Previously, sctp over udp was using udp tunnel's icmp err process, which
only does sk lookup on sctp side. However for sctp's icmp error process,
there are more things to do, like syncing assoc pmtu/retransmit packets
for toobig type err, and starting proto_unreach_timer for unreach type
err etc.
Now after adding PLPMTUD, which also requires to process toobig type err
on sctp side. This patch is to process icmp err on sctp side by parsing
the type/code/info in .encap_err_lookup and call sctp's icmp processing
functions. Note as the 'redirect' err process needs to know the outer
ip(v6) header's, we have to leave it to udp(v6)_err to handle it.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As described in rfc8899#section-5.2, when a probe succeeds, there might
be the following state transitions:
- Base -> Search, occurs when probe succeeds with BASE_PLPMTU,
pl.pmtu is not changing,
pl.probe_size increases by SCTP_PL_BIG_STEP,
- Error -> Search, occurs when probe succeeds with BASE_PLPMTU,
pl.pmtu is changed from SCTP_MIN_PLPMTU to SCTP_BASE_PLPMTU,
pl.probe_size increases by SCTP_PL_BIG_STEP.
- Search -> Search Complete, occurs when probe succeeds with the probe
size SCTP_MAX_PLPMTU less than pl.probe_high,
pl.pmtu is not changing, but update *pathmtu* with it,
pl.probe_size is set back to pl.pmtu to double check it.
- Search Complete -> Search, occurs when probe succeeds with the probe
size equal to pl.pmtu,
pl.pmtu is not changing,
pl.probe_size increases by SCTP_PL_MIN_STEP.
So search process can be described as:
1. When it just enters 'Search' state, *pathmtu* is not updated with
pl.pmtu, and probe_size increases by a big step (SCTP_PL_BIG_STEP)
each round.
2. Until pl.probe_high is set when a probe fails, and probe_size
decreases back to pl.pmtu, as described in the last patch.
3. When the probe with the new size succeeds, probe_size changes to
increase by a small step (SCTP_PL_MIN_STEP) due to pl.probe_high
is set.
4. Until probe_size is next to pl.probe_high, the searching finishes and
it goes to 'Complete' state and updates *pathmtu* with pl.pmtu, and
then probe_size is set to pl.pmtu to confirm by once more probe.
5. This probe occurs after "30 * probe_inteval", a much longer time than
that in Search state. Once it is done it goes to 'Search' state again
with probe_size increased by SCTP_PL_MIN_STEP.
As we can see above, during the searching, pl.pmtu changes while *pathmtu*
doesn't. *pathmtu* is only updated when the search finishes by which it
gets an optimal value for it. A big step is used at the beginning until
it gets close to the optimal value, then it changes to a small step until
it has this optimal value.
The small step is also used in 'Complete' until it goes to 'Search' state
again and the probe with 'pmtu + the small step' succeeds, which means a
higher size could be used. Then probe_size changes to increase by a big
step again until it gets close to the next optimal value.
Note that anytime when black hole is detected, it goes directly to 'Base'
state with pl.pmtu set to SCTP_BASE_PLPMTU, as described in the last patch.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The state transition is described in rfc8899#section-5.2,
PROBE_COUNT == MAX_PROBES means the probe fails for MAX times, and the
state transition includes:
- Base -> Error, occurs when BASE_PLPMTU Confirmation Fails,
pl.pmtu is set to SCTP_MIN_PLPMTU,
probe_size is still SCTP_BASE_PLPMTU;
- Search -> Base, occurs when Black Hole Detected,
pl.pmtu is set to SCTP_BASE_PLPMTU,
probe_size is set back to SCTP_BASE_PLPMTU;
- Search Complete -> Base, occurs when Black Hole Detected
pl.pmtu is set to SCTP_BASE_PLPMTU,
probe_size is set back to SCTP_BASE_PLPMTU;
Note a black hole is encountered when a sender is unaware that packets
are not being delivered to the destination endpoint. So it includes the
probe failures with equal probe_size to pl.pmtu, and definitely not
include that with greater probe_size than pl.pmtu. The later one is the
normal probe failure where probe_size should decrease back to pl.pmtu
and pl.probe_high is set. pl.probe_high would be used on HB ACK recv
path in the next patch.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch does exactly what rfc8899#section-6.2.1.2 says:
The SCTP sender needs to be able to determine the total size of a
probe packet. The HEARTBEAT chunk could carry a Heartbeat
Information parameter that includes, besides the information
suggested in [RFC4960], the probe size to help an implementation
associate a HEARTBEAT ACK with the size of probe that was sent. The
sender could also use other methods, such as sending a nonce and
verifying the information returned also contains the corresponding
nonce. The length of the PAD chunk is computed by reducing the
probing size by the size of the SCTP common header and the HEARTBEAT
chunk.
Note that HB ACK chunk will carry back whatever HB chunk carried, including
the probe_size we put it in; We also check hbinfo->probe_size in the HB ACK
against link->pl.probe_size to validate this HB ACK chunk.
v1->v2:
- Remove the unused 'sp' and add static for sctp_packet_bundle_pad().
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are 3 timers described in rfc8899#section-5.1.1:
PROBE_TIMER, PMTU_RAISE_TIMER, CONFIRMATION_TIMER
This patches adds a 'probe_timer' in transport, and it works as either
PROBE_TIMER or PMTU_RAISE_TIMER. At most time, it works as PROBE_TIMER
and expires every a 'probe_interval' time to send the HB probe packet.
When transport pl enters COMPLETE state, it works as PMTU_RAISE_TIMER
and expires in 'probe_interval * 30' time to go back to SEARCH state
and do searching again.
SCTP HB is an acknowledged packet, CONFIRMATION_TIMER is not needed.
The timer will start when transport pl enters BASE state and stop
when it enters DISABLED state.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
These are 4 constants described in rfc8899#section-5.1.2:
MAX_PROBES, MIN_PLPMTU, MAX_PLPMTU, BASE_PLPMTU;
And 2 variables described in rfc8899#section-5.1.3:
PROBED_SIZE, PROBE_COUNT;
And 5 states described in rfc8899#section-5.2:
DISABLED, BASE, SEARCH, SEARCH_COMPLETE, ERROR;
And these 4 APIs are used to reset/update PLPMTUD, check if PLPMTUD is
enabled, and calculate the additional headers length for a transport.
Note the member 'probe_high' in transport will be set to the probe
size when a probe fails with this probe size in the next patches.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With this socket option, users can change probe_interval for
a transport, asoc or sock after it's created.
Note that if the change is for an asoc, also apply the change
to each transport in this asoc.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
PLPMTUD can be enabled by doing 'sysctl -w net.sctp.probe_interval=n'.
'n' is the interval for PLPMTUD probe timer in milliseconds, and it
can't be less than 5000 if it's not 0.
All asoc/transport's PLPMTUD in a new socket will be enabled by default.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This chunk is defined in rfc4820#section-3, and used to pad an
SCTP packet. The receiver must discard this chunk and continue
processing the rest of the chunks in the packet.
Add it now, as it will be bundled with a heartbeat chunk to probe
pmtu in the following patches.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The struct is not visible to user space and therefore should not use the
user visible data types.
Instead, use internal data types like other structures in the file.
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
'ETHTOOL_A_MODULE_EEPROM_DATA' is a binary attribute, not a nested one.
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The WWAN core not only multiplex the netdev configuration data, but
process it too, and needs some space to store its private data
associated with the netdev. Add a structure to keep common WWAN core
data. The structure will be stored inside the netdev private data before
WWAN driver private data and have a field to make it easier to access
the driver data. Also add a helper function that simplifies drivers
access to their data.
At the moment we use the common WWAN private data to store the WWAN data
link (channel) id at the time the link is created, and report it back to
user using the .fill_info() RTNL callback. This should help the user to
be aware which network interface is bound to which WWAN device data
channel.
Signed-off-by: Sergey Ryazanov <ryazanov.s.a@gmail.com>
CC: M Chetan Kumar <m.chetan.kumar@intel.com>
CC: Intel Corporation <linuxwwan@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Most, if not each WWAN device driver will create a netdev for the
default data channel. Therefore, add an option for the WWAN netdev ops
registration function to create a default netdev for the WWAN device.
A WWAN device driver should pass a default data channel link id to the
ops registering function to request the creation of a default netdev, or
a special value WWAN_NO_DEFAULT_LINK to inform the WWAN core that the
default netdev should not be created.
For now, only wwan_hwsim utilize the default link creation option. Other
drivers will be reworked next.
Signed-off-by: Sergey Ryazanov <ryazanov.s.a@gmail.com>
CC: M Chetan Kumar <m.chetan.kumar@intel.com>
CC: Intel Corporation <linuxwwan@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The WWAN netdev ops owner holding was used to protect from the
unexpected memory disappear. This approach causes a dependency cycle
(driver -> core -> driver) and effectively prevents a WWAN driver
unloading. E.g. WWAN hwsim could not be unloaded until all simulated
devices are removed:
~# modprobe wwan_hwsim devices=2
~# lsmod | grep wwan
wwan_hwsim 16384 2
wwan 20480 1 wwan_hwsim
~# rmmod wwan_hwsim
rmmod: ERROR: Module wwan_hwsim is in use
~# echo > /sys/kernel/debug/wwan_hwsim/hwsim0/destroy
~# echo > /sys/kernel/debug/wwan_hwsim/hwsim1/destroy
~# lsmod | grep wwan
wwan_hwsim 16384 0
wwan 20480 1 wwan_hwsim
~# rmmod wwan_hwsim
For a real device driver this will cause an inability to unload module
until a served device is physically detached.
Since the last commit we are removing all child netdev(s) when a driver
unregister the netdev ops. This allows us to permit the driver
unloading, since any sane driver will call ops unregistering on a device
deinitialization. So, remove the holding of an ops owner to make it
easier to unload a driver module. The owner field has also beed removed
from the ops structure as there are no more users of this field.
Signed-off-by: Sergey Ryazanov <ryazanov.s.a@gmail.com>
Reviewed-by: Loic Poulain <loic.poulain@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch introduces a new helper function that
wraps acpi_/of_ mdiobus_register() and allows its
usage via common fwnode_ interface.
Fall back to raw mdiobus_register() in case CONFIG_FWNODE_MDIO
is not enabled, in order to satisfy compatibility
in all future user drivers.
Signed-off-by: Marcin Wojtas <mw@semihalf.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Similar to commit 3b707c3008 ("net: dev_is_mac_header_xmit() true for
ARPHRD_RAWIP"), add ARPHRD_IP6GRE to dev_is_mac_header_xmit(), to make
ip6gre compatible with act_mirred and __bpf_redirect().
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The difference between dsa_is_user_port and dsa_port_is_user is that the
former needs to look up the list of ports of the DSA switch tree in
order to find the struct dsa_port, while the latter directly receives it
as an argument.
dsa_is_user_port is already in widespread use and has its place, so
there isn't any chance of converting all callers to a single form.
But being able to do:
dsa_port_is_user(dp)
instead of
dsa_is_user_port(dp->ds, dp->index)
is much more efficient too, especially when the "dp" comes from an
iterator over the DSA switch tree - this reduces the complexity from
quadratic to linear.
Move these helpers from dsa2.c to include/net/dsa.h so that others can
use them too.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Trivial conflicts in net/can/isotp.c and
tools/testing/selftests/net/mptcp/mptcp_connect.sh
scaled_ppm_to_ppb() was moved from drivers/ptp/ptp_clock.c
to include/linux/ptp_clock_kernel.h in -next so re-apply
the fix there.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Pull networking fixes from Jakub Kicinski:
"Networking fixes for 5.13-rc7, including fixes from wireless, bpf,
bluetooth, netfilter and can.
Current release - regressions:
- mlxsw: spectrum_qdisc: Pass handle, not band number to find_class()
to fix modifying offloaded qdiscs
- lantiq: net: fix duplicated skb in rx descriptor ring
- rtnetlink: fix regression in bridge VLAN configuration, empty info
is not an error, bot-generated "fix" was not needed
- libbpf: s/rx/tx/ typo on umem->rx_ring_setup_done to fix umem
creation
Current release - new code bugs:
- ethtool: fix NULL pointer dereference during module EEPROM dump via
the new netlink API
- mlx5e: don't update netdev RQs with PTP-RQ, the special purpose
queue should not be visible to the stack
- mlx5e: select special PTP queue only for SKBTX_HW_TSTAMP skbs
- mlx5e: verify dev is present in get devlink port ndo, avoid a panic
Previous releases - regressions:
- neighbour: allow NUD_NOARP entries to be force GCed
- further fixes for fallout from reorg of WiFi locking (staging:
rtl8723bs, mac80211, cfg80211)
- skbuff: fix incorrect msg_zerocopy copy notifications
- mac80211: fix NULL ptr deref for injected rate info
- Revert "net/mlx5: Arm only EQs with EQEs" it may cause missed IRQs
Previous releases - always broken:
- bpf: more speculative execution fixes
- netfilter: nft_fib_ipv6: skip ipv6 packets from any to link-local
- udp: fix race between close() and udp_abort() resulting in a panic
- fix out of bounds when parsing TCP options before packets are
validated (in netfilter: synproxy, tc: sch_cake and mptcp)
- mptcp: improve operation under memory pressure, add missing
wake-ups
- mptcp: fix double-lock/soft lookup in subflow_error_report()
- bridge: fix races (null pointer deref and UAF) in vlan tunnel
egress
- ena: fix DMA mapping function issues in XDP
- rds: fix memory leak in rds_recvmsg
Misc:
- vrf: allow larger MTUs
- icmp: don't send out ICMP messages with a source address of 0.0.0.0
- cdc_ncm: switch to eth%d interface naming"
* tag 'net-5.13-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (139 commits)
net: ethernet: fix potential use-after-free in ec_bhf_remove
selftests/net: Add icmp.sh for testing ICMP dummy address responses
icmp: don't send out ICMP messages with a source address of 0.0.0.0
net: ll_temac: Avoid ndo_start_xmit returning NETDEV_TX_BUSY
net: ll_temac: Fix TX BD buffer overwrite
net: ll_temac: Add memory-barriers for TX BD access
net: ll_temac: Make sure to free skb when it is completely used
MAINTAINERS: add Guvenc as SMC maintainer
bnxt_en: Call bnxt_ethtool_free() in bnxt_init_one() error path
bnxt_en: Fix TQM fastpath ring backing store computation
bnxt_en: Rediscover PHY capabilities after firmware reset
cxgb4: fix wrong shift.
mac80211: handle various extensible elements correctly
mac80211: reset profile_periodicity/ema_ap
cfg80211: avoid double free of PMSR request
cfg80211: make certificate generation more robust
mac80211: minstrel_ht: fix sample time check
net: qed: Fix memcpy() overflow of qed_dcbx_params()
net: cdc_eem: fix tx fixup skb leak
net: hamradio: fix memory leak in mkiss_close
...
At the moment, the WWAN core provides wwan_port_txon/off() to implement
blocking writes. The tx() port operation should not block, instead
wwan_port_txon/off() should be called when the TX queue is full or has
free space again.
However, in some cases it is not straightforward to make use of that
functionality. For example, the RPMSG API used by rpmsg_wwan_ctrl.c
does not provide any way to be notified when the TX queue has space
again. Instead, it only provides the following operations:
- rpmsg_send(): blocking write (wait until there is space)
- rpmsg_trysend(): non-blocking write (return error if no space)
- rpmsg_poll(): set poll flags depending on TX queue state
Generally that's totally sufficient for implementing a char device,
but it does not fit well to the currently provided WWAN port ops.
Most of the time, using the non-blocking rpmsg_trysend() in the
WWAN tx() port operation works just fine. However, with high-frequent
writes to the char device it is possible to trigger a situation
where this causes issues. For example, consider the following
(somewhat unrealistic) example:
# dd if=/dev/zero bs=1000 of=/dev/wwan0qmi0
dd: error writing '/dev/wwan0qmi0': Resource temporarily unavailable
1+0 records out
This fails immediately after writing the first record. It's likely
only a matter of time until this triggers issues for some real application
(e.g. ModemManager sending a lot of large QMI packets).
The rpmsg_char device does not have this problem, because it uses
rpmsg_trysend() and rpmsg_poll() to support non-blocking operations.
Make it possible to use the same in the RPMSG WWAN driver by adding
two new optional wwan_port_ops:
- tx_blocking(): send data blocking if allowed
- tx_poll(): set additional TX poll flags
This integrates nicely with the RPMSG API and does not require
any change in existing WWAN drivers.
With these changes, the dd example above blocks instead of exiting
with an error.
Cc: Loic Poulain <loic.poulain@linaro.org>
Signed-off-by: Stephan Gerhold <stephan@gerhold.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Most device_id structs provide a driver_data field that can be used
by drivers to associate data more easily for a particular device ID.
Add the same for the rpmsg_device_id.
Cc: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Stephan Gerhold <stephan@gerhold.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Modify the pr_info content from int to char *, this looks more readable.
Signed-off-by: Yejune Deng <yejune.deng@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When constructing ICMP response messages, the kernel will try to pick a
suitable source address for the outgoing packet. However, if no IPv4
addresses are configured on the system at all, this will fail and we end up
producing an ICMP message with a source address of 0.0.0.0. This can happen
on a box routing IPv4 traffic via v6 nexthops, for instance.
Since 0.0.0.0 is not generally routable on the internet, there's a good
chance that such ICMP messages will never make it back to the sender of the
original packet that the ICMP message was sent in response to. This, in
turn, can create connectivity and PMTUd problems for senders. Fortunately,
RFC7600 reserves a dummy address to be used as a source for ICMP
messages (192.0.0.8/32), so let's teach the kernel to substitute that
address as a last resort if the regular source address selection procedure
fails.
Below is a quick example reproducing this issue with network namespaces:
ip netns add ns0
ip l add type veth peer netns ns0
ip l set dev veth0 up
ip a add 10.0.0.1/24 dev veth0
ip a add fc00:dead:cafe:42::1/64 dev veth0
ip r add 10.1.0.0/24 via inet6 fc00:dead:cafe:42::2
ip -n ns0 l set dev veth0 up
ip -n ns0 a add fc00:dead:cafe:42::2/64 dev veth0
ip -n ns0 r add 10.0.0.0/24 via inet6 fc00:dead:cafe:42::1
ip netns exec ns0 sysctl -w net.ipv4.icmp_ratelimit=0
ip netns exec ns0 sysctl -w net.ipv4.ip_forward=1
tcpdump -tpni veth0 -c 2 icmp &
ping -w 1 10.1.0.1 > /dev/null
tcpdump: verbose output suppressed, use -v[v]... for full protocol decode
listening on veth0, link-type EN10MB (Ethernet), snapshot length 262144 bytes
IP 10.0.0.1 > 10.1.0.1: ICMP echo request, id 29, seq 1, length 64
IP 0.0.0.0 > 10.0.0.1: ICMP net 10.1.0.1 unreachable, length 92
2 packets captured
2 packets received by filter
0 packets dropped by kernel
With this patch the above capture changes to:
IP 10.0.0.1 > 10.1.0.1: ICMP echo request, id 31127, seq 1, length 64
IP 192.0.0.8 > 10.0.0.1: ICMP net 10.1.0.1 unreachable, length 92
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Reported-by: Juliusz Chroboczek <jch@irif.fr>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch added a new member named csum in struct mptcp_options_received.
When parsing the MP_CAPABLE with data, if the checksum is enabled,
adjust the expected_opsize. If the receiving option length matches the
length with the data checksum, get the checksum value and save it in
mp_opt->csum. And in mptcp_incoming_options, pass it to mpext->csum.
We always parse any csum/nocsum combination and delay the presence check
to later code, to allow reset if missing.
Additionally, in the TX path, use the newly introduce ext field to avoid
MPTCP csum recomputation on TCP retransmission and unneeded csum update
on when setting the data fin_flag.
Co-developed-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch added a new member csum_reqd in struct mptcp_out_options and
struct mptcp_subflow_request_sock. Initialized it with the helper
function mptcp_is_checksum_enabled().
In mptcp_write_options, if this field is enabled, send out the MP_CAPABLE
suboption with the MPTCP_CAP_CHECKSUM_REQD flag.
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch added a new member named csum in struct mptcp_ext, implemented
a new function named mptcp_generate_data_checksum().
Generate the data checksum in mptcp_sendmsg_frag, save it in mpext->csum.
Note that we must generate the csum for zero window probe, too.
Do the csum update incrementally, to avoid multiple csum computation
when the data is appended to existing skb.
Note that in a later patch we will skip unneeded csum related operation.
Changes not included here to keep the delta small.
Co-developed-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch added a new member named csum_enabled in struct mptcp_sock,
used a dummy mptcp_is_checksum_enabled() helper to initialize it.
Also added a new member named mptcpi_csum_enabled in struct mptcp_info
to expose the csum_enabled flag.
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
IETF RFC 8986 [1] includes the definition of SRv6 End.DT4, End.DT6, and
End.DT46 Behaviors.
The current SRv6 code in the Linux kernel only implements End.DT4 and
End.DT6 which can be used respectively to support IPv4-in-IPv6 and
IPv6-in-IPv6 VPNs. With End.DT4 and End.DT6 it is not possible to create a
single SRv6 VPN tunnel to carry both IPv4 and IPv6 traffic.
The proposed End.DT46 implementation is meant to support the decapsulation
of IPv4 and IPv6 traffic coming from a single SRv6 tunnel.
The implementation of the SRv6 End.DT46 Behavior in the Linux kernel
greatly simplifies the setup and operations of SRv6 VPNs.
The SRv6 End.DT46 Behavior leverages the infrastructure of SRv6 End.DT{4,6}
Behaviors implemented so far, because it makes use of a VRF device in
order to force the routing lookup into the associated routing table.
To make the End.DT46 work properly, it must be guaranteed that the routing
table used for routing lookup operations is bound to one and only one VRF
during the tunnel creation. Such constraint has to be enforced by enabling
the VRF strict_mode sysctl parameter, i.e.:
$ sysctl -wq net.vrf.strict_mode=1
Note that the same approach is used for the SRv6 End.DT4 Behavior and for
the End.DT6 Behavior in VRF mode.
The command used to instantiate an SRv6 End.DT46 Behavior is
straightforward, i.e.:
$ ip -6 route add 2001:db8::1 encap seg6local action End.DT46 vrftable 100 dev vrf100.
[1] https://www.rfc-editor.org/rfc/rfc8986.html#name-enddt46-decapsulation-and-s
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Performance and impact of SRv6 End.DT46 Behavior on the SRv6 Networking
=======================================================================
This patch aims to add the SRv6 End.DT46 Behavior with minimal impact on
the performance of SRv6 End.DT4 and End.DT6 Behaviors.
In order to verify this, we tested the performance of the newly introduced
SRv6 End.DT46 Behavior and compared it with the performance of SRv6
End.DT{4,6} Behaviors, considering both the patched kernel and the kernel
before applying the End.DT46 patch (referred to as vanilla kernel).
In details, the following decapsulation scenarios were considered:
1.a) IPv6 traffic in SRv6 End.DT46 Behavior on patched kernel;
1.b) IPv4 traffic in SRv6 End.DT46 Behavior on patched kernel;
2.a) SRv6 End.DT6 Behavior (VRF mode) on patched kernel;
2.b) SRv6 End.DT4 Behavior on patched kernel;
3.a) SRv6 End.DT6 Behavior (VRF mode) on vanilla kernel (without the
End.DT46 patch);
3.b) SRv6 End.DT4 Behavior on vanilla kernel (without the End.DT46 patch).
All tests were performed on a testbed deployed on the CloudLab [2]
facilities. We considered IPv{4,6} traffic handled by a single core (at 2.4
GHz on a Xeon(R) CPU E5-2630 v3) on kernel 5.13-rc1 using packets of size
~ 100 bytes.
Scenario (1.a): average 684.70 kpps; std. dev. 0.7 kpps;
Scenario (1.b): average 711.69 kpps; std. dev. 1.2 kpps;
Scenario (2.a): average 690.70 kpps; std. dev. 1.2 kpps;
Scenario (2.b): average 722.22 kpps; std. dev. 1.7 kpps;
Scenario (3.a): average 690.02 kpps; std. dev. 2.6 kpps;
Scenario (3.b): average 721.91 kpps; std. dev. 1.2 kpps;
Considering the results for the patched kernel (1.a, 1.b, 2.a, 2.b) we
observe that the performance degradation incurred in using End.DT46 rather
than End.DT6 and End.DT4 respectively for IPv6 and IPv4 traffic is minimal,
around 0.9% and 1.5%. Such very minimal performance degradation is the
price to be paid if one prefers to use a single tunnel capable of handling
both types of traffic (IPv4 and IPv6).
Comparing the results for End.DT4 and End.DT6 under the patched and the
vanilla kernel (2.a, 2.b, 3.a, 3.b) we observe that the introduction of the
End.DT46 patch has no impact on the performance of End.DT4 and End.DT6.
[2] https://www.cloudlab.us
Signed-off-by: Andrea Mayer <andrea.mayer@uniroma2.it>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull power management fix from Rafael Wysocki:
"Remove recently added frequency invariance support from the CPPC
cpufreq driver, because it has turned out to be problematic and it
cannot be fixed properly on time for 5.13 (Viresh Kumar)"
* tag 'pm-5.13-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
Revert "cpufreq: CPPC: Add support for frequency invariance"
There are many places where both the fwnode_handle and the of_node of a
device need to be populated. Add a function which does both so that we
have consistency.
Suggested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann says:
====================
pull-request: bpf-next 2021-06-17
The following pull-request contains BPF updates for your *net-next* tree.
We've added 50 non-merge commits during the last 25 day(s) which contain
a total of 148 files changed, 4779 insertions(+), 1248 deletions(-).
The main changes are:
1) BPF infrastructure to migrate TCP child sockets from a listener to another
in the same reuseport group/map, from Kuniyuki Iwashima.
2) Add a provably sound, faster and more precise algorithm for tnum_mul() as
noted in https://arxiv.org/abs/2105.05398, from Harishankar Vishwanathan.
3) Streamline error reporting changes in libbpf as planned out in the
'libbpf: the road to v1.0' effort, from Andrii Nakryiko.
4) Add broadcast support to xdp_redirect_map(), from Hangbin Liu.
5) Extends bpf_map_lookup_and_delete_elem() functionality to 4 more map
types, that is, {LRU_,PERCPU_,LRU_PERCPU_,}HASH, from Denis Salopek.
6) Support new LLVM relocations in libbpf to make them more linker friendly,
also add a doc to describe the BPF backend relocations, from Yonghong Song.
7) Silence long standing KUBSAN complaints on register-based shifts in
interpreter, from Daniel Borkmann and Eric Biggers.
8) Add dummy PT_REGS macros in libbpf to fail BPF program compilation when
target arch cannot be determined, from Lorenz Bauer.
9) Extend AF_XDP to support large umems with 1M+ pages, from Magnus Karlsson.
10) Fix two minor libbpf tc BPF API issues, from Kumar Kartikeya Dwivedi.
11) Move libbpf BPF_SEQ_PRINTF/BPF_SNPRINTF macros that can be used by BPF
programs to bpf_helpers.h header, from Florent Revest.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Th_strings arrays netdev_features_strings, tunable_strings, and
phy_tunable_strings has been moved to file net/ethtool/common.c.
So fixes the comment.
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull quota and fanotify fixes from Jan Kara:
"A fixup finishing disabling of quotactl_path() syscall (I've missed
archs using different way to declare syscalls) and a fix of an fd leak
in error handling path of fanotify"
* tag 'fixes_for_v5.13-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
quota: finish disable quotactl_path syscall
fanotify: fix copy_event_to_user() fid error clean up
Running devlink reload command for port in switchdev mode cause
resources to corrupt: driver can't release allocated EQ and reclaim
memory pages, because "rdma" auxiliary device had add CQs which blocks
EQ from deletion.
Erroneous sequence happens during reload-down phase, and is following:
1. detach device - suspends auxiliary devices which support it, destroys
others. During this step "eth-rep" and "rdma-rep" are destroyed,
"eth" - suspended.
2. disable SRIOV - moves device to legacy mode; as part of disablement -
rescans drivers. This step adds "rdma" auxiliary device.
3. destroy EQ table - <failure>.
Driver shouldn't create any device during unload flows. To handle that
implement MLX5_PRIV_FLAGS_DETACH flag, set it on device detach and unset
on device attach. If flag is set do no-op on drivers rescan.
Fixes: a925b5e309 ("net/mlx5: Register mlx5 devices to auxiliary virtual bus")
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Make the gathered SMC statistics network namespace aware, for each
namespace collect an own set of statistic information.
Signed-off-by: Guvenc Gulce <guvenc@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support to collect more detailed SMC fallback reason statistics and
provide these statistics to user space on the netlink interface.
Signed-off-by: Guvenc Gulce <guvenc@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add the netlink function which collects the statistics information and
delivers it to the userspace.
Signed-off-by: Guvenc Gulce <guvenc@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a race between THP unmapping and truncation, when truncate sees
pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared
it, but before its page_remove_rmap() gets to decrement
compound_mapcount: generating false "BUG: Bad page cache" reports that
the page is still mapped when deleted. This commit fixes that, but not
in the way I hoped.
The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK)
instead of unmap_mapping_range() in truncate_cleanup_page(): it has
often been an annoyance that we usually call unmap_mapping_range() with
no pages locked, but there apply it to a single locked page.
try_to_unmap() looks more suitable for a single locked page.
However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page):
it is used to insert THP migration entries, but not used to unmap THPs.
Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB
needs are different, I'm too ignorant of the DAX cases, and couldn't
decide how far to go for anon+swap. Set that aside.
The second attempt took a different tack: make no change in truncate.c,
but modify zap_huge_pmd() to insert an invalidated huge pmd instead of
clearing it initially, then pmd_clear() between page_remove_rmap() and
unlocking at the end. Nice. But powerpc blows that approach out of the
water, with its serialize_against_pte_lookup(), and interesting pgtable
usage. It would need serious help to get working on powerpc (with a
minor optimization issue on s390 too). Set that aside.
Just add an "if (page_mapped(page)) synchronize_rcu();" or other such
delay, after unmapping in truncate_cleanup_page()? Perhaps, but though
that's likely to reduce or eliminate the number of incidents, it would
give less assurance of whether we had identified the problem correctly.
This successful iteration introduces "unmap_mapping_page(page)" instead
of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route,
with an addition to details. Then zap_pmd_range() watches for this
case, and does spin_unlock(pmd_lock) if so - just like
page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but
safe.
Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to
assert its interface; but currently that's only used to make sure that
page->mapping is stable, and zap_pmd_range() doesn't care if the page is
locked or not. Along these lines, in invalidate_inode_pages2_range()
move the initial unmap_mapping_range() out from under page lock, before
then calling unmap_mapping_page() under page lock if still mapped.
Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com
Fixes: fc127da085 ("truncate: handle file thp")
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jue Wang <juew@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Wang Yugui <wangyugui@e16-tech.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Stressing huge tmpfs often crashed on unmap_page()'s VM_BUG_ON_PAGE
(!unmap_success): with dump_page() showing mapcount:1, but then its raw
struct page output showing _mapcount ffffffff i.e. mapcount 0.
And even if that particular VM_BUG_ON_PAGE(!unmap_success) is removed,
it is immediately followed by a VM_BUG_ON_PAGE(compound_mapcount(head)),
and further down an IS_ENABLED(CONFIG_DEBUG_VM) total_mapcount BUG():
all indicative of some mapcount difficulty in development here perhaps.
But the !CONFIG_DEBUG_VM path handles the failures correctly and
silently.
I believe the problem is that once a racing unmap has cleared pte or
pmd, try_to_unmap_one() may skip taking the page table lock, and emerge
from try_to_unmap() before the racing task has reached decrementing
mapcount.
Instead of abandoning the unsafe VM_BUG_ON_PAGE(), and the ones that
follow, use PVMW_SYNC in try_to_unmap_one() in this case: adding
TTU_SYNC to the options, and passing that from unmap_page().
When CONFIG_DEBUG_VM, or for non-debug too? Consensus is to do the same
for both: the slight overhead added should rarely matter, except perhaps
if splitting sparsely-populated multiply-mapped shmem. Once confident
that bugs are fixed, TTU_SYNC here can be removed, and the race
tolerated.
Link: https://lkml.kernel.org/r/c1e95853-8bcd-d8fd-55fa-e7f2488e78f@google.com
Fixes: fec89c109f ("thp: rewrite freeze_page()/unfreeze_page() with generic rmap walkers")
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jue Wang <juew@google.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Wang Yugui <wangyugui@e16-tech.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The routine restore_reserve_on_error is called to restore reservation
information when an error occurs after page allocation. The routine
alloc_huge_page modifies the mapping reserve map and potentially the
reserve count during allocation. If code calling alloc_huge_page
encounters an error after allocation and needs to free the page, the
reservation information needs to be adjusted.
Currently, restore_reserve_on_error only takes action on pages for which
the reserve count was adjusted(HPageRestoreReserve flag). There is
nothing wrong with these adjustments. However, alloc_huge_page ALWAYS
modifies the reserve map during allocation even if the reserve count is
not adjusted. This can cause issues as observed during development of
this patch [1].
One specific series of operations causing an issue is:
- Create a shared hugetlb mapping
Reservations for all pages created by default
- Fault in a page in the mapping
Reservation exists so reservation count is decremented
- Punch a hole in the file/mapping at index previously faulted
Reservation and any associated pages will be removed
- Allocate a page to fill the hole
No reservation entry, so reserve count unmodified
Reservation entry added to map by alloc_huge_page
- Error after allocation and before instantiating the page
Reservation entry remains in map
- Allocate a page to fill the hole
Reservation entry exists, so decrement reservation count
This will cause a reservation count underflow as the reservation count
was decremented twice for the same index.
A user would observe a very large number for HugePages_Rsvd in
/proc/meminfo. This would also likely cause subsequent allocations of
hugetlb pages to fail as it would 'appear' that all pages are reserved.
This sequence of operations is unlikely to happen, however they were
easily reproduced and observed using hacked up code as described in [1].
Address the issue by having the routine restore_reserve_on_error take
action on pages where HPageRestoreReserve is not set. In this case, we
need to remove any reserve map entry created by alloc_huge_page. A new
helper routine vma_del_reservation assists with this operation.
There are three callers of alloc_huge_page which do not currently call
restore_reserve_on error before freeing a page on error paths. Add
those missing calls.
[1] https://lore.kernel.org/linux-mm/20210528005029.88088-1-almasrymina@google.com/
Link: https://lkml.kernel.org/r/20210607204510.22617-1-mike.kravetz@oracle.com
Fixes: 96b96a96dd ("mm/hugetlb: fix huge page reservation leak in private mapping error paths"
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When hugetlb page fault (under overcommitting situation) and
memory_failure() race, VM_BUG_ON_PAGE() is triggered by the following
race:
CPU0: CPU1:
gather_surplus_pages()
page = alloc_surplus_huge_page()
memory_failure_hugetlb()
get_hwpoison_page(page)
__get_hwpoison_page(page)
get_page_unless_zero(page)
zero = put_page_testzero(page)
VM_BUG_ON_PAGE(!zero, page)
enqueue_huge_page(h, page)
put_page(page)
__get_hwpoison_page() only checks the page refcount before taking an
additional one for memory error handling, which is not enough because
there's a time window where compound pages have non-zero refcount during
hugetlb page initialization.
So make __get_hwpoison_page() check page status a bit more for hugetlb
pages with get_hwpoison_huge_page(). Checking hugetlb-specific flags
under hugetlb_lock makes sure that the hugetlb page is not transitive.
It's notable that another new function, HWPoisonHandlable(), is helpful
to prevent a race against other transitive page states (like a generic
compound page just before PageHuge becomes true).
Link: https://lkml.kernel.org/r/20210603233632.2964832-2-nao.horiguchi@gmail.com
Fixes: ead07f6a86 ("mm/memory-failure: introduce get_hwpoison_page() for consistent refcount handling")
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reported-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: <stable@vger.kernel.org> [5.12+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The round-robin rr_tx_counter was shared across CPUs leading to
significant cache thrashing at high packet rates. This patch switches
the round-robin packet counter to use a per-cpu variable to decide
the destination slave.
On a test with 2x100Gbit ICE nic with pktgen_sample_04_many_flows.sh
(-s 64 -t 32) the tx rate was 19.6Mpps before and 22.3Mpps after
this patch.
"perf top -e cache_misses" before:
12.31% [bonding] [k] bond_xmit_roundrobin_slave_get
10.59% [sch_fq_codel] [k] fq_codel_dequeue
9.34% [kernel] [k] skb_release_data
after:
15.42% [sch_fq_codel] [k] fq_codel_dequeue
10.06% [kernel] [k] __memset
9.12% [kernel] [k] skb_release_data
Signed-off-by: Jussi Maki <joamaki@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The function get_net_ns_by_fd() could be inlined when NET_NS is not
enabled.
Signed-off-by: Changbin Du <changbin.du@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Scaled PPM conversion to PPB may (on 64bit systems) result
in a value larger than s32 can hold (freq/scaled_ppm is a long).
This means the kernel will not correctly reject unreasonably
high ->freq values (e.g. > 4294967295ppb, 281474976645 scaled PPM).
The conversion is equivalent to a division by ~66 (65.536),
so the value of ppb is always smaller than ppm, but not small
enough to assume narrowing the type from long -> s32 is okay.
Note that reasonable user space (e.g. ptp4l) will not use such
high values, anyway, 4289046510ppb ~= 4.3x, so the fix is
somewhat pedantic.
Fixes: d39a743511 ("ptp: validate the requested frequency adjustment.")
Fixes: d94ba80ebb ("ptp: Added a brand new class driver for ptp clocks.")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch introduces a new bpf_attach_type for BPF_PROG_TYPE_SK_REUSEPORT
to check if the attached eBPF program is capable of migrating sockets. When
the eBPF program is attached, we run it for socket migration if the
expected_attach_type is BPF_SK_REUSEPORT_SELECT_OR_MIGRATE or
net.ipv4.tcp_migrate_req is enabled.
Currently, the expected_attach_type is not enforced for the
BPF_PROG_TYPE_SK_REUSEPORT type of program. Thus, this commit follows the
earlier idea in the commit aac3fc320d ("bpf: Post-hooks for sys_bind") to
fix up the zero expected_attach_type in bpf_prog_load_fixup_attach_type().
Moreover, this patch adds a new field (migrating_sk) to sk_reuseport_md to
select a new listener based on the child socket. migrating_sk varies
depending on if it is migrating a request in the accept queue or during
3WHS.
- accept_queue : sock (ESTABLISHED/SYN_RECV)
- 3WHS : request_sock (NEW_SYN_RECV)
In the eBPF program, we can select a new listener by
BPF_FUNC_sk_select_reuseport(). Also, we can cancel migration by returning
SK_DROP. This feature is useful when listeners have different settings at
the socket API level or when we want to free resources as soon as possible.
- SK_PASS with selected_sk, select it as a new listener
- SK_PASS with selected_sk NULL, fallbacks to the random selection
- SK_DROP, cancel the migration.
There is a noteworthy point. We select a listening socket in three places,
but we do not have struct skb at closing a listener or retransmitting a
SYN+ACK. On the other hand, some helper functions do not expect skb is NULL
(e.g. skb_header_pointer() in BPF_FUNC_skb_load_bytes(), skb_tail_pointer()
in BPF_FUNC_skb_load_bytes_relative()). So we allocate an empty skb
temporarily before running the eBPF program.
Suggested-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/netdev/20201123003828.xjpjdtk4ygl6tg6h@kafai-mbp.dhcp.thefacebook.com/
Link: https://lore.kernel.org/netdev/20201203042402.6cskdlit5f3mw4ru@kafai-mbp.dhcp.thefacebook.com/
Link: https://lore.kernel.org/netdev/20201209030903.hhow5r53l6fmozjn@kafai-mbp.dhcp.thefacebook.com/
Link: https://lore.kernel.org/bpf/20210612123224.12525-10-kuniyu@amazon.co.jp
