Add per-ring and global ethtool counters for TX completions.
This helps us monitor and analyze TX flow performance.
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Local variable 'wq' already points to &sq->wq, use it.
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Replace calls to kzalloc_node with kvzalloc_node, as it fallsback
to lower-order pages if the higher-order trials fail.
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

This patch adds a counter for tx UDP GSO packets that contain a segment
that is not aligned to MSS - remaining segment.
Signed-off-by: NBoris Pismenny <borisp@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

This patch enables UDP GSO support. We enable this by using two WQEs
the first is a UDP LSO WQE for all segments with equal length, and the
second is for the last segment in case it has different length.
Due to HW limitation, before sending, we must adjust the packet length fields.

We measure performance between two Intel(R) Xeon(R) CPU E5-2643 v2 @3.50GHz
machines connected back-to-back with Connectx4-Lx (40Gbps) NICs.
We compare single stream UDP, UDP GSO and UDP GSO with offload.
Performance:
		| MSS (bytes)	| Throughput (Gbps)	| CPU utilization (%)
UDP GSO offload	| 1472		| 35.6			| 8%
UDP GSO 	| 1472		| 25.5			| 17%
UDP 		| 1472		| 10.2			| 17%
UDP GSO offload	| 1024		| 35.6			| 8%
UDP GSO		| 1024		| 19.2			| 17%
UDP 		| 1024		| 5.7			| 17%
UDP GSO offload	| 512		| 33.8			| 16%
UDP GSO		| 512		| 10.4			| 17%
UDP 		| 512		| 3.5			| 17%
Signed-off-by: NBoris Pismenny <borisp@mellanox.com>
Signed-off-by: NYossi Kuperman <yossiku@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Have one extack message for parsing and validating.
Signed-off-by: NDavid Ahern <dsahern@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We're ignoring the result of the attached phy device's read_status().
Return it so we can detect errors.
Signed-off-by: NBrandon Maier <brandon.maier@rockwellcollins.com>
Reviewed-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The xgmiitorgmii is using the mii_bus of the device it's attached to,
instead of the bus it was given during probe.
Signed-off-by: NBrandon Maier <brandon.maier@rockwellcollins.com>
Reviewed-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since a phy_device is added to the global mdio_bus list during
phy_device_register(), but a phy_device's phy_driver doesn't get
attached until phy_probe(). It's possible of_phy_find_device() in
xgmiitorgmii will return a valid phy with a NULL phy_driver. Leading to
a NULL pointer access during the memcpy().

Fixes this Oops:

Unable to handle kernel NULL pointer dereference at virtual address 00000000
pgd = c0004000
[00000000] *pgd=00000000
Internal error: Oops: 5 [#1] PREEMPT SMP ARM
Modules linked in:
CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.14.40 #1
Hardware name: Xilinx Zynq Platform
task: ce4c8d00 task.stack: ce4ca000
PC is at memcpy+0x48/0x330
LR is at xgmiitorgmii_probe+0x90/0xe8
pc : [<c074bc68>]    lr : [<c0529548>]    psr: 20000013
sp : ce4cbb54  ip : 00000000  fp : ce4cbb8c
r10: 00000000  r9 : 00000000  r8 : c0c49178
r7 : 00000000  r6 : cdc14718  r5 : ce762800  r4 : cdc14710
r3 : 00000000  r2 : 00000054  r1 : 00000000  r0 : cdc14718
Flags: nzCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none
Control: 18c5387d  Table: 0000404a  DAC: 00000051
Process swapper/0 (pid: 1, stack limit = 0xce4ca210)
...
[<c074bc68>] (memcpy) from [<c0529548>] (xgmiitorgmii_probe+0x90/0xe8)
[<c0529548>] (xgmiitorgmii_probe) from [<c0526a94>] (mdio_probe+0x28/0x34)
[<c0526a94>] (mdio_probe) from [<c04db98c>] (driver_probe_device+0x254/0x414)
[<c04db98c>] (driver_probe_device) from [<c04dbd58>] (__device_attach_driver+0xac/0x10c)
[<c04dbd58>] (__device_attach_driver) from [<c04d96f4>] (bus_for_each_drv+0x84/0xc8)
[<c04d96f4>] (bus_for_each_drv) from [<c04db5bc>] (__device_attach+0xd0/0x134)
[<c04db5bc>] (__device_attach) from [<c04dbdd4>] (device_initial_probe+0x1c/0x20)
[<c04dbdd4>] (device_initial_probe) from [<c04da8fc>] (bus_probe_device+0x98/0xa0)
[<c04da8fc>] (bus_probe_device) from [<c04d8660>] (device_add+0x43c/0x5d0)
[<c04d8660>] (device_add) from [<c0526cb8>] (mdio_device_register+0x34/0x80)
[<c0526cb8>] (mdio_device_register) from [<c0580b48>] (of_mdiobus_register+0x170/0x30c)
[<c0580b48>] (of_mdiobus_register) from [<c05349c4>] (macb_probe+0x710/0xc00)
[<c05349c4>] (macb_probe) from [<c04dd700>] (platform_drv_probe+0x44/0x80)
[<c04dd700>] (platform_drv_probe) from [<c04db98c>] (driver_probe_device+0x254/0x414)
[<c04db98c>] (driver_probe_device) from [<c04dbc58>] (__driver_attach+0x10c/0x118)
[<c04dbc58>] (__driver_attach) from [<c04d9600>] (bus_for_each_dev+0x8c/0xd0)
[<c04d9600>] (bus_for_each_dev) from [<c04db1fc>] (driver_attach+0x2c/0x30)
[<c04db1fc>] (driver_attach) from [<c04daa98>] (bus_add_driver+0x50/0x260)
[<c04daa98>] (bus_add_driver) from [<c04dc440>] (driver_register+0x88/0x108)
[<c04dc440>] (driver_register) from [<c04dd6b4>] (__platform_driver_register+0x50/0x58)
[<c04dd6b4>] (__platform_driver_register) from [<c0b31248>] (macb_driver_init+0x24/0x28)
[<c0b31248>] (macb_driver_init) from [<c010203c>] (do_one_initcall+0x60/0x1a4)
[<c010203c>] (do_one_initcall) from [<c0b00f78>] (kernel_init_freeable+0x15c/0x1f8)
[<c0b00f78>] (kernel_init_freeable) from [<c0763d10>] (kernel_init+0x18/0x124)
[<c0763d10>] (kernel_init) from [<c0112d74>] (ret_from_fork+0x14/0x20)
Code: ba000002 f5d1f03c f5d1f05c f5d1f07c (e8b151f8)
---[ end trace 3e4ec21905820a1f ]---
Signed-off-by: NBrandon Maier <brandon.maier@rockwellcollins.com>
Reviewed-by: NAndrew Lunn <andrew@lunn.ch>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Shannon Nelson says:

====================
Updates for ipsec selftests

Fix up the existing ipsec selftest and add tests for
the ipsec offload driver API.

v2: addressed formatting nits in netdevsim from Jakub Kicinski
v3: a couple more nits from Jakub
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Using the netdevsim as a device for testing, try out the XFRM commands
for setting up IPsec hardware offloads.
Signed-off-by: NShannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Implement the IPsec/XFRM offload API for testing.
Signed-off-by: NShannon Nelson <shannon.nelson@oracle.com>
Reviewed-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We really shouldn't mess with local system settings, so let's
use the already created dummy device instead for ipsec testing.
Oh, and let's put the temp file into a proper directory.
Signed-off-by: NShannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Following the custom from the other functions, clear the global
ret code before starting the test so as to not have previously
failed tests cause us to thing this test has failed.
Reported-by: NAnders Roxell <anders.roxell@linaro.org>
Signed-off-by: NShannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

'sockaddr_len' is checked against various values when entering
pppol2tp_connect(), to verify its validity. It is used again later, to
find out which sockaddr structure was passed from user space. This
patch combines these two operations into one new function in order to
simplify pppol2tp_connect().

A new structure, l2tp_connect_info, is used to pass sockaddr data back
to pppol2tp_connect(), to avoid passing too many parameters to
l2tp_sockaddr_get_info(). Also, the first parameter is void* in order
to avoid casting between all sockaddr_* structures manually.
Signed-off-by: NGuillaume Nault <g.nault@alphalink.fr>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NYuchung Cheng <ycheng@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The *enum* {A|M}PR_BIT were declared in the commit 86a74ff2 ("net:
sh_eth: add support for  Renesas SuperH Ethernet") adding SH771x support,
however the SH771x manual  doesn't have the APR/MPR registers described
and the code writing to them for SH7710 was later removed by the commit
380af9e3 ("net: sh_eth: CPU dependency code collect to "struct
sh_eth_cpu_data""). All the newer SoC manuals have these registers
documented as having a 16-bit TIME parameter of the PAUSE frame, not
1-bit -- update the *enum* accordingly, fixing up the APR/MPR writes...
Signed-off-by: NSergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Reviewed-by: NGeert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Added an extreme-case test for all 7 csum action headers.
Signed-off-by: NKeara Leibovitz <kleib@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Alexandre Belloni says:

====================
net: mscc: ocelot: add more features

This series adds link aggregation and VLAN filtering hardware offload
support to the ocelot driver.

PTP support will be sent later.

changes in v2:
 - rebased on v4.18-rc1
 - check for aggregation type and only offload it when type is hash (balance-xor
   or 802.3ad)
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add hardware VLAN filtering offloading on ocelot.
Signed-off-by: NAntoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: NAlexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add link aggregation hardware offload support for Ocelot.

ocelot_get_link_ksettings() is not great but it does work until the driver
is reworked to switch to phylink.
Signed-off-by: NAlexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NGanesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add flag tc_flower_initialized to indicate the
completion if tc flower initialization.
Signed-off-by: NCasey Leedom <leedom@chelsio.com>
Signed-off-by: NGanesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In systems where neigh gc thresh holds are set to high values,
admin deleted neigh entries (eg ip neigh flush or ip neigh del) can
linger around in NUD_FAILED state for a long time until periodic gc kicks
in. This patch forces neigh_invalidate when NUD_FAILED neigh_update is
from an admin.
Signed-off-by: NRoopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Petr Machata says:

====================
Multipath tests for tunnel devices

This patchset adds a test for ECMP and weighted ECMP between two GRE
tunnels.

In patches #1 and #2, the function multipath_eval() is first moved from
router_multipath.sh to lib.sh for ease of reuse, and then fixed up.

In patch #3, the function tc_rule_stats_get() is parameterized to be
useful for egress rules as well.

In patch #4, a new function __simple_if_init() is extracted from
simple_if_init(). This covers the logic that needs to be done for the
usual interface: VRF migration, upping and installation of IP addresses.

Patch #5 then adds the test itself.

Additionally in patch #6, a requirement to add diagrams to selftests is
documented.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ASCII art diagrams are well suited for presenting the topology that a
test uses while being easy to embed directly in the test file iteslf.
They make the information very easy to grasp even for simple topologies,
and for more complex ones they are almost essential, as figuring out the
interconnects from the script itself proves to be difficult.

Therefore state the requirement for topology ASCII art in README.
Signed-off-by: NPetr Machata <petrm@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add a GRE-tunneling test such that there are two tunnels involved, with
a multipath route listing both as next hops. Similarly to
router_multipath.sh, test that the distribution of traffic to the
tunnels honors the configured weights.
Signed-off-by: NPetr Machata <petrm@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The function simple_if_init() does two things: it creates a VRF, then
moves an interface into this VRF and configures addresses. The latter
comes in handy when adding more interfaces into a VRF later on. The
situation is similar for simple_if_fini().

Therefore split the interface remastering and address de/initialization
logic to a new pair of helpers __simple_if_init() / __simple_if_fini(),
and defer to these helpers from simple_if_init() and simple_if_fini().
Signed-off-by: NPetr Machata <petrm@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The GRE multipath tests need stats on an egress counter. Change
tc_rule_stats_get() to take direction as an optional argument, with
default of ingress.

Take the opportunity to change line continuation character from | to \.
Move the | to the next line, which indent.
Signed-off-by: NPetr Machata <petrm@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

- Change the indentation of the function body from 7 spaces to one tab.
- Move initialization of weights_ratio up so that it can be referenced
  from the error message about packet difference being zero.
- Move |'s consistently to continuation line, which reindent.
Signed-off-by: NPetr Machata <petrm@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This function will be useful for the GRE multipath test that is coming
later.
Signed-off-by: NPetr Machata <petrm@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It looks like the prior VLA removal, commit b16520f7 ("net/tls: Remove
VLA usage"), and a new VLA addition, commit c46234eb ("tls: RX path
for ktls"), passed in the night. This removes the newly added VLA, which
happens to have its bounds based on the same max value.
Signed-off-by: NKees Cook <keescook@chromium.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The IP addresses of tunnel endpoint at H3 are set at the VLAN device
$h3.555. Therefore when test_gretap_untagged_egress() sets vlan 555 to
egress untagged at $swp3, $h3's rp_filter rejects these packets. The
test then spuriously fails.

Therefore turn off net.ipv4.conf.{all, $h3}.rp_filter.

Fixes: 9c7c8a82 ("selftests: forwarding: mirror_gre_vlan_bridge_1q: Add more tests")
Signed-off-by: NPetr Machata <petrm@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In the quest to remove all stack VLA usage from the kernel[1], this
allocates the values buffer during the callback instead of putting it
on the stack.

[1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.comSigned-off-by: NKees Cook <keescook@chromium.org>
Reviewed-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jakub Kicinski says:

====================
net: sched: support replay of filter offload when binding to block

This series from John adds the ability to replay filter offload requests
when new offload callback is being registered on a TC block.  This is most
likely to take place for shared blocks today, when a block which already
has rules is bound to another interface.  Prior to this patch set if any
of the rules were offloaded the block bind would fail.

A new tcf_proto_op is added to generate a filter-specific offload request.
The new 'offload' op is supporting extack from day 0, hence we need to
propagate extack to .ndo_setup_tc TC_BLOCK_BIND/TC_BLOCK_UNBIND and
through tcf_block_cb_register() to tcf_block_playback_offloads().

The immediate use of this patch set is to simplify life of drivers which
require duplicating rules when sharing blocks.  Switch drivers (mlxsw)
can bind ports to rule lists dynamically, NIC drivers generally don't
have that ability and need the rules to be duplicated for each ingress
they match on.  In code terms this means that switch drivers don't
register multiple callbacks for each port.  NIC drivers do, and get a
separate request and hance rule per-port, as if the block was not shared.
The registration fails today, however, if some rules were already present.

As John notes in description of patch 7, drivers which register multiple
callbacks to shared blocks will likely need to flush the rules on block
unbind.  This set makes the core not only replay the the offload add
requests but also offload remove requests when callback is unregistered.

v2:
 - name parameters in patch 2;
 - use unsigned int instead of u32 for in_hw_coun;
 - improve extack message in patch 7.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Call the reoffload tcf_proto_op on all tcf_proto nodes in all chains of a
block when a callback tries to register to a block that already has
offloaded rules. If all existing rules cannot be offloaded then the
registration is rejected. This replaces the previous policy of rejecting
such callback registration outright.

On unregistration of a callback, the rules are flushed for that given cb.
The implementation of block sharing in the NFP driver, for example,
duplicates shared rules to all devs bound to a block. This meant that
rules could still exist in hw even after a device is unbound from a block
(assuming the block still remains active).
Signed-off-by: NJohn Hurley <john.hurley@netronome.com>
Signed-off-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add the offload tcf_proto_op in cls_bpf to generate an offload message for
each bpf prog in the given tcf_proto. Call the specified callback with
this new offload message. The function only returns an error if the
callback rejects adding a 'hardware only' prog.

A prog contains a flag to indicate if it is in hardware or not. To
ensure the offload function properly maintains this flag, keep a reference
counter for the number of instances of the prog that are in hardware. Only
update the flag when this counter changes from or to 0.
Signed-off-by: NJohn Hurley <john.hurley@netronome.com>
Signed-off-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add the offload tcf_proto_op in cls_u32 to generate an offload message for
each filter and the hashtable in the given tcf_proto. Call the specified
callback with this new offload message. The function only returns an error
if the callback rejects adding a 'hardware only' rule.

A filter contains a flag to indicate if it is in hardware or not. To
ensure the offload function properly maintains this flag, keep a reference
counter for the number of instances of the filter that are in hardware.
Only update the flag when this counter changes from or to 0.
Signed-off-by: NJohn Hurley <john.hurley@netronome.com>
Signed-off-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add the reoffload tcf_proto_op in matchall to generate an offload message
for each filter in the given tcf_proto. Call the specified callback with
this new offload message. The function only returns an error if the
callback rejects adding a 'hardware only' rule.

Ensure matchall flags correctly report if the rule is in hw by keeping a
reference counter for the number of instances of the rule offloaded. Only
update the flag when this counter changes from or to 0.
Signed-off-by: NJohn Hurley <john.hurley@netronome.com>
Signed-off-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add the reoffload tcf_proto_op in flower to generate an offload message
for each filter in the given tcf_proto. Call the specified callback with
this new offload message. The function only returns an error if the
callback rejects adding a 'hardware only' rule.

A filter contains a flag to indicate if it is in hardware or not. To
ensure the reoffload function properly maintains this flag, keep a
reference counter for the number of instances of the filter that are in
hardware. Only update the flag when this counter changes from or to 0. Add
a generic helper function to implement this behaviour.
Signed-off-by: NJohn Hurley <john.hurley@netronome.com>
Signed-off-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>