kernel/linux.git/net/sched/sch_api.c, branch v7.2-rc2

net/sched: prefer existing extack message in qdisc_offload_graft_helper()

2026-05-23T00:23:37+00:00

Use NL_SET_ERR_MSG_WEAK so any existing error message (probably from the underlying driver) is used instead of the generic fallback. Signed-off-by: David Yang Link: https://patch.msgid.link/20260521010320.208138-2-mmyangfl@gmail.com Signed-off-by: Jakub Kicinski

net/sched: annotate data-races around sch->qstats.backlog

2026-05-12T01:28:07+00:00

Add qstats_backlog_sub() and qstats_backlog_add() helpers and use them instead of open-coding them. These helpers use WRITE_ONCE() to prevent store-tearing. Also use WRITE_ONCE() in fq_reset() and qdisc_reset() when sch->qstats.backlog is cleared. Signed-off-by: Eric Dumazet Acked-by: Toke Høiland-Jørgensen Link: https://patch.msgid.link/20260510091455.4039245-4-edumazet@google.com Signed-off-by: Jakub Kicinski

net/sched: add qdisc_qlen_inc() and qdisc_qlen_dec()

2026-05-12T01:28:07+00:00

Helpers to increment or decrement sch->q.qlen, with appropriate WRITE_ONCE() to prevent store tearing. Add other WRITE_ONCE() when sch->q.qlen is changed. Signed-off-by: Eric Dumazet Acked-by: Toke Høiland-Jørgensen Link: https://patch.msgid.link/20260510091455.4039245-3-edumazet@google.com Signed-off-by: Jakub Kicinski

net/sched: speedup tc_dump_qdisc() when tcm_handle is provided

2026-05-05T02:32:19+00:00

"tc qdisc show ... handle xxx" filtering can be done by the kernel. A followup patch can do the same for tcm_parent. iproute2/tc needs a small companion patch. Signed-off-by: Eric Dumazet Reviewed-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260503114515.2460477-1-edumazet@google.com Signed-off-by: Jakub Kicinski

net/sched: speedup tc_dump_qdisc() when tcm_ifindex is provided

2026-05-01T03:54:27+00:00

There is no point dumping qdiscs for all devices when user space wants them for a single device: tc -s -d qdisc show dev eth1 Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260430023628.3216283-5-edumazet@google.com Signed-off-by: Jakub Kicinski

net/sched: switch tc_dump_qdisc() to for_each_netdev_dump()

2026-05-01T03:54:27+00:00

Use for_each_netdev_dump() instead of for_each_netdev(). This is more scalable, and will ease RCU conversion. This also offer better behavior when other threads are adding or deleting netevices concurrently. This enables dumping qdiscs for a single device at user space request in the following patch. Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260430023628.3216283-4-edumazet@google.com Signed-off-by: Jakub Kicinski

net/sched: tc_dump_qdisc_root() refactor

2026-05-01T03:54:27+00:00

Change tc_fill_qdisc() to return -EMSGSIZE when skb is too small. Change tc_dump_qdisc_root() to propagate tc_fill_qdisc() error to its callers. Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260430023628.3216283-3-edumazet@google.com Signed-off-by: Jakub Kicinski

net/sched: propagate tc_fill_tclass() error

2026-05-01T03:54:27+00:00

Change tc_fill_tclass() to return -EMSGSIZE when skb is too small. Change its caller to propagate this error (instead of -EINVAL) Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260430023628.3216283-2-edumazet@google.com Signed-off-by: Jakub Kicinski

net/sched: refine indirect call mitigation in tc_wrapper.h

2026-03-10T02:31:41+00:00

Some modern cpus disable X86_FEATURE_RETPOLINE feature, even if a direct call can still be beneficial. Even when IBRS is present, an indirect call is more expensive than a direct one: Direct Calls: Compilers can perform powerful optimizations like inlining, where the function body is directly inserted at the call site, eliminating call overhead entirely. Indirect Calls: Inlining is much harder, if not impossible, because the compiler doesn't know the target function at compile time. Techniques like Indirect Call Promotion can help by using profile-guided optimization to turn frequently taken indirect calls into conditional direct calls, but they still add complexity and potential overhead compared to a truly direct call. In this patch, I split tc_skip_wrapper in two different static keys, one for tc_act() (tc_skip_wrapper_act) and one for tc_classify() (tc_skip_wrapper_cls). Then I enable the tc_skip_wrapper_cls only if the count of builtin classifiers is above one. I enable tc_skip_wrapper_act only it the count of builtin actions is above one. In our production kernels, we only have CONFIG_NET_CLS_BPF=y and CONFIG_NET_ACT_BPF=y. Other are modules or are not compiled. Tested on AMD Turin cpus, cls_bpf_classify() cost went from 1% down to 0.18 %, and FDO will be able to inline it in tcf_classify() for further gains. Signed-off-by: Eric Dumazet Acked-by: Jamal Hadi Salim Reviewed-by: Pedro Tammela Reviewed-by: Victor Nogueira Link: https://patch.msgid.link/20260307133601.3863071-1-edumazet@google.com Signed-off-by: Jakub Kicinski

net/sched: do not reset queues in graft operations

2026-03-10T01:55:55+00:00

Following typical script is extremely disruptive, because each graft operation calls dev_deactivate() which resets all the queues of the device. QPARAM="limit 100000 flow_limit 1000 buckets 4096" TXQS=64 for ETH in eth1 do tc qd del dev $ETH root 2>/dev/null tc qd add dev $ETH root handle 1: mq for i in `seq 1 $TXQS` do slot=$( printf %x $(( i )) ) tc qd add dev $ETH parent 1:$slot fq $QPARAM done done One can add "ip link set dev $ETH down/up" to reduce the disruption time: QPARAM="limit 100000 flow_limit 1000 buckets 4096" TXQS=64 for ETH in eth1 do ip link set dev $ETH down tc qd del dev $ETH root 2>/dev/null tc qd add dev $ETH root handle 1: mq for i in `seq 1 $TXQS` do slot=$( printf %x $(( i )) ) tc qd add dev $ETH parent 1:$slot fq $QPARAM done ip link set dev $ETH up done Or we can add a @reset_needed flag to dev_deactivate() and dev_deactivate_many(). This flag is set to true at device dismantle or linkwatch_do_dev(), and to false for graft operations. In the future, we might only stop one queue instead of the whole device, ie call dev_deactivate_queue() instead of dev_deactivate(). I think the problem (quadratic behavior) was added in commit 2fb541c862c9 ("net: sch_generic: aviod concurrent reset and enqueue op for lockless qdisc") but this does not look serious enough to deserve risky backports. Signed-off-by: Eric Dumazet Cc: Yunsheng Lin Reviewed-by: Jamal Hadi Salim Reviewed-by: Toke Høiland-Jørgensen Reviewed-by: Victor Nogueira Link: https://patch.msgid.link/20260307163430.470644-1-edumazet@google.com Signed-off-by: Jakub Kicinski