There are many data structures (RDS socket options) used by RDS apps
which use a 32 bit integer to store IP address. To support IPv6,
struct in6_addr needs to be used. To ensure backward compatibility, a
new data structure is introduced for each of those data structures
which use a 32 bit integer to represent an IP address. And new socket
options are introduced to use those new structures. This means that
existing apps should work without a problem with the new RDS module.
For apps which want to use IPv6, those new data structures and socket
options can be used. IPv4 mapped address is used to represent IPv4
address in the new data structures.
v4: Revert changes to SO_RDS_TRANSPORT
Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com> Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
This patch enables RDS to use IPv6 addresses. For RDS/TCP, the
listener is now an IPv6 endpoint which accepts both IPv4 and IPv6
connection requests. RDS/RDMA/IB uses a private data (struct
rds_ib_connect_private) exchange between endpoints at RDS connection
establishment time to support RDMA. This private data exchange uses a
32 bit integer to represent an IP address. This needs to be changed in
order to support IPv6. A new private data struct
rds6_ib_connect_private is introduced to handle this. To ensure
backward compatibility, an IPv6 capable RDS stack uses another RDMA
listener port (RDS_CM_PORT) to accept IPv6 connection. And it
continues to use the original RDS_PORT for IPv4 RDS connections. When
it needs to communicate with an IPv6 peer, it uses the RDS_CM_PORT to
send the connection set up request.
v5: Fixed syntax problem (David Miller).
v4: Changed port history comments in rds.h (Sowmini Varadhan).
v3: Added support to set up IPv4 connection using mapped address
(David Miller).
Added support to set up connection between link local and non-link
addresses.
Various review comments from Santosh Shilimkar and Sowmini Varadhan.
v2: Fixed bound and peer address scope mismatched issue.
Added back rds_connect() IPv6 changes.
Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com> Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
rds: Changing IP address internal representation to struct in6_addr
This patch changes the internal representation of an IP address to use
struct in6_addr. IPv4 address is stored as an IPv4 mapped address.
All the functions which take an IP address as argument are also
changed to use struct in6_addr. But RDS socket layer is not modified
such that it still does not accept IPv6 address from an application.
And RDS layer does not accept nor initiate IPv6 connections.
v2: Fixed sparse warnings.
Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com> Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
====================
sched: introduce chain templates support with offloading to mlxsw
For the TC clsact offload these days, some of HW drivers need
to hold a magic ball. The reason is, with the first inserted rule inside
HW they need to guess what fields will be used for the matching. If
later on this guess proves to be wrong and user adds a filter with a
different field to match, there's a problem. Mlxsw resolves it now with
couple of patterns. Those try to cover as many match fields as possible.
This aproach is far from optimal, both performance-wise and scale-wise.
Also, there is a combination of filters that in certain order won't
succeed.
Most of the time, when user inserts filters in chain, he knows right away
how the filters are going to look like - what type and option will they
have. For example, he knows that he will only insert filters of type
flower matching destination IP address. He can specify a template that
would cover all the filters in the chain.
This patchset is providing the possibility to user to provide such
template to kernel and propagate it all the way down to device
drivers.
See the examples below.
Create dummy device with clsact first:
There is no chain present by by default:
Add chain number 11 by explicit command:
chain parent ffff: chain 11
Add filter to chain number 12 which does not exist. That will create
implicit chain 12:
chain parent ffff: chain 11
chain parent ffff: chain 12
Delete both chains:
Add a chain with template of type flower allowing to insert rules matching
on last 2 bytes of destination mac address:
The chain with template is now showed in the list:
chain parent ffff: flower chain 0
dst_mac 00:00:00:00:00:00/00:00:00:00:ff:ff
eth_type ipv4
Addition of filters that does not fit the template would fail:
Error: cls_flower: Mask does not fit the template.
We have an error talking to the kernel, -1
Error: cls_flower: Mask does not fit the template.
We have an error talking to the kernel, -1
Additions of filters to chain 22:
Error: cls_flower: Mask does not fit the template.
We have an error talking to the kernel, -1
Error: cls_flower: Mask does not fit the template.
We have an error talking to the kernel, -1
---
v3->v4:
- patch 2:
- new patch
- patch 3:
- new patch, derived from the previous v3 chaintemplate obj patch
- patch 4:
- only templates part as chains creation/deletion is now a separate patch
- don't pass template priv as arg of "change" op
- patch 6:
- rebased on top of flower cvlan patch and ip tos/ttl patch
- patch 7:
- templave priv is no longer passed as an arg to "change" op
- patch 11:
- split from the originally single patch
- patch 12:
- split from the originally single patch
v2->v3:
- patch 7:
- rebase on top of the reoffload patchset
- patch 8:
- rebase on top of the reoffload patchset
v1->v2:
- patch 8:
- remove leftover extack arg in fl_hw_create_tmplt()
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Since cld_flower provides information about the filter template for
specific chain, use this information in order to prepare a region.
Use the template to find out what elements are going to be used
and pass that down to mlxsw_sp_acl_tcam_group_add(). Later on, when the
first filter is inserted, the mlxsw_sp_acl_tcam_group_use_patterns()
function would use this element usage information instead of looking
up a pattern.
Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net: sched: cls_flower: propagate chain teplate creation and destruction to drivers
Introduce a couple of flower offload commands in order to propagate
template creation/destruction events down to device drivers.
Drivers may use this information to prepare HW in an optimal way
for future filter insertions.
Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Use the previously introduced template extension and implement
callback to create, destroy and dump chain template. The existing
parsing and dumping functions are re-used. Also, check if newly added
filters fit the template if it is set.
Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Allow user to set a template for newly created chains. Template lock
down the chain for particular classifier type/options combinations.
The classifier needs to support templates, otherwise kernel would
reply with error.
Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Allow user to create, destroy, get and dump chain objects. Do that by
extending rtnl commands by the chain-specific ones. User will now be
able to explicitly create or destroy chains (so far this was done only
automatically according the filter/act needs and refcounting). Also, the
user will receive notification about any chain creation or destuction.
Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, chain 0 is implicitly created during block creation. However
that does not align with chain object exposure, creation and destruction
api introduced later on. So make the chain 0 behave the same way as any
other chain and only create it when it is needed. Since chain 0 is
somehow special as the qdiscs need to hold pointer to the first chain
tp, this requires to move the chain head change callback infra to the
block structure.
Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
====================
net: ethernet: ti: cpsw: add MQPRIO and CBS Qdisc offload
This series adds MQPRIO and CBS Qdisc offload for TI cpsw driver.
It potentially can be used in audio video bridging (AVB) and time
sensitive networking (TSN).
Patchset was tested on AM572x EVM and BBB boards. Last patch from this
series adds detailed description of configuration with examples. For
consistency reasons, in role of talker and listener, tools from
patchset "TSN: Add qdisc based config interface for CBS" were used and
can be seen here: https://www.spinics.net/lists/netdev/msg460869.html
Based on net-next/master
v5..v4:
- corrected typo of "am57xx" board name, no functional changes
v4..v3:
- nothing, just rebase
v3..v2:
- corrected typo of "shaper" word, no functional changes
v2..v1:
- changed name cpsw.txt on ti-cpsw.txt
- changed name cpsw_set_tc() on cpsw_set_mqprio()
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Ivan Khoronzhuk [Mon, 23 Jul 2018 21:26:34 +0000 (00:26 +0300)]
Documentation: networking: cpsw: add MQPRIO & CBS offload examples
This document describes MQPRIO and CBS Qdisc offload configuration
for cpsw driver based on examples. It potentially can be used in
audio video bridging (AVB) and time sensitive networking (TSN).
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Ivan Khoronzhuk [Mon, 23 Jul 2018 21:26:33 +0000 (00:26 +0300)]
net: ethernet: ti: cpsw: restore shaper configuration while down/up
Need to restore shapers configuration after interface was down/up.
This is needed as appropriate configuration is still replicated in
kernel settings. This only shapers context restore, so vlan
configuration should be restored by user if needed, especially for
devices with one port where vlan frames are sent via ALE.
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Ivan Khoronzhuk [Mon, 23 Jul 2018 21:26:32 +0000 (00:26 +0300)]
net: ethernet: ti: cpsw: add CBS Qdisc offload
The cpsw has up to 4 FIFOs per port and upper 3 FIFOs can feed rate
limited queue with shaping. In order to set and enable shaping for
those 3 FIFOs queues the network device with CBS qdisc attached is
needed. The CBS configuration is added for dual-emac/single port mode
only, but potentially can be used in switch mode also, based on
switchdev for instance.
Despite the FIFO shapers can work w/o cpdma level shapers the base
usage must be in combine with cpdma level shapers as described in TRM,
that are set as maximum rates for interface queues with sysfs.
One of the possible configuration with txq shapers and CBS shapers:
CBS shaper configuration is supposed to be used with root MQPRIO Qdisc
offload allowing to add sk_prio->tc->txq maps that direct traffic to
appropriate tx queue and maps L2 priority to FIFO shaper.
The CBS shaper is intended to be used for AVB where L2 priority
(pcp field) is used to differentiate class of traffic. So additionally
vlan needs to be created with appropriate egress sk_prio->l2 prio map.
If CBS has several tx queues assigned to it, the sum of their
bandwidth has not overlap bandwidth set for CBS. It's recomended the
CBS bandwidth to be a little bit more.
The CBS shaper is configured with CBS qdisc offload interface using tc
tool from iproute2 packet.
$ tc -g class show dev eth0
+---(100:ffe2) mqprio
| +---(100:3) mqprio
| +---(100:4) mqprio
|
+---(100:ffe1) mqprio
| +---(100:2) mqprio
|
+---(100:ffe0) mqprio
+---(100:1) mqprio
$ tc qdisc add dev eth0 parent 100:1 cbs locredit -1440 \
hicredit 60 sendslope -960000 idleslope 40000 offload 1
$ tc qdisc add dev eth0 parent 100:2 cbs locredit -1470 \
hicredit 62 sendslope -980000 idleslope 20000 offload 1
The above code set CBS shapers for tc0 and tc1, for that txq0 and
txq1 is used. Pay attention, the real set bandwidth can differ a bit
due to discreteness of configuration parameters.
Here parameters like locredit, hicredit and sendslope are ignored
internally and are supposed to be set with assumption that maximum
frame size for frame - 1500.
It's supposed that interface speed is not changed while reconnection,
not always is true, so inform user in case speed of interface was
changed, as it can impact on dependent shapers configuration.
For more examples see Documentation.
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> Signed-off-by: David S. Miller <davem@davemloft.net>
$ tc -g class show dev eth0
+---(100:ffe2) mqprio
| +---(100:3) mqprio
| +---(100:4) mqprio
|
+---(100:ffe1) mqprio
| +---(100:2) mqprio
|
+---(100:ffe0) mqprio
+---(100:1) mqprio
Here, 100:1 is txq0, 100:2 is txq1, 100:3 is txq2, 100:4 is txq3
txq0 belongs to tc0, txq1 to tc1, txq2 and txq3 to tc2
The offload part only maps L2 prio to classes of traffic, but not
to transmit queues, so to direct traffic to traffic class vlan has
to be created with appropriate egress map.
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Ivan Khoronzhuk [Mon, 23 Jul 2018 21:26:30 +0000 (00:26 +0300)]
net: ethernet: ti: cpdma: fit rated channels in backward order
According to TRM tx rated channels should be in 7..0 order,
so correct it.
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Ivan Khoronzhuk [Mon, 23 Jul 2018 21:26:29 +0000 (00:26 +0300)]
net: ethernet: ti: cpsw: use cpdma channels in backward order for txq
The cpdma channel highest priority is from hi to lo number.
The driver has limited number of descriptors that are shared between
number of cpdma channels. Number of queues can be tuned with ethtool,
that allows to not spend descriptors on not needed cpdma channels.
In AVB usually only 2 tx queues can be enough with rate limitation.
The rate limitation can be used only for hi priority queues. Thus, to
use only 2 queues the 8 has to be created. It's wasteful.
So, in order to allow using only needed number of rate limited
tx queues, save resources, and be able to set rate limitation for
them, let assign tx cpdma channels in backward order to queues.
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 24 Jul 2018 03:22:33 +0000 (20:22 -0700)]
Merge tag 'mlx5e-updates-2018-07-18-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
mlx5e-updates-2018-07-18
This series includes update for mlx5e net device driver.
1) From Feras Daoud, Added the support for firmware log tracing,
first by introducing the firmware API needed for the task and then
For each PF do the following:
1- Allocate memory for the tracer strings database and read it from the FW to the SW.
2- Allocate and dma map tracer buffers.
Traces that will be written into the buffer will be parsed as a group
of one or more traces, referred to as trace message. The trace message
represents a C-like printf string.
Once a new trace is available FW will generate an event indicates new trace/s are
available and the driver will parse them and dump them using tracepoints
event tracing
2) From Roi Dayan, Remove redundant WARN when we cannot find neigh entry
3) From Jianbo Liu, TC double vlan support
- Support offloading tc double vlan headers match
- Support offloading double vlan push/pop tc actions
4) From Boris, re-visit UDP GSO, remove the splitting of UDP_GSO_L4 packets
in the driver, and exposes UDP_GSO_L4 as a PARTIAL_GSO feature.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Boris Pismenny [Sat, 30 Jun 2018 19:14:27 +0000 (22:14 +0300)]
net/mlx5e: Use PARTIAL_GSO for UDP segmentation
This patch removes the splitting of UDP_GSO_L4 packets in the driver,
and exposes UDP_GSO_L4 as a PARTIAL_GSO feature. Thus, the network stack
is not responsible for splitting the packet into two.
Signed-off-by: Boris Pismenny <borisp@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Roi Dayan [Mon, 4 Dec 2017 14:46:30 +0000 (16:46 +0200)]
net/mlx5e: Remove redundant WARN when we cannot find neigh entry
It is possible for neigh entry not to exist if it was cleaned already.
When we bring down an interface the neigh gets deleted but it could be
that our listener for neigh event to clear the encap valid bit didn't
start yet and the neigh update last used work is started first.
In this scenario the encap entry has valid bit set but the neigh entry
doesn't exist.
Signed-off-by: Roi Dayan <roid@mellanox.com> Reviewed-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Feras Daoud [Sun, 18 Feb 2018 08:06:35 +0000 (10:06 +0200)]
net/mlx5: FW tracer, parse traces and kernel tracing support
For each message the driver should do the following:
1- Find the message string in the strings database
2- Count the param number of each message
3- Wait for the param events and accumulate them
4- Calculate the event timestamp using the local event timestamp
and the first timestamp event following it.
5- Print message to trace log
Enable the tracing by:
echo 1 > /sys/kernel/debug/tracing/events/mlx5/mlx5_fw/enable
Feras Daoud [Wed, 7 Feb 2018 09:08:56 +0000 (11:08 +0200)]
net/mlx5: FW tracer, events handling
The tracer has one event, event 0x26, with two subtypes:
- Subtype 0: Ownership change
- Subtype 1: Traces available
An ownership change occurs in the following cases:
1- Owner releases his ownership, in this case, an event will be
sent to inform others to reattempt acquire ownership.
2- Ownership was taken by a higher priority tool, in this case
the owner should understand that it lost ownership, and go through
tear down flow.
The second subtype indicates that there are traces in the trace buffer,
in this case, the driver polls the tracer buffer for new traces, parse
them and prepares the messages for printing.
The HW starts tracing from the first address in the tracer buffer.
Driver receives an event notifying that new trace block exists.
HW posts a timestamp event at the last 8B of every 256B block.
Comparing the timestamp to the last handled timestamp would indicate
that this is a new trace block. Once the new timestamp is detected,
the entire block is considered valid.
Block validation and parsing, should be done after copying the current
block to a different location, in order to avoid block overwritten
during processing.
Feras Daoud [Tue, 6 Feb 2018 15:45:57 +0000 (17:45 +0200)]
net/mlx5: FW tracer, create trace buffer and copy strings database
For each PF do the following:
1- Allocate memory for the tracer strings database and read the
strings from the FW to the SW. These strings will be used later for
parsing traces.
2- Allocate and dma map tracer buffers.
Traces that will be written into the buffer will be parsed as a group
of one or more traces, referred to as trace message. The trace message
represents a C-like printf string.
First trace of a message holds the pointer to the correct string in
strings database. The following traces holds the variables of the
message.
Implement FW tracer logic and registers access, initialization and
cleanup flows.
Initializing the tracer will be part of load one flow, as multiple
PFs will try to acquire ownership but only one will succeed and will
be the tracer owner.
====================
lan743x: Add features to lan743x driver
This patch series adds extra features to the lan743x driver.
Updates for v4:
Patch 6/8 - Modified get/set_wol to use super set of
MAC and PHY driver support.
Patch 7/9 - In set_eee, return the return value from phy_ethtool_set_eee.
Updates for v3:
Removed patch 9 from this series, regarding PTP support
Patch 6/8 - Add call to phy_ethtool_get_wol to lan743x_ethtool_get_wol
Patch 7/8 - Add call to phy_ethtool_set_eee on (!eee->eee_enabled)
Updates for v2:
Patch 3/9 - Used ARRAY_SIZE macro in lan743x_ethtool_get_ethtool_stats.
Patch 5/9 - Used MAX_EEPROM_SIZE in lan743x_ethtool_set_eeprom.
Patch 6/9 - Removed unnecessary read of PMT_CTL.
Used CRC algorithm from lib.
Removed PHY interrupt settings from lan743x_pm_suspend
Change "#if CONFIG_PM" to "#ifdef CONFIG_PM"
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Implement ethtool eeprom access
Also provides access to OTP (One Time Programming)
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
Sergei Shtylyov [Mon, 23 Jul 2018 18:15:47 +0000 (21:15 +0300)]
sh_eth: make sh_eth_tsu_{read|write}_entry() prototypes symmetric
sh_eth_tsu_read_entry() is still asymmetric with sh_eth_tsu_write_entry()
WRT their prototypes -- make them symmetric by passing to the former a TSU
register offset instead of its address and also adding the (now necessary)
'ndev' parameter...
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Sergei Shtylyov [Mon, 23 Jul 2018 18:12:38 +0000 (21:12 +0300)]
sh_eth: call sh_eth_tsu_get_offset() from TSU register accessors
With sh_eth_tsu_get_offset() now actually returning TSU register's offset,
we can at last use it in sh_eth_tsu_{read|write}(). Somehow this saves 248
bytes of object code with AArch64 gcc 4.8.5... :-)
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Sergei Shtylyov [Mon, 23 Jul 2018 18:11:19 +0000 (21:11 +0300)]
sh_eth: make sh_eth_tsu_get_offset() match its name
sh_eth_tsu_get_offset(), despite its name, returns a TSU register's address,
not its offset. Make this function match its name and return a register's
offset from the TSU registers base address instead.
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Sergei Shtylyov [Mon, 23 Jul 2018 18:10:02 +0000 (21:10 +0300)]
sh_eth: uninline sh_eth_tsu_get_offset()
sh_eth_tsu_get_offset() is called several times by the driver, remove
*inline* and move that function from the header to the driver itself
to let gcc decide whether to expand it inline or not...
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> Signed-off-by: David S. Miller <davem@davemloft.net>
wan/fsl_ucc_hdlc: use IS_ERR_VALUE() to check return value of qe_muram_alloc
qe_muram_alloc return a unsigned long integer,which should not
compared with zero. check it using IS_ERR_VALUE() to fix this.
Fixes: c19b6d246a35 ("drivers/net: support hdlc function for QE-UCC") Signed-off-by: YueHaibing <yuehaibing@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 23 Jul 2018 17:57:14 +0000 (10:57 -0700)]
Merge branch 'smc-next'
Ursula Braun says:
====================
net/smc: patches 2018-07-23
here are some small patches for SMC: Just the first patch contains a
functional change. It allows to differ between the modes SMCR and SMCD
on s390 when monitoring SMC sockets. The remaining patches are cleanups
without functional changes.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Stefan Raspl [Mon, 23 Jul 2018 11:53:10 +0000 (13:53 +0200)]
net/smc: add function to get link group from link
Replace a frequently used construct with a more readable variant,
reducing the code. Also might come handy when we start to support
more than a single per link group.
Signed-off-by: Stefan Raspl <raspl@linux.ibm.com> Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Stefan Raspl [Mon, 23 Jul 2018 11:53:09 +0000 (13:53 +0200)]
net/smc: eliminate cursor read and write calls
The functions to read and write cursors are exclusively used to copy
cursors. Therefore switch to a respective function instead.
Signed-off-by: Stefan Raspl <raspl@linux.ibm.com> Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Rename field diag_fallback into diag_mode and set the smc mode of a
connection explicitly.
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Petr Machata [Mon, 23 Jul 2018 10:33:08 +0000 (12:33 +0200)]
selftests: forwarding: gre_multipath: Drop IPv6 tests
Support for device-only IPv6 multipath next hops was dropped in
commit 33bd5ac54dc4 ("net/ipv6: Revert attempt to simplify route replace
and append") and as of commit b5d2d75e079a ("net/ipv6: Do not allow
device only routes via the multipath API"), attempts to add a next hop
like that yield an explicit diagnostic.
Correspondingly, drop the IPv6 parts of GRE multipath test that are
supposed to test that code.
Signed-off-by: Petr Machata <petrm@mellanox.com> Reviewed-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
====================
net: bridge: add support for backup port
This set introduces a new bridge port option that allows any port to have
any other port (in the same bridge of course) as its backup and traffic
will be forwarded to the backup port when the primary goes down. This is
mainly used in MLAG and EVPN setups where we have peerlink path which is
a backup of many (or even all) ports and is a participating bridge port
itself. There's more detailed information in patch 02. Patch 01 just
prepares the port sysfs code for options that take raw value. The main
issues that this set solves are scalability and fallback latency.
We have used similar code for over 6 months now to bring the fallback
latency of the backup peerlink down and avoid fdb notification storms.
Also due to the nature of master devices such setup is currently not
possible, and last but not least having tens of thousands of fdbs require
thousands of calls to switch.
I've also CCed our MLAG experts that have been using similar option.
Roopa also adds:
"Two switches acting in a MLAG pair are connected by the peerlink
interface which is a bridge port.
the config on one of the switches looks like the below. The other
switch also has a similar config.
eth0 is connected to one port on the server. And the server is
connected to both switches.
br0 -- team0---eth0
|
-- switch-peerlink
switch-peerlink becomes the failover/backport port when say team0 to
the server goes down.
Today, when team0 goes down, control plane has to withdraw all the fdb
entries pointing to team0
and re-install the fdb entries pointing to switch-peerlink...and
restore the fdb entries when team0 comes back up again.
and this is the problem we are trying to solve.
This also becomes necessary when multihoming is implemented by a
standard like E-VPN https://tools.ietf.org/html/rfc8365#section-8
where the 'switch-peerlink' is an overlay vxlan port (like nikolay
mentions in his patch commit). In these implementations, the fdb scale
can be much larger.
On why bond failover cannot be used here ?: the point that nikolay was
alluding to is, switch-peerlink in the above example is a bridge port
and is a failover/backport port for more than one or all ports in the
bridge br0. And you cannot enslave switch-peerlink into a second level
team
with other bridge ports. Hence a multi layered team device is not an
option (FWIW, switch-peerlink is also a teamed interface to the peer
switch)."
v3: Added Roopa's explanation and diagram
v2: In patch 01 use kstrdup/kfree to avoid casting the const buf. In order
to avoid using GFP_ATOMIC or always allocating I kept the spinlock inside
each branch.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds a new port attribute - IFLA_BRPORT_BACKUP_PORT, which
allows to set a backup port to be used for known unicast traffic if the
port has gone carrier down. The backup pointer is rcu protected and set
only under RTNL, a counter is maintained so when deleting a port we know
how many other ports reference it as a backup and we remove it from all.
Also the pointer is in the first cache line which is hot at the time of
the check and thus in the common case we only add one more test.
The backup port will be used only for the non-flooding case since
it's a part of the bridge and the flooded packets will be forwarded to it
anyway. To remove the forwarding just send a 0/non-existing backup port.
This is used to avoid numerous scalability problems when using MLAG most
notably if we have thousands of fdbs one would need to change all of them
on port carrier going down which takes too long and causes a storm of fdb
notifications (and again when the port comes back up). In a Multi-chassis
Link Aggregation setup usually hosts are connected to two different
switches which act as a single logical switch. Those switches usually have
a control and backup link between them called peerlink which might be used
for communication in case a host loses connectivity to one of them.
We need a fast way to failover in case a host port goes down and currently
none of the solutions (like bond) cannot fulfill the requirements because
the participating ports are actually the "master" devices and must have the
same peerlink as their backup interface and at the same time all of them
must participate in the bridge device. As Roopa noted it's normal practice
in routing called fast re-route where a precalculated backup path is used
when the main one is down.
Another use case of this is with EVPN, having a single vxlan device which
is backup of every port. Due to the nature of master devices it's not
currently possible to use one device as a backup for many and still have
all of them participate in the bridge (which is master itself).
More detailed information about MLAG is available at the link below.
https://docs.cumulusnetworks.com/display/DOCS/Multi-Chassis+Link+Aggregation+-+MLAG
Further explanation and a diagram by Roopa:
Two switches acting in a MLAG pair are connected by the peerlink
interface which is a bridge port.
the config on one of the switches looks like the below. The other
switch also has a similar config.
eth0 is connected to one port on the server. And the server is
connected to both switches.
br0 -- team0---eth0
|
-- switch-peerlink
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net: bridge: add support for raw sysfs port options
This patch adds a new alternative store callback for port sysfs options
which takes a raw value (buf) and can use it directly. It is needed for the
backup port sysfs support since we have to pass the device by its name.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Sat, 21 Jul 2018 04:14:39 +0000 (21:14 -0700)]
nfp: avoid buffer leak when FW communication fails
After device is stopped we reset the rings by moving all free buffers
to positions [0, cnt - 2], and clear the position cnt - 1 in the ring.
We then proceed to clear the read/write pointers. This means that if
we try to reset the ring again the code will assume that the next to
fill buffer is at position 0 and swap it with cnt - 1. Since we
previously cleared position cnt - 1 it will lead to leaking the first
buffer and leaving ring in a bad state.
This scenario can only happen if FW communication fails, in which case
the ring will never be used again, so the fact it's in a bad state will
not be noticed. Buffer leak is the only problem. Don't try to move
buffers in the ring if the read/write pointers indicate the ring was
never used or have already been reset.
nfp_net_clear_config_and_disable() is now fully idempotent.
Found by code inspection, FW communication failures are very rare,
and reconfiguring a live device is not common either, so it's unlikely
anyone has ever noticed the leak.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Sat, 21 Jul 2018 04:14:38 +0000 (21:14 -0700)]
nfp: bring back support for offloading shared blocks
Now that we have offload replay infrastructure added by
commit 326367427cc0 ("net: sched: call reoffload op on block callback reg")
and flows are guaranteed to be removed correctly, we can revert
commit 951a8ee6def3 ("nfp: reject binding to shared blocks").
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Reviewed-by: John Hurley <john.hurley@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Commit f599c64fdf7d ("xen-netfront: Fix race between device setup and
open") changed the initialization order: xennet_create_queues() now
happens before we do register_netdev() so using netdev->name in
xennet_init_queue() is incorrect, we end up with the following in
/proc/interrupts:
and this looks ugly. Actually, using early netdev name (even when it's
already set) is also not ideal: nowadays we tend to rename eth devices
and queue name may end up not corresponding to the netdev name.
Use nodename from xenbus device for queue naming: this can't change in VM's
lifetime. Now /proc/interrupts looks like
Fixes: f599c64fdf7d ("xen-netfront: Fix race between device setup and open") Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Reviewed-by: Ross Lagerwall <ross.lagerwall@citrix.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Randy Dunlap [Fri, 20 Jul 2018 16:16:02 +0000 (09:16 -0700)]
net/dsa/realtek: add MODULE_LICENSE()
Add MODULE_LICENSE() to net/dsa/realtek.o to fix build warning message.
WARNING: modpost: missing MODULE_LICENSE() in drivers/net/dsa/realtek.o
Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Linus Walleij <linus.walleij@linaro.org> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: David S. Miller <davem@davemloft.net>
====================
TX used ring batched updating for vhost
This series implement batch updating of used ring for TX. This help to
reduce the cache contention on used ring. The idea is first split
datacopy path from zerocopy, and do only batching for datacopy. This
is because zercopy had already supported its own batching.
TX PPS was increased 25.8% and Netperf TCP does not show obvious
differences.
The split of datapath will also be helpful for future implementation
like in order completion.
====================
Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jason Wang [Fri, 20 Jul 2018 00:15:21 +0000 (08:15 +0800)]
vhost_net: batch update used ring for datacopy TX
Like commit e2b3b35eb989 ("vhost_net: batch used ring update in rx"),
this patches implements batch used ring update for datacopy TX
(zerocopy has already done some kind of batching).
Testpmd transmission from guest to host (XDP_DROP on tap) shows 25.8%
improvement (from ~3.1Mpps to ~3.9Mpps) on Broadwell i7-5600U CPU @
2.60GHz machine. Netperf TCP tests does not show obvious differences.
Signed-off-by: Jason Wang <jasowang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jason Wang [Fri, 20 Jul 2018 00:15:18 +0000 (08:15 +0800)]
vhost_net: split out datacopy logic
Instead of mixing zerocopy and datacopy logics, this patch tries to
split datacopy logic out. This results for a more compact code and
ad-hoc optimization could be done on top more easily.
Signed-off-by: Jason Wang <jasowang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Hangbin Liu [Fri, 20 Jul 2018 06:07:42 +0000 (14:07 +0800)]
multicast: remove useless parameter for group add
Remove the mode parameter for igmp/igmp6_group_added as we can get it
from first parameter.
Fixes: 6e2059b53f988 (ipv4/igmp: init group mode as INCLUDE when join source group) Fixes: c7ea20c9da5b9 (ipv6/mcast: init as INCLUDE when join SSM INCLUDE group) Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
"imply HWMON" was supposed to ensure that the SFP phy code can be built
with HWMON enabled or disabled while at the same time ensuring that
HWMON is not built as module if SFP is built into the kernel.
Unfortunately, that does not work as intended. With "allmodconfig", it
results in several unrelated HWMON drivers to be disabled instead of
being built as module as expected.
Let's use the old "depends on HWMON || HWMON=n" instead. This is slightly
different (it enforces SFP to be built as module if HWMON is built as
module), but it is better than the alternative of using "IS_REACHABLE()"
in the driver since that would disable sensor support if HWMON is built
as module and SFP is built into the kernel.
Fixes: 1323061a018a ("net: phy: sfp: Add HWMON support for module sensors") Cc: Andrew Lunn <andrew@lunn.ch> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
net/tipc/link.c:376:5: warning: symbol 'link_bc_rcv_gap' was not declared. Should it be static?
net/tipc/link.c:823:6: warning: symbol 'link_prepare_wakeup' was not declared. Should it be static?
net/tipc/link.c:959:6: warning: symbol 'tipc_link_advance_backlog' was not declared. Should it be static?
net/tipc/link.c:1009:5: warning: symbol 'tipc_link_retrans' was not declared. Should it be static?
net/tipc/monitor.c:687:5: warning: symbol '__tipc_nl_add_monitor_peer' was not declared. Should it be static?
net/tipc/group.c:230:20: warning: symbol 'tipc_group_find_member' was not declared. Should it be static?
Signed-off-by: YueHaibing <yuehaibing@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
1) Fix up units mismatch regarding msec/jiffies.
2) Address possiblility of time_remaining being negative.
3) Add a helper routine tcp_clamp_rto_to_user_timeout() to do the rto
calculation.
4) Move start_ts logic into helper routine tcp_retrans_stamp() to
validate tcp_sk(sk)->retrans_stamp.
5) Some u32 declation and return refactoring.
6) Return 0 instead of false in tcp_retransmit_stamp(), it's not a bool.
Suggestions by David Laight:
1) Don't cache rto in tcp_clamp_rto_to_user_timeout().
Suggestions by Eric Dumazet:
1) Make u32 declartions consistent.
2) Use patch series for easier review.
3) Convert icsk->icsk_user_timeout to millisconds to avoid jiffie to
msec dance.
4) Use seperate titles for each commit in the series.
5) Fix fuzzy indentation and line wrap issues.
6) Make commit titles descriptive.
Changes:
1) Call tcp_clamp_rto_to_user_timeout(sk) as an argument to
inet_csk_reset_xmit_timer() to save on rto declaration.
Every time the TCP retransmission timer fires. It checks to see if
there is a timeout before scheduling the next retransmit timer. The
retransmit interval between each retransmission increases
exponentially. The issue is that in order for the timeout to occur the
retransmit timer needs to fire again. If the user timeout check happens
after the 9th retransmit for example. It needs to wait for the 10th
retransmit timer to fire in order to evaluate whether a timeout has
occurred or not. If the interval is large enough then the timeout will
be inaccurate.
For example with a TCP_USER_TIMEOUT of 10 seconds without patch:
1st retransmit:
22:25:18.973488 IP host1.49310 > host2.search-agent: Flags [.]
Last retransmit:
22:25:26.205499 IP host1.49310 > host2.search-agent: Flags [.]
Timeout:
send: Connection timed out
Sun Jul 1 22:25:34 EDT 2018
We can see that last retransmit took ~7 seconds. Which pushed the total
timeout to ~15 seconds instead of the expected 10 seconds. This gets
more inaccurate the larger the TCP_USER_TIMEOUT value. As the interval
increases.
Add tcp_clamp_rto_to_user_timeout() to determine if the user rto has
expired. Or whether the rto interval needs to be recalculated. Use the
original interval if user rto is not set.
Test results with the patch is the expected 10 second timeout:
1st retransmit:
01:37:59.022555 IP host1.49310 > host2.search-agent: Flags [.]
Last retransmit:
01:38:06.486558 IP host1.49310 > host2.search-agent: Flags [.]
Jon Maxwell [Thu, 19 Jul 2018 01:14:44 +0000 (11:14 +1000)]
tcp: Add tcp_clamp_rto_to_user_timeout() helper to improve accuracy
Create the tcp_clamp_rto_to_user_timeout() helper routine. To calculate
the correct rto, so that the TCP_USER_TIMEOUT socket option is more
accurate. Taking suggestions and feedback into account from
Eric Dumazet, Neal Cardwell and David Laight. Due to the 1st commit we
can avoid the msecs_to_jiffies() and jiffies_to_msecs() dance.
Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Maxwell [Thu, 19 Jul 2018 01:14:43 +0000 (11:14 +1000)]
tcp: Add tcp_retransmit_stamp() helper routine
Create a seperate helper routine as per Neal Cardwells suggestion. To
be used by the final commit in this series and retransmits_timed_out().
Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Maxwell [Thu, 19 Jul 2018 01:14:42 +0000 (11:14 +1000)]
tcp: convert icsk_user_timeout from jiffies to msecs
This is a preparatory commit. Part of this series that improves the
socket TCP_USER_TIMEOUT option accuracy. Implement Eric Dumazets idea
to convert icsk->icsk_user_timeout from jiffies to msecs. To eliminate
the msecs_to_jiffies() and jiffies_to_msecs() dance in future.
Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
please apply one more round of qeth patches to net-next.
This brings additional performance improvements for the transmit code,
and some refactoring to pave the way for using netdev_priv.
Also, two minor fixes for rare corner cases.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Modify the L2 OSA xmit path so that it also supports L2 IQD devices
(in particular, their HW header requirements). This allows IQD devices
to advertise NETIF_F_SG support, and eliminates the allocation overhead
for the HW header.
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Some transmit modes require that the HW header is located in the same
page as the initial protocol headers in skb->data. Let callers specify
the size of this contiguous header range, and enforce it when building
the HW header.
While at it, apply some gentle renaming to the relevant L2 code so that
it matches the L3 code.
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
s390/qeth: merge linearize-check into HW header construction
When checking whether an skb needs to be linearized to fit into an IO
buffer, it's desirable to consider the skb's final size and layout
(ie. after the HW header was added). But a subsequent linearization can
then cause the re-positioned HW header to violate its alignment
restrictions.
Dealing with this situation in two different code paths is quite tricky.
This patch integrates a) linearize-check and b) HW header construction
into one 3 step-sequence:
1. evaluate how the HW header needs to be added (to identify if it takes
up an additional buffer element), then
2. check if the required buffer elements exceed the device's limit.
Linearize when necessary and re-evaluate the HW header placement.
3. Add the HW header in the best-possible way:
a) push, without taking up an additional buffer element
b) push, but consume another buffer element
c) allocate a header object from the cache.
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
s390/qeth: add statistics for consumed buffer elements
Nowadays an skb fragment typically spans over multiple pages. So replace
the obsolete, SG-only 'fragments' counter with one that tracks the
consumed buffer elements. This is what actually matters for performance.
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
When the MPC initialization code discovers the HW-specific max MTU,
apply the resulting changes straight to the netdevice.
If this is the device's first initialization, also set its MTU
(HiperSockets: the max MTU; else: a layer-specific default value).
Then cap the current MTU by the new max MTU.
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Allocation of the netdevice is currently delayed until a qeth card first
goes online. This complicates matters in several places, where we need
to cache values instead of applying them straight to the netdevice.
Improve on this by moving the allocation up to where the qeth card
itself is created. This is also one step in direction of eventually
placing the qeth card into netdev_priv().
In all subsequent code, remove the now redundant checks whether
card->dev is valid.
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
projects / mirror_ubuntu-hirsute-kernel.git / log