linux/include/net/netns
Kuniyuki Iwashima b46ab63181 net: Introduce net.core.bypass_prot_mem sysctl.
If a socket has sk->sk_bypass_prot_mem flagged, the socket opts out
of the global protocol memory accounting.

Let's control the flag by a new sysctl knob.

The flag is written once during socket(2) and is inherited to child
sockets.

Tested with a script that creates local socket pairs and send()s a
bunch of data without recv()ing.

Setup:

  # mkdir /sys/fs/cgroup/test
  # echo $$ >> /sys/fs/cgroup/test/cgroup.procs
  # sysctl -q net.ipv4.tcp_mem="1000 1000 1000"
  # ulimit -n 524288

Without net.core.bypass_prot_mem, charged to tcp_mem & memcg

  # python3 pressure.py &
  # cat /sys/fs/cgroup/test/memory.stat | grep sock
  sock 22642688 <-------------------------------------- charged to memcg
  # cat /proc/net/sockstat| grep TCP
  TCP: inuse 2006 orphan 0 tw 0 alloc 2008 mem 5376 <-- charged to tcp_mem
  # ss -tn | head -n 5
  State Recv-Q Send-Q Local Address:Port  Peer Address:Port
  ESTAB 2000   0          127.0.0.1:34479    127.0.0.1:53188
  ESTAB 2000   0          127.0.0.1:34479    127.0.0.1:49972
  ESTAB 2000   0          127.0.0.1:34479    127.0.0.1:53868
  ESTAB 2000   0          127.0.0.1:34479    127.0.0.1:53554
  # nstat | grep Pressure || echo no pressure
  TcpExtTCPMemoryPressures        1                  0.0

With net.core.bypass_prot_mem=1, charged to memcg only:

  # sysctl -q net.core.bypass_prot_mem=1
  # python3 pressure.py &
  # cat /sys/fs/cgroup/test/memory.stat | grep sock
  sock 2757468160 <------------------------------------ charged to memcg
  # cat /proc/net/sockstat | grep TCP
  TCP: inuse 2006 orphan 0 tw 0 alloc 2008 mem 0 <- NOT charged to tcp_mem
  # ss -tn | head -n 5
  State Recv-Q Send-Q  Local Address:Port  Peer Address:Port
  ESTAB 111000 0           127.0.0.1:36019    127.0.0.1:49026
  ESTAB 110000 0           127.0.0.1:36019    127.0.0.1:45630
  ESTAB 110000 0           127.0.0.1:36019    127.0.0.1:44870
  ESTAB 111000 0           127.0.0.1:36019    127.0.0.1:45274
  # nstat | grep Pressure || echo no pressure
  no pressure

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-4-kuniyu@google.com
History 2025-10-16 12:04:47 -07:00
..
bpf.h bpf: Invert the dependency between bpf-netns.h and netns/bpf.h 2021-12-29 20:03:05 -08:00
can.h net: add missing includes and forward declarations under net/ 2022-07-22 12:53:22 +01:00
conntrack.h netfilter: conntrack: remove DCCP protocol support 2025-07-03 13:51:39 +02:00
core.h net: Introduce net.core.bypass_prot_mem sysctl. 2025-10-16 12:04:47 -07:00
flow_table.h netfilter: nf_flow_table: count pending offload workqueue tasks 2022-07-11 16:25:14 +02:00
generic.h netns: Replace zero-length array with DECLARE_FLEX_ARRAY() helper 2022-09-28 18:51:47 -07:00
hash.h netns: provide pure entropy for net_hash_mix() 2019-03-28 17:00:45 -07:00
ieee802154_6lowpan.h net: dynamically allocate fqdir structures 2019-05-26 14:08:05 -07:00
ipv4.h tcp: accecn: AccECN option send control 2025-09-18 08:47:52 +02:00
ipv6.h ipv6: Protect fib6_link_table() with spinlock. 2025-04-24 09:29:56 +02:00
mctp.h net: mctp: Use hashtable for binds 2025-07-15 12:08:39 +02:00
mib.h net: reorganize fields in netns_mib 2021-04-02 14:31:44 -07:00
mpls.h net: add missing includes and forward declarations under net/ 2022-07-22 12:53:22 +01:00
netfilter.h netfilter: move the sysctl nf_hooks_lwtunnel into the netfilter core 2024-06-19 18:41:59 +02:00
nexthop.h net: add missing includes and forward declarations under net/ 2022-07-22 12:53:22 +01:00
nftables.h netfilter: nf_tables: place base_seq in struct net 2025-09-10 20:30:37 +02:00
packet.h License cleanup: add SPDX GPL-2.0 license identifier to files with no license 2017-11-02 11:10:55 +01:00
sctp.h sctp: Convert cookie authentication to use HMAC-SHA256 2025-08-19 19:36:26 -07:00
smc.h net/smc: add sysctl for max conns per lgr for SMC-R v2.1 2023-11-24 12:13:14 +00:00
unix.h net: add missing includes and forward declarations under net/ 2022-07-22 12:53:22 +01:00
xdp.h net: xsk: Don't include <linux/rculist.h> 2022-12-06 20:04:34 -08:00
xfrm.h xfrm: Add an inbound percpu state cache. 2024-10-29 11:56:18 +01:00