To build the maglev hashing scheduler, add some configuration
to Kconfig and Makefile.

 - The compile configurations of MH are added to the Kconfig.

 - The MH build rule is added to the Makefile.
Signed-off-by: Inju Song <inju.song@navercorp.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>

Implements the Google's Maglev hashing algorithm as a IPVS scheduler.

Basically it provides consistent hashing but offers some special
features about disruption and load balancing.

 1) minimal disruption: when the set of destinations changes,
    a connection will likely be sent to the same destination
    as it was before.

 2) load balancing: each destination will receive an almost
    equal number of connections.

Seel also for detail: [3.4 Consistent Hasing] in
https://www.usenix.org/system/files/conference/nsdi16/nsdi16-paper-eisenbud.pdfSigned-off-by: Inju Song <inju.song@navercorp.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>

The hashing table in scheduler such as source hash or maglev hash
should ignore the changed weight to 0 and allow changing the weight
from/to non-0 values. So, struct ip_vs_dest needs to keep weight
with latest non-0 weight.
Signed-off-by: Inju Song <inju.song@navercorp.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>

Fix checkpatch.pl error:
ERROR: space prohibited before open square bracket '['.
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>

Jisheng Zhang says:

====================
net: mvneta: improve suspend/resume

This series tries to optimize the mvneta's suspend/resume
implementation by only taking necessary actions.

Since v2:
 - keep rtnl lock when calling mvneta_start_dev() and mvneta_stop_dev()
   Thank Russell for pointing this out

Since v1:
 - unify ret check
 - try best to keep the suspend/resume behavior
 - split txq deinit into sw/hw parts as well
 - adjust mvneta_stop_dev() location

I didn't add Thomas's Ack tag to patch1, because in v2, I add new code
to split the txq deinit into two parts.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Current suspend/resume implementation reuses the mvneta_open() and
mvneta_close(), but it could be optimized to take only necessary
actions during suspend/resume.

One obvious problem of current implementation is: after hundreds of
system suspend/resume cycles, the resume of mvneta could fail due to
fragmented dma coherent memory. After this patch, the non-necessary
memory alloc/free is optimized out.
Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This is to prepare the suspend/resume improvement in next patch. The
SW parts can be optimized out during resume.

As for rxq handling during suspend, we'd like to drop packets by
calling mvneta_rxq_drop_pkts() which is both SW and HW operation,
so we don't split rxq deinit.
Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

I forgot to change ip6frag_low_thresh proc_handler
from proc_dointvec_minmax to proc_doulongvec_minmax

Fixes: 3e67f106 ("inet: frags: break the 2GB limit for frags storage")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Florian Fainelli says:

====================
net: bgmac: Couple of sparse warnings

This patch series fixes a couple of warnings reported by sparse, should not
cause any functional problems since bgmac is typically used on LE platforms
anyway.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

bgmac_dma_tx_ring_free() assigns the ctl1 word which is a litle endian
32-bit word without using proper accessors, fix this, and because a
length cannot be negative, use unsigned int while at it.

Fixes: 9cde9450 ("bgmac: implement scatter/gather support")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

All the members: base, idm_base and nicpm_base should be annotated with
__iomem since they are pointers to register space. This fixes a bunch of
sparse reported warnings.

Fixes: f6a95a24 ("net: ethernet: bgmac: Add platform device support")
Fixes: dd5c5d03 ("net: ethernet: bgmac: add NS2 support")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Prior to this patch, when one packet is hashed into path [1]
(hash <= nh_upper_bound) and it's neigh is dead, it will try
path [2]. However, if path [2]'s neigh is alive but it's
hash > nh_upper_bound, it will not return this alive path.
This packet will never be sent even if path [2] is alive.

 3.3.3.1/24:
  nexthop via 1.1.1.254 dev eth1 weight 1 <--[1] (dead neigh)
  nexthop via 2.2.2.254 dev eth2 weight 1 <--[2]

With sysctl_fib_multipath_use_neigh set is supposed to find an
available path respecting to the l3/l4 hash. But if there is
no available route with this hash, it should at least return
an alive route even with other hash.

This patch is to fix it by processing fib_multipath_use_neigh
earlier than the hash check, so that it will at least return
an alive route if there is when fib_multipath_use_neigh is
enabled. It's also compatible with before when there are alive
routes with the l3/l4 hash.

Fixes: a6db4494 ("net: ipv4: Consider failed nexthops in multipath routes")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

mdio-bitbang mentioned 10 for both read and write.
However mdio read opcode is 10 and write opcode is 01
Fixed comment.
Signed-off-by: Frans Meulenbroeks <fransmeulenbroeks@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

The sky2 ethernet stops working after system resume from suspend:
[ 582.852065] sky2 0000:04:00.0: Refused to change power state, currently in D3

The current 150ms delay is not enough, change it to 200ms can solve the
issue.

BugLink: https://bugs.launchpad.net/bugs/1758507
Cc: Stable <stable@vger.kernel.org>
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The default TX moderation mode was mistakenly set to CQE based. The
intention was to add a control ability in order to improve some specific
use-cases. In general, we prefer to use EQE based moderation as it gives
much better numbers for the common cases.

CQE based causes a degradation in the common case since it resets the
moderation timer on CQE generation. This causes an issue when TSO is
well utilized (large TSO sessions). The timer is set to 16us so traffic
of ~64KB TSO sessions per second would mean timer reset (CQE per TSO
session -> long time between CQEs). In this case we quickly reach the
tcp_limit_output_bytes (256KB by default) and cause a halt in TX traffic.

By setting EQE based moderation we make sure timer would expire after
16us regardless of the packet rate.
This fixes an up to 40% packet rate and up to 23% bandwidth degradtions.

Fixes: 0088cbbc ("net/mlx5e: Enable CQE based moderation on TX CQ")
Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

When the driver is closed, all the associated irqs are disabled. In the
event that the driver exits a reset in the closed state, we should be
consistent with the state we are in directly after a close. So before we
exit the reset routine, all irqs should be disabled as well. This will
prevent the irqs from being enabled twice in this case and reporting a
number of noisy warning traces.
Signed-off-by: John Allen <jallen@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

move messages emitting out of sch_tree_lock to avoid holding
this lock too long.
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Just like function ethtool_get_ts_info(), we should also consider the
phy_driver ts_info call back. For example, driver dp83640.

Fixes: 37dd9255 ("vlan: Pass ethtool get_ts_info queries to real device.")
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Minor conflicts in drivers/net/ethernet/mellanox/mlx5/core/en_rep.c,
we had some overlapping changes:

1) In 'net' MLX5E_PARAMS_LOG_{SQ,RQ}_SIZE -->
   MLX5E_REP_PARAMS_LOG_{SQ,RQ}_SIZE

2) In 'net-next' params->log_rq_size is renamed to be
   params->log_rq_mtu_frames.

3) In 'net-next' params->hard_mtu is added.
Signed-off-by: David S. Miller <davem@davemloft.net>

Merge branch 'for-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth-next

Johan Hedberg says:

====================
pull request: bluetooth-next 2018-04-01

Here's (most likely) the last bluetooth-next pull request for the 4.17
kernel:

 - Remove unused btuart_cs driver (replaced by serial_cs + hci_uart)
 - New USB ID for Edimax EW-7611ULB controller
 - Cleanups & fixes to hci_bcm driver
 - Clenups to btmrvl driver

Please let me know if there are any issues pulling. Thanks.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>

QCA Rome controllers can do both LE scan and BR/EDR inquiry at once.
Signed-off-by: Vic Wei <vwei@codeaurora.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>

Remove including <linux/version.h> that don't need it.
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>

As Interrupt resource specified IRQs are now assumed to be always
active-low the DMI quirk for the MINIX Z83-4 is no longer required.
Signed-off-by: Ian W MORRISON <ianwmorrison@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>

Sergei Shtylyov says:

====================
sh_eth: remove SH_ETH_OFFSET_INVALID abuses

Here's a set of 2 patches against DaveM's 'net-next.git' repo. They get rid of
the abuse of SH_ETH_OFFSET_INVALID for the register existence checks, so that
only its necessary uses would remain...
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Iff TSU registers exist on a given [G]Ether controller, they always include
the CAM entry table registers (TSU_ADR{H|L}<n>), thus the check for invalid
TSU_ADRH0 offset in __sh_eth_get_regs() is useless...
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The commit 6ded2865 ("sh_eth: Fix RX recovery on R-Car in case of RX
ring underrun") added a check for an bad RDFAR offset in sh_eth_rx(), so
that the code could work on the R-Car Ether controllers which don't have
this register (and TDFAR), then the commit 3365711d ("sh_eth: WARN on
access to a register not implemented in a particular chip") replaced
offset 0 with 0xffff. Adding/checking the 'no_xdfar' bit field in the
'struct sh_eth_cpu_data' instead results in less object code...
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Eric Dumazet says:

====================
inet: factorize sk_wmem_alloc updates

While testing my inet defrag changes, I found that senders
could spend ~20% of cpu cycles in skb_set_owner_w() updating
sk->sk_wmem_alloc for every fragment they cook, competing
with TX completion of prior skbs possibly happening on another cpus.

One solution to this problem is to use alloc_skb() instead
of sock_wmalloc() and manually perform a single sk_wmem_alloc change.

This greatly increases speed for applications sending big UDP datagrams.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

While testing my inet defrag changes, I found that the senders
could spend ~20% of cpu cycles in skb_set_owner_w() updating
sk->sk_wmem_alloc for every fragment they cook, competing
with TX completion of prior skbs possibly happening on another cpus.

The solution to this problem is to use alloc_skb() instead
of sock_wmalloc() and manually perform a single sk_wmem_alloc change.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

While testing my inet defrag changes, I found that the senders
could spend ~20% of cpu cycles in skb_set_owner_w() updating
sk->sk_wmem_alloc for every fragment they cook.

The solution to this problem is to use alloc_skb() instead
of sock_wmalloc() and manually perform a single sk_wmem_alloc change.

Similar change for IPv6 is provided in following patch.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This reverts commit cf29bded.

It causes regressions.
Signed-off-by: David S. Miller <davem@davemloft.net>

'tunnel' was already set at the start of ip6erspan_tap_init().

Fixes: 5a963eb6 ("ip6_gre: Add ERSPAN native tunnel support")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Refine the RX check summing handling to propagate the
hardware provided checksum so that we do not have to
compute it later in software.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Ido Schimmel says:

====================
mlxsw: Various cleanups

The first nine patches from Jiri perform small and unrelated cleanups.
The largest being the conversion of the KVD linear partitions from a
list to an array, which simplifies the code.

The last patch from Petr is a bug fix for a recent net-next commit that
prevented the "kvd" resource from being marked as the parent of its
various child resources (e.g., "/kvd/linear").

v2: Dropped devlink patch following David's comment. Will be sent
separately.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

In commit 14530746 ("devlink: Remove top_hierarchy arg to
devlink_resource_register"), the "top_hierarchy" parameter to
devlink_resource_register() was removed in favor of using the parameter
"parent_resource_id" exclusively to determine who the parent is. The
root node's resource ID for this purpose is
DEVLINK_RESOURCE_ID_PARENT_TOP with the value 0. It is therefore
problematic that the resource MLXSW_SP_RESOURCE_KVD has also ID of 0.

Fix this by numbering driver-specific resources from 1.

Fixes: 14530746 ("devlink: Remove top_hierarchy arg to devlink_resource_register")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Pass struct mlxsw_core instead of devlink since it is nicer within mlxsw
code and we need both structs in mlxsw_sp_kvdl_resources_register()
anyway.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

As struct mlxsw_config_profile is mapped to the payload of the FW
command of the same name, resources_query_enable flag does not belong
there. Move it to struct mlxsw_driver.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The check should be done directly in mlxsw_pci_config_profile, as for
other profile items. Also, be consistent in naming with the rest and
rename to "used_kvd_sizes".
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

First arg of these helpers should be "mlxsw_core".
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This should not be part of the struct, as the struct fields
are tightly coupled with the FW command payload of the same name.
Just use the "granularity" define directly, as in other places.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>