net/mlx5e: XDP, Consider large muti-buffer packets in Striding RQ params calculations
Function mlx5e_rx_get_linear_stride_sz() returns PAGE_SIZE immediately
in case an XDP program is attached. The more accurate formula is
ALIGN(sz, PAGE_SIZE), to prevent two packets from residing on the same
page.
The assumption behind the current code is that sz <= PAGE_SIZE holds for
all cases with XDP program set.
This is true because it is being called from:
- 3 times from Striding RQ flows, in which XDP is not supported for such
large packets.
- 1 time from Legacy RQ flow, under the condition
mlx5e_rx_is_linear_skb().
No functional change here, just removing the implied assumption in
preparation for supporting XDP multi-buffer in Striding RQ.
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com> Signed-off-by: Tariq Toukan <tariqt@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net/mlx5e: XDP, Let XDP checker function get the params as input
Change mlx5e_xdp_allowed() so it gets the params structure with the
xdp_prog applied, rather than creating a local copy based on the current
params in priv.
This reduces the amount of memory on the stack, and acts on the exact
params instance that's about to be applied.
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com> Signed-off-by: Tariq Toukan <tariqt@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net/mlx5e: XDP, Improve Striding RQ check with XDP
Non-linear mem scheme of Striding RQ does not yet support XDP at this
point. Take the check where it belongs, inside the params validation
function mlx5e_params_validate_xdp().
Reviewed-by: Gal Pressman <gal@nvidia.com> Reviewed-by: Saeed Mahameed <saeedm@nvidia.com> Signed-off-by: Tariq Toukan <tariqt@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net/mlx5e: XDP, Add support for multi-buffer XDP redirect-in
Handle multi-buffer XDP redirect-in requests coming through
mlx5e_xdp_xmit.
Extend struct mlx5e_xmit_data_frags with an additional dma_arr field, to
point to the fragments dma mapping, as they cannot be retrieved via the
page_pool_get_dma_addr() function.
Push a dma_addr xdpi instance per each fragment, and use them in the
completion flow to dma_unmap the frags.
Finally, remove the restriction in mlx5e_open_xdpsq, and set the flag in
xdp_features.
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com> Signed-off-by: Tariq Toukan <tariqt@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net/mlx5e: XDP, Use multiple single-entry objects in xdpi_fifo
Here we fix the current wi->num_pkts abuse, as it was used to indicate
multiple xdpi entries in the xdpi_fifo.
Instead, reduce mlx5e_xdp_info to the size of a single field, making it
a union of unions. Per packet, use as many instances as needed to
provide the information needed at the time of completion.
The sequence of xdpi instances pushed is well defined, derived by the
xmit_mode.
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com> Signed-off-by: Tariq Toukan <tariqt@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
stmmac_dev_probe doesn't propagate feature flags to VLANs. So features
like offloading don't correspond with the general features and it's not
possible to manipulate features via ethtool -K to affect VLANs.
Propagate feature flags to vlan features. Drop TSO feature because
it does not work on VLANs yet.
Hangbin Liu [Tue, 18 Apr 2023 03:48:41 +0000 (11:48 +0800)]
bonding: add software tx timestamping support
Currently, bonding only obtain the timestamp (ts) information of
the active slave, which is available only for modes 1, 5, and 6.
For other modes, bonding only has software rx timestamping support.
However, some users who use modes such as LACP also want tx timestamp
support. To address this issue, let's check the ts information of each
slave. If all slaves support tx timestamping, we can enable tx
timestamping support for the bond.
Add a note that the get_ts_info may be called with RCU, or rtnl or
reference on the device in ethtool.h>
====================
Add Ethernet driver for StarFive JH7110 SoC
This series adds ethernet support for the StarFive JH7110 RISC-V SoC,
which includes a dwmac-5.20 MAC driver (from Synopsys DesignWare).
This series has been tested and works fine on VisionFive-2 v1.2A and
v1.3B SBC boards.
For more information and support, you can visit RVspace wiki[1].
You can simply review or test the patches at the link [2].
This patchset should be applied after the patchset [3] [4].
r8169: use new macro netif_subqueue_maybe_stop in rtl8169_start_xmit
Use new net core macro netif_subqueue_maybe_stop in the start_xmit path
to simplify the code. Whilst at it, set the tx queue start threshold to
twice the stop threshold. Before values were the same, resulting in
stopping/starting the queue more often than needed.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
====================
Ocelot/Felix driver support for preemptible traffic classes
The series "Add tc-mqprio and tc-taprio support for preemptible traffic
classes" from:
https://lore.kernel.org/netdev/20230220122343.1156614-1-vladimir.oltean@nxp.com/
was eventually submitted in a form without the support for the
Ocelot/Felix switch driver. This patch set picks up that work again,
and presents a fairly modified form compared to the original.
====================
Vladimir Oltean [Sat, 15 Apr 2023 17:05:51 +0000 (20:05 +0300)]
net: mscc: ocelot: add support for preemptible traffic classes
In order to not transmit (preemptible) frames which will be received by
the link partner as corrupted (because it doesn't support FP), the
hardware requires the driver to program the QSYS_PREEMPTION_CFG_P_QUEUES
register only after the MAC Merge layer becomes active (verification
succeeds, or was disabled).
There are some cases when FP is known (through experimentation) to be
broken. Give priority to FP over cut-through switching, and disable FP
for known broken link modes.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Vladimir Oltean [Sat, 15 Apr 2023 17:05:50 +0000 (20:05 +0300)]
net: dsa: felix: act upon the mqprio qopt in taprio offload
The mqprio queue configuration can appear either through
TC_SETUP_QDISC_MQPRIO or through TC_SETUP_QDISC_TAPRIO. Make sure both
are treated in the same way.
Code does nothing new for now (except for rejecting multiple TXQs per
TC, which is a useless concept with DSA switches).
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Ferenc Fejes <fejes@inf.elte.hu> Reviewed-by: Simon Horman <simon.horman@corigine.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Vladimir Oltean [Sat, 15 Apr 2023 17:05:49 +0000 (20:05 +0300)]
net: mscc: ocelot: add support for mqprio offload
This doesn't apply anything to hardware and in general doesn't do
anything that the software variant doesn't do, except for checking that
there isn't more than 1 TXQ per TC (TXQs for a DSA switch are a dubious
concept anyway). The reason we add this is to be able to parse one more
field added to struct tc_mqprio_qopt_offload, namely preemptible_tcs.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Ferenc Fejes <fejes@inf.elte.hu> Reviewed-by: Simon Horman <simon.horman@corigine.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Vladimir Oltean [Sat, 15 Apr 2023 17:05:48 +0000 (20:05 +0300)]
net: mscc: ocelot: don't rely on cached verify_status in ocelot_port_get_mm()
ocelot_mm_update_port_status() updates mm->verify_status, but when the
verification state of a port changes, an IRQ isn't emitted, but rather,
only when the verification state reaches one of the final states (like
DISABLED, FAILED, SUCCEEDED) - things that would affect mm->tx_active,
which is what the IRQ *is* actually emitted for.
That is to say, user space may miss reports of an intermediary MAC Merge
verification state (like from INITIAL to VERIFYING), unless there was an
IRQ notifying the driver of the change in mm->tx_active as well.
This is not a huge deal, but for reliable reporting to user space, let's
call ocelot_mm_update_port_status() synchronously from
ocelot_port_get_mm(), which makes user space see the current MM status.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Vladimir Oltean [Sat, 15 Apr 2023 17:05:47 +0000 (20:05 +0300)]
net: mscc: ocelot: optimize ocelot_mm_irq()
The MAC Merge IRQ of all ports is shared with the PTP TX timestamp IRQ
of all ports, which means that currently, when a PTP TX timestamp is
generated, felix_irq_handler() also polls for the MAC Merge layer status
of all ports, looking for changes. This makes the kernel do more work,
and under certain circumstances may make ptp4l require a
tx_timestamp_timeout argument higher than before.
Changes to the MAC Merge layer status are only to be expected under
certain conditions - its TX direction needs to be enabled - so we can
check early if that is the case, and omit register access otherwise.
Make ocelot_mm_update_port_status() skip register access if
mm->tx_enabled is unset, and also call it once more, outside IRQ
context, from ocelot_port_set_mm(), when mm->tx_enabled transitions from
true to false, because an IRQ is also expected in that case.
Also, a port may have its MAC Merge layer enabled but it may not have
generated the interrupt. In that case, there's no point in writing to
DEV_MM_STATUS to acknowledge that IRQ. We can reduce the number of
register writes per port with MM enabled by keeping an "ack" variable
which writes the "write-one-to-clear" bits. Those are 3 in number:
PRMPT_ACTIVE_STICKY, UNEXP_RX_PFRM_STICKY and UNEXP_TX_PFRM_STICKY.
The other fields in DEV_MM_STATUS are read-only and it doesn't matter
what is written to them, so writing zero is just fine.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Unfortunately, the workarounds for the hardware bugs make it pointless
to keep fine-grained locking for the MAC Merge state of each port.
Our vsc9959_cut_through_fwd() implementation requires
ocelot->fwd_domain_lock to be held, in order to serialize with changes
to the bridging domains and to port speed changes (which affect which
ports can be cut-through). Simultaneously, the traffic classes which can
be cut-through cannot be preemptible at the same time, and this will
depend on the MAC Merge layer state (which changes from threaded
interrupt context).
Since vsc9959_cut_through_fwd() would have to hold the mm->lock of all
ports for a correct and race-free implementation with respect to
ocelot_mm_irq(), in practice it means that any time a port's mm->lock is
held, it would potentially block holders of ocelot->fwd_domain_lock.
In the interest of simple locking rules, make all MAC Merge layer state
changes (and preemptible traffic class changes) be serialized by the
ocelot->fwd_domain_lock.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Vladimir Oltean [Sat, 15 Apr 2023 17:05:45 +0000 (20:05 +0300)]
net: mscc: ocelot: export a single ocelot_mm_irq()
When the switch emits an IRQ, we don't know what caused it, and we
iterate through all ports to check the MAC Merge status.
Move that iteration inside the ocelot lib; we will change the locking in
a future change and it would be good to encapsulate that lock completely
within the ocelot lib.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Leon Romanovsky [Thu, 13 Apr 2023 12:29:27 +0000 (15:29 +0300)]
net/mlx5e: Create IPsec table with tunnel support only when encap is disabled
Current hardware doesn't support double encapsulation which is
happening when IPsec packet offload tunnel mode is configured
together with eswitch encap option.
Any user attempt to add new SA/policy after he/she sets encap mode, will
generate the following FW syndrome:
mlx5_core 0000:08:00.0: mlx5_cmd_out_err:803:(pid 1904): CREATE_FLOW_TABLE(0x930) op_mod(0x0) failed,
status bad parameter(0x3), syndrome (0xa43321), err(-22)
Make sure that we block encap changes before creating flow steering tables.
This is applicable only for packet offload in tunnel mode, while packet
offload in transport mode and crypto offload, don't have such limitation
as they don't perform encapsulation.
Reviewed-by: Raed Salem <raeds@nvidia.com> Signed-off-by: Leon Romanovsky <leonro@nvidia.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Leon Romanovsky [Thu, 13 Apr 2023 12:29:26 +0000 (15:29 +0300)]
net/mlx5: Allow blocking encap changes in eswitch
Existing eswitch encap option enables header encapsulation. Unfortunately
currently available hardware isn't able to perform double encapsulation,
which can happen once IPsec packet offload tunnel mode is used together
with encap mode set to BASIC.
So as a solution for misconfiguration, provide an option to block encap
changes, which will be used for IPsec packet offload.
Reviewed-by: Emeel Hakim <ehakim@nvidia.com> Signed-off-by: Leon Romanovsky <leonro@nvidia.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Leon Romanovsky [Thu, 13 Apr 2023 12:29:25 +0000 (15:29 +0300)]
net/mlx5e: Listen to ARP events to update IPsec L2 headers in tunnel mode
In IPsec packet offload mode all header manipulations are performed by
hardware, which is responsible to add/remove L2 header with source and
destinations MACs.
CX-7 devices don't support offload of in-kernel routing functionality,
as such HW needs external help to fill other side MAC as it isn't
available for HW.
As a solution, let's listen to neigh ARP updates and reconfigure IPsec
rules on the fly once new MAC data information arrives.
Signed-off-by: Leon Romanovsky <leonro@nvidia.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
From time to time, it was observed that the nanosecond part of the
received timestamp, which is extracted from the IFH, it was actually
bigger than 1 second. So then when actually calculating the full
received timestamp, based on the nanosecond part from IFH and the second
part which is read from HW, it was actually wrong.
The issue seems to be inside the function lan966x_ifh_get, which
extracts information from an IFH(which is an byte array) and returns the
value in a u64. When extracting the timestamp value from the IFH, which
starts at bit 192 and have the size of 32 bits, then if the most
significant bit was set in the timestamp, then this bit was extended
then the return value became 0xffffffff... . And the reason of this is
because constants without any postfix are treated as signed longs and
that is the reason why '1 << 31' becomes 0xffffffff80000000.
This is fixed by adding the postfix 'ULL' to 1.
Fixes: fd7627833ddf ("net: lan966x: Stop using packing library") Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 17 Apr 2023 07:28:21 +0000 (08:28 +0100)]
Merge branch 'sctp-info-dump'
Xin Long says:
====================
sctp: add some missing peer_capables in sctp info dump
The 1st patch removes the unused and obsolete hostname_address from
sctp_association peer and also the bit from sctp_info peer_capables,
and then reuses its bit for reconf_capable and use the higher
available bit for intl_capable in the 2nd patch.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Xin Long [Fri, 14 Apr 2023 21:21:16 +0000 (17:21 -0400)]
sctp: add intl_capable and reconf_capable in ss peer_capable
There are two new peer capables have been added since sctp_diag was
introduced into SCTP. When dumping the peer capables, these two new
peer capables should also be included. To not break the old capables,
reconf_capable takes the old hostname_address bit, and intl_capable
uses the higher available bit in sctpi_peer_capable.
Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Xin Long [Fri, 14 Apr 2023 21:21:15 +0000 (17:21 -0400)]
sctp: delete the obsolete code for the host name address param
In the latest RFC9260, the Host Name Address param has been deprecated.
For INIT chunk:
Note 3: An INIT chunk MUST NOT contain the Host Name Address
parameter. The receiver of an INIT chunk containing a Host Name
Address parameter MUST send an ABORT chunk and MAY include an
"Unresolvable Address" error cause.
For Supported Address Types:
The value indicating the Host Name Address parameter MUST NOT be
used when sending this parameter and MUST be ignored when receiving
this parameter.
Currently Linux SCTP doesn't really support Host Name Address param,
but only saves some flag and print debug info, which actually won't
even be triggered due to the verification in sctp_verify_param().
This patch is to delete those dead code.
Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Most of the code had an issue according to ShellCheck.
That's mainly due to the fact it incorrectly believes most of the code
was unreachable because it's invoked by variable name, see how the
"tests" array is used.
Once SC2317 has been ignored, three small warnings were still visible:
- SC2155: Declare and assign separately to avoid masking return values.
- SC2046: Quote this to prevent word splitting: can be ignored because
"ip netns pids" can display more than one pid.
- SC2166: Prefer [ p ] || [ q ] as [ p -o q ] is not well defined.
This probably didn't fix any actual issues but it might help spotting
new interesting warnings reported by ShellCheck as just before,
ShellCheck was reporting issues for most lines making it a bit useless.
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: David S. Miller <davem@davemloft.net>
selftests: mptcp: remove duplicated entries in usage
mptcp_connect tool was printing some duplicated entries when showing how
to use it: -j -l -r
While at it, I also:
- moved the very few entries that were not sorted,
- added -R that was missing since
commit 8a4b910d005d ("mptcp: selftests: add rcvbuf set option"),
- removed the -u parameter that has been removed in
commit f730b65c9d85 ("selftests: mptcp: try to set mptcp ulp mode in different sk states").
No need to backport this, it is just an internal tool used by our
selftests. The help menu is mainly useful for MPTCP kernel devs.
Acked-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: David S. Miller <davem@davemloft.net>
This will help occasional developers to find our git repo without having
to look at our wiki.
Acked-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: David S. Miller <davem@davemloft.net>
mptcp: make userspace_pm_append_new_local_addr static
mptcp_userspace_pm_append_new_local_addr() has always exclusively been
used in pm_userspace.c since its introduction in
commit 4638de5aefe5 ("mptcp: handle local addrs announced by userspace PMs").
So make it static.
Signed-off-by: Geliang Tang <geliang.tang@suse.com> Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 17 Apr 2023 07:18:34 +0000 (08:18 +0100)]
Merge branch 'mptcp-subflow-init'
Matthieu Baerts says:
====================
mptcp: refactor first subflow init
This series refactors the initialisation of the first subflow of a
listen socket. The first subflow allocation is no longer done at the
initialisation of the socket but later, when the connection request is
received or when requested by the userspace.
This is needed not just because Paolo likes to refactor things but
because this simplifies the code and makes the behaviour more consistent
with the rest. Also, this is a prerequisite for future patches adding
proper support of SELinux/LSM labels with MPTCP and accept(2).
In [1], Ondrej Mosnacek explained they discovered the (userspace-facing)
sockets returned by accept(2) when using MPTCP always end up with the
label representing the kernel (typically system_u:system_r:kernel_t:s0),
while it would make more sense to inherit the context from the parent
socket (the one that is passed to accept(2)).
Before being able to properly support that on SELinux/LSM side, patches
2-3/5 prepare the code to simplify the patch 4/5 moving the allocation.
Patch 1/5 is a small clean-up seen while working on the series and patch
5/5 is a small improvement when closing unaccepted sockets.
Paolo Abeni [Fri, 14 Apr 2023 14:08:04 +0000 (16:08 +0200)]
mptcp: fastclose msk when cleaning unaccepted sockets
When cleaning up unaccepted mptcp socket still laying inside
the listener queue at listener close time, such sockets will
go through a regular close, waiting for a timeout before
shutting down the subflows.
There is no need to keep the kernel resources in use for
such a possibly long time: short-circuit to fast-close.
Signed-off-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: David S. Miller <davem@davemloft.net>
Paolo Abeni [Fri, 14 Apr 2023 14:08:03 +0000 (16:08 +0200)]
mptcp: move first subflow allocation at mpc access time
In the long run this will simplify the mptcp code and will
allow for more consistent behavior. Move the first subflow
allocation out of the sock->init ops into the __mptcp_nmpc_socket()
helper.
Since the first subflow creation can now happen after the first
setsockopt() we additionally need to invoke mptcp_sockopt_sync()
on it.
Signed-off-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: David S. Miller <davem@davemloft.net>
So that we can avoid a bunch of check in fastpath. Additionally we
can specialize such check according to the specific fastopen method
- defer_connect vs MSG_FASTOPEN.
The latter bits will simplify the next patches.
Signed-off-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: David S. Miller <davem@davemloft.net>
Paolo Abeni [Fri, 14 Apr 2023 14:08:01 +0000 (16:08 +0200)]
mptcp: avoid unneeded __mptcp_nmpc_socket() usage
In a few spots, the mptcp code invokes the __mptcp_nmpc_socket() helper
multiple times under the same socket lock scope. Additionally, in such
places, the socket status ensures that there is no MP capable handshake
running.
Under the above condition we can replace the later __mptcp_nmpc_socket()
helper invocation with direct access to the msk->subflow pointer and
better document such access is not supposed to fail with WARN().
Signed-off-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: David S. Miller <davem@davemloft.net>
Paolo Abeni [Fri, 14 Apr 2023 14:08:00 +0000 (16:08 +0200)]
mptcp: drop unneeded argument
After commit 3a236aef280e ("mptcp: refactor passive socket initialization"),
every mptcp_pm_fully_established() call is always invoked with a
GFP_ATOMIC argument. We can then drop it.
Signed-off-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 17 Apr 2023 07:14:21 +0000 (08:14 +0100)]
Merge tag 'mlx5-updates-2023-04-14' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
mlx5-updates-2023-04-14
Yevgeny Kliteynik Says:
=======================
SW Steering: Support pattern/args modify_header actions
The following patch series adds support for a new pattern/arguments type
of modify_header actions.
Starting with ConnectX-6 DX, we use a new design of modify_header FW object.
The current modify_header object allows for having only limited number of
these FW objects, which means that we are limited in the number of offloaded
flows that require modify_header action.
The new approach comprises of two types of objects: pattern and argument.
Pattern holds header modification templates, later used with corresponding
argument object to create complete header modification actions.
The pattern indicates which headers are modified, while the arguments
provide the specific values.
Therefore a single pattern can be used with different arguments in different
flows, enabling offloading of large number of modify_header flows.
- Patch 1, 2: Add ICM pool for modify-header-pattern objects and implement
patterns cache, allowing patterns reuse for different flows
- Patch 3: Allow for chunk allocation separately for STEv0 and STEv1
- Patch 4: Read related device capabilities
- Patch 5: Add create/destroy functions for the new general object type
- Patch 6: Add support for writing modify header argument to ICM
- Patch 7, 8: Some required fixes to support pattern/arg - separate read
buffer from the write buffer and fix QP continuous allocation
- Patch 9: Add pool for modify header arg objects
- Patch 10, 11, 12: Implement MODIFY_HEADER and TNL_L3_TO_L2 actions with
the new patterns/args design
- Patch 13: Optimization - set modify header action of size 1 directly on
the STE instead of separate pattern/args combination
- Patch 14: Adjust debug dump for patterns/args
- Patch 15: Enable patterns and arguments for supporting devices
David S. Miller [Mon, 17 Apr 2023 07:12:33 +0000 (08:12 +0100)]
Merge branch 'ovs-selftests'
Aaron Conole says:
====================
selftests: openvswitch: add support for testing upcall interface
The existing selftest suite for openvswitch will work for regression
testing the datapath feature bits, but won't test things like adding
interfaces, or the upcall interface. Here, we add some additional
test facilities.
First, extend the ovs-dpctl.py python module to support the OVS_FLOW
and OVS_PACKET netlink families, with some associated messages. These
can be extended over time, but the initial support is for more well
known cases (output, userspace, and CT).
Next, extend the test suite to test upcalls by adding a datapath,
monitoring the upcall socket associated with the datapath, and then
dumping any upcalls that are received. Compare with expected ARP
upcall via arping.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a basic set of fields to print in a 'dpflow' format. This will be
used by future commits to check for flow fields after parsing, as
well as verifying the flow fields pushed into the kernel from
userspace.
Signed-off-by: Aaron Conole <aconole@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
If the 1PPS output was enabled and then lan8841 was configured to be a
follower, then target clock which is used to generate the 1PPS was not
configure correctly. The problem was that for each adjustments of the
time, also the nanosecond part of the target clock was changed.
Therefore the initial nanosecond part of the target clock was changed.
The issue can be observed if both the leader and the follower are
generating 1PPS and see that their PPS are not aligned even if the time
is allined.
The fix consists of not modifying the nanosecond part of the target
clock when adjusting the time. In this way the 1PPS get also aligned.
Fixes: e4ed8ba08e3f ("net: phy: micrel: Add support for PTP_PF_PEROUT for lan8841") Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com> Signed-off-by: David S. Miller <davem@davemloft.net>
====================
page_pool: allow caching from safely localized NAPI
I went back to the explicit "are we in NAPI method", mostly
because I don't like having both around :( (even tho I maintain
that in_softirq() && !in_hardirq() is as safe, as softirqs do
not nest).
Still returning the skbs to a CPU, tho, not to the NAPI instance.
I reckon we could create a small refcounted struct per NAPI instance
which would allow sockets and other users so hold a persisent
and safe reference. But that's a bigger change, and I get 90+%
recycling thru the cache with just these patches (for RR and
streaming tests with 100% CPU use it's almost 100%).
Some numbers for streaming test with 100% CPU use (from previous version,
but really they perform the same):
HW-GRO page=page
before after before after
recycle:
cached: 0 138669686 0 150197505
cache_full: 0 223391 0 74582
ring: 1385519339997191149299454 0
ring_full: 0 488 3154 127590
released_refcnt: 0 0 0 0
Jakub Kicinski [Thu, 13 Apr 2023 04:26:04 +0000 (21:26 -0700)]
page_pool: allow caching from safely localized NAPI
Recent patches to mlx5 mentioned a regression when moving from
driver local page pool to only using the generic page pool code.
Page pool has two recycling paths (1) direct one, which runs in
safe NAPI context (basically consumer context, so producing
can be lockless); and (2) via a ptr_ring, which takes a spin
lock because the freeing can happen from any CPU; producer
and consumer may run concurrently.
Since the page pool code was added, Eric introduced a revised version
of deferred skb freeing. TCP skbs are now usually returned to the CPU
which allocated them, and freed in softirq context. This places the
freeing (producing of pages back to the pool) enticingly close to
the allocation (consumer).
If we can prove that we're freeing in the same softirq context in which
the consumer NAPI will run - lockless use of the cache is perfectly fine,
no need for the lock.
Let drivers link the page pool to a NAPI instance. If the NAPI instance
is scheduled on the same CPU on which we're freeing - place the pages
in the direct cache.
With that and patched bnxt (XDP enabled to engage the page pool, sigh,
bnxt really needs page pool work :() I see a 2.6% perf boost with
a TCP stream test (app on a different physical core than softirq).
The CPU use of relevant functions decreases as expected:
Only consider lockless path to be safe when NAPI is scheduled
- in practice this should cover majority if not all of steady state
workloads. It's usually the NAPI kicking in that causes the skb flush.
The main case we'll miss out on is when application runs on the same
CPU as NAPI. In that case we don't use the deferred skb free path.
Jakub Kicinski [Thu, 13 Apr 2023 04:26:03 +0000 (21:26 -0700)]
net: skb: plumb napi state thru skb freeing paths
We maintain a NAPI-local cache of skbs which is fed by napi_consume_skb().
Going forward we will also try to cache head and data pages.
Plumb the "are we in a normal NAPI context" information thru
deeper into the freeing path, up to skb_release_data() and
skb_free_head()/skb_pp_recycle(). The "not normal NAPI context"
comes from netpoll which passes budget of 0 to try to reap
the Tx completions but not perform any Rx.
Use "bool napi_safe" rather than bare "int budget",
the further we get from NAPI the more confusing the budget
argument may seem (particularly whether 0 or MAX is the
correct value to pass in when not in NAPI).
net/mlx5: DR, Apply new accelerated modify action and decapl3
If there is support for pattern/args, use the new accelerated modify
header action for modify header and decap L3 actions.
Otherwise fall back to the old modify-header implementation.
net/mlx5: DR, Add modify header argument pointer to actions attributes
While building the actions, add the pointer of the arguments for
accelerated modify list action into the action's attributes.
This will be used later on while building the specific STE
for this action.
net/mlx5: DR, Add modify header arg pool mechanism
Added new mechanism for handling arguments for modify-header action.
The new action "accelerated modify-header" asks for the arguments from
separated area from the pattern, this area accessed via general objects.
Handling of these object is done via the pool-manager struct.
When the new header patterns are supported, while loading the domain,
a few pools for argument creations will be created. The requests for
allocating/deallocating arg objects are done via the pool manager API.
Signed-off-by: Muhammad Sammar <muhammads@nvidia.com> Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com> Reviewed-by: Alex Vesker <valex@nvidia.com> Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
When allocating a QP we allocate an RQ and an SQ, the RQ is stored first
in memory and followed by the SQ.
This allocation is not physically continiuos - it may span across different
physical pages. SW Steering code always writes in pairs: 1BB write + 1BB read,
or 2 continuous BBs of GTA WQE.
This lead to an issue where RQ allocation was 4x16 which is equal to 1 WQE BB,
causing 1 BB offset in the page and splitting the GTA WQE between different
physical pages.
The solution was to create the RQ with a even number of BBs and to have the
RQ aligned to a page.
net/mlx5: DR, Read ICM memory into dedicated buffer
Instead of using the write buffer for reading we will use a dedicated
buffer only for reading ICM memory.
Due to the new support for args, we can have a case with pending_wc
being odd number, and with reading into the same write buffer, it is
possible to overwrite next write on the same slot.
For example:
pending_wc is 17 so the buffer for write is:
| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
and we have requests as follows:
r wr wr wr wr wr wr wr wr
Now, the first read will be written into the last write because we use
the same buffer for read and write, before it was written to the HW and
we will have a wrong data in the ICM area.
net/mlx5: DR, Add support for writing modify header argument
The accelerated modify header arguments are written in the HW area
with special WQE and specific data format.
New function was added to support writing of new argument type.
Note that GTA WQE is larger than READ and WRITE, so the queue
management logic was updated to support this.
net/mlx5: DR, Split chunk allocation to HW-dependent ways
This way we are able to allocate chunk for modify_headers from 2 types:
STEv0 that is allocated from the action area, and STEv1 that is allocating
the chunks from the special area for patterns.
Signed-off-by: Muhammad Sammar <muhammads@nvidia.com> Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com> Reviewed-by: Alex Vesker <valex@nvidia.com> Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Starting with ConnectX-6 Dx, we use new design of modify_header FW object.
The current modify_header object allows for having only limited number
of FW objects, so the new design of pattern and argument allows pattern
reuse, saving memory, and having a large number of modify_header objects.
David S. Miller [Fri, 14 Apr 2023 10:09:27 +0000 (11:09 +0100)]
Merge branch 'msg_control-split'
Kevin Brodsky says:
====================
net: Finish up ->msg_control{,_user} split
Commit 1f466e1f15cf ("net: cleanly handle kernel vs user buffers for
->msg_control") introduced the msg_control_user and
msg_control_is_user fields in struct msghdr, to ensure that user
pointers are represented as such. It also took care of converting most
users of struct msghdr::msg_control where user pointers are involved. It
did however miss a number of cases, and some code using msg_control
inappropriately has also appeared in the meantime.
This series is attempting to complete the split, by eliminating the
remaining cases where msg_control is used when in fact a user
pointer is stored in the union (patch 1).
It also addresses a couple of issues with msg_control_is_user: one where
it is not updated as it should (patch 2), and one where it is not
initialised (patch 3).
v1..v2:
* Split out the msg_control_is_user fixes into separate patches.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Kevin Brodsky [Thu, 13 Apr 2023 11:47:05 +0000 (12:47 +0100)]
net/ipv6: Initialise msg_control_is_user
do_ipv6_setsockopt() makes use of struct msghdr::msg_control in the
IPV6_2292PKTOPTIONS case. Make sure to initialise
msg_control_is_user accordingly.
Cc: Christoph Hellwig <hch@lst.de> Cc: Eric Dumazet <edumazet@google.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: David S. Miller <davem@davemloft.net>
Kevin Brodsky [Thu, 13 Apr 2023 11:47:04 +0000 (12:47 +0100)]
net/compat: Update msg_control_is_user when setting a kernel pointer
cmsghdr_from_user_compat_to_kern() is an unusual case w.r.t. how
the kmsg->msg_control* fields are used. The input struct msghdr
holds a pointer to a user buffer, i.e. ksmg->msg_control_user is
active. However, upon success, a kernel pointer is stored in
kmsg->msg_control. kmsg->msg_control_is_user should therefore be
updated accordingly.
Cc: Christoph Hellwig <hch@lst.de> Cc: Eric Dumazet <edumazet@google.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: David S. Miller <davem@davemloft.net>
Kevin Brodsky [Thu, 13 Apr 2023 11:47:03 +0000 (12:47 +0100)]
net: Ensure ->msg_control_user is used for user buffers
Since commit 1f466e1f15cf ("net: cleanly handle kernel vs user
buffers for ->msg_control"), pointers to user buffers should be
stored in struct msghdr::msg_control_user, instead of the
msg_control field. Most users of msg_control have already been
converted (where user buffers are involved), but not all of them.
This patch attempts to address the remaining cases. An exception is
made for null checks, as it should be safe to use msg_control
unconditionally for that purpose.
Cc: Christoph Hellwig <hch@lst.de> Cc: Eric Dumazet <edumazet@google.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: David S. Miller <davem@davemloft.net>
vsock/loopback: don't disable irqs for queue access
This replaces 'skb_queue_tail()' with 'virtio_vsock_skb_queue_tail()'.
The first one uses 'spin_lock_irqsave()', second uses 'spin_lock_bh()'.
There is no need to disable interrupts in the loopback transport as
there is no access to the queue with skbs from interrupt context. Both
virtio and vhost transports work in the same way.
Signed-off-by: Arseniy Krasnov <AVKrasnov@sberdevices.ru> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
During probe, get the hardware-allowed max MTU by querying the device
configuration. Users can select MTU up to the device limit.
When XDP is in use, limit MTU settings so the buffer size is within
one page. And, when MTU is set to a too large value, XDP is not allowed
to run.
Also, to prevent changing MTU fails, and leaves the NIC in a bad state,
pre-allocate all buffers before starting the change. So in low memory
condition, it will return error, without affecting the NIC.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net: mana: Enable RX path to handle various MTU sizes
Update RX data path to allocate and use RX queue DMA buffers with
proper size based on potentially various MTU sizes.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net: mana: Refactor RX buffer allocation code to prepare for various MTU
Move out common buffer allocation code from mana_process_rx_cqe() and
mana_alloc_rx_wqe() to helper functions.
Refactor related variables so they can be changed in one place, and buffer
sizes are in sync.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Use napi_build_skb() instead of build_skb() to take advantage of the
NAPI percpu caches to obtain skbuff_head.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Fri, 14 Apr 2023 05:28:03 +0000 (22:28 -0700)]
Merge tag 'mlx5-updates-2023-04-11' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
mlx5-updates-2023-04-11
1) Vlad adds the support for linux bridge multicast offload support
Patches #1 through #9
Synopsis
Vlad Says:
==============
Implement support of bridge multicast offload in mlx5. Handle port object
attribute SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED notification to toggle multicast
offload and bridge snooping support on bridge. Handle port object
SWITCHDEV_OBJ_ID_PORT_MDB notification to attach a bridge port to MDB.
Steering architecture
Existing offload infrastructure relies on two levels of flow tables - bridge
ingress and egress. For multicast offload the architecture is extended with
additional layer of per-port multicast replication tables. Such tables filter
loopback traffic (so packets are not replicated to their source port) and pop
VLAN headers for "untagged" VLANs. The tables are referenced by the MDB rules in
egress table. MDB egress rule can point to multiple per-port multicast tables,
which causes matching multicast traffic to be replicated to all of them, and,
consecutively, to several bridge ports:
- Patch 1 adds hardware definition bits for capabilities required to replicate
multicast packets to multiple per-port tables. These bits are used by
following patches to only attempt multicast offload if firmware and hardware
provide necessary support.
- Pathces 2-4 patches are preparations and refactoring.
- Patch 5 implements necessary infrastructure to toggle multicast offload
via SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED port object attribute notification.
This also enabled IGMP and MLD snooping.
- Patch 6 implements per-port multicast replication tables. It only supports
filtering of loopback packets.
- Patch 7 extends per-port multicast tables with VLAN pop support for 'untagged'
VLANs.
- Patch 8 handles SWITCHDEV_OBJ_ID_PORT_MDB port object notifications. It
creates MDB replication rules in egress table that can replicate packets to
multiple per-port multicast tables.
- Patch 9 adds tracepoints for MDB events.
==============
2) Parav Create a new allocation profile for SFs, to save on memory
3) Yevgeny provides some initial patches for upcoming software steering
support new pattern/arguments type of modify_header actions.
Starting with ConnectX-6 DX, we use a new design of modify_header FW object.
The current modify_header object allows for having only limited number of
these FW objects, which means that we are limited in the number of offloaded
flows that require modify_header action.
As a preparation Yevgeny provides the following 4 patches:
- Patch 1: Add required mlx5_ifc HW bits
- Patch 2, 3: Add new WQE type and opcode that is required for pattern/arg
support and adds appropriate support in dr_send.c
- Patch 4: Add ICM pool for modify-header-pattern objects and implement
patterns cache, allowing patterns reuse for different flows
* tag 'mlx5-updates-2023-04-11' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
net/mlx5: DR, Add modify-header-pattern ICM pool
net/mlx5: DR, Prepare sending new WQE type
net/mlx5: Add new WQE for updating flow table
net/mlx5: Add mlx5_ifc bits for modify header argument
net/mlx5: DR, Set counter ID on the last STE for STEv1 TX
net/mlx5: Create a new profile for SFs
net/mlx5: Bridge, add tracepoints for multicast
net/mlx5: Bridge, implement mdb offload
net/mlx5: Bridge, support multicast VLAN pop
net/mlx5: Bridge, add per-port multicast replication tables
net/mlx5: Bridge, snoop igmp/mld packets
net/mlx5: Bridge, extract code to lookup parent bridge of port
net/mlx5: Bridge, move additional data structures to priv header
net/mlx5: Bridge, increase bridge tables sizes
net/mlx5: Add mlx5_ifc definitions for bridge multicast support
====================
====================
Add kernel tc-mqprio and tc-taprio support for preemptible traffic classes
The last RFC in August 2022 contained a proposal for the UAPI of both
TSN standards which together form Frame Preemption (802.1Q and 802.3):
https://lore.kernel.org/netdev/20220816222920.1952936-1-vladimir.oltean@nxp.com/
It wasn't clear at the time whether the 802.1Q portion of Frame Preemption
should be exposed via the tc qdisc (mqprio, taprio) or via some other
layer (perhaps also ethtool like the 802.3 portion, or dcbnl), even
though the options were discussed extensively, with pros and cons:
https://lore.kernel.org/netdev/20220816222920.1952936-3-vladimir.oltean@nxp.com/
So the 802.3 portion got submitted separately and finally was accepted:
https://lore.kernel.org/netdev/20230119122705.73054-1-vladimir.oltean@nxp.com/
leaving the only remaining question: how do we expose the 802.1Q bits?
This series proposes that we use the Qdisc layer, through separate
(albeit very similar) UAPI in mqprio and taprio, and that both these
Qdiscs pass the information down to the offloading device driver through
the common mqprio offload structure (which taprio also passes).
An implementation is provided for the NXP LS1028A on-board Ethernet
endpoint (enetc). Previous versions also contained support for its
embedded switch (felix), but this needs more work and will be submitted
separately.
projects / mirror_ubuntu-kernels.git / log