Chris Mi says:

====================
net/sched: Improve getting objects by indexes

Using current TC code, it is very slow to insert a lot of rules.

In order to improve the rules update rate in TC,
we introduced the following two changes:
        1) changed cls_flower to use IDR to manage the filters.
        2) changed all act_xxx modules to use IDR instead of
           a small hash table

But IDR has a limitation that it uses int. TC handle uses u32.
To make sure there is no regression, we add several new IDR APIs
to support unsigned long.

v2
==

Addressed Hannes's comment:
express idr_alloc in terms of idr_alloc_ext and most of the other functions
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Typically, each TC filter has its own action. All the actions of the
same type are saved in its hash table. But the hash buckets are too
small that it degrades to a list. And the performance is greatly
affected. For example, it takes about 0m11.914s to insert 64K rules.
If we convert the hash table to IDR, it only takes about 0m1.500s.
The improvement is huge.

But please note that the test result is based on previous patch that
cls_flower uses IDR.
Signed-off-by: Chris Mi <chrism@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Currently, all filters with the same priority are linked in a doubly
linked list. Every filter should have a unique handle. To make the
handle unique, we need to iterate the list every time to see if the
handle exists or not when inserting a new filter. It is time-consuming.
For example, it takes about 5m3.169s to insert 64K rules.

This patch changes cls_flower to use IDR. With this patch, it
takes about 0m1.127s to insert 64K rules. The improvement is huge.

But please note that in this testing, all filters share the same action.
If every filter has a unique action, that is another bottleneck.
Follow-up patch in this patchset addresses that.
Signed-off-by: Chris Mi <chrism@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The following new APIs are added:

int idr_alloc_ext(struct idr *idr, void *ptr, unsigned long *index,
                  unsigned long start, unsigned long end, gfp_t gfp);
void *idr_remove_ext(struct idr *idr, unsigned long id);
void *idr_find_ext(const struct idr *idr, unsigned long id);
void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id);
void *idr_get_next_ext(struct idr *idr, unsigned long *nextid);
Signed-off-by: Chris Mi <chrism@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Subash Abhinov Kasiviswanathan says:

====================
net: Add support for rmnet driver

This patch series adds support for the rmnet driver which is required to
support recent chipsets using Qualcomm Technologies, Inc. modems. The data
from hardware follows the multiplexing and aggregation protocol (MAP).

This driver can be used to register onto any physical network device in
IP mode. Physical transports include USB, HSIC, PCIe and IP accelerator.

rmnet driver helps to decode these packets and queue them to network
stack (and encode and transmit it to the physical device).

v1: Same as the RFC patch with some minor fixes for issues reported by
kbuild test robot.

v1->v2: Change datatypes and remove config IOCTL as mentioned by David.
Also fix checkpatch issues and remove some unused code.

v2->v3: Move location to drivers/net and rename to rmnet. Change the
userspace - netlink communication from custom netlink to rtnl_link_ops.
Refactor some code. Use a fixed config for ingress and egress.

v3->v4: Move location to drivers/net/ethernet/qualcomm/.
Fix comments from Stephen and Jiri -
Split the ether and arp type changes into seperate patches.
Remove debug and custom logging and switch to standard netdevice log.
Remove module parameters. Refactor and change some code style issues.

v4->v5: Rename some structs and variables. Move the initializer
before the for loop start. Put the arp type in correct sequence.

v5->v6: Fix comments from Dan -
Use the upper link API. As a result, remove all the refcounting logic.
Device refcount is explicitly held on real_dev on rx_handler
registration only. Modifiy the flow control struct. Remove the unused
ethernet mode handling.

v6->v7: Fix comments from David - Add newline to end of Makefile. Remove
inline from .c files. Move the module init/exit to rmnet config. Fix an
error reported by kbuild test robot for an unused file.

v7->v8: Use a smaller value for ETH_P_MAP as mentioned by David. Change
netdev_info to netdev_dbg as mentioned by Andew. Fix comments from
Stephen regarding netdev_priv and sparse related errors of using 0 as NULL

v8->v9: Fix comments from David - Remove the CFLAG rule. Change the way
rmnet devices are freed. Instead of using a workqueue to unregister devices
individually, go through the list and free all devices within the rtnl_lock().

v9->v10: Actually fix the locking as mentioned by David. The locking scheme is
mentioned in a comment in rmnet_config.c. Change comment near MAP type
definition as mentioned by Dan. Refactor some code.

v10->v11: Allow RMNET to compile as a module as mentioned by David
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

RmNet driver provides a transport agnostic MAP (multiplexing and
aggregation protocol) support in embedded module. Module provides
virtual network devices which can be attached to any IP-mode
physical device. This will be used to provide all MAP functionality
on future hardware in a single consistent location.
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Define the raw IP type. This is needed for raw IP net devices
like rmnet.
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Define the Qualcomm multiplexing and aggregation (MAP) ether type 0x00F9.
This is needed for receiving data in the MAP protocol like RMNET. This is
not an officially registered ID.
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Florian Westphal says:

====================
tcp: re-add header prediction

Eric reported a performance regression caused by header prediction
removal.

We now call tcp_ack() much more frequently, for some workloads
this brings in enough cache line misses to become noticeable.

We could possibly still kill HP provided we find a different
way to suppress unneeded tcp_ack, but given we're late in
the cycle it seems preferable to revert.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

This reverts commit 45f119bf.

Eric Dumazet says:
  We found at Google a significant regression caused by
  45f119bf tcp: remove header prediction

  In typical RPC  (TCP_RR), when a TCP socket receives data, we now call
  tcp_ack() while we used to not call it.

  This touches enough cache lines to cause a slowdown.

so problem does not seem to be HP removal itself but the tcp_ack()
call.  Therefore, it might be possible to remove HP after all, provided
one finds a way to elide tcp_ack for most cases.
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

This change was a followup to the header prediction removal,
so first revert this as a prerequisite to back out hp removal.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

When moving the IRDA code out of net/ into drivers/staging/irda/net, the
link order changes when IRDA is built into the kernel.  That causes a
kernel crash at boot time as netfilter isn't initialized yet.

To fix this, move the init call level of the irda core to be
device_initcall() as the link order keeps this being initialized at the
correct time.
Reported-by: kernel test robot <fengguang.wu@intel.com>
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

A stray return was added in the macro bcmgenet_##name##_writel where it
should not, drop it.
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Fixes: 69d2ea9c ("net: bcmgenet: Use correct I/O accessors")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Florian reported UDP xmit drops that could be root caused to the
too small neigh limit.

Current limit is 64 KB, meaning that even a single UDP socket would hit
it, since its default sk_sndbuf comes from net.core.wmem_default
(~212992 bytes on 64bit arches).

Once ARP/ND resolution is in progress, we should allow a little more
packets to be queued, at least for one producer.

Once neigh arp_queue is filled, a rogue socket should hit its sk_sndbuf
limit and either block in sendmsg() or return -EAGAIN.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Since the removal of NET_DMA, dmaengine.h header file shouldn't be needed
by netdevice.h anymore.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The GENET driver currently uses __raw_{read,write}l which means
native I/O endian. This works correctly for an ARM LE kernel (default)
but fails miserably on an ARM BE (BE8) kernel where registers are kept
little endian, so replace uses with {read,write}l_relaxed here which is
what we want because this is all performance sensitive code.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Weilin Chang <weilin.chang@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Make these const as they are not modified anywhere.
Signed-off-by: Bhumika Goyal <bhumirks@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Tariq repored local pings to linklocal address is failing:
$ ifconfig ens8
ens8: flags=4163<UP,BROADCAST,RUNNING,MULTICAST>  mtu 1500
        inet 11.141.16.6  netmask 255.255.0.0  broadcast 11.141.255.255
        inet6 fe80::7efe:90ff:fecb:7502  prefixlen 64  scopeid 0x20<link>
        ether 7c:fe:90:cb:75:02  txqueuelen 1000  (Ethernet)
        RX packets 12  bytes 1164 (1.1 KiB)
        RX errors 0  dropped 0  overruns 0  frame 0
        TX packets 30  bytes 2484 (2.4 KiB)
        TX errors 0  dropped 0 overruns 0  carrier 0  collisions 0

$  /bin/ping6 -c 3 fe80::7efe:90ff:fecb:7502%ens8
PING fe80::7efe:90ff:fecb:7502%ens8(fe80::7efe:90ff:fecb:7502) 56 data bytes
Signed-off-by: David S. Miller <davem@davemloft.net>

There is a difference in the bit position of the normal interrupt summary
enable (NIE) and abnormal interrupt summary enable (AIE) between revisions
of the hardware.  For older revisions the NIE and AIE bits are positions
16 and 15 respectively.  For newer revisions the NIE and AIE bits are
positions 15 and 14.  The effect in changing the bit position is that
newer hardware won't receive AIE interrupts in the current version of the
driver.  Specifically, the driver uses this interrupt to collect
statistics on when a receive buffer unavailable event occurs and to
restart the driver/device when a fatal bus error occurs.

Update the driver to set the interrupt enable bit based on the reported
version of the hardware.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Jiri Benc says:

====================
nsh: headers, GSO

This adds header structs and helpers for NSH together with GSO support.

Note there is no code in this patchset that actually manipulates the NSH
headers. That was sent to netdev by Yi Yang ("[PATCH net-next v6 0/3]
openvswitch: add NSH support"). The aim of this series is to lay the
groundwork and ease the implementation for him.

In addition to openvswitch, the NSH support should be added to tc (flower to
match, act_nsh to push/pop NSH headers). That will come later. There's
currently no plan to support NSH by other means than those two.

The patch 3 in this patchset was written by Yi Yang, I took it from the
aforementioned series and slightly modified it - see the note in the patch.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Add a new nsh/ directory. It currently holds only GSO functions but more
will come: in particular, code shared by openvswitch and tc to manipulate
NSH headers.

For now, assume there's no hardware support for NSH segmentation. We can
always introduce netdev->nsh_features later.
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

NSH (Network Service Header)[1] is a new protocol for service
function chaining, it can be handled as a L3 protocol like
IPv4 and IPv6, Eth + NSH + Inner packet or VxLAN-gpe + NSH +
Inner packet are two typical use cases.

This patch adds NSH header structures and helpers for NSH GSO
support and Open vSwitch NSH support.

[1] https://datatracker.ietf.org/doc/draft-ietf-sfc-nsh/

[Jiri: added nsh_hdr() helper and renamed the header struct to "struct
nshhdr" to match the usual pattern. Removed packet type defines, these are
now shared with VXLAN-GPE.]
Signed-off-by: Yi Yang <yi.y.yang@intel.com>
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The values are shared between VXLAN-GPE and NSH. Originally probably by
coincidence but I notified both working groups about this last year and they
seem to keep the values in sync since then.

Hopefully they'll get a single IANA registry for the values, too. (I asked
them for that.)

Factor out the code to be shared by the NSH implementation.

NSH and MPLS values are added in this patch, too. For MPLS, the drafts
incorrectly assign only a single value, while we have two MPLS ethertypes.
I raised the problem with both groups. For now, I assume the value is for
unicast.
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The NSH draft says:

   An IEEE EtherType, 0x894F, has been allocated for NSH.
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Alexander Aring says:

====================
tc: act_ife: handle IEEE IFE ethertype as default

this patch series will introduce the IFE ethertype which is registered by
IEEE. If the netlink act_ife type netlink attribute is not given it will
use this value by default now.
At least it will introduce some UAPI testcases to check if the default type
is used if not specified and vice versa.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch adds a new testcase for the IFE type setting in tc. In case
of user specified the type it will check if the ife is correctly
configured to react on it. If it's not specified the default IFE type
should be used.
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch handles a default IFE type if it's not given by user space
netlink api. The default IFE type will be the registered ethertype by
IEEE for IFE ForCES.
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch adds the forces IFE lfb type according to IEEE registered
ethertypes. See http://standards-oui.ieee.org/ethertype/eth.txt for more
information. Since there exists the IFE subsystem it can be used there.

This patch also use the correct word "ForCES" instead of "FoRCES" which
is a spelling error inside the IEEE ethertype specification.
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Explain that the patch queue in patchwork should not be touched by patch
submitters.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Tariq Toukan says:

====================
mlx4 misc patches

This patchset contains misc patches from the team
to the mlx4 Core and Eth drivers.

Patch 1 by Eran replaces large static allocations by dynamic ones.
Patch 2 by Leon makes an explicit conversion and solves a smatch warning.
In patch 3 I fix a misplaced brackets of the sizeof operation.
Patch 4 by Moshe adds the ability to inform the FW regarding user mac updates.

Series generated against net-next commit:
901c5d2f ARM: dts: rk3228-evb: Fix the compiling error
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Adding support for updating the FW on new port mac, when port mac change
is requested by the user. This info is required by the FW as OEM
management tools require this info directly from the NIC FW.
Check device capability bit to verify the FW supports user mac.
If the FW does support it, use set_port command to notify the FW on the
new mac.
The feature is relevant only to PF port mac.
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

When changing the sizeof style usage in the patch cited below,
one brackets misplacement was introduced. Here we fix it.

Fixes: 31975e27 ("mlx4: sizeof style usage")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

The "lg" variable is declared as int so in all places where this variable
is used as a shift operand, the output will be int too.

This produces the following smatch warning:
drivers/net/ethernet/mellanox/mlx4/fw.c:1532 mlx4_map_cmd() warn:
	should '1 << lg' be a 64 bit type?

Simple declaration of "1" to be "1ULL" will fix the issue.

Fixes: 225c7b1f ("IB/mlx4: Add a driver Mellanox ConnectX InfiniBand adapters")
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

In order to avoid temporary large structs on the stack,
allocate them dynamically.
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Tal Alon <talal@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

A few useful tracepoints to trace bridge forwarding
database updates.
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Florian Fainelli says:

====================
Endian fixes for SYSTEMPORT/SF2/MDIO

While trying an ARM BE kernel for kinks, the 3 drivers below started not
working and the reasons why became pretty obvious because the register space
remains LE (hardwired), except for Broadcom MIPS where it follows the CPU's
native endian (let's call that a feature).
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

The driver currently uses __raw_{read,write}l which works for all
platforms supported: Broadcom MIPS LE/BE (native endian), ARM LE (native
endian) but not ARM BE (registers are still LE). Switch to using the
proper accessors for all platforms and explain why Broadcom MIPS BE is
special here, in doing so, we introduce a couple of helper functions to
abstract these differences.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

RSB_SWAP0 needs to match the host CPU endian, and it needs to be set
for LE and clear for BE. RSB_SWAP1 must always be cleared for SYSTEMPORT
Lite.

With these settings, we have the Receive Status Block always match the
host endian and we do not need to perform any conversion. Since there is
not necessarily a CONFIG_CPU_LITTLE_ENDIAN option defined, we test for
!CONFIG_CPU_BIG_ENDIAN which is guaranteed to be set.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The Starfigther 2 driver currently uses __raw_{read,write}l which means
native I/O endian. This works correctly for an ARM LE kernel (default)
but fails miserably on an ARM BE (BE8) kernel where registers are kept
little endian, so replace uses with {read,write}l_relaxed here which is
what we want because this is all performance sensitive code.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>