linux.git/net/sunrpc, branch v5.1-rc2

Merge tag 'nfs-for-5.1-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

2019-03-16T19:28:18+00:00

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

  Bugfixes:
   - Fix an Oops in SUNRPC back channel tracepoints
   - Fix a SUNRPC client regression when handling oversized replies
   - Fix the minimal size for SUNRPC reply buffer allocation
   - rpc_decode_header() must always return a non-zero value on error
   - Fix a typo in pnfs_update_layout()

  Cleanup:
   - Remove redundant check for the reply length in call_decode()"

* tag 'nfs-for-5.1-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  SUNRPC: Remove redundant check for the reply length in call_decode()
  SUNRPC: Handle the SYSTEM_ERR rpc error
  SUNRPC: rpc_decode_header() must always return a non-zero value on error
  SUNRPC: Use the ENOTCONN error on socket disconnect
  SUNRPC: Fix the minimal size for reply buffer allocation
  SUNRPC: Fix a client regression when handling oversized replies
  pNFS: Fix a typo in pnfs_update_layout
  fix null pointer deref in tracepoints in back channel

SUNRPC: Remove redundant check for the reply length in call_decode()

2019-03-15T17:11:36+00:00

Now that we're using the xdr_stream functions to decode the header,
the test for the minimum reply length is redundant.

Signed-off-by: Trond Myklebust

SUNRPC: Handle the SYSTEM_ERR rpc error

2019-03-15T17:11:02+00:00

Handle the SYSTEM_ERR rpc error by retrying the RPC call as if it
were a garbage argument.

Signed-off-by: Trond Myklebust

SUNRPC: rpc_decode_header() must always return a non-zero value on error

2019-03-15T17:08:59+00:00

Ensure that when the "garbage args" case falls through, we do set
an error of EIO.

Fixes: a0584ee9aed8 ("SUNRPC: Use struct xdr_stream when decoding...")
Signed-off-by: Trond Myklebust

SUNRPC: Use the ENOTCONN error on socket disconnect

2019-03-15T17:08:20+00:00

When the socket is closed, we currently send an EAGAIN error to all
pending requests in order to ask them to retransmit. Use ENOTCONN
instead, to ensure that they try to reconnect before attempting to
transmit.
This also helps SOFTCONN tasks to behave correctly in this
situation.

Signed-off-by: Trond Myklebust

SUNRPC: Fix the minimal size for reply buffer allocation

2019-03-15T17:06:35+00:00

We must at minimum allocate enough memory to be able to see any auth
errors in the reply from the server.

Fixes: 2c94b8eca1a26 ("SUNRPC: Use au_rslack when computing reply...")
Signed-off-by: Trond Myklebust

SUNRPC: Fix a client regression when handling oversized replies

2019-03-15T17:06:21+00:00

If the server sends a reply that is larger than the pre-allocated
buffer, then the current code may fail to register how much of
the stream that it has finished reading. This again can lead to
hangs.

Fixes: e92053a52e68 ("SUNRPC: Handle zero length fragments correctly")
Signed-off-by: Trond Myklebust

Merge tag 'nfsd-5.1' of git://linux-nfs.org/~bfields/linux

2019-03-12T22:06:54+00:00

Pull NFS server updates from Bruce Fields:
 "Miscellaneous NFS server fixes.

  Probably the most visible bug is one that could artificially limit
  NFSv4.1 performance by limiting the number of oustanding rpcs from a
  single client.

  Neil Brown also gets a special mention for fixing a 14.5-year-old
  memory-corruption bug in the encoding of NFSv3 readdir responses"

* tag 'nfsd-5.1' of git://linux-nfs.org/~bfields/linux:
  nfsd: allow nfsv3 readdir request to be larger.
  nfsd: fix wrong check in write_v4_end_grace()
  nfsd: fix memory corruption caused by readdir
  nfsd: fix performance-limiting session calculation
  svcrpc: fix UDP on servers with lots of threads
  svcrdma: Remove syslog warnings in work completion handlers
  svcrdma: Squelch compiler warning when SUNRPC_DEBUG is disabled
  svcrdma: Use struct_size() in kmalloc()
  svcrpc: fix unlikely races preventing queueing of sockets
  svcrpc: svc_xprt_has_something_to_do seems a little long
  SUNRPC: Don't allow compiler optimisation of svc_xprt_release_slot()
  nfsd: fix an IS_ERR() vs NULL check

SUNRPC: Take the transport send lock before binding+connecting

2019-03-10T18:08:19+00:00

Before trying to bind a port, ensure we grab the send lock to
ensure that we don't change the port while another task is busy
transmitting requests.
The connect code already takes the send lock in xprt_connect(),
but it is harmless to take it before that.

Signed-off-by: Trond Myklebust

SUNRPC: Micro-optimise when the task is known not to be sleeping

2019-03-10T18:08:19+00:00

In cases where we know the task is not sleeping, try to optimise
away the indirect call to task->tk_action() by replacing it with
a direct call.
Only change tail calls, to allow gcc to perform tail call
elimination.

Signed-off-by: Trond Myklebust