Commit Graph

1026 Commits

Author SHA1 Message Date
Greg Banks
03cf6c9f49 knfsd: add file to export stats about nfsd pools
Add /proc/fs/nfsd/pool_stats to export to userspace various
statistics about the operation of rpc server thread pools.

This patch is based on a forward-ported version of
knfsd-add-pool-thread-stats which has been shipping in the SGI
"Enhanced NFS" product since 2006 and which was previously
posted:

http://article.gmane.org/gmane.linux.nfs/10375

It has also been updated thus:

 * moved EXPORT_SYMBOL() to near the function it exports
 * made the new struct struct seq_operations const
 * used SEQ_START_TOKEN instead of ((void *)1)
 * merged fix from SGI PV 990526 "sunrpc: use dprintk instead of
   printk in svc_pool_stats_*()" by Harshula Jayasuriya.
 * merged fix from SGI PV 964001 "Crash reading pool_stats before
   nfsds are started".

Signed-off-by: Greg Banks <gnb@sgi.com>
Signed-off-by: Harshula Jayasuriya <harshula@sgi.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-03-18 17:38:42 -04:00
Greg Banks
59a252ff8c knfsd: avoid overloading the CPU scheduler with enormous load averages
Avoid overloading the CPU scheduler with enormous load averages
when handling high call-rate NFS loads.  When the knfsd bottom half
is made aware of an incoming call by the socket layer, it tries to
choose an nfsd thread and wake it up.  As long as there are idle
threads, one will be woken up.

If there are lot of nfsd threads (a sensible configuration when
the server is disk-bound or is running an HSM), there will be many
more nfsd threads than CPUs to run them.  Under a high call-rate
low service-time workload, the result is that almost every nfsd is
runnable, but only a handful are actually able to run.  This situation
causes two significant problems:

1. The CPU scheduler takes over 10% of each CPU, which is robbing
   the nfsd threads of valuable CPU time.

2. At a high enough load, the nfsd threads starve userspace threads
   of CPU time, to the point where daemons like portmap and rpc.mountd
   do not schedule for tens of seconds at a time.  Clients attempting
   to mount an NFS filesystem timeout at the very first step (opening
   a TCP connection to portmap) because portmap cannot wake up from
   select() and call accept() in time.

Disclaimer: these effects were observed on a SLES9 kernel, modern
kernels' schedulers may behave more gracefully.

The solution is simple: keep in each svc_pool a counter of the number
of threads which have been woken but have not yet run, and do not wake
any more if that count reaches an arbitrary small threshold.

Testing was on a 4 CPU 4 NIC Altix using 4 IRIX clients, each with 16
synthetic client threads simulating an rsync (i.e. recursive directory
listing) workload reading from an i386 RH9 install image (161480
regular files in 10841 directories) on the server.  That tree is small
enough to fill in the server's RAM so no disk traffic was involved.
This setup gives a sustained call rate in excess of 60000 calls/sec
before being CPU-bound on the server.  The server was running 128 nfsds.

Profiling showed schedule() taking 6.7% of every CPU, and __wake_up()
taking 5.2%.  This patch drops those contributions to 3.0% and 2.2%.
Load average was over 120 before the patch, and 20.9 after.

This patch is a forward-ported version of knfsd-avoid-nfsd-overload
which has been shipping in the SGI "Enhanced NFS" product since 2006.
It has been posted before:

http://article.gmane.org/gmane.linux.nfs/10374

Signed-off-by: Greg Banks <gnb@sgi.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-03-18 17:38:41 -04:00
Rusty Russell
a70f730282 cpumask: replace node_to_cpumask with cpumask_of_node.
Impact: cleanup

node_to_cpumask (and the blecherous node_to_cpumask_ptr which
contained a declaration) are replaced now everyone implements
cpumask_of_node.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2009-03-13 14:49:46 +10:30
Trond Myklebust
5e3771ce2d SUNRPC: Ensure that xs_nospace return values are propagated
If xs_nospace() finds that the socket has disconnected, it attempts to
return ENOTCONN, however that value is then squashed by the callers.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-11 14:38:01 -04:00
Trond Myklebust
8a2cec295f SUNRPC: Delay, then retry on connection errors.
Enforce the comment in xs_tcp_connect_worker4/xs_tcp_connect_worker6 that
we should delay, then retry on certain connection errors.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-11 14:38:01 -04:00
Trond Myklebust
2a4919919a SUNRPC: Return EAGAIN instead of ENOTCONN when waking up xprt->pending
While we should definitely return socket errors to the task that is
currently trying to send data, there is no need to propagate the same error
to all the other tasks on xprt->pending. Doing so actually slows down
recovery, since it causes more than one tasks to attempt socket recovery.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-11 14:38:00 -04:00
Trond Myklebust
482f32e65d SUNRPC: Handle socket errors correctly
Ensure that we pick up and handle socket errors as they occur.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-11 14:38:00 -04:00
Trond Myklebust
c8485e4d63 SUNRPC: Handle ECONNREFUSED correctly in xprt_transmit()
If we get an ECONNREFUSED error, we currently go to sleep on the
'xprt->sending' wait queue. The problem is that no timeout is set there,
and there is nothing else that will wake the task up later.

We should deal with ECONNREFUSED in call_status, given that is where we
also deal with -EHOSTDOWN, and friends.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-11 14:37:59 -04:00
Trond Myklebust
40d2549db5 SUNRPC: Don't disconnect if a connection is still in progress.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-11 14:37:58 -04:00
Trond Myklebust
670f945731 SUNRPC: Ensure we set XPRT_CLOSING only after we've sent a tcp FIN...
...so that we can distinguish between when we need to shutdown and when we
don't. Also remove the call to xs_tcp_shutdown() from xs_tcp_connect(),
since xprt_connect() makes the same test.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-11 14:37:58 -04:00
Trond Myklebust
15f081ca8d SUNRPC: Avoid an unnecessary task reschedule on ENOTCONN
If the socket is unconnected, and xprt_transmit() returns ENOTCONN, we
currently give up the lock on the transport channel. Doing so means that
the lock automatically gets assigned to the next task in the xprt->sending
queue, and so that task needs to be woken up to do the actual connect.

The following patch aims to avoid that unnecessary task switch.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-11 14:37:57 -04:00
Tom Talpey
441e3e2429 SUNRPC: dynamically load RPC transport modules on-demand
Provide an api to attempt to load any necessary kernel RPC
client transport module automatically. By convention, the
desired module name is "xprt"+"transport name". For example,
when NFS mounting with "-o proto=rdma", attempt to load the
"xprtrdma" module.

Signed-off-by: Tom Talpey <tmtalpey@gmail.com>
Cc: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-11 14:37:56 -04:00
Tom Talpey
b38ab40ad5 XPRTRDMA: correct an rpc/rdma inline send marshaling error
Certain client rpc's which contain both lengthy page-contained
metadata and a non-empty xdr_tail buffer require careful handling
to avoid overlapped memory copying. Rearranging of existing rpcrdma
marshaling code avoids it; this fixes an NFSv4 symlink creation error
detected with connectathon basic/test8 to multiple servers.

Signed-off-by: Tom Talpey <tmtalpey@gmail.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-11 14:37:55 -04:00
Tom Talpey
b1e1e15877 SVCRDMA: remove faulty assertions in rpc/rdma chunk validation.
Certain client-provided RPCRDMA chunk alignments result in an
additional scatter/gather entry, which triggered nfs/rdma server
assertions incorrectly. OpenSolaris nfs/rdma client connectathon
testing was blocked by these in the special/locking section.

Signed-off-by: Tom Talpey <tmtalpey@gmail.com>
Cc: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-11 14:37:55 -04:00
Chuck Lever
fe315e76fc SUNRPC: Avoid spurious wake-up during UDP connect processing
To clear out old state, the UDP connect workers unconditionally invoke
xs_close() before proceeding with a new connect.  Nowadays this causes
a spurious wake-up of the task waiting for the connect to complete.

This is a little racey, but usually harmless.  The waiting task
immediately retries the connect via a call_bind/call_connect sequence,
which usually finds the transport already in the connected state
because the connect worker has finished in the background.

To avoid a spurious wake-up, factor the xs_close() logic that resets
the underlying socket into a helper, and have the UDP connect workers
call that helper instead of xs_close().

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-11 14:10:21 -04:00
Trond Myklebust
01d37c428a SUNRPC: xprt_connect() don't abort the task if the transport isn't bound
If the transport isn't bound, then we should just return ENOTCONN, letting
call_connect_status() and/or call_status() deal with retrying. Currently,
we appear to abort all pending tasks with an EIO error.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-11 14:09:39 -04:00
Trond Myklebust
fba91afbec SUNRPC: Fix an Oops due to socket not set up yet...
We can Oops in both xs_udp_send_request() and xs_tcp_send_request() if the
call to xs_sendpages() returns an error due to the socket not yet being
set up.
Deal with that situation by returning a new error: ENOTSOCK, so that we
know to avoid dereferencing transport->sock.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-11 14:06:41 -04:00
Trond Myklebust
eb9b55ab4d SUNRPC: Tighten up the task locking rules in __rpc_execute()
We should probably not be testing any flags after we've cleared the
RPC_TASK_RUNNING flag, since rpc_make_runnable() is then free to assign the
rpc_task to another workqueue, which may then destroy it.

We can fix any races with rpc_make_runnable() by ensuring that we only
clear the RPC_TASK_RUNNING flag while holding the rpc_wait_queue->lock that
the task is supposed to be sleeping on (and then checking whether or not
the task really is sleeping).

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-10 20:33:16 -04:00
Ilpo Järvinen
1f0fa15432 net/sunrpc/xprtsock.c: some common code found
$ diff-funcs xs_udp_write_space net/sunrpc/xprtsock.c
net/sunrpc/xprtsock.c xs_tcp_write_space
 --- net/sunrpc/xprtsock.c:xs_udp_write_space()
 +++ net/sunrpc/xprtsock.c:xs_tcp_write_space()
@@ -1,4 +1,4 @@
- * xs_udp_write_space - callback invoked when socket buffer space
+ * xs_tcp_write_space - callback invoked when socket buffer space
  *                             becomes available
  * @sk: socket whose state has changed
  *
@@ -7,12 +7,12 @@
  * progress, otherwise we'll waste resources thrashing kernel_sendmsg
  * with a bunch of small requests.
  */
-static void xs_udp_write_space(struct sock *sk)
+static void xs_tcp_write_space(struct sock *sk)
 {
 	read_lock(&sk->sk_callback_lock);

-	/* from net/core/sock.c:sock_def_write_space */
-	if (sock_writeable(sk)) {
+	/* from net/core/stream.c:sk_stream_write_space */
+	if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) {
 		struct socket *sock;
 		struct rpc_xprt *xprt;


$ codiff net/sunrpc/xprtsock.o net/sunrpc/xprtsock.o.new
net/sunrpc/xprtsock.c:
  xs_tcp_write_space | -163
  xs_udp_write_space | -163
 2 functions changed, 326 bytes removed

net/sunrpc/xprtsock.c:
  xs_write_space | +179
 1 function changed, 179 bytes added

net/sunrpc/xprtsock.o.new:
 3 functions changed, 179 bytes added, 326 bytes removed, diff: -147

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-02-06 23:48:33 -08:00
Randy Dunlap
55128bc23e sunrpc: fix rdma dependencies
Fix sunrpc/rdma build dependencies.
Survives 12 build combinations of INET, IPV6, SUNRPC,
INFINIBAND, and INFINIBAND_ADDR_TRANS.

ERROR: "rdma_destroy_id" [net/sunrpc/xprtrdma/xprtrdma.ko] undefined!
ERROR: "rdma_connect" [net/sunrpc/xprtrdma/xprtrdma.ko] undefined!
ERROR: "rdma_destroy_qp" [net/sunrpc/xprtrdma/xprtrdma.ko] undefined!
ERROR: "rdma_create_id" [net/sunrpc/xprtrdma/xprtrdma.ko] undefined!
ERROR: "rdma_create_qp" [net/sunrpc/xprtrdma/xprtrdma.ko] undefined!
ERROR: "rdma_resolve_route" [net/sunrpc/xprtrdma/xprtrdma.ko] undefined!
ERROR: "rdma_disconnect" [net/sunrpc/xprtrdma/xprtrdma.ko] undefined!
ERROR: "rdma_resolve_addr" [net/sunrpc/xprtrdma/xprtrdma.ko] undefined!
ERROR: "rdma_accept" [net/sunrpc/xprtrdma/svcrdma.ko] undefined!
ERROR: "rdma_destroy_id" [net/sunrpc/xprtrdma/svcrdma.ko] undefined!
ERROR: "rdma_listen" [net/sunrpc/xprtrdma/svcrdma.ko] undefined!
ERROR: "rdma_create_id" [net/sunrpc/xprtrdma/svcrdma.ko] undefined!
ERROR: "rdma_create_qp" [net/sunrpc/xprtrdma/svcrdma.ko] undefined!
ERROR: "rdma_bind_addr" [net/sunrpc/xprtrdma/svcrdma.ko] undefined!
ERROR: "rdma_disconnect" [net/sunrpc/xprtrdma/svcrdma.ko] undefined!

Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-02-03 15:20:13 -08:00
J. Bruce Fields
ce0cf6622c nfs: note that CONFIG_SUNRPC_XPRT_RDMA turns on server side support too
We forgot to update this when adding server-side support.

Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-01-27 17:26:58 -05:00
Alexey Dobriyan
9098c24f35 fs/Kconfig: move sunrpc out
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
2009-01-22 13:16:00 +03:00
Trond Myklebust
24c3767e41 SUNRPC: The sunrpc server code should not be used by out-of-tree modules
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-01-07 17:18:42 -05:00
Tom Tucker
22945e4a1c svc: Clean up deferred requests on transport destruction
A race between svc_revisit and svc_delete_xprt can result in
deferred requests holding references on a transport that can never be
recovered because dead transports are not enqueued for subsequent
processing.

Check for XPT_DEAD in revisit to clean up completing deferrals on a dead
transport and sweep a transport's deferred queue to do the same for queued
but unprocessed deferrals.

Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-01-07 17:08:46 -05:00
Tom Tucker
2779e3ae39 svc: Move kfree of deferral record to common code
The rqstp structure has a pointer to a svc_deferred_req record
that is allocated when requests are deferred. This record is common
to all transports and can be freed in common code.

Move the kfree of the rq_deferred to the common svc_xprt_release
function.

This also fixes a memory leak in the RDMA transport which does not
kfree the dr structure in it's version of the xpo_release_rqst callback.

Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-01-07 15:40:45 -05:00
Trond Myklebust
69b6ba3712 SUNRPC: Ensure the server closes sockets in a timely fashion
We want to ensure that connected sockets close down the connection when we
set XPT_CLOSE, so that we don't keep it hanging while cleaning up all the
stuff that is keeping a reference to the socket.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-01-06 11:53:57 -05:00
Jeff Layton
c9233eb7b0 sunrpc: add sv_maxconn field to svc_serv (try #3)
svc_check_conn_limits() attempts to prevent denial of service attacks
by having the service close old connections once it reaches a
threshold. This threshold is based on the number of threads in the
service:

	(serv->sv_nrthreads + 3) * 20

Once we reach this, we drop the oldest connections and a printk pops
to warn the admin that they should increase the number of threads.

Increasing the number of threads isn't an option however for services
like lockd. We don't want to eliminate this check entirely for such
services but we need some way to increase this limit.

This patch adds a sv_maxconn field to the svc_serv struct. When it's
set to 0, we use the current method to calculate the max number of
connections. RPC services can then set this on an as-needed basis.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Acked-by: Neil Brown <neilb@suse.de>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-01-06 11:53:47 -05:00
Al Viro
56ff5efad9 zero i_uid/i_gid on inode allocation
... and don't bother in callers.  Don't bother with zeroing i_blocks,
while we are at it - it's already been zeroed.

i_mode is not worth the effort; it has no common default value.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-01-05 11:54:28 -05:00
Trond Myklebust
08cc36cbd1 Merge branch 'devel' into next 2008-12-30 16:51:43 -05:00
Linus Torvalds
0191b625ca Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1429 commits)
  net: Allow dependancies of FDDI & Tokenring to be modular.
  igb: Fix build warning when DCA is disabled.
  net: Fix warning fallout from recent NAPI interface changes.
  gro: Fix potential use after free
  sfc: If AN is enabled, always read speed/duplex from the AN advertising bits
  sfc: When disabling the NIC, close the device rather than unregistering it
  sfc: SFT9001: Add cable diagnostics
  sfc: Add support for multiple PHY self-tests
  sfc: Merge top-level functions for self-tests
  sfc: Clean up PHY mode management in loopback self-test
  sfc: Fix unreliable link detection in some loopback modes
  sfc: Generate unique names for per-NIC workqueues
  802.3ad: use standard ethhdr instead of ad_header
  802.3ad: generalize out mac address initializer
  802.3ad: initialize ports LACPDU from const initializer
  802.3ad: remove typedef around ad_system
  802.3ad: turn ports is_individual into a bool
  802.3ad: turn ports is_enabled into a bool
  802.3ad: make ntt bool
  ixgbe: Fix set_ringparam in ixgbe to use the same memory pools.
  ...

Fixed trivial IPv4/6 address printing conflicts in fs/cifs/connect.c due
to the conversion to %pI (in this networking merge) and the addition of
doing IPv6 addresses (from the earlier merge of CIFS).
2008-12-28 12:49:40 -08:00
Olga Kornievskaia
2efef7080f rpc: add service field to new upcall
This patch extends the new upcall with a "service" field that currently
can have 2 values: "*" or "nfs". These values specify matching rules for
principals in the keytab file. The "*" means that gssd is allowed to use
"root", "nfs", or "host" keytab entries while the other option requires
"nfs".

Restricting gssd to use the "nfs" principal is needed for when the
server performs a callback to the client.  The server in this case has
to authenticate itself as an "nfs" principal.

We also need "service" field to distiguish between two client-side cases
both currently using a uid of 0: the case of regular file access by the
root user, and the case of state-management calls (such as setclientid)
which should use a keytab for authentication.  (And the upcall should
fail if an appropriate principal can't be found.)

Signed-off: Olga Kornievskaia <aglo@citi.umich.edu>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 16:19:56 -05:00
Olga Kornievskaia
8b1c7bf5b6 rpc: add target field to new upcall
This patch extends the new upcall by adding a "target" field
communicating who we want to authenticate to (equivalently, the service
principal that we want to acquire a ticket for).

Signed-off: Olga Kornievskaia <aglo@citi.umich.edu>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 16:19:26 -05:00
Olga Kornievskaia
61054b14d5 nfsd: support callbacks with gss flavors
This patch adds server-side support for callbacks other than AUTH_SYS.

Signed-off-by: Olga Kornievskaia <aglo@citi.umich.edu>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 16:19:00 -05:00
Olga Kornievskaia
945b34a772 rpc: allow gss callbacks to client
This patch adds client-side support to allow for callbacks other than
AUTH_SYS.

Signed-off-by: Olga Kornievskaia <aglo@citi.umich.edu>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 16:18:34 -05:00
Olga Kornievskaia
608207e888 rpc: pass target name down to rpc level on callbacks
The rpc client needs to know the principal that the setclientid was done
as, so it can tell gssd who to authenticate to.

Signed-off-by: Olga Kornievskaia <aglo@citi.umich.edu>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 16:17:40 -05:00
Olga Kornievskaia
68e76ad0ba nfsd: pass client principal name in rsc downcall
Two principals are involved in krb5 authentication: the target, who we
authenticate *to* (normally the name of the server, like
nfs/server.citi.umich.edu@CITI.UMICH.EDU), and the source, we we
authenticate *as* (normally a user, like bfields@UMICH.EDU)

In the case of NFSv4 callbacks, the target of the callback should be the
source of the client's setclientid call, and the source should be the
nfs server's own principal.

Therefore we allow svcgssd to pass down the name of the principal that
just authenticated, so that on setclientid we can store that principal
name with the new client, to be used later on callbacks.

Signed-off-by: Olga Kornievskaia <aglo@citi.umich.edu>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 16:17:15 -05:00
\"J. Bruce Fields\
34769fc488 rpc: implement new upcall
Implement the new upcall.  We decide which version of the upcall gssd
will use (new or old), by creating both pipes (the new one named "gssd",
the old one named after the mechanism (e.g., "krb5")), and then waiting
to see which version gssd actually opens.

We don't permit pipes of the two different types to be opened at once.

Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 16:16:37 -05:00
\"J. Bruce Fields\
5b7ddd4a7b rpc: store pointer to pipe inode in gss upcall message
Keep a pointer to the inode that the message is queued on in the struct
gss_upcall_msg.  This will be convenient, especially after we have a
choice of two pipes that an upcall could be queued on.

Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 16:15:44 -05:00
\"J. Bruce Fields\
79a3f20b64 rpc: use count of pipe openers to wait for first open
Introduce a global variable pipe_version which will eventually be used
to keep track of which version of the upcall gssd is using.

For now, though, it only keeps track of whether any pipe is open or not;
it is negative if not, zero if one is opened.  We use this to wait for
the first gssd to open a pipe.

(Minor digression: note this waits only for the very first open of any
pipe, not for the first open of a pipe for a given auth; thus we still
need the RPC_PIPE_WAIT_FOR_OPEN behavior to wait for gssd to open new
pipes that pop up on subsequent mounts.)

Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 16:10:52 -05:00
\"J. Bruce Fields\
cf81939d6f rpc: track number of users of the gss upcall pipe
Keep a count of the number of pipes open plus the number of messages on
a pipe.  This count isn't used yet.

Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 16:10:19 -05:00
\"J. Bruce Fields\
e712804ae4 rpc: call release_pipe only on last close
I can't see any reason we need to call this until either the kernel or
the last gssd closes the pipe.

Also, this allows to guarantee that open_pipe and release_pipe are
called strictly in pairs; open_pipe on gssd's first open, release_pipe
on gssd's last close (or on the close of the kernel side of the pipe, if
that comes first).

That will make it very easy for the gss code to keep track of which
pipes gssd is using.

Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 16:09:47 -05:00
\"J. Bruce Fields\
c381060869 rpc: add an rpc_pipe_open method
We want to transition to a new gssd upcall which is text-based and more
easily extensible.

To simplify upgrades, as well as testing and debugging, it will help if
we can upgrade gssd (to a version which understands the new upcall)
without having to choose at boot (or module-load) time whether we want
the new or the old upcall.

We will do this by providing two different pipes: one named, as
currently, after the mechanism (normally "krb5"), and supporting the
old upcall.  One named "gssd" and supporting the new upcall version.

We allow gssd to indicate which version it supports by its choice of
which pipe to open.

As we have no interest in supporting *simultaneous* use of both
versions, we'll forbid opening both pipes at the same time.

So, add a new pipe_open callback to the rpc_pipefs api, which the gss
code can use to track which pipes have been open, and to refuse opens of
incompatible pipes.

We only need this to be called on the first open of a given pipe.

Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 16:08:32 -05:00
\"J. Bruce Fields\
db75b3d6b5 rpc: minor gss_alloc_msg cleanup
I want to add a little more code here, so it'll be convenient to have
this flatter.

Also, I'll want to add another error condition, so it'll be more
convenient to return -ENOMEM than NULL in the error case.  The only
caller is already converting NULL to -ENOMEM anyway.

Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 16:07:13 -05:00
\"J. Bruce Fields\
b03568c322 rpc: factor out warning code from gss_pipe_destroy_msg
We'll want to call this from elsewhere soon.  And this is a bit nicer
anyway.

Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 16:06:55 -05:00
\"J. Bruce Fields\
99db356368 rpc: remove unnecessary assignment
We're just about to kfree() gss_auth, so there's no point to setting any
of its fields.

Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 16:06:33 -05:00
Jeff Layton
6dcd3926b2 sunrpc: fix code that makes auth_gss send destroy_cred message (try #2)
There's a bit of a chicken and egg problem when it comes to destroying
auth_gss credentials. When we destroy the last instance of a GSSAPI RPC
credential, we should send a NULL RPC call with a GSS procedure of
RPCSEC_GSS_DESTROY to hint to the server that it can destroy those
creds.

This isn't happening because we're setting clearing the uptodate bit on
the credentials and then setting the operations to the gss_nullops. When
we go to do the RPC call, we try to refresh the creds. That fails with
-EACCES and the call fails.

Fix this by not clearing the UPTODATE bit for the credentials and adding
a new crdestroy op for gss_nullops that just tears down the cred without
trying to destroy the context.

The only difference between this patch and the first one is the removal
of some minor formatting deltas.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 15:21:57 -05:00
Peter Staubach
64672d55d9 optimize attribute timeouts for "noac" and "actimeo=0"
Hi.

I've been looking at a bugzilla which describes a problem where
a customer was advised to use either the "noac" or "actimeo=0"
mount options to solve a consistency problem that they were
seeing in the file attributes.  It turned out that this solution
did not work reliably for them because sometimes, the local
attribute cache was believed to be valid and not timed out.
(With an attribute cache timeout of 0, the cache should always
appear to be timed out.)

In looking at this situation, it appears to me that the problem
is that the attribute cache timeout code has an off-by-one
error in it.  It is assuming that the cache is valid in the
region, [read_cache_jiffies, read_cache_jiffies + attrtimeo].  The
cache should be considered valid only in the region,
[read_cache_jiffies, read_cache_jiffies + attrtimeo).  With this
change, the options, "noac" and "actimeo=0", work as originally
expected.

This problem was previously addressed by special casing the
attrtimeo == 0 case.  However, since the problem is only an off-
by-one error, the cleaner solution is address the off-by-one
error and thus, not require the special case.

    Thanx...

        ps

Signed-off-by: Peter Staubach <staubach@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 15:21:56 -05:00
Trond Myklebust
7bd8826915 SUNRPC: rpcsec_gss modules should not be used by out-of-tree code
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 15:21:32 -05:00
Trond Myklebust
468039ee46 SUNRPC: Convert the xdr helpers and rpc_pipefs to EXPORT_SYMBOL_GPL
We've never considered the sunrpc code as part of any ABI to be used by
out-of-tree modules.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 15:21:31 -05:00
Trond Myklebust
88a9fe8cae SUNRPC: Remove the last remnant of the BKL...
Somehow, this escaped the previous purge. There should be no need to keep
any extra locks in the XDR callbacks.

The NFS client XDR code only writes into private objects, whereas all reads
of shared objects are confined to fields that do not change, such as
filehandles...

Ditto for lockd, the NFSv2/v3 client mount code, and rpcbind.

The nfsd XDR code may require the BKL, but since it does a synchronous RPC
call from a thread that already holds the lock, that issue is moot.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-23 15:21:31 -05:00
David S. Miller
eb14f01959 Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
Conflicts:

	drivers/net/e1000e/ich8lan.c
2008-12-15 20:03:50 -08:00
Ilpo Järvinen
b1721d2bb9 rpc/rdma: goto instead of copypaste
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-14 23:19:48 -08:00
Roel Kluin
5eaa65b240 net: Make static
Sparse asked whether these could be static.

Signed-off-by: Roel Kluin <roel.kluin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-10 15:18:31 -08:00
James Morris
ec98ce480a Merge branch 'master' into next
Conflicts:
	fs/nfsd/nfs4recover.c

Manually fixed above to use new creds API functions, e.g.
nfs4_save_creds().

Signed-off-by: James Morris <jmorris@namei.org>
2008-12-04 17:16:36 +11:00
Linus Torvalds
2433c41789 Merge branch 'for-2.6.28' of git://linux-nfs.org/~bfields/linux
* 'for-2.6.28' of git://linux-nfs.org/~bfields/linux:
  NLM: client-side nlm_lookup_host() should avoid matching on srcaddr
  nfsd: use of unitialized list head on error exit in nfs4recover.c
  Add a reference to sunrpc in svc_addsock
  nfsd: clean up grace period on early exit
2008-12-03 16:40:37 -08:00
Ingo Molnar
ff0db0490a sunrpc: fix warning in net/sunrpc/xprtrdma/verbs.c
fix this warning:

  net/sunrpc/xprtrdma/verbs.c: In function ‘rpcrdma_conn_upcall’:
  net/sunrpc/xprtrdma/verbs.c:279: warning: unused variable ‘addr’

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-25 16:58:42 -08:00
Ingo Molnar
ed72b9c6e0 sunrpc: fix warning in net/sunrpc/xprtrdma/svc_rdma_transport.c
this warning:

  net/sunrpc/xprtrdma/svc_rdma_transport.c: In function ‘svc_rdma_accept’:
  net/sunrpc/xprtrdma/svc_rdma_transport.c:830: warning: ‘dma_mr_acc’ may be used uninitialized in this function

triggers because GCC does not recognize the (correct) flow connection
between need_dma_mr and dma_mr_acc.

Annotate it.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-25 16:49:37 -08:00
Tom Tucker
2da2c21d75 Add a reference to sunrpc in svc_addsock
The svc_addsock function adds transport instances without taking a
reference on the sunrpc.ko module, however, the generic transport
destruction code drops a reference when a transport instance
is destroyed.

Add a try_module_get call to the svc_addsock function for transport
instances added by this function.

Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Tested-by: Jeff Moyer <jmoyer@redhat.com>
2008-11-24 10:15:01 -06:00
David S. Miller
6ab33d5171 Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
Conflicts:

	drivers/net/ixgbe/ixgbe_main.c
	include/net/mac80211.h
	net/phonet/af_phonet.c
2008-11-20 16:44:00 -08:00
Trond Myklebust
23918b0306 SUNRPC: Fix a performance regression in the RPC authentication code
Fix a regression reported by Max Kellermann whereby kernel profiling
showed that his clients were spending 45% of their time in
rpcauth_lookup_credcache.

It turns out that although his processes had identical uid/gid/groups,
generic_match() was failing to detect this, because the task->group_info
pointers were not shared. This again lead to the creation of a huge number
of identical credentials at the RPC layer.

The regression is fixed by comparing the contents of task->group_info
if the actual pointers are not identical.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-11-20 13:17:40 -08:00
David Howells
86a264abe5 CRED: Wrap current->cred and a few other accessors
Wrap current->cred and a few other accessors to hide their actual
implementation.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: James Morris <jmorris@namei.org>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: James Morris <jmorris@namei.org>
2008-11-14 10:39:18 +11:00
David Howells
b6dff3ec5e CRED: Separate task security context from task_struct
Separate the task security context from task_struct.  At this point, the
security data is temporarily embedded in the task_struct with two pointers
pointing to it.

Note that the Alpha arch is altered as it refers to (E)UID and (E)GID in
entry.S via asm-offsets.

With comment fixes Signed-off-by: Marc Dionne <marc.c.dionne@gmail.com>

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: James Morris <jmorris@namei.org>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: James Morris <jmorris@namei.org>
2008-11-14 10:39:16 +11:00
David Howells
8f4194026b CRED: Wrap task credential accesses in the SunRPC protocol
Wrap access to task credentials so that they can be separated more easily from
the task_struct during the introduction of COW creds.

Change most current->(|e|s|fs)[ug]id to current_(|e|s|fs)[ug]id().

Change some task->e?[ug]id to task_e?[ug]id().  In some places it makes more
sense to use RCU directly rather than a convenient wrapper; these will be
addressed by later patches.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: James Morris <jmorris@namei.org>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: J. Bruce Fields <bfields@fieldses.org>
Cc: Neil Brown <neilb@suse.de>
Cc: linux-nfs@vger.kernel.org
Signed-off-by: James Morris <jmorris@namei.org>
2008-11-14 10:39:09 +11:00
David S. Miller
e0db4a786b sunrpc: Fix build warning due to typo in %pI4 format changes.
Noticed by Stephen Hemminger.

Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-02 23:57:06 -08:00
Harvey Harrison
21454aaad3 net: replace NIPQUAD() in net/*/
Using NIPQUAD() with NIPQUAD_FMT, %d.%d.%d.%d or %u.%u.%u.%u
can be replaced with %pI4

Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-31 00:54:56 -07:00
David S. Miller
a1744d3bee Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
Conflicts:

	drivers/net/wireless/p54/p54common.c
2008-10-31 00:17:34 -07:00
Harvey Harrison
5b095d9892 net: replace %p6 with %pI6
Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-29 12:52:50 -07:00
Harvey Harrison
4b7a4274ca net: replace %#p6 format specifier with %pi6
gcc warns when using the # modifier with the %p format specifier,
so we can't use this to omit the colons when needed, introduces
%pi6 instead.

Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-29 12:50:24 -07:00
Harvey Harrison
b189db5d29 net: remove NIP6(), NIP6_FMT, NIP6_SEQFMT and final users
Open code NIP6_FMT in the one call inside sscanf and one user
of NIP6() that could use %p6 in the netfilter code.

Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-28 23:02:38 -07:00
Harvey Harrison
fdb46ee752 net, misc: replace uses of NIP6_FMT with %p6
Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-28 23:02:32 -07:00
Harvey Harrison
b071195deb net: replace all current users of NIP6_SEQFMT with %#p6
The define in kernel.h can be done away with at a later time.

Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-28 16:05:40 -07:00
Trond Myklebust
5f707eb429 SUNRPC: Fix potential race in put_rpccred()
We have to be careful when we try to unhash the credential in
put_rpccred(), because we're not holding the credcache lock, so the call to
rpcauth_unhash_cred() may fail if someone else has looked the cred up, and
obtained a reference to it.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-28 15:21:42 -04:00
Trond Myklebust
eac0d18d44 SUNRPC: Fix rpcauth_prune_expired
We need to make sure that we don't remove creds from the cred_unused list
if they are still under the moratorium, or else they will never get
garbage collected.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-28 15:21:41 -04:00
Trond Myklebust
2a9e1cfa23 SUNRPC: Respond promptly to server TCP resets
If the server sends us an RST error while we're in the TCP_ESTABLISHED
state, then that will not result in a state change, and so the RPC client
ends up hanging forever (see
http://bugzilla.kernel.org/show_bug.cgi?id=11154)

We can intercept the reset by setting up an sk->sk_error_report callback,
which will then allow us to initiate a proper shutdown and retry...

We also make sure that if the send request receives an ECONNRESET, then we
shutdown too...

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-28 15:21:39 -04:00
Linus Torvalds
b225ee5bed Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6:
  net: Remove CONFIG_KMOD from net/ (towards removing CONFIG_KMOD entirely)
  ipv4: Add a missing rcu_assign_pointer() in routing cache.
  [netdrvr] ibmtr: PCMCIA IBMTR is ok on 64bit
  xen-netfront: Avoid unaligned accesses to IP header
  lmc: copy_*_user under spinlock
  [netdrvr] myri10ge, ixgbe: remove broken select INTEL_IOATDMA
2008-10-17 08:58:52 -07:00
Johannes Berg
95a5afca4a net: Remove CONFIG_KMOD from net/ (towards removing CONFIG_KMOD entirely)
Some code here depends on CONFIG_KMOD to not try to load
protocol modules or similar, replace by CONFIG_MODULES
where more than just request_module depends on CONFIG_KMOD
and and also use try_then_request_module in ebtables.

Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-16 15:24:51 -07:00
Trond Myklebust
6925bac120 Merge branch 'next' 2008-10-15 15:54:56 -04:00
Linus Torvalds
8acd3a60bc Merge branch 'for-2.6.28' of git://linux-nfs.org/~bfields/linux
* 'for-2.6.28' of git://linux-nfs.org/~bfields/linux: (59 commits)
  svcrdma: Fix IRD/ORD polarity
  svcrdma: Update svc_rdma_send_error to use DMA LKEY
  svcrdma: Modify the RPC reply path to use FRMR when available
  svcrdma: Modify the RPC recv path to use FRMR when available
  svcrdma: Add support to svc_rdma_send to handle chained WR
  svcrdma: Modify post recv path to use local dma key
  svcrdma: Add a service to register a Fast Reg MR with the device
  svcrdma: Query device for Fast Reg support during connection setup
  svcrdma: Add FRMR get/put services
  NLM: Remove unused argument from svc_addsock() function
  NLM: Remove "proto" argument from lockd_up()
  NLM: Always start both UDP and TCP listeners
  lockd: Remove unused fields in the nlm_reboot structure
  lockd: Add helper to sanity check incoming NOTIFY requests
  lockd: change nlmclnt_grant() to take a "struct sockaddr *"
  lockd: Adjust nlmsvc_lookup_host() to accomodate AF_INET6 addresses
  lockd: Adjust nlmclnt_lookup_host() signature to accomodate non-AF_INET
  lockd: Support non-AF_INET addresses in nlm_lookup_host()
  NLM: Convert nlm_lookup_host() to use a single argument
  svcrdma: Add Fast Reg MR Data Types
  ...
2008-10-14 12:31:14 -07:00
Alan Cox
113aa838ec net: Rationalise email address: Network Specific Parts
Clean up the various different email addresses of mine listed in the code
to a single current and valid address. As Dave says his network merges
for 2.6.28 are now done this seems a good point to send them in where
they won't risk disrupting real changes.

Signed-off-by: Alan Cox <alan@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-13 19:01:08 -07:00
Tom Talpey
c055551e97 RPC/RDMA: ensure connection attempt is complete before signalling.
The RPC/RDMA connection logic could return early from reconnection
attempts, leading to additional spurious retries.

Signed-off-by: Tom Talpey <talpey@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:15:06 -04:00
Tom Talpey
08ca0dce1e RPC/RDMA: correct the reconnect timer backoff
The RPC/RDMA code had a constant 5-second reconnect backoff, and
always performed it, even when re-establishing a connection to a
server after the RPC layer closed it due to being idle. Make it
an geometric backoff (up to 30 seconds), and don't delay idle
reconnect.

Signed-off-by: Tom Talpey <talpey@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:15:02 -04:00
Tom Talpey
b3cd8d45a7 RPC/RDMA: optionally emit useful transport info upon connect/disconnect.
Signed-off-by: Tom Talpey <talpey@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:13:59 -04:00
Tom Talpey
5f37d561e0 RPC/RDMA: reformat a debug printk to keep lines together.
The send marshaling code split a particular dprintk across two
lines, which makes it hard to extract from logfiles.

Signed-off-by: Tom Talpey <talpey@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:13:42 -04:00
Tom Talpey
5675add36e RPC/RDMA: harden connection logic against missing/late rdma_cm upcalls.
Add defensive timeouts to wait_for_completion() calls in RDMA
address resolution, and make them interruptible. Fix the timeout
units to milliseconds (formerly jiffies) and move to private header.

Signed-off-by: Tom Talpey <talpey@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:13:31 -04:00
Tom Talpey
1a954051b0 RPC/RDMA: fix connect/reconnect resource leak.
The RPC/RDMA code can leak RDMA connection manager endpoints in
certain error cases on connect. Don't signal unwanted events,
and be certain to destroy any allocated qp.

Signed-off-by: Tom Talpey <talpey@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:13:02 -04:00
Tom Talpey
926449ba66 RPC/RDMA: return a consistent error, when connect fails.
The xprt_connect call path does not expect such errors as ECONNREFUSED
to be returned from failed transport connection attempts, otherwise it
translates them to EIO and signals fatal errors. For example, mount.nfs
prints simply "internal error". Translate all such errors to ENOTCONN
from RPC/RDMA to match sockets behavior.

Signed-off-by: Tom Talpey <talpey@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:12:44 -04:00
Tom Talpey
9191ca3b38 RPC/RDMA: adhere to protocol for unpadded client trailing write chunks.
The RPC/RDMA protocol allows clients and servers to avoid RDMA
operations for data which is purely the result of XDR padding.
On the client, automatically insert the necessary padding for
such server replies, and optionally don't marshal such chunks.

Signed-off-by: Tom Talpey <talpey@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:12:33 -04:00
Tom Talpey
fee08caf94 RPC/RDMA: avoid an oops due to disconnect racing with async upcalls.
RDMA disconnects yield an upcall from the RDMA connection manager,
which can race with rpc transport close, e.g. on ^C of a mount.
Ensure any rdma cm_id and qp are fully destroyed before continuing.

Signed-off-by: Tom Talpey <talpey@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:11:40 -04:00
Tom Talpey
ad0e9e01da RPC/RDMA: maintain the RPC task bytes-sent statistic.
Signed-off-by: Tom Talpey <talpey@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:10:40 -04:00
Tom Talpey
575448bd36 RPC/RDMA: suppress retransmit on RPC/RDMA clients.
An RPC/RDMA client cannot retransmit on an unbroken connection,
doing so violates its flow control with the server.

Signed-off-by: Tom Talpey <talpey@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:10:36 -04:00
Tom Tucker
b334eaabf4 RPC/RDMA: fix connection IRD/ORD setting
This logic sets the connection parameter that configures the local device
and informs the remote peer how many concurrent incoming RDMA_READ
requests are supported. The original logic didn't really do what was
intended for two reasons:

- The max number supported by the device is typically smaller than
any one factor in the calculation used, and

- The field in the connection parameter structure where the value is
stored is a u8 and always overflows for the default settings.

So what really happens is the value requested for responder resources
is the left over 8 bits from the "desired value". If the desired value
happened to be a multiple of 256, the result was zero and it wouldn't
connect at all.

Given the above and the fact that max_requests is almost always larger
than the max responder resources supported by the adapter, this patch
simplifies this logic and simply requests the max supported by the device,
subject to a reasonable limit.

This bug was found by Jim Schutt at Sandia.

Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Acked-by: Tom Talpey <talpey@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:09:56 -04:00
Tom Talpey
3197d309f5 RPC/RDMA: support FRMR client memory registration.
Configure, detect and use "fastreg" support from IB/iWARP verbs
layer to perform RPC/RDMA memory registration.

Make FRMR the default memreg mode (will fall back if not supported
by the selected RDMA adapter).

This allows full and optimal operation over the cxgb3 adapter, and others.

Signed-off-by: Tom Talpey <talpey@netapp.com>
Acked-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:09:34 -04:00
Tom Talpey
bd7ed1d133 RPC/RDMA: check selected memory registration mode at runtime.
At transport creation, check for, and use, any local dma lkey.
Then, check that the selected memory registration mode is in fact
supported by the RDMA adapter selected for the mount. Fall back
to best alternative if not.

Signed-off-by: Tom Talpey <talpey@netapp.com>
Acked-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:09:26 -04:00
Tom Talpey
fe9053b30b RPC/RDMA: add data types and new FRMR memory registration enum.
Internal RPC/RDMA structure updates in preparation for FRMR support.

Signed-off-by: Tom Talpey <talpey@netapp.com>
Acked-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:09:24 -04:00
Tom Talpey
8d4ba0347c RPC/RDMA: refactor the inline memory registration code.
Refactor the memory registration and deregistration routines.
This saves stack space, makes the code more readable and prepares
to add the new FRMR registration methods.

Signed-off-by: Tom Talpey <talpey@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-10 15:09:16 -04:00
J. Bruce Fields
107e0008df Merge branch 'from-tomtucker' into for-2.6.28 2008-10-08 18:22:18 -04:00
Cedric Le Goater
63ffc23d30 sunrpc: fix oops in rpc_create when the mount namespace is unshared
On a system with nfs mounts, if a task unshares its mount namespace,
a oops can occur when the system is rebooted if the task is the last
to unreference the nfs mount. It will try to create a rpc request
using utsname() which has been invalidated by free_nsproxy().

The patch fixes the issue by using the global init_utsname() which is
always valid. the capability of identifying rpc clients per uts namespace
stills needs some extra work so this should not be a problem.

BUG: unable to handle kernel NULL pointer dereference at 00000004
IP: [<c024c9ab>] rpc_create+0x332/0x42f
Oops: 0000 [#1] DEBUG_PAGEALLOC

Pid: 1857, comm: uts-oops Not tainted (2.6.27-rc5-00319-g7686ad5 #4)
EIP: 0060:[<c024c9ab>] EFLAGS: 00210287 CPU: 0
EIP is at rpc_create+0x332/0x42f
EAX: 00000000 EBX: df26adf0 ECX: c0251887 EDX: 00000001
ESI: df26ae58 EDI: c02f293c EBP: dda0fc9c ESP: dda0fc2c
 DS: 007b ES: 007b FS: 0000 GS: 0000 SS: 0068
Process uts-oops (pid: 1857, ti=dda0e000 task=dd9a0778 task.ti=dda0e000)
Stack: c0104532 dda0fffc dda0fcac dda0e000 dda0e000 dd93b7f0 00000009 c02f2880
       df26aefc dda0fc68 c01096b7 00000000 c0266ee0 c039a070 c039a070 dda0fc74
       c012ca67 c039a064 dda0fc8c c012cb20 c03daf74 00000011 00000000 c0275c90
Call Trace:
 [<c0104532>] ? dump_trace+0xc2/0xe2
 [<c01096b7>] ? save_stack_trace+0x1c/0x3a
 [<c012ca67>] ? save_trace+0x37/0x8c
 [<c012cb20>] ? add_lock_to_list+0x64/0x96
 [<c0256fc4>] ? rpcb_register_call+0x62/0xbb
 [<c02570c8>] ? rpcb_register+0xab/0xb3
 [<c0252f4d>] ? svc_register+0xb4/0x128
 [<c0253114>] ? svc_destroy+0xec/0x103
 [<c02531b2>] ? svc_exit_thread+0x87/0x8d
 [<c01a75cd>] ? lockd_down+0x61/0x81
 [<c01a577b>] ? nlmclnt_done+0xd/0xf
 [<c01941fe>] ? nfs_destroy_server+0x14/0x16
 [<c0194328>] ? nfs_free_server+0x4c/0xaa
 [<c019a066>] ? nfs_kill_super+0x23/0x27
 [<c0158585>] ? deactivate_super+0x3f/0x51
 [<c01695d1>] ? mntput_no_expire+0x95/0xb4
 [<c016965b>] ? release_mounts+0x6b/0x7a
 [<c01696cc>] ? __put_mnt_ns+0x62/0x70
 [<c0127501>] ? free_nsproxy+0x25/0x80
 [<c012759a>] ? switch_task_namespaces+0x3e/0x43
 [<c01275a9>] ? exit_task_namespaces+0xa/0xc
 [<c0117fed>] ? do_exit+0x4fd/0x666
 [<c01181b3>] ? do_group_exit+0x5d/0x83
 [<c011fa8c>] ? get_signal_to_deliver+0x2c8/0x2e0
 [<c0102630>] ? do_notify_resume+0x69/0x700
 [<c011d85a>] ? do_sigaction+0x134/0x145
 [<c0127205>] ? hrtimer_nanosleep+0x8f/0xce
 [<c0126d1a>] ? hrtimer_wakeup+0x0/0x1c
 [<c0103488>] ? work_notifysig+0x13/0x1b
 =======================
Code: 70 20 68 cb c1 2c c0 e8 75 4e 01 00 8b 83 ac 00 00 00 59 3d 00 f0 ff ff 5f 77 63 eb 57 a1 00 80 2d c0 8b 80 a8 02 00 00 8d 73 68 <8b> 40 04 83 c0 45 e8 41 46 f7 ff ba 20 00 00 00 83 f8 21 0f 4c
EIP: [<c024c9ab>] rpc_create+0x332/0x42f SS:ESP 0068:dda0fc2c

Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: "Serge E. Hallyn" <serue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-07 18:19:10 -04:00
Trond Myklebust
96165e2b7c SUNRPC: Fix a memory leak in rpcb_getport_async
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-07 18:18:57 -04:00
Trond Myklebust
9a4bd29fe8 SUNRPC: Fix autobind on cloned rpc clients
Despite the fact that cloned rpc clients won't have the cl_autobind flag
set, they may still find themselves calling rpcb_getport_async(). For this
to happen, it suffices for a _parent_ rpc_clnt to use autobinding, in which
case any clone may find itself triggering the !xprt_bound() case in
call_bind().

The correct fix for this is to walk back up the tree of cloned rpc clients,
in order to find the parent that 'owns' the transport, either because it
has clnt->cl_autobind set, or because it originally created the
transport...

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-07 18:18:53 -04:00
Denis V. Lunev
c9f6cde6e2 sunrpc: do not pin sunrpc module in the memory
Basically, try_module_get here are pretty useless. Any other module using
this API will pin sunrpc in memory due using exported symbols.

Signed-off-by: Denis V. Lunev <den@openvz.org>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-10-07 18:14:54 -04:00