kernel/linux.git/net/sched/sch_api.c, branch v7.1

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

Convert 'alloc_flex' family to use the new default GFP_KERNEL argument

2026-02-22T01:09:51+00:00

This is the exact same thing as the 'alloc_obj()' version, only much smaller because there are a lot fewer users of the *alloc_flex() interface. As with alloc_obj() version, this was done entirely with mindless brute force, using the same script, except using 'flex' in the pattern rather than 'objs*'. Signed-off-by: Linus Torvalds

Convert 'alloc_obj' family to use the new default GFP_KERNEL argument

2026-02-22T01:09:51+00:00

This was done entirely with mindless brute force, using git grep -l '\

treewide: Replace kmalloc with kmalloc_obj for non-scalar types

2026-02-21T09:02:28+00:00

This is the result of running the Coccinelle script from scripts/coccinelle/api/kmalloc_objs.cocci. The script is designed to avoid scalar types (which need careful case-by-case checking), and instead replace kmalloc-family calls that allocate struct or union object instances: Single allocations: kmalloc(sizeof(TYPE), ...) are replaced with: kmalloc_obj(TYPE, ...) Array allocations: kmalloc_array(COUNT, sizeof(TYPE), ...) are replaced with: kmalloc_objs(TYPE, COUNT, ...) Flex array allocations: kmalloc(struct_size(PTR, FAM, COUNT), ...) are replaced with: kmalloc_flex(*PTR, FAM, COUNT, ...) (where TYPE may also be *VAR) The resulting allocations no longer return "void *", instead returning "TYPE *". Signed-off-by: Kees Cook

net/sched: don't use dynamic lockdep keys with clsact/ingress/noqueue

2026-02-05T17:32:45+00:00

Currently we are registering one dynamic lockdep key for each allocated qdisc, to avoid false deadlock reports when mirred (or TC eBPF) redirects packets to another device while the root lock is acquired [1]. Since dynamic keys are a limited resource, we can save them at least for qdiscs that are not meant to acquire the root lock in the traffic path, or to carry traffic at all, like: - clsact - ingress - noqueue Don't register dynamic keys for the above schedulers, so that we hit MAX_LOCKDEP_KEYS later in our tests. [1] https://github.com/multipath-tcp/mptcp_net-next/issues/451 Changes in v2: - change ordering of spin_lock_init() vs. lockdep_register_key() (Jakub Kicinski) Signed-off-by: Davide Caratti Link: https://patch.msgid.link/94448f7fa7c4f52d2ce416a4895ec87d456d7417.1770220576.git.dcaratti@redhat.com Signed-off-by: Jakub Kicinski

net/sched: Abort __tc_modify_qdisc if parent is a clsact/ingress qdisc

2025-11-11T00:57:56+00:00

Wang reported an illegal configuration [1] where the user attempts to add a child qdisc to the ingress qdisc as follows: tc qdisc add dev eth0 handle ffff:0 ingress tc qdisc add dev eth0 handle ffe0:0 parent ffff:a fq To solve this, we reject any configuration attempt to add a child qdisc to ingress or clsact. [1] https://lore.kernel.org/netdev/20251105022213.1981982-1-wangliang74@huawei.com/ Fixes: 5e50da01d0ce ("[NET_SCHED]: Fix endless loops (part 2): "simple" qdiscs") Reported-by: Wang Liang Closes: https://lore.kernel.org/netdev/20251105022213.1981982-1-wangliang74@huawei.com/ Reviewed-by: Pedro Tammela Acked-by: Jamal Hadi Salim Signed-off-by: Victor Nogueira Reviewed-by: Cong Wang Link: https://patch.msgid.link/20251106205621.3307639-1-victor@mojatatu.com Signed-off-by: Jakub Kicinski

net/sched: Use TC_RTAB_SIZE instead of magic number

2025-08-15T00:37:48+00:00

Replace magic number with TC_RTAB_SIZE to make it more informative. Signed-off-by: Yue Haibing Link: https://patch.msgid.link/20250813125526.853895-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski

net/sched: sch_qfq: Fix null-deref in agg_dequeue

2025-07-10T09:08:35+00:00

To prevent a potential crash in agg_dequeue (net/sched/sch_qfq.c) when cl->qdisc->ops->peek(cl->qdisc) returns NULL, we check the return value before using it, similar to the existing approach in sch_hfsc.c. To avoid code duplication, the following changes are made: 1. Changed qdisc_warn_nonwc(include/net/pkt_sched.h) into a static inline function. 2. Moved qdisc_peek_len from net/sched/sch_hfsc.c to include/net/pkt_sched.h so that sch_qfq can reuse it. 3. Applied qdisc_peek_len in agg_dequeue to avoid crashing. Signed-off-by: Xiang Mei Reviewed-by: Cong Wang Link: https://patch.msgid.link/20250705212143.3982664-1-xmei5@asu.edu Signed-off-by: Paolo Abeni

net/sched: Abort __tc_modify_qdisc if parent class does not exist

2025-07-10T02:23:25+00:00

Lion's patch [1] revealed an ancient bug in the qdisc API. Whenever a user creates/modifies a qdisc specifying as a parent another qdisc, the qdisc API will, during grafting, detect that the user is not trying to attach to a class and reject. However grafting is performed after qdisc_create (and thus the qdiscs' init callback) is executed. In qdiscs that eventually call qdisc_tree_reduce_backlog during init or change (such as fq, hhf, choke, etc), an issue arises. For example, executing the following commands: sudo tc qdisc add dev lo root handle a: htb default 2 sudo tc qdisc add dev lo parent a: handle beef fq Qdiscs such as fq, hhf, choke, etc unconditionally invoke qdisc_tree_reduce_backlog() in their control path init() or change() which then causes a failure to find the child class; however, that does not stop the unconditional invocation of the assumed child qdisc's qlen_notify with a null class. All these qdiscs make the assumption that class is non-null. The solution is ensure that qdisc_leaf() which looks up the parent class, and is invoked prior to qdisc_create(), should return failure on not finding the class. In this patch, we leverage qdisc_leaf to return ERR_PTRs whenever the parentid doesn't correspond to a class, so that we can detect it earlier on and abort before qdisc_create is called. [1] https://lore.kernel.org/netdev/d912cbd7-193b-4269-9857-525bee8bbb6a@gmail.com/ Fixes: 5e50da01d0ce ("[NET_SCHED]: Fix endless loops (part 2): "simple" qdiscs") Reported-by: syzbot+d8b58d7b0ad89a678a16@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/68663c93.a70a0220.5d25f.0857.GAE@google.com/ Reported-by: syzbot+5eccb463fa89309d8bdc@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/68663c94.a70a0220.5d25f.0858.GAE@google.com/ Reported-by: syzbot+1261670bbdefc5485a06@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/686764a5.a00a0220.c7b3.0013.GAE@google.com/ Reported-by: syzbot+15b96fc3aac35468fe77@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/686764a5.a00a0220.c7b3.0014.GAE@google.com/ Reported-by: syzbot+4dadc5aecf80324d5a51@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/68679e81.a70a0220.29cf51.0016.GAE@google.com/ Acked-by: Jamal Hadi Salim Reviewed-by: Cong Wang Signed-off-by: Victor Nogueira Link: https://patch.msgid.link/20250707210801.372995-1-victor@mojatatu.com Signed-off-by: Jakub Kicinski