phy_loopback() leaves it to the PHY driver to select the speed of the
loopback mode. Thus, the speed of the loopback mode depends on the PHY
driver in use.
Add support for speed selection to phy_loopback() to enable loopback
with defined speeds. Ensure that link up is signaled if speed changes
as speed is not allowed to change during link up. Link down and up is
necessary for a new speed.
Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Link: https://patch.msgid.link/20250312203010.47429-3-gerhard@engleder-embedded.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
PHY drivers support loopback mode, but it is not possible to select the
speed of the loopback mode. The speed is chosen by the set_loopback()
operation of the PHY driver. Same is valid for genphy_loopback().
There are PHYs that support loopback with different speeds. Extend
set_loopback() to make loopback speed selection possible.
Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250312203010.47429-2-gerhard@engleder-embedded.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
When a character array without a terminating NUL character has a static
initializer, GCC 15's -Wunterminated-string-initialization will only
warn if the array lacks the "nonstring" attribute[1]. Mark the arrays
with __nonstring to correctly identify the char array as "not a C string"
and thereby eliminate the warning:
In file included from ../drivers/net/ethernet/cadence/macb_main.c:42:
../drivers/net/ethernet/cadence/macb.h:1070:35: warning: initializer-string for array of 'char' truncates NUL terminator but destination lacks 'nonstring' attribute (33 chars into 32 available) [-Wunterminated-string-initialization]
1070 | GEM_STAT_TITLE(TX1519CNT, "tx_greater_than_1518_byte_frames"),
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
../drivers/net/ethernet/cadence/macb.h:1050:24: note: in definition of macro 'GEM_STAT_TITLE_BITS'
1050 | .stat_string = title, \
| ^~~~~
../drivers/net/ethernet/cadence/macb.h:1070:9: note: in expansion of macro 'GEM_STAT_TITLE'
1070 | GEM_STAT_TITLE(TX1519CNT, "tx_greater_than_1518_byte_frames"),
| ^~~~~~~~~~~~~~
../drivers/net/ethernet/cadence/macb.h:1097:35: warning: initializer-string for array of 'char' truncates NUL terminator but destination lacks 'nonstring' attribute (33 chars into 32 available) [-Wunterminated-string-initialization]
1097 | GEM_STAT_TITLE(RX1519CNT, "rx_greater_than_1518_byte_frames"),
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
../drivers/net/ethernet/cadence/macb.h:1050:24: note: in definition of macro 'GEM_STAT_TITLE_BITS'
1050 | .stat_string = title, \
| ^~~~~
../drivers/net/ethernet/cadence/macb.h:1097:9: note: in expansion of macro 'GEM_STAT_TITLE'
1097 | GEM_STAT_TITLE(RX1519CNT, "rx_greater_than_1518_byte_frames"),
| ^~~~~~~~~~~~~~
Since these strings are copied with memcpy() they do not need to be
NUL terminated, and can use __nonstring:
memcpy(p, gem_statistics[i].stat_string,
ETH_GSTRING_LEN);
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117178 [1]
Signed-off-by: Kees Cook <kees@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250312200700.make.521-kees@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Uday Shankar says:
====================
netconsole: allow selection of egress interface via MAC address
This series adds support for selecting a netconsole egress interface by
specifying the MAC address (in place of the interface name) in the
boot/module parameter.
Signed-off-by: Uday Shankar <ushankar@purestorage.com>
====================
Link: https://patch.msgid.link/20250312-netconsole-v6-0-3437933e79b8@purestorage.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Currently, netconsole has two methods of configuration - module
parameter and configfs. The former interface allows for netconsole
activation earlier during boot (by specifying the module parameter on
the kernel command line), so it is preferred for debugging issues which
arise before userspace is up/the configfs interface can be used. The
module parameter syntax requires specifying the egress interface name.
This requirement makes it hard to use for a couple reasons:
- The egress interface name can be hard or impossible to predict. For
example, installing a new network card in a system can change the
interface names assigned by the kernel.
- When constructing the module parameter, one may have trouble
determining the original (kernel-assigned) name of the interface
(which is the name that should be given to netconsole) if some stable
interface naming scheme is in effect. A human can usually look at
kernel logs to determine the original name, but this is very painful
if automation is constructing the parameter.
For these reasons, allow selection of the egress interface via MAC
address when configuring netconsole using the module parameter. Update
the netconsole documentation with an example of the new syntax.
Selection of egress interface by MAC address via configfs is far less
interesting (since when this interface can be used, one should be able
to easily convert between MAC address and interface name), so it is left
unimplemented.
Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Reviewed-by: Breno Leitao <leitao@debian.org>
Tested-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250312-netconsole-v6-2-3437933e79b8@purestorage.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
There are a few places in the tree which compute the length of the
string representation of a MAC address as 3 * ETH_ALEN - 1. Define a
constant for this and use it where relevant. No functionality changes
are expected.
Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Reviewed-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@verge.net.au>
Link: https://patch.msgid.link/20250312-netconsole-v6-1-3437933e79b8@purestorage.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Avoid using deprecated pcim_iomap_table by switching to
pcim_iomap_region.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/a36b4cf3-c792-40fa-8164-5dc9d5f14dd0@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Stanislav Fomichev says:
====================
net: bring back dev_addr_sem
Kohei reports an issue with dev_addr_sem conversion to netdev instance
lock in [0]. Based on the discussion, switching to netdev instance
lock to protect the address might not work for the devices that
are not using netdev ops lock.
Bring dev_addr_sem instance lock back but fix the ordering.
0: https://lore.kernel.org/netdev/20250308203835.60633-2-enjuk@amazon.com
====================
Link: https://patch.msgid.link/20250312190513.1252045-1-sdf@fomichev.me
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Before tc's recent change to fix rounding errors, several tests which
specified a burst size of "1m" would translate back to being 1048574
bytes (2b less than 1Mb). sprint_size prints this as "1024Kb".
With the tc fix, the burst size is instead correctly reported as
1048576 bytes (precisely 1Mb), which sprint_size prints as "1Mb".
This updates the expected output in the tests' matchPattern values
to accept either the old or the new output.
Signed-off-by: Jonathan Lennox <jonathan.lennox@8x8.com>
Link: https://patch.msgid.link/20250312174804.313107-1-jonathan.lennox@8x8.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The DWMAC 1000 DMA capabilities register does not provide actual
FIFO sizes, nor does the driver really care. If they are not
provided via some other means, the driver will work fine, only
disallowing changing the MTU setting.
Provide the FIFO sizes through the driver's platform data to enable
MTU changes. The FIFO sizes are confirmed to be the same across RK3288,
RK3328, RK3399 and PX30, based on their respective manuals. It is
likely that Rockchip synthesized their DWMAC 1000 with the same
parameters on all their chips that have it.
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250312163426.2178314-1-wens@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tariq Toukan says:
====================
net/mlx5: HW Steering cleanups
This short series by Yevgeny contains several small HW Steering cleanups:
- Patch 1: removing unused FW commands
- Patch 2: using list_move() instead of list_del/add
- Patch 3: printing the unsupported combination of match fields
====================
Link: https://patch.msgid.link/1741780194-137519-1-git-send-email-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
If a user requested to match on an unsupported combination of fields,
print the unsupported combination in the error message.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Vlad Dogaru <vdogaru@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1741780194-137519-4-git-send-email-tariqt@nvidia.com
Reviewed-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Alias flow tables are not in use by HWS - remove the unused code.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Vlad Dogaru <vdogaru@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1741780194-137519-2-git-send-email-tariqt@nvidia.com
Reviewed-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Russell King says:
====================
net: stmmac: deprecate "snps,en-tx-lpi-clockgating" property
This series deprecates the "snps,en-tx-lpi-clockgating" property for
stmmac.
MII Transmit clock gating, where the MAC hardware supports gating this
clock, is a function of the connected PHY capabilities, which it
reports through its status register.
GMAC versions that support transmit clock gating twiddle the LPITCSE
bit accordingly in the LPI control/status register, which is handled
by the GMAC core specific code.
So, "snps,en-tx-lpi-clockgating" not something that is a GMAC property,
but is a work-around for phylib not providing an interface to determine
whether the PHY allows the transmit clock to be disabled.
This series converts the two SoCs that make use of this property (which,
I hasten to add, is set in the SoC code) to use the PHY capability bit
instead of a DT property, then removes the DT property from the .dtsi,
deprecates it in the snps,dwmac binding, and finally in the stmmac code.
I am expecting some discussion on how to merge this, as I think the
order in which these changes is made is important - we don't want to
deprecate the old way until the new code has landed.
====================
Link: https://patch.msgid.link/Z9FVHEf3uUqtKzyt@shell.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Whether the MII transmit clock can be stopped is primarily a property
of the PHY (there is a capability bit that should be checked first.)
Whether the MAC is capable of stopping the transmit clock is a separate
issue, but this is already handled by the core DesignWare MAC code.
Therefore, snps,en-tx-lpi-clockgating is technically incorrect, and
this commit adds a warning should a DT be encountered with the property
present.
However, we keep backwards compatibility.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://patch.msgid.link/E1tsIUK-005vGk-H7@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Whether the MII transmit clock can be stopped is primarily a property
of the PHY (there is a capability bit that should be checked first.)
Whether the MAC is capable of stopping the transmit clock is a separate
issue, but this is already handled by the core DesignWare MAC code.
Therefore, snps,en-tx-lpi-clockgating is technically incorrect, so this
commit deprecates the property in the binding.
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIUF-005vGd-C5@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Whether the MII transmit clock can be stopped is primarily a property
of the PHY (there is a capability bit that should be checked first.)
Whether the MAC is capable of stopping the transmit clock is a separate
issue, but this is already handled by the core DesignWare MAC code.
As commit "net: stmmac: stm32: use PHY capability for TX clock stop"
adds the flag to use the PHY capability, remove the DT property that is
now unecessary.
Cc: Samin Guo <samin.guo@starfivetech.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIUA-005vGX-8A@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Whether the MII transmit clock can be stopped is primarily a property
of the PHY (there is a capability bit that should be checked first.)
Whether the MAC is capable of stopping the transmit clock is a separate
issue, but this is already handled by the core DesignWare MAC code.
As commit "net: stmmac: starfive: use PHY capability for TX clock stop"
adds the flag to use the PHY capability, remove the DT property that is
now unecessary.
Cc: Samin Guo <samin.guo@starfivetech.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIU5-005vGR-4c@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Whether the MII transmit clock can be stopped is primarily a property
of the PHY (there is a capability bit that should be checked first.)
Whether the MAC is capable of stopping the transmit clock is a separate
issue, but this is already handled by the core DesignWare MAC code.
Add the flag to allow the stmmac core to use the PHY capability.
Cc: Christophe Roullier <christophe.roullier@st.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIU0-005vGL-17@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Whether the MII transmit clock can be stopped is primarily a property
of the PHY (there is a capability bit that should be checked first.)
Whether the MAC is capable of stopping the transmit clock is a separate
issue, but this is already handled by the core DesignWare MAC code.
Add the flag to allow the stmmac core to use the PHY capability.
Cc: Samin Guo <samin.guo@starfivetech.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsITu-005vGF-TM@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Allow platform glue to instruct stmmac to make use of the PHY transmit
clock stop capability when deciding whether to allow the transmit clock
from the DWMAC core to be stopped.
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsITp-005vG9-Px@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Stefan Schmidt says:
====================
pull-request: ieee802154-next 2025-03-10
An update from ieee802154 for your *net-next* tree:
Andy Shevchenko reworked the ca8210 driver to use the gpiod API and fixed
a few problems of the driver along the way.
* tag 'ieee802154-for-net-next-2025-03-10' of git://git.kernel.org/pub/scm/linux/kernel/git/wpan/wpan-next:
dt-bindings: ieee802154: ca8210: Update polarity of the reset pin
ieee802154: ca8210: Switch to using gpiod API
ieee802154: ca8210: Get platform data via dev_get_platdata()
ieee802154: ca8210: Use proper setters and getters for bitwise types
====================
Link: https://patch.msgid.link/20250310185752.2683890-1-stefan@datenfreihafen.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Russell King says:
====================
net: stmmac: remove unnecessary of_get_phy_mode() calls
This series removes unnecessary of_get_phy_mode() calls from the stmmac
glue drivers. stmmac_probe_config_dt() / devm_stmmac_probe_config_dt()
already gets the interface mode using device_get_phy_mode() and stores
it in plat_dat->phy_interface.
Therefore, glue drivers using of_get_phy_mode() are just duplicating
the work that has already been done.
This series adjusts the glue drivers to remove their usage of
of_get_phy_mode().
====================
Link: https://patch.msgid.link/Z9FQjQZb0IMaQJ9H@shell.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.
Set gmac->interface from plat_dat->phy_interface.
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Acked-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGx-005v0F-Ev@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.
sun8i was using of_get_phy_mode() to set plat_dat->mac_interface, which
defaults to plat_dat->phy_interface when the mac-mode DT property is
not present. As nothing in arch/*/boot/dts sets the mac-mode property,
it is highly likely that these two will be identical, and thus there
is no need for this glue driver to set plat_dat->mac_interface.
Reviewed-by: Andre Przywara <andre.przywara@arm.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGs-005v09-CD@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.
Pass plat_dat into sti_dwmac_parse_data(), and set dwmac->interface
from plat_dat->phy_interface.
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGn-005v02-7G@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.
Set bsp_priv->phy_iface from plat->phy_interface.
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGi-005uzx-3p@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.
Set dwmac->phy_mode from plat_dat->phy_interface.
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGd-005uzr-0C@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.
Pass plat_dat into ipq806x_gmac_of_parse(), and set gmac->phy_mode from
plat_dat->phy_interface.
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGX-005uzl-TQ@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.
Rearrange the initialisation order so we can pass plat_dat into
anarion_config_dt(), thereby providing plat_dat->phy_interface as
necessary there.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGS-005uzf-QE@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.
Initialise priv_plat->phy_mode from plat->phy_interface
inmediatek_dwmac_common_data().
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGN-005uzZ-NG@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it a second time in qcom_ethqos_probe(). Use
plat_dat->phy_interface to initialise ethqos->phy_mode.
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGI-005uzT-KB@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
tcp_in_quickack_mode() is called from input path for small packets.
It calls __sk_dst_get() which reads sk->sk_dst_cache which has been
put in sock_read_tx group (for good reasons).
Then dst_metric(dst, RTAX_QUICKACK) also needs extra cache line misses.
Cache RTAX_QUICKACK in icsk->icsk_ack.dst_quick_ack to no longer pull
these cache lines for the cases a delayed ACK is scheduled.
After this patch TCP receive path does not longer access sock_read_tx
group.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250312083907.1931644-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Eric Dumazet says:
====================
inet: frags: fully use RCU
While inet reassembly uses RCU, it is acquiring/releasing
a refcount on struct inet_frag_queue in fast path,
for no good reason.
This was mentioned in one patch changelog seven years ago :/
This series is removing these refcount changes, by extending
RCU sections.
====================
Link: https://patch.msgid.link/20250312082250.1803501-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
As mentioned in commit 648700f76b ("inet: frags:
use rhashtables for reassembly units"):
A followup patch will even remove the refcount hold/release
left from prior implementation and save a couple of atomic
operations.
This patch implements this idea, seven years later.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250312082250.1803501-5-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
In the following patch, we no longer assume inet_frag_kill()
callers own a reference.
Consuming two refcounts from inet_frag_kill() would lead in UAF.
Propagate the pointer to the refs that will be consumed later
by the final inet_frag_putn() call.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250312082250.1803501-4-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
inet_frag_putn() can release multiple references
in one step.
Use it in inet_frags_free_cb().
Replace inet_frag_put(X) with inet_frag_putn(X, 1)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250312082250.1803501-2-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Since commit a4ea4c4776 ("rxrpc: Don't use a ring buffer for call Tx
queue") this function is not used anymore.
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250312063450.183652-1-yuehaibing@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
-----BEGIN PGP SIGNATURE-----
iQFHBAABCgAxFiEEn/sM2K9nqF/8FWzzDHRl3/mQkZwFAmfULLETHG1rbEBwZW5n
dXRyb25peC5kZQAKCRAMdGXf+ZCRnNkYCACi2AeabY32Q9uZRVexq6/i7uaZYJH9
hF1Rcee0CR2A7JxuMywO/8X6hiXJYsJ+yKOYDiwnspNsMAPsH9VjWjI+OYf2qmLq
+y8/rArx2p3S/01Nh/BBTNxUX5A2impDMnAwRwIgz39zGmrkVvN04NfPXPvtLRuA
+76V7GtRfy5vwdED6YNcGDUG/Ss5e2Shw88q8bTtmIlMviehAIPfhOKa6CCMNB7q
yVHeyvi1B/HQvruyQqhwa2BSy2V5FkZpbXvwTu7RM9mWG/gVJjgls1eqFNp8/bLN
YjbSztd/ZXQYd5jrCSbu+uPL72k+uwt2PdiO3sGuWR73ZiaLQeJFWHG/
=YF4Y
-----END PGP SIGNATURE-----
Merge tag 'linux-can-next-for-6.15-20250314' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next
Marc Kleine-Budde says:
====================
pull-request: can-next 2025-03-14
this is a pull request of 4 patches for net-next/main.
In the first 2 patches by Dimitri Fedrau add CAN transceiver support
to the flexcan driver.
Frank Li's patch adds i.MX94 support to the flexcan device tree
bindings.
The last patch is by Davide Caratti and adds protocol counter for
AF_CAN sockets.
linux-can-next-for-6.15-20250314
* tag 'linux-can-next-for-6.15-20250314' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next:
can: add protocol counter for AF_CAN sockets
dt-bindings: can: fsl,flexcan: add i.MX94 support
can: flexcan: add transceiver capabilities
dt-bindings: can: fsl,flexcan: add transceiver capabilities
====================
Link: https://patch.msgid.link/20250314132327.2905693-1-mkl@pengutronix.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
- bump version strings, by Simon Wunderlich
- drop batadv_priv_debug_log struct, by Sven Eckelmann
- adopt netdev_hold() / netdev_put(), by Eric Dumazet
- add support for jumbo frames, by Sven Eckelmann
- use consistent name for mesh interface, by Sven Eckelmann
- cleanup B.A.T.M.A.N. IV OGM aggregation handling,
by Sven Eckelmann (4 patches)
- add missing newlines for log macros, by Sven Eckelmann
-----BEGIN PGP SIGNATURE-----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=hmiI
-----END PGP SIGNATURE-----
Merge tag 'batadv-next-pullrequest-20250313' of git://git.open-mesh.org/linux-merge
Simon Wunderlich says:
====================
This feature/cleanup patchset includes the following patches:
- bump version strings, by Simon Wunderlich
- drop batadv_priv_debug_log struct, by Sven Eckelmann
- adopt netdev_hold() / netdev_put(), by Eric Dumazet
- add support for jumbo frames, by Sven Eckelmann
- use consistent name for mesh interface, by Sven Eckelmann
- cleanup B.A.T.M.A.N. IV OGM aggregation handling,
by Sven Eckelmann (4 patches)
- add missing newlines for log macros, by Sven Eckelmann
* tag 'batadv-next-pullrequest-20250313' of git://git.open-mesh.org/linux-merge:
batman-adv: add missing newlines for log macros
batman-adv: Limit aggregation size to outgoing MTU
batman-adv: Use actual packet count for aggregated packets
batman-adv: Switch to bitmap helper for aggregation handling
batman-adv: Limit number of aggregated packets directly
batman-adv: Use consistent name for mesh interface
batman-adv: Add support for jumbo frames
batman-adv: adopt netdev_hold() / netdev_put()
batman-adv: Drop batadv_priv_debug_log struct
batman-adv: Start new development cycle
====================
Link: https://patch.msgid.link/20250313164519.72808-1-sw@simonwunderlich.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Paolo Abeni says:
====================
udp_tunnel: GRO optimizations
The UDP tunnel GRO stage is source of measurable overhead for workload
based on UDP-encapsulated traffic: each incoming packets requires a full
UDP socket lookup and an indirect call.
In the most common setups a single UDP tunnel device is used. In such
case we can optimize both the lookup and the indirect call.
Patch 1 tracks per netns the active UDP tunnels and replaces the socket
lookup with a single destination port comparison when possible.
Patch 2 tracks the different types of UDP tunnels and replaces the
indirect call with a static one when there is a single UDP tunnel type
active.
I measure ~5% performance improvement in TCP over UDP tunnel stream
tests on top of this series.
v3: https://lore.kernel.org/netdev/cover.1741632298.git.pabeni@redhat.com/
v2: https://lore.kernel.org/netdev/cover.1741338765.git.pabeni@redhat.com/
v1: https://lore.kernel.org/netdev/cover.1741275846.git.pabeni@redhat.com/
====================
Link: https://patch.msgid.link/cover.1741718157.git.pabeni@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
It's quite common to have a single UDP tunnel type active in the
whole system. In such a case we can replace the indirect call for
the UDP tunnel GRO callback with a static call.
Add the related accounting in the control path and switch to static
call when possible. To keep the code simple use a static array for
the registered tunnel types, and size such array based on the kernel
config.
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/6fd1f9c7651151493ecab174e7b8386a1534170d.1741718157.git.pabeni@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Most UDP tunnels bind a socket to a local port, with ANY address, no
peer and no interface index specified.
Additionally it's quite common to have a single tunnel device per
namespace.
Track in each namespace the UDP tunnel socket respecting the above.
When only a single one is present, store a reference in the netns.
When such reference is not NULL, UDP tunnel GRO lookup just need to
match the incoming packet destination port vs the socket local port.
The tunnel socket never sets the reuse[port] flag[s]. When bound to no
address and interface, no other socket can exist in the same netns
matching the specified local port.
Matching packets with non-local destination addresses will be
aggregated, and eventually segmented as needed - no behavior changes
intended.
Note that the UDP tunnel socket reference is stored into struct
netns_ipv4 for both IPv4 and IPv6 tunnels. That is intentional to keep
all the fastpath-related netns fields in the same struct and allow
cacheline-based optimization. Currently both the IPv4 and IPv6 socket
pointer share the same cacheline as the `udp_table` field.
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/4d5c319c4471161829f50cb8436841de81a5edae.1741718157.git.pabeni@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tariq Toukan says:
====================
mlx5: Support setting a parent for a devlink rate node
This series by Carolina adds mlx5 support for the setting of a parent to
devlink rate nodes.
By introducing a hierarchical level to scheduling nodes, these changes
allow for more granular control over bandwidth allocation and isolation
of Virtual Functions.
Function renaming for parent setting on leafs:
- net/mlx5: Rename devlink rate parent set function for leaf nodes
Add support for hierarchy level tracking:
- net/mlx5: Introduce hierarchy level tracking on scheduling nodes
- net/mlx5: Preserve rate settings when creating a rate node
Support setting parent for rate nodes:
- net/mlx5: Add support for setting parent of nodes
====================
Link: https://patch.msgid.link/1741642016-44918-1-git-send-email-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Introduce `mlx5_esw_devlink_rate_node_parent_set()` to allow assigning
a parent to scheduling nodes.
Implement `mlx5_esw_qos_node_update_parent()` and
`mlx5_esw_qos_node_validate_set_parent()` to enforce constraints on
node reassignment.
Don't allow reassignment of nodes with active rate objects.
Update `esw_qos_node_set_parent()` to handle cases where
the parent is NULL. A NULL parent indicates that the scheduling element
is attached to the root scheduling element, and since only rate nodes
can be connected to the root, this update is now necessary.
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1741642016-44918-5-git-send-email-tariqt@nvidia.com
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
