From 64fdaa94bfe0cca3a0f4b2dd922486c5f59fe678 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 4 Aug 2025 17:36:54 -0700 Subject: net: page_pool: allow enabling recycling late, fix false positive warning Page pool can have pages "directly" (locklessly) recycled to it, if the NAPI that owns the page pool is scheduled to run on the same CPU. To make this safe we check that the NAPI is disabled while we destroy the page pool. In most cases NAPI and page pool lifetimes are tied together so this happens naturally. The queue API expects the following order of calls: -> mem_alloc alloc new pp -> stop napi_disable -> start napi_enable -> mem_free free old pp Here we allocate the page pool in ->mem_alloc and free in ->mem_free. But the NAPIs are only stopped between ->stop and ->start. We created page_pool_disable_direct_recycling() to safely shut down the recycling in ->stop. This way the page_pool_destroy() call in ->mem_free doesn't have to worry about recycling any more. Unfortunately, the page_pool_disable_direct_recycling() is not enough to deal with failures which necessitate freeing the _new_ page pool. If we hit a failure in ->mem_alloc or ->stop the new page pool has to be freed while the NAPI is active (assuming driver attaches the page pool to an existing NAPI instance and doesn't reallocate NAPIs). Freeing the new page pool is technically safe because it hasn't been used for any packets, yet, so there can be no recycling. But the check in napi_assert_will_not_race() has no way of knowing that. We could check if page pool is empty but that'd make the check much less likely to trigger during development. Add page_pool_enable_direct_recycling(), pairing with page_pool_disable_direct_recycling(). It will allow us to create the new page pools in "disabled" state and only enable recycling when we know the reconfig operation will not fail. Coincidentally it will also let us re-enable the recycling for the old pool, if the reconfig failed: -> mem_alloc (new) -> stop (old) # disables direct recycling for old -> start (new) # fail!! -> start (old) # go back to old pp but direct recycling is lost :( -> mem_free (new) The new helper is idempotent to make the life easier for drivers, which can operate in HDS mode and support zero-copy Rx. The driver can call the helper twice whether there are two pools or it has multiple references to a single pool. Fixes: 40eca00ae605 ("bnxt_en: unlink page pool when stopping Rx queue") Tested-by: David Wei Link: https://patch.msgid.link/20250805003654.2944974-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/net/page_pool/types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 431b593de709..1509a536cb85 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -265,6 +265,8 @@ struct page_pool *page_pool_create_percpu(const struct page_pool_params *params, struct xdp_mem_info; #ifdef CONFIG_PAGE_POOL +void page_pool_enable_direct_recycling(struct page_pool *pool, + struct napi_struct *napi); void page_pool_disable_direct_recycling(struct page_pool *pool); void page_pool_destroy(struct page_pool *pool); void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), -- cgit v1.2.3 From c5ec7f49b480db0dfc83f395755b1c2a7c979920 Mon Sep 17 00:00:00 2001 From: Jedrzej Jagielski Date: Fri, 4 Jul 2025 13:17:47 +0200 Subject: devlink: let driver opt out of automatic phys_port_name generation Currently when adding devlink port, phys_port_name is automatically generated within devlink port initialization flow. As a result adding devlink port support to driver may result in forced changes of interface names, which breaks already existing network configs. This is an expected behavior but in some scenarios it would not be preferable to provide such limitation for legacy driver not being able to keep 'pre-devlink' interface name. Add flag no_phys_port_name to devlink_port_attrs struct which indicates if devlink should not alter name of interface. Suggested-by: Jiri Pirko Link: https://lore.kernel.org/all/nbwrfnjhvrcduqzjl4a2jafnvvud6qsbxlvxaxilnryglf4j7r@btuqrimnfuly/ Signed-off-by: Jedrzej Jagielski Signed-off-by: Tony Nguyen --- include/net/devlink.h | 6 +++++- net/devlink/port.c | 2 +- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/devlink.h b/include/net/devlink.h index 93640a29427c..b32c9ceeb81d 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -78,6 +78,9 @@ struct devlink_port_pci_sf_attrs { * @flavour: flavour of the port * @split: indicates if this is split port * @splittable: indicates if the port can be split. + * @no_phys_port_name: skip automatic phys_port_name generation; for + * compatibility only, newly added driver/port instance + * should never set this. * @lanes: maximum number of lanes the port supports. 0 value is not passed to netlink. * @switch_id: if the port is part of switch, this is buffer with ID, otherwise this is NULL * @phys: physical port attributes @@ -87,7 +90,8 @@ struct devlink_port_pci_sf_attrs { */ struct devlink_port_attrs { u8 split:1, - splittable:1; + splittable:1, + no_phys_port_name:1; u32 lanes; enum devlink_port_flavour flavour; struct netdev_phys_item_id switch_id; diff --git a/net/devlink/port.c b/net/devlink/port.c index 939081a0e615..cb8d4df61619 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -1519,7 +1519,7 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, struct devlink_port_attrs *attrs = &devlink_port->attrs; int n = 0; - if (!devlink_port->attrs_set) + if (!devlink_port->attrs_set || devlink_port->attrs.no_phys_port_name) return -EOPNOTSUPP; switch (attrs->flavour) { -- cgit v1.2.3 From c0a23bbc98e93704a1f4fb5e7e7bb2d7c0fb6eb3 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 29 Jul 2025 14:26:11 +0200 Subject: ipvs: Fix estimator kthreads preferred affinity The estimator kthreads' affinity are defined by sysctl overwritten preferences and applied through a plain call to the scheduler's affinity API. However since the introduction of managed kthreads preferred affinity, such a practice shortcuts the kthreads core code which eventually overwrites the target to the default unbound affinity. Fix this with using the appropriate kthread's API. Fixes: d1a89197589c ("kthread: Default affine kthread to its preferred NUMA node") Signed-off-by: Frederic Weisbecker Acked-by: Julian Anastasov Signed-off-by: Florian Westphal --- include/net/ip_vs.h | 13 +++++++++++++ kernel/kthread.c | 1 + net/netfilter/ipvs/ip_vs_est.c | 3 ++- 3 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index ff406ef4fd4a..29a36709e7f3 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1163,6 +1163,14 @@ static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs) return housekeeping_cpumask(HK_TYPE_KTHREAD); } +static inline const struct cpumask *sysctl_est_preferred_cpulist(struct netns_ipvs *ipvs) +{ + if (ipvs->est_cpulist_valid) + return ipvs->sysctl_est_cpulist; + else + return NULL; +} + static inline int sysctl_est_nice(struct netns_ipvs *ipvs) { return ipvs->sysctl_est_nice; @@ -1270,6 +1278,11 @@ static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs) return housekeeping_cpumask(HK_TYPE_KTHREAD); } +static inline const struct cpumask *sysctl_est_preferred_cpulist(struct netns_ipvs *ipvs) +{ + return NULL; +} + static inline int sysctl_est_nice(struct netns_ipvs *ipvs) { return IPVS_EST_NICE; diff --git a/kernel/kthread.c b/kernel/kthread.c index 0e98b228a8ef..31b072e8d427 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -893,6 +893,7 @@ out: return ret; } +EXPORT_SYMBOL_GPL(kthread_affine_preferred); /* * Re-affine kthreads according to their preferences diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index f821ad2e19b3..15049b826732 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -265,7 +265,8 @@ int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, } set_user_nice(kd->task, sysctl_est_nice(ipvs)); - set_cpus_allowed_ptr(kd->task, sysctl_est_cpulist(ipvs)); + if (sysctl_est_preferred_cpulist(ipvs)) + kthread_affine_preferred(kd->task, sysctl_est_preferred_cpulist(ipvs)); pr_info("starting estimator thread %d...\n", kd->id); wake_up_process(kd->task); -- cgit v1.2.3 From 52565a935213cd6a8662ddb8efe5b4219343a25d Mon Sep 17 00:00:00 2001 From: Sven Stegemann Date: Tue, 12 Aug 2025 21:18:03 +0200 Subject: net: kcm: Fix race condition in kcm_unattach() syzbot found a race condition when kcm_unattach(psock) and kcm_release(kcm) are executed at the same time. kcm_unattach() is missing a check of the flag kcm->tx_stopped before calling queue_work(). If the kcm has a reserved psock, kcm_unattach() might get executed between cancel_work_sync() and unreserve_psock() in kcm_release(), requeuing kcm->tx_work right before kcm gets freed in kcm_done(). Remove kcm->tx_stopped and replace it by the less error-prone disable_work_sync(). Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module") Reported-by: syzbot+e62c9db591c30e174662@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=e62c9db591c30e174662 Reported-by: syzbot+d199b52665b6c3069b94@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=d199b52665b6c3069b94 Reported-by: syzbot+be6b1fdfeae512726b4e@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=be6b1fdfeae512726b4e Signed-off-by: Sven Stegemann Link: https://patch.msgid.link/20250812191810.27777-1-sven@stegemann.de Signed-off-by: Jakub Kicinski --- include/net/kcm.h | 1 - net/kcm/kcmsock.c | 10 ++-------- 2 files changed, 2 insertions(+), 9 deletions(-) (limited to 'include/net') diff --git a/include/net/kcm.h b/include/net/kcm.h index 441e993be634..d9c35e71ecea 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -71,7 +71,6 @@ struct kcm_sock { struct list_head wait_psock_list; struct sk_buff *seq_skb; struct mutex tx_mutex; - u32 tx_stopped : 1; /* Don't use bit fields here, these are set under different locks */ bool tx_wait; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index a4971e6fa943..b4f01cb07561 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -430,7 +430,7 @@ static void psock_write_space(struct sock *sk) /* Check if the socket is reserved so someone is waiting for sending. */ kcm = psock->tx_kcm; - if (kcm && !unlikely(kcm->tx_stopped)) + if (kcm) queue_work(kcm_wq, &kcm->tx_work); spin_unlock_bh(&mux->lock); @@ -1693,12 +1693,6 @@ static int kcm_release(struct socket *sock) */ __skb_queue_purge(&sk->sk_write_queue); - /* Set tx_stopped. This is checked when psock is bound to a kcm and we - * get a writespace callback. This prevents further work being queued - * from the callback (unbinding the psock occurs after canceling work. - */ - kcm->tx_stopped = 1; - release_sock(sk); spin_lock_bh(&mux->lock); @@ -1714,7 +1708,7 @@ static int kcm_release(struct socket *sock) /* Cancel work. After this point there should be no outside references * to the kcm socket. */ - cancel_work_sync(&kcm->tx_work); + disable_work_sync(&kcm->tx_work); lock_sock(sk); psock = kcm->tx_psock; -- cgit v1.2.3 From 52bf272636bda69587952b35ae97690b8dc89941 Mon Sep 17 00:00:00 2001 From: William Liu Date: Tue, 12 Aug 2025 23:57:57 +0000 Subject: net/sched: Fix backlog accounting in qdisc_dequeue_internal This issue applies for the following qdiscs: hhf, fq, fq_codel, and fq_pie, and occurs in their change handlers when adjusting to the new limit. The problem is the following in the values passed to the subsequent qdisc_tree_reduce_backlog call given a tbf parent: When the tbf parent runs out of tokens, skbs of these qdiscs will be placed in gso_skb. Their peek handlers are qdisc_peek_dequeued, which accounts for both qlen and backlog. However, in the case of qdisc_dequeue_internal, ONLY qlen is accounted for when pulling from gso_skb. This means that these qdiscs are missing a qdisc_qstats_backlog_dec when dropping packets to satisfy the new limit in their change handlers. One can observe this issue with the following (with tc patched to support a limit of 0): export TARGET=fq tc qdisc del dev lo root tc qdisc add dev lo root handle 1: tbf rate 8bit burst 100b latency 1ms tc qdisc replace dev lo handle 3: parent 1:1 $TARGET limit 1000 echo ''; echo 'add child'; tc -s -d qdisc show dev lo ping -I lo -f -c2 -s32 -W0.001 127.0.0.1 2>&1 >/dev/null echo ''; echo 'after ping'; tc -s -d qdisc show dev lo tc qdisc change dev lo handle 3: parent 1:1 $TARGET limit 0 echo ''; echo 'after limit drop'; tc -s -d qdisc show dev lo tc qdisc replace dev lo handle 2: parent 1:1 sfq echo ''; echo 'post graft'; tc -s -d qdisc show dev lo The second to last show command shows 0 packets but a positive number (74) of backlog bytes. The problem becomes clearer in the last show command, where qdisc_purge_queue triggers qdisc_tree_reduce_backlog with the positive backlog and causes an underflow in the tbf parent's backlog (4096 Mb instead of 0). To fix this issue, the codepath for all clients of qdisc_dequeue_internal has been simplified: codel, pie, hhf, fq, fq_pie, and fq_codel. qdisc_dequeue_internal handles the backlog adjustments for all cases that do not directly use the dequeue handler. The old fq_codel_change limit adjustment loop accumulated the arguments to the subsequent qdisc_tree_reduce_backlog call through the cstats field. However, this is confusing and error prone as fq_codel_dequeue could also potentially mutate this field (which qdisc_dequeue_internal calls in the non gso_skb case), so we have unified the code here with other qdiscs. Fixes: 2d3cbfd6d54a ("net_sched: Flush gso_skb list too during ->change()") Fixes: 4b549a2ef4be ("fq_codel: Fair Queue Codel AQM") Fixes: 10239edf86f1 ("net-qdisc-hhf: Heavy-Hitter Filter (HHF) qdisc") Signed-off-by: William Liu Reviewed-by: Savino Dicanosa Link: https://patch.msgid.link/20250812235725.45243-1-will@willsroot.io Signed-off-by: Jakub Kicinski --- include/net/sch_generic.h | 11 ++++++++--- net/sched/sch_codel.c | 12 +++++++----- net/sched/sch_fq.c | 12 +++++++----- net/sched/sch_fq_codel.c | 12 +++++++----- net/sched/sch_fq_pie.c | 12 +++++++----- net/sched/sch_hhf.c | 12 +++++++----- net/sched/sch_pie.c | 12 +++++++----- 7 files changed, 50 insertions(+), 33 deletions(-) (limited to 'include/net') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 638948be4c50..738cd5b13c62 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1038,12 +1038,17 @@ static inline struct sk_buff *qdisc_dequeue_internal(struct Qdisc *sch, bool dir skb = __skb_dequeue(&sch->gso_skb); if (skb) { sch->q.qlen--; + qdisc_qstats_backlog_dec(sch, skb); return skb; } - if (direct) - return __qdisc_dequeue_head(&sch->q); - else + if (direct) { + skb = __qdisc_dequeue_head(&sch->q); + if (skb) + qdisc_qstats_backlog_dec(sch, skb); + return skb; + } else { return sch->dequeue(sch); + } } static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index c93761040c6e..fa0314679e43 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -101,9 +101,9 @@ static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = { static int codel_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CODEL_MAX + 1]; - unsigned int qlen, dropped = 0; int err; err = nla_parse_nested_deprecated(tb, TCA_CODEL_MAX, opt, @@ -142,15 +142,17 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt, WRITE_ONCE(q->params.ecn, !!nla_get_u32(tb[TCA_CODEL_ECN])); - qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, true); - dropped += qdisc_pkt_len(skb); - qdisc_qstats_backlog_dec(sch, skb); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_qdisc_drop(skb, sch); } - qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 902ff5470607..fee922da2f99 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -1013,11 +1013,11 @@ static int fq_load_priomap(struct fq_sched_data *q, static int fq_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct fq_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_MAX + 1]; - int err, drop_count = 0; - unsigned drop_len = 0; u32 fq_log; + int err; err = nla_parse_nested_deprecated(tb, TCA_FQ_MAX, opt, fq_policy, NULL); @@ -1135,16 +1135,18 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, err = fq_resize(sch, fq_log); sch_tree_lock(sch); } + while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); if (!skb) break; - drop_len += qdisc_pkt_len(skb); + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); - drop_count++; } - qdisc_tree_reduce_backlog(sch, drop_count, drop_len); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return err; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 2a0f3a513bfa..a14142392939 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -366,6 +366,7 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct fq_codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_CODEL_MAX + 1]; u32 quantum = 0; @@ -443,13 +444,14 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->memory_usage > q->memory_limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); - q->cstats.drop_len += qdisc_pkt_len(skb); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); - q->cstats.drop_count++; } - qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len); - q->cstats.drop_count = 0; - q->cstats.drop_len = 0; + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index b0e34daf1f75..7b96bc3ff891 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -287,10 +287,9 @@ begin: static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct fq_pie_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_PIE_MAX + 1]; - unsigned int len_dropped = 0; - unsigned int num_dropped = 0; int err; err = nla_parse_nested(tb, TCA_FQ_PIE_MAX, opt, fq_pie_policy, extack); @@ -368,11 +367,14 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); - len_dropped += qdisc_pkt_len(skb); - num_dropped += 1; + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); } - qdisc_tree_reduce_backlog(sch, num_dropped, len_dropped); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 5aa434b46707..2d4855e28a28 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -508,9 +508,9 @@ static const struct nla_policy hhf_policy[TCA_HHF_MAX + 1] = { static int hhf_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct hhf_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_HHF_MAX + 1]; - unsigned int qlen, prev_backlog; int err; u64 non_hh_quantum; u32 new_quantum = q->quantum; @@ -561,15 +561,17 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt, usecs_to_jiffies(us)); } - qlen = sch->q.qlen; - prev_backlog = sch->qstats.backlog; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); } - qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, - prev_backlog - sch->qstats.backlog); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index ad46ee3ed5a9..0a377313b6a9 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -141,9 +141,9 @@ static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = { static int pie_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct pie_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_PIE_MAX + 1]; - unsigned int qlen, dropped = 0; int err; err = nla_parse_nested_deprecated(tb, TCA_PIE_MAX, opt, pie_policy, @@ -193,15 +193,17 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt, nla_get_u32(tb[TCA_PIE_DQ_RATE_ESTIMATOR])); /* Drop excess packets if new limit is lower */ - qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, true); - dropped += qdisc_pkt_len(skb); - qdisc_qstats_backlog_dec(sch, skb); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_qdisc_drop(skb, sch); } - qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; -- cgit v1.2.3 From 709788b154caf042874d765628ffa860f0bb0d1e Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 4 Aug 2025 09:54:05 -0400 Subject: Bluetooth: hci_core: Fix using {cis,bis}_capable for current settings {cis,bis}_capable only indicates the controller supports the feature since it doesn't check that LE is enabled so it shall not be used for current setting, instead this introduces {cis,bis}_enabled macros that can be used to indicate that these features are currently enabled. Fixes: 26afbd826ee3 ("Bluetooth: Add initial implementation of CIS connections") Fixes: eca0ae4aea66 ("Bluetooth: Add initial implementation of BIS connections") Fixes: ae7533613133 ("Bluetooth: Check for ISO support in controller") Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/bluetooth.h | 4 ++-- include/net/bluetooth/hci_core.h | 13 ++++++++++++- net/bluetooth/hci_sync.c | 4 ++-- net/bluetooth/iso.c | 14 +++++++------- net/bluetooth/mgmt.c | 10 +++++----- 5 files changed, 28 insertions(+), 17 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index ada5b56a4413..e5751f3070b8 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -647,7 +647,7 @@ static inline void sco_exit(void) #if IS_ENABLED(CONFIG_BT_LE) int iso_init(void); int iso_exit(void); -bool iso_enabled(void); +bool iso_inited(void); #else static inline int iso_init(void) { @@ -659,7 +659,7 @@ static inline int iso_exit(void) return 0; } -static inline bool iso_enabled(void) +static inline bool iso_inited(void) { return false; } diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 4dc11c66f7b8..bc29f2e2e16f 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1915,6 +1915,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn); !hci_dev_test_flag(dev, HCI_RPA_EXPIRED)) #define adv_rpa_valid(adv) (bacmp(&adv->random_addr, BDADDR_ANY) && \ !adv->rpa_expired) +#define le_enabled(dev) (lmp_le_capable(dev) && \ + hci_dev_test_flag(dev, HCI_LE_ENABLED)) #define scan_1m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_1M) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_1M)) @@ -1981,14 +1983,23 @@ void hci_conn_del_sysfs(struct hci_conn *conn); /* CIS Master/Slave and BIS support */ #define iso_capable(dev) (cis_capable(dev) || bis_capable(dev)) +#define iso_enabled(dev) (le_enabled(dev) && iso_capable(dev)) #define cis_capable(dev) \ (cis_central_capable(dev) || cis_peripheral_capable(dev)) +#define cis_enabled(dev) (le_enabled(dev) && cis_capable(dev)) #define cis_central_capable(dev) \ ((dev)->le_features[3] & HCI_LE_CIS_CENTRAL) +#define cis_central_enabled(dev) \ + (le_enabled(dev) && cis_central_capable(dev)) #define cis_peripheral_capable(dev) \ ((dev)->le_features[3] & HCI_LE_CIS_PERIPHERAL) +#define cis_peripheral_enabled(dev) \ + (le_enabled(dev) && cis_peripheral_capable(dev)) #define bis_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_BROADCASTER) -#define sync_recv_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER) +#define bis_enabled(dev) (le_enabled(dev) && bis_capable(dev)) +#define sync_recv_capable(dev) \ + ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER) +#define sync_recv_enabled(dev) (le_enabled(dev) && sync_recv_capable(dev)) #define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \ (!hci_test_quirk((dev), HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG))) diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 387c128f2ba0..aa7d7a8ec3ee 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4531,14 +4531,14 @@ static int hci_le_set_host_feature_sync(struct hci_dev *hdev) { struct hci_cp_le_set_host_feature cp; - if (!cis_capable(hdev)) + if (!iso_capable(hdev)) return 0; memset(&cp, 0, sizeof(cp)); /* Connected Isochronous Channels (Host Support) */ cp.bit_number = 32; - cp.bit_value = 1; + cp.bit_value = iso_enabled(hdev) ? 0x01 : 0x00; return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_HOST_FEATURE, sizeof(cp), &cp, HCI_CMD_TIMEOUT); diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index eaffd25570e3..5ce823ca3aaf 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -2483,11 +2483,11 @@ static const struct net_proto_family iso_sock_family_ops = { .create = iso_sock_create, }; -static bool iso_inited; +static bool inited; -bool iso_enabled(void) +bool iso_inited(void) { - return iso_inited; + return inited; } int iso_init(void) @@ -2496,7 +2496,7 @@ int iso_init(void) BUILD_BUG_ON(sizeof(struct sockaddr_iso) > sizeof(struct sockaddr)); - if (iso_inited) + if (inited) return -EALREADY; err = proto_register(&iso_proto, 0); @@ -2524,7 +2524,7 @@ int iso_init(void) iso_debugfs = debugfs_create_file("iso", 0444, bt_debugfs, NULL, &iso_debugfs_fops); - iso_inited = true; + inited = true; return 0; @@ -2535,7 +2535,7 @@ error: int iso_exit(void) { - if (!iso_inited) + if (!inited) return -EALREADY; bt_procfs_cleanup(&init_net, "iso"); @@ -2549,7 +2549,7 @@ int iso_exit(void) proto_unregister(&iso_proto); - iso_inited = false; + inited = false; return 0; } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 1ce682038b51..c42dffe77daf 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -922,16 +922,16 @@ static u32 get_current_settings(struct hci_dev *hdev) if (hci_dev_test_flag(hdev, HCI_WIDEBAND_SPEECH_ENABLED)) settings |= MGMT_SETTING_WIDEBAND_SPEECH; - if (cis_central_capable(hdev)) + if (cis_central_enabled(hdev)) settings |= MGMT_SETTING_CIS_CENTRAL; - if (cis_peripheral_capable(hdev)) + if (cis_peripheral_enabled(hdev)) settings |= MGMT_SETTING_CIS_PERIPHERAL; - if (bis_capable(hdev)) + if (bis_enabled(hdev)) settings |= MGMT_SETTING_ISO_BROADCASTER; - if (sync_recv_capable(hdev)) + if (sync_recv_enabled(hdev)) settings |= MGMT_SETTING_ISO_SYNC_RECEIVER; if (ll_privacy_capable(hdev)) @@ -4513,7 +4513,7 @@ static int read_exp_features_info(struct sock *sk, struct hci_dev *hdev, } if (IS_ENABLED(CONFIG_BT_LE)) { - flags = iso_enabled() ? BIT(0) : 0; + flags = iso_inited() ? BIT(0) : 0; memcpy(rp->features[idx].uuid, iso_socket_uuid, 16); rp->features[idx].flags = cpu_to_le32(flags); idx++; -- cgit v1.2.3 From 3dcf7175f2c04bd3a7d50db3fa42a0bd933b6e23 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 4 Aug 2025 14:05:03 -0400 Subject: Bluetooth: hci_core: Fix using ll_privacy_capable for current settings ll_privacy_capable only indicates that the controller supports the feature but it doesnt' check that LE is enabled so it end up being marked as active in the current settings when it shouldn't. Fixes: ad383c2c65a5 ("Bluetooth: hci_sync: Enable advertising when LL privacy is enabled") Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 1 + net/bluetooth/mgmt.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index bc29f2e2e16f..bb30bde6f0e8 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1934,6 +1934,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn); ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED)) #define ll_privacy_capable(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY) +#define ll_privacy_enabled(dev) (le_enabled(dev) && ll_privacy_capable(dev)) #define privacy_mode_capable(dev) (ll_privacy_capable(dev) && \ ((dev)->commands[39] & 0x04)) diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index c42dffe77daf..3166f5fb876b 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -934,7 +934,7 @@ static u32 get_current_settings(struct hci_dev *hdev) if (sync_recv_enabled(hdev)) settings |= MGMT_SETTING_ISO_SYNC_RECEIVER; - if (ll_privacy_capable(hdev)) + if (ll_privacy_enabled(hdev)) settings |= MGMT_SETTING_LL_PRIVACY; return settings; -- cgit v1.2.3 From 9d4b01a0bf8d2163ae129c9c537cb0753ad5a2aa Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Thu, 14 Aug 2025 11:57:19 -0400 Subject: Bluetooth: hci_core: Fix not accounting for BIS/CIS/PA links separately This fixes the likes of hci_conn_num(CIS_LINK) returning the total of ISO connection which includes BIS_LINK as well, so this splits the iso_num into each link type and introduces hci_iso_num that can be used in places where the total number of ISO connection still needs to be used. Fixes: 23205562ffc8 ("Bluetooth: separate CIS_LINK and BIS_LINK link types") Fixes: a7bcffc673de ("Bluetooth: Add PA_LINK to distinguish BIG sync and PA sync connections") Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 30 +++++++++++++++++++++++++----- 1 file changed, 25 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index bb30bde6f0e8..6906af7a8f24 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -129,7 +129,9 @@ struct hci_conn_hash { struct list_head list; unsigned int acl_num; unsigned int sco_num; - unsigned int iso_num; + unsigned int cis_num; + unsigned int bis_num; + unsigned int pa_num; unsigned int le_num; unsigned int le_num_peripheral; }; @@ -1014,9 +1016,13 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c) h->sco_num++; break; case CIS_LINK: + h->cis_num++; + break; case BIS_LINK: + h->bis_num++; + break; case PA_LINK: - h->iso_num++; + h->pa_num++; break; } } @@ -1042,9 +1048,13 @@ static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c) h->sco_num--; break; case CIS_LINK: + h->cis_num--; + break; case BIS_LINK: + h->bis_num--; + break; case PA_LINK: - h->iso_num--; + h->pa_num--; break; } } @@ -1061,9 +1071,11 @@ static inline unsigned int hci_conn_num(struct hci_dev *hdev, __u8 type) case ESCO_LINK: return h->sco_num; case CIS_LINK: + return h->cis_num; case BIS_LINK: + return h->bis_num; case PA_LINK: - return h->iso_num; + return h->pa_num; default: return 0; } @@ -1073,7 +1085,15 @@ static inline unsigned int hci_conn_count(struct hci_dev *hdev) { struct hci_conn_hash *c = &hdev->conn_hash; - return c->acl_num + c->sco_num + c->le_num + c->iso_num; + return c->acl_num + c->sco_num + c->le_num + c->cis_num + c->bis_num + + c->pa_num; +} + +static inline unsigned int hci_iso_count(struct hci_dev *hdev) +{ + struct hci_conn_hash *c = &hdev->conn_hash; + + return c->cis_num + c->bis_num; } static inline bool hci_conn_valid(struct hci_dev *hdev, struct hci_conn *conn) -- cgit v1.2.3 From b64d035f77b1f02ab449393342264b44950a75ae Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 15 Aug 2025 06:19:58 +0000 Subject: bonding: update LACP activity flag after setting lacp_active The port's actor_oper_port_state activity flag should be updated immediately after changing the lacp_active option to reflect the current mode correctly. Fixes: 3a755cd8b7c6 ("bonding: add new option lacp_active") Signed-off-by: Hangbin Liu Link: https://patch.msgid.link/20250815062000.22220-2-liuhangbin@gmail.com Signed-off-by: Paolo Abeni --- drivers/net/bonding/bond_3ad.c | 25 +++++++++++++++++++++++++ drivers/net/bonding/bond_options.c | 1 + include/net/bond_3ad.h | 1 + 3 files changed, 27 insertions(+) (limited to 'include/net') diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 2fca8e84ab10..414fecfd2a0e 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -2883,6 +2883,31 @@ void bond_3ad_update_lacp_rate(struct bonding *bond) spin_unlock_bh(&bond->mode_lock); } +/** + * bond_3ad_update_lacp_active - change the lacp active + * @bond: bonding struct + * + * Update actor_oper_port_state when lacp_active is modified. + */ +void bond_3ad_update_lacp_active(struct bonding *bond) +{ + struct port *port = NULL; + struct list_head *iter; + struct slave *slave; + int lacp_active; + + lacp_active = bond->params.lacp_active; + spin_lock_bh(&bond->mode_lock); + bond_for_each_slave(bond, slave, iter) { + port = &(SLAVE_AD_INFO(slave)->port); + if (lacp_active) + port->actor_oper_port_state |= LACP_STATE_LACP_ACTIVITY; + else + port->actor_oper_port_state &= ~LACP_STATE_LACP_ACTIVITY; + } + spin_unlock_bh(&bond->mode_lock); +} + size_t bond_3ad_stats_size(void) { return nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_RX */ diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 1d639a3be6ba..3b6f815c55ff 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1660,6 +1660,7 @@ static int bond_option_lacp_active_set(struct bonding *bond, netdev_dbg(bond->dev, "Setting LACP active to %s (%llu)\n", newval->string, newval->value); bond->params.lacp_active = newval->value; + bond_3ad_update_lacp_active(bond); return 0; } diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 2053cd8e788a..dba369a2cf27 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -307,6 +307,7 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); int bond_3ad_set_carrier(struct bonding *bond); void bond_3ad_update_lacp_rate(struct bonding *bond); +void bond_3ad_update_lacp_active(struct bonding *bond); void bond_3ad_update_ad_actor_settings(struct bonding *bond); int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats); size_t bond_3ad_stats_size(void); -- cgit v1.2.3