From bb3d0b8bf5be61ab1d6f472c43cbf34de17e796b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 23 Dec 2019 11:13:24 -0800 Subject: net_sched: sch_fq: properly set sk->sk_pacing_status If fq_classify() recycles a struct fq_flow because a socket structure has been reallocated, we do not set sk->sk_pacing_status immediately, but later if the flow becomes detached. This means that any flow requiring pacing (BBR, or SO_MAX_PACING_RATE) might fallback to TCP internal pacing, which requires a per-socket high resolution timer, and therefore more cpu cycles. Fixes: 218af599fa63 ("tcp: internal implementation for pacing") Signed-off-by: Eric Dumazet Cc: Soheil Hassas Yeganeh Cc: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- net/sched/sch_fq.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'net/sched') diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index b1c7e726ce5d..ff4c5e9d0d77 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -301,6 +301,9 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) f->socket_hash != sk->sk_hash)) { f->credit = q->initial_quantum; f->socket_hash = sk->sk_hash; + if (q->rate_enable) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); if (fq_flow_is_throttled(f)) fq_flow_unset_throttled(q, f); f->time_next_packet = 0ULL; @@ -322,8 +325,12 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) fq_flow_set_detached(f); f->sk = sk; - if (skb->sk == sk) + if (skb->sk == sk) { f->socket_hash = sk->sk_hash; + if (q->rate_enable) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); + } f->credit = q->initial_quantum; rb_link_node(&f->fq_node, parent, p); @@ -428,17 +435,9 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, f->qlen++; qdisc_qstats_backlog_inc(sch, skb); if (fq_flow_is_detached(f)) { - struct sock *sk = skb->sk; - fq_flow_add_tail(&q->new_flows, f); if (time_after(jiffies, f->age + q->flow_refill_delay)) f->credit = max_t(u32, f->credit, q->quantum); - if (sk && q->rate_enable) { - if (unlikely(smp_load_acquire(&sk->sk_pacing_status) != - SK_PACING_FQ)) - smp_store_release(&sk->sk_pacing_status, - SK_PACING_FQ); - } q->inactive_flows--; } -- cgit v1.2.3-58-ga151 From 70cf3dc7313207816255b9acb0dffb19dae78144 Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Wed, 25 Dec 2019 10:51:01 +0200 Subject: net/sched: act_mirred: Pull mac prior redir to non mac_header_xmit device There's no skb_pull performed when a mirred action is set at egress of a mac device, with a target device/action that expects skb->data to point at the network header. As a result, either the target device is errornously given an skb with data pointing to the mac (egress case), or the net stack receives the skb with data pointing to the mac (ingress case). E.g: # tc qdisc add dev eth9 root handle 1: prio # tc filter add dev eth9 parent 1: prio 9 protocol ip handle 9 basic \ action mirred egress redirect dev tun0 (tun0 is a tun device. result: tun0 errornously gets the eth header instead of the iph) Revise the push/pull logic of tcf_mirred_act() to not rely on the skb_at_tc_ingress() vs tcf_mirred_act_wants_ingress() comparison, as it does not cover all "pull" cases. Instead, calculate whether the required action on the target device requires the data to point at the network header, and compare this to whether skb->data points to network header - and make the push/pull adjustments as necessary. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Shmulik Ladkani Tested-by: Jamal Hadi Salim Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/sched/act_mirred.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'net/sched') diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 1e3eb3a97532..1ad300e6dbc0 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -219,8 +219,10 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, bool use_reinsert; bool want_ingress; bool is_redirect; + bool expects_nh; int m_eaction; int mac_len; + bool at_nh; rec_level = __this_cpu_inc_return(mirred_rec_level); if (unlikely(rec_level > MIRRED_RECURSION_LIMIT)) { @@ -261,19 +263,19 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, goto out; } - /* If action's target direction differs than filter's direction, - * and devices expect a mac header on xmit, then mac push/pull is - * needed. - */ want_ingress = tcf_mirred_act_wants_ingress(m_eaction); - if (skb_at_tc_ingress(skb) != want_ingress && m_mac_header_xmit) { - if (!skb_at_tc_ingress(skb)) { - /* caught at egress, act ingress: pull mac */ - mac_len = skb_network_header(skb) - skb_mac_header(skb); + + expects_nh = want_ingress || !m_mac_header_xmit; + at_nh = skb->data == skb_network_header(skb); + if (at_nh != expects_nh) { + mac_len = skb_at_tc_ingress(skb) ? skb->mac_len : + skb_network_header(skb) - skb_mac_header(skb); + if (expects_nh) { + /* target device/action expect data at nh */ skb_pull_rcsum(skb2, mac_len); } else { - /* caught at ingress, act egress: push mac */ - skb_push_rcsum(skb2, skb->mac_len); + /* target device/action expect data at mac */ + skb_push_rcsum(skb2, mac_len); } } -- cgit v1.2.3-58-ga151 From a5b72a083da197b493c7ed1e5730d62d3199f7d6 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Sat, 28 Dec 2019 16:36:58 +0100 Subject: net/sched: add delete_empty() to filters and use it in cls_flower Revert "net/sched: cls_u32: fix refcount leak in the error path of u32_change()", and fix the u32 refcount leak in a more generic way that preserves the semantic of rule dumping. On tc filters that don't support lockless insertion/removal, there is no need to guard against concurrent insertion when a removal is in progress. Therefore, for most of them we can avoid a full walk() when deleting, and just decrease the refcount, like it was done on older Linux kernels. This fixes situations where walk() was wrongly detecting a non-empty filter, like it happened with cls_u32 in the error path of change(), thus leading to failures in the following tdc selftests: 6aa7: (filter, u32) Add/Replace u32 with source match and invalid indev 6658: (filter, u32) Add/Replace u32 with custom hash table and invalid handle 74c2: (filter, u32) Add/Replace u32 filter with invalid hash table id On cls_flower, and on (future) lockless filters, this check is necessary: move all the check_empty() logic in a callback so that each filter can have its own implementation. For cls_flower, it's sufficient to check if no IDRs have been allocated. This reverts commit 275c44aa194b7159d1191817b20e076f55f0e620. Changes since v1: - document the need for delete_empty() when TCF_PROTO_OPS_DOIT_UNLOCKED is used, thanks to Vlad Buslov - implement delete_empty() without doing fl_walk(), thanks to Vlad Buslov - squash revert and new fix in a single patch, to be nice with bisect tests that run tdc on u32 filter, thanks to Dave Miller Fixes: 275c44aa194b ("net/sched: cls_u32: fix refcount leak in the error path of u32_change()") Fixes: 6676d5e416ee ("net: sched: set dedicated tcf_walker flag when tp is empty") Suggested-by: Jamal Hadi Salim Suggested-by: Vlad Buslov Signed-off-by: Davide Caratti Reviewed-by: Vlad Buslov Tested-by: Jamal Hadi Salim Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/sch_generic.h | 5 +++++ net/sched/cls_api.c | 31 +++++-------------------------- net/sched/cls_flower.c | 12 ++++++++++++ net/sched/cls_u32.c | 25 ------------------------- 4 files changed, 22 insertions(+), 51 deletions(-) (limited to 'net/sched') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 144f264ea394..fceddf89592a 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -308,6 +308,7 @@ struct tcf_proto_ops { int (*delete)(struct tcf_proto *tp, void *arg, bool *last, bool rtnl_held, struct netlink_ext_ack *); + bool (*delete_empty)(struct tcf_proto *tp); void (*walk)(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held); int (*reoffload)(struct tcf_proto *tp, bool add, @@ -336,6 +337,10 @@ struct tcf_proto_ops { int flags; }; +/* Classifiers setting TCF_PROTO_OPS_DOIT_UNLOCKED in tcf_proto_ops->flags + * are expected to implement tcf_proto_ops->delete_empty(), otherwise race + * conditions can occur when filters are inserted/deleted simultaneously. + */ enum tcf_proto_ops_flags { TCF_PROTO_OPS_DOIT_UNLOCKED = 1, }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 6a0eacafdb19..76e0d122616a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -308,33 +308,12 @@ static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held, tcf_proto_destroy(tp, rtnl_held, true, extack); } -static int walker_check_empty(struct tcf_proto *tp, void *fh, - struct tcf_walker *arg) +static bool tcf_proto_check_delete(struct tcf_proto *tp) { - if (fh) { - arg->nonempty = true; - return -1; - } - return 0; -} - -static bool tcf_proto_is_empty(struct tcf_proto *tp, bool rtnl_held) -{ - struct tcf_walker walker = { .fn = walker_check_empty, }; - - if (tp->ops->walk) { - tp->ops->walk(tp, &walker, rtnl_held); - return !walker.nonempty; - } - return true; -} + if (tp->ops->delete_empty) + return tp->ops->delete_empty(tp); -static bool tcf_proto_check_delete(struct tcf_proto *tp, bool rtnl_held) -{ - spin_lock(&tp->lock); - if (tcf_proto_is_empty(tp, rtnl_held)) - tp->deleting = true; - spin_unlock(&tp->lock); + tp->deleting = true; return tp->deleting; } @@ -1751,7 +1730,7 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, * concurrently. * Mark tp for deletion if it is empty. */ - if (!tp_iter || !tcf_proto_check_delete(tp, rtnl_held)) { + if (!tp_iter || !tcf_proto_check_delete(tp)) { mutex_unlock(&chain->filter_chain_lock); return; } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 0d125de54285..b0f42e62dd76 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2773,6 +2773,17 @@ static void fl_bind_class(void *fh, u32 classid, unsigned long cl) f->res.class = cl; } +static bool fl_delete_empty(struct tcf_proto *tp) +{ + struct cls_fl_head *head = fl_head_dereference(tp); + + spin_lock(&tp->lock); + tp->deleting = idr_is_empty(&head->handle_idr); + spin_unlock(&tp->lock); + + return tp->deleting; +} + static struct tcf_proto_ops cls_fl_ops __read_mostly = { .kind = "flower", .classify = fl_classify, @@ -2782,6 +2793,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = { .put = fl_put, .change = fl_change, .delete = fl_delete, + .delete_empty = fl_delete_empty, .walk = fl_walk, .reoffload = fl_reoffload, .hw_add = fl_hw_add, diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 66c6bcec16cb..a0e6fac613de 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1108,33 +1108,10 @@ erridr: return err; } -static bool u32_hnode_empty(struct tc_u_hnode *ht, bool *non_root_ht) -{ - int i; - - if (!ht) - return true; - if (!ht->is_root) { - *non_root_ht = true; - return false; - } - if (*non_root_ht) - return false; - if (ht->refcnt < 2) - return true; - - for (i = 0; i <= ht->divisor; i++) { - if (rtnl_dereference(ht->ht[i])) - return false; - } - return true; -} - static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held) { struct tc_u_common *tp_c = tp->data; - bool non_root_ht = false; struct tc_u_hnode *ht; struct tc_u_knode *n; unsigned int h; @@ -1147,8 +1124,6 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, ht = rtnl_dereference(ht->next)) { if (ht->prio != tp->prio) continue; - if (u32_hnode_empty(ht, &non_root_ht)) - return; if (arg->count >= arg->skip) { if (arg->fn(tp, ht, arg) < 0) { arg->stop = 1; -- cgit v1.2.3-58-ga151