linux.git/net/core/sysctl_net_core.c, branch v7.1 Linux kernel source tree net: add skb_defer_disable_key static key 2026-03-13T02:25:33+00:00 Eric Dumazet edumazet@google.com 2026-03-11T19:13:40+00:00 08dc30de1a402fe88fd80592cf6c72c4c2ebbcbc Add a static key to bypass skb_attempt_defer_free() steps if net.core.skb_defer_max is set to zero. Main benefit is the atomic_long_inc_return() avoidance. Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://patch.msgid.link/20260311191340.1996888-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
Add a static key to bypass skb_attempt_defer_free() steps
if net.core.skb_defer_max is set to zero.

Main benefit is the atomic_long_inc_return() avoidance.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260311191340.1996888-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net-sysfs: use rps_tag_ptr and remove metadata from rps_sock_flow_table 2026-03-05T00:54:09+00:00 Eric Dumazet edumazet@google.com 2026-03-02T18:14:29+00:00 dd378109d20ff6789091fa3558607c1d242d80ad Instead of storing the @mask at the beginning of rps_sock_flow_table, use 5 low order bits of the rps_tag_ptr to store the log of the size. This removes a potential cache line miss to fetch @mask. More importantly, we can switch to vmalloc_huge() without wasting memory. Tested with: numactl --interleave=all bash -c "echo 4194304 >/proc/sys/net/core/rps_sock_flow_entries" Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com> Link: https://patch.msgid.link/20260302181432.1836150-5-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
Instead of storing the @mask at the beginning of rps_sock_flow_table,
use 5 low order bits of the rps_tag_ptr to store the log of the size.

This removes a potential cache line miss to fetch @mask.

More importantly, we can switch to vmalloc_huge() without wasting memory.

Tested with:

numactl --interleave=all bash -c "echo 4194304 >/proc/sys/net/core/rps_sock_flow_entries"

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260302181432.1836150-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net-sysfs: add rps_sock_flow_table_mask() helper 2026-03-05T00:54:09+00:00 Eric Dumazet edumazet@google.com 2026-03-02T18:14:28+00:00 9cde131cdd888873363b5d9dfd8d4d4c1fae6986 In preparation of the following patch, abstract access to the @mask field in 'struct rps_sock_flow_table'. Also cleanup rps_sock_flow_sysctl() a bit : - Rename orig_sock_table to o_sock_table. Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com> Link: https://patch.msgid.link/20260302181432.1836150-4-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
In preparation of the following patch, abstract access
to the @mask field in 'struct rps_sock_flow_table'.

Also cleanup rps_sock_flow_sysctl() a bit :

- Rename orig_sock_table to o_sock_table.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260302181432.1836150-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net-sysfs: remove rcu field from 'struct rps_sock_flow_table' 2026-03-05T00:54:09+00:00 Eric Dumazet edumazet@google.com 2026-03-02T18:14:27+00:00 61753849b8bc6420cc5834fb3de331ce1134060d Removing rcu_head (and @mask in a following patch) will allow a power-of-two allocation and thus high-order allocation for better performance. Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com> Link: https://patch.msgid.link/20260302181432.1836150-3-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
Removing rcu_head (and @mask in a following patch)
will allow a power-of-two allocation and thus high-order
allocation for better performance.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260302181432.1836150-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net: include <linux/hex.h> from sysctl_net_core.c 2026-01-27T00:35:53+00:00 Eric Dumazet edumazet@google.com 2026-01-26T17:47:31+00:00 3da35aa8af345abf6cd180cfc0538c753b927a18 Needed for hex_byte_pack(). x86_64 was already including it, but some arches were not. Fixes: 37b0ea8fef56 ("net: expand NETDEV_RSS_KEY_LEN to 256 bytes") Reported-by: Mark Brown <broonie@kernel.org> Closes: https://lore.kernel.org/netdev/aXeka0KYBnrkwUcF@sirena.org.uk/ Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://patch.msgid.link/20260126174731.2767372-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
Needed for hex_byte_pack().

x86_64 was already including it, but some arches were not.

Fixes: 37b0ea8fef56 ("net: expand NETDEV_RSS_KEY_LEN to 256 bytes")
Reported-by: Mark Brown <broonie@kernel.org>
Closes: https://lore.kernel.org/netdev/aXeka0KYBnrkwUcF@sirena.org.uk/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260126174731.2767372-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net: expand NETDEV_RSS_KEY_LEN to 256 bytes 2026-01-25T21:20:46+00:00 Eric Dumazet edumazet@google.com 2026-01-22T19:03:49+00:00 37b0ea8fef56ccc29bd5a07f235ac218f7f98379 NETDEV_RSS_KEY_LEN has been set to 52 bytes in 2014, until now. Jakub suggested we bump the size to 128 bytes or more. Some drivers (like idpf) were already working around the core limit. Since this change might cause some issues in admin scripts, bump it directly to 256 in one go. tjbp26:~# cat /proc/sys/net/core/netdev_rss_key | wc -c 768 tjbp26:~# ethtool -x eth1 RX flow hash indirection table for eth1 with 32 RX ring(s): ... RSS hash key: fe:16:5b:2f:93:85:c2:c9:c1:ef:bd:60:c6:e0:2b:99:4d:bf:b7:14:c8:1e:8d:cb:31:17:51:da:55:eb:91:d9:9e:f9:89:9b:44:a1:dc:08:72:3a:b3:d6:31:86:9a:fe:02:3a:0d:eb:a1:7c:f5:a3:51:3b:08:56:c9:3f:71:69:01:ba:70:38 RSS hash function: toeplitz: on xor: off crc32: off Suggested-by: Jakub Kicinski <kuba@kernel.org> Link: https://lore.kernel.org/netdev/20260122075206.504ec591@kernel.org/ Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Link: https://patch.msgid.link/20260122190349.2771064-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
NETDEV_RSS_KEY_LEN has been set to 52 bytes in 2014, until now.

Jakub suggested we bump the size to 128 bytes or more.

Some drivers (like idpf) were already working around the core limit.

Since this change might cause some issues in admin scripts,
bump it directly to 256 in one go.

tjbp26:~# cat /proc/sys/net/core/netdev_rss_key | wc -c
768

tjbp26:~# ethtool -x eth1
RX flow hash indirection table for eth1 with 32 RX ring(s):
...
RSS hash key:
fe:16:5b:2f:93:85:c2:c9:c1:ef:bd:60:c6:e0:2b:99:4d:bf:b7:14:c8:1e:8d:cb:31:17:51:da:55:eb:91:d9:9e:f9:89:9b:44:a1:dc:08:72:3a:b3:d6:31:86:9a:fe:02:3a:0d:eb:a1:7c:f5:a3:51:3b:08:56:c9:3f:71:69:01:ba:70:38
RSS hash function:
    toeplitz: on
    xor: off
    crc32: off

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/netdev/20260122075206.504ec591@kernel.org/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20260122190349.2771064-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net: add net.core.qdisc_max_burst 2026-01-13T09:12:11+00:00 Eric Dumazet edumazet@google.com 2026-01-07T10:41:59+00:00 ffe4ccd359d006eba559cb1a3c6113144b7fb38c In blamed commit, I added a check against the temporary queue built in __dev_xmit_skb(). Idea was to drop packets early, before any spinlock was acquired. if (unlikely(defer_count > READ_ONCE(q->limit))) { kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_DROP); return NET_XMIT_DROP; } It turned out that HTB Qdisc has a zero q->limit. HTB limits packets on a per-class basis. Some of our tests became flaky. Add a new sysctl : net.core.qdisc_max_burst to control how many packets can be stored in the temporary lockless queue. Also add a new QDISC_BURST_DROP drop reason to better diagnose future issues. Thanks Neal ! Fixes: 100dfa74cad9 ("net: dev_queue_xmit() llist adoption") Reported-and-bisected-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Neal Cardwell <ncardwell@google.com> Link: https://patch.msgid.link/20260107104159.3669285-1-edumazet@google.com Signed-off-by: Paolo Abeni <pabeni@redhat.com> 
In blamed commit, I added a check against the temporary queue
built in __dev_xmit_skb(). Idea was to drop packets early,
before any spinlock was acquired.

if (unlikely(defer_count > READ_ONCE(q->limit))) {
	kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_DROP);
	return NET_XMIT_DROP;
}

It turned out that HTB Qdisc has a zero q->limit.
HTB limits packets on a per-class basis.
Some of our tests became flaky.

Add a new sysctl : net.core.qdisc_max_burst to control
how many packets can be stored in the temporary lockless queue.

Also add a new QDISC_BURST_DROP drop reason to better diagnose
future issues.

Thanks Neal !

Fixes: 100dfa74cad9 ("net: dev_queue_xmit() llist adoption")
Reported-and-bisected-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Link: https://patch.msgid.link/20260107104159.3669285-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
net: Introduce net.core.bypass_prot_mem sysctl. 2025-10-16T19:04:47+00:00 Kuniyuki Iwashima kuniyu@google.com 2025-10-14T23:54:56+00:00 b46ab63181ff973ddce44ebc9ac24b269d42f481 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 
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
net: add /proc/sys/net/core/txq_reselection_ms control 2025-10-15T16:04:21+00:00 Eric Dumazet edumazet@google.com 2025-10-13T15:22:33+00:00 2ddef3462b3a5d62e5485e22ce128a5c02276438 Add a new sysctl to control how often a queue reselection can happen even if a flow has a persistent queue of skbs in a Qdisc or NIC queue. A value of zero means the feature is disabled. Default is 1000 (1 second). This sysctl is used in the following patch. Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Neal Cardwell <ncardwell@google.com> Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com> Link: https://patch.msgid.link/20251013152234.842065-4-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
Add a new sysctl to control how often a queue reselection
can happen even if a flow has a persistent queue of skbs
in a Qdisc or NIC queue.

A value of zero means the feature is disabled.

Default is 1000 (1 second).

This sysctl is used in the following patch.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251013152234.842065-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net: remove RTNL use for /proc/sys/net/core/rps_default_mask 2025-07-08T01:42:12+00:00 Eric Dumazet edumazet@google.com 2025-07-02T06:15:58+00:00 6058099da5e5eb057751905e587328affb93a81a Use a dedicated mutex instead. Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com> Link: https://patch.msgid.link/20250702061558.1585870-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
Use a dedicated mutex instead.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250702061558.1585870-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>