linux-stable.git/net/sunrpc, branch v3.16.35

sunrpc/cache: drop reference when sunrpc_cache_pipe_upcall() detects a race

2016-04-30T22:06:01+00:00

commit a6ab1e8126d205238defbb55d23661a3a5c6a0d8 upstream.

sunrpc_cache_pipe_upcall() can detect a race if CACHE_PENDING is no longer
set.  In this case it aborts the queuing of the upcall.
However it has already taken a new counted reference on "h" and
doesn't "put" it, even though it frees the data structure holding the reference.

So let's delay the "cache_get" until we know we need it.

Fixes: f9e1aedc6c79 ("sunrpc/cache: remove races with queuing an upcall.")
Signed-off-by: NeilBrown 
Signed-off-by: J. Bruce Fields 
Signed-off-by: Ben Hutchings

sunrpc/cache: fix off-by-one in qword_get()

2016-03-08T12:15:29+00:00

commit b7052cd7bcf3c1478796e93e3dff2b44c9e82943 upstream.

The qword_get() function NUL-terminates its output buffer.  If the input
string is in hex format \xXXXX... and the same length as the output
buffer, there is an off-by-one:

  int qword_get(char **bpp, char *dest, int bufsize)
  {
      ...
      while (len < bufsize) {
          ...
          *dest++ = (h << 4) | l;
          len++;
      }
      ...
      *dest = '\0';
      return len;
  }

This patch ensures the NUL terminator doesn't fall outside the output
buffer.

Signed-off-by: Stefan Hajnoczi 
Signed-off-by: J. Bruce Fields 
Signed-off-by: Luis Henriques

SUNRPC: Fix callback channel

2016-01-11T10:50:19+00:00

commit 756b9b37cfb2e3dc76b2e43a8c097402ac736e07 upstream.

The NFSv4.1 callback channel is currently broken because the receive
message will keep shrinking because the backchannel receive buffer size
never gets reset.
The easiest solution to this problem is instead of changing the receive
buffer, to rather adjust the copied request.

Fixes: 38b7631fbe42 ("nfs4: limit callback decoding to received bytes")
Cc: Benjamin Coddington 
Signed-off-by: Trond Myklebust 
Signed-off-by: Luis Henriques

nfs4: limit callback decoding to received bytes

2016-01-11T10:50:19+00:00

commit 38b7631fbe42e6e247e9fc9879f961b14a687e3b upstream.

A truncated cb_compound request will cause the client to decode null or
data from a previous callback for nfs4.1 backchannel case, or uninitialized
data for the nfs4.0 case. This is because the path through
svc_process_common() advances the request's iov_base and decrements iov_len
without adjusting the overall xdr_buf's len field.  That causes
xdr_init_decode() to set up the xdr_stream with an incorrect length in
nfs4_callback_compound().

Fixing this for the nfs4.1 backchannel case first requires setting the
correct iov_len and page_len based on the length of received data in the
same manner as the nfs4.0 case.

Then the request's xdr_buf length can be adjusted for both cases based upon
the remaining iov_len and page_len.

Signed-off-by: Benjamin Coddington 
Signed-off-by: Trond Myklebust 
Signed-off-by: Luis Henriques

xprtrdma: Re-arm after missed events

2015-12-13T17:49:41+00:00

commit 7b3d770c67bc07db5035999e4f864c5f2ff7b10e upstream.

ib_req_notify_cq(IB_CQ_REPORT_MISSED_EVENTS) returns a positive
value if WCs were added to a CQ after the last completion upcall
but before the CQ has been re-armed.

Commit 7f23f6f6e388 ("xprtrmda: Reduce lock contention in
completion handlers") assumed that when ib_req_notify_cq() returned
a positive RC, the CQ had also been successfully re-armed, making
it safe to return control to the provider without losing any
completion signals. That is an invalid assumption.

Change both completion handlers to continue polling while
ib_req_notify_cq() returns a positive value.

Fixes: 7f23f6f6e388 ("xprtrmda: Reduce lock contention in ...")
Signed-off-by: Chuck Lever 
Reviewed-by: Sagi Grimberg 
Reviewed-by: Devesh Sharma 
Tested-By: Devesh Sharma 
Signed-off-by: Anna Schumaker 
Signed-off-by: Luis Henriques

svcrdma: handle rdma read with a non-zero initial page offset

2015-10-30T13:59:27+00:00

commit c91aed9896946721bb30705ea2904edb3725dd61 upstream.

The server rdma_read_chunk_lcl() and rdma_read_chunk_frmr() functions
were not taking into account the initial page_offset when determining
the rdma read length.  This resulted in a read who's starting address
and length exceeded the base/bounds of the frmr.

The server gets an async error from the rdma device and kills the
connection, and the client then reconnects and resends.  This repeats
indefinitely, and the application hangs.

Most work loads don't tickle this bug apparently, but one test hit it
every time: building the linux kernel on a 16 core node with 'make -j
16 O=/mnt/0' where /mnt/0 is a ramdisk mounted via NFSRDMA.

This bug seems to only be tripped with devices having small fastreg page
list depths.  I didn't see it with mlx4, for instance.

Fixes: 0bf4828983df ('svcrdma: refactor marshalling logic')
Signed-off-by: Steve Wise 
Tested-by: Chuck Lever 
Signed-off-by: J. Bruce Fields 
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques

svcrdma: Fix send_reply() scatter/gather set-up

2015-09-30T12:20:36+00:00

commit 9d11b51ce7c150a69e761e30518f294fc73d55ff upstream.

The Linux NFS server returns garbage in the data payload of inline
NFS/RDMA READ replies. These are READs of under 1000 bytes or so
where the client has not provided either a reply chunk or a write
list.

The NFS server delivers the data payload for an NFS READ reply to
the transport in an xdr_buf page list. If the NFS client did not
provide a reply chunk or a write list, send_reply() is supposed to
set up a separate sge for the page containing the READ data, and
another sge for XDR padding if needed, then post all of the sges via
a single SEND Work Request.

The problem is send_reply() does not advance through the xdr_buf
when setting up scatter/gather entries for SEND WR. It always calls
dma_map_xdr with xdr_off set to zero. When there's more than one
sge, dma_map_xdr() sets up the SEND sge's so they all point to the
xdr_buf's head.

The current Linux NFS/RDMA client always provides a reply chunk or
a write list when performing an NFS READ over RDMA. Therefore, it
does not exercise this particular case. The Linux server has never
had to use more than one extra sge for building RPC/RDMA replies
with a Linux client.

However, an NFS/RDMA client _is_ allowed to send small NFS READs
without setting up a write list or reply chunk. The NFS READ reply
fits entirely within the inline reply buffer in this case. This is
perhaps a more efficient way of performing NFS READs that the Linux
NFS/RDMA client may some day adopt.

Fixes: b432e6b3d9c1 ('svcrdma: Change DMA mapping logic to . . .')
BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=285
Signed-off-by: Chuck Lever 
Signed-off-by: J. Bruce Fields 
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques

SUNRPC: Fix a memory leak in the backchannel code

2015-07-15T09:00:17+00:00

commit 88de6af24f2b48b06c514d3c3d0a8f22fafe30bd upstream.

req->rq_private_buf isn't initialised when xprt_setup_backchannel calls
xprt_free_allocation.

Fixes: fb7a0b9addbdb ("nfs41: New backchannel helper routines")
Signed-off-by: Trond Myklebust 
Signed-off-by: Luis Henriques

svcrpc: fix potential GSSX_ACCEPT_SEC_CONTEXT decoding failures

2015-05-28T08:59:59+00:00

commit 9507271d960a1911a51683888837d75c171cd91f upstream.

In an environment where the KDC is running Active Directory, the
exported composite name field returned in the context could be large
enough to span a page boundary.  Attaching a scratch buffer to the
decoding xdr_stream helps deal with those cases.

The case where we saw this was actually due to behavior that's been
fixed in newer gss-proxy versions, but we're fixing it here too.

Signed-off-by: Scott Mayhew 
Reviewed-by: Simo Sorce 
Signed-off-by: J. Bruce Fields 
Signed-off-by: Luis Henriques

xprtrdma: Free the pd if ib_query_qp() fails

2015-05-20T12:26:24+00:00

commit 5ae711a24601257f395c1f8746ac95be0cbd75e5 upstream.

If ib_query_qp() fails or the memory registration mode isn't
supported, don't leak the PD. An orphaned IB/core resource will
cause IB module removal to hang.

Fixes: bd7ed1d13304 ("RPC/RDMA: check selected memory registration ...")
Signed-off-by: Chuck Lever 
Reviewed-by: Steve Wise 
Signed-off-by: Anna Schumaker 
Signed-off-by: Luis Henriques