| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
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
|
|
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
|
|
iavf driver should set RSS LUT and key unconditionally in reset
path. Currently, the driver does not do that. This patch fixes
this issue.
Fixes: 2c86ac3c7079 ("i40evf: create a generic config RSS function")
Signed-off-by: Md Fahad Iqbal Polash <md.fahad.iqbal.polash@intel.com>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
In some circumstances, such as with bridging, it's possible that the
stack will add the device's own MAC address to its unicast address list.
If, later, the stack deletes this address, the driver will receive a
request to remove this address.
The driver stores its current MAC address as part of the VSI MAC filter
list instead of separately. So, this causes a problem when the device's
MAC address is deleted unexpectedly, which results in traffic failure in
some cases.
The following configuration steps will reproduce the previously
mentioned problem:
> ip link set eth0 up
> ip link add dev br0 type bridge
> ip link set br0 up
> ip addr flush dev eth0
> ip link set eth0 master br0
> echo 1 > /sys/class/net/br0/bridge/vlan_filtering
> modprobe -r veth
> modprobe -r bridge
> ip addr add 192.168.1.100/24 dev eth0
The following ping command fails due to the netdev->dev_addr being
deleted when removing the bridge module.
> ping <link partner>
Fix this by making sure to not delete the netdev->dev_addr during MAC
address sync. After fixing this issue it was noticed that the
netdev_warn() in .set_mac was overly verbose, so make it at
netdev_dbg().
Also, there is a possibility of a race condition between .set_mac and
.set_rx_mode. Fix this by calling netif_addr_lock_bh() and
netif_addr_unlock_bh() on the device's netdev when the netdev->dev_addr
is going to be updated in .set_mac.
Fixes: e94d44786693 ("ice: Implement filter sync, NDO operations and bump version")
Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Liang Li <liali@redhat.com>
Tested-by: Gurucharan G <gurucharanx.g@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
When VFs are setup and torn down in quick succession, it is possible
that a VF is torn down by the PF while the VF's virtchnl requests are
still in the PF's mailbox ring. Processing the VF's virtchnl request
when the VF itself doesn't exist results in undefined behavior. Fix
this by adding a check to stop processing virtchnl requests when VF
teardown is in progress.
Fixes: ddf30f7ff840 ("ice: Add handler to configure SR-IOV")
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
The userspace utility "driverctl" can be used to change/override the
system's default driver choices. This is useful in some situations
(buggy driver, old driver missing a device ID, trying a workaround,
etc.) where the user needs to load a different driver.
However, this is also prone to user error, where a driver is mapped
to a device it's not designed to drive. For example, if the ice driver
is mapped to driver iavf devices, the ice driver crashes.
Add a check to return an error if the ice driver is being used to
probe a virtual function.
Fixes: 837f08fdecbe ("ice: Add basic driver framework for Intel(R) E800 Series")
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Gurucharan G <gurucharanx.g@intel.com>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
make.cross ARCH=m68k m5272c3_defconfig
make.cross ARCH=m68k
drivers/net/ethernet/freescale/fec_main.c: In function 'fec_enet_eee_mode_set':
>> drivers/net/ethernet/freescale/fec_main.c:2758:33: error: 'FEC_LPI_SLEEP' undeclared (first use in this function); did you mean 'FEC_ECR_SLEEP'?
2758 | writel(sleep_cycle, fep->hwp + FEC_LPI_SLEEP);
| ^~~~~~~~~~~~~
arch/m68k/include/asm/io_no.h:25:66: note: in definition of macro '__raw_writel'
25 | #define __raw_writel(b, addr) (void)((*(__force volatile u32 *) (addr)) = (b))
| ^~~~
drivers/net/ethernet/freescale/fec_main.c:2758:2: note: in expansion of macro 'writel'
2758 | writel(sleep_cycle, fep->hwp + FEC_LPI_SLEEP);
| ^~~~~~
drivers/net/ethernet/freescale/fec_main.c:2758:33: note: each undeclared identifier is reported only once for each function it appears in
2758 | writel(sleep_cycle, fep->hwp + FEC_LPI_SLEEP);
| ^~~~~~~~~~~~~
arch/m68k/include/asm/io_no.h:25:66: note: in definition of macro '__raw_writel'
25 | #define __raw_writel(b, addr) (void)((*(__force volatile u32 *) (addr)) = (b))
| ^~~~
drivers/net/ethernet/freescale/fec_main.c:2758:2: note: in expansion of macro 'writel'
2758 | writel(sleep_cycle, fep->hwp + FEC_LPI_SLEEP);
| ^~~~~~
>> drivers/net/ethernet/freescale/fec_main.c:2759:32: error: 'FEC_LPI_WAKE' undeclared (first use in this function)
2759 | writel(wake_cycle, fep->hwp + FEC_LPI_WAKE);
| ^~~~~~~~~~~~
arch/m68k/include/asm/io_no.h:25:66: note: in definition of macro '__raw_writel'
25 | #define __raw_writel(b, addr) (void)((*(__force volatile u32 *) (addr)) = (b))
| ^~~~
drivers/net/ethernet/freescale/fec_main.c:2759:2: note: in expansion of macro 'writel'
2759 | writel(wake_cycle, fep->hwp + FEC_LPI_WAKE);
| ^~~~~~
This patch adds register definition for M5272 platform to pass build.
Fixes: b82f8c3f1409 ("net: fec: add eee mode tx lpi support")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Joakim Zhang <qiangqing.zhang@nxp.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: aa730a9905b7 ("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>
|
|
The CPSW switchdev driver inherited fix from commit 9421c9015047 ("net:
ethernet: ti: cpsw: fix min eth packet size") which changes min TX packet
size to 64bytes (VLAN_ETH_ZLEN, excluding ETH_FCS). It was done to fix HW
packed drop issue when packets are sent from Host to the port with PVID and
un-tagging enabled. Unfortunately this breaks some other non-switch
specific use-cases, like:
- [1] CPSW port as DSA CPU port with DSA-tag applied at the end of the
packet
- [2] Some industrial protocols, which expects min TX packet size 60Bytes
(excluding FCS).
Fix it by configuring min TX packet size depending on driver mode
- 60Bytes (ETH_ZLEN) for multi mac (dual-mac) mode
- 64Bytes (VLAN_ETH_ZLEN) for switch mode
and update it during driver mode change and annotate with
READ_ONCE()/WRITE_ONCE() as it can be read by napi while writing.
[1] https://lore.kernel.org/netdev/20210531124051.GA15218@cephalopod/
[2] https://e2e.ti.com/support/arm/sitara_arm/f/791/t/701669
Cc: stable@vger.kernel.org
Fixes: ed3525eda4c4 ("net: ethernet: ti: introduce cpsw switchdev based driver part 1 - dual-emac")
Reported-by: Ben Hutchings <ben.hutchings@essensium.com>
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
We need the driver core fixes in here as well.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
We need the fixes in here as well, and resolves some merge issues with
the mhi codebase.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
We need the tty/serial fixes in here as well.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
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 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>
|
|
When registering new ppp interface via PPPIOCNEWUNIT ioctl then kernel has
to choose interface name as this ioctl API does not support specifying it.
Kernel in this case register new interface with name "ppp<id>" where <id>
is the ppp unit id, which can be obtained via PPPIOCGUNIT ioctl. This
applies also in the case when registering new ppp interface via rtnl
without supplying IFLA_IFNAME.
PPPIOCNEWUNIT ioctl allows to specify own ppp unit id which will kernel
assign to ppp interface, in case this ppp id is not already used by other
ppp interface.
In case user does not specify ppp unit id then kernel choose the first free
ppp unit id. This applies also for case when creating ppp interface via
rtnl method as it does not provide a way for specifying own ppp unit id.
If some network interface (does not have to be ppp) has name "ppp<id>"
with this first free ppp id then PPPIOCNEWUNIT ioctl or rtnl call fails.
And registering new ppp interface is not possible anymore, until interface
which holds conflicting name is renamed. Or when using rtnl method with
custom interface name in IFLA_IFNAME.
As list of allocated / used ppp unit ids is not possible to retrieve from
kernel to userspace, userspace has no idea what happens nor which interface
is doing this conflict.
So change the algorithm how ppp unit id is generated. And choose the first
number which is not neither used as ppp unit id nor in some network
interface with pattern "ppp<id>".
This issue can be simply reproduced by following pppd call when there is no
ppp interface registered and also no interface with name pattern "ppp<id>":
pppd ifname ppp1 +ipv6 noip noauth nolock local nodetach pty "pppd +ipv6 noip noauth nolock local nodetach notty"
Or by creating the one ppp interface (which gets assigned ppp unit id 0),
renaming it to "ppp1" and then trying to create a new ppp interface (which
will always fails as next free ppp unit id is 1, but network interface with
name "ppp1" exists).
This patch fixes above described issue by generating new and new ppp unit
id until some non-conflicting id with network interfaces is generated.
Signed-off-by: Pali Rohár <pali@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
IFLA_IFNAME is nul-term string which means that IFLA_IFNAME buffer can be
larger than length of string which contains.
Function __rtnl_newlink() generates new own ifname if either IFLA_IFNAME
was not specified at all or userspace passed empty nul-term string.
It is expected that if userspace does not specify ifname for new ppp netdev
then kernel generates one in format "ppp<id>" where id matches to the ppp
unit id which can be later obtained by PPPIOCGUNIT ioctl.
And it works in this way if IFLA_IFNAME is not specified at all. But it
does not work when IFLA_IFNAME is specified with empty string.
So fix this logic also for empty IFLA_IFNAME in ppp_nl_newlink() function
and correctly generates ifname based on ppp unit identifier if userspace
did not provided preferred ifname.
Without this patch when IFLA_IFNAME was specified with empty string then
kernel created a new ppp interface in format "ppp<id>" but id did not
match ppp unit id returned by PPPIOCGUNIT ioctl. In this case id was some
number generated by __rtnl_newlink() function.
Signed-off-by: Pali Rohár <pali@kernel.org>
Fixes: bb8082f69138 ("ppp: build ifname using unit identifier for rtnl based devices")
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Some older Broadcom debug tools use window 5 and may conflict, so switch
to use window 6 instead.
Fixes: 118612d519d8 ("bnxt_en: Add PTP clock APIs, ioctls, and ethtool methods")
Reviewed-by: Andy Gospodarek <gospo@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
New firmware interface requires the PTP sequence ID header offset to
be passed to the firmware to properly find the matching timestamp
for all protocols.
Fixes: 83bb623c968e ("bnxt_en: Transmit and retrieve packet timestamps")
Reviewed-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The key change is the firmware call to retrieve the PTP TX timestamp.
The header offset for the PTP sequence number field is now added.
Signed-off-by: Michael Chan <michael.chan@broadcom.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>
|
|
Commit a5e63c7d38d5 "net: phy: micrel: Fix detection of ksz87xx
switch" broke link detection on the external ports of the KSZ8795.
The previously unused phy_driver structure for these devices specifies
config_aneg and read_status functions that appear to be designed for a
fixed link and do not work with the embedded PHYs in the KSZ8795.
Delete the use of these functions in favour of the generic PHY
implementations which were used previously.
Fixes: a5e63c7d38d5 ("net: phy: micrel: Fix detection of ksz87xx switch")
Signed-off-by: Ben Hutchings <ben.hutchings@mind.be>
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>
|
|
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>
|
|
Lockdep detected possible interrupt unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&mhiwwan->rx_lock);
local_irq_disable();
lock(&mhi_cntrl->pm_lock);
lock(&mhiwwan->rx_lock);
<Interrupt>
lock(&mhi_cntrl->pm_lock);
*** DEADLOCK ***
To prevent this we need to disable the soft-interrupts when taking
the rx_lock.
Cc: stable@vger.kernel.org
Fixes: fa588eba632d ("net: Add Qcom WWAN control driver")
Reported-by: Thomas Perrot <thomas.perrot@bootlin.com>
Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Reviewed-by: Sergey Ryazanov <ryazanov.s.a@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Make sure that all external port are actually isolated from each other,
so no packets are leaked.
Fixes: ec6698c272de ("net: dsa: add support for Atheros AR9331 built-in switch")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The original L0 and L1 entrance latencies of RTL8106e are 4us. And
they cause the delay of link-up interrupt when enabling ASPM. Change
the L0 entrance latency to 7us and L1 entrance latency to 32us. Then,
they could avoid the issue.
Tested-by: Koba Ko <koba.ko@canonical.com>
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This reverts commit 1ee8856de82faec9bc8bd0f2308a7f27e30ba207.
This is used to re-enable ASPM on RTL8106e, if it is possible.
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This reverts commit 9ffc513f95ee ("net: ethernet: ti: davinci_cpdma: drop
frame padding") which has depndency from not yet merged patch [1] and so
breaks cpsw_new driver.
[1] https://patchwork.kernel.org/project/netdevbpf/patch/20210805145511.12016-1-grygorii.strashko@ti.com/
Fixes: 9ffc513f95ee ("net: ethernet: ti: davinci_cpdma: drop frame padding")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Link: https://lore.kernel.org/r/20210806142809.15069-1-grygorii.strashko@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The "skb" pointer is NULL on this error path so we can't dereference it.
Use "dev" instead.
Fixes: 14ee70ca89e6 ("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>
|
|
On s390, the following build warning occurs:
drivers/net/ethernet/marvell/mvpp2/mvpp2.h:844:2: warning: overflow in
conversion from 'long unsigned int' to 'int' changes value from
'18446744073709551584' to '-32' [-Woverflow]
844 | ((total_size) - MVPP2_SKB_HEADROOM - MVPP2_SKB_SHINFO_SIZE)
This happens because MVPP2_SKB_SHINFO_SIZE, which is 320 bytes (which is
already 64-byte aligned) on some architectures, actually gets ALIGN'd up
to 512 bytes in the s390 case.
So then, when this is invoked:
MVPP2_RX_MAX_PKT_SIZE(MVPP2_BM_SHORT_FRAME_SIZE)
...that turns into:
704 - 224 - 512 == -32
...which is not a good frame size to end up with! The warning above is a
bit lucky: it notices a signed/unsigned bad behavior here, which leads
to the real problem of a frame that is too short for its contents.
Increase MVPP2_BM_SHORT_FRAME_SIZE by 32 (from 704 to 736), which is
just exactly big enough. (The other values can't readily be changed
without causing a lot of other problems.)
Fixes: 07dd0a7aae7f ("mvpp2: add basic XDP support")
Cc: Sven Auhagen <sven.auhagen@voleatech.de>
Cc: Matteo Croce <mcroce@microsoft.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Add the missing RxUnicast counter.
Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch")
Signed-off-by: DENG Qingfang <dqfext@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
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>
|
|
querier
Commit 08cc83cc7fd8 ("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 a8b659e7ff75 ("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: a8b659e7ff75 ("net: dsa: act as passthrough for bridge port flags")
Fixes: 08cc83cc7fd8 ("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 a8b659e7ff75 ("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: 5a30833b9a16 ("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>
|
|
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: 4f7cce272403 ("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>
|
|
Don't progress with adding and deleting ports as long as devlink
reload is running.
Fixes: 23809a726c0d ("netdevsim: Forbid devlink reload when adding or deleting ports")
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Hence all users of davinci_cpdma switched to skb_put_padto() the frame
padding can be removed from it.
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Use skb_put_padto() instead of skb_padto() so skb->len also got updated, as
preparation for further removing frame padding from cpdma.
It also makes xmit path more clear and linear.
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Use skb_put_padto() instead of skb_padto() so skb->len also got updated, as
preparation for further removing frame padding from cpdma.
It also makes xmit path more clear and linear.
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 1d89cae1b47d ("MAINTAINERS: mark prism54 obsolete") indicated the
prism54 driver as obsolete in July 2010.
Now, after being exposed for ten years to refactoring, general tree-wide
changes and various janitor clean-up, it is really time to delete the
driver for good.
This was discovered as part of a checkpatch evaluation, investigating all
reports of checkpatch's WARNING:OBSOLETE check.
p54 replaces prism54 so users should be unaffected. There was a one off chipset
someone long ago reported that p54 didn't work with but the reporter never
followed up on that. Additionally, distributions have been blacklisting prism54
for years now.
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Acked-by: Luis Chamberlain <mcgrof@kernel.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210713054025.32006-1-lukas.bulwahn@gmail.com
|
|
There is no 'NONE' version of 'enum mcu_cipher_type', and returning
'MT_CIPHER_NONE' causes a warning:
drivers/net/wireless/mediatek/mt76/mt7921/mcu.c: In function 'mt7921_mcu_get_cipher':
drivers/net/wireless/mediatek/mt76/mt7921/mcu.c:114:24: error: implicit conversion from 'enum mt76_cipher_type' to 'enum mcu_cipher_type' [-Werror=enum-conversion]
114 | return MT_CIPHER_NONE;
| ^~~~~~~~~~~~~~
Add the missing MCU_CIPHER_NONE defintion that fits in here with
the same value.
Fixes: c368362c36d3 ("mt76: fix iv and CCMP header insertion")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210721150745.1914829-1-arnd@kernel.org
|
|
Build failure in drivers/net/wwan/mhi_wwan_mbim.c:
add missing parameter (0, assuming we don't want buffer pre-alloc).
Conflict in drivers/net/dsa/sja1105/sja1105_main.c between:
589918df9322 ("net: dsa: sja1105: be stateless with FDB entries on SJA1105P/Q/R/S/SJA1110 too")
0fac6aa098ed ("net: dsa: sja1105: delete the best_effort_vlan_filtering mode")
Follow the instructions from the commit message of the former commit
- removed the if conditions. When looking at commit 589918df9322 ("net:
dsa: sja1105: be stateless with FDB entries on SJA1105P/Q/R/S/SJA1110 too")
note that the mask_iotag fields get removed by the following patch.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
If both eswitches are in switchdev mode and the uplink representors
are enslaved to the same bond device create a shared FDB configuration.
When moving to shared FDB mode not only the hardware needs be configured
but the RDMA driver needs to reconfigure itself.
When such change is done, unload the RDMA devices, configure the hardware
and load the RDMA representors.
When destroying the lag (can happen if a PCI function is unbinded,
driver is unloaded or by just removing a netdev from the bond) make sure
to restore the system to the previous state only if possible.
For example, if a PCI function is unbinded there is no need to load the
representors as the device is going away.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Shared FDB allows to direct traffic from all the vports in the HCA to a
single eswitch. In order to do that three things are needed.
1) Point the ingress ACL of the slave uplink to that of the master.
With this, wire traffic from both uplinks will reach the same eswitch
with the same metadata where a single steering rule can catch traffic
from both ports.
2) Set the FDB root flow table of the slave's eswitch to that of the
master. As this flow table can change dynamically make sure to
sync it on any set root flow table FDB command.
This will make sure traffic from SFs, VFs, ECPFs and PFs reach the
master eswitch.
3) Split wire traffic at the eswitch manager egress ACL so that it's
directed to the native eswitch manager. We only treat wire traffic
from both ports the same at the eswitch level. If such traffic wasn't
handled in the eswitch it needs to reach the right representor to be
processed by software. For example LACP packets should *always*
reach the right uplink representor for correct operation.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Mark Zhang <markzhang@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
If a netdev is removed from the lag the lag should be destroyed.
With downstream patches this might trigger a reconfiguration of
representors on a different eswitch and such we don't have the proper
locking to so from this path. Move the destruction to be done by the
workqueue.
As the destruction won't affect the netdev side it okay to do so.
The RDMA side will be reconfigured and it already coded to handle such
reconfiguration.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Mark Zhang <markzhang@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Currently when doing hardware lag we check the eswitch mode
but as this isn't done under a lock the check isn't valid.
As the code needs to sync between two different devices an extra
care is needed.
- When going to change eswitch mode, if hardware lag is active destroy it.
- While changing eswitch modes block any hardware bond creation.
- Delay handling bonding events until there are no mode changes in
progress.
- When attaching a new mdev to lag, block until there is no mode change
in progress. In order for the mode change to finish the interface lock
will have to be taken. Release the lock and sleep for 100ms to
allow forward progress. As this is a very rare condition (can happen if
the user unbinds and binds a PCI function while also changing eswitch
mode of the other PCI function) it has no real world impact.
As taking multiple eswitch mode locks is now required lockdep will
complain about a possible deadlock. Register a key per eswitch to make
lockdep happy.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Mark Zhang <markzhang@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
