The MPTCP ADD_ADDR suboption with echo-flag=1 has no HMAC, the size is
smaller than the one initially sent without echo-flag=1. We then need to
use the correct size everywhere when we need this echo bit.
Before this patch, the wrong size was reserved but the correct amount of
bytes were written (and read): the remaining bytes contained garbage.
Fixes: 6a6c05a8b0 ("mptcp: send out ADD_ADDR with echo flag")
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/95
Reported-and-tested-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Define the MAC_PUSH action which pushes an MPLS LSE before the mac
header (instead of between the mac and the network headers as the
plain PUSH action does).
The only special case is when the skb has an offloaded VLAN. In that
case, it has to be inlined before pushing the MPLS header.
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Implement TCA_VLAN_ACT_POP_ETH and TCA_VLAN_ACT_PUSH_ETH, to
respectively pop and push a base Ethernet header at the beginning of a
frame.
POP_ETH is just a matter of pulling ETH_HLEN bytes. VLAN tags, if any,
must be stripped before calling POP_ETH.
PUSH_ETH is restricted to skbs with no mac_header, and only the MAC
addresses can be configured. The Ethertype is automatically set from
skb->protocol. These restrictions ensure that all skb's fields remain
consistent, so that this action can't confuse other part of the
networking stack (like GSO).
Since openvswitch already had these actions, consolidate the code in
skbuff.c (like for vlan and mpls push/pop).
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The check for old hardware versions that did not have SMCDv2 support was
using suspicious pointer magic. Address the fields using an array.
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When building a CLC proposal message then the list of ISM devices does
not need to contain multiple devices that have the same chid value,
all these devices use the same function at the end.
Improve smc_find_ism_v2_device_clnt() to collect only ISM devices that
have unique chid values.
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The retransmission refactoring patch
686989700c ("tcp: simplify tcp_mark_skb_lost")
does not properly update the total lost packet counter which may
break the policer mode in BBR. This patch fixes it.
Fixes: 686989700c ("tcp: simplify tcp_mark_skb_lost")
Reported-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
smatch complains about
net/iucv/iucv.c:1119 __iucv_message_receive() warn: inconsistent indenting
While touching this line, also make the return logic consistent and thus
get rid of a goto label.
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Reviewed-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
smatch complains about
net/iucv/af_iucv.c:624 iucv_sock_bind() error: memcpy() 'sa->siucv_user_id' too small (8 vs 9)
Which is absolutely correct - the memcpy() takes 9 bytes (sizeof(uid))
from an 8-byte field (sa->siucv_user_id).
Luckily the sockaddr_iucv struct contains more data after the
.siucv_user_id field, and we checked the size of the passed data earlier
on. So the memcpy() won't accidentally read from an invalid location.
Fix the warning by reducing the size of the uid variable to what's
actually needed, and thus reducing the amount of copied data.
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Reviewed-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Right now CTRL_CMD_GETPOLICY can only dump the family-wide
policy. Support dumping policy of a specific op.
v3:
- rebase after per-op policy export and handle that
v2:
- make cmd U32, just in case.
v1:
- don't echo op in the output in a naive way, this should
make it cleaner to extend the output format for dumping
policies for all the commands at once in the future.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20201001225933.1373426-11-kuba@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for per-op policy dumping. The data is pretty much
as before, except that now the assumption that the policy with
index 0 is "the" policy no longer holds - you now need to look
at the new CTRL_ATTR_OP_POLICY attribute which is a nested attr
(indexed by op) containing attributes for do and dump policies.
When a single op is requested, the CTRL_ATTR_OP_POLICY will be
added in the same way, since do and dump policies may differ.
v2:
- conditionally advertise per-command policies only if there
actually is a policy being used for the do/dump and it's
present at all
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We'll need this later for the per-op policy index dump.
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rework the policy dump code a bit to support adding multiple
policies to a single dump, in order to e.g. support per-op
policies in generic netlink.
v2:
- move kernel-doc to implementation [Jakub]
- squash the first patch to not flip-flop on the prototype
[Jakub]
- merge netlink_policy_dump_get_policy_idx() with the old
get_policy_idx() we already had
- rebase without Jakub's patch to have per-op dump
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The maxtype is really an integral part of the policy, and while we
haven't gotten into a situation yet where this happens, it seems
that some developer might eventually have two places pointing to
identical policies, with different maxattr to exclude some attrs
in one of the places.
Even if not, it's really the right thing to compare both since the
two data items fundamentally belong together.
v2:
- also do the proper comparison in get_policy_idx()
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In preparation for adding a new attribute to CTRL_CMD_GETPOLICY
split the policies for getpolicy and getfamily apart.
This will cause a slight user-visible change in that dumping
the policies will switch from per family to per op, but
supposedly sniffer-type applications (which are the main use
case for policy dumping thus far) should support both, anyway.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Attributes are already parsed based on the policy specified
in the family and ready-to-use in info->attrs. No need to
call genlmsg_parse() again.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add policy to the struct genl_ops structure, this time
with maxattr, so it can be used properly.
Propagate .policy and .maxattr from the family
in genl_get_cmd() if needed, this way the rest of the
code does not have to worry if the policy is per op
or global.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The structure of ctrl_dumppolicy() is clearly split into
init and dumping. Move the init to a .start callback
for clarity, it's a more idiomatic netlink dump code structure.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Whenever netlink dump uses more than 2 cb->args[] entries
code gets hard to read. We're about to add more state to
ctrl_dumppolicy() so create a structure.
Since the structure is typed and clearly named we can remove
the local fam_id variable and use ctx->fam_id directly.
v3:
- rebase onto explicit free fix
v1:
- s/nl_policy_dump/netlink_policy_dump_state/
- forward declare struct netlink_policy_dump_state,
and move from passing unsigned long to actual pointer type
- add build bug on
- u16 fam_id
- s/args/ctx/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Bulk of the genetlink users can use smaller ops, move them.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
We want to add maxattr and policy back to genl_ops, to enable
dumping per command policy to user space. This, however, would
cause bloat for all the families with global policies. Introduce
smaller version of ops (half the size of genl_ops). Translate
these smaller ops into a full blown struct before use in the
core.
v1:
- use struct assignment
- put a full copy of the op in struct genl_dumpit_info
- s/light/small/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a new devlink callback, .trap_group_action_set(), which can be used
by device drivers which do not support controlling the action (drop,
trap) on each trap but rather on the entire group trap.
If this new callback is populated, it will take precedence over the
.trap_action_set() callback when the user requests a change of all the
traps in a group.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add parser error drop packet traps, so that capable device driver could
register them with devlink. The new packet trap group holds any drops of
packets which were marked by the device as erroneous during header
parsing. Add documentation for every added packet trap and packet trap
group.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
* lots more S1G band support
* 6 GHz scanning, finally
* kernel-doc fixes
* non-split wiphy dump fixes in nl80211
* various other small cleanups/features
-----BEGIN PGP SIGNATURE-----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=B9Xl
-----END PGP SIGNATURE-----
Merge tag 'mac80211-next-for-net-next-2020-10-02' of git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next
Johannes Berg says:
====================
Another set of changes, this time with:
* lots more S1G band support
* 6 GHz scanning, finally
* kernel-doc fixes
* non-split wiphy dump fixes in nl80211
* various other small cleanups/features
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that we are guaranteed that dsa_untag_bridge_pvid() is called after
eth_type_trans() we can utilize __vlan_find_dev_deep_rcu() which will
take care of finding an 802.1Q upper on top of a bridge master.
A common use case, prior to 12a1526d067 ("net: dsa: untag the bridge
pvid from rx skbs") was to configure a bridge 802.1Q upper like this:
ip link add name br0 type bridge vlan_filtering 0
ip link add link br0 name br0.1 type vlan id 1
in order to pop the default_pvid VLAN tag.
With this change we restore that behavior while still allowing the DSA
receive path to automatically pop the VLAN tag.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that dsa_untag_bridge_pvid() is called after eth_type_trans() we are
guaranteed that skb->protocol will be set to a correct value, thus
allowing us to avoid calling vlan_eth_hdr().
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Indicate to the DSA receive path that we need to untage the bridge PVID,
this allows us to remove the dsa_untag_bridge_pvid() calls from
net/dsa/tag_brcm.c.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When a DSA switch driver needs to call dsa_untag_bridge_pvid(), it can
set dsa_switch::untag_brige_pvid to indicate this is necessary.
This is a pre-requisite to making sure that we are always calling
dsa_untag_bridge_pvid() after eth_type_trans() has been called.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Steffen Klassert says:
====================
pull request (net-next): ipsec-next 2020-10-02
1) Add a full xfrm compatible layer for 32-bit applications on
64-bit kernels. From Dmitry Safonov.
Please pull or let me know if there are problems.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
[ Upstream commit a95bc734e6 ]
If userspace doesn't complete the policy dump, we leak the
allocated state. Fix this.
Fixes: d07dcf9aad ("netlink: add infrastructure to expose policies to userspace")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
In ieee80211_determine_chantype(), the sband->ht_cap was
being processed before S1G Operation element. Since the
HT capability element should not be present on the S1G
band, avoid processing potential garbage by moving the
call to ieee80211_apply_htcap_overrides() to after the S1G
block.
Also, in case of a missing S1G Operation element, we would
continue trying to process non-S1G elements (and return
with a channel width of 20MHz). Instead, just assume
primary channel is equal to operating and infer the
operating width from the BSS channel, then return.
Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20201001174748.24520-1-thomas@adapt-ip.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
When dumping wiphy information, we try to split the data into
many submessages, but for old userspace we still support the
old mode where this doesn't happen.
However, in this case we were not resetting our state correctly
and dumping multiple messages for each wiphy, which would have
broken such older userspace.
This was broken pretty much immediately afterwards because it
only worked in the original commit where non-split dumps didn't
have any more data than split dumps...
Fixes: fe1abafd94 ("nl80211: re-add channel width and extended capa advertising")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://lore.kernel.org/r/20200928130717.3e6d9c6bada2.Ie0f151a8d0d00a8e1e18f6a8c9244dd02496af67@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
When wiphy dumps cannot be split, such as in events or with
older userspace that doesn't support it, the size can today
be too big.
Reduce it, by doing two things:
1) remove data that couldn't have been present before the
split capability was introduced since it's new, such as
HE capabilities
2) as suggested by Martin Willi, remove management frame
subtypes from the split dumps, as just (1) isn't even
enough due to other new code capabilities. This is fine
as old consumers (really just wpa_supplicant) didn't
check this data before they got support for split dumps.
Reported-by: Martin Willi <martin@strongswan.org>
Suggested-by: Martin Willi <martin@strongswan.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Tested-by: Martin Willi <martin@strongswan.org>
Link: https://lore.kernel.org/r/20200928130655.53bce7873164.I71f06c9a221cd0630429a1a56eeae68a13beca61@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Fix follow warnings:
[net/core/net-sysfs.c:1161]: (warning) %u in format string (no. 1)
requires 'unsigned int' but the argument type is 'int'.
[net/core/net-sysfs.c:1162]: (warning) %u in format string (no. 1)
requires 'unsigned int' but the argument type is 'int'.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Ye Bin <yebin10@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix follow warnings:
[net/core/pktgen.c:925]: (warning) %u in format string (no. 1)
requires 'unsigned int' but the argument type is 'signed int'.
[net/core/pktgen.c:942]: (warning) %u in format string (no. 1)
requires 'unsigned int' but the argument type is 'signed int'.
[net/core/pktgen.c:962]: (warning) %u in format string (no. 1)
requires 'unsigned int' but the argument type is 'signed int'.
[net/core/pktgen.c:984]: (warning) %u in format string (no. 1)
requires 'unsigned int' but the argument type is 'signed int'.
[net/core/pktgen.c:1149]: (warning) %d in format string (no. 1)
requires 'int' but the argument type is 'unsigned int'.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Ye Bin <yebin10@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann says:
====================
pull-request: bpf-next 2020-10-01
The following pull-request contains BPF updates for your *net-next* tree.
We've added 90 non-merge commits during the last 8 day(s) which contain
a total of 103 files changed, 7662 insertions(+), 1894 deletions(-).
Note that once bpf(/net) tree gets merged into net-next, there will be a small
merge conflict in tools/lib/bpf/btf.c between commit 1245008122 ("libbpf: Fix
native endian assumption when parsing BTF") from the bpf tree and the commit
3289959b97 ("libbpf: Support BTF loading and raw data output in both endianness")
from the bpf-next tree. Correct resolution would be to stick with bpf-next, it
should look like:
[...]
/* check BTF magic */
if (fread(&magic, 1, sizeof(magic), f) < sizeof(magic)) {
err = -EIO;
goto err_out;
}
if (magic != BTF_MAGIC && magic != bswap_16(BTF_MAGIC)) {
/* definitely not a raw BTF */
err = -EPROTO;
goto err_out;
}
/* get file size */
[...]
The main changes are:
1) Add bpf_snprintf_btf() and bpf_seq_printf_btf() helpers to support displaying
BTF-based kernel data structures out of BPF programs, from Alan Maguire.
2) Speed up RCU tasks trace grace periods by a factor of 50 & fix a few race
conditions exposed by it. It was discussed to take these via BPF and
networking tree to get better testing exposure, from Paul E. McKenney.
3) Support multi-attach for freplace programs, needed for incremental attachment
of multiple XDP progs using libxdp dispatcher model, from Toke Høiland-Jørgensen.
4) libbpf support for appending new BTF types at the end of BTF object, allowing
intrusive changes of prog's BTF (useful for future linking), from Andrii Nakryiko.
5) Several BPF helper improvements e.g. avoid atomic op in cookie generator and add
a redirect helper into neighboring subsys, from Daniel Borkmann.
6) Allow map updates on sockmaps from bpf_iter context in order to migrate sockmaps
from one to another, from Lorenz Bauer.
7) Fix 32 bit to 64 bit assignment from latest alu32 bounds tracking which caused
a verifier issue due to type downgrade to scalar, from John Fastabend.
8) Follow-up on tail-call support in BPF subprogs which optimizes x64 JIT prologue
and epilogue sections, from Maciej Fijalkowski.
9) Add an option to perf RB map to improve sharing of event entries by avoiding remove-
on-close behavior. Also, add BPF_PROG_TEST_RUN for raw_tracepoint, from Song Liu.
10) Fix a crash in AF_XDP's socket_release when memory allocation for UMEMs fails,
from Magnus Karlsson.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Previously, devlink called into drop monitor in order to report hardware
originated drops / exceptions. devlink intentionally filtered control
packets and did not pass them to drop monitor as they were not dropped
by the underlying hardware.
Now drop monitor registers its probe on a generic 'devlink_trap_report'
tracepoint and should therefore perform this filtering itself instead of
having devlink do that.
Add the trap type as metadata and have drop monitor ignore control
packets.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
'struct net_dm_hw_metadata' is a duplicate of 'struct
devlink_trap_metadata'.
Remove the former and simplify the code.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The old probe functions that were invoked by drop monitor code are no
longer called and can thus be removed. They were replaced by actual
probe functions that are registered on the recently introduced
'devlink_trap_report' tracepoint.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Convert drop monitor to use the recently introduced
'devlink_trap_report' tracepoint instead of having devlink call into
drop monitor.
This is both consistent with software originated drops ('kfree_skb'
tracepoint) and also allows drop monitor to be built as a module and
still report hardware originated drops.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Drop monitor supports two alerting modes: Summary and packet. Prepare a
probe function for each, so that they could be later registered on the
devlink tracepoint by calling register_trace_devlink_trap_report(),
based on the configured alerting mode.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a tracepoint for trap reports so that drop monitor could register
its probe on it. Use trace_devlink_trap_report_enabled() to avoid
wasting cycles setting the trap metadata if the tracepoint is not
enabled.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Whenever host is under very high memory pressure,
__tcp_send_ack() skb allocation fails, and we setup
a 200 ms (TCP_DELACK_MAX) timer before retrying.
On hosts with high number of TCP sockets, we can spend
considerable amount of cpu cycles in these attempts,
add high pressure on various spinlocks in mm-layer,
ultimately blocking threads attempting to free space
from making any progress.
This patch adds standard exponential backoff to avoid
adding fuel to the fire.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
TCP has been using it to work around the possibility of tcp_delack_timer()
finding the socket owned by user.
After commit 6f458dfb40 ("tcp: improve latencies of timer triggered events")
we added TCP_DELACK_TIMER_DEFERRED atomic bit for more immediate recovery,
so we can get rid of icsk_ack.blocked
This frees space that following patch will reuse.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a redirect_neigh() helper as redirect() drop-in replacement
for the xmit side. Main idea for the helper is to be very similar
in semantics to the latter just that the skb gets injected into
the neighboring subsystem in order to let the stack do the work
it knows best anyway to populate the L2 addresses of the packet
and then hand over to dev_queue_xmit() as redirect() does.
This solves two bigger items: i) skbs don't need to go up to the
stack on the host facing veth ingress side for traffic egressing
the container to achieve the same for populating L2 which also
has the huge advantage that ii) the skb->sk won't get orphaned in
ip_rcv_core() when entering the IP routing layer on the host stack.
Given that skb->sk neither gets orphaned when crossing the netns
as per 9c4c325252 ("skbuff: preserve sock reference when scrubbing
the skb.") the helper can then push the skbs directly to the phys
device where FQ scheduler can do its work and TCP stack gets proper
backpressure given we hold on to skb->sk as long as skb is still
residing in queues.
With the helper used in BPF data path to then push the skb to the
phys device, I observed a stable/consistent TCP_STREAM improvement
on veth devices for traffic going container -> host -> host ->
container from ~10Gbps to ~15Gbps for a single stream in my test
environment.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: David Ahern <dsahern@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Cc: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/bpf/f207de81629e1724899b73b8112e0013be782d35.1601477936.git.daniel@iogearbox.net
With its use in BPF, the cookie generator can be called very frequently
in particular when used out of cgroup v2 hooks (e.g. connect / sendmsg)
and attached to the root cgroup, for example, when used in v1/v2 mixed
environments. In particular, when there's a high churn on sockets in the
system there can be many parallel requests to the bpf_get_socket_cookie()
and bpf_get_netns_cookie() helpers which then cause contention on the
atomic counter.
As similarly done in f991bd2e14 ("fs: introduce a per-cpu last_ino
allocator"), add a small helper library that both can use for the 64 bit
counters. Given this can be called from different contexts, we also need
to deal with potential nested calls even though in practice they are
considered extremely rare. One idea as suggested by Eric Dumazet was
to use a reverse counter for this situation since we don't expect 64 bit
overflows anyways; that way, we can avoid bigger gaps in the 64 bit
counter space compared to just batch-wise increase. Even on machines
with small number of cores (e.g. 4) the cookie generation shrinks from
min/max/med/avg (ns) of 22/50/40/38.9 down to 10/35/14/17.3 when run
in parallel from multiple CPUs.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Link: https://lore.kernel.org/bpf/8a80b8d27d3c49f9a14e1d5213c19d8be87d1dc8.1601477936.git.daniel@iogearbox.net
Similarly to 5a52ae4e32 ("bpf: Allow to retrieve cgroup v1 classid
from v2 hooks"), add a helper to retrieve cgroup v1 classid solely
based on the skb->sk, so it can be used as key as part of BPF map
lookups out of tc from host ns, in particular given the skb->sk is
retained these days when crossing net ns thanks to 9c4c325252
("skbuff: preserve sock reference when scrubbing the skb."). This
is similar to bpf_skb_cgroup_id() which implements the same for v2.
Kubernetes ecosystem is still operating on v1 however, hence net_cls
needs to be used there until this can be dropped in with the v2
helper of bpf_skb_cgroup_id().
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/ed633cf27a1c620e901c5aa99ebdefb028dce600.1601477936.git.daniel@iogearbox.net
Quite some drivers make conditional decisions based on in_interrupt() to
invoke either netif_rx() or netif_rx_ni().
Conditionals based on in_interrupt() or other variants of preempt count
checks in drivers should not exist for various reasons and Linus clearly
requested to either split the code pathes or pass an argument to the
common functions which provides the context.
This is obviously the correct solution, but for some of the affected
drivers this needs a major rewrite due to their convoluted structure.
As in_interrupt() usage in drivers needs to be phased out, provide
netif_rx_any_context() as a stop gap for these drivers.
This confines the in_interrupt() conditional to core code which in turn
allows to remove the access to this check for driver code and provides one
central place to do further modifications once the driver maze is cleaned
up.
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
When an L2TPv3 session receives a data frame with an incorrect cookie
l2tp_core logs a warning message and bumps a stats counter to reflect
the fact that the packet has been dropped.
However, the stats counter in question is missing from the l2tp_netlink
get message for tunnel and session instances.
Include the statistic in the netlink get response.
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Johan Hedberg says:
====================
pull request: bluetooth-next 2020-09-29
Here's the main bluetooth-next pull request for 5.10:
- Multiple fixes to suspend/resume handling
- Added mgmt events for controller suspend/resume state
- Improved extended advertising support
- btintel: Enhanced support for next generation controllers
- Added Qualcomm Bluetooth SoC WCN6855 support
- Several other smaller fixes & improvements
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
