large krb5
tickets). Tested against W2K3R2. Should fix bug #4400.
Jeremy.
(This used to be commit b81c5c6adce51cec06df0e993534064b20666a8e)
|
|
where return value was incorrectly initialized.
Jeremy.
(This used to be commit 8d45f1f3b524031a34cfba21b677be8a09fc192c)
|
|
broken :-). This will do until Simo fixes the escape
calls properly.
Jeremy.
(This used to be commit b7d91ec1b20f8d58903a3283f7789a30041461be)
|
|
(This used to be commit 9a9b9421673ed1c455658d8ae79d7a1522a1baa7)
|
|
builtin
domain. Without this patch we leaked a DISPINFO for the (NULL) domain per
samr_connect*() call.
Volker
(This used to be commit 4423880ff47a94074c625a4f4f81c3b516faa644)
|
|
(This used to be commit 952f648d8132a0652bb03b9e7671239e57614ee9)
|
|
directly after another.
Guenther
(This used to be commit 76ba11d7770bac7c6db2eb1640139bbe270d82c3)
|
|
Guenther
(This used to be commit 28ce79629bc36929f508c1ccb1d27d48e8898045)
|
|
Guenther
(This used to be commit 7b18a4730d61c04867fc11df8980943d422589d8)
|
|
Guenther
(This used to be commit 8ff0903a17cfd8c09b73ef637484a72719e82071)
|
|
Guenther
(This used to be commit 020601ea0abeb15f2aef9da354fcf6d7d5459710)
|
|
proto should be required before creating any binary from now on.
Remove proto_exists from the all, pam_smbpass, and pam_bindind rule.
(This used to be commit 95d22979743c94565d9d0bbb64eb1e9adeba10d3)
|
|
(This used to be commit f63189907efe857ef51ff91470ddb8d21b9a41fa)
|
|
comment :-)
(This used to be commit fad2ee8aa3e99c31a0632a80b4a64dedb6e01495)
|
|
them. It just does not make sense to do a querydispinfo on an alias handle...
This fixes a memleak: Every samr_connect*() call leaked a DISP_INFO for the
(NULL) sid.
More cleanup pending: Essentially, we only need the DISP_INFO cache for the
get_global_sam_sid() domain. BUILTIN is fixed and small enough, and there are
no other domains around where enumerations could happen.
This also removes the explicit builtin_domain flags. I don't think this is
worth it. If this makes a significant difference, then we have a *VERY* tuned
RPC layer...
Jeremy, please check this. If it's ok, we might want to merge it across.
Volker
(This used to be commit 0aceda68a825788895759e79de55b080ad3f971d)
|