Trond Myklebust [Sat, 7 Sep 2013 16:58:57 +0000 (12:58 -0400)]
NFSv4: Fix security auto-negotiation
NFSv4 security auto-negotiation has been broken since
commit
4580a92d44e2b21c2254fa5fef0f1bfb43c82318 (NFS:
Use server-recommended security flavor by default (NFSv3))
because nfs4_try_mount() will automatically select AUTH_SYS
if it sees no auth flavours.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Chuck Lever <chuck.lever@oracle.com>
Trond Myklebust [Sat, 7 Sep 2013 18:09:52 +0000 (14:09 -0400)]
NFS: Clean up nfs_parse_security_flavors()
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Sat, 7 Sep 2013 17:26:57 +0000 (13:26 -0400)]
NFS: Clean up the auth flavour array mess
What is the point of having a 'auth_flavor_len' field, if it is
always set to 1, and can't be used to determine if the user has
selected an auth flavour?
This cleanup goes back to using auth_flavor_len for its original
intended purpose, and gets rid of the ad-hoc replacements.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Andy Adamson [Fri, 6 Sep 2013 18:14:00 +0000 (14:14 -0400)]
NFSv4.1 Use MDS auth flavor for data server connection
Commit
4edaa308 "NFS: Use "krb5i" to establish NFSv4 state whenever possible"
uses the nfs_client cl_rpcclient for all state management operations, and
will use krb5i or auth_sys with no regard to the mount command authflavor
choice.
The MDS, as any NFSv4.1 mount point, uses the nfs_server rpc client for all
non-state management operations with a different nfs_server for each fsid
encountered traversing the mount point, each with a potentially different
auth flavor.
pNFS data servers are not mounted in the normal sense as there is no associated
nfs_server structure. Data servers can also export multiple fsids, each with
a potentially different auth flavor.
Data servers need to use the same authflavor as the MDS server rpc client for
non-state management operations. Populate a list of rpc clients with the MDS
server rpc client auth flavor for the DS to use.
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Fri, 6 Sep 2013 15:09:38 +0000 (11:09 -0400)]
NFS: Don't check lock owner compatability unless file is locked (part 2)
When coalescing requests into a single READ or WRITE RPC call, and there
is no file locking involved, we don't have to refuse coalescing for
requests where the lock owner information doesn't match.
Reported-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Thu, 5 Sep 2013 19:52:51 +0000 (15:52 -0400)]
NFS: Don't check lock owner compatibility in writes unless file is locked
If we're doing buffered writes, and there is no file locking involved,
then we don't have to worry about whether or not the lock owner information
is identical.
By relaxing this check, we ensure that fork()ed child processes can write
to a page without having to first sync dirty data that was written
by the parent to disk.
Reported-by: Quentin Barnes <qbarnes@gmail.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Tested-by: Quentin Barnes <qbarnes@gmail.com>
Weston Andros Adamson [Tue, 13 Aug 2013 20:37:38 +0000 (16:37 -0400)]
nfs4: Map NFS4ERR_WRONG_CRED to EPERM
Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Weston Andros Adamson [Tue, 13 Aug 2013 20:37:37 +0000 (16:37 -0400)]
nfs4.1: Add SP4_MACH_CRED write and commit support
WRITE and COMMIT can use the machine credential.
If WRITE is supported and COMMIT is not, make all (mach cred) writes FILE_SYNC4.
Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Weston Andros Adamson [Tue, 13 Aug 2013 20:37:36 +0000 (16:37 -0400)]
nfs4.1: Add SP4_MACH_CRED stateid support
TEST_STATEID and FREE_STATEID can use the machine credential.
Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Weston Andros Adamson [Tue, 13 Aug 2013 20:37:35 +0000 (16:37 -0400)]
nfs4.1: Add SP4_MACH_CRED secinfo support
SECINFO and SECINFO_NONAME can use the machine credential.
Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Weston Andros Adamson [Tue, 13 Aug 2013 20:37:34 +0000 (16:37 -0400)]
nfs4.1: Add SP4_MACH_CRED cleanup support
CLOSE and LOCKU can use the machine credential.
Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Weston Andros Adamson [Tue, 13 Aug 2013 20:37:33 +0000 (16:37 -0400)]
nfs4.1: Add state protection handler
Add nfs4_state_protect - the function responsible for switching to the machine
credential and the correct rpc client when SP4_MACH_CRED is in use.
Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Weston Andros Adamson [Tue, 13 Aug 2013 20:37:32 +0000 (16:37 -0400)]
nfs4.1: Minimal SP4_MACH_CRED implementation
This is a minimal client side implementation of SP4_MACH_CRED. It will
attempt to negotiate SP4_MACH_CRED iff the EXCHANGE_ID is using
krb5i or krb5p auth. SP4_MACH_CRED will be used if the server supports the
minimal operations:
BIND_CONN_TO_SESSION
EXCHANGE_ID
CREATE_SESSION
DESTROY_SESSION
DESTROY_CLIENTID
This patch only includes the EXCHANGE_ID negotiation code because
the client will already use the machine cred for these operations.
If the server doesn't support SP4_MACH_CRED or doesn't support the minimal
operations, the exchange id will be resent with SP4_NONE.
Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Thu, 5 Sep 2013 02:09:50 +0000 (22:09 -0400)]
SUNRPC: Replace pointer values with task->tk_pid and rpc_clnt->cl_clid
Instead of the pointer values, use the task and client identifier values
for tracing purposes.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Thu, 5 Sep 2013 01:51:44 +0000 (21:51 -0400)]
SUNRPC: Add an identifier for struct rpc_clnt
Add an identifier in order to aid debugging.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 4 Sep 2013 18:45:13 +0000 (14:45 -0400)]
SUNRPC: Ensure rpc_task->tk_pid is available for tracepoints
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 4 Sep 2013 14:08:54 +0000 (10:08 -0400)]
NFSv4: Document the recover_lost_locks kernel parameter
Rename the new 'recover_locks' kernel parameter to 'recover_lost_locks'
and change the default to 'false'. Document why in
Documentation/kernel-parameters.txt
Move the 'recover_lost_locks' kernel parameter to fs/nfs/super.c to
make it easy to backport to kernels prior to 3.6.x, which don't have
a separate NFSv4 module.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
NeilBrown [Wed, 4 Sep 2013 07:04:49 +0000 (17:04 +1000)]
NFSv4: Don't try to recover NFSv4 locks when they are lost.
When an NFSv4 client loses contact with the server it can lose any
locks that it holds.
Currently when it reconnects to the server it simply tries to reclaim
those locks. This might succeed even though some other client has
held and released a lock in the mean time. So the first client might
think the file is unchanged, but it isn't. This isn't good.
If, when recovery happens, the locks cannot be claimed because some
other client still holds the lock, then we get a message in the kernel
logs, but the client can still write. So two clients can both think
they have a lock and can both write at the same time. This is equally
not good.
There was a patch a while ago
http://comments.gmane.org/gmane.linux.nfs/41917
which tried to address some of this, but it didn't seem to go
anywhere. That patch would also send a signal to the process. That
might be useful but for now this patch just causes writes to fail.
For NFSv4 (unlike v2/v3) there is a strong link between the lock and
the write request so we can fairly easily fail any IO of the lock is
gone. While some applications might not expect this, it is still
safer than allowing the write to succeed.
Because this is a fairly big change in behaviour a module parameter,
"recover_locks", is introduced which defaults to true (the current
behaviour) but can be set to "false" to tell the client not to try to
recover things that were lost.
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 4 Sep 2013 16:16:23 +0000 (12:16 -0400)]
SUNRPC: Add tracepoints to help debug socket connection issues
Add client side debugging to help trace socket connection/disconnection
and unexpected state change issues.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Wed, 4 Sep 2013 16:26:05 +0000 (12:26 -0400)]
NFS: Fix warning introduced by NFSv4.0 transport blocking patches
When CONFIG_NFS_V4_1 is not enabled, gcc emits this warning:
linux/fs/nfs/nfs4state.c:255:12: warning:
‘nfs4_begin_drain_session’ defined but not used [-Wunused-function]
static int nfs4_begin_drain_session(struct nfs_client *clp)
^
Eventually NFSv4.0 migration recovery will invoke this function, but
that has not yet been merged. Hide nfs4_begin_drain_session()
behind CONFIG_NFS_V4_1 for now.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Wed, 4 Sep 2013 16:26:03 +0000 (12:26 -0400)]
When CONFIG_NFS_V4_1 is not enabled, "make C=2" emits this warning:
linux/fs/nfs/nfs4session.c:337:6: warning:
symbol 'nfs41_set_target_slotid' was not declared. Should it be static?
Move nfs41_set_target_slotid() and nfs41_update_target_slotid() back
behind CONFIG_NFS_V4_1, since, in the final revision of this work,
they are used only in NFSv4.1 and later.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 9 Aug 2013 16:49:56 +0000 (12:49 -0400)]
NFS: Update session draining barriers for NFSv4.0 transport blocking
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 9 Aug 2013 16:49:47 +0000 (12:49 -0400)]
NFS: Add nfs4_sequence calls for OPEN_CONFIRM
Ensure OPEN_CONFIRM is not emitted while the transport is plugged.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 9 Aug 2013 16:49:38 +0000 (12:49 -0400)]
NFS: Add nfs4_sequence calls for RELEASE_LOCKOWNER
Ensure RELEASE_LOCKOWNER is not emitted while the transport is
plugged.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 9 Aug 2013 16:49:29 +0000 (12:49 -0400)]
NFS: Enable nfs4_setup_sequence() for DELEGRETURN
When CONFIG_NFS_V4_1 is disabled, the calls to nfs4_setup_sequence()
and nfs4_sequence_done() are compiled out for the DELEGRETURN
operation. To allow NFSv4.0 transport blocking to work for
DELEGRETURN, these call sites have to be present all the time.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 9 Aug 2013 16:49:19 +0000 (12:49 -0400)]
NFS: NFSv4.0 transport blocking
Plumb in a mechanism for plugging an NFSv4.0 mount, using the
same infrastructure as NFSv4.1 sessions.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 9 Aug 2013 16:49:11 +0000 (12:49 -0400)]
NFS: Add a slot table to struct nfs_client for NFSv4.0 transport blocking
Anchor an nfs4_slot_table in the nfs_client for use with NFSv4.0
transport blocking. It is initialized only for NFSv4.0 nfs_client's.
Introduce appropriate minor version ops to handle nfs_client
initialization and shutdown requirements that differ for each minor
version.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 9 Aug 2013 16:49:02 +0000 (12:49 -0400)]
NFS: Add global helper for releasing slot table resources
The nfs4_destroy_slot_tables() function is renamed to avoid
confusion with the new helper.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 9 Aug 2013 16:48:53 +0000 (12:48 -0400)]
NFS: Add global helper to set up a stand-along nfs4_slot_table
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 9 Aug 2013 16:48:44 +0000 (12:48 -0400)]
NFS: Enable slot table helpers for NFSv4.0
I'd like to re-use NFSv4.1's slot table machinery for NFSv4.0
transport blocking. Re-organize some of nfs4session.c so the slot
table code is built even when NFS_V4_1 is disabled.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 9 Aug 2013 16:48:35 +0000 (12:48 -0400)]
NFS: Remove unused call_sync minor version op
Clean up.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 9 Aug 2013 16:48:27 +0000 (12:48 -0400)]
NFS: Add RPC callouts to start NFSv4.0 synchronous requests
Refactor nfs4_call_sync_sequence() so it is used for NFSv4.0 now.
The RPC callouts will house transport blocking logic similar to
NFSv4.1 sessions.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 9 Aug 2013 16:48:18 +0000 (12:48 -0400)]
NFS: Common versions of sequence helper functions
NFSv4.0 will have need for this functionality when I add the ability
to block NFSv4.0 traffic before migration recovery.
I'm not really clear on why nfs4_set_sequence_privileged() gets a
generic name, but nfs41_init_sequence() gets a minor
version-specific name.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 9 Aug 2013 16:48:09 +0000 (12:48 -0400)]
NFS: Clean up nfs4_setup_sequence()
Clean up: Both the NFSv4.0 and NFSv4.1 version of
nfs4_setup_sequence() are used only in fs/nfs/nfs4proc.c. No need
to keep global header declarations for either version.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 9 Aug 2013 16:48:00 +0000 (12:48 -0400)]
NFS: Rename nfs41_call_sync_data as a common data structure
Clean up: rename nfs41_call_sync_data for use as a data structure
common to all NFSv4 minor versions.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 9 Aug 2013 16:47:51 +0000 (12:47 -0400)]
NFS: When displaying session slot numbers, use "%u" consistently
Clean up, since slot and sequence numbers are all unsigned anyway.
Among other things, squelch compiler warnings:
linux/fs/nfs/nfs4proc.c: In function ‘nfs4_setup_sequence’:
linux/fs/nfs/nfs4proc.c:703:2: warning: signed and unsigned type in
conditional expression [-Wsign-compare]
and
linux/fs/nfs/nfs4session.c: In function ‘nfs4_alloc_slot’:
linux/fs/nfs/nfs4session.c:151:31: warning: signed and unsigned type in
conditional expression [-Wsign-compare]
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Fri, 30 Aug 2013 16:24:25 +0000 (12:24 -0400)]
NFS: Ensure that rmdir() waits for sillyrenames to complete
If an NFS client does
mkdir("dir");
fd = open("dir/file");
unlink("dir/file");
close(fd);
rmdir("dir");
then the asynchronous nature of the sillyrename operation means that
we can end up getting EBUSY for the rmdir() in the above test. Fix
that by ensuring that we wait for any in-progress sillyrenames
before sending the rmdir() to the server.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Weston Andros Adamson [Tue, 3 Sep 2013 19:18:49 +0000 (15:18 -0400)]
NFSv4: use the mach cred for SECINFO w/ integrity
Commit
5ec16a8500d339b0e7a0cc76b785d18daad354d4 introduced a regression
that causes SECINFO to fail without actualy sending an RPC if:
1) the nfs_client's rpc_client was using KRB5i/p (now tried by default)
2) the current user doesn't have valid kerberos credentials
This situation is quite common - as of now a sec=sys mount would use
krb5i for the nfs_client's rpc_client and a user would hardly be faulted
for not having run kinit.
The solution is to use the machine cred when trying to use an integrity
protected auth flavor for SECINFO.
Older servers may not support using the machine cred or an integrity
protected auth flavor for SECINFO in every circumstance, so we fall back
to using the user's cred and the filesystem's auth flavor in this case.
We run into another problem when running against linux nfs servers -
they return NFS4ERR_WRONGSEC when using integrity auth flavor (unless the
mount is also that flavor) even though that is not a valid error for
SECINFO*. Even though it's against spec, handle WRONGSEC errors on SECINFO
by falling back to using the user cred and the filesystem's auth flavor.
Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Andy Adamson [Wed, 14 Aug 2013 15:59:17 +0000 (11:59 -0400)]
SUNRPC refactor rpcauth_checkverf error returns
Most of the time an error from the credops crvalidate function means the
server has sent us a garbage verifier. The gss_validate function is the
exception where there is an -EACCES case if the user GSS_context on the client
has expired.
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Andy Adamson [Wed, 14 Aug 2013 15:59:16 +0000 (11:59 -0400)]
NFS avoid expired credential keys for buffered writes
We must avoid buffering a WRITE that is using a credential key (e.g. a GSS
context key) that is about to expire or has expired. We currently will
paint ourselves into a corner by returning success to the applciation
for such a buffered WRITE, only to discover that we do not have permission when
we attempt to flush the WRITE (and potentially associated COMMIT) to disk.
Use the RPC layer credential key timeout and expire routines which use a
a watermark, gss_key_expire_timeo. We test the key in nfs_file_write.
If a WRITE is using a credential with a key that will expire within
watermark seconds, flush the inode in nfs_write_end and send only
NFS_FILE_SYNC WRITEs by adding nfs_ctx_key_to_expire to nfs_need_sync_write.
Note that this results in single page NFS_FILE_SYNC WRITEs.
Signed-off-by: Andy Adamson <andros@netapp.com>
[Trond: removed a pr_warn_ratelimited() for now]
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Andy Adamson [Wed, 14 Aug 2013 15:59:15 +0000 (11:59 -0400)]
SUNRPC new rpc_credops to test credential expiry
This patch provides the RPC layer helper functions to allow NFS to manage
data in the face of expired credentials - such as avoiding buffered WRITEs
and COMMITs when the gss context will expire before the WRITEs are flushed
and COMMITs are sent.
These helper functions enable checking the expiration of an underlying
credential key for a generic rpc credential, e.g. the gss_cred gss context
gc_expiry which for Kerberos is set to the remaining TGT lifetime.
A new rpc_authops key_timeout is only defined for the generic auth.
A new rpc_credops crkey_to_expire is only defined for the generic cred.
A new rpc_credops crkey_timeout is only defined for the gss cred.
Set a credential key expiry watermark, RPC_KEY_EXPIRE_TIMEO set to 240 seconds
as a default and can be set via a module parameter as we need to ensure there
is time for any dirty data to be flushed.
If key_timeout is called on a credential with an underlying credential key that
will expire within watermark seconds, we set the RPC_CRED_KEY_EXPIRE_SOON
flag in the generic_cred acred so that the NFS layer can clean up prior to
key expiration.
Checking a generic credential's underlying credential involves a cred lookup.
To avoid this lookup in the normal case when the underlying credential has
a key that is valid (before the watermark), a notify flag is set in
the generic credential the first time the key_timeout is called. The
generic credential then stops checking the underlying credential key expiry, and
the underlying credential (gss_cred) match routine then checks the key
expiration upon each normal use and sets a flag in the associated generic
credential only when the key expiration is within the watermark.
This in turn signals the generic credential key_timeout to perform the extra
credential lookup thereafter.
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Andy Adamson [Wed, 14 Aug 2013 15:59:13 +0000 (11:59 -0400)]
SUNRPC: don't map EKEYEXPIRED to EACCES in call_refreshresult
The NFS layer needs to know when a key has expired.
This change also returns -EKEYEXPIRED to the application, and the informative
"Key has expired" error message is displayed. The user then knows that
credential renewal is required.
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 2 Sep 2013 17:28:04 +0000 (13:28 -0400)]
SUNRPC: rpcauth_create needs to know about rpc_clnt clone status
Ensure that we set rpc_clnt->cl_parent before calling rpc_client_register
so that rpcauth_create can find any existing RPCSEC_GSS caches for this
transport.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 28 Aug 2013 19:26:25 +0000 (15:26 -0400)]
RPCSEC_GSS: Share all credential caches on a per-transport basis
Ensure that all struct rpc_clnt for any given socket/rdma channel
share the same RPCSEC_GSS/krb5,krb5i,krb5p caches.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Tue, 27 Aug 2013 20:52:16 +0000 (16:52 -0400)]
RPCSEC_GSS: Share rpc_pipes when an rpc_clnt owns multiple rpcsec auth caches
Ensure that if an rpc_clnt owns more than one RPCSEC_GSS-based authentication
mechanism, then those caches will share the same 'gssd' upcall pipe.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Tue, 27 Aug 2013 20:27:04 +0000 (16:27 -0400)]
SUNRPC: Add a helper to allow sharing of rpc_pipefs directory objects
Add support for looking up existing objects and creating new ones if there
is no match.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 26 Aug 2013 21:44:26 +0000 (17:44 -0400)]
SUNRPC: Remove the rpc_client->cl_dentry
It is now redundant.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 26 Aug 2013 21:16:17 +0000 (17:16 -0400)]
NFSv4: Convert idmapper to use the new framework for pipefs dentries
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 26 Aug 2013 20:47:20 +0000 (16:47 -0400)]
SUNRPC: Remove the obsolete auth-only interface for pipefs dentry management
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 26 Aug 2013 20:44:42 +0000 (16:44 -0400)]
RPCSEC_GSS: Switch auth_gss to use the new framework for pipefs dentries
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 26 Aug 2013 19:38:11 +0000 (15:38 -0400)]
SUNRPC: Add a framework to clean up management of rpc_pipefs directories
The current system requires everyone to set up notifiers, manage directory
locking, etc.
What we really want to do is have the rpc_client create its directory,
and then create all the entries.
This patch will allow the RPCSEC_GSS and NFS code to register all the
objects that they want to have appear in the directory, and then have
the sunrpc code call them back to actually create/destroy their pipefs
dentries when the rpc_client creates/destroys the parent.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 26 Aug 2013 21:26:51 +0000 (17:26 -0400)]
NFSv4: Fix a potentially Oopsable condition in __nfs_idmap_unregister
Ensure that __nfs_idmap_unregister can be called twice without
consequences.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 26 Aug 2013 20:05:11 +0000 (16:05 -0400)]
RPCSEC_GSS: Fix an Oopsable condition when creating/destroying pipefs objects
If an error condition occurs on rpc_pipefs creation, or the user mounts
rpc_pipefs and then unmounts it, then the dentries in struct gss_auth
need to be reset to NULL so that a second call to gss_pipes_dentries_destroy
doesn't try to free them again.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Fri, 23 Aug 2013 18:42:29 +0000 (14:42 -0400)]
RPCSEC_GSS: Further cleanups
Don't pass the rpc_client as a parameter, when what we really want is
the net namespace.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 26 Aug 2013 23:23:04 +0000 (19:23 -0400)]
SUNRPC: Replace clnt->cl_principal
The clnt->cl_principal is being used exclusively to store the service
target name for RPCSEC_GSS/krb5 callbacks. Replace it with something that
is stored only in the RPCSEC_GSS-specific code.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Fri, 23 Aug 2013 18:02:24 +0000 (14:02 -0400)]
RPCSEC_GSS: Clean up upcall message allocation
Optimise away gss_encode_msg: we don't need to look up the pipe
version a second time.
Save the gss target name in struct gss_auth. It is a property of the
auth cache itself, and doesn't really belong in the rpc_client.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Fri, 23 Aug 2013 17:03:50 +0000 (13:03 -0400)]
SUNRPC: Cleanup rpc_setup_pipedir
The directory name is _always_ clnt->cl_program->pipe_dir_name.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 26 Aug 2013 23:58:45 +0000 (19:58 -0400)]
SUNRPC: Remove unused struct rpc_clnt field cl_protname
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Fri, 23 Aug 2013 15:48:15 +0000 (11:48 -0400)]
SUNRPC: Deprecate rpc_client->cl_protname
It just duplicates the cl_program->name, and is not used in any fast
paths where the extra dereference will cause a hit.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Fri, 30 Aug 2013 13:17:33 +0000 (09:17 -0400)]
NFS: Fix up two use-after-free issues with the new tracing code
We don't want to pass the context argument to trace_nfs_atomic_open_exit()
after it has been released.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
NeilBrown [Mon, 12 Aug 2013 06:52:47 +0000 (16:52 +1000)]
NFS: remove incorrect "Lock reclaim failed!" warning.
After reclaiming state that was lost, the NFS client tries to reclaim
any locks, and then checks that each one has NFS_LOCK_INITIALIZED set
(which means that the server has confirmed the lock).
However if the client holds a delegation, nfs_reclaim_locks() simply aborts
(or more accurately it called nfs_lock_reclaim() and that returns without
doing anything).
This is because when a delegation is held, the server doesn't need to
know about locks.
So if a delegation is held, NFS_LOCK_INITIALIZED is not expected, and
its absence is certainly not an error.
So don't print the warnings if NFS_DELGATED_STATE is set.
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 21 Aug 2013 01:59:40 +0000 (21:59 -0400)]
NFSv4.1: Add tracepoints for debugging test_stateid events
Add tracepoints to detect issues with the TEST_STATEID operation.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 14 Aug 2013 21:58:28 +0000 (17:58 -0400)]
NFSv4.1: Add tracepoints for debugging slot table operations
Add tracepoints to nfs41_setup_sequence and nfs41_sequence_done
to track session and slot table state changes.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 14 Aug 2013 20:36:51 +0000 (16:36 -0400)]
NFSv4.1: Add tracepoints for debugging layoutget/return/commit
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 14 Aug 2013 19:31:28 +0000 (15:31 -0400)]
NFSv4: Add tracepoints for debugging reads and writes
Set up tracepoints to track read, write and commit, as well as
pNFS reads and writes and commits to the data server.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Tue, 13 Aug 2013 17:01:39 +0000 (13:01 -0400)]
NFSv4: Add tracepoints for debugging getattr
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Tue, 13 Aug 2013 15:34:01 +0000 (11:34 -0400)]
NFSv4: Add tracepoints for debugging the idmapper
Add tracepoints to help debug uid/gid mappings to username/group.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Tue, 13 Aug 2013 14:36:56 +0000 (10:36 -0400)]
NFSv4: Add tracepoints for debugging delegations
Set up tracepoints to track when delegations are set, reclaimed,
returned by the client, or recalled by the server.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 12 Aug 2013 21:08:26 +0000 (17:08 -0400)]
NFSv4: Add tracepoints for debugging rename
Add tracepoints to debug renames.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 12 Aug 2013 20:58:42 +0000 (16:58 -0400)]
NFSv4: Add tracepoints for debugging inode manipulations
Set up basic tracepoints for debugging NFSv4 setattr, access,
readlink, readdir, get_acl set_acl get_security_label,
and set_security_label.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 12 Aug 2013 20:45:55 +0000 (16:45 -0400)]
NFSv4: Add tracepoints for debugging lookup/create operations
Set up basic tracepoints for debugging NFSv4 lookup, unlink/remove,
symlink, mkdir, mknod, fs_locations and secinfo.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 12 Aug 2013 20:35:20 +0000 (16:35 -0400)]
NFSv4: Add tracepoints for debugging file locking
Set up basic tracepoints for debugging NFSv4 file lock/unlock
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 12 Aug 2013 20:19:27 +0000 (16:19 -0400)]
NFSv4: Add tracepoints for debugging file open
Set up basic tracepoints for debugging NFSv4 file open/close
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Fri, 9 Aug 2013 15:51:26 +0000 (11:51 -0400)]
NFSv4: Add tracepoints for debugging state management problems
Set up basic tracepoints for debugging client id creation/destruction
and session creation/destruction.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 21 Aug 2013 17:54:44 +0000 (13:54 -0400)]
NFS: Add tracepoints for debugging NFS hard links
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 21 Aug 2013 16:08:45 +0000 (12:08 -0400)]
NFS: Add tracepoints for debugging NFS rename and sillyrename issues
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 21 Aug 2013 16:36:04 +0000 (12:36 -0400)]
NFS: Add tracepoints for debugging directory changes
Add tracepoints for mknod, mkdir, rmdir, remove (unlink) and symlink.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 21 Aug 2013 14:53:09 +0000 (10:53 -0400)]
NFS: Add tracepoints for debugging generic file create events
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Tue, 20 Aug 2013 15:26:17 +0000 (11:26 -0400)]
NFS: Add event tracing for generic NFS lookups
Add tracepoints for lookup, lookup_revalidate and atomic_open
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Tue, 20 Aug 2013 15:59:41 +0000 (11:59 -0400)]
NFS: Pass in lookup flags from nfs_atomic_open to nfs_lookup
When doing an open of a directory, ensure that we do pass the lookup flags
from nfs_atomic_open into nfs_lookup.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 19 Aug 2013 22:59:33 +0000 (18:59 -0400)]
NFS: Add event tracing for generic NFS events
Add tracepoints for inode attribute updates, attribute revalidation,
writeback start/end fsync start/end, attribute change start/end,
permission check start/end.
The intention is to enable performance tracing using 'perf'as well as
improving debugging.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Mon, 12 Aug 2013 20:06:31 +0000 (16:06 -0400)]
NFS: refactor code for calculating the crc32 hash of a filehandle
We want to be able to display the crc32 hash of the filehandle in
tracepoints.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 21 Aug 2013 23:54:08 +0000 (19:54 -0400)]
NFS: Clean up nfs_sillyrename()
Optimise for the case where we only do one lookup.
Clean up the code so it is obvious that silly[] is not a dynamic array.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 21 Aug 2013 01:08:56 +0000 (21:08 -0400)]
NFSv4: Fix an incorrect pointer declaration in decode_first_pnfs_layout_type
We always encode to __be32 format in XDR: silences a sparse warning.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Andy Adamson <andros@netapp.com>
Trond Myklebust [Thu, 22 Aug 2013 00:06:11 +0000 (20:06 -0400)]
NFSv4: Deal with a sparse warning in nfs_idmap_get_key()
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Bryan Schumaker <bjschuma@netapp.com>
Trond Myklebust [Wed, 21 Aug 2013 19:48:42 +0000 (15:48 -0400)]
NFSv4: Deal with some more sparse warnings
Technically, we don't really need to convert these time stamps,
since they are actually cookies.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Chuck Lever <Chuck.Lever@oracle.com>
Trond Myklebust [Wed, 21 Aug 2013 01:06:49 +0000 (21:06 -0400)]
NFSv4: Deal with a sparse warning in nfs4_opendata_alloc
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 21 Aug 2013 01:04:11 +0000 (21:04 -0400)]
NFSv3: Deal with a sparse warning in nfs3_proc_create
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Tue, 20 Aug 2013 16:29:27 +0000 (12:29 -0400)]
NFS: Remove the NFSv4 "open optimisation" from nfs_permission
Ever since commit
6168f62cb (Add ACCESS operation to OPEN compound)
the NFSv4 atomic open has primed the access cache, and so nfs_permission
will no longer do an RPC call on the wire.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Andy Adamson [Thu, 8 Aug 2013 14:57:56 +0000 (10:57 -0400)]
NFSv4.1 Use clientid management rpc_clnt for secinfo_no_name
As per RFC 5661 Security Considerations
Commit
4edaa308 "NFS: Use "krb5i" to establish NFSv4 state whenever possible"
uses the nfs_client cl_rpcclient for all clientid management operations.
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Andy Adamson [Thu, 8 Aug 2013 14:57:55 +0000 (10:57 -0400)]
NFSv4.1 Use clientid management rpc_clnt for secinfo
As per RFC 3530 and RFC 5661 Security Considerations
Commit
4edaa308 "NFS: Use "krb5i" to establish NFSv4 state whenever possible"
uses the nfs_client cl_rpcclient for all clientid management operations.
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Andy Adamson [Mon, 22 Jul 2013 22:41:23 +0000 (18:41 -0400)]
NFSv4.1 Increase NFS4_DEF_SLOT_TABLE_SIZE
Increase NFS4_DEF_SLOT_TABLE_SIZE which is used as the client ca_maxreequests
value in CREATE_SESSION. Current non-dynamic session slot server
implementations use the client ca_maxrequests as a maximum slot number: 64
session slots can handle most workloads.
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Andy Adamson [Wed, 24 Jul 2013 15:59:49 +0000 (11:59 -0400)]
NFS Remove unused authflavour parameter from init_client
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Wed, 24 Jul 2013 16:28:37 +0000 (12:28 -0400)]
NFS: Never use user credentials for lease renewal
Never try to use a non-UID 0 user credential for lease management,
as that credential can change out from under us. The server will
block NFSv4 lease recovery with NFS4ERR_CLID_INUSE.
Since the mechanism to acquire a credential for lease management
is now the same for all minor versions, replace the minor version-
specific callout with a single function.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Wed, 24 Jul 2013 16:28:28 +0000 (12:28 -0400)]
NFS: Use root's credential for lease management when keytab is missing
Commit
05f4c350 "NFS: Discover NFSv4 server trunking when mounting"
Fri Sep 14 17:24:32 2012 introduced Uniform Client String support,
which forces our NFS client to establish a client ID immediately
during a mount operation rather than waiting until a user wants to
open a file.
Normally machine credentials (eg. from a keytab) are used to perform
a mount operation that is protected by Kerberos. Before
05fc350,
SETCLIENTID used a machine credential, or fell back to a regular
user's credential if no keytab is available.
On clients that don't have a keytab, performing SETCLIENTID early
means there's no user credential to fall back on, since no regular
user has kinit'd yet.
05f4c350 seems to have broken the ability
to mount with sec=krb5 on clients that don't have a keytab in
kernels 3.7 - 3.10.
To address this regression, commit
4edaa308 (NFS: Use "krb5i" to
establish NFSv4 state whenever possible), Sat Mar 16 15:56:20 2013,
was merged in 3.10. This commit forces the NFS client to fall back
to AUTH_SYS for lease management operations if no keytab is
available.
Neil Brown noticed that, since root is required to kinit to do a
sec=krb5 mount when a client doesn't have a keytab, we can try to
use root's Kerberos credential before AUTH_SYS.
Now, when determining a principal and flavor to use for lease
management, the NFS client tries in this order:
1. Flavor: AUTH_GSS, krb5i
Principal: service principal (via keytab)
2. Flavor: AUTH_GSS, krb5i
Principal: user principal established for UID 0 (via kinit)
3. Flavor: AUTH_SYS
Principal: UID 0 / GID 0
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 7 Aug 2013 16:30:52 +0000 (12:30 -0400)]
NFSv4: Refuse mount attempts with proto=udp
RFC3530 disallows the use of udp as a transport protocol for NFSv4.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Jeff Layton [Fri, 2 Aug 2013 15:39:32 +0000 (11:39 -0400)]
nfs: verify open flags before allowing an atomic open
Currently, you can open a NFSv4 file with O_APPEND|O_DIRECT, but cannot
fcntl(F_SETFL,...) with those flags. This flag combination is explicitly
forbidden on NFSv3 opens, and it seems like it should also be on NFSv4.
Reported-by: Chao Ye <cye@redhat.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust [Wed, 24 Jul 2013 20:36:35 +0000 (16:36 -0400)]
NFSv4: Fix nfs4_init_uniform_client_string for net namespaces
Commit
6f2ea7f2a (NFS: Add nfs4_unique_id boot parameter) introduces a
boot parameter that allows client administrators to set a string
identifier for use by the EXCHANGE_ID and SETCLIENTID arguments in order
to make them more globally unique.
Unfortunately, that uniquifier is no longer globally unique in the presence
of net namespaces, since each container expects to be able to set up their
own lease when mounting a new NFSv4/4.1 partition.
The fix is to add back in the container-specific hostname in addition to
the unique id.
Cc: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Andy Adamson [Mon, 22 Jul 2013 16:42:05 +0000 (12:42 -0400)]
NFSv4.1 Use the mount point rpc_clnt for layoutreturn
Should not use the clientid maintenance rpc_clnt.
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Chuck Lever [Fri, 12 Jul 2013 16:31:45 +0000 (12:31 -0400)]
NFS: Fix return type of nfs4_end_drain_session() stub
Clean up: when NFSv4.1 support is compiled out,
nfs4_end_drain_session() becomes a stub. Make the synopsis of the
stub match the synopsis of the real version of the function.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>