Commit Graph

271 Commits

Author SHA1 Message Date
Trond Myklebust
a6b31d18b0 SUNRPC: Fix a data corruption issue when retransmitting RPC calls
The following scenario can cause silent data corruption when doing
NFS writes. It has mainly been observed when doing database writes
using O_DIRECT.

1) The RPC client uses sendpage() to do zero-copy of the page data.
2) Due to networking issues, the reply from the server is delayed,
   and so the RPC client times out.

3) The client issues a second sendpage of the page data as part of
   an RPC call retransmission.

4) The reply to the first transmission arrives from the server
   _before_ the client hardware has emptied the TCP socket send
   buffer.
5) After processing the reply, the RPC state machine rules that
   the call to be done, and triggers the completion callbacks.
6) The application notices the RPC call is done, and reuses the
   pages to store something else (e.g. a new write).

7) The client NIC drains the TCP socket send buffer. Since the
   page data has now changed, it reads a corrupted version of the
   initial RPC call, and puts it on the wire.

This patch fixes the problem in the following manner:

The ordering guarantees of TCP ensure that when the server sends a
reply, then we know that the _first_ transmission has completed. Using
zero-copy in that situation is therefore safe.
If a time out occurs, we then send the retransmission using sendmsg()
(i.e. no zero-copy), We then know that the socket contains a full copy of
the data, and so it will retransmit a faithful reproduction even if the
RPC call completes, and the application reuses the O_DIRECT buffer in
the meantime.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@vger.kernel.org
2013-11-08 17:19:15 -05:00
Trond Myklebust
a1311d87fa SUNRPC: Cleanup xs_destroy()
There is no longer any need for a separate xs_local_destroy() helper.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-10-31 09:31:17 -04:00
NeilBrown
93dc41bdc5 SUNRPC: close a rare race in xs_tcp_setup_socket.
We have one report of a crash in xs_tcp_setup_socket.
The call path to the crash is:

  xs_tcp_setup_socket -> inet_stream_connect -> lock_sock_nested.

The 'sock' passed to that last function is NULL.

The only way I can see this happening is a concurrent call to
xs_close:

  xs_close -> xs_reset_transport -> sock_release -> inet_release

inet_release sets:
   sock->sk = NULL;
inet_stream_connect calls
   lock_sock(sock->sk);
which gets NULL.

All calls to xs_close are protected by XPRT_LOCKED as are most
activations of the workqueue which runs xs_tcp_setup_socket.
The exception is xs_tcp_schedule_linger_timeout.

So presumably the timeout queued by the later fires exactly when some
other code runs xs_close().

To protect against this we can move the cancel_delayed_work_sync()
call from xs_destory() to xs_close().

As xs_close is never called from the worker scheduled on
->connect_worker, this can never deadlock.

Signed-off-by: NeilBrown <neilb@suse.de>
[Trond: Make it safe to call cancel_delayed_work_sync() on AF_LOCAL sockets]
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-10-31 09:14:50 -04:00
J. Bruce Fields
e3bfab1848 sunrpc: comment typo fix
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-10-28 18:16:54 -04:00
Trond Myklebust
8b71798c0d SUNRPC: Only update the TCP connect cookie on a successful connect
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-10-01 18:22:10 -04:00
Trond Myklebust
7f260e8575 SUNRPC: Enable the keepalive option for TCP sockets
For NFSv4 we want to avoid retransmitting RPC calls unless the TCP
connection breaks. However we still want to detect TCP connection
breakage as soon as possible. Do this by setting the keepalive option
with the idle timeout and count set to the 'timeo' and 'retrans' mount
options.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-10-01 18:22:10 -04:00
Linus Torvalds
bf97293eb8 NFS client updates for Linux 3.12
Highlights include:
 
 - Fix NFSv4 recovery so that it doesn't recover lost locks in cases such as
   lease loss due to a network partition, where doing so may result in data
   corruption. Add a kernel parameter to control choice of legacy behaviour
   or not.
 - Performance improvements when 2 processes are writing to the same file.
 - Flush data to disk when an RPCSEC_GSS session timeout is imminent.
 - Implement NFSv4.1 SP4_MACH_CRED state protection to prevent other
   NFS clients from being able to manipulate our lease and file lockingr
   state.
 - Allow sharing of RPCSEC_GSS caches between different rpc clients
 - Fix the broken NFSv4 security auto-negotiation between client and server
 - Fix rmdir() to wait for outstanding sillyrename unlinks to complete
 - Add a tracepoint framework for debugging NFSv4 state recovery issues.
 - Add tracing to the generic NFS layer.
 - Add tracing for the SUNRPC socket connection state.
 - Clean up the rpc_pipefs mount/umount event management.
 - Merge more patches from Chuck in preparation for NFSv4 migration support.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.14 (GNU/Linux)
 
 iQIcBAABAgAGBQJSLelVAAoJEGcL54qWCgDyo2IQAKOfRJyZVnf4ipxi3xLNl1QF
 w/70DVSIF1S1djWN7G3vgkxj/R8KCvJ8CcvkAD2BEgRDeZJ9TtyKAdM/jYLZ+W05
 7k2QKk8fkwZmc1Y2qDqFwKHzP5ZgP5L2nGx7FNhi/99wEAe47yFG3qd3rUWKrcOf
 mnd863zgGDE2Q10slhoq/bywwMJo6tKZNeaIE8kPjgFbBEh/jslpAWr8dSA4QgvJ
 nZ8VB5XU8L+XJ0GpHHdjYm9LvQ51DbQ6omOF+0P4fI093azKmf4ZsrjMDWT8+iu3
 XkXlnQmKLGTi7yB43hHtn2NiRqwGzCcZ1Amo9PpCFaHUt1RP9cc37UhG1T+x1xWJ
 STEKDbvCdQ3FU9FvbgrGEwBR0e8fNS4fZY3ToDBflIcfwre0aWs5RCodZMUD0nUI
 4wY5J9NsQR/bL+v8KeUR4V4cXK8YrgL0zB4u4WYzH5Npxr5KD0NEKDNqRPhrB9l2
 LLF9Haql8j76Ff0ek6UGFIZjDE0h6Fs71wLBpLj+ZWArOJ7vBuLMBSOVqNpld9+9
 f2fEG7qoGF4FGTY4myH/eakMPaWnk9Ol4Ls/svSIapJ9+rePD+a93e/qnmdofIMf
 4TuEYk6ERib1qXgaeDRQuCsm2YE1Co5skGMaOsRFWgReE1c12QoJQVst2nMtEKp3
 uV2w8LgX18aZOZXJVkCM
 =ZuW+
 -----END PGP SIGNATURE-----

Merge tag 'nfs-for-3.12-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

   - Fix NFSv4 recovery so that it doesn't recover lost locks in cases
     such as lease loss due to a network partition, where doing so may
     result in data corruption.  Add a kernel parameter to control
     choice of legacy behaviour or not.
   - Performance improvements when 2 processes are writing to the same
     file.
   - Flush data to disk when an RPCSEC_GSS session timeout is imminent.
   - Implement NFSv4.1 SP4_MACH_CRED state protection to prevent other
     NFS clients from being able to manipulate our lease and file
     locking state.
   - Allow sharing of RPCSEC_GSS caches between different rpc clients.
   - Fix the broken NFSv4 security auto-negotiation between client and
     server.
   - Fix rmdir() to wait for outstanding sillyrename unlinks to complete
   - Add a tracepoint framework for debugging NFSv4 state recovery
     issues.
   - Add tracing to the generic NFS layer.
   - Add tracing for the SUNRPC socket connection state.
   - Clean up the rpc_pipefs mount/umount event management.
   - Merge more patches from Chuck in preparation for NFSv4 migration
     support"

* tag 'nfs-for-3.12-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (107 commits)
  NFSv4: use mach cred for SECINFO_NO_NAME w/ integrity
  NFS: nfs_compare_super shouldn't check the auth flavour unless 'sec=' was set
  NFSv4: Allow security autonegotiation for submounts
  NFSv4: Disallow security negotiation for lookups when 'sec=' is specified
  NFSv4: Fix security auto-negotiation
  NFS: Clean up nfs_parse_security_flavors()
  NFS: Clean up the auth flavour array mess
  NFSv4.1 Use MDS auth flavor for data server connection
  NFS: Don't check lock owner compatability unless file is locked (part 2)
  NFS: Don't check lock owner compatibility in writes unless file is locked
  nfs4: Map NFS4ERR_WRONG_CRED to EPERM
  nfs4.1: Add SP4_MACH_CRED write and commit support
  nfs4.1: Add SP4_MACH_CRED stateid support
  nfs4.1: Add SP4_MACH_CRED secinfo support
  nfs4.1: Add SP4_MACH_CRED cleanup support
  nfs4.1: Add state protection handler
  nfs4.1: Minimal SP4_MACH_CRED implementation
  SUNRPC: Replace pointer values with task->tk_pid and rpc_clnt->cl_clid
  SUNRPC: Add an identifier for struct rpc_clnt
  SUNRPC: Ensure rpc_task->tk_pid is available for tracepoints
  ...
2013-09-09 09:19:15 -07:00
Trond Myklebust
40b5ea0c25 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>
2013-09-04 12:26:31 -04:00
Eric Dumazet
64dc61306c net: add sk_stream_is_writeable() helper
Several call sites use the hardcoded following condition :

sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)

Lets use a helper because TCP_NOTSENT_LOWAT support will change this
condition for TCP sockets.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-07-24 17:54:48 -07:00
Linus Torvalds
0ff08ba5d0 Merge branch 'for-3.11' of git://linux-nfs.org/~bfields/linux
Pull nfsd changes from Bruce Fields:
 "Changes this time include:

   - 4.1 enabled on the server by default: the last 4.1-specific issues
     I know of are fixed, so we're not going to find the rest of the
     bugs without more exposure.
   - Experimental support for NFSv4.2 MAC Labeling (to allow running
     selinux over NFS), from Dave Quigley.
   - Fixes for some delicate cache/upcall races that could cause rare
     server hangs; thanks to Neil Brown and Bodo Stroesser for extreme
     debugging persistence.
   - Fixes for some bugs found at the recent NFS bakeathon, mostly v4
     and v4.1-specific, but also a generic bug handling fragmented rpc
     calls"

* 'for-3.11' of git://linux-nfs.org/~bfields/linux: (31 commits)
  nfsd4: support minorversion 1 by default
  nfsd4: allow destroy_session over destroyed session
  svcrpc: fix failures to handle -1 uid's
  sunrpc: Don't schedule an upcall on a replaced cache entry.
  net/sunrpc: xpt_auth_cache should be ignored when expired.
  sunrpc/cache: ensure items removed from cache do not have pending upcalls.
  sunrpc/cache: use cache_fresh_unlocked consistently and correctly.
  sunrpc/cache: remove races with queuing an upcall.
  nfsd4: return delegation immediately if lease fails
  nfsd4: do not throw away 4.1 lock state on last unlock
  nfsd4: delegation-based open reclaims should bypass permissions
  svcrpc: don't error out on small tcp fragment
  svcrpc: fix handling of too-short rpc's
  nfsd4: minor read_buf cleanup
  nfsd4: fix decoding of compounds across page boundaries
  nfsd4: clean up nfs4_open_delegation
  NFSD: Don't give out read delegations on creates
  nfsd4: allow client to send no cb_sec flavors
  nfsd4: fail attempts to request gss on the backchannel
  nfsd4: implement minimal SP4_MACH_CRED
  ...
2013-07-11 10:17:13 -07:00
Joe Perches
fe2c6338fd net: Convert uses of typedef ctl_table to struct ctl_table
Reduce the uses of this unnecessary typedef.

Done via perl script:

$ git grep --name-only -w ctl_table net | \
  xargs perl -p -i -e '\
	sub trim { my ($local) = @_; $local =~ s/(^\s+|\s+$)//g; return $local; } \
        s/\b(?<!struct\s)ctl_table\b(\s*\*\s*|\s+\w+)/"struct ctl_table " . trim($1)/ge'

Reflow the modified lines that now exceed 80 columns.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-13 02:36:09 -07:00
J. Bruce Fields
2fccbd9cc0 sunrpc: server back channel needs no rpcbind method
XPRT_BOUND is set on server backchannel xprts by xs_setup_bc_tcp()
(using xprt_set_bound()), and is never cleared, so ->rpcbind() will
never need to be called.

Reported-by: "Myklebust, Trond" <Trond.Myklebust@netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2013-05-15 09:27:02 -04:00
J. Bruce Fields
7073ea8799 SUNRPC: attempt AF_LOCAL connect on setup
In the gss-proxy case, setup time is when I know I'll have the right
namespace for the connect.

In other cases, it might be useful to get any connection errors
earlier--though actually in practice it doesn't make any difference for
rpcbind.

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2013-04-26 11:41:25 -04:00
J. Bruce Fields
c85b03ab20 Merge Trond's nfs-for-next
Merging Trond's nfs-for-next branch, mainly to get
b7993cebb8 "SUNRPC: Allow rpc_create() to
request that TCP slots be unlimited", which a small piece of the
gss-proxy work depends on.
2013-04-26 11:37:43 -04:00
Trond Myklebust
b7993cebb8 SUNRPC: Allow rpc_create() to request that TCP slots be unlimited
This is mainly for use by NFSv4.1, where the session negotiation
ultimately wants to decide how many RPC slots we can fill.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-04-14 12:26:03 -04:00
Trond Myklebust
3ed5e2a2c3 SUNRPC: Report network/connection errors correctly for SOFTCONN rpc tasks
In the case of a SOFTCONN rpc task, we really want to ensure that it
reports errors like ENETUNREACH back to the caller. Currently, only
some of these errors are being reported back (connect errors are not),
and they are being converted by the RPC layer into EIO.

Reported-by: Jan Engelhardt <jengelh@inai.de>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-03-25 12:04:10 -04:00
J. Bruce Fields
190b1ecf25 sunrpc: don't attempt to cancel unitialized work
As of dc107402ae "SUNRPC: make AF_LOCAL connect synchronous", we no longer initialize connect_worker in the
AF_LOCAL case, resulting in warnings like:

    WARNING: at lib/debugobjects.c:261 debug_print_object+0x8c/0xb0() Hardware name: Bochs
    ODEBUG: assert_init not available (active state 0) object type: timer_list hint: stub_timer+0x0/0x20
    Modules linked in: iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi nfsd auth_rpcgss nfs_acl lockd sunrpc
    Pid: 4816, comm: nfsd Tainted: G        W    3.8.0-rc2-00049-gdc10740 #801
    Call Trace:
     [<ffffffff8156ec00>] ? free_obj_work+0x60/0xa0
     [<ffffffff81046aaf>] warn_slowpath_common+0x7f/0xc0
     [<ffffffff81046ba6>] warn_slowpath_fmt+0x46/0x50
     [<ffffffff8156eccc>] debug_print_object+0x8c/0xb0
     [<ffffffff81055030>] ? timer_debug_hint+0x10/0x10
     [<ffffffff8156f7e3>] debug_object_assert_init+0xe3/0x120
     [<ffffffff81057ebb>] del_timer+0x2b/0x80
     [<ffffffff8109c4e6>] ? mark_held_locks+0x86/0x110
     [<ffffffff81065a29>] try_to_grab_pending+0xd9/0x150
     [<ffffffff81065b57>] __cancel_work_timer+0x27/0xc0
     [<ffffffff81065c03>] cancel_delayed_work_sync+0x13/0x20
     [<ffffffffa0007067>] xs_destroy+0x27/0x80 [sunrpc]
     [<ffffffffa00040d8>] xprt_destroy+0x78/0xa0 [sunrpc]
     [<ffffffffa0006241>] xprt_put+0x21/0x30 [sunrpc]
     [<ffffffffa00030cf>] rpc_free_client+0x10f/0x1a0 [sunrpc]
     [<ffffffffa0002ff3>] ? rpc_free_client+0x33/0x1a0 [sunrpc]
     [<ffffffffa0002f7e>] rpc_release_client+0x6e/0xb0 [sunrpc]
     [<ffffffffa000325d>] rpc_shutdown_client+0xfd/0x1b0 [sunrpc]
     [<ffffffffa0017196>] rpcb_put_local+0x106/0x130 [sunrpc]
    ...

Acked-by: "Myklebust, Trond" <Trond.Myklebust@netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2013-03-09 12:43:42 -05:00
Linus Torvalds
b6669737d3 Merge branch 'for-3.9' of git://linux-nfs.org/~bfields/linux
Pull nfsd changes from J Bruce Fields:
 "Miscellaneous bugfixes, plus:

   - An overhaul of the DRC cache by Jeff Layton.  The main effect is
     just to make it larger.  This decreases the chances of intermittent
     errors especially in the UDP case.  But we'll need to watch for any
     reports of performance regressions.

   - Containerized nfsd: with some limitations, we now support
     per-container nfs-service, thanks to extensive work from Stanislav
     Kinsbursky over the last year."

Some notes about conflicts, since there were *two* non-data semantic
conflicts here:

 - idr_remove_all() had been added by a memory leak fix, but has since
   become deprecated since idr_destroy() does it for us now.

 - xs_local_connect() had been added by this branch to make AF_LOCAL
   connections be synchronous, but in the meantime Trond had changed the
   calling convention in order to avoid a RCU dereference.

There were a couple of more obvious actual source-level conflicts due to
the hlist traversal changes and one just due to code changes next to
each other, but those were trivial.

* 'for-3.9' of git://linux-nfs.org/~bfields/linux: (49 commits)
  SUNRPC: make AF_LOCAL connect synchronous
  nfsd: fix compiler warning about ambiguous types in nfsd_cache_csum
  svcrpc: fix rpc server shutdown races
  svcrpc: make svc_age_temp_xprts enqueue under sv_lock
  lockd: nlmclnt_reclaim(): avoid stack overflow
  nfsd: enable NFSv4 state in containers
  nfsd: disable usermode helper client tracker in container
  nfsd: use proper net while reading "exports" file
  nfsd: containerize NFSd filesystem
  nfsd: fix comments on nfsd_cache_lookup
  SUNRPC: move cache_detail->cache_request callback call to cache_read()
  SUNRPC: remove "cache_request" argument in sunrpc_cache_pipe_upcall() function
  SUNRPC: rework cache upcall logic
  SUNRPC: introduce cache_detail->cache_request callback
  NFS: simplify and clean cache library
  NFS: use SUNRPC cache creation and destruction helper for DNS cache
  nfsd4: free_stid can be static
  nfsd: keep a checksum of the first 256 bytes of request
  sunrpc: trim off trailing checksum before returning decrypted or integrity authenticated buffer
  sunrpc: fix comment in struct xdr_buf definition
  ...
2013-02-28 18:02:55 -08:00
J. Bruce Fields
dc107402ae SUNRPC: make AF_LOCAL connect synchronous
It doesn't appear that anyone actually needs to connect asynchronously.

Also, using a workqueue for the connect means we lose the namespace
information from the original process.  This is a problem since there's
no way to explicitly pass in a filesystem namespace for resolution of an
AF_LOCAL address.

Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2013-02-28 09:47:17 -08:00
Jeff Layton
5976687a2b sunrpc: move address copy/cmp/convert routines and prototypes from clnt.h to addr.h
These routines are used by server and client code, so having them in a
separate header would be best.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2013-02-05 09:41:14 -05:00
Trond Myklebust
6a24dfb645 SUNRPC: Pass pointers to struct rpc_xprt to the congestion window
Avoid access to task->tk_xprt

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-02-01 10:13:47 -05:00
Trond Myklebust
3dc0da278e SUNRPC: Fix an RCU dereference in xs_local_rpcbind
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-02-01 10:13:47 -05:00
Trond Myklebust
1b092092bf SUNRPC: Pass a pointer to struct rpc_xprt to the connect callback
Avoid another RCU dereference by passing the pointer to struct rpc_xprt
from the caller.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-02-01 10:13:47 -05:00
Trond Myklebust
a4f0835c60 SUNRPC: Eliminate task->tk_xprt accesses that bypass rcu_dereference()
tk_xprt is just a shortcut for tk_client->cl_xprt, however cl_xprt is
defined as an __rcu variable. Replace dereferences of tk_xprt with
non-rcu dereferences where it is safe to do so.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-02-01 10:13:47 -05:00
Trond Myklebust
1efc28780b SUNRPC: variable 'svsk' is unused in function bc_send_request
Silence a compile time warning.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2012-12-15 17:05:57 -05:00
Trond Myklebust
4a20a988f7 SUNRPC: Handle ECONNREFUSED in xs_local_setup_socket
Silence the unnecessary warning "unhandled error (111) connecting to..."
and convert it to a dprintk for debugging purposes.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2012-12-15 17:02:29 -05:00
Weston Andros Adamson
b8a13d039c SUNRPC: remove BUG_ON from bc_malloc
Replace BUG_ON() with WARN_ON_ONCE() and NULL return - the caller will handle
this like a memory allocation failure.

Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2012-11-04 14:43:42 -05:00
Weston Andros Adamson
1b7a181907 SUNRPC: remove BUG_ONs from *_reclassify_socket*
Replace multiple BUG_ON() calls with WARN_ON_ONCE() and early return when
sanity checking socket ownership (lock). The bind call will fail if the
socket was unsuccessfully reclassified.

Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2012-11-04 14:43:41 -05:00
Trond Myklebust
f878b657ce SUNRPC: Get rid of the xs_error_report socket callback
Chris Perl reports that we're seeing races between the wakeup call in
xs_error_report and the connect attempts. Basically, Chris has shown
that in certain circumstances, the call to xs_error_report causes the
rpc_task that is responsible for reconnecting to wake up early, thus
triggering a disconnect and retry.

Since the sk->sk_error_report() calls in the socket layer are always
followed by a tcp_done() in the cases where we care about waking up
the rpc_tasks, just let the state_change callbacks take responsibility
for those wake ups.

Reported-by: Chris Perl <chris.perl@gmail.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@vger.kernel.org
Tested-by: Chris Perl <chris.perl@gmail.com>
2012-10-24 10:46:15 -04:00
Trond Myklebust
4bc1e68ed6 SUNRPC: Prevent races in xs_abort_connection()
The call to xprt_disconnect_done() that is triggered by a successful
connection reset will trigger another automatic wakeup of all tasks
on the xprt->pending rpc_wait_queue. In particular it will cause an
early wake up of the task that called xprt_connect().

All we really want to do here is clear all the socket-specific state
flags, so we split that functionality out of xs_sock_mark_closed()
into a helper that can be called by xs_abort_connection()

Reported-by: Chris Perl <chris.perl@gmail.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@vger.kernel.org
Tested-by: Chris Perl <chris.perl@gmail.com>
2012-10-24 10:46:08 -04:00
Trond Myklebust
b9d2bb2ee5 Revert "SUNRPC: Ensure we close the socket on EPIPE errors too..."
This reverts commit 55420c24a0.
Now that we clear the connected flag when entering TCP_CLOSE_WAIT,
the deadlock described in this commit is no longer possible.
Instead, the resulting call to xs_tcp_shutdown() can interfere
with pending reconnection attempts.

Reported-by: Chris Perl <chris.perl@gmail.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@vger.kernel.org
Tested-by: Chris Perl <chris.perl@gmail.com>
2012-10-24 10:45:39 -04:00
Trond Myklebust
d0bea455dd SUNRPC: Clear the connect flag when socket state is TCP_CLOSE_WAIT
This is needed to ensure that we call xprt_connect() upon the next
call to call_connect().

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@vger.kernel.org
Tested-by: Chris Perl <chris.perl@gmail.com>
2012-10-24 10:44:49 -04:00
Trond Myklebust
d19751e7b9 SUNRPC: Get rid of the redundant xprt->shutdown bit field
It is only set after everyone has dereferenced the transport,
and serves no useful purpose: setting it is racy, so all the
socket code, etc still needs to be able to cope with the cases
where they miss reading it.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2012-09-28 16:03:05 -04:00
Bryan Schumaker
84e28a307e SUNRPC: Set alloc_slot for backchannel tcp ops
f39c1bfb5a (SUNRPC: Fix a UDP transport
regression) introduced the "alloc_slot" function for xprt operations,
but never created one for the backchannel operations.  This patch fixes
a null pointer dereference when mounting NFS over v4.1.

Call Trace:
 [<ffffffffa0207957>] ? xprt_reserve+0x47/0x50 [sunrpc]
 [<ffffffffa02023a4>] call_reserve+0x34/0x60 [sunrpc]
 [<ffffffffa020e280>] __rpc_execute+0x90/0x400 [sunrpc]
 [<ffffffffa020e61a>] rpc_async_schedule+0x2a/0x40 [sunrpc]
 [<ffffffff81073589>] process_one_work+0x139/0x500
 [<ffffffff81070e70>] ? alloc_worker+0x70/0x70
 [<ffffffffa020e5f0>] ? __rpc_execute+0x400/0x400 [sunrpc]
 [<ffffffff81073d1e>] worker_thread+0x15e/0x460
 [<ffffffff8145c839>] ? preempt_schedule+0x49/0x70
 [<ffffffff81073bc0>] ? rescuer_thread+0x230/0x230
 [<ffffffff81079603>] kthread+0x93/0xa0
 [<ffffffff81465d04>] kernel_thread_helper+0x4/0x10
 [<ffffffff81079570>] ? kthread_freezable_should_stop+0x70/0x70
 [<ffffffff81465d00>] ? gs_change+0x13/0x13

Signed-off-by: Bryan Schumaker <bjschuma@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2012-09-25 10:33:59 -04:00
Trond Myklebust
a519fc7a70 SUNRPC: Ensure that the TCP socket is closed when in CLOSE_WAIT
Instead of doing a shutdown() call, we need to do an actual close().
Ditto if/when the server is sending us junk RPC headers.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Tested-by: Simon Kirby <sim@hostway.ca>
Cc: stable@vger.kernel.org
2012-09-19 18:16:10 -04:00
Trond Myklebust
f39c1bfb5a SUNRPC: Fix a UDP transport regression
Commit 43cedbf0e8 (SUNRPC: Ensure that
we grab the XPRT_LOCK before calling xprt_alloc_slot) is causing
hangs in the case of NFS over UDP mounts.

Since neither the UDP or the RDMA transport mechanism use dynamic slot
allocation, we can skip grabbing the socket lock for those transports.
Add a new rpc_xprt_op to allow switching between the TCP and UDP/RDMA
case.

Note that the NFSv4.1 back channel assigns the slot directly
through rpc_run_bc_task, so we can ignore that case.

Reported-by: Dick Streefland <dick.streefland@altium.nl>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@vger.kernel.org [>= 3.1]
2012-09-07 11:43:49 -04:00
Linus Torvalds
ac694dbdbc Merge branch 'akpm' (Andrew's patch-bomb)
Merge Andrew's second set of patches:
 - MM
 - a few random fixes
 - a couple of RTC leftovers

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (120 commits)
  rtc/rtc-88pm80x: remove unneed devm_kfree
  rtc/rtc-88pm80x: assign ret only when rtc_register_driver fails
  mm: hugetlbfs: close race during teardown of hugetlbfs shared page tables
  tmpfs: distribute interleave better across nodes
  mm: remove redundant initialization
  mm: warn if pg_data_t isn't initialized with zero
  mips: zero out pg_data_t when it's allocated
  memcg: gix memory accounting scalability in shrink_page_list
  mm/sparse: remove index_init_lock
  mm/sparse: more checks on mem_section number
  mm/sparse: optimize sparse_index_alloc
  memcg: add mem_cgroup_from_css() helper
  memcg: further prevent OOM with too many dirty pages
  memcg: prevent OOM with too many dirty pages
  mm: mmu_notifier: fix freed page still mapped in secondary MMU
  mm: memcg: only check anon swapin page charges for swap cache
  mm: memcg: only check swap cache pages for repeated charging
  mm: memcg: split swapin charge function into private and public part
  mm: memcg: remove needless !mm fixup to init_mm when charging
  mm: memcg: remove unneeded shmem charge type
  ...
2012-07-31 19:25:39 -07:00
Linus Torvalds
6dbb35b0a7 NFS client updates for Linux 3.6
Features include:
 - Patches from Bryan to allow splitting of the NFSv2/v3/v4 code into
   separate modules.
 - Fix Oopses in the NFSv4 idmapper
 - Fix a deadlock whereby rpciod tries to allocate a new socket and
   ends up recursing into the NFS code due to memory reclaim.
 - Increase the number of permitted callback connections.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.12 (GNU/Linux)
 
 iQIcBAABAgAGBQJQGF+vAAoJEGcL54qWCgDy6ncP/jKVl/Yjz6i1b/8QtC0EmYFb
 XNwbjZicNupVM98XPLm+sfdWxvoGiHSMbwG8t/hx5Z6CteM18adeGNO1KqP9xQyg
 scPvFmqj5VJNHsHztcHIFHFYdpsuJqRKcW3TA2l8AkNOm6uBcnXArRosYN6LrXik
 hI/jWcyv8wZuooSQrLf463JK37t/s6LuUQo6jKP4582sbANHvPdLkHFCYg3yt1Sk
 2IIo2CLLs2cJUswGJnsHT76Jxfvh21NdGtvydjVjpr4H0/LY5GykBc23AAL9TWj6
 KlegDO902hLzEE93xazF59hQZrPuwBi3quEMJ3X0mjdNQWb4G96s/t2hmwpTjWyc
 mjpRsuaGlCXDxcrI5dnU52hqKa0Ju1ipbLpghxSVfilRy998xvGp5Yc6ADU+pYnt
 uP09lamCyjFEa+gDSqGt7lv4dFmdPJjWZdkXLPv0ah5sXVMYAT8NRLUfiE1+hLLu
 zKaM84PHSEvykFeJ2WvjDTgF3L55y3x6L3LN4UkKmfO5nqQf7csPcquU1NfHh25S
 jjKGq2SKGoYG1l6FwK3hemup5cnFUEX78E2QeLrmaHg92fJDGrz587i6MPc5jrSe
 sOSX/CpuCJd4VhodIo8T00me0GZSHEU7RP2KEc518ZvrPmz13avXeLeG9nYhjuxM
 cV9Ex8zh2Y4aiUXCy3uA
 =KSix
 -----END PGP SIGNATURE-----

Merge tag 'nfs-for-3.6-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull second wave of NFS client updates from Trond Myklebust:

 - Patches from Bryan to allow splitting of the NFSv2/v3/v4 code into
   separate modules.

 - Fix Oopses in the NFSv4 idmapper

 - Fix a deadlock whereby rpciod tries to allocate a new socket and ends
   up recursing into the NFS code due to memory reclaim.

 - Increase the number of permitted callback connections.

* tag 'nfs-for-3.6-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  nfs: explicitly reject LOCK_MAND flock() requests
  nfs: increase number of permitted callback connections.
  SUNRPC: return negative value in case rpcbind client creation error
  NFS: Convert v4 into a module
  NFS: Convert v3 into a module
  NFS: Convert v2 into a module
  NFS: Keep module parameters in the generic NFS client
  NFS: Split out remaining NFS v4 inode functions
  NFS: Pass super operations and xattr handlers in the nfs_subversion
  NFS: Only initialize the ACL client in the v3 case
  NFS: Create a try_mount rpc op
  NFS: Remove the NFS v4 xdev mount function
  NFS: Add version registering framework
  NFS: Fix a number of bugs in the idmapper
  nfs: skip commit in releasepage if we're freeing memory for fs-related reasons
  sunrpc: clarify comments on rpc_make_runnable
  pnfsblock: bail out partial page IO
2012-07-31 18:45:44 -07:00
Mel Gorman
a564b8f039 nfs: enable swap on NFS
Implement the new swapfile a_ops for NFS and hook up ->direct_IO.  This
will set the NFS socket to SOCK_MEMALLOC and run socket reconnect under
PF_MEMALLOC as well as reset SOCK_MEMALLOC before engaging the protocol
->connect() method.

PF_MEMALLOC should allow the allocation of struct socket and related
objects and the early (re)setting of SOCK_MEMALLOC should allow us to
receive the packets required for the TCP connection buildup.

[jlayton@redhat.com: Restore PF_MEMALLOC task flags in all cases]
[dfeng@redhat.com: Fix handling of multiple swap files]
[a.p.zijlstra@chello.nl: Original patch]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Paris <eparis@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Neil Brown <neilb@suse.de>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Xiaotian Feng <dfeng@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 18:42:48 -07:00
Jeff Layton
5cf02d09b5 nfs: skip commit in releasepage if we're freeing memory for fs-related reasons
We've had some reports of a deadlock where rpciod ends up with a stack
trace like this:

    PID: 2507   TASK: ffff88103691ab40  CPU: 14  COMMAND: "rpciod/14"
     #0 [ffff8810343bf2f0] schedule at ffffffff814dabd9
     #1 [ffff8810343bf3b8] nfs_wait_bit_killable at ffffffffa038fc04 [nfs]
     #2 [ffff8810343bf3c8] __wait_on_bit at ffffffff814dbc2f
     #3 [ffff8810343bf418] out_of_line_wait_on_bit at ffffffff814dbcd8
     #4 [ffff8810343bf488] nfs_commit_inode at ffffffffa039e0c1 [nfs]
     #5 [ffff8810343bf4f8] nfs_release_page at ffffffffa038bef6 [nfs]
     #6 [ffff8810343bf528] try_to_release_page at ffffffff8110c670
     #7 [ffff8810343bf538] shrink_page_list.clone.0 at ffffffff81126271
     #8 [ffff8810343bf668] shrink_inactive_list at ffffffff81126638
     #9 [ffff8810343bf818] shrink_zone at ffffffff8112788f
    #10 [ffff8810343bf8c8] do_try_to_free_pages at ffffffff81127b1e
    #11 [ffff8810343bf958] try_to_free_pages at ffffffff8112812f
    #12 [ffff8810343bfa08] __alloc_pages_nodemask at ffffffff8111fdad
    #13 [ffff8810343bfb28] kmem_getpages at ffffffff81159942
    #14 [ffff8810343bfb58] fallback_alloc at ffffffff8115a55a
    #15 [ffff8810343bfbd8] ____cache_alloc_node at ffffffff8115a2d9
    #16 [ffff8810343bfc38] kmem_cache_alloc at ffffffff8115b09b
    #17 [ffff8810343bfc78] sk_prot_alloc at ffffffff81411808
    #18 [ffff8810343bfcb8] sk_alloc at ffffffff8141197c
    #19 [ffff8810343bfce8] inet_create at ffffffff81483ba6
    #20 [ffff8810343bfd38] __sock_create at ffffffff8140b4a7
    #21 [ffff8810343bfd98] xs_create_sock at ffffffffa01f649b [sunrpc]
    #22 [ffff8810343bfdd8] xs_tcp_setup_socket at ffffffffa01f6965 [sunrpc]
    #23 [ffff8810343bfe38] worker_thread at ffffffff810887d0
    #24 [ffff8810343bfee8] kthread at ffffffff8108dd96
    #25 [ffff8810343bff48] kernel_thread at ffffffff8100c1ca

rpciod is trying to allocate memory for a new socket to talk to the
server. The VM ends up calling ->releasepage to get more memory, and it
tries to do a blocking commit. That commit can't succeed however without
a connected socket, so we deadlock.

Fix this by setting PF_FSTRANS on the workqueue task prior to doing the
socket allocation, and having nfs_release_page check for that flag when
deciding whether to do a commit call. Also, set PF_FSTRANS
unconditionally in rpc_async_schedule since that function can also do
allocations sometimes.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@vger.kernel.org
2012-07-30 18:55:59 -04:00
David S. Miller
60d354ebeb sunrpc: Don't do a dst_confirm() on an input routes.
xs_udp_data_ready() is operating on received packets, and tries to
do a dst_confirm() on the dst attached to the SKB.

This isn't right, dst confirmation is for output routes, not input
rights.  It's for resetting the timers on the nexthop neighbour entry
for the route, indicating that we've got good evidence that we've
successfully reached it.

Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-05 01:02:43 -07:00
J. Bruce Fields
92769108f5 sunrpc: skip portmap calls on sessions backchannel
There's obviously no point to doing portmap calls over the sessions
backchannel.

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2012-03-26 11:49:48 -04:00
Trond Myklebust
09acfea5d8 SUNRPC: Fix a few sparse warnings
net/sunrpc/svcsock.c:412:22: warning: incorrect type in assignment
(different address spaces)
 - svc_partial_recvfrom now takes a struct kvec, so the variable
   save_iovbase needs to be an ordinary (void *)

Make a bunch of variables in net/sunrpc/xprtsock.c static

Fix a couple of "warning: symbol 'foo' was not declared. Should it be
static?" reports.

Fix a couple of conflicting function declarations.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2012-03-11 19:30:02 -04:00
Andy Adamson
15a4520621 SUNRPC: add sending,pending queue and max slot to xprt stats
With static RPC slots, the xprt backlog queue stats were useful in showing
when the transport (TCP) was starved by lack of RPC slots. The new dynamic
RPC slot code, commit d9ba131d8f, always
provides an RPC slot and so only uses the xprt backlog queue when the
tcp_max_slot_table_entries value has been hit or when an allocation error
occurs. All requests are now placed on the xprt sending or pending queue which
need to be monitored for debugging.

The max_slot stat shows the maximum number of dynamic RPC slots reached which is
useful when debugging performance issues.

Add the new fields at the end of the mountstats xprt stanza so that mountstats
outputs the previous correct values and ignores the new fields. Bump
NFS_IOSTATS_VERS.

Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2012-02-16 14:55:27 -05:00
Trond Myklebust
24ca9a8477 SUNRPC: Ensure we return EAGAIN in xs_nospace if congestion is cleared
By returning '0' instead of 'EAGAIN' when the tests in xs_nospace() fail
to find evidence of socket congestion, we are making the RPC engine believe
that the message was incorrectly sent and so it disconnects the socket
instead of just retrying.

The bug appears to have been introduced by commit
5e3771ce2d (SUNRPC: Ensure that xs_nospace
return values are propagated).

Reported-by: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@vger.kernel.org [>= 2.6.30]
Tested-by: Andrew Cooper <andrew.cooper3@citrix.com>
2011-11-22 23:55:27 +02:00
Stanislav Kinsbursky
2aa13531bb SUNRPC: destroy freshly allocated transport in case of sockaddr init error
Otherwise we will leak xprt structure and struct net reference.

Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-11-10 14:50:07 -05:00
Trond Myklebust
d9ba131d8f SUNRPC: Support dynamic slot allocation for TCP connections
Allow the number of available slots to grow with the TCP window size.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-07-17 18:11:30 -04:00
Trond Myklebust
43cedbf0e8 SUNRPC: Ensure that we grab the XPRT_LOCK before calling xprt_alloc_slot
This throttles the allocation of new slots when the socket is busy
reconnecting and/or is out of buffer space.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-07-17 16:01:03 -04:00
Trond Myklebust
9e00abc3c2 SUNRPC: sunrpc should not explicitly depend on NFS config options
Change explicit references to CONFIG_NFS_V4_1 to implicit ones
Get rid of the unnecessary defines in backchannel_rqst.c and
bc_svc.c: the Makefile takes care of those dependency.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-07-15 09:12:23 -04:00
Chuck Lever
176e21ee2e SUNRPC: Support for RPC over AF_LOCAL transports
TI-RPC introduces the capability of performing RPC over AF_LOCAL
sockets.  It uses this mainly for registering and unregistering
local RPC services securely with the local rpcbind, but we could
also conceivably use it as a generic upcall mechanism.

This patch provides a client-side only implementation for the moment.
We might also consider a server-side implementation to provide
AF_LOCAL access to NLM (for statd downcalls, and such like).

Autobinding is not supported on kernel AF_LOCAL transports at this
time.  Kernel ULPs must specify the pathname of the remote endpoint
when an AF_LOCAL transport is created.  rpcbind supports registering
services available via AF_LOCAL, so the kernel could handle it with
some adjustment to ->rpcbind and ->set_port.  But we don't need this
feature for doing upcalls via well-known named sockets.

This has not been tested with ULPs that move a substantial amount of
data.  Thus, I can't attest to how robust the write_space and
congestion management logic is.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-05-27 17:42:47 -04:00