Before this patch, retransmitted SYN/ACK did not have a specific
synack_type; however, the upcoming patch needs to distinguish between
retransmitted and non-retransmitted SYN/ACK for AccECN negotiation to
transmit the fallback SYN/ACK during AccECN negotiation. Therefore, this
patch introduces a new synack_type (TCP_SYNACK_RETRANS).
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260131222515.8485-9-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Based on AccECN spec (RFC9768) Section 3.1.4.1, if the sender of an
AccECN SYN (the TCP Client) times out before receiving the SYN/ACK, it
SHOULD attempt to negotiate the use of AccECN at least one more time
by continuing to set all three TCP ECN flags (AE,CWR,ECE) = (1,1,1) on
the first retransmitted SYN (using the usual retransmission time-outs).
If this first retransmission also fails to be acknowledged, in
deployment scenarios where AccECN path traversal might be problematic,
the TCP Client SHOULD send subsequent retransmissions of the SYN with
the three TCP-ECN flags cleared (AE,CWR,ECE) = (0,0,0).
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260131222515.8485-8-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
According to Sections 3.1.2 and 3.1.3 of AccECN spec (RFC9768).
In Section 3.1.2, it says an AccECN implementation has no need to
recognize or support the Server response labelled 'Nonce' or ECN-nonce
feedback more generally, as RFC 3540 has been reclassified as Historic.
AccECN is compatible with alternative ECN feedback integrity approaches
to the nonce. The SYN/ACK labelled 'Nonce' with (AE,CWR,ECE) = (1,0,1)
is reserved for future use. A TCP Client (A) that receives such a SYN/ACK
follows the procedure for forward compatibility given in Section 3.1.3.
Then in Section 3.1.3, it says if a TCP Client has sent a SYN requesting
AccECN feedback with (AE,CWR,ECE) = (1,1,1) then receives a SYN/ACK with
the currently reserved combination (AE,CWR,ECE) = (1,0,1) but it does not
have logic specific to such a combination, the Client MUST enable AccECN
mode as if the SYN/ACK onfirmed that the Server supported AccECN and as
if it fed back that the IP-ECN field on the SYN had arrived unchanged.
Fixes: 3cae34274c ("tcp: accecn: AccECN negotiation").
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260131222515.8485-7-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
When AccECN is not successfully negociated for a TCP flow, it defaults
fallback to classic ECN (RFC3168). However, L4S service will fallback
to non-ECN.
This patch enables congestion control module to control whether it
should not fallback to classic ECN after unsuccessful AccECN negotiation.
A new CA module flag (TCP_CONG_NO_FALLBACK_RFC3168) identifies this
behavior expected by the CA.
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260131222515.8485-6-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Two flags for congestion control (CC) module are added in this patch
related to AccECN negotiation. First, a new flag (TCP_CONG_NEEDS_ACCECN)
defines that the CC expects to negotiate AccECN functionality using the
ECE, CWR and AE flags in the TCP header.
Second, during ECN negotiation, ECT(0) in the IP header is used. This
patch enables CC to control whether ECT(0) or ECT(1) should be used on
a per-segment basis. A new flag (TCP_CONG_ECT_1_NEGOTIATION) defines the
expected ECT value in the IP header by the CA when not-yet initialized
for the connection.
The detailed AccECN negotiaotn can be found in IETF RFC9768.
Co-developed-by: Olivier Tilmans <olivier.tilmans@nokia.com>
Signed-off-by: Olivier Tilmans <olivier.tilmans@nokia.com>
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260131222515.8485-5-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Currently, GRO does not flush packets when the CWR bit is set.
A corresponding self-test is being added, in which the CWR flag
is set for two consecutive packets, but the first packet with the
CWR flag set will not be flushed immediately.
+===================+==========+===============+===========+
| Packet id | CWR flag | Payload | Flushing? |
+===================+==========+===============+===========+
| 0 | 0 | PAYLOAD_LEN | 0 |
| ... | 0 | PAYLOAD_LEN | 1 |
+-------------------+----------+---------------+-----------+
| NUM_PACKETS/2 - 1 | 1 | payload_len | 0 |
| NUM_PACKETS/2 | 1 | payload_len | 1 |
+-------------------+----------+---------------+-----------+
| ... | 0 | PAYLOAD_LEN | 0 |
| NUM_PACKETS | 0 | PAYLOAD_LEN | 1 |
+===================+==========+===============+===========+
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260131222515.8485-4-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
As AccECN may keep CWR bit asserted due to different
interpretation of the bit, flushing with GRO because of
CWR may effectively disable GRO until AccECN counter
field changes such that CWR-bit becomes 0.
There is no harm done from not immediately forwarding the
CWR'ed segment with RFC3168 ECN.
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260131222515.8485-3-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Add newly acked pkts EWMA. When ACK thinning occurs, select
between safer and unsafe cep delta in AccECN processing based
on it. If the packets ACKed per ACK tends to be large, don't
conservatively assume ACE field overflow.
This patch uses the existing 2-byte holes in the rx group for new
u16 variables withtout creating more holes. Below are the pahole
outcomes before and after this patch:
[BEFORE THIS PATCH]
struct tcp_sock {
[...]
u32 delivered_ecn_bytes[3]; /* 2744 12 */
/* XXX 4 bytes hole, try to pack */
[...]
__cacheline_group_end__tcp_sock_write_rx[0]; /* 2816 0 */
[...]
/* size: 3264, cachelines: 51, members: 177 */
}
[AFTER THIS PATCH]
struct tcp_sock {
[...]
u32 delivered_ecn_bytes[3]; /* 2744 12 */
u16 pkts_acked_ewma; /* 2756 2 */
/* XXX 2 bytes hole, try to pack */
[...]
__cacheline_group_end__tcp_sock_write_rx[0]; /* 2816 0 */
[...]
/* size: 3264, cachelines: 51, members: 178 */
}
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Co-developed-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260131222515.8485-2-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Set up global DSCP/PCP priority mappings and add related DCB methods.
Signed-off-by: David Yang <mmyangfl@gmail.com>
Link: https://patch.msgid.link/20260131021854.3405036-6-mmyangfl@gmail.com
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
yt921x_chip_setup() is already pretty long, and is going to become
longer. Split it into parts.
Signed-off-by: David Yang <mmyangfl@gmail.com>
Link: https://patch.msgid.link/20260131021854.3405036-5-mmyangfl@gmail.com
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Create a helper function to centralize the logic for enabling and
disabling VLAN awareness on a port.
Signed-off-by: David Yang <mmyangfl@gmail.com>
Link: https://patch.msgid.link/20260131021854.3405036-4-mmyangfl@gmail.com
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Required by DCB/QoS support of the switch driver, since the rx packets
will have non-zero priorities.
Signed-off-by: David Yang <mmyangfl@gmail.com>
Link: https://patch.msgid.link/20260131021854.3405036-3-mmyangfl@gmail.com
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Packet priority is part of the tag, and the priority and code fields are
used by tx and rx. Make revisions to reflect the facts.
Signed-off-by: David Yang <mmyangfl@gmail.com>
Link: https://patch.msgid.link/20260131021854.3405036-2-mmyangfl@gmail.com
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Heiner Kallweit says:
====================
net: phy: remove modalias-based MDIO device bus matching
modalias-based MDIO device bus matching has only one user (dsa-loop),
where we can replace modalias-based matching with a simple custom
match function. This, and first patch of the series, lay the foundation
for removing modalias-based matching.
====================
Link: https://patch.msgid.link/d9543e7d-23e1-4dba-a6b3-35dcd6a35dec@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Last user dsa_loop has been migrated away from modalias-based matching,
so we can remove this feature now. It was the only user of MDIO_NAME_SIZE,
so remove also this constant.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/ce1c6df0-4785-4b28-8322-32dc6bceea18@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
This change is a prerequisite for removing the MDIO device modalias,
as dsa_loop is the only user. Switch from modalias to a custom
bus match function.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Tested-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/15a4318f-50b5-4df5-874e-e387ee070a9d@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Primary reason for this change is to remove the misuse of MDIO_NAME_SIZE
here, so that this constant can be removed in a follow-up patch.
Use case here is simply a chip name w/o any relationship to a MDIO
device. Also there's no need to reserve a longer char array, so make
the name a pointer.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/61bc14fa-eed3-43b6-ae40-b98063e81578@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tariq Toukan says:
====================
devlink and mlx5: Support cross-function rate scheduling [part]
Apply trivial cleanups from the series to make it smaller.
====================
Link: https://patch.msgid.link/20260128112544.1661250-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
devlink_rate_nodes_check() was used to verify there are no devlink rate
nodes created when switching the esw mode.
Rate management code is about to become more complex, so refactor this
function:
- remove unused param 'mode'.
- add a new 'rate_filter' param.
- rename to devlink_rates_check().
- expose devlink_rate_is_node() to be used as a rate filter.
This makes it more usable from multiple places, so use it from those
places as well.
Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260128112544.1661250-6-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commit [1] defined the locking expectations for nested devlink
instances: the nested-in devlink instance lock needs to be acquired
before the nested devlink instance lock. The code handling devlink rels
was architected with that assumption in mind.
There are no actual users of double locking yet but that is about to
change in the upcoming patches in the series.
Code operating on nested devlink instances will require also obtaining
the nested-in instance lock, but such code may already be called from a
variety of places with the nested devlink instance lock. Then, there's
no way to acquire the nested-in lock other than making sure that all
callers acquire it first.
Reversing the nested lock order allows incrementally acquiring the
nested-in instance lock when needed (perhaps even a chain of locks up to
the root) without affecting any caller.
The only affected use of nesting is devlink_nl_nested_fill(), which
iterates over nested devlink instances with the RCU lock, without
locking them, so there's no possibility of deadlock.
So this commit just updates a comment regarding the nested locks.
[1] commit c137743bce ("devlink: introduce object and nested devlink
relationship infra")
Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260128112544.1661250-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Russell King says:
====================
net: stmmac: pcs preparation
These three patches prepare for the PCS changes, which, subject
to Qualcomm testing, should be coming in the next cycle.
====================
Link: https://patch.msgid.link/aXyRlFw7ZuhRPiKo@shell.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The dwmac core has no support for SGMII without using its integrated
PCS. Thus, PHY_INTF_SEL_SGMII is only supported when this block is
present, and it makes no sense for stmmac_get_phy_intf_sel() to decode
this.
None of the platform glue users that use stmmac_get_phy_intf_sel()
directly accept PHY_INTF_SEL_SGMII as a valid mode.
Check whether a PCS will be used by the driver for the interface mode,
and if it is the integrated PCS, query the integrated PCS for the
phy_intf_sel_i value to use.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Tested-by: Mohd Ayaan Anwar <mohd.anwar@oss.qualcomm.com>
Link: https://patch.msgid.link/E1vlmOa-00000006zvB-1fIe@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Move most of the PCS register offset definitions to stmmac_pcs.c.
Since stmmac_pcs.c only ever passes zero into the register offset
macros, remove that ability, making them simple constant integer
definitions.
Add appropriate descriptions of the registers, pointing out their
similarity with their IEEE 802.3 counterparts. Make use of the
BMSR definitions for the GMAC_AN_STATUS register and remove the
driver private versions.
Note that BMSR_LSTATUS is non-low-latching, unlike it's 802.3z
counterpart.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Tested-by: Mohd Ayaan Anwar <mohd.anwar@oss.qualcomm.com>
Link: https://patch.msgid.link/E1vlmOV-00000006zv5-1CwO@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Where a core supports hardware features, but does not indicate support
for half-duplex, clear phylink's half-duplex 1G, 100M and 10M
capability bits to disallow half-duplex operation and advertisement of
these link modes.
This will avoid the need for special code in the PCS driver to do this
based on the ESTATUS register bits, as the support in the PCS is
dependent on the same synthesis choice as the MAC core.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Tested-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Tested-by: Mohd Ayaan Anwar <mohd.anwar@oss.qualcomm.com>
Link: https://patch.msgid.link/E1vlmOQ-00000006zuz-0ffN@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Biju Das says:
====================
Add support for Renesas RZ/G3L GBETH
From: Biju Das <biju.das.jz@bp.renesas.com>
The Renesas RZ/G3L GBETH IP uses Synopsys DesignWare MAC version 5.30
compared to other Renesas SoC such as RZ/V2H that use MAC version 5.20.
The RZ/G3L GBETH requires an extra clock compared to RZ/G3E and has pps
interrupts. Document the Renesas RZ/G3L GBETH IP in bindings and add
support for the RZ/G3L GBETH in dwmac-renesas-gbeth glue driver.
====================
Link: https://patch.msgid.link/20260131161250.5047-1-biju.das.jz@bp.renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Compared to other Renesas GBETH stmmac glue drivers, RZ/G3L GBETH IP use
the version Synopsys DesignWare MAC (version 5.30). It has an extra clock
compared to RZ/V2H and has ptp_pps_o interrupts. Add support for RZ/G3L
GBETH by reusing device data of RZ/V2H and can be extended to add other
functionalities later.
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://patch.msgid.link/20260131161250.5047-3-biju.das.jz@bp.renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add device tree binding support for the Gigabit Ethernet (GBETH) IP on
Renesas RZ/G3L SoC. This SoC uses different Synopsys DesignWare MAC
version 5.30 compared to RZ/G3E.
RZ/G3L requires an extra clock compared to RZ/G3E and has pps interrupts.
Add a new compatible string "renesas,r9a08g046-gbeth" for RZ/G3L SoC and
update the schema to handle hardware differences between SoC variants.
Extend the base snps,dwmac.yaml schema to accommodate the PPS interrupts.
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://patch.msgid.link/20260131161250.5047-2-biju.das.jz@bp.renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Matthieu Baerts says:
====================
mptcp: implement .read_sock and .splice_read
This series is a preparation work for future in-kernel MPTCP sockets
usage. Here, two interfaces are implemented: read_sock and splice_read.
As a result of this series, splice() with MPTCP sockets -- which was
already supported -- is now improved.
- Patches 1-2: .read_sock implementation
- Patches 3-4: .splice_read implementation
- Patches 5-6: validate splice() support with MPTCP sockets.
====================
Link: https://patch.msgid.link/20260130-net-next-mptcp-splice-v2-0-31332ba70d7f@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The "splice" alternate mode for mptcp_connect.sh/.c is available now,
this patch adds mptcp_connect_splice.sh to test it in the MPTCP CI by
default.
Note that this mode is also supported by stable kernel versions, but
optimised in this patch series.
Suggested-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260130-net-next-mptcp-splice-v2-6-31332ba70d7f@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This patch adds a new 'splice' io mode for mptcp_connect to test
the newly added read_sock() and splice_read() functions of MPTCP.
do_splice() efficiently transfers data directly between two file
descriptors (infd and outfd) without copying to userspace, using
Linux's splice() system call.
Usage:
./mptcp_connect.sh -m splice
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Co-developed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260130-net-next-mptcp-splice-v2-5-31332ba70d7f@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This patch implements .splice_read interface of mptcp struct proto_ops
as mptcp_splice_read() with reference to tcp_splice_read().
Corresponding to __tcp_splice_read(), __mptcp_splice_read() is defined,
invoking mptcp_read_sock() instead of tcp_read_sock().
mptcp_splice_read() is almost the same as tcp_splice_read(), except for
sock_rps_record_flow().
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260130-net-next-mptcp-splice-v2-4-31332ba70d7f@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Export struct tcp_splice_state and tcp_splice_data_recv() in net/tcp.h
so that they can be used by MPTCP in the next patch.
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Acked-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260130-net-next-mptcp-splice-v2-3-31332ba70d7f@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Current in-kernel TCP sockets -- i.e. from nvme_tcp_try_recv() -- need
to call .read_sock interface of struct proto_ops, but it's not
implemented in MPTCP.
This patch implements it with reference to __tcp_read_sock() and
__mptcp_recvmsg_mskq().
Corresponding to tcp_recv_skb(), a new helper for MPTCP named
mptcp_recv_skb() is added to peek a skb from sk->sk_receive_queue.
Compared with __mptcp_recvmsg_mskq(), mptcp_read_sock() uses
sk->sk_rcvbuf as the max read length. The LISTEN status is checked
before the while loop, and mptcp_recv_skb() and mptcp_cleanup_rbuf()
are invoked after the loop. In the loop, all flags checks for
__mptcp_recvmsg_mskq() are removed.
Reviewed-by: Hannes Reinecke <hare@kernel.org>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260130-net-next-mptcp-splice-v2-2-31332ba70d7f@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This patch extracts the free skb related code in __mptcp_recvmsg_mskq()
into a new helper mptcp_eat_recv_skb().
This new helper will be used in the next patch.
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260130-net-next-mptcp-splice-v2-1-31332ba70d7f@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Takahiro Itazuri says:
====================
ptp: vmclock: Add VM generation counter and ACPI notification
Similarly to live migration, starting a VM from some serialized state
(aka snapshot) is an event which calls for adjusting guest clocks, hence
a hypervisor should increase the disruption_marker before resuming the
VM vCPUs, letting the guest know.
However, loading a snapshot, is slightly different than live migration,
especially since we can start multiple VMs from the same serialized
state. Apart from adjusting clocks, the guest needs to take additional
action during such events, e.g. recreate UUIDs, reset network
adapters/connections, reseed entropy pools, etc. These actions are not
necessary during live migration. This calls for a differentiation
between the two triggering events.
We differentiate between the two events via an extra field in the
vmclock_abi, called vm_generation_counter. Whereas hypervisors should
increase the disruption marker in both cases, they should only increase
vm_generation_counter when a snapshot is loaded in a VM (not during live
migration).
Additionally, we attach an ACPI notification to VMClock. Implementing
the notification is optional for the device. VMClock device will declare
that it implements the notification by setting
VMCLOCK_FLAG_NOTIFICATION_PRESENT bit in vmclock_abi flags. Hypervisors
that implement the notification must send an ACPI notification every
time seq_count changes to an even number. The driver will propagate
these notifications to userspace via the poll() interface.
====================
Link: https://patch.msgid.link/20260130173704.12575-1-itazur@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
To output UTC would involve complex calculations about whether the time
elapsed since the reference time has crossed the end of the month when
a leap second takes effect. I've prototyped that, but it made me sad.
Much better to report TAI, which is what PHCs should do anyway.
And much much simpler.
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Babis Chalios <bchalios@amazon.es>
Tested-by: Takahiro Itazuri <itazur@amazon.com>
Link: https://patch.msgid.link/20260130173704.12575-8-itazur@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Now that we added device tree support we can remove dependency on
CONFIG_ACPI.
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Babis Chalios <bchalios@amazon.es>
Tested-by: Takahiro Itazuri <itazur@amazon.dom>
Link: https://patch.msgid.link/20260130173704.12575-7-itazur@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
As we finalised the spec, we spotted that vmgenid actually says that the
_HID is supposed to be hypervisor-specific. Although in the 13 years
since the original vmgenid doc was published, nobody seems to have cared
about using _HID to distinguish between implementations on different
hypervisors, and we only ever use the _CID.
For consistency, match the _CID of "VMCLOCK" too.
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Babis Chalios <bchalios@amazon.es>
Tested-by: Takahiro Itazuri <itazur@amazon.com>
Link: https://patch.msgid.link/20260130173704.12575-6-itazur@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add device tree support to the ptp_vmclock driver, allowing it to probe
via device tree in addition to ACPI.
Handle optional interrupt for clock disruption notifications, mirroring
the ACPI notification behaviour.
Although the interrupt is marked as 'optional' in the DT bindings, if
the device *advertises* the VMCLOCK_FLAG_NOTIFICATION_ABSENT then it
*should* have an interrupt. The driver will refuse to initialize if not.
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Babis Chalios <bchalios@amazon.es>
Signed-off-by: Takahiro Itazuri <itazur@amazon.com>
Tested-by: Takahiro Itazuri <itazur@amazon.com>
Link: https://patch.msgid.link/20260130173704.12575-5-itazur@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The vmclock device provides a PTP clock source and precise timekeeping
across live migration and snapshot/restore operations.
The binding has a required memory region containing the vmclock_abi
structure and an optional interrupt for clock disruption notifications.
The full spec is at https://uapi-group.org/specifications/specs/vmclock/
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Babis Chalios <bchalios@amazon.es>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Tested-by: Takahiro Itazuri <itazur@amazon.com>
Link: https://patch.msgid.link/20260130173704.12575-4-itazur@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add optional support for device notifications in VMClock. When
supported, the hypervisor will send a device notification every time it
updates the seq_count to a new even value.
Moreover, add support for poll() in VMClock as a means to propagate this
notification to user space. poll() will return a POLLIN event to
listeners every time seq_count changes to a value different than the one
last seen (since open() or last read()/pread()). This means that when
poll() returns a POLLIN event, listeners need to use read() to observe
what has changed and update the reader's view of seq_count. In other
words, after a poll() returned, all subsequent calls to poll() will
immediately return with a POLLIN event until the listener calls read().
The device advertises support for the notification mechanism by setting
flag VMCLOCK_FLAG_NOTIFICATION_PRESENT in vmclock_abi flags field. If
the flag is not present the driver won't setup the ACPI notification
handler and poll() will always immediately return POLLHUP.
Signed-off-by: Babis Chalios <bchalios@amazon.es>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Takahiro Itazuri <itazur@amazon.com>
Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>
Tested-by: Takahiro Itazuri <itazur@amazon.com>
Link: https://patch.msgid.link/20260130173704.12575-3-itazur@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Similar to live migration, loading a VM from some saved state (aka
snapshot) is also an event that calls for clock adjustments in the
guest. However, guests might want to take more actions as a response to
such events, e.g. as discarding UUIDs, resetting network connections,
reseeding entropy pools, etc. These are actions that guests don't
typically take during live migration, so add a new field in the
vmclock_abi called vm_generation_counter which informs the guest about
such events.
Hypervisor advertises support for vm_generation_counter through the
VMCLOCK_FLAG_VM_GEN_COUNTER_PRESENT flag. Users need to check the
presence of this bit in vmclock_abi flags field before using this flag.
Signed-off-by: Babis Chalios <bchalios@amazon.es>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>
Tested-by: Takahiro Itazur <itazur@amazon.com>
Link: https://patch.msgid.link/20260130173704.12575-2-itazur@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
All inet6_cork users also use one inet_cork_full.
Reduce number of parameters and increase data locality.
This saves ~275 bytes of code on x86_64.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260130210303.3888261-9-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When we expect an IPv4 dst, use dst4_mtu() instead of dst_mtu()
to save some code space.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260130210303.3888261-8-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When we expect an IPv6 dst, use dst6_mtu() instead of dst_mtu()
to save some code space.
Due to current dst6_mtu() implementation, only convert
users in IPv6 stack.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260130210303.3888261-7-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
With CONFIG_MITIGATION_RETPOLINE=y dst_mtu() is a bit fat,
because it is generic.
Indeed, clang does not always inline it.
Add dst4_mtu() and dst6_mtu() helpers for callers that
expect either ipv4_mtu() or ip6_mtu() to be called.
These helpers are always inlined.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260130210303.3888261-6-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When a too big packet is dropped, use SKB_DROP_REASON_PKT_TOO_BIG.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260130210303.3888261-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
ip6_xmit() makes sure there is enough headroom in the skb,
it can uses __skb_push() instead of the out-of-line skb_push().
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260130210303.3888261-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
