For the XDP bonding slave lookup to work in the NAPI poll context in which
the redudant rcu_read_lock() has been removed we have to follow the same
approach as in 694cea395f ("bpf: Allow RCU-protected lookups to happen
from bh context") and modify the WARN_ON to also check rcu_read_lock_bh_held().
Signed-off-by: Jussi Maki <joamaki@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20210731055738.16820-6-joamaki@gmail.com
XDP is implemented in the bonding driver by transparently delegating
the XDP program loading, removal and xmit operations to the bonding
slave devices. The overall goal of this work is that XDP programs
can be attached to a bond device *without* any further changes (or
awareness) necessary to the program itself, meaning the same XDP
program can be attached to a native device but also a bonding device.
Semantics of XDP_TX when attached to a bond are equivalent in such
setting to the case when a tc/BPF program would be attached to the
bond, meaning transmitting the packet out of the bond itself using one
of the bond's configured xmit methods to select a slave device (rather
than XDP_TX on the slave itself). Handling of XDP_TX to transmit
using the configured bonding mechanism is therefore implemented by
rewriting the BPF program return value in bpf_prog_run_xdp. To avoid
performance impact this check is guarded by a static key, which is
incremented when a XDP program is loaded onto a bond device. This
approach was chosen to avoid changes to drivers implementing XDP. If
the slave device does not match the receive device, then XDP_REDIRECT
is transparently used to perform the redirection in order to have
the network driver release the packet from its RX ring. The bonding
driver hashing functions have been refactored to allow reuse with
xdp_buff's to avoid code duplication.
The motivation for this change is to enable use of bonding (and
802.3ad) in hairpinning L4 load-balancers such as [1] implemented with
XDP and also to transparently support bond devices for projects that
use XDP given most modern NICs have dual port adapters. An alternative
to this approach would be to implement 802.3ad in user-space and
implement the bonding load-balancing in the XDP program itself, but
is rather a cumbersome endeavor in terms of slave device management
(e.g. by watching netlink) and requires separate programs for native
vs bond cases for the orchestrator. A native in-kernel implementation
overcomes these issues and provides more flexibility.
Below are benchmark results done on two machines with 100Gbit
Intel E810 (ice) NIC and with 32-core 3970X on sending machine, and
16-core 3950X on receiving machine. 64 byte packets were sent with
pktgen-dpdk at full rate. Two issues [2, 3] were identified with the
ice driver, so the tests were performed with iommu=off and patch [2]
applied. Additionally the bonding round robin algorithm was modified
to use per-cpu tx counters as high CPU load (50% vs 10%) and high rate
of cache misses were caused by the shared rr_tx_counter (see patch
2/3). The statistics were collected using "sar -n dev -u 1 10". On top
of that, for ice, further work is in progress on improving the XDP_TX
numbers [4].
-----------------------| CPU |--| rxpck/s |--| txpck/s |----
without patch (1 dev):
XDP_DROP: 3.15% 48.6Mpps
XDP_TX: 3.12% 18.3Mpps 18.3Mpps
XDP_DROP (RSS): 9.47% 116.5Mpps
XDP_TX (RSS): 9.67% 25.3Mpps 24.2Mpps
-----------------------
with patch, bond (1 dev):
XDP_DROP: 3.14% 46.7Mpps
XDP_TX: 3.15% 13.9Mpps 13.9Mpps
XDP_DROP (RSS): 10.33% 117.2Mpps
XDP_TX (RSS): 10.64% 25.1Mpps 24.0Mpps
-----------------------
with patch, bond (2 devs):
XDP_DROP: 6.27% 92.7Mpps
XDP_TX: 6.26% 17.6Mpps 17.5Mpps
XDP_DROP (RSS): 11.38% 117.2Mpps
XDP_TX (RSS): 14.30% 28.7Mpps 27.4Mpps
--------------------------------------------------------------
RSS: Receive Side Scaling, e.g. the packets were sent to a range of
destination IPs.
[1]: https://cilium.io/blog/2021/05/20/cilium-110#standalonelb
[2]: https://lore.kernel.org/bpf/20210601113236.42651-1-maciej.fijalkowski@intel.com/T/#t
[3]: https://lore.kernel.org/bpf/CAHn8xckNXci+X_Eb2WMv4uVYjO2331UWB2JLtXr_58z0Av8+8A@mail.gmail.com/
[4]: https://lore.kernel.org/bpf/20210805230046.28715-1-maciej.fijalkowski@intel.com/T/#t
Signed-off-by: Jussi Maki <joamaki@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Cc: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Cc: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20210731055738.16820-4-joamaki@gmail.com
This adds the ndo_xdp_get_xmit_slave hook for transforming XDP_TX
into XDP_REDIRECT after BPF program run when the ingress device
is a bond slave.
The dev_xdp_prog_count is exposed so that slave devices can be checked
for loaded XDP programs in order to avoid the situation where both
bond master and slave have programs loaded according to xdp_state.
Signed-off-by: Jussi Maki <joamaki@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Link: https://lore.kernel.org/bpf/20210731055738.16820-3-joamaki@gmail.com
In preparation for adding XDP support to the bonding driver
refactor the packet hashing functions to be able to work with
any linear data buffer without an skb.
Signed-off-by: Jussi Maki <joamaki@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Link: https://lore.kernel.org/bpf/20210731055738.16820-2-joamaki@gmail.com
Fix a typo when checking existence of port_type_set function pointer.
Fixes: 82564f6c70 ("devlink: Simplify devlink port API calls")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit a3fe3d01bd ("net/smc: introduce sg-logic for RMBs") introduced
a restriction for RMB allocations as used by SMC-R. However, SMC-D does
not use scatter-gather lists to back its DMBs, yet it was limited by
this restriction, still.
This patch exempts SMC, but limits allocations to the maximum RMB/DMB
size respectively.
Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Guvenc Gulce <guvenc@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
All kernel devlink implementations call to devlink_alloc() during
initialization routine for specific device which is used later as
a parent device for devlink_register().
Such late device assignment causes to the situation which requires us to
call to device_register() before setting other parameters, but that call
opens devlink to the world and makes accessible for the netlink users.
Any attempt to move devlink_register() to be the last call generates the
following error due to access to the devlink->dev pointer.
[ 8.758862] devlink_nl_param_fill+0x2e8/0xe50
[ 8.760305] devlink_param_notify+0x6d/0x180
[ 8.760435] __devlink_params_register+0x2f1/0x670
[ 8.760558] devlink_params_register+0x1e/0x20
The simple change of API to set devlink device in the devlink_alloc()
instead of devlink_register() fixes all this above and ensures that
prior to call to devlink_register() everything already set.
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The driver allocates the spinlock but not initialize it.
Use spin_lock_init() on it to initialize it correctly.
Fixes: aa730a9905 ("net: wwan: Add MHI MBIM network driver")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Reviewed-by: Sergey Ryazanov <ryazanov.s.a@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Karsten Graul says:
====================
net/iucv: updates 2021-08-09
Please apply the following iucv patches to netdev's net-next tree.
Remove the usage of register asm statements and replace deprecated
CPU-hotplug functions with the current version.
Use use consume_skb() instead of kfree_skb() to avoid flooding
dropwatch with false-positives, and 2 patches with cleanups.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The functions get_online_cpus() and put_online_cpus() have been
deprecated during the CPU hotplug rework. They map directly to
cpus_read_lock() and cpus_read_unlock().
Replace deprecated CPU-hotplug functions with the official version.
The behavior remains unchanged.
Cc: Julian Wiedmann <jwi@linux.ibm.com>
Cc: Karsten Graul <kgraul@linux.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: linux-s390@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Using register asm statements has been proven to be very error prone,
especially when using code instrumentation where gcc may add function
calls, which clobbers register contents in an unexpected way.
Therefore get rid of register asm statements in iucv code, even though
there is currently nothing wrong with it. This way we know for sure
that the above mentioned bug class won't be introduced here.
Acked-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
These wrappers are just unnecessary obfuscation.
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use IS_ENABLED(CONFIG_IUCV) to determine whether the iucv_if symbol
is available, and let depmod deal with the module dependency.
This was introduced back with commit 6fcd61f7bf ("af_iucv: use
loadable iucv interface"). And to avoid sprinkling IS_ENABLED() over
all the code, we're keeping the indirection through pr_iucv->...().
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change the good paths to use consume_skb() instead of kfree_skb(). This
avoids flooding dropwatch with false-positives.
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vladimir Oltean says:
====================
DSA fast ageing fixes/improvements
These are 2 small improvements brought to the DSA fast ageing changes
merged earlier today.
Patch 1 restores the behavior for DSA drivers that don't implement the
.port_bridge_flags function (I don't think there is any breakage due
to the new behavior, but just to be sure). This came as a result of
Andrew's review.
Patch 2 reduces the number of fast ages of a port from 2 to 1 when it
leaves a bridge.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Drivers that support both the toggling of address learning and dynamic
FDB flushing (mv88e6xxx, b53, sja1105) currently need to fast-age a port
twice when it leaves a bridge:
- once, when del_nbp() calls br_stp_disable_port() which puts the port
in the BLOCKING state
- twice, when dsa_port_switchdev_unsync_attrs() calls
dsa_port_clear_brport_flags() which disables address learning
The knee-jerk reaction might be to say "dsa_port_clear_brport_flags does
not need to fast-age the port at all", but the thing is, we still need
both code paths to flush the dynamic FDB entries in different situations.
When a DSA switch port leaves a bonding/team interface that is (still) a
bridge port, no del_nbp() will be called, so we rely on
dsa_port_clear_brport_flags() function to restore proper standalone port
functionality with address learning disabled.
So the solution is just to avoid double the work when both code paths
are called in series. Luckily, DSA already caches the STP port state, so
we can skip flushing the dynamic FDB when we disable address learning
and the STP state is one where no address learning takes place at all.
Under that condition, not flushing the FDB is safe because there is
supposed to not be any dynamic FDB entry at all (they were flushed
during the transition towards that state, and none were learned in the
meanwhile).
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 39f3210154 ("net: dsa: don't fast age standalone ports")
assumed that all standalone ports disable address learning, but if the
switch driver implements .port_fast_age but not .port_bridge_flags (like
ksz9477, ksz8795, lantiq_gswip, lan9303), then that might not actually
be true.
So whereas before, the bridge temporarily walking us through the
BLOCKING STP state meant that the standalone ports had a checkpoint to
flush their baggage and start fresh when they join a bridge, after that
commit they no longer do.
Restore the old behavior for these drivers by checking if the switch can
toggle address learning. If it can't, disregard the "do_fast_age"
argument and unconditionally perform fast ageing on STP state changes.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For historical reasons x_tables still register tables by default in the
initial namespace.
Only newly created net namespaces add the hook on demand.
This means that the init_net always pays hook cost, even if no filtering
rules are added (e.g. only used inside a single netns).
Note that the hooks are added even when 'iptables -L' is called.
This is because there is no way to tell 'iptables -A' and 'iptables -L'
apart at kernel level.
The only solution would be to register the table, but delay hook
registration until the first rule gets added (or policy gets changed).
That however means that counters are not hooked either, so 'iptables -L'
would always show 0-counters even when traffic is flowing which might be
unexpected.
This keeps table and hook registration consistent with what is already done
in non-init netns: first iptables(-save) invocation registers both table
and hooks.
This applies the same solution adopted for ebtables.
All tables register a template that contains the l3 family, the name
and a constructor function that is called when the initial table has to
be added.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Vladimir Oltean says:
====================
Fast ageing support for SJA1105 DSA driver
While adding support for flushing dynamically learned FDB entries in the
sja1105 driver, I noticed a few things that could be improved in DSA.
Most notably, drivers could omit a fast age when address learning is
turned off, which might mean that ports leaving a bridge and becoming
standalone could still have FDB entries pointing towards them. Secondly,
when DSA fast ages a port after the 'learning' flag has been turned off,
the software bridge still has the dynamically learned 'master' FDB
entries installed, and those should be deleted too.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Delete the dynamically learned FDB entries when the STP state changes
and when address learning is disabled.
On sja1105 there is no shorthand SPI command for this, so we need to
walk through the entire FDB to delete.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that DSA keeps track of the port learning state, it becomes
superfluous to keep an additional variable with this information in the
sja1105 driver. Remove it.
The DSA core's learning state is present in struct dsa_port *dp.
To avoid the antipattern where we iterate through a DSA switch's
ports and then call dsa_to_port to obtain the "dp" reference (which is
bad because dsa_to_port iterates through the DSA switch tree once
again), just iterate through the dst->ports and operate on those
directly.
The sja1105 had an extra use of priv->learn_ena on non-user ports. DSA
does not touch the learning state of those ports - drivers are free to
do what they wish on them. Mark that information with a comment in
struct dsa_port and let sja1105 set dp->learning for cascade ports.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, when DSA performs fast ageing on a port, 'bridge fdb' shows
us that the 'self' entries (corresponding to the hardware bridge, as
printed by dsa_slave_fdb_dump) are deleted, but the 'master' entries
(corresponding to the software bridge) aren't.
Indeed, searching through the bridge driver, neither the
brport_attr_learning handler nor the IFLA_BRPORT_LEARNING handler call
br_fdb_delete_by_port. However, br_stp_disable_port does, which is one
of the paths which DSA uses to trigger a fast ageing process anyway.
There is, however, one other very promising caller of
br_fdb_delete_by_port, and that is the bridge driver's handler of the
SWITCHDEV_FDB_FLUSH_TO_BRIDGE atomic notifier. Currently the s390/qeth
HiperSockets card driver is the only user of this.
I can't say I understand that driver's architecture or interaction with
the bridge, but it appears to not be a switchdev driver in the traditional
sense of the word. Nonetheless, the mechanism it provides is a useful
way for DSA to express the fact that it performs fast ageing too, in a
way that does not change the existing behavior for other drivers.
Cc: Alexandra Winter <wintera@linux.ibm.com>
Cc: Julian Wiedmann <jwi@linux.ibm.com>
Cc: Roopa Prabhu <roopa@nvidia.com>
Cc: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On topology changes, stations that were dynamically learned on ports
that are no longer part of the active topology must be flushed - this is
described by clause "17.11 Updating learned station location information"
of IEEE 802.1D-2004.
However, when address learning on the bridge port is turned off in the
first place, there is nothing to flush, so skip a potentially expensive
operation.
We can finally do this now since DSA is aware of the learning state of
its bridged ports.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently DSA leaves it down to device drivers to fast age the FDB on a
port when address learning is disabled on it. There are 2 reasons for
doing that in the first place:
- when address learning is disabled by user space, through
IFLA_BRPORT_LEARNING or the brport_attr_learning sysfs, what user
space typically wants to achieve is to operate in a mode with no
dynamic FDB entry on that port. But if the port is already up, some
addresses might have been already learned on it, and it seems silly to
wait for 5 minutes for them to expire until something useful can be
done.
- when a port leaves a bridge and becomes standalone, DSA turns off
address learning on it. This also has the nice side effect of flushing
the dynamically learned bridge FDB entries on it, which is a good idea
because standalone ports should not have bridge FDB entries on them.
We let drivers manage fast ageing under this condition because if DSA
were to do it, it would need to track each port's learning state, and
act upon the transition, which it currently doesn't.
But there are 2 reasons why doing it is better after all:
- drivers might get it wrong and not do it (see b53_port_set_learning)
- we would like to flush the dynamic entries from the software bridge
too, and letting drivers do that would be another pain point
So track the port learning state and trigger a fast age process
automatically within DSA.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It's "must not", not "musn't", meaning "shall not".
Let's fix that.
Suggested-by: Joe Perches <joe@perches.com>
Signed-off-by: Jun Miao <jun.miao@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Devlink port already has pointer to the devlink instance and all API
calls that forward these devlink ports to the drivers perform same
"devlink_port->devlink" assignment before actual call.
This patch removes useless parameter and allows us in the future
to create specific devlink_port_ops to manage user space access with
reliable ops assignment.
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
DSA drives the procedure to flush dynamic FDB entries from a port based
on the change of STP state: whenever we go from a state where address
learning is enabled (LEARNING, FORWARDING) to a state where it isn't
(LISTENING, BLOCKING, DISABLED), we need to flush the existing dynamic
entries.
However, there are cases when this is not needed. Internally, when a
DSA switch interface is not under a bridge, DSA still keeps it in the
"FORWARDING" STP state. And when that interface joins a bridge, the
bridge will meticulously iterate that port through all STP states,
starting with BLOCKING and ending with FORWARDING. Because there is a
state transition from the standalone version of FORWARDING into the
temporary BLOCKING bridge port state, DSA calls the fast age procedure.
Since commit 5e38c15856 ("net: dsa: configure better brport flags when
ports leave the bridge"), DSA asks standalone ports to disable address
learning. Therefore, there can be no dynamic FDB entries on a standalone
port. Therefore, it does not make sense to flush dynamic FDB entries on
one.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
commit <47595e32869f> ("<MAINTAINERS: Mark some staging directories>")
indicated the ipx network layer as obsolete in Jan 2018,
updated in the MAINTAINERS file
now, after being exposed for 3 years to refactoring,
so to delete the ipx net layer related code for good.
Signed-off-by: Cai Huoqing <caihuoqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When compiling with clang in certain configurations, an objtool warning
appears:
drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.o: warning: objtool:
ipq806x_gmac_probe() falls through to next function phy_modes()
This happens because the unreachable annotation in the third switch
statement is not eliminated. The compiler should know that the first
default case would prevent the second and third from being reached as
the comment notes but sanitizer options can make it harder for the
compiler to reason this out.
Help the compiler out by eliminating the unreachable() annotation and
unifying the default case error handling so that there is no objtool
warning, the meaning of the code stays the same, and there is less
duplication.
Reported-by: Sami Tolvanen <samitolvanen@google.com>
Tested-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Karsten Graul says:
====================
s390/qeth: Add bridge to switchdev LEARNING_SYNC
The netlink bridgeport attribute LEARNING_SYNC can be used to enable
qeth interfaces to report MAC addresses that are reachable via this
qeth interface to the attached software bridge via switchdev
notifiers SWITCHDEV_FDB_ADD_TO_BRIDGE and SWITCHDEV_FDB_DEL_TO_BRIDGE.
Extend this support of LEARNING_SYNC to the bridge to switchdev notifiers
SWITCHDEV_FDB_ADD_TO_DEVICE and SWITCHDEV_FDB_DEL_TO_DEVICE.
Add the capability to sync MAC addresses that are learned by a
north-facing, non-isolated bridgeport of a software bridge to
south-facing, isolated bridgeports. This enables the software bridge to
influence south to north traffic steering in hardware.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Update the MAC addresses that are registered with a LEARNING_SYNC qeth
device with the events announced by the attached software bridge.
Typically the LEARNING_SYNC qeth bridge port has an isolated sibling (the
default interface of an 'HiperSockets Converged Interface' (HSCI)). Update
the MACs of isolated siblings as well, to avoid unnecessary flooding in
the attached virtualized switches.
Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
QETH HiperSockets devices with LEARNING_SYNC capability can be used
to construct a linux bridge with:
2 isolated southbound interfaces:
a) a default network interface
b) a LEARNING-SYNC HiperSockets interface
and 1 non-isolated northbound interface. This is called a 'HiperSockets
Converged Interface' (HSCI).
The existing LEARNING_SYNC functionality is used to update the bridge fdb
with MAC addresses that should be sent-out via the HiperSockets interface,
instead of the default network interface.
Add handling of switchdev events SWITCHDEV_FDB_ADD_TO_DEVICE and
SWITCHDEV_FDB_DEL_TO_DEVICE to the qeth LEARNING_SYNC functionality. Thus
if the northbound bridgeport of an HSCI doesn't only have a single static
MAC address, but instead is a learning bridgeport, work is enqueued, so
the HiperSockets virtual switch (that is external to this Linux instance)
can update its fdb.
When BRIDGE is a loadable module, QETH_L2 mustn't be built-in:
drivers/s390/net/qeth_l2_main.o: in function 'qeth_l2_switchdev_event':
drivers/s390/net/qeth_l2_main.c:927: undefined reference to
'br_port_flag_is_set'
Add Kconfig dependency to enforce usable configurations.
Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conditionally register a qeth_l2 switchdev_event handler to handle bridge
to device switchdev events, when at least one qeth interface has the
bridgeport attribute LEARNING_SYNC enabled.
Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The true check on the variable startable in the ternary operator
is always false because the previous if statement handles the true
condition for startable. Hence the ternary check is dead code and
can be removed.
Addresses-Coverity: ("Logically dead code")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Simon Horman says:
====================
This short series provides minor enhancements to the
sample code in samples/bpf/xdpsock_user.c.
Each change is explained more fully in its own commit message.
====================
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
There is a forward declaration of ip_fast_csum() just before its
implementation, remove the unneeded forward declaration.
While at it mark the implementation as static inline.
Signed-off-by: Niklas Söderlund <niklas.soderlund@corigine.com>
Signed-off-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Louis Peens <louis.peens@corigine.com>
Link: https://lore.kernel.org/bpf/20210806122855.26115-3-simon.horman@corigine.com
The xdpsock sample application is a useful base for experiment's around
AF_XDP sockets. Compiling the sample outside of the kernel tree is made
harder then it has to be as the sample includes two headers and that are
not installed by 'make install_header' nor are usually part of
distributions kernel headers.
The first header asm/barrier.h is not used and can just be dropped.
The second linux/compiler.h are only needed for the decorator __force
and are only used in ip_fast_csum(), csum_fold() and
csum_tcpudp_nofold(). These functions are copied verbatim from
include/asm-generic/checksum.h and lib/checksum.c. While it's fine to
copy and use these functions in the sample application the decorator
brings no value and can be dropped together with the include.
With this change it's trivial to compile the xdpsock sample outside the
kernel tree from xdpsock_user.c and xdpsock.h.
$ gcc -o xdpsock xdpsock_user.c -lbpf -lpthread
Signed-off-by: Niklas Söderlund <niklas.soderlund@corigine.com>
Signed-off-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Louis Peens <louis.peens@corigine.com>
Link: https://lore.kernel.org/bpf/20210806122855.26115-2-simon.horman@corigine.com
The "skb" pointer is NULL on this error path so we can't dereference it.
Use "dev" instead.
Fixes: 14ee70ca89 ("vrf: use skb_expand_head in vrf_finish_output")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Link: https://lore.kernel.org/r/20210806150435.GB15586@kili
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
BPF programs for reference_tracking selftest use "fail_" prefix to notify that
they are expected to fail. This is really confusing and inconvenient when
trying to grep through test_progs output to find *actually* failed tests. So
rename the prefix from "fail_" to "err_".
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210805230734.437914-1-andrii@kernel.org
Currently, this test is incorrectly printing the destination port in
place of the destination IP.
Fixes: 2767c97765 ("selftests/bpf: Implement sample tcp/tcp6 bpf_iter programs")
Signed-off-by: Jose Blanquicet <josebl@microsoft.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210805164044.527903-1-josebl@microsoft.com
The driver currently still accepts untagged frames on VLAN-aware ports
without PVID. Use PVC.ACC_FRM to drop untagged frames in that case.
Signed-off-by: DENG Qingfang <dqfext@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vladimir Oltean says:
====================
Always flood multicast to the DSA CPU port
Discussing with Qingfang, it became obvious that DSA is not prepared to
disable multicast flooding towards the CPU port under any circumstance
right now, and this in fact breaks traffic quite blatantly.
This series is a revert done in reverse chronological order. These
should be propagated to stable trees up to commit a8b659e7ff ("net:
dsa: act as passthrough for bridge port flags") which is in v5.12.
For older kernels, that commit blocks further backporting, so I need to
send a modified version of patch 3 separately to Greg after these go
into "net".
v1->v2: delete unused b53_set_mrouter function prototype
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 08cc83cc7f ("net: dsa: add support for BRIDGE_MROUTER
attribute") added an option for users to turn off multicast flooding
towards the CPU if they turn off the IGMP querier on a bridge which
already has enslaved ports (echo 0 > /sys/class/net/br0/bridge/multicast_router).
And commit a8b659e7ff ("net: dsa: act as passthrough for bridge port flags")
simply papered over that issue, because it moved the decision to flood
the CPU with multicast (or not) from the DSA core down to individual drivers,
instead of taking a more radical position then.
The truth is that disabling multicast flooding to the CPU is simply
something we are not prepared to do now, if at all. Some reasons:
- ICMP6 neighbor solicitation messages are unregistered multicast
packets as far as the bridge is concerned. So if we stop flooding
multicast, the outside world cannot ping the bridge device's IPv6
link-local address.
- There might be foreign interfaces bridged with our DSA switch ports
(sending a packet towards the host does not necessarily equal
termination, but maybe software forwarding). So if there is no one
interested in that multicast traffic in the local network stack, that
doesn't mean nobody is.
- PTP over L4 (IPv4, IPv6) is multicast, but is unregistered as far as
the bridge is concerned. This should reach the CPU port.
- The switch driver might not do FDB partitioning. And since we don't
even bother to do more fine-grained flood disabling (such as "disable
flooding _from_port_N_ towards the CPU port" as opposed to "disable
flooding _from_any_port_ towards the CPU port"), this breaks standalone
ports, or even multiple bridges where one has an IGMP querier and one
doesn't.
Reverting the logic makes all of the above work.
Fixes: a8b659e7ff ("net: dsa: act as passthrough for bridge port flags")
Fixes: 08cc83cc7f ("net: dsa: add support for BRIDGE_MROUTER attribute")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
DSA's idea of optimizing out multicast flooding to the CPU port leaves
quite a few holes open, so it should be reverted.
The mt7530 driver is the only new driver which added a .port_set_mrouter
implementation after the reorg from commit a8b659e7ff ("net: dsa: act
as passthrough for bridge port flags"), so it needs to be reverted
separately so that the other revert commit can go a bit further down the
git history.
Fixes: 5a30833b9a ("net: dsa: mt7530: support MDB and bridge flag operations")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Qingfang points out that when a bridge with the default settings is
created and a port joins it:
ip link add br0 type bridge
ip link set swp0 master br0
DSA calls br_multicast_router() on the bridge to see if the br0 device
is a multicast router port, and if it is, it enables multicast flooding
to the CPU port, otherwise it disables it.
If we look through the multicast_router_show() sysfs or at the
IFLA_BR_MCAST_ROUTER netlink attribute, we see that the default mrouter
attribute for the bridge device is "1" (MDB_RTR_TYPE_TEMP_QUERY).
However, br_multicast_router() will return "0" (MDB_RTR_TYPE_DISABLED),
because an mrouter port in the MDB_RTR_TYPE_TEMP_QUERY state may not be
actually _active_ until it receives an actual IGMP query. So, the
br_multicast_router() function should really have been called
br_multicast_router_active() perhaps.
When/if an IGMP query is received, the bridge device will transition via
br_multicast_mark_router() into the active state until the
ip4_mc_router_timer expires after an multicast_querier_interval.
Of course, this does not happen if the bridge is created with an
mcast_router attribute of "2" (MDB_RTR_TYPE_PERM).
The point is that in lack of any IGMP query messages, and in the default
bridge configuration, unregistered multicast packets will not be able to
reach the CPU port through flooding, and this breaks many use cases
(most obviously, IPv6 ND, with its ICMP6 neighbor solicitation multicast
messages).
Leave the multicast flooding setting towards the CPU port down to a driver
level decision.
Fixes: 010e269f91 ("net: dsa: sync up switchdev objects and port attributes when joining the bridge")
Reported-by: DENG Qingfang <dqfext@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch enables support for hard irqs deferral feature from Eric Dumazet
[1] for TI K3 CPSW driver by using napi_complete_done() in TX completion
path.
Depending on gro_flush_timeout and napi_defer_hard_irqs at gives up to 30%
CPU utilization reduction:
gro_flush_timeout=50000
napi_defer_hard_irqs=2
netperf -l 10 -H 192.168.1.1 -t UDP_STREAM -c -C -- -m 1470
MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.1.1 () port 0 AF_INET
Socket Message Elapsed Messages CPU Service
Size Size Time Okay Errors Throughput Util Demand
bytes bytes secs # # 10^6bits/sec % SS us/KB
before:
212992 1470 10.00 809632 0 952.0 42.98 14.792
212992 10.00 809630 952.0 50.66 8.719
after:
212992 1470 10.00 813686 0 956.8 32.14 11.009
212992 10.00 813686 956.8 50.05 8.570
[1] https://lore.kernel.org/netdev/20200422161329.56026-1-edumazet@google.com/
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On TI K3 am64x platform the issue with RX IRQ is observed - it's become
disabled forever after .ndo_stop(). The K3 CPSW driver manipulates RX IRQ
by using standard Linux enable_irq()/disable_irq_nosync() API as there is
no IRQ enable/disable options in CPSW HW itself, as result during
.ndo_stop() following sequence happens
phy_stop()
teardown TX/RX channels
wait for TX tdown complete
napi_disable(TX)
clean up TX channels
(a)
napi_disable(RX)
At point (a) it's not possible to predict if RX IRQ was triggered or not.
if RX IRQ was triggered then it also not possible to definitely say if RX
NAPI was run or only scheduled and immediately canceled by
napi_disable(RX). Actually the last case causes RX IRQ to be permanently
disabled.
Another observed issue is that RX IRQ enable counter become unbalanced if
(gro_flush_timeout =! 0) while (napi_defer_hard_irqs == 0):
Unbalanced enable for IRQ 44
WARNING: CPU: 0 PID: 10 at ../kernel/irq/manage.c:776 __enable_irq+0x38/0x80
__enable_irq+0x38/0x80
enable_irq+0x54/0xb0
am65_cpsw_nuss_rx_poll+0x2f4/0x368
__napi_poll+0x34/0x1b8
net_rx_action+0xe4/0x220
_stext+0x11c/0x284
run_ksoftirqd+0x4c/0x60
To avoid above issues introduce flag indicating if RX was actually disabled
before enabling it in am65_cpsw_nuss_rx_poll() and restore RX IRQ state in
.ndo_open()
Fixes: 4f7cce2724 ("net: ethernet: ti: am65-cpsw: add support for am64x cpsw3g")
Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>