Close-to-open cache consistency rules really only require us to flush out
writes on calls to close(), and require us to revalidate attributes on the
very last close of the file.

Currently we appear to be doing a lot of extra attribute revalidation
and cache flushes.
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

NFS appears to be returning an unnecessary "delete" notification when
we're doing an atomic rename. See

  http://bugzilla.gnome.org/show_bug.cgi?id=575684

The fix is to get rid of the redundant call to d_delete().
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

Move the definition of nfs_need_commit() into the #ifdef CONFIG_NFS_V3
section as originally intended in the patch "NFS: cleanup - remove
struct nfs_inode->ncommit"
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

printk formats in prior commit were reversed/incorrect.
Compiled without warning on x86 and x86_64, but detected on ppc.
Signed-off-by: NTom Talpey <tmtalpey@gmail.com>
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

As long as one task is holding the socket lock, then calls to
xprt_force_disconnect(xprt) will not succeed in shutting down the socket.
In particular, this would mean that a server initiated shutdown will not
succeed until the lock is relinquished.
In order to avoid the deadlock, we should ensure that xs_tcp_send_request()
closes the socket on EPIPE errors too.
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

This fixes a regression against FreeBSD servers as reported by Tomas
Kasparek. Apparently when using RPC over a TCP socket, the FreeBSD servers
don't ever react to the client closing the socket, and so commit
e06799f9 (SUNRPC: Use shutdown() instead of
close() when disconnecting a TCP socket) causes the setup to hang forever
whenever the client attempts to close and then reconnect.

We break the deadlock by adding a 'linger2' style timeout to the socket,
after which, the client will abort the connection using a TCP 'RST'.

The default timeout is set to 15 seconds. A subsequent patch will put it
under user control by means of a systctl.
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

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: NTrond Myklebust <Trond.Myklebust@netapp.com>

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: NTrond Myklebust <Trond.Myklebust@netapp.com>

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: NTrond Myklebust <Trond.Myklebust@netapp.com>

Ensure that we pick up and handle socket errors as they occur.
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

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: NTrond Myklebust <Trond.Myklebust@netapp.com>

Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

...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: NTrond Myklebust <Trond.Myklebust@netapp.com>

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: NTrond Myklebust <Trond.Myklebust@netapp.com>

When mounting an NFS/RDMA server with the "-o proto=rdma" or
"-o rdma" options, attempt to dynamically load the necessary
"xprtrdma" client transport module. Doing so improves usability,
while avoiding a static module dependency and any unnecesary
resources.
Signed-off-by: NTom Talpey <tmtalpey@gmail.com>
Cc: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

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: NTom Talpey <tmtalpey@gmail.com>
Cc: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

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: NTom Talpey <tmtalpey@gmail.com>
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

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: NTom Talpey <tmtalpey@gmail.com>
Cc: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

Bryan Wu reports that when compiling NFS on nommu machines he gets a
"defined but not used" error on nfs_file_mmap().

The easiest fix is simply to get rid of the special casing in NFS, and
just always call generic_file_mmap() to set up the file.
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

The following patch is a combination of a patch by myself and Peter
Staubach.

Trond: If we allow other processes to dirty pages while a process is doing
a consistency sync to disk, we can end up never making progress.

Peter: Attached is a patch which addresses a continuing problem with
the NFS client generating out of order WRITE requests.  While
this is compliant with all of the current protocol
specifications, there are servers in the market which can not
handle out of order WRITE requests very well.  Also, this may
lead to sub-optimal block allocations in the underlying file
system on the server.  This may cause the read throughputs to
be reduced when reading the file from the server.

Peter: There has been a lot of work recently done to address out of
order issues on a systemic level.  However, the NFS client is
still susceptible to the problem.  Out of order WRITE
requests can occur when pdflush is in the middle of writing
out pages while the process dirtying the pages calls
generic_file_buffered_write which calls
generic_perform_write which calls
balance_dirty_pages_rate_limited which ends up calling
writeback_inodes which ends up calling back into the NFS
client to writes out dirty pages for the same file that
pdflush happens to be working with.
Signed-off-by: NPeter Staubach <staubach@redhat.com>
[modification by Trond to merge the two similar patches]
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

Certain asynchronous operations such as write() do not expect
(or care) that other metadata such as the file owner, mode, acls, ...
change. All they want to do is update and/or check the change attribute,
ctime, and mtime.
By skipping the file owner and group update, we also avoid having to do a
potential idmapper upcall for these asynchronous RPC calls.
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

Fix a bug whereby we would fail to create a mount point for a referral.
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

There is no point in using anything other than umode_t, since we copy the
content pretty much directly into inode->i_mode.
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

We don't need the bitmap[] field anymore, since the 'valid' field tells us
all we need to know about which attributes were filled in...
Also move the pre-op attributes in order to improve the structure packing.
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

Currently, filling struct nfs_fattr is more or less an all or nothing
operation, since NFSv2 and NFSv3 have only mandatory attributes.
In NFSv4, some attributes are optional, and so we may simply not be able to
fill in those fields. Furthermore, NFSv4 allows you to specify which
attributes you are interested in retrieving, thus permitting you to
optimise away retrieval of attributes that you know will no change...
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

There is no need to fail or retry a SETATTR call just because the post-op
GETATTR failed.
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

If cached directory contents becomes incorrect, there is no way to
flush the contents.  This contrasts with files where file locking is
the recommended way to ensure cache consistency between multiple
applications (a read-lock always flushes the cache).

Also while changes to files often change the size of the file (thus
triggering a cache flush), changes to directories often do not change
the apparent size (as the size is often rounded to a block size).

So it is particularly important with directories to avoid the
possibility of an incorrect cache wherever possible.

When the link count on a directory changes it implies a change in the
number of child directories, and so a change in the contents of this
directory.  So use that as a trigger to flush cached contents.

When the ctime changes but the mtime does not, there are two possible
reasons.
 1/ The owner/mode information has been changed.
 2/ utimes has been used to set the mtime backwards.

In the first case, a data-cache flush is not required.
In the second case it is.

So on the basis that correctness trumps performance, flush the
directory contents cache in this case also.
Signed-off-by: NNeilBrown <neilb@suse.de>
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

Remove redundant NFS_STALE() check, a leftover due to the commit
691beb13Signed-off-by: NSuresh Jayaraman <sjayaraman@suse.de>
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

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: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

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: NTrond Myklebust <Trond.Myklebust@netapp.com>

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: NTrond Myklebust <Trond.Myklebust@netapp.com>

Addresses: http://bugzilla.kernel.org/show_bug.cgi?id=11061

sockaddr structures can't be reliably compared using memcmp() because
there are padding bytes in the structure which can't be guaranteed to
be the same even when the sockaddr structures refer to the same
socket. Instead compare all the relevant fields. In the case of IPv6
sin6_flowinfo is not compared because it only affects QoS and
sin6_scope_id is only compared if the address is "link local" because
"link local" addresses need only be unique to a specific link.
Signed-off-by: NIan Dall <ian@beware.dropbear.id.au>
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

Hi Trond,

I have been looking at a bugreport where trying to open applications on KDE
on a NFS mounted home fails temporarily. There have been multiple reports on
different kernel versions pointing to this common issue:
http://bugzilla.kernel.org/show_bug.cgi?id=12557
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/269954
http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=508866.html

This issue can be reproducible consistently by doing this on a NFS mounted
home (KDE):
1. Open 2 xterm sessions
2. From one of the xterm session, do "ssh -X <remote host>"
3. "stat ~/.Xauthority" on the remote SSH session
4. Close the two xterm sessions
5. On the server do a "stat ~/.Xauthority"
6. Now on the client, try to open xterm
This will fail.

Even if the filehandle had become stale, the NFS client should invalidate
the cache/inode and should repeat LOOKUP. Looking at the packet capture when
the failure occurs shows that there were two subsequent ACCESS() calls with
the same filehandle and both fails with -ESTALE error.

I have tested the fix below. Now the client issue a LOOKUP after the
ACCESS() call fails with -ESTALE. If all this makes sense to you, can you
consider this for inclusion?

Thanks,


If the server returns an -ESTALE error due to stale filehandle in response to
an ACCESS() call, we need to invalidate the cache and inode so that LOOKUP()
can be retried. Without this change, the nfs client retries ACCESS() with the
same filehandle, fails again and could lead to temporary failure of
applications running on nfs mounted home.
Signed-off-by: NSuresh Jayaraman <sjayaraman@suse.de>
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

The NFS mount command may pass an AF_INET server address to lockd.  If
lockd happens to be using a PF_INET6 listener, the nlm_cmp_addr() in
nlmclnt_grant() will fail to match requests from that host because they
will all have a mapped IPv4 AF_INET6 address.

Adopt the same solution used in nfs_sockaddr_match_ipaddr() for NFSv4
callbacks: if either address is AF_INET, map it to an AF_INET6 address
before doing the comparison.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

Clean up/micro-optimatization:  Make the AF_INET-only version of
nlm_cmp_addr() smaller.  This matches the style of
nlm_privileged_requester(), and makes the AF_INET-only version of
nlm_cmp_addr() nearly the same size as it was before IPv6 support.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>