Rework the local RxRPC endpoint management.

Local endpoint objects are maintained in a flat list as before.  This
should be okay as there shouldn't be more than one per open AF_RXRPC socket
(there can be fewer as local endpoints can be shared if their local service
ID is 0 and they share the same local transport parameters).

Changes:

 (1) Local endpoints may now only be shared if they have local service ID 0
     (ie. they're not being used for listening).

     This prevents a scenario where process A is listening of the Cache
     Manager port and process B contacts a fileserver - which may then
     attempt to send CM requests back to B.  But if A and B are sharing a
     local endpoint, A will get the CM requests meant for B.

 (2) We use a mutex to handle lookups and don't provide RCU-only lookups
     since we only expect to access the list when opening a socket or
     destroying an endpoint.

     The local endpoint object is pointed to by the transport socket's
     sk_user_data for the life of the transport socket - allowing us to
     refer to it directly from the sk_data_ready and sk_error_report
     callbacks.

 (3) atomic_inc_not_zero() now exists and can be used to only share a local
     endpoint if the last reference hasn't yet gone.

 (4) We can remove rxrpc_local_lock - a spinlock that had to be taken with
     BH processing disabled given that we assume sk_user_data won't change
     under us.

 (5) The transport socket is shut down before we clear the sk_user_data
     pointer so that we can be sure that the transport socket's callbacks
     won't be invoked once the RCU destruction is scheduled.

 (6) Local endpoints have a work item that handles both destruction and
     event processing.  The means that destruction doesn't then need to
     wait for event processing.  The event queues can then be cleared after
     the transport socket is shut down.

 (7) Local endpoints are no longer available for resurrection beyond the
     life of the sockets that had them open.  As soon as their last ref
     goes, they are scheduled for destruction and may not have their usage
     count moved from 0.
Signed-off-by: David Howells <dhowells@redhat.com>

Separate local endpoint event handling out into its own file preparatory to
overhauling the object management aspect (which remains in the original
file).
Signed-off-by: David Howells <dhowells@redhat.com>

Use the peer record to distribute network errors rather than the transport
object (which I want to get rid of).  An error from a particular peer
terminates all calls on that peer.

For future consideration:

 (1) For ICMP-induced errors it might be worth trying to extract the RxRPC
     header from the offending packet, if one is returned attached to the
     ICMP packet, to better direct the error.

     This may be overkill, though, since an ICMP packet would be expected
     to be relating to the destination port, machine or network.  RxRPC
     ABORT and BUSY packets give notice at RxRPC level.

 (2) To also abort connection-level communications (such as CHALLENGE
     packets) where indicted by an error - but that requires some revamping
     of the connection event handling first.
Signed-off-by: David Howells <dhowells@redhat.com>

Do a little bit of tidying in the ICMP processing code.
Signed-off-by: David Howells <dhowells@redhat.com>

Don't assume anything about the address in an ICMP packet in
rxrpc_error_report() as the address may not be IPv4 in future, especially
since we're just printing these details.
Signed-off-by: David Howells <dhowells@redhat.com>

Break MTU determination from ICMP out into its own function to reduce the
complexity of the error report handler.
Signed-off-by: David Howells <dhowells@redhat.com>

Rename rxrpc_UDP_error_report() to rxrpc_error_report() as it might get
called for something other than UDP.
Signed-off-by: David Howells <dhowells@redhat.com>

Rework peer object handling to use a hash table instead of a flat list and
to use RCU.  Peer objects are no longer destroyed by passing them to a
workqueue to process, but rather are just passed to the RCU garbage
collector as kfree'able objects.

The hash function uses the local endpoint plus all the components of the
remote address, except for the RxRPC service ID.  Peers thus represent a
UDP port on the remote machine as contacted by a UDP port on this machine.

The RCU read lock is used to handle non-creating lookups so that they can
be called from bottom half context in the sk_error_report handler without
having to lock the hash table against modification.
rxrpc_lookup_peer_rcu() *does* take a reference on the peer object as in
the future, this will be passed to a work item for error distribution in
the error_report path and this function will cease being used in the
data_ready path.

Creating lookups are done under spinlock rather than mutex as they might be
set up due to an external stimulus if the local endpoint is a server.

Captured network error messages (ICMP) are handled with respect to this
struct and MTU size and RTT are cached here.
Signed-off-by: David Howells <dhowells@redhat.com>

This function is just ->init(), rename it to make it obvious.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

These should be gone when we removed CONFIG_NET_CLS_POLICE.
We can not totally remove them since they are exposed
to userspace.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Sowmini Varadhan says:

====================
RDS: multiple connection paths for scaling

Today RDS-over-TCP is implemented by demux-ing multiple PF_RDS sockets
between any 2 endpoints (where endpoint == [IP address, port]) over a
single TCP socket between the 2 IP addresses involved. This has the
limitation that it ends up funneling multiple RDS flows over a single
TCP flow, thus the rds/tcp connection is
   (a) upper-bounded to the single-flow bandwidth,
   (b) suffers from head-of-line blocking for the RDS sockets.

Better throughput (for a fixed small packet size, MTU) can be achieved
by having multiple TCP/IP flows per rds/tcp connection, i.e., multipathed
RDS (mprds).  Each such TCP/IP flow constitutes a path for the rds/tcp
connection. RDS sockets will be attached to a path based on some hash
(e.g., of local address and RDS port number) and packets for that RDS
socket will be sent over the attached path using TCP to segment/reassemble
RDS datagrams on that path.

The table below, generated using a prototype that implements mprds,
shows that this is significant for scaling to 40G.  Packet sizes
used were: 8K byte req, 256 byte resp. MTU: 1500.  The parameters for
RDS-concurrency used below are described in the rds-stress(1) man page-
the number listed is proportional to the number of threads at which max
throughput was attained.

  -------------------------------------------------------------------
     RDS-concurrency   Num of       tx+rx K/s (iops)       throughput
     (-t N -d N)       TCP paths
  -------------------------------------------------------------------
        16             1             600K -  700K            4 Gbps
        28             8            5000K - 6000K           32 Gbps
  -------------------------------------------------------------------

FAQ: what is the relation between mprds and mptcp?
  mprds is orthogonal to mptcp. Whereas mptcp creates
  sub-flows for a single TCP connection, mprds parallelizes tx/rx
  at the RDS layer. MPRDS with N paths will allow N datagrams to
  be sent in parallel; each path will continue to send one
  datagram at a time, with sender and receiver keeping track of
  the retransmit and dgram-assembly state based on the RDS header.
  If desired, mptcp can additionally be used to speed up each TCP
  path. That acceleration is orthogonal to the parallelization benefits
  of mprds.

This patch series lays down the foundational data-structures to support
mprds in the kernel. It implements the changes to split up the
rds_connection structure into a common (to all paths) part,
and a per-path rds_conn_path. All I/O workqs are driven from
the rds_conn_path.

Note that this patchset does not (yet) actually enable multipathing
for any of the transports; all transports will continue to use a
single path with the refactored data-structures. A subsequent patchset
will  add the changes to the rds-tcp module to actually use mprds
in rds-tcp.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Refactor rds_conn_destroy() so that the per-path dismantling
is done in rds_conn_path_destroy, and then iterate as needed
over rds_conn_path_destroy().
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This commit changes rds_conn_shutdown to take a rds_conn_path *
argument, allowing it to shutdown paths other than c_path[0] for
MP-capable transports.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add a for() loop in __rds_conn_create to initialize all the
conn_paths, in preparate for MP capable transports.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

rds_conn_path_error() is the MP-aware analog of rds_conn_error,
to be used by multipath-capable callers.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This commit updates the callbacks related to the rds-info command
so that they walk through all the rds_conn_path structures and
report the requested info.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

rds_conn_path_connect_if_down() works on the rds_conn_path
that it is passed. Callers who are not t_m_capable may continue
calling rds_conn_connect_if_down, which will invoke
rds_conn_path_connect_if_down() with the default c_path[0].
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This commit allows rds_send_pong() callers to send back
the rds pong message on some path other than c_path[0] by
passing in a struct rds_conn_path * argument.  It also
removes the last dependency on the #defines in rds_single.h
from send.c
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Explicitly set up rds_conn_path, either from i_conn_path (for
MP capable transpots) or as c_path[0], and use this in
rds_send_drop_to()
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Pass a struct rds_conn_path to rds_send_xmit so that MP capable
transports can transmit packets on something other than c_path[0].
The eventual goal for MP capable transports is to hash the rds
socket to a path based on the bound local address/port, and use
this path as the argument to rds_send_xmit()
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Pass the rds_conn_path to rds_send_queue_rm, and use it to initialize
the i_conn_path field in struct rds_incoming. This commit also makes
rds_send_queue_rm() MP capable, because it now takes locks
specific to the rds_conn_path passed in, instead of defaulting to
the c_path[0] based defines from rds_single_path.h
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The only caller of rds_send_get_message() was
rds_iw_send_cq_comp_handler() which was removed as part of
commit dcdede04 ("RDS: Drop stale iWARP RDMA transport"),
so remove rds_send_get_message() for the same reason.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

rds_send_path_drop_acked() is the path-specific version of
rds_send_drop_acked() to be invoked by MP capable callers.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

rds_send_path_reset() is the path specific version of rds_send_reset()
intended for MP capable callers.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

t_mp_capable transports can use rds_inc_path_init to initialize
all fields in struct rds_incoming, including the i_conn_path.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Transports that are t_mp_capable should set the rds_conn_path
on which the datagram was recived in the ->i_conn_path field
of struct rds_incoming.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The t_mp_capable bit will be used in the core rds module
to support multipathing logic when the transport supports it.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

In preparation for multipath RDS, split the rds_connection
structure into a base structure, and a per-path struct rds_conn_path.
The base structure tracks information and locks common to all
paths. The workqs for send/recv/shutdown etc are tracked per
rds_conn_path. Thus the workq callbacks now work with rds_conn_path.

This commit allows for one rds_conn_path per rds_connection, and will
be extended into multiple conn_paths in  subsequent commits.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Make sure that dctcp_get_info() returns only the size of the
info->dctcp struct that it zeroes out and fills in. Previously it had
been returning the size of the enclosing tcp_cc_info union,
sizeof(*info).  There is no problem yet, but that union that may one
day be larger than struct tcp_dctcp_info, in which case the
TCP_CC_INFO code might accidentally copy uninitialized bytes from the
stack.
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

Fix to return a negative error code from the error handling
case instead of 0, as done elsewhere in this function.
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Acked-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Merge tag 'rxrpc-rewrite-20160613' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs

David Howells says:

====================
rxrpc: Rename rxrpc source files

Here's the next part of the AF_RXRPC rewrite.  In this set I rename some of
the files in the net/rxrpc/ directory and adjust the Makefile and
ar-internal.h to reflect the changes.

The aim is twofold:

 (1) Remove the "ar-" prefix on those files that have it as it's not really
     useful, especially now that I'm building rxkad in.

 (2) To aid splitting the local, peer, connection and call handling code
     into separate files for object and event handling in future patches by
     making it easier to come up with new filenames.

There are two commits:

 (1) The first commit does a bunch of renames of .c files and alters the
     Makefile.  ar-internal.h isn't renamed at this time to avoid having to
     change the contents of the files being renamed.

 (2) The second commit changes the section label comments in ar-internal.h
     to reflect the changed filenames and reorders the file so that the
     sections are back in filename order.

The patches can be found here also:

	http://git.kernel.org/cgit/linux/kernel/git/dhowells/linux-fs.git/log/?h=rxrpc-rewrite

Tagged thusly:

	git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs.git
	rxrpc-rewrite-20160613
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

After the patchset about adding support of ACPI (commit id is 63434888)
being applied, HNS does not depend on OF. It depends on OF or ACPI, so
the Kconfig file needs to be updated.
Signed-off-by: Kejian Yan <yankejian@huawei.com>
Signed-off-by: Yisen Zhuang <Yisen.Zhuang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Hayes Wang says:

====================
r8152: code adjustment for PHY

These patches are for adjusting the code about PHY and setting speed.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

The user may change the speed. Use it to replace the default one.
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Move calling set_speed() from open() to rtl_hw_phy_work_func_t().
Then, we would set the default speed only for first initialization
or after resuming.

Besides, the set_speed() could handle the flag of PHY_RESET which
would be set in rtl_ops.hw_phy_cfg().
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Move the settings of PHY to a work queue and schedule it after
rtl_ops.init().

There are some reasons for this. First, the settings are only
needed for the first time initialization or after the power
down occurs.

Second, the settings are independent with the others.

Last, the settings may take more time than the others. Leave
they in probe() or open() may delay the following flows.
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

When skip_sw is set and hardware fails to apply filter, return error to
user. This will make error propagation logic similar to the one
currently used in u32 classifier.
Also, changed code to use tc_skip_sw() utility function.
Signed-off-by: Amir Vadai <amirva@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Michael Chan says:

====================
bnxt_en: Updates for net-next.

-Add default VLAN support for VFs.
-Add NPAR (NIC partioning) support.
-Add support for new device 5731x and 5741x. GRO logic is different.
-Support new ETHTOOL_{G|S}LINKSETTINGS.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

To fully support 25G and 50G link settings.
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Some cards do not support autoneg.  The current code does not prevent the
user from enabling autoneg with ethtool on such cards, causing confusion.
Firmware provides the autoneg capability information and we just need to
store it in the support_auto_speeds field in bnxt_link_info struct.
The ethtool set_settings() call will check this field before proceeding
with autoneg.
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>