diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-01-31 14:31:10 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-01-31 14:31:10 -0800 |
| commit | b2fe5fa68642860e7de76167c3111623aa0d5de1 (patch) | |
| tree | b7f9b89b7039ecefbc35fe3c8e73a6ff972641dd /net/sched | |
| parent | a103950e0dd2058df5e8a8d4a915707bdcf205f0 (diff) | |
| parent | a54667f6728c2714a400f3c884727da74b6d1717 (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
1) Significantly shrink the core networking routing structures. Result
of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf
2) Add netdevsim driver for testing various offloads, from Jakub
Kicinski.
3) Support cross-chip FDB operations in DSA, from Vivien Didelot.
4) Add a 2nd listener hash table for TCP, similar to what was done for
UDP. From Martin KaFai Lau.
5) Add eBPF based queue selection to tun, from Jason Wang.
6) Lockless qdisc support, from John Fastabend.
7) SCTP stream interleave support, from Xin Long.
8) Smoother TCP receive autotuning, from Eric Dumazet.
9) Lots of erspan tunneling enhancements, from William Tu.
10) Add true function call support to BPF, from Alexei Starovoitov.
11) Add explicit support for GRO HW offloading, from Michael Chan.
12) Support extack generation in more netlink subsystems. From Alexander
Aring, Quentin Monnet, and Jakub Kicinski.
13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
Russell King.
14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.
15) Many improvements and simplifications to the NFP driver bpf JIT,
from Jakub Kicinski.
16) Support for ipv6 non-equal cost multipath routing, from Ido
Schimmel.
17) Add resource abstration to devlink, from Arkadi Sharshevsky.
18) Packet scheduler classifier shared filter block support, from Jiri
Pirko.
19) Avoid locking in act_csum, from Davide Caratti.
20) devinet_ioctl() simplifications from Al viro.
21) More TCP bpf improvements from Lawrence Brakmo.
22) Add support for onlink ipv6 route flag, similar to ipv4, from David
Ahern.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
tls: Add support for encryption using async offload accelerator
ip6mr: fix stale iterator
net/sched: kconfig: Remove blank help texts
openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
tcp_nv: fix potential integer overflow in tcpnv_acked
r8169: fix RTL8168EP take too long to complete driver initialization.
qmi_wwan: Add support for Quectel EP06
rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
ipmr: Fix ptrdiff_t print formatting
ibmvnic: Wait for device response when changing MAC
qlcnic: fix deadlock bug
tcp: release sk_frag.page in tcp_disconnect
ipv4: Get the address of interface correctly.
net_sched: gen_estimator: fix lockdep splat
net: macb: Handle HRESP error
net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
ipv6: addrconf: break critical section in addrconf_verify_rtnl()
ipv6: change route cache aging logic
i40e/i40evf: Update DESC_NEEDED value to reflect larger value
bnxt_en: cleanup DIM work on device shutdown
...
Diffstat (limited to 'net/sched')
60 files changed, 2052 insertions, 927 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig index c03d86a7775e..f24a6ae6819a 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -857,17 +857,14 @@ config NET_ACT_TUNNEL_KEY config NET_IFE_SKBMARK tristate "Support to encoding decoding skb mark on IFE action" depends on NET_ACT_IFE - ---help--- config NET_IFE_SKBPRIO tristate "Support to encoding decoding skb prio on IFE action" depends on NET_ACT_IFE - ---help--- config NET_IFE_SKBTCINDEX tristate "Support to encoding decoding skb tcindex on IFE action" depends on NET_ACT_IFE - ---help--- config NET_CLS_IND bool "Incoming device classification" diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 4d33a50a8a6d..52622a3d2517 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -99,7 +99,7 @@ int __tcf_idr_release(struct tc_action *p, bool bind, bool strict) p->tcfa_refcnt--; if (p->tcfa_bindcnt <= 0 && p->tcfa_refcnt <= 0) { if (p->ops->cleanup) - p->ops->cleanup(p, bind); + p->ops->cleanup(p); tcf_idr_remove(p->idrinfo, p); ret = ACT_P_DELETED; } diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 5ef8ce8c83d4..b3f2c15affa7 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -357,7 +357,7 @@ out: return ret; } -static void tcf_bpf_cleanup(struct tc_action *act, int bind) +static void tcf_bpf_cleanup(struct tc_action *act) { struct tcf_bpf_cfg tmp; @@ -401,16 +401,14 @@ static __net_init int bpf_init_net(struct net *net) return tc_action_net_init(tn, &act_bpf_ops); } -static void __net_exit bpf_exit_net(struct net *net) +static void __net_exit bpf_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, bpf_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, bpf_net_id); } static struct pernet_operations bpf_net_ops = { .init = bpf_init_net, - .exit = bpf_exit_net, + .exit_batch = bpf_exit_net, .id = &bpf_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 10b7a8855a6c..2b15ba84e0c8 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -209,16 +209,14 @@ static __net_init int connmark_init_net(struct net *net) return tc_action_net_init(tn, &act_connmark_ops); } -static void __net_exit connmark_exit_net(struct net *net) +static void __net_exit connmark_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, connmark_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, connmark_net_id); } static struct pernet_operations connmark_net_ops = { .init = connmark_init_net, - .exit = connmark_exit_net, + .exit_batch = connmark_exit_net, .id = &connmark_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index d836f998117b..b7ba9b06b147 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -49,6 +49,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, int bind) { struct tc_action_net *tn = net_generic(net, csum_net_id); + struct tcf_csum_params *params_old, *params_new; struct nlattr *tb[TCA_CSUM_MAX + 1]; struct tc_csum *parm; struct tcf_csum *p; @@ -67,7 +68,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, if (!tcf_idr_check(tn, parm->index, a, bind)) { ret = tcf_idr_create(tn, parm->index, est, a, - &act_csum_ops, bind, false); + &act_csum_ops, bind, true); if (ret) return ret; ret = ACT_P_CREATED; @@ -80,10 +81,21 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, } p = to_tcf_csum(*a); - spin_lock_bh(&p->tcf_lock); - p->tcf_action = parm->action; - p->update_flags = parm->update_flags; - spin_unlock_bh(&p->tcf_lock); + ASSERT_RTNL(); + + params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); + if (unlikely(!params_new)) { + if (ret == ACT_P_CREATED) + tcf_idr_release(*a, bind); + return -ENOMEM; + } + params_old = rtnl_dereference(p->params); + + params_new->action = parm->action; + params_new->update_flags = parm->update_flags; + rcu_assign_pointer(p->params, params_new); + if (params_old) + kfree_rcu(params_old, rcu); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); @@ -539,19 +551,21 @@ static int tcf_csum(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_csum *p = to_tcf_csum(a); - int action; + struct tcf_csum_params *params; u32 update_flags; + int action; + + rcu_read_lock(); + params = rcu_dereference(p->params); - spin_lock(&p->tcf_lock); tcf_lastuse_update(&p->tcf_tm); - bstats_update(&p->tcf_bstats, skb); - action = p->tcf_action; - update_flags = p->update_flags; - spin_unlock(&p->tcf_lock); + bstats_cpu_update(this_cpu_ptr(p->common.cpu_bstats), skb); + action = params->action; if (unlikely(action == TC_ACT_SHOT)) - goto drop; + goto drop_stats; + update_flags = params->update_flags; switch (tc_skb_protocol(skb)) { case cpu_to_be16(ETH_P_IP): if (!tcf_csum_ipv4(skb, update_flags)) @@ -563,13 +577,16 @@ static int tcf_csum(struct sk_buff *skb, const struct tc_action *a, break; } +unlock: + rcu_read_unlock(); return action; drop: - spin_lock(&p->tcf_lock); - p->tcf_qstats.drops++; - spin_unlock(&p->tcf_lock); - return TC_ACT_SHOT; + action = TC_ACT_SHOT; + +drop_stats: + qstats_drop_inc(this_cpu_ptr(p->common.cpu_qstats)); + goto unlock; } static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, @@ -577,15 +594,18 @@ static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, { unsigned char *b = skb_tail_pointer(skb); struct tcf_csum *p = to_tcf_csum(a); + struct tcf_csum_params *params; struct tc_csum opt = { - .update_flags = p->update_flags, .index = p->tcf_index, - .action = p->tcf_action, .refcnt = p->tcf_refcnt - ref, .bindcnt = p->tcf_bindcnt - bind, }; struct tcf_t t; + params = rtnl_dereference(p->params); + opt.action = params->action; + opt.update_flags = params->update_flags; + if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -600,6 +620,15 @@ nla_put_failure: return -1; } +static void tcf_csum_cleanup(struct tc_action *a) +{ + struct tcf_csum *p = to_tcf_csum(a); + struct tcf_csum_params *params; + + params = rcu_dereference_protected(p->params, 1); + kfree_rcu(params, rcu); +} + static int tcf_csum_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, const struct tc_action_ops *ops) @@ -623,6 +652,7 @@ static struct tc_action_ops act_csum_ops = { .act = tcf_csum, .dump = tcf_csum_dump, .init = tcf_csum_init, + .cleanup = tcf_csum_cleanup, .walk = tcf_csum_walker, .lookup = tcf_csum_search, .size = sizeof(struct tcf_csum), @@ -635,16 +665,14 @@ static __net_init int csum_init_net(struct net *net) return tc_action_net_init(tn, &act_csum_ops); } -static void __net_exit csum_exit_net(struct net *net) +static void __net_exit csum_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, csum_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, csum_net_id); } static struct pernet_operations csum_net_ops = { .init = csum_init_net, - .exit = csum_exit_net, + .exit_batch = csum_exit_net, .id = &csum_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index a0ac42b3ed06..b56986d41c87 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -235,16 +235,14 @@ static __net_init int gact_init_net(struct net *net) return tc_action_net_init(tn, &act_gact_ops); } -static void __net_exit gact_exit_net(struct net *net) +static void __net_exit gact_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, gact_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, gact_net_id); } static struct pernet_operations gact_net_ops = { .init = gact_init_net, - .exit = gact_exit_net, + .exit_batch = gact_exit_net, .id = &gact_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 3007cb1310ea..5954e992685a 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -387,7 +387,7 @@ out_nlmsg_trim: } /* under ife->tcf_lock */ -static void _tcf_ife_cleanup(struct tc_action *a, int bind) +static void _tcf_ife_cleanup(struct tc_action *a) { struct tcf_ife_info *ife = to_ife(a); struct tcf_meta_info *e, *n; @@ -405,13 +405,13 @@ static void _tcf_ife_cleanup(struct tc_action *a, int bind) } } -static void tcf_ife_cleanup(struct tc_action *a, int bind) +static void tcf_ife_cleanup(struct tc_action *a) { struct tcf_ife_info *ife = to_ife(a); struct tcf_ife_params *p; spin_lock_bh(&ife->tcf_lock); - _tcf_ife_cleanup(a, bind); + _tcf_ife_cleanup(a); spin_unlock_bh(&ife->tcf_lock); p = rcu_dereference_protected(ife->params, 1); @@ -546,7 +546,7 @@ metadata_parse_err: if (exists) tcf_idr_release(*a, bind); if (ret == ACT_P_CREATED) - _tcf_ife_cleanup(*a, bind); + _tcf_ife_cleanup(*a); if (exists) spin_unlock_bh(&ife->tcf_lock); @@ -567,7 +567,7 @@ metadata_parse_err: err = use_all_metadata(ife); if (err) { if (ret == ACT_P_CREATED) - _tcf_ife_cleanup(*a, bind); + _tcf_ife_cleanup(*a); if (exists) spin_unlock_bh(&ife->tcf_lock); @@ -858,16 +858,14 @@ static __net_init int ife_init_net(struct net *net) return tc_action_net_init(tn, &act_ife_ops); } -static void __net_exit ife_exit_net(struct net *net) +static void __net_exit ife_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, ife_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, ife_net_id); } static struct pernet_operations ife_net_ops = { .init = ife_init_net, - .exit = ife_exit_net, + .exit_batch = ife_exit_net, .id = &ife_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index d9e399a7e3d5..06e380ae0928 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -77,7 +77,7 @@ static void ipt_destroy_target(struct xt_entry_target *t) module_put(par.target->me); } -static void tcf_ipt_release(struct tc_action *a, int bind) +static void tcf_ipt_release(struct tc_action *a) { struct tcf_ipt *ipt = to_ipt(a); ipt_destroy_target(ipt->tcfi_t); @@ -337,16 +337,14 @@ static __net_init int ipt_init_net(struct net *net) return tc_action_net_init(tn, &act_ipt_ops); } -static void __net_exit ipt_exit_net(struct net *net) +static void __net_exit ipt_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, ipt_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, ipt_net_id); } static struct pernet_operations ipt_net_ops = { .init = ipt_init_net, - .exit = ipt_exit_net, + .exit_batch = ipt_exit_net, .id = &ipt_net_id, .size = sizeof(struct tc_action_net), }; @@ -387,16 +385,14 @@ static __net_init int xt_init_net(struct net *net) return tc_action_net_init(tn, &act_xt_ops); } -static void __net_exit xt_exit_net(struct net *net) +static void __net_exit xt_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, xt_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, xt_net_id); } static struct pernet_operations xt_net_ops = { .init = xt_init_net, - .exit = xt_exit_net, + .exit_batch = xt_exit_net, .id = &xt_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 08b61849c2a2..e6ff88f72900 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -29,7 +29,6 @@ #include <net/tc_act/tc_mirred.h> static LIST_HEAD(mirred_list); -static DEFINE_SPINLOCK(mirred_list_lock); static bool tcf_mirred_is_act_redirect(int action) { @@ -50,18 +49,15 @@ static bool tcf_mirred_act_wants_ingress(int action) } } -static void tcf_mirred_release(struct tc_action *a, int bind) +static void tcf_mirred_release(struct tc_action *a) { struct tcf_mirred *m = to_mirred(a); struct net_device *dev; - /* We could be called either in a RCU callback or with RTNL lock held. */ - spin_lock_bh(&mirred_list_lock); list_del(&m->tcfm_list); - dev = rcu_dereference_protected(m->tcfm_dev, 1); + dev = rtnl_dereference(m->tcfm_dev); if (dev) dev_put(dev); - spin_unlock_bh(&mirred_list_lock); } static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { @@ -139,8 +135,6 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, m->tcf_action = parm->action; m->tcfm_eaction = parm->eaction; if (dev != NULL) { - m->tcfm_ifindex = parm->ifindex; - m->net = net; if (ret != ACT_P_CREATED) dev_put(rcu_dereference_protected(m->tcfm_dev, 1)); dev_hold(dev); @@ -149,9 +143,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } if (ret == ACT_P_CREATED) { - spin_lock_bh(&mirred_list_lock); list_add(&m->tcfm_list, &mirred_list); - spin_unlock_bh(&mirred_list_lock); tcf_idr_insert(tn, *a); } @@ -247,13 +239,14 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, { unsigned char *b = skb_tail_pointer(skb); struct tcf_mirred *m = to_mirred(a); + struct net_device *dev = rtnl_dereference(m->tcfm_dev); struct tc_mirred opt = { .index = m->tcf_index, .action = m->tcf_action, .refcnt = m->tcf_refcnt - ref, .bindcnt = m->tcf_bindcnt - bind, .eaction = m->tcfm_eaction, - .ifindex = m->tcfm_ifindex, + .ifindex = dev ? dev->ifindex : 0, }; struct tcf_t t; @@ -294,7 +287,6 @@ static int mirred_device_event(struct notifier_block *unused, ASSERT_RTNL(); if (event == NETDEV_UNREGISTER) { - spin_lock_bh(&mirred_list_lock); list_for_each_entry(m, &mirred_list, tcfm_list) { if (rcu_access_pointer(m->tcfm_dev) == dev) { dev_put(dev); @@ -304,7 +296,6 @@ static int mirred_device_event(struct notifier_block *unused, RCU_INIT_POINTER(m->tcfm_dev, NULL); } } - spin_unlock_bh(&mirred_list_lock); } return NOTIFY_DONE; @@ -318,7 +309,7 @@ static struct net_device *tcf_mirred_get_dev(const struct tc_action *a) { struct tcf_mirred *m = to_mirred(a); - return __dev_get_by_index(m->net, m->tcfm_ifindex); + return rtnl_dereference(m->tcfm_dev); } static struct tc_action_ops act_mirred_ops = { @@ -343,16 +334,14 @@ static __net_init int mirred_init_net(struct net *net) return tc_action_net_init(tn, &act_mirred_ops); } -static void __net_exit mirred_exit_net(struct net *net) +static void __net_exit mirred_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, mirred_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, mirred_net_id); } static struct pernet_operations mirred_net_ops = { .init = mirred_init_net, - .exit = mirred_exit_net, + .exit_batch = mirred_exit_net, .id = &mirred_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index c365d01b99c8..98c6a4b2f523 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -310,16 +310,14 @@ static __net_init int nat_init_net(struct net *net) return tc_action_net_init(tn, &act_nat_ops); } -static void __net_exit nat_exit_net(struct net *net) +static void __net_exit nat_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, nat_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, nat_net_id); } static struct pernet_operations nat_net_ops = { .init = nat_init_net, - .exit = nat_exit_net, + .exit_batch = nat_exit_net, .id = &nat_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 491fe5deb09e..349beaffb29e 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -216,7 +216,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, return ret; } -static void tcf_pedit_cleanup(struct tc_action *a, int bind) +static void tcf_pedit_cleanup(struct tc_action *a) { struct tcf_pedit *p = to_pedit(a); struct tc_pedit_key *keys = p->tcfp_keys; @@ -453,16 +453,14 @@ static __net_init int pedit_init_net(struct net *net) return tc_action_net_init(tn, &act_pedit_ops); } -static void __net_exit pedit_exit_net(struct net *net) +static void __net_exit pedit_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, pedit_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, pedit_net_id); } static struct pernet_operations pedit_net_ops = { .init = pedit_init_net, - .exit = pedit_exit_net, + .exit_batch = pedit_exit_net, .id = &pedit_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 3bb2ebf9e9ae..95d3c9097b25 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -118,13 +118,13 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla, police = to_police(*a); if (parm->rate.rate) { err = -ENOMEM; - R_tab = qdisc_get_rtab(&parm->rate, tb[TCA_POLICE_RATE]); + R_tab = qdisc_get_rtab(&parm->rate, tb[TCA_POLICE_RATE], NULL); if (R_tab == NULL) goto failure; if (parm->peakrate.rate) { P_tab = qdisc_get_rtab(&parm->peakrate, - tb[TCA_POLICE_PEAKRATE]); + tb[TCA_POLICE_PEAKRATE], NULL); if (P_tab == NULL) goto failure; } @@ -334,16 +334,14 @@ static __net_init int police_init_net(struct net *net) return tc_action_net_init(tn, &act_police_ops); } -static void __net_exit police_exit_net(struct net *net) +static void __net_exit police_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, police_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, police_net_id); } static struct pernet_operations police_net_ops = { .init = police_init_net, - .exit = police_exit_net, + .exit_batch = police_exit_net, .id = &police_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 9438969290a6..1ba0df238756 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -96,7 +96,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, return ret; } -static void tcf_sample_cleanup(struct tc_action *a, int bind) +static void tcf_sample_cleanup(struct tc_action *a) { struct tcf_sample *s = to_sample(a); struct psample_group *psample_group; @@ -236,16 +236,14 @@ static __net_init int sample_init_net(struct net *net) return tc_action_net_init(tn, &act_sample_ops); } -static void __net_exit sample_exit_net(struct net *net) +static void __net_exit sample_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, sample_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, sample_net_id); } static struct pernet_operations sample_net_ops = { .init = sample_init_net, - .exit = sample_exit_net, + .exit_batch = sample_exit_net, .id = &sample_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index e7b57e5071a3..425eac11f6da 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -47,7 +47,7 @@ static int tcf_simp(struct sk_buff *skb, const struct tc_action *a, return d->tcf_action; } -static void tcf_simp_release(struct tc_action *a, int bind) +static void tcf_simp_release(struct tc_action *a) { struct tcf_defact *d = to_defact(a); kfree(d->tcfd_defdata); @@ -204,16 +204,14 @@ static __net_init int simp_init_net(struct net *net) return tc_action_net_init(tn, &act_simp_ops); } -static void __net_exit simp_exit_net(struct net *net) +static void __net_exit simp_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, simp_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, simp_net_id); } static struct pernet_operations simp_net_ops = { .init = simp_init_net, - .exit = simp_exit_net, + .exit_batch = simp_exit_net, .id = &simp_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 59949d61f20d..5a3f691bb545 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -241,16 +241,14 @@ static __net_init int skbedit_init_net(struct net *net) return tc_action_net_init(tn, &act_skbedit_ops); } -static void __net_exit skbedit_exit_net(struct net *net) +static void __net_exit skbedit_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, skbedit_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, skbedit_net_id); } static struct pernet_operations skbedit_net_ops = { .init = skbedit_init_net, - .exit = skbedit_exit_net, + .exit_batch = skbedit_exit_net, .id = &skbedit_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index b642ad3d39dd..fa975262dbac 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -184,7 +184,7 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, return ret; } -static void tcf_skbmod_cleanup(struct tc_action *a, int bind) +static void tcf_skbmod_cleanup(struct tc_action *a) { struct tcf_skbmod *d = to_skbmod(a); struct tcf_skbmod_params *p; @@ -266,16 +266,14 @@ static __net_init int skbmod_init_net(struct net *net) return tc_action_net_init(tn, &act_skbmod_ops); } -static void __net_exit skbmod_exit_net(struct net *net) +static void __net_exit skbmod_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, skbmod_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, skbmod_net_id); } static struct pernet_operations skbmod_net_ops = { .init = skbmod_init_net, - .exit = skbmod_exit_net, + .exit_batch = skbmod_exit_net, .id = &skbmod_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 30c96274c638..0e23aac09ad6 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -201,7 +201,7 @@ err_out: return ret; } -static void tunnel_key_release(struct tc_action *a, int bind) +static void tunnel_key_release(struct tc_action *a) { struct tcf_tunnel_key *t = to_tunnel_key(a); struct tcf_tunnel_key_params *params; @@ -325,16 +325,14 @@ static __net_init int tunnel_key_init_net(struct net *net) return tc_action_net_init(tn, &act_tunnel_key_ops); } -static void __net_exit tunnel_key_exit_net(struct net *net) +static void __net_exit tunnel_key_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, tunnel_key_net_id); } static struct pernet_operations tunnel_key_net_ops = { .init = tunnel_key_init_net, - .exit = tunnel_key_exit_net, + .exit_batch = tunnel_key_exit_net, .id = &tunnel_key_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 97f717a13ad5..e1a1b3f3983a 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -219,7 +219,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, return ret; } -static void tcf_vlan_cleanup(struct tc_action *a, int bind) +static void tcf_vlan_cleanup(struct tc_action *a) { struct tcf_vlan *v = to_vlan(a); struct tcf_vlan_params *p; @@ -301,16 +301,14 @@ static __net_init int vlan_init_net(struct net *net) return tc_action_net_init(tn, &act_vlan_ops); } -static void __net_exit vlan_exit_net(struct net *net) +static void __net_exit vlan_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, vlan_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, vlan_net_id); } static struct pernet_operations vlan_net_ops = { .init = vlan_init_net, - .exit = vlan_exit_net, + .exit_batch = vlan_exit_net, .id = &vlan_net_id, .size = sizeof(struct tc_action_net), }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index b9d63d2246e6..bcb4ccb5f894 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -24,6 +24,7 @@ #include <linux/init.h> #include <linux/kmod.h> #include <linux/slab.h> +#include <linux/idr.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> @@ -121,8 +122,8 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) } static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, - u32 prio, u32 parent, struct Qdisc *q, - struct tcf_chain *chain) + u32 prio, struct tcf_chain *chain, + struct netlink_ext_ack *extack) { struct tcf_proto *tp; int err; @@ -148,6 +149,7 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, module_put(tp->ops->owner); err = -EAGAIN; } else { + NL_SET_ERR_MSG(extack, "TC classifier not found"); err = -ENOENT; } goto errout; @@ -156,8 +158,6 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, tp->classify = tp->ops->classify; tp->protocol = protocol; tp->prio = prio; - tp->classid = parent; - tp->q = q; tp->chain = chain; err = tp->ops->init(tp); @@ -172,13 +172,20 @@ errout: return ERR_PTR(err); } -static void tcf_proto_destroy(struct tcf_proto *tp) +static void tcf_proto_destroy(struct tcf_proto *tp, + struct netlink_ext_ack *extack) { - tp->ops->destroy(tp); + tp->ops->destroy(tp, extack); module_put(tp->ops->owner); kfree_rcu(tp, rcu); } +struct tcf_filter_chain_list_item { + struct list_head list; + tcf_chain_head_change_t *chain_head_change; + void *chain_head_change_priv; +}; + static struct tcf_chain *tcf_chain_create(struct tcf_block *block, u32 chain_index) { @@ -187,6 +194,7 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block, chain = kzalloc(sizeof(*chain), GFP_KERNEL); if (!chain) return NULL; + INIT_LIST_HEAD(&chain->filter_chain_list); list_add_tail(&chain->list, &block->chain_list); chain->block = block; chain->index = chain_index; @@ -194,12 +202,19 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block, return chain; } +static void tcf_chain_head_change_item(struct tcf_filter_chain_list_item *item, + struct tcf_proto *tp_head) +{ + if (item->chain_head_change) + item->chain_head_change(tp_head, item->chain_head_change_priv); +} static void tcf_chain_head_change(struct tcf_chain *chain, struct tcf_proto *tp_head) { - if (chain->chain_head_change) - chain->chain_head_change(tp_head, - chain->chain_head_change_priv); + struct tcf_filter_chain_list_item *item; + + list_for_each_entry(item, &chain->filter_chain_list, list) + tcf_chain_head_change_item(item, tp_head); } static void tcf_chain_flush(struct tcf_chain *chain) @@ -209,7 +224,7 @@ static void tcf_chain_flush(struct tcf_chain *chain) tcf_chain_head_change(chain, NULL); while (tp) { RCU_INIT_POINTER(chain->filter_chain, tp->next); - tcf_proto_destroy(tp); + tcf_proto_destroy(tp, NULL); tp = rtnl_dereference(chain->filter_chain); tcf_chain_put(chain); } @@ -217,8 +232,12 @@ static void tcf_chain_flush(struct tcf_chain *chain) static void tcf_chain_destroy(struct tcf_chain *chain) { + struct tcf_block *block = chain->block; + list_del(&chain->list); kfree(chain); + if (list_empty(&block->chain_list)) + kfree(block); } static void tcf_chain_hold(struct tcf_chain *chain) @@ -249,62 +268,300 @@ void tcf_chain_put(struct tcf_chain *chain) } EXPORT_SYMBOL(tcf_chain_put); -static void tcf_block_offload_cmd(struct tcf_block *block, struct Qdisc *q, - struct tcf_block_ext_info *ei, - enum tc_block_command command) +static bool tcf_block_offload_in_use(struct tcf_block *block) +{ + return block->offloadcnt; +} + +static int tcf_block_offload_cmd(struct tcf_block *block, + struct net_device *dev, + struct tcf_block_ext_info *ei, + enum tc_block_command command) { - struct net_device *dev = q->dev_queue->dev; struct tc_block_offload bo = {}; - if (!dev->netdev_ops->ndo_setup_tc) - return; bo.command = command; bo.binder_type = ei->binder_type; bo.block = block; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); } -static void tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, - struct tcf_block_ext_info *ei) +static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei) { - tcf_block_offload_cmd(block, q, ei, TC_BLOCK_BIND); + struct net_device *dev = q->dev_queue->dev; + int err; + + if (!dev->netdev_ops->ndo_setup_tc) + goto no_offload_dev_inc; + + /* If tc offload feature is disabled and the block we try to bind + * to already has some offloaded filters, forbid to bind. + */ + if (!tc_can_offload(dev) && tcf_block_offload_in_use(block)) + return -EOPNOTSUPP; + + err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND); + if (err == -EOPNOTSUPP) + goto no_offload_dev_inc; + return err; + +no_offload_dev_inc: + if (tcf_block_offload_in_use(block)) + return -EOPNOTSUPP; + block->nooffloaddevcnt++; + return 0; } static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q, struct tcf_block_ext_info *ei) { - tcf_block_offload_cmd(block, q, ei, TC_BLOCK_UNBIND); + struct net_device *dev = q->dev_queue->dev; + int err; + + if (!dev->netdev_ops->ndo_setup_tc) + goto no_offload_dev_dec; + err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND); + if (err == -EOPNOTSUPP) + goto no_offload_dev_dec; + return; + +no_offload_dev_dec: + WARN_ON(block->nooffloaddevcnt-- == 0); } -int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, - struct tcf_block_ext_info *ei) +static int +tcf_chain_head_change_cb_add(struct tcf_chain *chain, + struct tcf_block_ext_info *ei, + struct netlink_ext_ack *extack) +{ + struct tcf_filter_chain_list_item *item; + + item = kmalloc(sizeof(*item), GFP_KERNEL); + if (!item) { + NL_SET_ERR_MSG(extack, "Memory allocation for head change callback item failed"); + return -ENOMEM; + } + item->chain_head_change = ei->chain_head_change; + item->chain_head_change_priv = ei->chain_head_change_priv; + if (chain->filter_chain) + tcf_chain_head_change_item(item, chain->filter_chain); + list_add(&item->list, &chain->filter_chain_list); + return 0; +} + +static void +tcf_chain_head_change_cb_del(struct tcf_chain *chain, + struct tcf_block_ext_info *ei) +{ + struct tcf_filter_chain_list_item *item; + + list_for_each_entry(item, &chain->filter_chain_list, list) { + if ((!ei->chain_head_change && !ei->chain_head_change_priv) || + (item->chain_head_change == ei->chain_head_change && + item->chain_head_change_priv == ei->chain_head_change_priv)) { + tcf_chain_head_change_item(item, NULL); + list_del(&item->list); + kfree(item); + return; + } + } + WARN_ON(1); +} + +struct tcf_net { + struct idr idr; +}; + +static unsigned int tcf_net_id; + +static int tcf_block_insert(struct tcf_block *block, struct net *net, + u32 block_index, struct netlink_ext_ack *extack) +{ + struct tcf_net *tn = net_generic(net, tcf_net_id); + int err; + + err = idr_alloc_ext(&tn->idr, block, NULL, block_index, + block_index + 1, GFP_KERNEL); + if (err) + return err; + block->index = block_index; + return 0; +} + +static void tcf_block_remove(struct tcf_block *block, struct net *net) +{ + struct tcf_net *tn = net_generic(net, tcf_net_id); + + idr_remove_ext(&tn->idr, block->index); +} + +static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, + struct netlink_ext_ack *extack) { - struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL); + struct tcf_block *block; struct tcf_chain *chain; int err; - if (!block) - return -ENOMEM; + block = kzalloc(sizeof(*block), GFP_KERNEL); + if (!block) { + NL_SET_ERR_MSG(extack, "Memory allocation for block failed"); + return ERR_PTR(-ENOMEM); + } INIT_LIST_HEAD(&block->chain_list); INIT_LIST_HEAD(&block->cb_list); + INIT_LIST_HEAD(&block->owner_list); /* Create chain 0 by default, it has to be always present. */ chain = tcf_chain_create(block, 0); if (!chain) { + NL_SET_ERR_MSG(extack, "Failed to create new tcf chain"); err = -ENOMEM; goto err_chain_create; } - WARN_ON(!ei->chain_head_change); - chain->chain_head_change = ei->chain_head_change; - chain->chain_head_change_priv = ei->chain_head_change_priv; block->net = qdisc_net(q); + block->refcnt = 1; + block->net = net; block->q = q; - tcf_block_offload_bind(block, q, ei); - *p_block = block; - return 0; + return block; err_chain_create: kfree(block); + return ERR_PTR(err); +} + +static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index) +{ + struct tcf_net *tn = net_generic(net, tcf_net_id); + + return idr_find_ext(&tn->idr, block_index); +} + +static struct tcf_chain *tcf_block_chain_zero(struct tcf_block *block) +{ + return list_first_entry(&block->chain_list, struct tcf_chain, list); +} + +struct tcf_block_owner_item { + struct list_head list; + struct Qdisc *q; + enum tcf_block_binder_type binder_type; +}; + +static void +tcf_block_owner_netif_keep_dst(struct tcf_block *block, + struct Qdisc *q, + enum tcf_block_binder_type binder_type) +{ + if (block->keep_dst && + binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS && + binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS) + netif_keep_dst(qdisc_dev(q)); +} + +void tcf_block_netif_keep_dst(struct tcf_block *block) +{ + struct tcf_block_owner_item *item; + + block->keep_dst = true; + list_for_each_entry(item, &block->owner_list, list) + tcf_block_owner_netif_keep_dst(block, item->q, + item->binder_type); +} +EXPORT_SYMBOL(tcf_block_netif_keep_dst); + +static int tcf_block_owner_add(struct tcf_block *block, + struct Qdisc *q, + enum tcf_block_binder_type binder_type) +{ + struct tcf_block_owner_item *item; + + item = kmalloc(sizeof(*item), GFP_KERNEL); + if (!item) + return -ENOMEM; + item->q = q; + item->binder_type = binder_type; + list_add(&item->list, &block->owner_list); + return 0; +} + +static void tcf_block_owner_del(struct tcf_block *block, + struct Qdisc *q, + enum tcf_block_binder_type binder_type) +{ + struct tcf_block_owner_item *item; + + list_for_each_entry(item, &block->owner_list, list) { + if (item->q == q && item->binder_type == binder_type) { + list_del(&item->list); + kfree(item); + return; + } + } + WARN_ON(1); +} + +int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, + struct tcf_block_ext_info *ei, + struct netlink_ext_ack *extack) +{ + struct net *net = qdisc_net(q); + struct tcf_block *block = NULL; + bool created = false; + int err; + + if (ei->block_index) { + /* block_index not 0 means the shared block is requested */ + block = tcf_block_lookup(net, ei->block_index); + if (block) + block->refcnt++; + } + + if (!block) { + block = tcf_block_create(net, q, extack); + if (IS_ERR(block)) + return PTR_ERR(block); + created = true; + if (ei->block_index) { + err = tcf_block_insert(block, net, + ei->block_index, extack); + if (err) + goto err_block_insert; + } + } + + err = tcf_block_owner_add(block, q, ei->binder_type); + if (err) + goto err_block_owner_add; + + tcf_block_owner_netif_keep_dst(block, q, ei->binder_type); + + err = tcf_chain_head_change_cb_add(tcf_block_chain_zero(block), + ei, extack); + if (err) + goto err_chain_head_change_cb_add; + + err = tcf_block_offload_bind(block, q, ei); + if (err) + goto err_block_offload_bind; + + *p_block = block; + return 0; + +err_block_offload_bind: + tcf_chain_head_change_cb_del(tcf_block_chain_zero(block), ei); +err_chain_head_change_cb_add: + tcf_block_owner_del(block, q, ei->binder_type); +err_block_owner_add: + if (created) { + if (tcf_block_shared(block)) + tcf_block_remove(block, net); +err_block_insert: + kfree(tcf_block_chain_zero(block)); + kfree(block); + } else { + block->refcnt--; + } return err; } EXPORT_SYMBOL(tcf_block_get_ext); @@ -317,7 +574,8 @@ static void tcf_chain_head_change_dflt(struct tcf_proto *tp_head, void *priv) } int tcf_block_get(struct tcf_block **p_block, - struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q) + struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, + struct netlink_ext_ack *extack) { struct tcf_block_ext_info ei = { .chain_head_change = tcf_chain_head_change_dflt, @@ -325,53 +583,47 @@ int tcf_block_get(struct tcf_block **p_block, }; WARN_ON(!p_filter_chain); - return tcf_block_get_ext(p_block, q, &ei); + return tcf_block_get_ext(p_block, q, &ei, extack); } EXPORT_SYMBOL(tcf_block_get); -static void tcf_block_put_final(struct work_struct *work) -{ - struct tcf_block *block = container_of(work, struct tcf_block, work); - struct tcf_chain *chain, *tmp; - - rtnl_lock(); - - /* At this point, all the chains should have refcnt == 1. */ - list_for_each_entry_safe(chain, tmp, &block->chain_list, list) - tcf_chain_put(chain); - rtnl_unlock(); - kfree(block); -} - /* XXX: Standalone actions are not allowed to jump to any chain, and bound * actions should be all removed after flushing. */ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, struct tcf_block_ext_info *ei) { - struct tcf_chain *chain; + struct tcf_chain *chain, *tmp; if (!block) return; - /* Hold a refcnt for all chains, except 0, so that they don't disappear - * while we are iterating. - */ - list_for_each_entry(chain, &block->chain_list, list) - if (chain->index) + tcf_chain_head_change_cb_del(tcf_block_chain_zero(block), ei); + tcf_block_owner_del(block, q, ei->binder_type); + + if (--block->refcnt == 0) { + if (tcf_block_shared(block)) + tcf_block_remove(block, block->net); + + /* Hold a refcnt for all chains, so that they don't disappear + * while we are iterating. + */ + list_for_each_entry(chain, &block->chain_list, list) tcf_chain_hold(chain); - list_for_each_entry(chain, &block->chain_list, list) - tcf_chain_flush(chain); + list_for_each_entry(chain, &block->chain_list, list) + tcf_chain_flush(chain); + } tcf_block_offload_unbind(block, q, ei); - INIT_WORK(&block->work, tcf_block_put_final); - /* Wait for existing RCU callbacks to cool down, make sure their works - * have been queued before this. We can not flush pending works here - * because we are holding the RTNL lock. - */ - rcu_barrier(); - tcf_queue_work(&block->work); + if (block->refcnt == 0) { + /* At this point, all the chains should have refcnt >= 1. */ + list_for_each_entry_safe(chain, tmp, &block->chain_list, list) + tcf_chain_put(chain); + + /* Finally, put chain 0 and allow block to be freed. */ + tcf_chain_put(tcf_block_chain_zero(block)); + } } EXPORT_SYMBOL(tcf_block_put_ext); @@ -429,9 +681,16 @@ struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, { struct tcf_block_cb *block_cb; + /* At this point, playback of previous block cb calls is not supported, + * so forbid to register to block which already has some offloaded + * filters present. + */ + if (tcf_block_offload_in_use(block)) + return ERR_PTR(-EOPNOTSUPP); + block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL); if (!block_cb) - return NULL; + return ERR_PTR(-ENOMEM); block_cb->cb = cb; block_cb->cb_ident = cb_ident; block_cb->cb_priv = cb_priv; @@ -447,7 +706,7 @@ int tcf_block_cb_register(struct tcf_block *block, struct tcf_block_cb *block_cb; block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv); - return block_cb ? 0 : -ENOMEM; + return IS_ERR(block_cb) ? PTR_ERR(block_cb) : 0; } EXPORT_SYMBOL(tcf_block_cb_register); @@ -477,6 +736,10 @@ static int tcf_block_cb_call(struct tcf_block *block, enum tc_setup_type type, int ok_count = 0; int err; + /* Make sure all netdevs sharing this block are offload-capable. */ + if (block->nooffloaddevcnt && err_stop) + return -EOPNOTSUPP; + list_for_each_entry(block_cb, &block->cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err) { @@ -530,8 +793,9 @@ reclassify: #ifdef CONFIG_NET_CLS_ACT reset: if (unlikely(limit++ >= max_reclassify_loop)) { - net_notice_ratelimited("%s: reclassify loop, rule prio %u, protocol %02x\n", - tp->q->ops->id, tp->prio & 0xffff, + net_notice_ratelimited("%u: reclassify loop, rule prio %u, protocol %02x\n", + tp->chain->block->index, + tp->prio & 0xffff, ntohs(tp->protocol)); return TC_ACT_SHOT; } @@ -604,8 +868,9 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, } static int tcf_fill_node(struct net *net, struct sk_buff *skb, - struct tcf_proto *tp, struct Qdisc *q, u32 parent, - void *fh, u32 portid, u32 seq, u16 flags, int event) + struct tcf_proto *tp, struct tcf_block *block, + struct Qdisc *q, u32 parent, void *fh, + u32 portid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -618,8 +883,13 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, tcm->tcm_family = AF_UNSPEC; tcm->tcm__pad1 = 0; tcm->tcm__pad2 = 0; - tcm->tcm_ifindex = qdisc_dev(q)->ifindex; - tcm->tcm_parent = parent; + if (q) { + tcm->tcm_ifindex = qdisc_dev(q)->ifindex; + tcm->tcm_parent = parent; + } else { + tcm->tcm_ifindex = TCM_IFINDEX_MAGIC_BLOCK; + tcm->tcm_block_index = block->index; + } tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol); if (nla_put_string(skb, TCA_KIND, tp->ops->kind)) goto nla_put_failure; @@ -642,8 +912,8 @@ nla_put_failure: static int tfilter_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, - struct Qdisc *q, u32 parent, - void *fh, int event, bool unicast) + struct tcf_block *block, struct Qdisc *q, + u32 parent, void *fh, int event, bool unicast) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; @@ -652,8 +922,8 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq, - n->nlmsg_flags, event) <= 0) { + if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, + n->nlmsg_seq, n->nlmsg_flags, event) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -667,8 +937,9 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, - struct Qdisc *q, u32 parent, - void *fh, bool unicast, bool *last) + struct tcf_block *block, struct Qdisc *q, + u32 parent, void *fh, bool unicast, bool *last, + struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; @@ -678,13 +949,14 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq, - n->nlmsg_flags, RTM_DELTFILTER) <= 0) { + if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, + n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER) <= 0) { + NL_SET_ERR_MSG(extack, "Failed to build del event notification"); kfree_skb(skb); return -EINVAL; } - err = tp->ops->delete(tp, fh, last); + err = tp->ops->delete(tp, fh, last, extack); if (err) { kfree_skb(skb); return err; @@ -693,20 +965,24 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, if (unicast) return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT); - return rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); + err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); + if (err < 0) + NL_SET_ERR_MSG(extack, "Failed to send filter delete notification"); + return err; } static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, - struct Qdisc *q, u32 parent, - struct nlmsghdr *n, + struct tcf_block *block, struct Qdisc *q, + u32 parent, struct nlmsghdr *n, struct tcf_chain *chain, int event) { struct tcf_proto *tp; for (tp = rtnl_dereference(chain->filter_chain); tp; tp = rtnl_dereference(tp->next)) - tfilter_notify(net, oskb, n, tp, q, parent, 0, event, false); + tfilter_notify(net, oskb, n, tp, block, + q, parent, 0, event, false); } /* Add/change/delete/get a filter node */ @@ -722,13 +998,11 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, bool prio_allocate; u32 parent; u32 chain_index; - struct net_device *dev; - struct Qdisc *q; + struct Qdisc *q = NULL; struct tcf_chain_info chain_info; struct tcf_chain *chain = NULL; struct tcf_block *block; struct tcf_proto *tp; - const struct Qdisc_class_ops *cops; unsigned long cl; void *fh; int err; @@ -755,8 +1029,10 @@ replay: if (prio == 0) { switch (n->nlmsg_type) { case RTM_DELTFILTER: - if (protocol || t->tcm_handle || tca[TCA_KIND]) + if (protocol || t->tcm_handle || tca[TCA_KIND]) { + NL_SET_ERR_MSG(extack, "Cannot flush filters with protocol, handle or kind set"); return -ENOENT; + } break; case RTM_NEWTFILTER: /* If no priority is provided by the user, @@ -769,63 +1045,91 @@ replay: } /* fall-through */ default: + NL_SET_ERR_MSG(extack, "Invalid filter command with priority of zero"); return -ENOENT; } } /* Find head of filter chain. */ - /* Find link */ - dev = __dev_get_by_index(net, t->tcm_ifindex); - if (dev == NULL) - return -ENODEV; - - /* Find qdisc */ - if (!parent) { - q = dev->qdisc; - parent = q->handle; + if (t->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) { + block = tcf_block_lookup(net, t->tcm_block_index); + if (!block) { + NL_SET_ERR_MSG(extack, "Block of given index was not found"); + err = -EINVAL; + goto errout; + } } else { - q = qdisc_lookup(dev, TC_H_MAJ(t->tcm_parent)); - if (q == NULL) - return -EINVAL; - } + const struct Qdisc_class_ops *cops; + struct net_device *dev; - /* Is it classful? */ - cops = q->ops->cl_ops; - if (!cops) - return -EINVAL; + /* Find link */ + dev = __dev_get_by_index(net, t->tcm_ifindex); + if (!dev) + return -ENODEV; - if (!cops->tcf_block) - return -EOPNOTSUPP; + /* Find qdisc */ + if (!parent) { + q = dev->qdisc; + parent = q->handle; + } else { + q = qdisc_lookup(dev, TC_H_MAJ(t->tcm_parent)); + if (!q) { + NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); + return -EINVAL; + } + } - /* Do we search for filter, attached to class? */ - if (TC_H_MIN(parent)) { - cl = cops->find(q, parent); - if (cl == 0) - return -ENOENT; - } + /* Is it classful? */ + cops = q->ops->cl_ops; + if (!cops) { + NL_SET_ERR_MSG(extack, "Qdisc not classful"); + return -EINVAL; + } - /* And the last stroke */ - block = cops->tcf_block(q, cl); - if (!block) { - err = -EINVAL; - goto errout; + if (!cops->tcf_block) { + NL_SET_ERR_MSG(extack, "Class doesn't support blocks"); + return -EOPNOTSUPP; + } + + /* Do we search for filter, attached to class? */ + if (TC_H_MIN(parent)) { + cl = cops->find(q, parent); + if (cl == 0) { + NL_SET_ERR_MSG(extack, "Specified class doesn't exist"); + return -ENOENT; + } + } + + /* And the last stroke */ + block = cops->tcf_block(q, cl, extack); + if (!block) { + err = -EINVAL; + goto errout; + } + if (tcf_block_shared(block)) { + NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters"); + err = -EOPNOTSUPP; + goto errout; + } } chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; if (chain_index > TC_ACT_EXT_VAL_MASK) { + NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); err = -EINVAL; goto errout; } chain = tcf_chain_get(block, chain_index, n->nlmsg_type == RTM_NEWTFILTER); if (!chain) { + NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); err = n->nlmsg_type == RTM_NEWTFILTER ? -ENOMEM : -EINVAL; goto errout; } if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) { - tfilter_notify_chain(net, skb, q, parent, n, + tfilter_notify_chain(net, skb, block, q, parent, n, chain, RTM_DELTFILTER); tcf_chain_flush(chain); err = 0; @@ -835,6 +1139,7 @@ replay: tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, prio_allocate); if (IS_ERR(tp)) { + NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); err = PTR_ERR(tp); goto errout; } @@ -843,12 +1148,14 @@ replay: /* Proto-tcf does not exist, create new one */ if (tca[TCA_KIND] == NULL || !protocol) { + NL_SET_ERR_MSG(extack, "Filter kind and protocol must be specified"); err = -EINVAL; goto errout; } if (n->nlmsg_type != RTM_NEWTFILTER || !(n->nlmsg_flags & NLM_F_CREATE)) { + NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter"); err = -ENOENT; goto errout; } @@ -857,13 +1164,14 @@ replay: prio = tcf_auto_prio(tcf_chain_tp_prev(&chain_info)); tp = tcf_proto_create(nla_data(tca[TCA_KIND]), - protocol, prio, parent, q, chain); + protocol, prio, chain, extack); if (IS_ERR(tp)) { err = PTR_ERR(tp); goto errout; } tp_created = 1; } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { + NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one"); err = -EINVAL; goto errout; } @@ -873,15 +1181,16 @@ replay: if (!fh) { if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) { tcf_chain_tp_remove(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, q, parent, fh, + tfilter_notify(net, skb, n, tp, block, q, parent, fh, RTM_DELTFILTER, false); - tcf_proto_destroy(tp); + tcf_proto_destroy(tp, extack); err = 0; goto errout; } if (n->nlmsg_type != RTM_NEWTFILTER || !(n->nlmsg_flags & NLM_F_CREATE)) { + NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter"); err = -ENOENT; goto errout; } @@ -892,41 +1201,47 @@ replay: case RTM_NEWTFILTER: if (n->nlmsg_flags & NLM_F_EXCL) { if (tp_created) - tcf_proto_destroy(tp); + tcf_proto_destroy(tp, NULL); + NL_SET_ERR_MSG(extack, "Filter already exists"); err = -EEXIST; goto errout; } break; case RTM_DELTFILTER: - err = tfilter_del_notify(net, skb, n, tp, q, parent, - fh, false, &last); + err = tfilter_del_notify(net, skb, n, tp, block, + q, parent, fh, false, &last, + extack); if (err) goto errout; if (last) { tcf_chain_tp_remove(chain, &chain_info, tp); - tcf_proto_destroy(tp); + tcf_proto_destroy(tp, extack); } goto errout; case RTM_GETTFILTER: - err = tfilter_notify(net, skb, n, tp, q, parent, fh, - RTM_NEWTFILTER, true); + err = tfilter_notify(net, skb, n, tp, block, q, parent, + fh, RTM_NEWTFILTER, true); + if (err < 0) + NL_SET_ERR_MSG(extack, "Failed to send filter notify message"); goto errout; default: + NL_SET_ERR_MSG(extack, "Invalid netlink message type"); err = -EINVAL; goto errout; } } err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, - n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE); + n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE, + extack); if (err == 0) { if (tp_created) tcf_chain_tp_insert(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, q, parent, fh, + tfilter_notify(net, skb, n, tp, block, q, parent, fh, RTM_NEWTFILTER, false); } else { if (tp_created) - tcf_proto_destroy(tp); + tcf_proto_destroy(tp, NULL); } errout: @@ -942,6 +1257,7 @@ struct tcf_dump_args { struct tcf_walker w; struct sk_buff *skb; struct netlink_callback *cb; + struct tcf_block *block; struct Qdisc *q; u32 parent; }; @@ -951,7 +1267,7 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) struct tcf_dump_args *a = (void *)arg; struct net *net = sock_net(a->skb->sk); - return tcf_fill_node(net, a->skb, tp, a->q, a->parent, + return tcf_fill_node(net, a->skb, tp, a->block, a->q, a->parent, n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER); @@ -962,6 +1278,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, long index_start, long *p_index) { struct net *net = sock_net(skb->sk); + struct tcf_block *block = chain->block; struct tcmsg *tcm = nlmsg_data(cb->nlh); struct tcf_dump_args arg; struct tcf_proto *tp; @@ -980,7 +1297,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (cb->args[1] == 0) { - if (tcf_fill_node(net, skb, tp, q, parent, 0, + if (tcf_fill_node(net, skb, tp, block, q, parent, 0, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER) <= 0) @@ -993,6 +1310,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, arg.w.fn = tcf_node_dump; arg.skb = skb; arg.cb = cb; + arg.block = block; arg.q = q; arg.parent = parent; arg.w.stop = 0; @@ -1011,13 +1329,10 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; - struct net_device *dev; - struct Qdisc *q; + struct Qdisc *q = NULL; struct tcf_block *block; struct tcf_chain *chain; struct tcmsg *tcm = nlmsg_data(cb->nlh); - unsigned long cl = 0; - const struct Qdisc_class_ops *cops; long index_start; long index; u32 parent; @@ -1030,32 +1345,51 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (err) return err; - dev = __dev_get_by_index(net, tcm->tcm_ifindex); - if (!dev) - return skb->len; - - parent = tcm->tcm_parent; - if (!parent) { - q = dev->qdisc; - parent = q->handle; + if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) { + block = tcf_block_lookup(net, tcm->tcm_block_index); + if (!block) + goto out; + /* If we work with block index, q is NULL and parent value + * will never be used in the following code. The check + * in tcf_fill_node prevents it. However, compiler does not + * see that far, so set parent to zero to silence the warning + * about parent being uninitialized. + */ + parent = 0; } else { - q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); - } - if (!q) - goto out; - cops = q->ops->cl_ops; - if (!cops) - goto out; - if (!cops->tcf_block) - goto out; - if (TC_H_MIN(tcm->tcm_parent)) { - cl = cops->find(q, tcm->tcm_parent); - if (cl == 0) + const struct Qdisc_class_ops *cops; + struct net_device *dev; + unsigned long cl = 0; + + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) + return skb->len; + + parent = tcm->tcm_parent; + if (!parent) { + q = dev->qdisc; + parent = q->handle; + } else { + q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); + } + if (!q) + goto out; + cops = q->ops->cl_ops; + if (!cops) + goto out; + if (!cops->tcf_block) + goto out; + if (TC_H_MIN(tcm->tcm_parent)) { + cl = cops->find(q, tcm->tcm_parent); + if (cl == 0) + goto out; + } + block = cops->tcf_block(q, cl, NULL); + if (!block) goto out; + if (tcf_block_shared(block)) + q = NULL; } - block = cops->tcf_block(q, cl); - if (!block) - goto out; index_start = cb->args[0]; index = 0; @@ -1090,7 +1424,8 @@ void tcf_exts_destroy(struct tcf_exts *exts) EXPORT_SYMBOL(tcf_exts_destroy); int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, - struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr) + struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr, + struct netlink_ext_ack *extack) { #ifdef CONFIG_NET_CLS_ACT { @@ -1123,8 +1458,10 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, } #else if ((exts->action && tb[exts->action]) || - (exts->police && tb[exts->police])) + (exts->police && tb[exts->police])) { + NL_SET_ERR_MSG(extack, "Classifier actions are not supported per compile options (CONFIG_NET_CLS_ACT)"); return -EOPNOTSUPP; + } #endif return 0; @@ -1258,18 +1595,50 @@ int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts, } EXPORT_SYMBOL(tc_setup_cb_call); +static __net_init int tcf_net_init(struct net *net) +{ + struct tcf_net *tn = net_generic(net, tcf_net_id); + + idr_init(&tn->idr); + return 0; +} + +static void __net_exit tcf_net_exit(struct net *net) +{ + struct tcf_net *tn = net_generic(net, tcf_net_id); + + idr_destroy(&tn->idr); +} + +static struct pernet_operations tcf_net_ops = { + .init = tcf_net_init, + .exit = tcf_net_exit, + .id = &tcf_net_id, + .size = sizeof(struct tcf_net), +}; + static int __init tc_filter_init(void) { + int err; + tc_filter_wq = alloc_ordered_workqueue("tc_filter_workqueue", 0); if (!tc_filter_wq) return -ENOMEM; + err = register_pernet_subsys(&tcf_net_ops); + if (err) + goto err_register_pernet_subsys; + rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_ctl_tfilter, tc_dump_tfilter, 0); return 0; + +err_register_pernet_subsys: + destroy_workqueue(tc_filter_wq); + return err; } subsys_initcall(tc_filter_init); diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 5f169ded347e..d333f5c5101d 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -112,7 +112,7 @@ static void basic_delete_filter(struct rcu_head *head) tcf_queue_work(&f->work); } -static void basic_destroy(struct tcf_proto *tp) +static void basic_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f, *n; @@ -130,7 +130,8 @@ static void basic_destroy(struct tcf_proto *tp) kfree_rcu(head, rcu); } -static int basic_delete(struct tcf_proto *tp, void *arg, bool *last) +static int basic_delete(struct tcf_proto *tp, void *arg, bool *last, + struct netlink_ext_ack *extack) { struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f = arg; @@ -152,11 +153,12 @@ static const struct nla_policy basic_policy[TCA_BASIC_MAX + 1] = { static int basic_set_parms(struct net *net, struct tcf_proto *tp, struct basic_filter *f, unsigned long base, struct nlattr **tb, - struct nlattr *est, bool ovr) + struct nlattr *est, bool ovr, + struct netlink_ext_ack *extack) { int err; - err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, extack); if (err < 0) return err; @@ -175,7 +177,8 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp, static int basic_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, void **arg, bool ovr) + struct nlattr **tca, void **arg, bool ovr, + struct netlink_ext_ack *extack) { int err; struct basic_head *head = rtnl_dereference(tp->root); @@ -221,7 +224,8 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, fnew->handle = idr_index; } - err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], ovr); + err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], ovr, + extack); if (err < 0) { if (!fold) idr_remove_ext(&head->handle_idr, fnew->handle); diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index a62586e2dbdb..8e5326bc6440 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -147,7 +147,8 @@ static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog) } static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, - struct cls_bpf_prog *oldprog) + struct cls_bpf_prog *oldprog, + struct netlink_ext_ack *extack) { struct tcf_block *block = tp->chain->block; struct tc_cls_bpf_offload cls_bpf = {}; @@ -158,22 +159,25 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, skip_sw = prog && tc_skip_sw(prog->gen_flags); obj = prog ?: oldprog; - tc_cls_common_offload_init(&cls_bpf.common, tp); + tc_cls_common_offload_init(&cls_bpf.common, tp, obj->gen_flags, + extack); cls_bpf.command = TC_CLSBPF_OFFLOAD; cls_bpf.exts = &obj->exts; cls_bpf.prog = prog ? prog->filter : NULL; cls_bpf.oldprog = oldprog ? oldprog->filter : NULL; cls_bpf.name = obj->bpf_name; cls_bpf.exts_integrated = obj->exts_integrated; - cls_bpf.gen_flags = obj->gen_flags; + + if (oldprog) + tcf_block_offload_dec(block, &oldprog->gen_flags); err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, skip_sw); if (prog) { if (err < 0) { - cls_bpf_offload_cmd(tp, oldprog, prog); + cls_bpf_offload_cmd(tp, oldprog, prog, extack); return err; } else if (err > 0) { - prog->gen_flags |= TCA_CLS_FLAGS_IN_HW; + tcf_block_offload_inc(block, &prog->gen_flags); } } @@ -189,7 +193,8 @@ static u32 cls_bpf_flags(u32 flags) } static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, - struct cls_bpf_prog *oldprog) + struct cls_bpf_prog *oldprog, + struct netlink_ext_ack *extack) { if (prog && oldprog && cls_bpf_flags(prog->gen_flags) != @@ -203,15 +208,16 @@ static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, if (!prog && !oldprog) return 0; - return cls_bpf_offload_cmd(tp, prog, oldprog); + return cls_bpf_offload_cmd(tp, prog, oldprog, extack); } static void cls_bpf_stop_offload(struct tcf_proto *tp, - struct cls_bpf_prog *prog) + struct cls_bpf_prog *prog, + struct netlink_ext_ack *extack) { int err; - err = cls_bpf_offload_cmd(tp, NULL, prog); + err = cls_bpf_offload_cmd(tp, NULL, prog, extack); if (err) pr_err("Stopping hardware offload failed: %d\n", err); } @@ -222,13 +228,12 @@ static void cls_bpf_offload_update_stats(struct tcf_proto *tp, struct tcf_block *block = tp->chain->block; struct tc_cls_bpf_offload cls_bpf = {}; - tc_cls_common_offload_init(&cls_bpf.common, tp); + tc_cls_common_offload_init(&cls_bpf.common, tp, prog->gen_flags, NULL); cls_bpf.command = TC_CLSBPF_STATS; cls_bpf.exts = &prog->exts; cls_bpf.prog = prog->filter; cls_bpf.name = prog->bpf_name; cls_bpf.exts_integrated = prog->exts_integrated; - cls_bpf.gen_flags = prog->gen_flags; tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, false); } @@ -285,12 +290,13 @@ static void cls_bpf_delete_prog_rcu(struct rcu_head *rcu) tcf_queue_work(&prog->work); } -static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog) +static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog, + struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); idr_remove_ext(&head->handle_idr, prog->handle); - cls_bpf_stop_offload(tp, prog); + cls_bpf_stop_offload(tp, prog, extack); list_del_rcu(&prog->link); tcf_unbind_filter(tp, &prog->res); if (tcf_exts_get_net(&prog->exts)) @@ -299,22 +305,24 @@ static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog) __cls_bpf_delete_prog(prog); } -static int cls_bpf_delete(struct tcf_proto *tp, void *arg, bool *last) +static int cls_bpf_delete(struct tcf_proto *tp, void *arg, bool *last, + struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); - __cls_bpf_delete(tp, arg); + __cls_bpf_delete(tp, arg, extack); *last = list_empty(&head->plist); return 0; } -static void cls_bpf_destroy(struct tcf_proto *tp) +static void cls_bpf_destroy(struct tcf_proto *tp, + struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); struct cls_bpf_prog *prog, *tmp; list_for_each_entry_safe(prog, tmp, &head->plist, link) - __cls_bpf_delete(tp, prog); + __cls_bpf_delete(tp, prog, extack); idr_destroy(&head->handle_idr); kfree_rcu(head, rcu); @@ -399,15 +407,16 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, prog->bpf_name = name; prog->filter = fp; - if (fp->dst_needed && !(tp->q->flags & TCQ_F_INGRESS)) - netif_keep_dst(qdisc_dev(tp->q)); + if (fp->dst_needed) + tcf_block_netif_keep_dst(tp->chain->block); return 0; } static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, struct cls_bpf_prog *prog, unsigned long base, - struct nlattr **tb, struct nlattr *est, bool ovr) + struct nlattr **tb, struct nlattr *est, bool ovr, + struct netlink_ext_ack *extack) { bool is_bpf, is_ebpf, have_exts = false; u32 gen_flags = 0; @@ -418,7 +427,7 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) return -EINVAL; - ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, ovr); + ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, ovr, extack); if (ret < 0) return ret; @@ -456,7 +465,7 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr) + void **arg, bool ovr, struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); struct cls_bpf_prog *oldprog = *arg; @@ -504,11 +513,12 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, prog->handle = handle; } - ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], ovr); + ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], ovr, + extack); if (ret < 0) goto errout_idr; - ret = cls_bpf_offload(tp, prog, oldprog); + ret = cls_bpf_offload(tp, prog, oldprog, extack); if (ret) goto errout_parms; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 309d5899265f..762da5c0cf5e 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -91,7 +91,8 @@ static void cls_cgroup_destroy_rcu(struct rcu_head *root) static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr) + void **arg, bool ovr, + struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_CGROUP_MAX + 1]; struct cls_cgroup_head *head = rtnl_dereference(tp->root); @@ -121,7 +122,8 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &new->exts, ovr); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &new->exts, ovr, + extack); if (err < 0) goto errout; @@ -141,7 +143,8 @@ errout: return err; } -static void cls_cgroup_destroy(struct tcf_proto *tp) +static void cls_cgroup_destroy(struct tcf_proto *tp, + struct netlink_ext_ack *extack) { struct cls_cgroup_head *head = rtnl_dereference(tp->root); @@ -154,7 +157,8 @@ static void cls_cgroup_destroy(struct tcf_proto *tp) } } -static int cls_cgroup_delete(struct tcf_proto *tp, void *arg, bool *last) +static int cls_cgroup_delete(struct tcf_proto *tp, void *arg, bool *last, + struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 25c2a888e1f0..cd5fe383afdd 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -401,7 +401,7 @@ static void flow_destroy_filter(struct rcu_head *head) static int flow_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr) + void **arg, bool ovr, struct netlink_ext_ack *extack) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *fold, *fnew; @@ -454,7 +454,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto err2; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &fnew->exts, ovr); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &fnew->exts, ovr, + extack); if (err < 0) goto err2; @@ -526,7 +527,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, timer_setup(&fnew->perturb_timer, flow_perturbation, TIMER_DEFERRABLE); - netif_keep_dst(qdisc_dev(tp->q)); + tcf_block_netif_keep_dst(tp->chain->block); if (tb[TCA_FLOW_KEYS]) { fnew->keymask = keymask; @@ -574,7 +575,8 @@ err1: return err; } -static int flow_delete(struct tcf_proto *tp, void *arg, bool *last) +static int flow_delete(struct tcf_proto *tp, void *arg, bool *last, + struct netlink_ext_ack *extack) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f = arg; @@ -598,7 +600,7 @@ static int flow_init(struct tcf_proto *tp) return 0; } -static void flow_destroy(struct tcf_proto *tp) +static void flow_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f, *next; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 543a3e875d05..dc9acaafc0a8 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -166,6 +166,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, * so do it rather here. */ skb_key.basic.n_proto = skb->protocol; + skb_flow_dissect_tunnel_info(skb, &head->dissector, &skb_key); skb_flow_dissect(skb, &head->dissector, &skb_key, 0); fl_set_masked_key(&skb_mkey, &skb_key, &head->mask); @@ -217,30 +218,33 @@ static void fl_destroy_filter(struct rcu_head *head) tcf_queue_work(&f->work); } -static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f) +static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f, + struct netlink_ext_ack *extack) { struct tc_cls_flower_offload cls_flower = {}; struct tcf_block *block = tp->chain->block; - tc_cls_common_offload_init(&cls_flower.common, tp); + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); cls_flower.command = TC_CLSFLOWER_DESTROY; cls_flower.cookie = (unsigned long) f; tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER, &cls_flower, false); + tcf_block_offload_dec(block, &f->flags); } static int fl_hw_replace_filter(struct tcf_proto *tp, struct flow_dissector *dissector, struct fl_flow_key *mask, - struct cls_fl_filter *f) + struct cls_fl_filter *f, + struct netlink_ext_ack *extack) { struct tc_cls_flower_offload cls_flower = {}; struct tcf_block *block = tp->chain->block; bool skip_sw = tc_skip_sw(f->flags); int err; - tc_cls_common_offload_init(&cls_flower.common, tp); + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); cls_flower.command = TC_CLSFLOWER_REPLACE; cls_flower.cookie = (unsigned long) f; cls_flower.dissector = dissector; @@ -252,10 +256,10 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, err = tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER, &cls_flower, skip_sw); if (err < 0) { - fl_hw_destroy_filter(tp, f); + fl_hw_destroy_filter(tp, f, NULL); return err; } else if (err > 0) { - f->flags |= TCA_CLS_FLAGS_IN_HW; + tcf_block_offload_inc(block, &f->flags); } if (skip_sw && !(f->flags & TCA_CLS_FLAGS_IN_HW)) @@ -269,7 +273,7 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) struct tc_cls_flower_offload cls_flower = {}; struct tcf_block *block = tp->chain->block; - tc_cls_common_offload_init(&cls_flower.common, tp); + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, NULL); cls_flower.command = TC_CLSFLOWER_STATS; cls_flower.cookie = (unsigned long) f; cls_flower.exts = &f->exts; @@ -279,14 +283,15 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) &cls_flower, false); } -static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f) +static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, + struct netlink_ext_ack *extack) { struct cls_fl_head *head = rtnl_dereference(tp->root); idr_remove_ext(&head->handle_idr, f->handle); list_del_rcu(&f->list); if (!tc_skip_hw(f->flags)) - fl_hw_destroy_filter(tp, f); + fl_hw_destroy_filter(tp, f, extack); tcf_unbind_filter(tp, &f->res); if (tcf_exts_get_net(&f->exts)) call_rcu(&f->rcu, fl_destroy_filter); @@ -312,13 +317,13 @@ static void fl_destroy_rcu(struct rcu_head *rcu) schedule_work(&head->work); } -static void fl_destroy(struct tcf_proto *tp) +static void fl_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f, *next; list_for_each_entry_safe(f, next, &head->filters, list) - __fl_delete(tp, f); + __fl_delete(tp, f, extack); idr_destroy(&head->handle_idr); __module_get(THIS_MODULE); @@ -524,13 +529,14 @@ static void fl_set_key_ip(struct nlattr **tb, } static int fl_set_key(struct net *net, struct nlattr **tb, - struct fl_flow_key *key, struct fl_flow_key *mask) + struct fl_flow_key *key, struct fl_flow_key *mask, + struct netlink_ext_ack *extack) { __be16 ethertype; int ret = 0; #ifdef CONFIG_NET_CLS_IND if (tb[TCA_FLOWER_INDEV]) { - int err = tcf_change_indev(net, tb[TCA_FLOWER_INDEV]); + int err = tcf_change_indev(net, tb[TCA_FLOWER_INDEV], extack); if (err < 0) return err; key->indev_ifindex = err; @@ -825,11 +831,12 @@ static int fl_check_assign_mask(struct cls_fl_head *head, static int fl_set_parms(struct net *net, struct tcf_proto *tp, struct cls_fl_filter *f, struct fl_flow_mask *mask, unsigned long base, struct nlattr **tb, - struct nlattr *est, bool ovr) + struct nlattr *est, bool ovr, + struct netlink_ext_ack *extack) { int err; - err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, extack); if (err < 0) return err; @@ -838,7 +845,7 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp, tcf_bind_filter(tp, &f->res, base); } - err = fl_set_key(net, tb, &f->key, &mask->key); + err = fl_set_key(net, tb, &f->key, &mask->key, extack); if (err) return err; @@ -851,7 +858,7 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp, static int fl_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr) + void **arg, bool ovr, struct netlink_ext_ack *extack) { struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *fold = *arg; @@ -914,7 +921,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, } } - err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr); + err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr, + extack); if (err) goto errout_idr; @@ -938,7 +946,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, err = fl_hw_replace_filter(tp, &head->dissector, &mask.key, - fnew); + fnew, + extack); if (err) goto errout_idr; } @@ -951,7 +960,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, rhashtable_remove_fast(&head->ht, &fold->ht_node, head->ht_params); if (!tc_skip_hw(fold->flags)) - fl_hw_destroy_filter(tp, fold); + fl_hw_destroy_filter(tp, fold, NULL); } *arg = fnew; @@ -981,7 +990,8 @@ errout_tb: return err; } -static int fl_delete(struct tcf_proto *tp, void *arg, bool *last) +static int fl_delete(struct tcf_proto *tp, void *arg, bool *last, + struct netlink_ext_ack *extack) { struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f = arg; @@ -989,7 +999,7 @@ static int fl_delete(struct tcf_proto *tp, void *arg, bool *last) if (!tc_skip_sw(f->flags)) rhashtable_remove_fast(&head->ht, &f->ht_node, head->ht_params); - __fl_delete(tp, f); + __fl_delete(tp, f, extack); *last = list_empty(&head->filters); return 0; } diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 20f0de1a960a..8b207723fbc2 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -149,7 +149,7 @@ static void fw_delete_filter(struct rcu_head *head) tcf_queue_work(&f->work); } -static void fw_destroy(struct tcf_proto *tp) +static void fw_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f; @@ -172,7 +172,8 @@ static void fw_destroy(struct tcf_proto *tp) kfree_rcu(head, rcu); } -static int fw_delete(struct tcf_proto *tp, void *arg, bool *last) +static int fw_delete(struct tcf_proto *tp, void *arg, bool *last, + struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f = arg; @@ -218,13 +219,15 @@ static const struct nla_policy fw_policy[TCA_FW_MAX + 1] = { static int fw_set_parms(struct net *net, struct tcf_proto *tp, struct fw_filter *f, struct nlattr **tb, - struct nlattr **tca, unsigned long base, bool ovr) + struct nlattr **tca, unsigned long base, bool ovr, + struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); u32 mask; int err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &f->exts, ovr); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &f->exts, ovr, + extack); if (err < 0) return err; @@ -236,7 +239,7 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, #ifdef CONFIG_NET_CLS_IND if (tb[TCA_FW_INDEV]) { int ret; - ret = tcf_change_indev(net, tb[TCA_FW_INDEV]); + ret = tcf_change_indev(net, tb[TCA_FW_INDEV], extack); if (ret < 0) return ret; f->ifindex = ret; @@ -257,7 +260,7 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, static int fw_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, void **arg, - bool ovr) + bool ovr, struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f = *arg; @@ -296,7 +299,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, return err; } - err = fw_set_parms(net, tp, fnew, tb, tca, base, ovr); + err = fw_set_parms(net, tp, fnew, tb, tca, base, ovr, extack); if (err < 0) { tcf_exts_destroy(&fnew->exts); kfree(fnew); @@ -345,7 +348,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, f->id = handle; f->tp = tp; - err = fw_set_parms(net, tp, f, tb, tca, base, ovr); + err = fw_set_parms(net, tp, f, tb, tca, base, ovr, extack); if (err < 0) goto errout; diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 66d4e0099158..2ba721a590a7 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -71,28 +71,31 @@ static void mall_destroy_rcu(struct rcu_head *rcu) static void mall_destroy_hw_filter(struct tcf_proto *tp, struct cls_mall_head *head, - unsigned long cookie) + unsigned long cookie, + struct netlink_ext_ack *extack) { struct tc_cls_matchall_offload cls_mall = {}; struct tcf_block *block = tp->chain->block; - tc_cls_common_offload_init(&cls_mall.common, tp); + tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack); cls_mall.command = TC_CLSMATCHALL_DESTROY; cls_mall.cookie = cookie; tc_setup_cb_call(block, NULL, TC_SETUP_CLSMATCHALL, &cls_mall, false); + tcf_block_offload_dec(block, &head->flags); } static int mall_replace_hw_filter(struct tcf_proto *tp, struct cls_mall_head *head, - unsigned long cookie) + unsigned long cookie, + struct netlink_ext_ack *extack) { struct tc_cls_matchall_offload cls_mall = {}; struct tcf_block *block = tp->chain->block; bool skip_sw = tc_skip_sw(head->flags); int err; - tc_cls_common_offload_init(&cls_mall.common, tp); + tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack); cls_mall.command = TC_CLSMATCHALL_REPLACE; cls_mall.exts = &head->exts; cls_mall.cookie = cookie; @@ -100,10 +103,10 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSMATCHALL, &cls_mall, skip_sw); if (err < 0) { - mall_destroy_hw_filter(tp, head, cookie); + mall_destroy_hw_filter(tp, head, cookie, NULL); return err; } else if (err > 0) { - head->flags |= TCA_CLS_FLAGS_IN_HW; + tcf_block_offload_inc(block, &head->flags); } if (skip_sw && !(head->flags & TCA_CLS_FLAGS_IN_HW)) @@ -112,7 +115,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, return 0; } -static void mall_destroy(struct tcf_proto *tp) +static void mall_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct cls_mall_head *head = rtnl_dereference(tp->root); @@ -120,7 +123,7 @@ static void mall_destroy(struct tcf_proto *tp) return; if (!tc_skip_hw(head->flags)) - mall_destroy_hw_filter(tp, head, (unsigned long) head); + mall_destroy_hw_filter(tp, head, (unsigned long) head, extack); if (tcf_exts_get_net(&head->exts)) call_rcu(&head->rcu, mall_destroy_rcu); @@ -141,11 +144,12 @@ static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = { static int mall_set_parms(struct net *net, struct tcf_proto *tp, struct cls_mall_head *head, unsigned long base, struct nlattr **tb, - struct nlattr *est, bool ovr) + struct nlattr *est, bool ovr, + struct netlink_ext_ack *extack) { int err; - err = tcf_exts_validate(net, tp, tb, est, &head->exts, ovr); + err = tcf_exts_validate(net, tp, tb, est, &head->exts, ovr, extack); if (err < 0) return err; @@ -159,7 +163,7 @@ static int mall_set_parms(struct net *net, struct tcf_proto *tp, static int mall_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr) + void **arg, bool ovr, struct netlink_ext_ack *extack) { struct cls_mall_head *head = rtnl_dereference(tp->root); struct nlattr *tb[TCA_MATCHALL_MAX + 1]; @@ -197,12 +201,14 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, new->handle = handle; new->flags = flags; - err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], ovr); + err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], ovr, + extack); if (err) goto err_set_parms; if (!tc_skip_hw(new->flags)) { - err = mall_replace_hw_filter(tp, new, (unsigned long) new); + err = mall_replace_hw_filter(tp, new, (unsigned long)new, + extack); if (err) goto err_replace_hw_filter; } @@ -222,7 +228,8 @@ err_exts_init: return err; } -static int mall_delete(struct tcf_proto *tp, void *arg, bool *last) +static int mall_delete(struct tcf_proto *tp, void *arg, bool *last, + struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index ac9a5b8825b9..21a03a8ee029 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -281,7 +281,7 @@ static void route4_delete_filter(struct rcu_head *head) tcf_queue_work(&f->work); } -static void route4_destroy(struct tcf_proto *tp) +static void route4_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); int h1, h2; @@ -316,7 +316,8 @@ static void route4_destroy(struct tcf_proto *tp) kfree_rcu(head, rcu); } -static int route4_delete(struct tcf_proto *tp, void *arg, bool *last) +static int route4_delete(struct tcf_proto *tp, void *arg, bool *last, + struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); struct route4_filter *f = arg; @@ -389,7 +390,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct route4_filter *f, u32 handle, struct route4_head *head, struct nlattr **tb, struct nlattr *est, int new, - bool ovr) + bool ovr, struct netlink_ext_ack *extack) { u32 id = 0, to = 0, nhandle = 0x8000; struct route4_filter *fp; @@ -397,7 +398,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, struct route4_bucket *b; int err; - err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, extack); if (err < 0) return err; @@ -471,7 +472,8 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, static int route4_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, void **arg, bool ovr) + struct nlattr **tca, void **arg, bool ovr, + struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); struct route4_filter __rcu **fp; @@ -515,7 +517,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, } err = route4_set_parms(net, tp, base, f, handle, head, tb, - tca[TCA_RATE], new, ovr); + tca[TCA_RATE], new, ovr, extack); if (err < 0) goto errout; @@ -527,7 +529,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (f->handle < f1->handle) break; - netif_keep_dst(qdisc_dev(tp->q)); + tcf_block_netif_keep_dst(tp->chain->block); rcu_assign_pointer(f->next, f1); rcu_assign_pointer(*fp, f); diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index cf325625c99d..4f1297657c27 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -322,7 +322,7 @@ static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) __rsvp_delete_filter(f); } -static void rsvp_destroy(struct tcf_proto *tp) +static void rsvp_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct rsvp_head *data = rtnl_dereference(tp->root); int h1, h2; @@ -350,7 +350,8 @@ static void rsvp_destroy(struct tcf_proto *tp) kfree_rcu(data, rcu); } -static int rsvp_delete(struct tcf_proto *tp, void *arg, bool *last) +static int rsvp_delete(struct tcf_proto *tp, void *arg, bool *last, + struct netlink_ext_ack *extack) { struct rsvp_head *head = rtnl_dereference(tp->root); struct rsvp_filter *nfp, *f = arg; @@ -486,7 +487,7 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr) + void **arg, bool ovr, struct netlink_ext_ack *extack) { struct rsvp_head *data = rtnl_dereference(tp->root); struct rsvp_filter *f, *nfp; @@ -511,7 +512,7 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, err = tcf_exts_init(&e, TCA_RSVP_ACT, TCA_RSVP_POLICE); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr, extack); if (err < 0) goto errout2; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 67467ae24c97..b49cc990a000 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -193,7 +193,8 @@ static void tcindex_destroy_fexts(struct rcu_head *head) tcf_queue_work(&f->work); } -static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last) +static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last, + struct netlink_ext_ack *extack) { struct tcindex_data *p = rtnl_dereference(tp->root); struct tcindex_filter_result *r = arg; @@ -246,7 +247,7 @@ static int tcindex_destroy_element(struct tcf_proto *tp, { bool last; - return tcindex_delete(tp, arg, &last); + return tcindex_delete(tp, arg, &last, NULL); } static void __tcindex_destroy(struct rcu_head *head) @@ -322,7 +323,7 @@ static int tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, u32 handle, struct tcindex_data *p, struct tcindex_filter_result *r, struct nlattr **tb, - struct nlattr *est, bool ovr) + struct nlattr *est, bool ovr, struct netlink_ext_ack *extack) { struct tcindex_filter_result new_filter_result, *old_r = r; struct tcindex_filter_result cr; @@ -334,7 +335,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = tcf_exts_init(&e, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); + err = tcf_exts_validate(net, tp, tb, est, &e, ovr, extack); if (err < 0) goto errout; @@ -520,7 +521,8 @@ errout: static int tcindex_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, void **arg, bool ovr) + struct nlattr **tca, void **arg, bool ovr, + struct netlink_ext_ack *extack) { struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_TCINDEX_MAX + 1]; @@ -540,7 +542,7 @@ tcindex_change(struct net *net, struct sk_buff *in_skb, return err; return tcindex_set_parms(net, tp, base, handle, p, r, tb, - tca[TCA_RATE], ovr); + tca[TCA_RATE], ovr, extack); } static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) @@ -579,7 +581,8 @@ static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) } } -static void tcindex_destroy(struct tcf_proto *tp) +static void tcindex_destroy(struct tcf_proto *tp, + struct netlink_ext_ack *extack) { struct tcindex_data *p = rtnl_dereference(tp->root); struct tcf_walker walker; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 507859cdd1cb..60c892c36a60 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -87,6 +87,7 @@ struct tc_u_hnode { unsigned int divisor; struct idr handle_idr; struct rcu_head rcu; + u32 flags; /* The 'ht' field MUST be the last field in structure to allow for * more entries allocated at end of structure. */ @@ -486,12 +487,13 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) return 0; } -static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) +static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, + struct netlink_ext_ack *extack) { struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; - tc_cls_common_offload_init(&cls_u32.common, tp); + tc_cls_common_offload_init(&cls_u32.common, tp, h->flags, extack); cls_u32.command = TC_CLSU32_DELETE_HNODE; cls_u32.hnode.divisor = h->divisor; cls_u32.hnode.handle = h->handle; @@ -501,7 +503,7 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) } static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, - u32 flags) + u32 flags, struct netlink_ext_ack *extack) { struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; @@ -509,7 +511,7 @@ static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, bool offloaded = false; int err; - tc_cls_common_offload_init(&cls_u32.common, tp); + tc_cls_common_offload_init(&cls_u32.common, tp, flags, extack); cls_u32.command = TC_CLSU32_NEW_HNODE; cls_u32.hnode.divisor = h->divisor; cls_u32.hnode.handle = h->handle; @@ -517,7 +519,7 @@ static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw); if (err < 0) { - u32_clear_hw_hnode(tp, h); + u32_clear_hw_hnode(tp, h, NULL); return err; } else if (err > 0) { offloaded = true; @@ -529,27 +531,29 @@ static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, return 0; } -static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) +static void u32_remove_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, + struct netlink_ext_ack *extack) { struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; - tc_cls_common_offload_init(&cls_u32.common, tp); + tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, extack); cls_u32.command = TC_CLSU32_DELETE_KNODE; - cls_u32.knode.handle = handle; + cls_u32.knode.handle = n->handle; tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, false); + tcf_block_offload_dec(block, &n->flags); } static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, - u32 flags) + u32 flags, struct netlink_ext_ack *extack) { struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; bool skip_sw = tc_skip_sw(flags); int err; - tc_cls_common_offload_init(&cls_u32.common, tp); + tc_cls_common_offload_init(&cls_u32.common, tp, flags, extack); cls_u32.command = TC_CLSU32_REPLACE_KNODE; cls_u32.knode.handle = n->handle; cls_u32.knode.fshift = n->fshift; @@ -567,10 +571,10 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw); if (err < 0) { - u32_remove_hw_knode(tp, n->handle); + u32_remove_hw_knode(tp, n, NULL); return err; } else if (err > 0) { - n->flags |= TCA_CLS_FLAGS_IN_HW; + tcf_block_offload_inc(block, &n->flags); } if (skip_sw && !(n->flags & TCA_CLS_FLAGS_IN_HW)) @@ -579,7 +583,8 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, return 0; } -static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) +static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, + struct netlink_ext_ack *extack) { struct tc_u_knode *n; unsigned int h; @@ -589,7 +594,7 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) RCU_INIT_POINTER(ht->ht[h], rtnl_dereference(n->next)); tcf_unbind_filter(tp, &n->res); - u32_remove_hw_knode(tp, n->handle); + u32_remove_hw_knode(tp, n, extack); idr_remove_ext(&ht->handle_idr, n->handle); if (tcf_exts_get_net(&n->exts)) call_rcu(&n->rcu, u32_delete_key_freepf_rcu); @@ -599,7 +604,8 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) } } -static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) +static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, + struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode __rcu **hn; @@ -607,14 +613,14 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) WARN_ON(ht->refcnt); - u32_clear_hnode(tp, ht); + u32_clear_hnode(tp, ht, extack); hn = &tp_c->hlist; for (phn = rtnl_dereference(*hn); phn; hn = &phn->next, phn = rtnl_dereference(*hn)) { if (phn == ht) { - u32_clear_hw_hnode(tp, ht); + u32_clear_hw_hnode(tp, ht, extack); idr_destroy(&ht->handle_idr); idr_remove_ext(&tp_c->handle_idr, ht->handle); RCU_INIT_POINTER(*hn, ht->next); @@ -637,7 +643,7 @@ static bool ht_empty(struct tc_u_hnode *ht) return true; } -static void u32_destroy(struct tcf_proto *tp) +static void u32_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *root_ht = rtnl_dereference(tp->root); @@ -645,7 +651,7 @@ static void u32_destroy(struct tcf_proto *tp) WARN_ON(root_ht == NULL); if (root_ht && --root_ht->refcnt == 0) - u32_destroy_hnode(tp, root_ht); + u32_destroy_hnode(tp, root_ht, extack); if (--tp_c->refcnt == 0) { struct tc_u_hnode *ht; @@ -656,7 +662,7 @@ static void u32_destroy(struct tcf_proto *tp) ht; ht = rtnl_dereference(ht->next)) { ht->refcnt--; - u32_clear_hnode(tp, ht); + u32_clear_hnode(tp, ht, extack); } while ((ht = rtnl_dereference(tp_c->hlist)) != NULL) { @@ -671,7 +677,8 @@ static void u32_destroy(struct tcf_proto *tp) tp->data = NULL; } -static int u32_delete(struct tcf_proto *tp, void *arg, bool *last) +static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, + struct netlink_ext_ack *extack) { struct tc_u_hnode *ht = arg; struct tc_u_hnode *root_ht = rtnl_dereference(tp->root); @@ -682,18 +689,21 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last) goto out; if (TC_U32_KEY(ht->handle)) { - u32_remove_hw_knode(tp, ht->handle); + u32_remove_hw_knode(tp, (struct tc_u_knode *)ht, extack); ret = u32_delete_key(tp, (struct tc_u_knode *)ht); goto out; } - if (root_ht == ht) + if (root_ht == ht) { + NL_SET_ERR_MSG_MOD(extack, "Not allowed to delete root node"); return -EINVAL; + } if (ht->refcnt == 1) { ht->refcnt--; - u32_destroy_hnode(tp, ht); + u32_destroy_hnode(tp, ht, extack); } else { + NL_SET_ERR_MSG_MOD(extack, "Can not delete in-use filter"); return -EBUSY; } @@ -764,11 +774,12 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { static int u32_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct tc_u_hnode *ht, struct tc_u_knode *n, struct nlattr **tb, - struct nlattr *est, bool ovr) + struct nlattr *est, bool ovr, + struct netlink_ext_ack *extack) { int err; - err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr); + err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr, extack); if (err < 0) return err; @@ -776,14 +787,18 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, u32 handle = nla_get_u32(tb[TCA_U32_LINK]); struct tc_u_hnode *ht_down = NULL, *ht_old; - if (TC_U32_KEY(handle)) + if (TC_U32_KEY(handle)) { + NL_SET_ERR_MSG_MOD(extack, "u32 Link handle must be a hash table"); return -EINVAL; + } if (handle) { ht_down = u32_lookup_ht(ht->tp_c, handle); - if (ht_down == NULL) + if (!ht_down) { + NL_SET_ERR_MSG_MOD(extack, "Link hash table not found"); return -EINVAL; + } ht_down->refcnt++; } @@ -801,7 +816,7 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, #ifdef CONFIG_NET_CLS_IND if (tb[TCA_U32_INDEV]) { int ret; - ret = tcf_change_indev(net, tb[TCA_U32_INDEV]); + ret = tcf_change_indev(net, tb[TCA_U32_INDEV], extack); if (ret < 0) return -EINVAL; n->ifindex = ret; @@ -892,7 +907,8 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, static int u32_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, void **arg, bool ovr) + struct nlattr **tca, void **arg, bool ovr, + struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *ht; @@ -906,28 +922,40 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, size_t size; #endif - if (opt == NULL) - return handle ? -EINVAL : 0; + if (!opt) { + if (handle) { + NL_SET_ERR_MSG_MOD(extack, "Filter handle requires options"); + return -EINVAL; + } else { + return 0; + } + } - err = nla_parse_nested(tb, TCA_U32_MAX, opt, u32_policy, NULL); + err = nla_parse_nested(tb, TCA_U32_MAX, opt, u32_policy, extack); if (err < 0) return err; if (tb[TCA_U32_FLAGS]) { flags = nla_get_u32(tb[TCA_U32_FLAGS]); - if (!tc_flags_valid(flags)) + if (!tc_flags_valid(flags)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid filter flags"); return -EINVAL; + } } n = *arg; if (n) { struct tc_u_knode *new; - if (TC_U32_KEY(n->handle) == 0) + if (TC_U32_KEY(n->handle) == 0) { + NL_SET_ERR_MSG_MOD(extack, "Key node id cannot be zero"); return -EINVAL; + } - if (n->flags != flags) + if (n->flags != flags) { + NL_SET_ERR_MSG_MOD(extack, "Key node flags do not match passed flags"); return -EINVAL; + } new = u32_init_knode(tp, n); if (!new) @@ -935,14 +963,14 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, err = u32_set_parms(net, tp, base, rtnl_dereference(n->ht_up), new, tb, - tca[TCA_RATE], ovr); + tca[TCA_RATE], ovr, extack); if (err) { u32_destroy_key(tp, new, false); return err; } - err = u32_replace_hw_knode(tp, new, flags); + err = u32_replace_hw_knode(tp, new, flags, extack); if (err) { u32_destroy_key(tp, new, false); return err; @@ -961,10 +989,14 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (tb[TCA_U32_DIVISOR]) { unsigned int divisor = nla_get_u32(tb[TCA_U32_DIVISOR]); - if (--divisor > 0x100) + if (--divisor > 0x100) { + NL_SET_ERR_MSG_MOD(extack, "Exceeded maximum 256 hash buckets"); return -EINVAL; - if (TC_U32_KEY(handle)) + } + if (TC_U32_KEY(handle)) { + NL_SET_ERR_MSG_MOD(extack, "Divisor can only be used on a hash table"); return -EINVAL; + } ht = kzalloc(sizeof(*ht) + divisor*sizeof(void *), GFP_KERNEL); if (ht == NULL) return -ENOBUFS; @@ -988,8 +1020,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, ht->handle = handle; ht->prio = tp->prio; idr_init(&ht->handle_idr); + ht->flags = flags; - err = u32_replace_hw_hnode(tp, ht, flags); + err = u32_replace_hw_hnode(tp, ht, flags, extack); if (err) { idr_remove_ext(&tp_c->handle_idr, handle); kfree(ht); @@ -1010,20 +1043,26 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, htid = ht->handle; } else { ht = u32_lookup_ht(tp->data, TC_U32_HTID(htid)); - if (ht == NULL) + if (!ht) { + NL_SET_ERR_MSG_MOD(extack, "Specified hash table not found"); return -EINVAL; + } } } else { ht = rtnl_dereference(tp->root); htid = ht->handle; } - if (ht->divisor < TC_U32_HASH(htid)) + if (ht->divisor < TC_U32_HASH(htid)) { + NL_SET_ERR_MSG_MOD(extack, "Specified hash table buckets exceed configured value"); return -EINVAL; + } if (handle) { - if (TC_U32_HTID(handle) && TC_U32_HTID(handle^htid)) + if (TC_U32_HTID(handle) && TC_U32_HTID(handle ^ htid)) { + NL_SET_ERR_MSG_MOD(extack, "Handle specified hash table address mismatch"); return -EINVAL; + } handle = htid | TC_U32_NODE(handle); err = idr_alloc_ext(&ht->handle_idr, NULL, NULL, handle, handle + 1, @@ -1034,6 +1073,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, handle = gen_new_kid(ht, htid); if (tb[TCA_U32_SEL] == NULL) { + NL_SET_ERR_MSG_MOD(extack, "Selector not specified"); err = -EINVAL; goto erridr; } @@ -1082,12 +1122,13 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, } #endif - err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE], ovr); + err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE], ovr, + extack); if (err == 0) { struct tc_u_knode __rcu **ins; struct tc_u_knode *pins; - err = u32_replace_hw_knode(tp, n, flags); + err = u32_replace_hw_knode(tp, n, flags, extack); if (err) goto errhw; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 52529b7f8d96..d512f49ee83c 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -393,13 +393,16 @@ static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab) static struct qdisc_rate_table *qdisc_rtab_list; struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, - struct nlattr *tab) + struct nlattr *tab, + struct netlink_ext_ack *extack) { struct qdisc_rate_table *rtab; if (tab == NULL || r->rate == 0 || r->cell_log == 0 || - nla_len(tab) != TC_RTAB_SIZE) + nla_len(tab) != TC_RTAB_SIZE) { + NL_SET_ERR_MSG(extack, "Invalid rate table parameters for searching"); return NULL; + } for (rtab = qdisc_rtab_list; rtab; rtab = rtab->next) { if (!memcmp(&rtab->rate, r, sizeof(struct tc_ratespec)) && @@ -418,6 +421,8 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, r->linklayer = __detect_linklayer(r, rtab->data); rtab->next = qdisc_rtab_list; qdisc_rtab_list = rtab; + } else { + NL_SET_ERR_MSG(extack, "Failed to allocate new qdisc rate table"); } return rtab; } @@ -449,7 +454,8 @@ static const struct nla_policy stab_policy[TCA_STAB_MAX + 1] = { [TCA_STAB_DATA] = { .type = NLA_BINARY }, }; -static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt) +static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt, + struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_STAB_MAX + 1]; struct qdisc_size_table *stab; @@ -458,23 +464,29 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt) u16 *tab = NULL; int err; - err = nla_parse_nested(tb, TCA_STAB_MAX, opt, stab_policy, NULL); + err = nla_parse_nested(tb, TCA_STAB_MAX, opt, stab_policy, extack); if (err < 0) return ERR_PTR(err); - if (!tb[TCA_STAB_BASE]) + if (!tb[TCA_STAB_BASE]) { + NL_SET_ERR_MSG(extack, "Size table base attribute is missing"); return ERR_PTR(-EINVAL); + } s = nla_data(tb[TCA_STAB_BASE]); if (s->tsize > 0) { - if (!tb[TCA_STAB_DATA]) + if (!tb[TCA_STAB_DATA]) { + NL_SET_ERR_MSG(extack, "Size table data attribute is missing"); return ERR_PTR(-EINVAL); + } tab = nla_data(tb[TCA_STAB_DATA]); tsize = nla_len(tb[TCA_STAB_DATA]) / sizeof(u16); } - if (tsize != s->tsize || (!tab && tsize > 0)) + if (tsize != s->tsize || (!tab && tsize > 0)) { + NL_SET_ERR_MSG(extack, "Invalid size of size table"); return ERR_PTR(-EINVAL); + } list_for_each_entry(stab, &qdisc_stab_list, list) { if (memcmp(&stab->szopts, s, sizeof(*s))) @@ -669,7 +681,7 @@ int qdisc_class_hash_init(struct Qdisc_class_hash *clhash) unsigned int size = 4; clhash->hash = qdisc_class_hash_alloc(size); - if (clhash->hash == NULL) + if (!clhash->hash) return -ENOMEM; clhash->hashsize = size; clhash->hashmask = size - 1; @@ -779,6 +791,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, unsigned char *b = skb_tail_pointer(skb); struct gnet_dump d; struct qdisc_size_table *stab; + u32 block_index; __u32 qlen; cond_resched(); @@ -795,11 +808,23 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, tcm->tcm_info = refcount_read(&q->refcnt); if (nla_put_string(skb, TCA_KIND, q->ops->id)) goto nla_put_failure; - if (nla_put_u8(skb, TCA_HW_OFFLOAD, !!(q->flags & TCQ_F_OFFLOADED))) - goto nla_put_failure; + if (q->ops->ingress_block_get) { + block_index = q->ops->ingress_block_get(q); + if (block_index && + nla_put_u32(skb, TCA_INGRESS_BLOCK, block_index)) + goto nla_put_failure; + } + if (q->ops->egress_block_get) { + block_index = q->ops->egress_block_get(q); + if (block_index && + nla_put_u32(skb, TCA_EGRESS_BLOCK, block_index)) + goto nla_put_failure; + } if (q->ops->dump && q->ops->dump(q, skb) < 0) goto nla_put_failure; - qlen = q->q.qlen; + if (nla_put_u8(skb, TCA_HW_OFFLOAD, !!(q->flags & TCQ_F_OFFLOADED))) + goto nla_put_failure; + qlen = qdisc_qlen_sum(q); stab = rtnl_dereference(q->stab); if (stab && qdisc_dump_stab(skb, stab) < 0) @@ -898,7 +923,8 @@ static void notify_and_destroy(struct net *net, struct sk_buff *skb, static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, struct sk_buff *skb, struct nlmsghdr *n, u32 classid, - struct Qdisc *new, struct Qdisc *old) + struct Qdisc *new, struct Qdisc *old, + struct netlink_ext_ack *extack) { struct Qdisc *q = old; struct net *net = dev_net(dev); @@ -913,8 +939,10 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, (new && new->flags & TCQ_F_INGRESS)) { num_q = 1; ingress = 1; - if (!dev_ingress_queue(dev)) + if (!dev_ingress_queue(dev)) { + NL_SET_ERR_MSG(extack, "Device does not have an ingress queue"); return -ENOENT; + } } if (dev->flags & IFF_UP) @@ -956,14 +984,22 @@ skip: } else { const struct Qdisc_class_ops *cops = parent->ops->cl_ops; + /* Only support running class lockless if parent is lockless */ + if (new && (new->flags & TCQ_F_NOLOCK) && + parent && !(parent->flags & TCQ_F_NOLOCK)) + new->flags &= ~TCQ_F_NOLOCK; + err = -EOPNOTSUPP; if (cops && cops->graft) { unsigned long cl = cops->find(parent, classid); - if (cl) - err = cops->graft(parent, cl, new, &old); - else + if (cl) { + err = cops->graft(parent, cl, new, &old, + extack); + } else { + NL_SET_ERR_MSG(extack, "Specified class not found"); err = -ENOENT; + } } if (!err) notify_and_destroy(net, skb, n, classid, old, new); @@ -971,6 +1007,40 @@ skip: return err; } +static int qdisc_block_indexes_set(struct Qdisc *sch, struct nlattr **tca, + struct netlink_ext_ack *extack) +{ + u32 block_index; + + if (tca[TCA_INGRESS_BLOCK]) { + block_index = nla_get_u32(tca[TCA_INGRESS_BLOCK]); + + if (!block_index) { + NL_SET_ERR_MSG(extack, "Ingress block index cannot be 0"); + return -EINVAL; + } + if (!sch->ops->ingress_block_set) { + NL_SET_ERR_MSG(extack, "Ingress block sharing is not supported"); + return -EOPNOTSUPP; + } + sch->ops->ingress_block_set(sch, block_index); + } + if (tca[TCA_EGRESS_BLOCK]) { + block_index = nla_get_u32(tca[TCA_EGRESS_BLOCK]); + + if (!block_index) { + NL_SET_ERR_MSG(extack, "Egress block index cannot be 0"); + return -EINVAL; + } + if (!sch->ops->egress_block_set) { + NL_SET_ERR_MSG(extack, "Egress block sharing is not supported"); + return -EOPNOTSUPP; + } + sch->ops->egress_block_set(sch, block_index); + } + return 0; +} + /* lockdep annotation is needed for ingress; egress gets it only for name */ static struct lock_class_key qdisc_tx_lock; static struct lock_class_key qdisc_rx_lock; @@ -984,7 +1054,8 @@ static struct lock_class_key qdisc_rx_lock; static struct Qdisc *qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, struct Qdisc *p, u32 parent, u32 handle, - struct nlattr **tca, int *errp) + struct nlattr **tca, int *errp, + struct netlink_ext_ack *extack) { int err; struct nlattr *kind = tca[TCA_KIND]; @@ -1022,10 +1093,12 @@ static struct Qdisc *qdisc_create(struct net_device *dev, #endif err = -ENOENT; - if (ops == NULL) + if (!ops) { + NL_SET_ERR_MSG(extack, "Specified qdisc not found"); goto err_out; + } - sch = qdisc_alloc(dev_queue, ops); + sch = qdisc_alloc(dev_queue, ops, extack); if (IS_ERR(sch)) { err = PTR_ERR(sch); goto err_out2; @@ -1062,43 +1135,57 @@ static struct Qdisc *qdisc_create(struct net_device *dev, netdev_info(dev, "Caught tx_queue_len zero misconfig\n"); } - if (!ops->init || (err = ops->init(sch, tca[TCA_OPTIONS])) == 0) { - if (tca[TCA_STAB]) { - stab = qdisc_get_stab(tca[TCA_STAB]); - if (IS_ERR(stab)) { - err = PTR_ERR(stab); - goto err_out4; - } - rcu_assign_pointer(sch->stab, stab); - } - if (tca[TCA_RATE]) { - seqcount_t *running; - - err = -EOPNOTSUPP; - if (sch->flags & TCQ_F_MQROOT) - goto err_out4; - - if ((sch->parent != TC_H_ROOT) && - !(sch->flags & TCQ_F_INGRESS) && - (!p || !(p->flags & TCQ_F_MQROOT))) - running = qdisc_root_sleeping_running(sch); - else - running = &sch->running; - - err = gen_new_estimator(&sch->bstats, - sch->cpu_bstats, - &sch->rate_est, - NULL, - running, - tca[TCA_RATE]); - if (err) - goto err_out4; + err = qdisc_block_indexes_set(sch, tca, extack); + if (err) + goto err_out3; + + if (ops->init) { + err = ops->init(sch, tca[TCA_OPTIONS], extack); + if (err != 0) + goto err_out5; + } + + if (tca[TCA_STAB]) { + stab = qdisc_get_stab(tca[TCA_STAB], extack); + if (IS_ERR(stab)) { + err = PTR_ERR(stab); + goto err_out4; } + rcu_assign_pointer(sch->stab, stab); + } + if (tca[TCA_RATE]) { + seqcount_t *running; - qdisc_hash_add(sch, false); + err = -EOPNOTSUPP; + if (sch->flags & TCQ_F_MQROOT) { + NL_SET_ERR_MSG(extack, "Cannot attach rate estimator to a multi-queue root qdisc"); + goto err_out4; + } - return sch; + if (sch->parent != TC_H_ROOT && + !(sch->flags & TCQ_F_INGRESS) && + (!p || !(p->flags & TCQ_F_MQROOT))) + running = qdisc_root_sleeping_running(sch); + else + running = &sch->running; + + err = gen_new_estimator(&sch->bstats, + sch->cpu_bstats, + &sch->rate_est, + NULL, + running, + tca[TCA_RATE]); + if (err) { + NL_SET_ERR_MSG(extack, "Failed to generate new estimator"); + goto err_out4; + } } + + qdisc_hash_add(sch, false); + + return sch; + +err_out5: /* ops->init() failed, we call ->destroy() like qdisc_create_dflt() */ if (ops->destroy) ops->destroy(sch); @@ -1122,21 +1209,28 @@ err_out4: goto err_out3; } -static int qdisc_change(struct Qdisc *sch, struct nlattr **tca) +static int qdisc_change(struct Qdisc *sch, struct nlattr **tca, + struct netlink_ext_ack *extack) { struct qdisc_size_table *ostab, *stab = NULL; int err = 0; if (tca[TCA_OPTIONS]) { - if (sch->ops->change == NULL) + if (!sch->ops->change) { + NL_SET_ERR_MSG(extack, "Change operation not supported by specified qdisc"); return -EINVAL; - err = sch->ops->change(sch, tca[TCA_OPTIONS]); + } + if (tca[TCA_INGRESS_BLOCK] || tca[TCA_EGRESS_BLOCK]) { + NL_SET_ERR_MSG(extack, "Change of blocks is not supported"); + return -EOPNOTSUPP; + } + err = sch->ops->change(sch, tca[TCA_OPTIONS], extack); if (err) return err; } if (tca[TCA_STAB]) { - stab = qdisc_get_stab(tca[TCA_STAB]); + stab = qdisc_get_stab(tca[TCA_STAB], extack); if (IS_ERR(stab)) return PTR_ERR(stab); } @@ -1234,8 +1328,10 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, if (clid != TC_H_ROOT) { if (TC_H_MAJ(clid) != TC_H_MAJ(TC_H_INGRESS)) { p = qdisc_lookup(dev, TC_H_MAJ(clid)); - if (!p) + if (!p) { + NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified classid"); return -ENOENT; + } q = qdisc_leaf(p, clid); } else if (dev_ingress_queue(dev)) { q = dev_ingress_queue(dev)->qdisc_sleeping; @@ -1243,26 +1339,38 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, } else { q = dev->qdisc; } - if (!q) + if (!q) { + NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device"); return -ENOENT; + } - if (tcm->tcm_handle && q->handle != tcm->tcm_handle) + if (tcm->tcm_handle && q->handle != tcm->tcm_handle) { + NL_SET_ERR_MSG(extack, "Invalid handle"); return -EINVAL; + } } else { q = qdisc_lookup(dev, tcm->tcm_handle); - if (!q) + if (!q) { + NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified handle"); return -ENOENT; + } } - if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) + if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { + NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; + } if (n->nlmsg_type == RTM_DELQDISC) { - if (!clid) + if (!clid) { + NL_SET_ERR_MSG(extack, "Classid cannot be zero"); return -EINVAL; - if (q->handle == 0) + } + if (q->handle == 0) { + NL_SET_ERR_MSG(extack, "Cannot delete qdisc with handle of zero"); return -ENOENT; - err = qdisc_graft(dev, p, skb, n, clid, NULL, q); + } + err = qdisc_graft(dev, p, skb, n, clid, NULL, q, extack); if (err != 0) return err; } else { @@ -1308,8 +1416,10 @@ replay: if (clid != TC_H_ROOT) { if (clid != TC_H_INGRESS) { p = qdisc_lookup(dev, TC_H_MAJ(clid)); - if (!p) + if (!p) { + NL_SET_ERR_MSG(extack, "Failed to find specified qdisc"); return -ENOENT; + } q = qdisc_leaf(p, clid); } else if (dev_ingress_queue_create(dev)) { q = dev_ingress_queue(dev)->qdisc_sleeping; @@ -1324,20 +1434,31 @@ replay: if (!q || !tcm->tcm_handle || q->handle != tcm->tcm_handle) { if (tcm->tcm_handle) { - if (q && !(n->nlmsg_flags & NLM_F_REPLACE)) + if (q && !(n->nlmsg_flags & NLM_F_REPLACE)) { + NL_SET_ERR_MSG(extack, "NLM_F_REPLACE needed to override"); return -EEXIST; - if (TC_H_MIN(tcm->tcm_handle)) + } + if (TC_H_MIN(tcm->tcm_handle)) { + NL_SET_ERR_MSG(extack, "Invalid minor handle"); return -EINVAL; + } q = qdisc_lookup(dev, tcm->tcm_handle); if (!q) goto create_n_graft; - if (n->nlmsg_flags & NLM_F_EXCL) + if (n->nlmsg_flags & NLM_F_EXCL) { + NL_SET_ERR_MSG(extack, "Exclusivity flag on, cannot override"); return -EEXIST; - if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) + } + if (tca[TCA_KIND] && + nla_strcmp(tca[TCA_KIND], q->ops->id)) { + NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; + } if (q == p || - (p && check_loop(q, p, 0))) + (p && check_loop(q, p, 0))) { + NL_SET_ERR_MSG(extack, "Qdisc parent/child loop detected"); return -ELOOP; + } qdisc_refcount_inc(q); goto graft; } else { @@ -1372,33 +1493,45 @@ replay: } } } else { - if (!tcm->tcm_handle) + if (!tcm->tcm_handle) { + NL_SET_ERR_MSG(extack, "Handle cannot be zero"); return -EINVAL; + } q = qdisc_lookup(dev, tcm->tcm_handle); } /* Change qdisc parameters */ - if (q == NULL) + if (!q) { + NL_SET_ERR_MSG(extack, "Specified qdisc not found"); return -ENOENT; - if (n->nlmsg_flags & NLM_F_EXCL) + } + if (n->nlmsg_flags & NLM_F_EXCL) { + NL_SET_ERR_MSG(extack, "Exclusivity flag on, cannot modify"); return -EEXIST; - if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) + } + if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { + NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; - err = qdisc_change(q, tca); + } + err = qdisc_change(q, tca, extack); if (err == 0) qdisc_notify(net, skb, n, clid, NULL, q); return err; create_n_graft: - if (!(n->nlmsg_flags & NLM_F_CREATE)) + if (!(n->nlmsg_flags & NLM_F_CREATE)) { + NL_SET_ERR_MSG(extack, "Qdisc not found. To create specify NLM_F_CREATE flag"); return -ENOENT; + } if (clid == TC_H_INGRESS) { - if (dev_ingress_queue(dev)) + if (dev_ingress_queue(dev)) { q = qdisc_create(dev, dev_ingress_queue(dev), p, tcm->tcm_parent, tcm->tcm_parent, - tca, &err); - else + tca, &err, extack); + } else { + NL_SET_ERR_MSG(extack, "Cannot find ingress queue for specified device"); err = -ENOENT; + } } else { struct netdev_queue *dev_queue; @@ -1411,7 +1544,7 @@ create_n_graft: q = qdisc_create(dev, dev_queue, p, tcm->tcm_parent, tcm->tcm_handle, - tca, &err); + tca, &err, extack); } if (q == NULL) { if (err == -EAGAIN) @@ -1420,7 +1553,7 @@ create_n_graft: } graft: - err = qdisc_graft(dev, p, skb, n, clid, q, NULL); + err = qdisc_graft(dev, p, skb, n, clid, q, NULL, extack); if (err) { if (q) qdisc_destroy(q); @@ -1672,7 +1805,7 @@ static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, cl = cops->find(q, portid); if (!cl) return; - block = cops->tcf_block(q, cl); + block = cops->tcf_block(q, cl, NULL); if (!block) return; list_for_each_entry(chain, &block->chain_list, list) { @@ -1816,10 +1949,15 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, } } + if (tca[TCA_INGRESS_BLOCK] || tca[TCA_EGRESS_BLOCK]) { + NL_SET_ERR_MSG(extack, "Shared blocks are not supported for classes"); + return -EOPNOTSUPP; + } + new_cl = cl; err = -EOPNOTSUPP; if (cops->change) - err = cops->change(q, clid, portid, tca, &new_cl); + err = cops->change(q, clid, portid, tca, &new_cl, extack); if (err == 0) { tclass_notify(net, skb, n, q, new_cl, RTM_NEWTCLASS); /* We just create a new class, need to do reverse binding. */ @@ -1955,7 +2093,6 @@ static int psched_open(struct inode *inode, struct file *file) } static const struct file_operations psched_fops = { - .owner = THIS_MODULE, .open = psched_open, .read = seq_read, .llseek = seq_lseek, diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 2dbd249c0b2f..cd49afca9617 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -82,7 +82,8 @@ static inline struct atm_flow_data *lookup_flow(struct Qdisc *sch, u32 classid) } static int atm_tc_graft(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old) + struct Qdisc *new, struct Qdisc **old, + struct netlink_ext_ack *extack) { struct atm_qdisc_data *p = qdisc_priv(sch); struct atm_flow_data *flow = (struct atm_flow_data *)arg; @@ -191,7 +192,8 @@ static const struct nla_policy atm_policy[TCA_ATM_MAX + 1] = { }; static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, - struct nlattr **tca, unsigned long *arg) + struct nlattr **tca, unsigned long *arg, + struct netlink_ext_ack *extack) { struct atm_qdisc_data *p = qdisc_priv(sch); struct atm_flow_data *flow = (struct atm_flow_data *)*arg; @@ -281,13 +283,15 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, goto err_out; } - error = tcf_block_get(&flow->block, &flow->filter_list, sch); + error = tcf_block_get(&flow->block, &flow->filter_list, sch, + extack); if (error) { kfree(flow); goto err_out; } - flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); + flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, + extack); if (!flow->q) flow->q = &noop_qdisc; pr_debug("atm_tc_change: qdisc %p\n", flow->q); @@ -356,7 +360,8 @@ static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker) } } -static struct tcf_block *atm_tc_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *atm_tc_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct atm_qdisc_data *p = qdisc_priv(sch); struct atm_flow_data *flow = (struct atm_flow_data *)cl; @@ -531,7 +536,8 @@ static struct sk_buff *atm_tc_peek(struct Qdisc *sch) return p->link.q->ops->peek(p->link.q); } -static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) +static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct atm_qdisc_data *p = qdisc_priv(sch); int err; @@ -541,12 +547,13 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) INIT_LIST_HEAD(&p->link.list); list_add(&p->link.list, &p->flows); p->link.q = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, sch->handle); + &pfifo_qdisc_ops, sch->handle, extack); if (!p->link.q) p->link.q = &noop_qdisc; pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); - err = tcf_block_get(&p->link.block, &p->link.filter_list, sch); + err = tcf_block_get(&p->link.block, &p->link.filter_list, sch, + extack); if (err) return err; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 525eb3a6d625..f42025d53cfe 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1132,7 +1132,8 @@ static const struct nla_policy cbq_policy[TCA_CBQ_MAX + 1] = { [TCA_CBQ_POLICE] = { .len = sizeof(struct tc_cbq_police) }, }; -static int cbq_init(struct Qdisc *sch, struct nlattr *opt) +static int cbq_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct cbq_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CBQ_MAX + 1]; @@ -1143,22 +1144,27 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt) hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); q->delay_timer.function = cbq_undelay; - if (!opt) + if (!opt) { + NL_SET_ERR_MSG(extack, "CBQ options are required for this operation"); return -EINVAL; + } - err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy, NULL); + err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy, extack); if (err < 0) return err; - if (tb[TCA_CBQ_RTAB] == NULL || tb[TCA_CBQ_RATE] == NULL) + if (!tb[TCA_CBQ_RTAB] || !tb[TCA_CBQ_RATE]) { + NL_SET_ERR_MSG(extack, "Rate specification missing or incomplete"); return -EINVAL; + } r = nla_data(tb[TCA_CBQ_RATE]); - if ((q->link.R_tab = qdisc_get_rtab(r, tb[TCA_CBQ_RTAB])) == NULL) + q->link.R_tab = qdisc_get_rtab(r, tb[TCA_CBQ_RTAB], extack); + if (!q->link.R_tab) return -EINVAL; - err = tcf_block_get(&q->link.block, &q->link.filter_list, sch); + err = tcf_block_get(&q->link.block, &q->link.filter_list, sch, extack); if (err) goto put_rtab; @@ -1170,7 +1176,7 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt) q->link.common.classid = sch->handle; q->link.qdisc = sch; q->link.q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle); + sch->handle, NULL); if (!q->link.q) q->link.q = &noop_qdisc; else @@ -1369,13 +1375,13 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, } static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct cbq_class *cl = (struct cbq_class *)arg; if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, cl->common.classid); + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + cl->common.classid, extack); if (new == NULL) return -ENOBUFS; } @@ -1450,7 +1456,7 @@ static void cbq_destroy(struct Qdisc *sch) static int cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, - unsigned long *arg) + unsigned long *arg, struct netlink_ext_ack *extack) { int err; struct cbq_sched_data *q = qdisc_priv(sch); @@ -1460,29 +1466,37 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t struct cbq_class *parent; struct qdisc_rate_table *rtab = NULL; - if (opt == NULL) + if (!opt) { + NL_SET_ERR_MSG(extack, "Mandatory qdisc options missing"); return -EINVAL; + } - err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy, NULL); + err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy, extack); if (err < 0) return err; - if (tb[TCA_CBQ_OVL_STRATEGY] || tb[TCA_CBQ_POLICE]) + if (tb[TCA_CBQ_OVL_STRATEGY] || tb[TCA_CBQ_POLICE]) { + NL_SET_ERR_MSG(extack, "Neither overlimit strategy nor policing attributes can be used for changing class params"); return -EOPNOTSUPP; + } if (cl) { /* Check parent */ if (parentid) { if (cl->tparent && - cl->tparent->common.classid != parentid) + cl->tparent->common.classid != parentid) { + NL_SET_ERR_MSG(extack, "Invalid parent id"); return -EINVAL; - if (!cl->tparent && parentid != TC_H_ROOT) + } + if (!cl->tparent && parentid != TC_H_ROOT) { + NL_SET_ERR_MSG(extack, "Parent must be root"); return -EINVAL; + } } if (tb[TCA_CBQ_RATE]) { rtab = qdisc_get_rtab(nla_data(tb[TCA_CBQ_RATE]), - tb[TCA_CBQ_RTAB]); + tb[TCA_CBQ_RTAB], extack); if (rtab == NULL) return -EINVAL; } @@ -1494,6 +1508,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) { + NL_SET_ERR_MSG(extack, "Failed to replace specified rate estimator"); qdisc_put_rtab(rtab); return err; } @@ -1532,19 +1547,23 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (parentid == TC_H_ROOT) return -EINVAL; - if (tb[TCA_CBQ_WRROPT] == NULL || tb[TCA_CBQ_RATE] == NULL || - tb[TCA_CBQ_LSSOPT] == NULL) + if (!tb[TCA_CBQ_WRROPT] || !tb[TCA_CBQ_RATE] || !tb[TCA_CBQ_LSSOPT]) { + NL_SET_ERR_MSG(extack, "One of the following attributes MUST be specified: WRR, rate or link sharing"); return -EINVAL; + } - rtab = qdisc_get_rtab(nla_data(tb[TCA_CBQ_RATE]), tb[TCA_CBQ_RTAB]); + rtab = qdisc_get_rtab(nla_data(tb[TCA_CBQ_RATE]), tb[TCA_CBQ_RTAB], + extack); if (rtab == NULL) return -EINVAL; if (classid) { err = -EINVAL; if (TC_H_MAJ(classid ^ sch->handle) || - cbq_class_lookup(q, classid)) + cbq_class_lookup(q, classid)) { + NL_SET_ERR_MSG(extack, "Specified class not found"); goto failure; + } } else { int i; classid = TC_H_MAKE(sch->handle, 0x8000); @@ -1556,8 +1575,10 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t break; } err = -ENOSR; - if (i >= 0x8000) + if (i >= 0x8000) { + NL_SET_ERR_MSG(extack, "Unable to generate classid"); goto failure; + } classid = classid|q->hgenerator; } @@ -1565,8 +1586,10 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (parentid) { parent = cbq_class_lookup(q, parentid); err = -EINVAL; - if (parent == NULL) + if (!parent) { + NL_SET_ERR_MSG(extack, "Failed to find parentid"); goto failure; + } } err = -ENOBUFS; @@ -1574,7 +1597,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (cl == NULL) goto failure; - err = tcf_block_get(&cl->block, &cl->filter_list, sch); + err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); return err; @@ -1586,6 +1609,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) { + NL_SET_ERR_MSG(extack, "Couldn't create new estimator"); tcf_block_put(cl->block); kfree(cl); goto failure; @@ -1594,7 +1618,8 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t cl->R_tab = rtab; rtab = NULL; - cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); + cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, + NULL); if (!cl->q) cl->q = &noop_qdisc; else @@ -1678,7 +1703,8 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg) return 0; } -static struct tcf_block *cbq_tcf_block(struct Qdisc *sch, unsigned long arg) +static struct tcf_block *cbq_tcf_block(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl = (struct cbq_class *)arg; diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index 7a72980c1509..cdd96b9a27bc 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -219,14 +219,17 @@ static void cbs_disable_offload(struct net_device *dev, } static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q, - const struct tc_cbs_qopt *opt) + const struct tc_cbs_qopt *opt, + struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; struct tc_cbs_qopt_offload cbs = { }; int err; - if (!ops->ndo_setup_tc) + if (!ops->ndo_setup_tc) { + NL_SET_ERR_MSG(extack, "Specified device does not support cbs offload"); return -EOPNOTSUPP; + } cbs.queue = q->queue; @@ -237,8 +240,10 @@ static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q, cbs.sendslope = opt->sendslope; err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_CBS, &cbs); - if (err < 0) + if (err < 0) { + NL_SET_ERR_MSG(extack, "Specified device failed to setup cbs hardware offload"); return err; + } q->enqueue = cbs_enqueue_offload; q->dequeue = cbs_dequeue_offload; @@ -246,7 +251,8 @@ static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q, return 0; } -static int cbs_change(struct Qdisc *sch, struct nlattr *opt) +static int cbs_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct cbs_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); @@ -254,12 +260,14 @@ static int cbs_change(struct Qdisc *sch, struct nlattr *opt) struct tc_cbs_qopt *qopt; int err; - err = nla_parse_nested(tb, TCA_CBS_MAX, opt, cbs_policy, NULL); + err = nla_parse_nested(tb, TCA_CBS_MAX, opt, cbs_policy, extack); if (err < 0) return err; - if (!tb[TCA_CBS_PARMS]) + if (!tb[TCA_CBS_PARMS]) { + NL_SET_ERR_MSG(extack, "Missing CBS parameter which are mandatory"); return -EINVAL; + } qopt = nla_data(tb[TCA_CBS_PARMS]); @@ -276,7 +284,7 @@ static int cbs_change(struct Qdisc *sch, struct nlattr *opt) cbs_disable_offload(dev, q); } else { - err = cbs_enable_offload(dev, q, qopt); + err = cbs_enable_offload(dev, q, qopt, extack); if (err < 0) return err; } @@ -291,13 +299,16 @@ static int cbs_change(struct Qdisc *sch, struct nlattr *opt) return 0; } -static int cbs_init(struct Qdisc *sch, struct nlattr *opt) +static int cbs_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct cbs_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); - if (!opt) + if (!opt) { + NL_SET_ERR_MSG(extack, "Missing CBS qdisc options which are mandatory"); return -EINVAL; + } q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0); @@ -306,7 +317,7 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt) qdisc_watchdog_init(&q->watchdog, sch); - return cbs_change(sch, opt); + return cbs_change(sch, opt, extack); } static void cbs_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 531250fceb9e..eafc0d17d174 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -344,7 +344,8 @@ static void choke_free(void *addr) kvfree(addr); } -static int choke_change(struct Qdisc *sch, struct nlattr *opt) +static int choke_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct choke_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CHOKE_MAX + 1]; @@ -431,9 +432,10 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt) return 0; } -static int choke_init(struct Qdisc *sch, struct nlattr *opt) +static int choke_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { - return choke_change(sch, opt); + return choke_change(sch, opt, extack); } static int choke_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index c518a1efcb9d..17cd81f84b5d 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -130,7 +130,8 @@ static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = { [TCA_CODEL_CE_THRESHOLD]= { .type = NLA_U32 }, }; -static int codel_change(struct Qdisc *sch, struct nlattr *opt) +static int codel_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CODEL_MAX + 1]; @@ -184,7 +185,8 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt) return 0; } -static int codel_init(struct Qdisc *sch, struct nlattr *opt) +static int codel_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct codel_sched_data *q = qdisc_priv(sch); @@ -196,7 +198,7 @@ static int codel_init(struct Qdisc *sch, struct nlattr *opt) q->params.mtu = psched_mtu(qdisc_dev(sch)); if (opt) { - int err = codel_change(sch, opt); + int err = codel_change(sch, opt, extack); if (err) return err; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 5bbcef3dcd8c..e0b0cf8a9939 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -64,7 +64,8 @@ static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = { }; static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, - struct nlattr **tca, unsigned long *arg) + struct nlattr **tca, unsigned long *arg, + struct netlink_ext_ack *extack) { struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl = (struct drr_class *)*arg; @@ -73,17 +74,21 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, u32 quantum; int err; - if (!opt) + if (!opt) { + NL_SET_ERR_MSG(extack, "DRR options are required for this operation"); return -EINVAL; + } - err = nla_parse_nested(tb, TCA_DRR_MAX, opt, drr_policy, NULL); + err = nla_parse_nested(tb, TCA_DRR_MAX, opt, drr_policy, extack); if (err < 0) return err; if (tb[TCA_DRR_QUANTUM]) { quantum = nla_get_u32(tb[TCA_DRR_QUANTUM]); - if (quantum == 0) + if (quantum == 0) { + NL_SET_ERR_MSG(extack, "Specified DRR quantum cannot be zero"); return -EINVAL; + } } else quantum = psched_mtu(qdisc_dev(sch)); @@ -94,8 +99,10 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, NULL, qdisc_root_sleeping_running(sch), tca[TCA_RATE]); - if (err) + if (err) { + NL_SET_ERR_MSG(extack, "Failed to replace estimator"); return err; + } } sch_tree_lock(sch); @@ -113,7 +120,8 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cl->common.classid = classid; cl->quantum = quantum; cl->qdisc = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, classid); + &pfifo_qdisc_ops, classid, + NULL); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; else @@ -125,6 +133,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) { + NL_SET_ERR_MSG(extack, "Failed to replace estimator"); qdisc_destroy(cl->qdisc); kfree(cl); return err; @@ -172,12 +181,15 @@ static unsigned long drr_search_class(struct Qdisc *sch, u32 classid) return (unsigned long)drr_find_class(sch, classid); } -static struct tcf_block *drr_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *drr_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct drr_sched *q = qdisc_priv(sch); - if (cl) + if (cl) { + NL_SET_ERR_MSG(extack, "DRR classid must be zero"); return NULL; + } return q->block; } @@ -201,13 +213,14 @@ static void drr_unbind_tcf(struct Qdisc *sch, unsigned long arg) } static int drr_graft_class(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old) + struct Qdisc *new, struct Qdisc **old, + struct netlink_ext_ack *extack) { struct drr_class *cl = (struct drr_class *)arg; if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, cl->common.classid); + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + cl->common.classid, NULL); if (new == NULL) new = &noop_qdisc; } @@ -408,12 +421,13 @@ out: return NULL; } -static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt) +static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct drr_sched *q = qdisc_priv(sch); int err; - err = tcf_block_get(&q->block, &q->filter_list, sch); + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; err = qdisc_class_hash_init(&q->clhash); diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index fb4fb71c68cf..049714c57075 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -61,7 +61,8 @@ static inline int dsmark_valid_index(struct dsmark_qdisc_data *p, u16 index) /* ------------------------- Class/flow operations ------------------------- */ static int dsmark_graft(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old) + struct Qdisc *new, struct Qdisc **old, + struct netlink_ext_ack *extack) { struct dsmark_qdisc_data *p = qdisc_priv(sch); @@ -70,7 +71,7 @@ static int dsmark_graft(struct Qdisc *sch, unsigned long arg, if (new == NULL) { new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle); + sch->handle, NULL); if (new == NULL) new = &noop_qdisc; } @@ -112,7 +113,8 @@ static const struct nla_policy dsmark_policy[TCA_DSMARK_MAX + 1] = { }; static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, - struct nlattr **tca, unsigned long *arg) + struct nlattr **tca, unsigned long *arg, + struct netlink_ext_ack *extack) { struct dsmark_qdisc_data *p = qdisc_priv(sch); struct nlattr *opt = tca[TCA_OPTIONS]; @@ -184,7 +186,8 @@ ignore: } } -static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct dsmark_qdisc_data *p = qdisc_priv(sch); @@ -330,7 +333,8 @@ static struct sk_buff *dsmark_peek(struct Qdisc *sch) return p->q->ops->peek(p->q); } -static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) +static int dsmark_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct dsmark_qdisc_data *p = qdisc_priv(sch); struct nlattr *tb[TCA_DSMARK_MAX + 1]; @@ -344,7 +348,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) goto errout; - err = tcf_block_get(&p->block, &p->filter_list, sch); + err = tcf_block_get(&p->block, &p->filter_list, sch, extack); if (err) return err; @@ -377,7 +381,8 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) p->default_index = default_index; p->set_tc_index = nla_get_flag(tb[TCA_DSMARK_SET_TC_INDEX]); - p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle); + p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle, + NULL); if (p->q == NULL) p->q = &noop_qdisc; else diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 1e37247656f8..24893d3b5d22 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -55,7 +55,8 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch, return NET_XMIT_CN; } -static int fifo_init(struct Qdisc *sch, struct nlattr *opt) +static int fifo_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { bool bypass; bool is_bfifo = sch->ops == &bfifo_qdisc_ops; @@ -157,7 +158,7 @@ int fifo_set_limit(struct Qdisc *q, unsigned int limit) nla->nla_len = nla_attr_size(sizeof(struct tc_fifo_qopt)); ((struct tc_fifo_qopt *)nla_data(nla))->limit = limit; - ret = q->ops->change(q, nla); + ret = q->ops->change(q, nla, NULL); kfree(nla); } return ret; @@ -165,12 +166,14 @@ int fifo_set_limit(struct Qdisc *q, unsigned int limit) EXPORT_SYMBOL(fifo_set_limit); struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, - unsigned int limit) + unsigned int limit, + struct netlink_ext_ack *extack) { struct Qdisc *q; int err = -ENOMEM; - q = qdisc_create_dflt(sch->dev_queue, ops, TC_H_MAKE(sch->handle, 1)); + q = qdisc_create_dflt(sch->dev_queue, ops, TC_H_MAKE(sch->handle, 1), + extack); if (q) { err = fifo_set_limit(q, limit); if (err < 0) { diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 263d16e3219e..a366e4c9413a 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -685,7 +685,8 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { [TCA_FQ_LOW_RATE_THRESHOLD] = { .type = NLA_U32 }, }; -static int fq_change(struct Qdisc *sch, struct nlattr *opt) +static int fq_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct fq_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_MAX + 1]; @@ -788,7 +789,8 @@ static void fq_destroy(struct Qdisc *sch) qdisc_watchdog_cancel(&q->watchdog); } -static int fq_init(struct Qdisc *sch, struct nlattr *opt) +static int fq_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct fq_sched_data *q = qdisc_priv(sch); int err; @@ -811,7 +813,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt) qdisc_watchdog_init(&q->watchdog, sch); if (opt) - err = fq_change(sch, opt); + err = fq_change(sch, opt, extack); else err = fq_resize(sch, q->fq_trees_log); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 0305d791ea94..22fa13cf5d8b 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -377,7 +377,8 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { [TCA_FQ_CODEL_MEMORY_LIMIT] = { .type = NLA_U32 }, }; -static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt) +static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct fq_codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_CODEL_MAX + 1]; @@ -458,7 +459,8 @@ static void fq_codel_destroy(struct Qdisc *sch) kvfree(q->flows); } -static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) +static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct fq_codel_sched_data *q = qdisc_priv(sch); int i; @@ -477,12 +479,12 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) q->cparams.mtu = psched_mtu(qdisc_dev(sch)); if (opt) { - int err = fq_codel_change(sch, opt); + int err = fq_codel_change(sch, opt, extack); if (err) return err; } - err = tcf_block_get(&q->block, &q->filter_list, sch); + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; @@ -595,7 +597,8 @@ static void fq_codel_unbind(struct Qdisc *q, unsigned long cl) { } -static struct tcf_block *fq_codel_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *fq_codel_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct fq_codel_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index cac003fddf3e..190570f21b20 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -26,11 +26,13 @@ #include <linux/list.h> #include <linux/slab.h> #include <linux/if_vlan.h> +#include <linux/skb_array.h> #include <linux/if_macvlan.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/dst.h> #include <trace/events/qdisc.h> +#include <net/xfrm.h> /* Qdisc to use by default */ const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops; @@ -47,17 +49,115 @@ EXPORT_SYMBOL(default_qdisc_ops); * - updates to tree and tree walking are only done under the rtnl mutex. */ -static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) +static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q) +{ + const struct netdev_queue *txq = q->dev_queue; + spinlock_t *lock = NULL; + struct sk_buff *skb; + + if (q->flags & TCQ_F_NOLOCK) { + lock = qdisc_lock(q); + spin_lock(lock); + } + + skb = skb_peek(&q->skb_bad_txq); + if (skb) { + /* check the reason of requeuing without tx lock first */ + txq = skb_get_tx_queue(txq->dev, skb); + if (!netif_xmit_frozen_or_stopped(txq)) { + skb = __skb_dequeue(&q->skb_bad_txq); + if (qdisc_is_percpu_stats(q)) { + qdisc_qstats_cpu_backlog_dec(q, skb); + qdisc_qstats_cpu_qlen_dec(q); + } else { + qdisc_qstats_backlog_dec(q, skb); + q->q.qlen--; + } + } else { + skb = NULL; + } + } + + if (lock) + spin_unlock(lock); + + return skb; +} + +static inline struct sk_buff *qdisc_dequeue_skb_bad_txq(struct Qdisc *q) { - q->gso_skb = skb; - q->qstats.requeues++; - qdisc_qstats_backlog_inc(q, skb); - q->q.qlen++; /* it's still part of the queue */ + struct sk_buff *skb = skb_peek(&q->skb_bad_txq); + + if (unlikely(skb)) + skb = __skb_dequeue_bad_txq(q); + + return skb; +} + +static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q, + struct sk_buff *skb) +{ + spinlock_t *lock = NULL; + + if (q->flags & TCQ_F_NOLOCK) { + lock = qdisc_lock(q); + spin_lock(lock); + } + + __skb_queue_tail(&q->skb_bad_txq, skb); + + if (lock) + spin_unlock(lock); +} + +static inline int __dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) +{ + while (skb) { + struct sk_buff *next = skb->next; + + __skb_queue_tail(&q->gso_skb, skb); + q->qstats.requeues++; + qdisc_qstats_backlog_inc(q, skb); + q->q.qlen++; /* it's still part of the queue */ + + skb = next; + } + __netif_schedule(q); + + return 0; +} + +static inline int dev_requeue_skb_locked(struct sk_buff *skb, struct Qdisc *q) +{ + spinlock_t *lock = qdisc_lock(q); + + spin_lock(lock); + while (skb) { + struct sk_buff *next = skb->next; + + __skb_queue_tail(&q->gso_skb, skb); + + qdisc_qstats_cpu_requeues_inc(q); + qdisc_qstats_cpu_backlog_inc(q, skb); + qdisc_qstats_cpu_qlen_inc(q); + + skb = next; + } + spin_unlock(lock); + __netif_schedule(q); return 0; } +static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) +{ + if (q->flags & TCQ_F_NOLOCK) + return dev_requeue_skb_locked(skb, q); + else + return __dev_requeue_skb(skb, q); +} + static void try_bulk_dequeue_skb(struct Qdisc *q, struct sk_buff *skb, const struct netdev_queue *txq, @@ -95,9 +195,15 @@ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, if (!nskb) break; if (unlikely(skb_get_queue_mapping(nskb) != mapping)) { - q->skb_bad_txq = nskb; - qdisc_qstats_backlog_inc(q, nskb); - q->q.qlen++; + qdisc_enqueue_skb_bad_txq(q, nskb); + + if (qdisc_is_percpu_stats(q)) { + qdisc_qstats_cpu_backlog_inc(q, nskb); + qdisc_qstats_cpu_qlen_inc(q); + } else { + qdisc_qstats_backlog_inc(q, nskb); + q->q.qlen++; + } break; } skb->next = nskb; @@ -113,40 +219,62 @@ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, int *packets) { - struct sk_buff *skb = q->gso_skb; const struct netdev_queue *txq = q->dev_queue; + struct sk_buff *skb = NULL; *packets = 1; - if (unlikely(skb)) { + if (unlikely(!skb_queue_empty(&q->gso_skb))) { + spinlock_t *lock = NULL; + + if (q->flags & TCQ_F_NOLOCK) { + lock = qdisc_lock(q); + spin_lock(lock); + } + + skb = skb_peek(&q->gso_skb); + + /* skb may be null if another cpu pulls gso_skb off in between + * empty check and lock. + */ + if (!skb) { + if (lock) + spin_unlock(lock); + goto validate; + } + /* skb in gso_skb were already validated */ *validate = false; + if (xfrm_offload(skb)) + *validate = true; /* check the reason of requeuing without tx lock first */ txq = skb_get_tx_queue(txq->dev, skb); if (!netif_xmit_frozen_or_stopped(txq)) { - q->gso_skb = NULL; - qdisc_qstats_backlog_dec(q, skb); - q->q.qlen--; - } else + skb = __skb_dequeue(&q->gso_skb); + if (qdisc_is_percpu_stats(q)) { + qdisc_qstats_cpu_backlog_dec(q, skb); + qdisc_qstats_cpu_qlen_dec(q); + } else { + qdisc_qstats_backlog_dec(q, skb); + q->q.qlen--; + } + } else { skb = NULL; - goto trace; - } - *validate = true; - skb = q->skb_bad_txq; - if (unlikely(skb)) { - /* check the reason of requeuing without tx lock first */ - txq = skb_get_tx_queue(txq->dev, skb); - if (!netif_xmit_frozen_or_stopped(txq)) { - q->skb_bad_txq = NULL; - qdisc_qstats_backlog_dec(q, skb); - q->q.qlen--; - goto bulk; } - skb = NULL; + if (lock) + spin_unlock(lock); goto trace; } - if (!(q->flags & TCQ_F_ONETXQUEUE) || - !netif_xmit_frozen_or_stopped(txq)) - skb = q->dequeue(q); +validate: + *validate = true; + + if ((q->flags & TCQ_F_ONETXQUEUE) && + netif_xmit_frozen_or_stopped(txq)) + return skb; + + skb = qdisc_dequeue_skb_bad_txq(q); + if (unlikely(skb)) + goto bulk; + skb = q->dequeue(q); if (skb) { bulk: if (qdisc_may_bulk(q)) @@ -165,21 +293,33 @@ trace: * only one CPU can execute this function. * * Returns to the caller: - * 0 - queue is empty or throttled. - * >0 - queue is not empty. + * false - hardware queue frozen backoff + * true - feel free to send more pkts */ -int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, - struct net_device *dev, struct netdev_queue *txq, - spinlock_t *root_lock, bool validate) +bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, + struct net_device *dev, struct netdev_queue *txq, + spinlock_t *root_lock, bool validate) { int ret = NETDEV_TX_BUSY; + bool again = false; /* And release qdisc */ - spin_unlock(root_lock); + if (root_lock) + spin_unlock(root_lock); /* Note that we validate skb (GSO, checksum, ...) outside of locks */ if (validate) - skb = validate_xmit_skb_list(skb, dev); + skb = validate_xmit_skb_list(skb, dev, &again); + +#ifdef CONFIG_XFRM_OFFLOAD + if (unlikely(again)) { + if (root_lock) + spin_lock(root_lock); + + dev_requeue_skb(skb, q); + return false; + } +#endif if (likely(skb)) { HARD_TX_LOCK(dev, txq, smp_processor_id()); @@ -188,27 +328,28 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, HARD_TX_UNLOCK(dev, txq); } else { - spin_lock(root_lock); - return qdisc_qlen(q); + if (root_lock) + spin_lock(root_lock); + return true; } - spin_lock(root_lock); - if (dev_xmit_complete(ret)) { - /* Driver sent out skb successfully or skb was consumed */ - ret = qdisc_qlen(q); - } else { + if (root_lock) + spin_lock(root_lock); + + if (!dev_xmit_complete(ret)) { /* Driver returned NETDEV_TX_BUSY - requeue skb */ if (unlikely(ret != NETDEV_TX_BUSY)) net_warn_ratelimited("BUG %s code %d qlen %d\n", dev->name, ret, q->q.qlen); - ret = dev_requeue_skb(skb, q); + dev_requeue_skb(skb, q); + return false; } if (ret && netif_xmit_frozen_or_stopped(txq)) - ret = 0; + return false; - return ret; + return true; } /* @@ -230,20 +371,22 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, * >0 - queue is not empty. * */ -static inline int qdisc_restart(struct Qdisc *q, int *packets) +static inline bool qdisc_restart(struct Qdisc *q, int *packets) { + spinlock_t *root_lock = NULL; struct netdev_queue *txq; struct net_device *dev; - spinlock_t *root_lock; struct sk_buff *skb; bool validate; /* Dequeue packet */ skb = dequeue_skb(q, &validate, packets); if (unlikely(!skb)) - return 0; + return false; + + if (!(q->flags & TCQ_F_NOLOCK)) + root_lock = qdisc_lock(q); - root_lock = qdisc_lock(q); dev = qdisc_dev(q); txq = skb_get_tx_queue(dev, skb); @@ -267,8 +410,6 @@ void __qdisc_run(struct Qdisc *q) break; } } - - qdisc_run_end(q); } unsigned long dev_trans_start(struct net_device *dev) @@ -369,7 +510,7 @@ void netif_carrier_on(struct net_device *dev) if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) { if (dev->reg_state == NETREG_UNINITIALIZED) return; - atomic_inc(&dev->carrier_changes); + atomic_inc(&dev->carrier_up_count); linkwatch_fire_event(dev); if (netif_running(dev)) __netdev_watchdog_up(dev); @@ -388,7 +529,7 @@ void netif_carrier_off(struct net_device *dev) if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) { if (dev->reg_state == NETREG_UNINITIALIZED) return; - atomic_inc(&dev->carrier_changes); + atomic_inc(&dev->carrier_down_count); linkwatch_fire_event(dev); } } @@ -437,7 +578,8 @@ struct Qdisc noop_qdisc = { }; EXPORT_SYMBOL(noop_qdisc); -static int noqueue_init(struct Qdisc *qdisc, struct nlattr *opt) +static int noqueue_init(struct Qdisc *qdisc, struct nlattr *opt, + struct netlink_ext_ack *extack) { /* register_qdisc() assigns a default of noop_enqueue if unset, * but __dev_queue_xmit() treats noqueue only as such @@ -468,93 +610,99 @@ static const u8 prio2band[TC_PRIO_MAX + 1] = { /* * Private data for a pfifo_fast scheduler containing: - * - queues for the three band - * - bitmap indicating which of the bands contain skbs + * - rings for priority bands */ struct pfifo_fast_priv { - u32 bitmap; - struct qdisc_skb_head q[PFIFO_FAST_BANDS]; + struct skb_array q[PFIFO_FAST_BANDS]; }; -/* - * Convert a bitmap to the first band number where an skb is queued, where: - * bitmap=0 means there are no skbs on any band. - * bitmap=1 means there is an skb on band 0. - * bitmap=7 means there are skbs on all 3 bands, etc. - */ -static const int bitmap2band[] = {-1, 0, 1, 0, 2, 0, 1, 0}; - -static inline struct qdisc_skb_head *band2list(struct pfifo_fast_priv *priv, - int band) +static inline struct skb_array *band2list(struct pfifo_fast_priv *priv, + int band) { - return priv->q + band; + return &priv->q[band]; } static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, struct sk_buff **to_free) { - if (qdisc->q.qlen < qdisc_dev(qdisc)->tx_queue_len) { - int band = prio2band[skb->priority & TC_PRIO_MAX]; - struct pfifo_fast_priv *priv = qdisc_priv(qdisc); - struct qdisc_skb_head *list = band2list(priv, band); - - priv->bitmap |= (1 << band); - qdisc->q.qlen++; - return __qdisc_enqueue_tail(skb, qdisc, list); - } + int band = prio2band[skb->priority & TC_PRIO_MAX]; + struct pfifo_fast_priv *priv = qdisc_priv(qdisc); + struct skb_array *q = band2list(priv, band); + int err; + + err = skb_array_produce(q, skb); - return qdisc_drop(skb, qdisc, to_free); + if (unlikely(err)) + return qdisc_drop_cpu(skb, qdisc, to_free); + + qdisc_qstats_cpu_qlen_inc(qdisc); + qdisc_qstats_cpu_backlog_inc(qdisc, skb); + return NET_XMIT_SUCCESS; } static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); - int band = bitmap2band[priv->bitmap]; - - if (likely(band >= 0)) { - struct qdisc_skb_head *qh = band2list(priv, band); - struct sk_buff *skb = __qdisc_dequeue_head(qh); + struct sk_buff *skb = NULL; + int band; - if (likely(skb != NULL)) { - qdisc_qstats_backlog_dec(qdisc, skb); - qdisc_bstats_update(qdisc, skb); - } + for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) { + struct skb_array *q = band2list(priv, band); - qdisc->q.qlen--; - if (qh->qlen == 0) - priv->bitmap &= ~(1 << band); + if (__skb_array_empty(q)) + continue; - return skb; + skb = skb_array_consume_bh(q); + } + if (likely(skb)) { + qdisc_qstats_cpu_backlog_dec(qdisc, skb); + qdisc_bstats_cpu_update(qdisc, skb); + qdisc_qstats_cpu_qlen_dec(qdisc); } - return NULL; + return skb; } static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); - int band = bitmap2band[priv->bitmap]; + struct sk_buff *skb = NULL; + int band; - if (band >= 0) { - struct qdisc_skb_head *qh = band2list(priv, band); + for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) { + struct skb_array *q = band2list(priv, band); - return qh->head; + skb = __skb_array_peek(q); } - return NULL; + return skb; } static void pfifo_fast_reset(struct Qdisc *qdisc) { - int prio; + int i, band; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); - for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) - __qdisc_reset_queue(band2list(priv, prio)); + for (band = 0; band < PFIFO_FAST_BANDS; band++) { + struct skb_array *q = band2list(priv, band); + struct sk_buff *skb; - priv->bitmap = 0; - qdisc->qstats.backlog = 0; - qdisc->q.qlen = 0; + /* NULL ring is possible if destroy path is due to a failed + * skb_array_init() in pfifo_fast_init() case. + */ + if (!q->ring.queue) + continue; + + while ((skb = skb_array_consume_bh(q)) != NULL) + kfree_skb(skb); + } + + for_each_possible_cpu(i) { + struct gnet_stats_queue *q = per_cpu_ptr(qdisc->cpu_qstats, i); + + q->backlog = 0; + q->qlen = 0; + } } static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb) @@ -570,19 +718,68 @@ nla_put_failure: return -1; } -static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt) +static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt, + struct netlink_ext_ack *extack) { - int prio; + unsigned int qlen = qdisc_dev(qdisc)->tx_queue_len; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); + int prio; + + /* guard against zero length rings */ + if (!qlen) + return -EINVAL; - for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) - qdisc_skb_head_init(band2list(priv, prio)); + for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { + struct skb_array *q = band2list(priv, prio); + int err; + + err = skb_array_init(q, qlen, GFP_KERNEL); + if (err) + return -ENOMEM; + } /* Can by-pass the queue discipline */ qdisc->flags |= TCQ_F_CAN_BYPASS; return 0; } +static void pfifo_fast_destroy(struct Qdisc *sch) +{ + struct pfifo_fast_priv *priv = qdisc_priv(sch); + int prio; + + for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { + struct skb_array *q = band2list(priv, prio); + + /* NULL ring is possible if destroy path is due to a failed + * skb_array_init() in pfifo_fast_init() case. + */ + if (!q->ring.queue) + continue; + /* Destroy ring but no need to kfree_skb because a call to + * pfifo_fast_reset() has already done that work. + */ + ptr_ring_cleanup(&q->ring, NULL); + } +} + +static int pfifo_fast_change_tx_queue_len(struct Qdisc *sch, + unsigned int new_len) +{ + struct pfifo_fast_priv *priv = qdisc_priv(sch); + struct skb_array *bands[PFIFO_FAST_BANDS]; + int prio; + + for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { + struct skb_array *q = band2list(priv, prio); + + bands[prio] = q; + } + + return skb_array_resize_multiple(bands, PFIFO_FAST_BANDS, new_len, + GFP_KERNEL); +} + struct Qdisc_ops pfifo_fast_ops __read_mostly = { .id = "pfifo_fast", .priv_size = sizeof(struct pfifo_fast_priv), @@ -590,9 +787,12 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = { .dequeue = pfifo_fast_dequeue, .peek = pfifo_fast_peek, .init = pfifo_fast_init, + .destroy = pfifo_fast_destroy, .reset = pfifo_fast_reset, .dump = pfifo_fast_dump, + .change_tx_queue_len = pfifo_fast_change_tx_queue_len, .owner = THIS_MODULE, + .static_flags = TCQ_F_NOLOCK | TCQ_F_CPUSTATS, }; EXPORT_SYMBOL(pfifo_fast_ops); @@ -600,7 +800,8 @@ static struct lock_class_key qdisc_tx_busylock; static struct lock_class_key qdisc_running_key; struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, - const struct Qdisc_ops *ops) + const struct Qdisc_ops *ops, + struct netlink_ext_ack *extack) { void *p; struct Qdisc *sch; @@ -609,6 +810,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, struct net_device *dev; if (!dev_queue) { + NL_SET_ERR_MSG(extack, "No device queue given"); err = -EINVAL; goto errout; } @@ -630,6 +832,8 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p); sch->padded = (char *) sch - (char *) p; } + __skb_queue_head_init(&sch->gso_skb); + __skb_queue_head_init(&sch->skb_bad_txq); qdisc_skb_head_init(&sch->q); spin_lock_init(&sch->q.lock); @@ -671,21 +875,24 @@ errout: struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, - unsigned int parentid) + unsigned int parentid, + struct netlink_ext_ack *extack) { struct Qdisc *sch; - if (!try_module_get(ops->owner)) + if (!try_module_get(ops->owner)) { + NL_SET_ERR_MSG(extack, "Failed to increase module reference counter"); return NULL; + } - sch = qdisc_alloc(dev_queue, ops); + sch = qdisc_alloc(dev_queue, ops, extack); if (IS_ERR(sch)) { module_put(ops->owner); return NULL; } sch->parent = parentid; - if (!ops->init || ops->init(sch, NULL) == 0) + if (!ops->init || ops->init(sch, NULL, extack) == 0) return sch; qdisc_destroy(sch); @@ -698,17 +905,21 @@ EXPORT_SYMBOL(qdisc_create_dflt); void qdisc_reset(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; + struct sk_buff *skb, *tmp; if (ops->reset) ops->reset(qdisc); - kfree_skb(qdisc->skb_bad_txq); - qdisc->skb_bad_txq = NULL; + skb_queue_walk_safe(&qdisc->gso_skb, skb, tmp) { + __skb_unlink(skb, &qdisc->gso_skb); + kfree_skb_list(skb); + } - if (qdisc->gso_skb) { - kfree_skb_list(qdisc->gso_skb); - qdisc->gso_skb = NULL; + skb_queue_walk_safe(&qdisc->skb_bad_txq, skb, tmp) { + __skb_unlink(skb, &qdisc->skb_bad_txq); + kfree_skb_list(skb); } + qdisc->q.qlen = 0; qdisc->qstats.backlog = 0; } @@ -727,6 +938,7 @@ void qdisc_free(struct Qdisc *qdisc) void qdisc_destroy(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; + struct sk_buff *skb, *tmp; if (qdisc->flags & TCQ_F_BUILTIN || !refcount_dec_and_test(&qdisc->refcnt)) @@ -746,8 +958,16 @@ void qdisc_destroy(struct Qdisc *qdisc) module_put(ops->owner); dev_put(qdisc_dev(qdisc)); - kfree_skb_list(qdisc->gso_skb); - kfree_skb(qdisc->skb_bad_txq); + skb_queue_walk_safe(&qdisc->gso_skb, skb, tmp) { + __skb_unlink(skb, &qdisc->gso_skb); + kfree_skb_list(skb); + } + + skb_queue_walk_safe(&qdisc->skb_bad_txq, skb, tmp) { + __skb_unlink(skb, &qdisc->skb_bad_txq); + kfree_skb_list(skb); + } + qdisc_free(qdisc); } EXPORT_SYMBOL(qdisc_destroy); @@ -762,10 +982,6 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, root_lock = qdisc_lock(oqdisc); spin_lock_bh(root_lock); - /* Prune old scheduler */ - if (oqdisc && refcount_read(&oqdisc->refcnt) <= 1) - qdisc_reset(oqdisc); - /* ... and graft new one */ if (qdisc == NULL) qdisc = &noop_qdisc; @@ -788,7 +1004,7 @@ static void attach_one_default_qdisc(struct net_device *dev, if (dev->priv_flags & IFF_NO_QUEUE) ops = &noqueue_qdisc_ops; - qdisc = qdisc_create_dflt(dev_queue, ops, TC_H_ROOT); + qdisc = qdisc_create_dflt(dev_queue, ops, TC_H_ROOT, NULL); if (!qdisc) { netdev_info(dev, "activation failed\n"); return; @@ -811,7 +1027,7 @@ static void attach_default_qdiscs(struct net_device *dev) dev->qdisc = txq->qdisc_sleeping; qdisc_refcount_inc(dev->qdisc); } else { - qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT); + qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT, NULL); if (qdisc) { dev->qdisc = qdisc; qdisc->ops->attach(qdisc); @@ -901,14 +1117,18 @@ static bool some_qdisc_is_busy(struct net_device *dev) dev_queue = netdev_get_tx_queue(dev, i); q = dev_queue->qdisc_sleeping; - root_lock = qdisc_lock(q); - spin_lock_bh(root_lock); + if (q->flags & TCQ_F_NOLOCK) { + val = test_bit(__QDISC_STATE_SCHED, &q->state); + } else { + root_lock = qdisc_lock(q); + spin_lock_bh(root_lock); - val = (qdisc_is_running(q) || - test_bit(__QDISC_STATE_SCHED, &q->state)); + val = (qdisc_is_running(q) || + test_bit(__QDISC_STATE_SCHED, &q->state)); - spin_unlock_bh(root_lock); + spin_unlock_bh(root_lock); + } if (val) return true; @@ -916,6 +1136,16 @@ static bool some_qdisc_is_busy(struct net_device *dev) return false; } +static void dev_qdisc_reset(struct net_device *dev, + struct netdev_queue *dev_queue, + void *none) +{ + struct Qdisc *qdisc = dev_queue->qdisc_sleeping; + + if (qdisc) + qdisc_reset(qdisc); +} + /** * dev_deactivate_many - deactivate transmissions on several devices * @head: list of devices to deactivate @@ -926,7 +1156,6 @@ static bool some_qdisc_is_busy(struct net_device *dev) void dev_deactivate_many(struct list_head *head) { struct net_device *dev; - bool sync_needed = false; list_for_each_entry(dev, head, close_list) { netdev_for_each_tx_queue(dev, dev_deactivate_queue, @@ -936,20 +1165,25 @@ void dev_deactivate_many(struct list_head *head) &noop_qdisc); dev_watchdog_down(dev); - sync_needed |= !dev->dismantle; } /* Wait for outstanding qdisc-less dev_queue_xmit calls. * This is avoided if all devices are in dismantle phase : * Caller will call synchronize_net() for us */ - if (sync_needed) - synchronize_net(); + synchronize_net(); /* Wait for outstanding qdisc_run calls. */ - list_for_each_entry(dev, head, close_list) + list_for_each_entry(dev, head, close_list) { while (some_qdisc_is_busy(dev)) yield(); + /* The new qdisc is assigned at this point so we can safely + * unwind stale skb lists and qdisc statistics + */ + netdev_for_each_tx_queue(dev, dev_qdisc_reset, NULL); + if (dev_ingress_queue(dev)) + dev_qdisc_reset(dev, dev_ingress_queue(dev), NULL); + } } void dev_deactivate(struct net_device *dev) @@ -962,6 +1196,39 @@ void dev_deactivate(struct net_device *dev) } EXPORT_SYMBOL(dev_deactivate); +static int qdisc_change_tx_queue_len(struct net_device *dev, + struct netdev_queue *dev_queue) +{ + struct Qdisc *qdisc = dev_queue->qdisc_sleeping; + const struct Qdisc_ops *ops = qdisc->ops; + + if (ops->change_tx_queue_len) + return ops->change_tx_queue_len(qdisc, dev->tx_queue_len); + return 0; +} + +int dev_qdisc_change_tx_queue_len(struct net_device *dev) +{ + bool up = dev->flags & IFF_UP; + unsigned int i; + int ret = 0; + + if (up) + dev_deactivate(dev); + + for (i = 0; i < dev->num_tx_queues; i++) { + ret = qdisc_change_tx_queue_len(dev, &dev->_tx[i]); + + /* TODO: revert changes on a partial failure */ + if (ret) + break; + } + + if (up) + dev_activate(dev); + return ret; +} + static void dev_init_scheduler_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_qdisc) @@ -970,6 +1237,8 @@ static void dev_init_scheduler_queue(struct net_device *dev, rcu_assign_pointer(dev_queue->qdisc, qdisc); dev_queue->qdisc_sleeping = qdisc; + __skb_queue_head_init(&qdisc->gso_skb); + __skb_queue_head_init(&qdisc->skb_bad_txq); } void dev_init_scheduler(struct net_device *dev) diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index bc30f9186ac6..cbe4831f46f4 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -306,12 +306,13 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps) struct tc_gred_sopt *sopt; int i; - if (dps == NULL) + if (!dps) return -EINVAL; sopt = nla_data(dps); - if (sopt->DPs > MAX_DPs || sopt->DPs == 0 || sopt->def_DP >= sopt->DPs) + if (sopt->DPs > MAX_DPs || sopt->DPs == 0 || + sopt->def_DP >= sopt->DPs) return -EINVAL; sch_tree_lock(sch); @@ -391,7 +392,8 @@ static const struct nla_policy gred_policy[TCA_GRED_MAX + 1] = { [TCA_GRED_LIMIT] = { .type = NLA_U32 }, }; -static int gred_change(struct Qdisc *sch, struct nlattr *opt) +static int gred_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct gred_sched *table = qdisc_priv(sch); struct tc_gred_qopt *ctl; @@ -465,12 +467,13 @@ errout: return err; } -static int gred_init(struct Qdisc *sch, struct nlattr *opt) +static int gred_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_GRED_MAX + 1]; int err; - if (opt == NULL) + if (!opt) return -EINVAL; err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy, NULL); diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index d04068a97d81..3ae9877ea205 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -921,7 +921,8 @@ static const struct nla_policy hfsc_policy[TCA_HFSC_MAX + 1] = { static int hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, - struct nlattr **tca, unsigned long *arg) + struct nlattr **tca, unsigned long *arg, + struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)*arg; @@ -1033,7 +1034,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; - err = tcf_block_get(&cl->block, &cl->filter_list, sch); + err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); return err; @@ -1061,8 +1062,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cl->cl_common.classid = classid; cl->sched = q; cl->cl_parent = parent; - cl->qdisc = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, classid); + cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + classid, NULL); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; else @@ -1176,7 +1177,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) static int hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct hfsc_class *cl = (struct hfsc_class *)arg; @@ -1184,7 +1185,7 @@ hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, return -EINVAL; if (new == NULL) { new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - cl->cl_common.classid); + cl->cl_common.classid, NULL); if (new == NULL) new = &noop_qdisc; } @@ -1246,7 +1247,8 @@ hfsc_unbind_tcf(struct Qdisc *sch, unsigned long arg) cl->filter_cnt--; } -static struct tcf_block *hfsc_tcf_block(struct Qdisc *sch, unsigned long arg) +static struct tcf_block *hfsc_tcf_block(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)arg; @@ -1388,7 +1390,8 @@ hfsc_schedule_watchdog(struct Qdisc *sch) } static int -hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) +hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct tc_hfsc_qopt *qopt; @@ -1396,7 +1399,7 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) qdisc_watchdog_init(&q->watchdog, sch); - if (opt == NULL || nla_len(opt) < sizeof(*qopt)) + if (!opt || nla_len(opt) < sizeof(*qopt)) return -EINVAL; qopt = nla_data(opt); @@ -1406,14 +1409,14 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) return err; q->eligible = RB_ROOT; - err = tcf_block_get(&q->root.block, &q->root.filter_list, sch); + err = tcf_block_get(&q->root.block, &q->root.filter_list, sch, extack); if (err) return err; q->root.cl_common.classid = sch->handle; q->root.sched = q; q->root.qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle); + sch->handle, NULL); if (q->root.qdisc == NULL) q->root.qdisc = &noop_qdisc; else @@ -1429,7 +1432,8 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) } static int -hfsc_change_qdisc(struct Qdisc *sch, struct nlattr *opt) +hfsc_change_qdisc(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct tc_hfsc_qopt *qopt; diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 73a53c08091b..bce2632212d3 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -504,7 +504,8 @@ static const struct nla_policy hhf_policy[TCA_HHF_MAX + 1] = { [TCA_HHF_NON_HH_WEIGHT] = { .type = NLA_U32 }, }; -static int hhf_change(struct Qdisc *sch, struct nlattr *opt) +static int hhf_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct hhf_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_HHF_MAX + 1]; @@ -571,7 +572,8 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt) return 0; } -static int hhf_init(struct Qdisc *sch, struct nlattr *opt) +static int hhf_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct hhf_sched_data *q = qdisc_priv(sch); int i; @@ -589,7 +591,7 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt) q->hhf_non_hh_weight = 2; if (opt) { - int err = hhf_change(sch, opt); + int err = hhf_change(sch, opt, extack); if (err) return err; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index fa0380730ff0..1ea9846cc6ce 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1017,7 +1017,8 @@ static void htb_work_func(struct work_struct *work) rcu_read_unlock(); } -static int htb_init(struct Qdisc *sch, struct nlattr *opt) +static int htb_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct htb_sched *q = qdisc_priv(sch); struct nlattr *tb[TCA_HTB_MAX + 1]; @@ -1031,7 +1032,7 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list, sch); + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; @@ -1171,7 +1172,7 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) } static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct htb_class *cl = (struct htb_class *)arg; @@ -1179,7 +1180,7 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, return -EINVAL; if (new == NULL && (new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - cl->common.classid)) == NULL) + cl->common.classid, extack)) == NULL) return -ENOBUFS; *old = qdisc_replace(sch, new, &cl->un.leaf.q); @@ -1289,7 +1290,8 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) if (!cl->level && htb_parent_last_child(cl)) { new_q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - cl->parent->common.classid); + cl->parent->common.classid, + NULL); last_child = 1; } @@ -1326,7 +1328,7 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) static int htb_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, - unsigned long *arg) + unsigned long *arg, struct netlink_ext_ack *extack) { int err = -EINVAL; struct htb_sched *q = qdisc_priv(sch); @@ -1356,10 +1358,12 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, /* Keeping backward compatible with rate_table based iproute2 tc */ if (hopt->rate.linklayer == TC_LINKLAYER_UNAWARE) - qdisc_put_rtab(qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB])); + qdisc_put_rtab(qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB], + NULL)); if (hopt->ceil.linklayer == TC_LINKLAYER_UNAWARE) - qdisc_put_rtab(qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB])); + qdisc_put_rtab(qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB], + NULL)); if (!cl) { /* new class */ struct Qdisc *new_q; @@ -1394,7 +1398,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!cl) goto failure; - err = tcf_block_get(&cl->block, &cl->filter_list, sch); + err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); goto failure; @@ -1423,8 +1427,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, * so that can't be used inside of sch_tree_lock * -- thanks to Karlis Peisenieks */ - new_q = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, classid); + new_q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + classid, NULL); sch_tree_lock(sch); if (parent && !parent->level) { unsigned int qlen = parent->un.leaf.q->q.qlen; @@ -1524,7 +1528,8 @@ failure: return err; } -static struct tcf_block *htb_tcf_block(struct Qdisc *sch, unsigned long arg) +static struct tcf_block *htb_tcf_block(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)arg; diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 003e1b063447..ce3f55259d0d 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -48,7 +48,8 @@ static void ingress_walk(struct Qdisc *sch, struct qdisc_walker *walker) { } -static struct tcf_block *ingress_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *ingress_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct ingress_sched_data *q = qdisc_priv(sch); @@ -60,9 +61,24 @@ static void clsact_chain_head_change(struct tcf_proto *tp_head, void *priv) struct mini_Qdisc_pair *miniqp = priv; mini_qdisc_pair_swap(miniqp, tp_head); +}; + +static void ingress_ingress_block_set(struct Qdisc *sch, u32 block_index) +{ + struct ingress_sched_data *q = qdisc_priv(sch); + + q->block_info.block_index = block_index; } -static int ingress_init(struct Qdisc *sch, struct nlattr *opt) +static u32 ingress_ingress_block_get(struct Qdisc *sch) +{ + struct ingress_sched_data *q = qdisc_priv(sch); + + return q->block_info.block_index; +} + +static int ingress_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct ingress_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); @@ -75,7 +91,7 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) q->block_info.chain_head_change = clsact_chain_head_change; q->block_info.chain_head_change_priv = &q->miniqp; - return tcf_block_get_ext(&q->block, sch, &q->block_info); + return tcf_block_get_ext(&q->block, sch, &q->block_info, extack); } static void ingress_destroy(struct Qdisc *sch) @@ -111,14 +127,16 @@ static const struct Qdisc_class_ops ingress_class_ops = { }; static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { - .cl_ops = &ingress_class_ops, - .id = "ingress", - .priv_size = sizeof(struct ingress_sched_data), - .static_flags = TCQ_F_CPUSTATS, - .init = ingress_init, - .destroy = ingress_destroy, - .dump = ingress_dump, - .owner = THIS_MODULE, + .cl_ops = &ingress_class_ops, + .id = "ingress", + .priv_size = sizeof(struct ingress_sched_data), + .static_flags = TCQ_F_CPUSTATS, + .init = ingress_init, + .destroy = ingress_destroy, + .dump = ingress_dump, + .ingress_block_set = ingress_ingress_block_set, + .ingress_block_get = ingress_ingress_block_get, + .owner = THIS_MODULE, }; struct clsact_sched_data { @@ -147,7 +165,8 @@ static unsigned long clsact_bind_filter(struct Qdisc *sch, return clsact_find(sch, classid); } -static struct tcf_block *clsact_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *clsact_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct clsact_sched_data *q = qdisc_priv(sch); @@ -161,7 +180,36 @@ static struct tcf_block *clsact_tcf_block(struct Qdisc *sch, unsigned long cl) } } -static int clsact_init(struct Qdisc *sch, struct nlattr *opt) +static void clsact_ingress_block_set(struct Qdisc *sch, u32 block_index) +{ + struct clsact_sched_data *q = qdisc_priv(sch); + + q->ingress_block_info.block_index = block_index; +} + +static void clsact_egress_block_set(struct Qdisc *sch, u32 block_index) +{ + struct clsact_sched_data *q = qdisc_priv(sch); + + q->egress_block_info.block_index = block_index; +} + +static u32 clsact_ingress_block_get(struct Qdisc *sch) +{ + struct clsact_sched_data *q = qdisc_priv(sch); + + return q->ingress_block_info.block_index; +} + +static u32 clsact_egress_block_get(struct Qdisc *sch) +{ + struct clsact_sched_data *q = qdisc_priv(sch); + + return q->egress_block_info.block_index; +} + +static int clsact_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct clsact_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); @@ -176,7 +224,8 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) q->ingress_block_info.chain_head_change = clsact_chain_head_change; q->ingress_block_info.chain_head_change_priv = &q->miniqp_ingress; - err = tcf_block_get_ext(&q->ingress_block, sch, &q->ingress_block_info); + err = tcf_block_get_ext(&q->ingress_block, sch, &q->ingress_block_info, + extack); if (err) return err; @@ -186,7 +235,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) q->egress_block_info.chain_head_change = clsact_chain_head_change; q->egress_block_info.chain_head_change_priv = &q->miniqp_egress; - return tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info); + return tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info, extack); } static void clsact_destroy(struct Qdisc *sch) @@ -210,14 +259,18 @@ static const struct Qdisc_class_ops clsact_class_ops = { }; static struct Qdisc_ops clsact_qdisc_ops __read_mostly = { - .cl_ops = &clsact_class_ops, - .id = "clsact", - .priv_size = sizeof(struct clsact_sched_data), - .static_flags = TCQ_F_CPUSTATS, - .init = clsact_init, - .destroy = clsact_destroy, - .dump = ingress_dump, - .owner = THIS_MODULE, + .cl_ops = &clsact_class_ops, + .id = "clsact", + .priv_size = sizeof(struct clsact_sched_data), + .static_flags = TCQ_F_CPUSTATS, + .init = clsact_init, + .destroy = clsact_destroy, + .dump = ingress_dump, + .ingress_block_set = clsact_ingress_block_set, + .egress_block_set = clsact_egress_block_set, + .ingress_block_get = clsact_ingress_block_get, + .egress_block_get = clsact_egress_block_get, + .owner = THIS_MODULE, }; static int __init ingress_module_init(void) diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index 213b586a06a0..f062a18e9162 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -17,6 +17,7 @@ #include <linux/skbuff.h> #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/sch_generic.h> struct mq_sched { struct Qdisc **qdiscs; @@ -35,7 +36,8 @@ static void mq_destroy(struct Qdisc *sch) kfree(priv->qdiscs); } -static int mq_init(struct Qdisc *sch, struct nlattr *opt) +static int mq_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct net_device *dev = qdisc_dev(sch); struct mq_sched *priv = qdisc_priv(sch); @@ -59,7 +61,8 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt) dev_queue = netdev_get_tx_queue(dev, ntx); qdisc = qdisc_create_dflt(dev_queue, get_default_qdisc_ops(dev, ntx), TC_H_MAKE(TC_H_MAJ(sch->handle), - TC_H_MIN(ntx + 1))); + TC_H_MIN(ntx + 1)), + extack); if (!qdisc) return -ENOMEM; priv->qdiscs[ntx] = qdisc; @@ -97,23 +100,42 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) struct net_device *dev = qdisc_dev(sch); struct Qdisc *qdisc; unsigned int ntx; + __u32 qlen = 0; sch->q.qlen = 0; memset(&sch->bstats, 0, sizeof(sch->bstats)); memset(&sch->qstats, 0, sizeof(sch->qstats)); + /* MQ supports lockless qdiscs. However, statistics accounting needs + * to account for all, none, or a mix of locked and unlocked child + * qdiscs. Percpu stats are added to counters in-band and locking + * qdisc totals are added at end. + */ for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; spin_lock_bh(qdisc_lock(qdisc)); - sch->q.qlen += qdisc->q.qlen; - sch->bstats.bytes += qdisc->bstats.bytes; - sch->bstats.packets += qdisc->bstats.packets; - sch->qstats.backlog += qdisc->qstats.backlog; - sch->qstats.drops += qdisc->qstats.drops; - sch->qstats.requeues += qdisc->qstats.requeues; - sch->qstats.overlimits += qdisc->qstats.overlimits; + + if (qdisc_is_percpu_stats(qdisc)) { + qlen = qdisc_qlen_sum(qdisc); + __gnet_stats_copy_basic(NULL, &sch->bstats, + qdisc->cpu_bstats, + &qdisc->bstats); + __gnet_stats_copy_queue(&sch->qstats, + qdisc->cpu_qstats, + &qdisc->qstats, qlen); + } else { + sch->q.qlen += qdisc->q.qlen; + sch->bstats.bytes += qdisc->bstats.bytes; + sch->bstats.packets += qdisc->bstats.packets; + sch->qstats.backlog += qdisc->qstats.backlog; + sch->qstats.drops += qdisc->qstats.drops; + sch->qstats.requeues += qdisc->qstats.requeues; + sch->qstats.overlimits += qdisc->qstats.overlimits; + } + spin_unlock_bh(qdisc_lock(qdisc)); } + return 0; } @@ -134,7 +156,7 @@ static struct netdev_queue *mq_select_queue(struct Qdisc *sch, } static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); struct net_device *dev = qdisc_dev(sch); diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index b85885a9d8a1..0e9d761cdd80 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -132,7 +132,8 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, return 0; } -static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) +static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct net_device *dev = qdisc_dev(sch); struct mqprio_sched *priv = qdisc_priv(sch); @@ -229,7 +230,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) qdisc = qdisc_create_dflt(dev_queue, get_default_qdisc_ops(dev, i), TC_H_MAKE(TC_H_MAJ(sch->handle), - TC_H_MIN(i + 1))); + TC_H_MIN(i + 1)), extack); if (!qdisc) return -ENOMEM; @@ -319,7 +320,7 @@ static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch, } static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct net_device *dev = qdisc_dev(sch); struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); @@ -388,22 +389,40 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) struct nlattr *nla = (struct nlattr *)skb_tail_pointer(skb); struct tc_mqprio_qopt opt = { 0 }; struct Qdisc *qdisc; - unsigned int i; + unsigned int ntx, tc; sch->q.qlen = 0; memset(&sch->bstats, 0, sizeof(sch->bstats)); memset(&sch->qstats, 0, sizeof(sch->qstats)); - for (i = 0; i < dev->num_tx_queues; i++) { - qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc); + /* MQ supports lockless qdiscs. However, statistics accounting needs + * to account for all, none, or a mix of locked and unlocked child + * qdiscs. Percpu stats are added to counters in-band and locking + * qdisc totals are added at end. + */ + for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { + qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; spin_lock_bh(qdisc_lock(qdisc)); - sch->q.qlen += qdisc->q.qlen; - sch->bstats.bytes += qdisc->bstats.bytes; - sch->bstats.packets += qdisc->bstats.packets; - sch->qstats.backlog += qdisc->qstats.backlog; - sch->qstats.drops += qdisc->qstats.drops; - sch->qstats.requeues += qdisc->qstats.requeues; - sch->qstats.overlimits += qdisc->qstats.overlimits; + + if (qdisc_is_percpu_stats(qdisc)) { + __u32 qlen = qdisc_qlen_sum(qdisc); + + __gnet_stats_copy_basic(NULL, &sch->bstats, + qdisc->cpu_bstats, + &qdisc->bstats); + __gnet_stats_copy_queue(&sch->qstats, + qdisc->cpu_qstats, + &qdisc->qstats, qlen); + } else { + sch->q.qlen += qdisc->q.qlen; + sch->bstats.bytes += qdisc->bstats.bytes; + sch->bstats.packets += qdisc->bstats.packets; + sch->qstats.backlog += qdisc->qstats.backlog; + sch->qstats.drops += qdisc->qstats.drops; + sch->qstats.requeues += qdisc->qstats.requeues; + sch->qstats.overlimits += qdisc->qstats.overlimits; + } + spin_unlock_bh(qdisc_lock(qdisc)); } @@ -411,9 +430,9 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); opt.hw = priv->hw_offload; - for (i = 0; i < netdev_get_num_tc(dev); i++) { - opt.count[i] = dev->tc_to_txq[i].count; - opt.offset[i] = dev->tc_to_txq[i].offset; + for (tc = 0; tc < netdev_get_num_tc(dev); tc++) { + opt.count[tc] = dev->tc_to_txq[tc].count; + opt.offset[tc] = dev->tc_to_txq[tc].offset; } if (nla_put(skb, TCA_OPTIONS, NLA_ALIGN(sizeof(opt)), &opt)) @@ -495,7 +514,6 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, if (cl >= TC_H_MIN_PRIORITY) { int i; __u32 qlen = 0; - struct Qdisc *qdisc; struct gnet_stats_queue qstats = {0}; struct gnet_stats_basic_packed bstats = {0}; struct net_device *dev = qdisc_dev(sch); @@ -511,18 +529,26 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, for (i = tc.offset; i < tc.offset + tc.count; i++) { struct netdev_queue *q = netdev_get_tx_queue(dev, i); + struct Qdisc *qdisc = rtnl_dereference(q->qdisc); + struct gnet_stats_basic_cpu __percpu *cpu_bstats = NULL; + struct gnet_stats_queue __percpu *cpu_qstats = NULL; - qdisc = rtnl_dereference(q->qdisc); spin_lock_bh(qdisc_lock(qdisc)); - qlen += qdisc->q.qlen; - bstats.bytes += qdisc->bstats.bytes; - bstats.packets += qdisc->bstats.packets; - qstats.backlog += qdisc->qstats.backlog; - qstats.drops += qdisc->qstats.drops; - qstats.requeues += qdisc->qstats.requeues; - qstats.overlimits += qdisc->qstats.overlimits; + if (qdisc_is_percpu_stats(qdisc)) { + cpu_bstats = qdisc->cpu_bstats; + cpu_qstats = qdisc->cpu_qstats; + } + + qlen = qdisc_qlen_sum(qdisc); + __gnet_stats_copy_basic(NULL, &sch->bstats, + cpu_bstats, &qdisc->bstats); + __gnet_stats_copy_queue(&sch->qstats, + cpu_qstats, + &qdisc->qstats, + qlen); spin_unlock_bh(qdisc_lock(qdisc)); } + /* Reclaim root sleeping lock before completing stats */ if (d->lock) spin_lock_bh(d->lock); diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 012216386c0b..1da7ea8de0ad 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -180,7 +180,8 @@ multiq_destroy(struct Qdisc *sch) kfree(q->queues); } -static int multiq_tune(struct Qdisc *sch, struct nlattr *opt) +static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct multiq_sched_data *q = qdisc_priv(sch); struct tc_multiq_qopt *qopt; @@ -215,7 +216,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt) child = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, TC_H_MAKE(sch->handle, - i + 1)); + i + 1), extack); if (child) { sch_tree_lock(sch); old = q->queues[i]; @@ -236,17 +237,18 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt) return 0; } -static int multiq_init(struct Qdisc *sch, struct nlattr *opt) +static int multiq_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct multiq_sched_data *q = qdisc_priv(sch); int i, err; q->queues = NULL; - if (opt == NULL) + if (!opt) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list, sch); + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; @@ -258,7 +260,7 @@ static int multiq_init(struct Qdisc *sch, struct nlattr *opt) for (i = 0; i < q->max_bands; i++) q->queues[i] = &noop_qdisc; - return multiq_tune(sch, opt); + return multiq_tune(sch, opt, extack); } static int multiq_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -281,7 +283,7 @@ nla_put_failure: } static int multiq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct multiq_sched_data *q = qdisc_priv(sch); unsigned long band = arg - 1; @@ -369,7 +371,8 @@ static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg) } } -static struct tcf_block *multiq_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *multiq_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct multiq_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index dd70924cbcdf..7bbc13b8ca47 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -893,7 +893,8 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, } /* Parse netlink message to set options */ -static int netem_change(struct Qdisc *sch, struct nlattr *opt) +static int netem_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_NETEM_MAX + 1]; @@ -984,7 +985,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) return ret; } -static int netem_init(struct Qdisc *sch, struct nlattr *opt) +static int netem_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct netem_sched_data *q = qdisc_priv(sch); int ret; @@ -995,7 +997,7 @@ static int netem_init(struct Qdisc *sch, struct nlattr *opt) return -EINVAL; q->loss_model = CLG_RANDOM; - ret = netem_change(sch, opt); + ret = netem_change(sch, opt, extack); if (ret) pr_info("netem: change failed\n"); return ret; @@ -1157,7 +1159,7 @@ static int netem_dump_class(struct Qdisc *sch, unsigned long cl, } static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct netem_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 776c694c77c7..18d30bb86881 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -181,7 +181,8 @@ static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = { [TCA_PIE_BYTEMODE] = {.type = NLA_U32}, }; -static int pie_change(struct Qdisc *sch, struct nlattr *opt) +static int pie_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct pie_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_PIE_MAX + 1]; @@ -439,7 +440,8 @@ static void pie_timer(struct timer_list *t) } -static int pie_init(struct Qdisc *sch, struct nlattr *opt) +static int pie_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct pie_sched_data *q = qdisc_priv(sch); @@ -451,7 +453,7 @@ static int pie_init(struct Qdisc *sch, struct nlattr *opt) timer_setup(&q->adapt_timer, pie_timer, 0); if (opt) { - int err = pie_change(sch, opt); + int err = pie_change(sch, opt, extack); if (err) return err; diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c index 1c6cbab3e7b9..5619d2eb17b6 100644 --- a/net/sched/sch_plug.c +++ b/net/sched/sch_plug.c @@ -123,7 +123,8 @@ static struct sk_buff *plug_dequeue(struct Qdisc *sch) return qdisc_dequeue_head(sch); } -static int plug_init(struct Qdisc *sch, struct nlattr *opt) +static int plug_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct plug_sched_data *q = qdisc_priv(sch); @@ -158,7 +159,8 @@ static int plug_init(struct Qdisc *sch, struct nlattr *opt) * command is received (just act as a pass-thru queue). * TCQ_PLUG_LIMIT: Increase/decrease queue size */ -static int plug_change(struct Qdisc *sch, struct nlattr *opt) +static int plug_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct plug_sched_data *q = qdisc_priv(sch); struct tc_plug_qopt *msg; diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 2c79559a0d31..efbf51f35778 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -142,6 +142,31 @@ prio_reset(struct Qdisc *sch) sch->q.qlen = 0; } +static int prio_offload(struct Qdisc *sch, bool enable) +{ + struct prio_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_prio_qopt_offload opt = { + .handle = sch->handle, + .parent = sch->parent, + }; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return -EOPNOTSUPP; + + if (enable) { + opt.command = TC_PRIO_REPLACE; + opt.replace_params.bands = q->bands; + memcpy(&opt.replace_params.priomap, q->prio2band, + TC_PRIO_MAX + 1); + opt.replace_params.qstats = &sch->qstats; + } else { + opt.command = TC_PRIO_DESTROY; + } + + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_PRIO, &opt); +} + static void prio_destroy(struct Qdisc *sch) { @@ -149,11 +174,13 @@ prio_destroy(struct Qdisc *sch) struct prio_sched_data *q = qdisc_priv(sch); tcf_block_put(q->block); + prio_offload(sch, false); for (prio = 0; prio < q->bands; prio++) qdisc_destroy(q->queues[prio]); } -static int prio_tune(struct Qdisc *sch, struct nlattr *opt) +static int prio_tune(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct prio_sched_data *q = qdisc_priv(sch); struct Qdisc *queues[TCQ_PRIO_BANDS]; @@ -175,7 +202,8 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) /* Before commit, make sure we can allocate all new qdiscs */ for (i = oldbands; i < qopt->bands; i++) { queues[i] = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - TC_H_MAKE(sch->handle, i + 1)); + TC_H_MAKE(sch->handle, i + 1), + extack); if (!queues[i]) { while (i > oldbands) qdisc_destroy(queues[--i]); @@ -202,10 +230,12 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) } sch_tree_unlock(sch); + prio_offload(sch, true); return 0; } -static int prio_init(struct Qdisc *sch, struct nlattr *opt) +static int prio_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct prio_sched_data *q = qdisc_priv(sch); int err; @@ -213,11 +243,42 @@ static int prio_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list, sch); + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; - return prio_tune(sch, opt); + return prio_tune(sch, opt, extack); +} + +static int prio_dump_offload(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_prio_qopt_offload hw_stats = { + .command = TC_PRIO_STATS, + .handle = sch->handle, + .parent = sch->parent, + { + .stats = { + .bstats = &sch->bstats, + .qstats = &sch->qstats, + }, + }, + }; + int err; + + sch->flags &= ~TCQ_F_OFFLOADED; + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return 0; + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_PRIO, + &hw_stats); + if (err == -EOPNOTSUPP) + return 0; + + if (!err) + sch->flags |= TCQ_F_OFFLOADED; + + return err; } static int prio_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -225,10 +286,15 @@ static int prio_dump(struct Qdisc *sch, struct sk_buff *skb) struct prio_sched_data *q = qdisc_priv(sch); unsigned char *b = skb_tail_pointer(skb); struct tc_prio_qopt opt; + int err; opt.bands = q->bands; memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX + 1); + err = prio_dump_offload(sch); + if (err) + goto nla_put_failure; + if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; @@ -240,7 +306,7 @@ nla_put_failure: } static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct prio_sched_data *q = qdisc_priv(sch); unsigned long band = arg - 1; @@ -327,7 +393,8 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg) } } -static struct tcf_block *prio_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *prio_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct prio_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 6962b37a3ad3..bb1a9c11fc54 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -402,7 +402,8 @@ static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight, } static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, - struct nlattr **tca, unsigned long *arg) + struct nlattr **tca, unsigned long *arg, + struct netlink_ext_ack *extack) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl = (struct qfq_class *)*arg; @@ -479,8 +480,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cl->common.classid = classid; cl->deficit = lmax; - cl->qdisc = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, classid); + cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + classid, NULL); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; @@ -564,7 +565,8 @@ static unsigned long qfq_search_class(struct Qdisc *sch, u32 classid) return (unsigned long)qfq_find_class(sch, classid); } -static struct tcf_block *qfq_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *qfq_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct qfq_sched *q = qdisc_priv(sch); @@ -593,13 +595,14 @@ static void qfq_unbind_tcf(struct Qdisc *sch, unsigned long arg) } static int qfq_graft_class(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old) + struct Qdisc *new, struct Qdisc **old, + struct netlink_ext_ack *extack) { struct qfq_class *cl = (struct qfq_class *)arg; if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, cl->common.classid); + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + cl->common.classid, NULL); if (new == NULL) new = &noop_qdisc; } @@ -1413,14 +1416,15 @@ static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg) qfq_deactivate_class(q, cl); } -static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt) +static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_group *grp; int i, j, err; u32 max_cl_shift, maxbudg_shift, max_classes; - err = tcf_block_get(&q->block, &q->filter_list, sch); + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index f0747eb87dc4..16644b3d2362 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -157,7 +157,6 @@ static int red_offload(struct Qdisc *sch, bool enable) .handle = sch->handle, .parent = sch->parent, }; - int err; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; @@ -168,18 +167,12 @@ static int red_offload(struct Qdisc *sch, bool enable) opt.set.max = q->parms.qth_max >> q->parms.Wlog; opt.set.probability = q->parms.max_P; opt.set.is_ecn = red_use_ecn(q); + opt.set.qstats = &sch->qstats; } else { opt.command = TC_RED_DESTROY; } - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, &opt); - - if (!err && enable) - sch->flags |= TCQ_F_OFFLOADED; - else - sch->flags &= ~TCQ_F_OFFLOADED; - - return err; + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, &opt); } static void red_destroy(struct Qdisc *sch) @@ -197,7 +190,8 @@ static const struct nla_policy red_policy[TCA_RED_MAX + 1] = { [TCA_RED_MAX_P] = { .type = NLA_U32 }, }; -static int red_change(struct Qdisc *sch, struct nlattr *opt) +static int red_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct red_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_RED_MAX + 1]; @@ -224,7 +218,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) return -EINVAL; if (ctl->limit > 0) { - child = fifo_create_dflt(sch, &bfifo_qdisc_ops, ctl->limit); + child = fifo_create_dflt(sch, &bfifo_qdisc_ops, ctl->limit, + extack); if (IS_ERR(child)) return PTR_ERR(child); } @@ -272,14 +267,15 @@ static inline void red_adaptative_timer(struct timer_list *t) spin_unlock(root_lock); } -static int red_init(struct Qdisc *sch, struct nlattr *opt) +static int red_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct red_sched_data *q = qdisc_priv(sch); q->qdisc = &noop_qdisc; q->sch = sch; timer_setup(&q->adapt_timer, red_adaptative_timer, 0); - return red_change(sch, opt); + return red_change(sch, opt, extack); } static int red_dump_offload_stats(struct Qdisc *sch, struct tc_red_qopt *opt) @@ -294,12 +290,22 @@ static int red_dump_offload_stats(struct Qdisc *sch, struct tc_red_qopt *opt) .stats.qstats = &sch->qstats, }, }; + int err; - if (!(sch->flags & TCQ_F_OFFLOADED)) + sch->flags &= ~TCQ_F_OFFLOADED; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return 0; - return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, - &hw_stats); + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, + &hw_stats); + if (err == -EOPNOTSUPP) + return 0; + + if (!err) + sch->flags |= TCQ_F_OFFLOADED; + + return err; } static int red_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -317,7 +323,6 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) }; int err; - sch->qstats.backlog = q->qdisc->qstats.backlog; err = red_dump_offload_stats(sch, &opt); if (err) goto nla_put_failure; @@ -339,32 +344,24 @@ static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct red_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); - struct tc_red_xstats st = { - .early = q->stats.prob_drop + q->stats.forced_drop, - .pdrop = q->stats.pdrop, - .other = q->stats.other, - .marked = q->stats.prob_mark + q->stats.forced_mark, - }; + struct tc_red_xstats st = {0}; if (sch->flags & TCQ_F_OFFLOADED) { - struct red_stats hw_stats = {0}; struct tc_red_qopt_offload hw_stats_request = { .command = TC_RED_XSTATS, .handle = sch->handle, .parent = sch->parent, { - .xstats = &hw_stats, + .xstats = &q->stats, }, }; - if (!dev->netdev_ops->ndo_setup_tc(dev, - TC_SETUP_QDISC_RED, - &hw_stats_request)) { - st.early += hw_stats.prob_drop + hw_stats.forced_drop; - st.pdrop += hw_stats.pdrop; - st.other += hw_stats.other; - st.marked += hw_stats.prob_mark + hw_stats.forced_mark; - } + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, + &hw_stats_request); } + st.early = q->stats.prob_drop + q->stats.forced_drop; + st.pdrop = q->stats.pdrop; + st.other = q->stats.other; + st.marked = q->stats.prob_mark + q->stats.forced_mark; return gnet_stats_copy_app(d, &st, sizeof(st)); } @@ -380,7 +377,7 @@ static int red_dump_class(struct Qdisc *sch, unsigned long cl, } static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct red_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 0678debdd856..7cbdad8419b7 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -488,7 +488,8 @@ static const struct tc_sfb_qopt sfb_default_ops = { .penalty_burst = 20, }; -static int sfb_change(struct Qdisc *sch, struct nlattr *opt) +static int sfb_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); struct Qdisc *child; @@ -512,7 +513,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt) if (limit == 0) limit = qdisc_dev(sch)->tx_queue_len; - child = fifo_create_dflt(sch, &pfifo_qdisc_ops, limit); + child = fifo_create_dflt(sch, &pfifo_qdisc_ops, limit, extack); if (IS_ERR(child)) return PTR_ERR(child); @@ -549,17 +550,18 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt) return 0; } -static int sfb_init(struct Qdisc *sch, struct nlattr *opt) +static int sfb_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); int err; - err = tcf_block_get(&q->block, &q->filter_list, sch); + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; q->qdisc = &noop_qdisc; - return sfb_change(sch, opt); + return sfb_change(sch, opt, extack); } static int sfb_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -615,7 +617,7 @@ static int sfb_dump_class(struct Qdisc *sch, unsigned long cl, } static int sfb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); @@ -643,7 +645,8 @@ static void sfb_unbind(struct Qdisc *sch, unsigned long arg) } static int sfb_change_class(struct Qdisc *sch, u32 classid, u32 parentid, - struct nlattr **tca, unsigned long *arg) + struct nlattr **tca, unsigned long *arg, + struct netlink_ext_ack *extack) { return -ENOSYS; } @@ -665,7 +668,8 @@ static void sfb_walk(struct Qdisc *sch, struct qdisc_walker *walker) } } -static struct tcf_block *sfb_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *sfb_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 930e5bd26d3d..2f2678197760 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -721,7 +721,8 @@ static void sfq_destroy(struct Qdisc *sch) kfree(q->red_parms); } -static int sfq_init(struct Qdisc *sch, struct nlattr *opt) +static int sfq_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct sfq_sched_data *q = qdisc_priv(sch); int i; @@ -730,7 +731,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) q->sch = sch; timer_setup(&q->perturb_timer, sfq_perturbation, TIMER_DEFERRABLE); - err = tcf_block_get(&q->block, &q->filter_list, sch); + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; @@ -836,7 +837,8 @@ static void sfq_unbind(struct Qdisc *q, unsigned long cl) { } -static struct tcf_block *sfq_tcf_block(struct Qdisc *sch, unsigned long cl) +static struct tcf_block *sfq_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { struct sfq_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 120f4f365967..83e76d046993 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -302,7 +302,8 @@ static const struct nla_policy tbf_policy[TCA_TBF_MAX + 1] = { [TCA_TBF_PBURST] = { .type = NLA_U32 }, }; -static int tbf_change(struct Qdisc *sch, struct nlattr *opt) +static int tbf_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { int err; struct tbf_sched_data *q = qdisc_priv(sch); @@ -326,11 +327,13 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) qopt = nla_data(tb[TCA_TBF_PARMS]); if (qopt->rate.linklayer == TC_LINKLAYER_UNAWARE) qdisc_put_rtab(qdisc_get_rtab(&qopt->rate, - tb[TCA_TBF_RTAB])); + tb[TCA_TBF_RTAB], + NULL)); if (qopt->peakrate.linklayer == TC_LINKLAYER_UNAWARE) qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate, - tb[TCA_TBF_PTAB])); + tb[TCA_TBF_PTAB], + NULL)); buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U); mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U); @@ -383,7 +386,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) if (err) goto done; } else if (qopt->limit > 0) { - child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit); + child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit, + extack); if (IS_ERR(child)) { err = PTR_ERR(child); goto done; @@ -421,19 +425,20 @@ done: return err; } -static int tbf_init(struct Qdisc *sch, struct nlattr *opt) +static int tbf_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct tbf_sched_data *q = qdisc_priv(sch); qdisc_watchdog_init(&q->watchdog, sch); q->qdisc = &noop_qdisc; - if (opt == NULL) + if (!opt) return -EINVAL; q->t_c = ktime_get_ns(); - return tbf_change(sch, opt); + return tbf_change(sch, opt, extack); } static void tbf_destroy(struct Qdisc *sch) @@ -494,7 +499,7 @@ static int tbf_dump_class(struct Qdisc *sch, unsigned long cl, } static int tbf_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old, struct netlink_ext_ack *extack) { struct tbf_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 9fe6b427afed..93f04cf5cac1 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -167,7 +167,8 @@ teql_destroy(struct Qdisc *sch) } } -static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt) +static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { struct net_device *dev = qdisc_dev(sch); struct teql_master *m = (struct teql_master *)sch->ops; |