| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
icsk->icsk_timeout can be replaced by icsk->icsk_retransmit_timer.expires
This saves 8 bytes in TCP/DCCP sockets and helps for better cache locality.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250324203607.703850-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Ensure that all accesses to mp_params are under the netdev
instance lock. The only change we need is to move
dev_memory_provider_uninstall() under the lock.
Appropriately swap the asserts.
Reviewed-by: Mina Almasry <almasrymina@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250324224537.248800-8-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
netdev netlink is the only reader of netdev_{,rx_}queue->napi,
and it already holds netdev->lock. Switch protection of
the writes to netdev->lock to "ops protected".
The expectation will be now that accessing queue->napi
will require netdev->lock for "ops locked" drivers, and
rtnl_lock for all other drivers.
Current "ops locked" drivers don't require any changes.
gve and netdevsim use _locked() helpers right next to
netif_queue_set_napi() so they must be holding the instance
lock. iavf doesn't call it. bnxt is a bit messy but all paths
seem locked.
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250324224537.248800-7-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Drivers which opt into instance lock protection of ops should
only call set_real_num_*_queues() under the instance lock.
This means that queue counts are double protected (writes
are under both rtnl_lock and instance lock, readers under
either).
Some readers may still be under the rtnl_lock, however, so for
now we need double protection of writers.
OTOH queue API paths are only under the protection of the instance
lock, so we need to validate that the instance is actually locking
ops, otherwise the input checks we do against queue count are racy.
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250324224537.248800-6-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Try to define some terminology for which fields are protected
by which lock and how. Some fields are protected by both rtnl_lock
and instance lock which is hard to talk about without having
a "key phrase" to refer to a particular protection scheme.
"ops protected" fields are defined later in the series, one by one.
Add ASSERT_RTNL() to netdev_ops_assert_locked() for drivers
not other instance protection of ops. Hopefully it's not too
confusion that netdev_lock_ops() does not match the lock which
netdev_ops_assert_locked() will assert, exactly. The noun "ops"
is in a different place in the name, so I think it's acceptable...
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250324224537.248800-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
lockdep asserts and predicates can operate on const pointers.
In the future this will let us add asserts in functions
which operate on const pointers like dev_get_min_mp_channel_count().
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250324224537.248800-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Since commit a953be53ce40 ("net-sysfs: add support for device-specific
rx queue sysfs attributes"), so for at least a decade now it is safe
to call net_rx_queue_update_kobjects() when SYSFS=n. That function
does its own ifdef-inery and will return 0. Remove the unnecessary
stub for netif_set_real_num_rx_queues().
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250324224537.248800-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
A recent commit added taking the netdev instance lock
in netdev_nl_bind_rx_doit(), but didn't remove it in
net_devmem_unbind_dmabuf() which it calls from an error path.
Always expect the callers of net_devmem_unbind_dmabuf() to
hold the lock. This is consistent with net_devmem_bind_dmabuf().
(Not so) coincidentally this also protects mp_param with the instance
lock, which the rest of this series needs.
Fixes: 1d22d3060b9b ("net: drop rtnl_lock for queue_mgmt operations")
Reviewed-by: Mina Almasry <almasrymina@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250324224537.248800-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
virtnet_probe() lacks the code to free rss_hdr in its error path.
Allocate rss_hdr with devres so that it will be automatically freed.
Fixes: 86a48a00efdf ("virtio_net: Support dynamic rss indirection table size")
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Link: https://patch.msgid.link/20250321-virtio-v2-4-33afb8f4640b@daynix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The new RSS configuration structures allow easily constructing data for
VIRTIO_NET_CTRL_MQ_RSS_CONFIG as they strictly follow the order of data
for the command.
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Link: https://patch.msgid.link/20250321-virtio-v2-3-33afb8f4640b@daynix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Mark the fields of struct virtio_net_ctrl_rss as little endian as
they are in struct virtio_net_rss_config, which it follows.
Fixes: c7114b1249fa ("drivers/net/virtio_net: Added basic RSS support.")
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Link: https://patch.msgid.link/20250321-virtio-v2-2-33afb8f4640b@daynix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
struct virtio_net_rss_config was less useful in actual code because of a
flexible array placed in the middle. Add new structures that split it
into two to avoid having a flexible array in the middle.
Suggested-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Link: https://patch.msgid.link/20250321-virtio-v2-1-33afb8f4640b@daynix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
'destroy_workqueue()' already drains the queue before destroying it, so
there is no need to flush it explicitly.
Remove the redundant 'flush_workqueue()' calls.
This was generated with coccinelle:
@@
expression E;
@@
- flush_workqueue(E);
destroy_workqueue(E);
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Reviewed-by: Geetha sowjanya <gakula@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250324080854.408188-1-nichen@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Revert "udp_tunnel: use static call for GRO hooks when possible"
This reverts commit 311b36574ceaccfa3f91b74054a09cd4bb877702.
Revert "udp_tunnel: create a fastpath GRO lookup."
This reverts commit 8d4880db378350f8ed8969feea13bdc164564fc1.
There are multiple small issues with the series. In the interest
of unblocking the merge window let's opt for a revert.
Link: https://lore.kernel.org/cover.1742557254.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
PHYs that are within copper SFP modules have their MDIO bus accessible
through address 0x56 (usually) on the i2c bus. The MDIO-I2C bridge is
desgned for 16 bits accesses, but we can also perform 8bits accesses by
reading/writing the high and low bytes sequentially.
This commit adds support for this type of accesses, thus supporting
smbus controllers such as the one in the VSC8552.
This was only tested on Copper SFP modules that embed a Marvell 88e1111
PHY.
Tested-by: Sean Anderson <sean.anderson@linux.dev>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250322075745.120831-3-maxime.chevallier@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The SFP module's eeprom and internals are accessible through an i2c bus.
It is possible that the SFP might be connected to an SMBus-only
controller, such as the one found in some PHY devices in the VSC85xx
family.
Introduce a set of sfp read/write ops that are going to be used if the
i2c bus is only capable of doing smbus byte accesses.
As Single-byte SMBus transaction go against SFF-8472 and breaks the
atomicity for diagnostics data access, hwmon is disabled in the case
of SMBus access.
Moreover, as this may cause other instabilities, print a warning at
probe time to indicate that the setup may be unreliable because of the
hardware design.
As hwmon may be disabled for both broken EEPROM and smbus, the warnings
are udpated accordingly.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250322075745.120831-2-maxime.chevallier@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
DTS example in the bindings should be indented with 2- or 4-spaces and
aligned with opening '- |', so correct any differences like 3-spaces or
mixtures 2- and 4-spaces in one binding.
No functional changes here, but saves some comments during reviews of
new patches built on existing code.
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Alex Elder <elder@riscstar.com>
Link: https://patch.msgid.link/20250324125222.82057-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
This fixes the following build warning:
```
drivers/net/ethernet/amd/au1000_eth.c:574:6: warning: no previous prototype for 'au1000_ReleaseDB' [-Wmissing-prototypes]
574 | void au1000_ReleaseDB(struct au1000_private *aup, struct db_dest *pDB)
| ^~~~~~~~~~~~~~~~
```
Signed-off-by: Johan Korsnes <johan.korsnes@gmail.com>
Cc: Andrew Lunn <andrew+netdev@lunn.ch>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250323190450.111241-1-johan.korsnes@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
RFS is using two kinds of hash tables.
First one is controlled by /proc/sys/net/core/rps_sock_flow_entries = 2^N
and using the N low order bits of the l4 hash is good enough.
Then each RX queue has its own hash table, controlled by
/sys/class/net/eth1/queues/rx-$q/rps_flow_cnt = 2^X
Current hash function, using the X low order bits is suboptimal,
because RSS is usually using Func(hash) = (hash % power_of_two);
For example, with 32 RX queues, 6 low order bits have no entropy
for a given queue.
Switch this hash function to hash_32(hash, log) to increase
chances to use all possible slots and reduce collisions.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <tom@herbertland.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250321171309.634100-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Rockchip RK3528 (and RV1106) has a different integrated PHY compared to
the integrated PHY on RK3228/RK3328. Current powerup/down operation is
not compatible with the integrated PHY found in these newer SoCs.
Add operations to powerup/down the integrated PHY found in RK3528.
Use helpers that can be used by other GMAC variants in the future.
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250319214415.3086027-6-jonas@kwiboo.se
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Rockchip RK3528 (and RV1106) has a different integrated PHY compared to
the integrated PHY on RK3228/RK3328. Current powerup/down operation is
not compatible with the integrated PHY found in these newer SoCs.
Add a new integrated_phy_powerdown operation and change the call chain
for integrated_phy_powerup to prepare support for the integrated PHY
found in these newer SoCs.
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250319214415.3086027-5-jonas@kwiboo.se
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Rockchip RK3528 (and RV1106) has a different integrated PHY compared to
the integrated PHY on RK3228/RK3328. Current powerup/down operation is
not compatible with the integrated PHY found in these SoCs.
Move the rk_gmac_integrated_phy_powerup/down functions to top of the
file to prepare for them to be called directly by a GMAC variant
specific powerup/down operation.
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250319214415.3086027-4-jonas@kwiboo.se
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Rockchip RK3528 has two Ethernet controllers based on Synopsys DWC
Ethernet QoS IP.
Add initial support for the RK3528 GMAC variant.
Signed-off-by: David Wu <david.wu@rock-chips.com>
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Link: https://patch.msgid.link/20250319214415.3086027-3-jonas@kwiboo.se
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Rockchip RK3528 has two Ethernet controllers based on Synopsys DWC
Ethernet QoS IP.
Add compatible string for the RK3528 variant.
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20250319214415.3086027-2-jonas@kwiboo.se
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The DesignWare core requires the receive clock to be running during
certain operations. Ensure that we block PHY RXC clock-stop during
these operations.
This is a best-efforts change - not everywhere can be covered by this
because of net's core locking, which means we can't access the MDIO
bus to configure the PHY to disable RXC clock-stop in certain areas.
These are marked with FIXME comments.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tvO6p-008Vjz-Qy@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Some MACs require the PHY receive clock to be running to complete setup
actions. This may fail if the PHY has negotiated EEE, the MAC supports
receive clock stop, and the link has entered LPI state. Provide a pair
of APIs that MAC drivers can use to temporarily block the PHY disabling
the receive clock.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tvO6k-008Vjt-MZ@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
As the previous commit addressed DWGMAC resuming with a PHY in
suspended state, there is now no need for socfpga to work around
this. Remove this code.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tvO6f-008Vjn-J1@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The Synopsys Designware GMAC core databook requires all clocks to be
active in order to complete software reset, which we perform during
resume.
However, IEEE 802.3 allows a PHY to stop its clocks when placed in
low-power mode, which happens when the system is suspended and WoL
is not enabled.
As an attempt to work around this, commit 36d18b5664ef ("net: stmmac:
start phylink instance before stmmac_hw_setup()") started phylink
early, but this has the side effect that the mac_link_up() method may
be called before or during the initialisation of GMAC hardware.
We also have the socfpga glue driver directly calling phy_resume()
also as an attempt to work around this.
In a previous commit, phylink_prepare_resume() has been introduced
to give MAC drivers a way to ensure that the PHY is resumed prior to
their initialisation of their MAC hardware. This commit adds the call,
and moves the phylink_resume() call back to where it should be before
the aforementioned commit.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tvO6a-008Vjh-FG@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
When the system is suspended, the PHY may be placed in low-power mode
by setting the BMCR 0.11 Power down bit. IEEE 802.3 states that the
behaviour of the PHY in this state is implementation specific, and
the PHY is not required to meet the RX_CLK and TX_CLK requirements.
Essentially, this means that a PHY may stop the clocks that it is
generating while in power down state.
However, MACs exist which require the clocks from the PHY to be running
in order to properly resume. phylink_prepare_resume() provides them
with a way to clear the Power down bit early.
Note, however, that IEEE 802.3 gives PHYs up to 500ms grace before the
transmit and receive clocks meet the requirements after clearing the
power down bit.
Add a resume preparation function, which will ensure that the receive
clock from the PHY is appropriately configured while resuming.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tvO6V-008Vjb-AP@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Unlike X2 and EF100, we do not attempt to parse the firmware file to
find an image within it; we simply hand the entire file to the MC,
which is responsible for understanding any container formats we might
use and validating that the firmware file is applicable to this NIC.
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/9a72a74002a7819c780b0a18ce9294c9d4e1db12.1742493017.git.ecree.xilinx@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/bcb7597460a5a99d1dca4ef282f4aa2dd46ae545.1742493017.git.ecree.xilinx@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Unlike Siena, no EF10 board ever had an external PHY, and consequently
MDIO handling isn't even built into the firmware. Since Siena has
been split out into its own driver, the MDIO code can be deleted from
the sfc driver.
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/aa689d192ddaef7abe82709316c2be648a7bd66e.1742493017.git.ecree.xilinx@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Commit 14a196807482 ("net: reorganize IP MIB values") changed
MIB values to group hot fields together.
Since then 5 new fields have been added without caring about
data locality.
This patch moves IPSTATS_MIB_OUTPKTS, IPSTATS_MIB_NOECTPKTS,
IPSTATS_MIB_ECT1PKTS, IPSTATS_MIB_ECT0PKTS, IPSTATS_MIB_CEPKTS
to the hot portion of per-cpu data.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250320101434.3174412-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
TCP uses generic skb_set_owner_r() and sock_rfree()
for received packets, with socket lock being owned.
Switch to private versions, avoiding two atomic operations
per packet.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250320121604.3342831-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In rtm_del_nexthop(), only nexthop_find_by_id() and remove_nexthop()
require RTNL as they touch net->nexthop.rb_root.
Let's move RTNL down as rtnl_net_lock() before nexthop_find_by_id().
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250319230743.65267-8-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
If we pass false to the rtnl_held param of lwtunnel_valid_encap_type(),
we can move RTNL down before rtm_to_nh_config_rtnl().
Let's use rtnl_net_lock() in rtm_new_nexthop().
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250319230743.65267-7-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The number of NHA_GROUP entries is guaranteed to be non-zero in
nh_check_attr_group().
Let's remove the redundant check in nexthop_create_group().
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250319230743.65267-6-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
nexthop_add() checks if NLM_F_REPLACE is specified without
non-zero NHA_ID, which does not require RTNL.
Let's move the check to rtm_new_nexthop().
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250319230743.65267-5-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
NHA_OIF needs to look up a device by __dev_get_by_index(),
which requires RTNL.
Let's move NHA_OIF validation to rtm_to_nh_config_rtnl().
Note that the proceeding checks made the original !cfg->nh_fdb
check redundant.
NHA_FDB is set -> NHA_OIF cannot be set
NHA_FDB is set but false -> NHA_OIF must be set
NHA_FDB is not set -> NHA_OIF must be set
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250319230743.65267-4-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
We will push RTNL down to rtm_new_nexthop(), and then we
want to move non-RTNL operations out of the scope.
nh_check_attr_group() validates NHA_GROUP attributes, and
nexthop_find_by_id() and some validation requires RTNL.
Let's factorise such parts as nh_check_attr_group_rtnl()
and call it from rtm_to_nh_config_rtnl().
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250319230743.65267-3-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
We will split rtm_to_nh_config() into non-RTNL and RTNL parts,
and then the latter also needs tb.
As a prep, let's move nlmsg_parse() to rtm_new_nexthop().
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250319230743.65267-2-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
ip6_rcv_core() is using:
__IP6_ADD_STATS(net, idev,
IPSTATS_MIB_NOECTPKTS +
(ipv6_get_dsfield(hdr) & INET_ECN_MASK),
max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
This is currently evaluating both expressions twice.
Fix _DEVADD() and _DEVUPD() macros to evaluate their arguments once.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250319212516.2385451-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
For CT action with commit argument, it's usually followed by the
forward action, either to the output netdev or next chain. The default
behavior for software is to drop by setting action attribute to
TC_ACT_SHOT instead of TC_ACT_PIPE if it's the last action. But driver
can't handle it, so block the offload for such case.
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1742392983-153050-6-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In nic mode CT setup where we do hairpin between the two
nics, both nics register to the same flow table (per zone),
and try to offload all rules on it.
Instead, filter the rules that originated from the relevant nic
(so only one side is offloaded for each nic).
Signed-off-by: Paul Blakey <paulb@nvidia.com>
Reviewed-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1742392983-153050-5-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Align mlx5 driver usage of 'pfnum' with the documentation clarification
introduced in commit bb70b0d48d8e ("devlink: Improve the port attributes
description").
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1742392983-153050-4-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Currently, mlx5_is_reset_now_capable() checks whether the pci bridge is
accessible only on bridge hot plug capability check. If the pci bridge
is not accessible, reset now will fail regardless of bridge hotplug
capability. Move this check to function mlx5_is_reset_now_capable()
which, in such case, aborts the reset and does so in the request phase
instead of the reset now phase.
Signed-off-by: Aya Levin <ayal@nvidia.com>
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Amir Tzin <amirtz@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1742392983-153050-3-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
As queue affinity is being deprecated and will no longer be supported
in the future, Always check for the presence of the port selection
namespace. When available, leverage it to distribute traffic
across the physical ports via steering, ensuring compatibility with
future NICs.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1742392983-153050-2-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
For simplicity reasons, the driver avoids crossing work queue fragment
boundaries within the same TX WQE (Work-Queue Element). Until today, as
the number of packets in a TX MPWQE (Multi-Packet WQE) descriptor is not
known in advance, the driver pre-prepared contiguous memory for the
largest possible WQE. For this, when getting too close to the fragment
edge, having no room for the largest WQE possible, the driver was
filling the fragment remainder with NOP descriptors, aligning the next
descriptor to the beginning of the next fragment.
Generating and handling these NOPs wastes resources, like: CPU cycles,
work-queue entries fetched to the device, and PCI bandwidth.
In this patch, we replace this NOPs filling mechanism in the TX MPWQE
flow. Instead, we utilize the remaining entries of the fragment with a
TX MPWQE. If this room turns out to be too small, we simply open an
additional descriptor starting at the beginning of the next fragment.
Performance benchmark:
uperf test, single server against 3 clients.
TCP multi-stream, bidir, traffic profile "2x350B read, 1400B write".
Bottleneck is in inbound PCI bandwidth (device POV).
+---------------+------------+------------+--------+
| | Before | After | |
+---------------+------------+------------+--------+
| BW | 117.4 Gbps | 121.1 Gbps | +3.1% |
+---------------+------------+------------+--------+
| tx_packets | 15 M/sec | 15.5 M/sec | +3.3% |
+---------------+------------+------------+--------+
| tx_nops | 3 M/sec | 0 | -100% |
+---------------+------------+------------+--------+
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/1742391746-118647-1-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Executing dql_reset after setting a non-zero value for limit_min can
lead to an unreasonable situation where dql->limit is less than
dql->limit_min.
For instance, after setting
/sys/class/net/eth*/queues/tx-0/byte_queue_limits/limit_min,
an ifconfig down/up operation might cause the ethernet driver to call
netdev_tx_reset_queue, which in turn invokes dql_reset.
In this case, dql->limit is reset to 0 while dql->limit_min remains
non-zero value, which is unexpected. The limit should always be
greater than or equal to limit_min.
Signed-off-by: Jing Su <jingsusu@didiglobal.com>
Link: https://patch.msgid.link/Z9qHD1s/NEuQBdgH@pilot-ThinkCentre-M930t-N000
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
It's always TEST_TIMEOUT_SEC, with an unjustified exception in rst test,
that is more paranoia-long timeout rather than based on requirements.
Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://patch.msgid.link/20250319-tcp-ao-selftests-polling-v2-7-da48040153d1@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
Eric Dumazet
Jakub Kicinski
Akihiko Odaki
Chen Ni
Maxime Chevallier
Krzysztof Kozlowski
Johan Korsnes
Jonas Karlman
David Wu
Russell King (Oracle)
Edward Cree
Kuniyuki Iwashima
Jianbo Liu
Paul Blakey
Shay Drory
Amir Tzin
Mark Bloch
Tariq Toukan
Jing Su
Dmitry Safonov