diff options
Diffstat (limited to 'net/sched')
-rw-r--r-- | net/sched/cls_api.c | 650 | ||||
-rw-r--r-- | net/sched/cls_basic.c | 14 | ||||
-rw-r--r-- | net/sched/cls_bpf.c | 31 | ||||
-rw-r--r-- | net/sched/cls_cgroup.c | 9 | ||||
-rw-r--r-- | net/sched/cls_flow.c | 10 | ||||
-rw-r--r-- | net/sched/cls_flower.c | 23 | ||||
-rw-r--r-- | net/sched/cls_fw.c | 17 | ||||
-rw-r--r-- | net/sched/cls_matchall.c | 18 | ||||
-rw-r--r-- | net/sched/cls_route.c | 14 | ||||
-rw-r--r-- | net/sched/cls_rsvp.h | 7 | ||||
-rw-r--r-- | net/sched/cls_tcindex.c | 14 | ||||
-rw-r--r-- | net/sched/cls_u32.c | 89 | ||||
-rw-r--r-- | net/sched/sch_api.c | 76 | ||||
-rw-r--r-- | net/sched/sch_generic.c | 2 | ||||
-rw-r--r-- | net/sched/sch_ingress.c | 96 | ||||
-rw-r--r-- | net/sched/sch_prio.c | 63 | ||||
-rw-r--r-- | net/sched/sch_red.c | 26 |
17 files changed, 872 insertions, 287 deletions
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 6708b6953bfa..f5d293416f46 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); @@ -179,6 +179,12 @@ static void tcf_proto_destroy(struct tcf_proto *tp) 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 +193,7 @@ 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 +201,19 @@ 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) @@ -253,47 +267,149 @@ 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, - struct netlink_ext_ack *extack) +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_block *block = kzalloc(sizeof(*block), GFP_KERNEL); + 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; struct tcf_chain *chain; int err; + block = kzalloc(sizeof(*block), GFP_KERNEL); if (!block) { NL_SET_ERR_MSG(extack, "Memory allocation for block failed"); - return -ENOMEM; + 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); @@ -302,17 +418,149 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, 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); @@ -346,26 +594,35 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, { struct tcf_chain *chain, *tmp; - /* Hold a refcnt for all chains, so that they don't disappear - * while we are iterating. - */ if (!block) return; - list_for_each_entry(chain, &block->chain_list, list) - tcf_chain_hold(chain); + tcf_chain_head_change_cb_del(tcf_block_chain_zero(block), ei); + tcf_block_owner_del(block, q, ei->binder_type); - list_for_each_entry(chain, &block->chain_list, list) - tcf_chain_flush(chain); + 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); + } tcf_block_offload_unbind(block, q, ei); - /* 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); + 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. */ - chain = list_first_entry(&block->chain_list, struct tcf_chain, 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); @@ -423,9 +680,16 @@ 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; @@ -441,7 +705,7 @@ 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); @@ -471,6 +735,10 @@ 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) { @@ -524,8 +792,9 @@ 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; } @@ -598,8 +867,9 @@ 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; @@ -612,8 +882,13 @@ 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; @@ -636,8 +911,8 @@ 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; @@ -646,8 +921,8 @@ 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; } @@ -661,8 +936,9 @@ 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; @@ -672,13 +948,14 @@ 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; @@ -687,20 +964,24 @@ 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 */ @@ -716,13 +997,11 @@ 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; @@ -749,8 +1028,10 @@ 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, @@ -763,63 +1044,91 @@ 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, extack); - 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; @@ -829,6 +1138,7 @@ 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; } @@ -837,12 +1147,14 @@ 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; } @@ -851,13 +1163,14 @@ 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; } @@ -867,7 +1180,7 @@ 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); err = 0; @@ -876,6 +1189,7 @@ replay: 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; } @@ -887,13 +1201,15 @@ replay: if (n->nlmsg_flags & NLM_F_EXCL) { if (tp_created) tcf_proto_destroy(tp); + 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) { @@ -902,21 +1218,25 @@ replay: } 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) @@ -936,6 +1256,7 @@ 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; }; @@ -945,7 +1266,7 @@ 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); @@ -956,6 +1277,7 @@ 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; @@ -974,7 +1296,7 @@ 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) @@ -987,6 +1309,7 @@ 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; @@ -1005,13 +1328,10 @@ 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; @@ -1024,32 +1344,51 @@ 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, NULL); - if (!block) - goto out; index_start = cb->args[0]; index = 0; @@ -1084,7 +1423,8 @@ 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 { @@ -1117,8 +1457,10 @@ 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; @@ -1252,18 +1594,50 @@ 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..6088be65d167 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -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 8d78e7f4ecc3..988ad45d78b8 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -167,13 +167,16 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, 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); return err; } else if (err > 0) { - prog->gen_flags |= TCA_CLS_FLAGS_IN_HW; + tcf_block_offload_inc(block, &prog->gen_flags); } } @@ -183,10 +186,17 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, return 0; } +static u32 cls_bpf_flags(u32 flags) +{ + return flags & CLS_BPF_SUPPORTED_GEN_FLAGS; +} + static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, struct cls_bpf_prog *oldprog) { - if (prog && oldprog && prog->gen_flags != oldprog->gen_flags) + if (prog && oldprog && + cls_bpf_flags(prog->gen_flags) != + cls_bpf_flags(oldprog->gen_flags)) return -EINVAL; if (prog && tc_skip_hw(prog->gen_flags)) @@ -292,7 +302,8 @@ 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); @@ -392,15 +403,16 @@ 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; @@ -411,7 +423,7 @@ 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; @@ -449,7 +461,7 @@ 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; @@ -497,7 +509,8 @@ 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; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 309d5899265f..1b54fbfca414 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; @@ -154,7 +156,8 @@ 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..64c24b488058 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; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 6132a7317efa..c6ac4a612c4a 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -229,6 +229,7 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *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, @@ -256,7 +257,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, fl_hw_destroy_filter(tp, f); 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)) @@ -525,13 +526,14 @@ 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; @@ -826,11 +828,12 @@ 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; @@ -839,7 +842,7 @@ 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; @@ -852,7 +855,7 @@ 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; @@ -915,7 +918,8 @@ 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; @@ -982,7 +986,8 @@ 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; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 20f0de1a960a..94d159a8869a 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -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..f67d3d7fcf40 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -81,6 +81,7 @@ static void mall_destroy_hw_filter(struct tcf_proto *tp, 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, @@ -103,7 +104,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, mall_destroy_hw_filter(tp, head, cookie); 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)) @@ -141,11 +142,12 @@ 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 +161,7 @@ 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 +199,13 @@ 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); if (err) goto err_replace_hw_filter; } @@ -222,7 +225,8 @@ 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..55467c30d524 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -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..5cc0df690cff 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -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..01a163e0b6aa 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) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 507859cdd1cb..57113e936155 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -529,16 +529,17 @@ 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 tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; tc_cls_common_offload_init(&cls_u32.common, tp); 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, @@ -567,10 +568,10 @@ 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); 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)) @@ -589,7 +590,7 @@ 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); idr_remove_ext(&ht->handle_idr, n->handle); if (tcf_exts_get_net(&n->exts)) call_rcu(&n->rcu, u32_delete_key_freepf_rcu); @@ -671,7 +672,8 @@ 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 +684,21 @@ 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); 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); } else { + NL_SET_ERR_MSG_MOD(extack, "Can not delete in-use filter"); return -EBUSY; } @@ -764,11 +769,12 @@ 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 +782,18 @@ 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 +811,7 @@ 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 +902,8 @@ 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 +917,40 @@ 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) @@ -935,7 +958,7 @@ 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); @@ -961,10 +984,14 @@ 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; @@ -1010,20 +1037,26 @@ 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 +1067,7 @@ 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; } @@ -1082,7 +1116,8 @@ 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; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 8a04c36e579f..d512f49ee83c 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -791,6 +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(); @@ -807,6 +808,18 @@ 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 (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; if (nla_put_u8(skb, TCA_HW_OFFLOAD, !!(q->flags & TCQ_F_OFFLOADED))) @@ -994,6 +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; @@ -1088,23 +1135,16 @@ static struct Qdisc *qdisc_create(struct net_device *dev, netdev_info(dev, "Caught tx_queue_len zero misconfig\n"); } + 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 (qdisc_is_percpu_stats(sch)) { - sch->cpu_bstats = - netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); - if (!sch->cpu_bstats) - goto err_out4; - - sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue); - if (!sch->cpu_qstats) - goto err_out4; - } - if (tca[TCA_STAB]) { stab = qdisc_get_stab(tca[TCA_STAB], extack); if (IS_ERR(stab)) { @@ -1151,7 +1191,7 @@ err_out5: ops->destroy(sch); err_out3: dev_put(dev); - kfree((char *) sch - sch->padded); + qdisc_free(sch); err_out2: module_put(ops->owner); err_out: @@ -1159,8 +1199,6 @@ err_out: return NULL; err_out4: - free_percpu(sch->cpu_bstats); - free_percpu(sch->cpu_qstats); /* * Any broken qdiscs that would require a ops->reset() here? * The qdisc was never in action so it shouldn't be necessary. @@ -1182,6 +1220,10 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca, NL_SET_ERR_MSG(extack, "Change operation not supported by specified qdisc"); return -EINVAL; } + 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; @@ -1907,6 +1949,11 @@ 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) @@ -2046,7 +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_generic.c b/net/sched/sch_generic.c index a883c501d5ec..ef8b4ecde2ac 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -907,7 +907,7 @@ void qdisc_reset(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_reset); -static void qdisc_free(struct Qdisc *qdisc) +void qdisc_free(struct Qdisc *qdisc) { if (qdisc_is_percpu_stats(qdisc)) { free_percpu(qdisc->cpu_bstats); diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 7ca2be20dd6f..ce3f55259d0d 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -61,6 +61,20 @@ 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 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, @@ -68,7 +82,6 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, { struct ingress_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); - int err; net_inc_ingress_queue(); @@ -78,13 +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; - err = tcf_block_get_ext(&q->block, sch, &q->block_info, extack); - if (err) - return err; - - sch->flags |= TCQ_F_CPUSTATS; - - return 0; + return tcf_block_get_ext(&q->block, sch, &q->block_info, extack); } static void ingress_destroy(struct Qdisc *sch) @@ -120,13 +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), - .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 { @@ -170,6 +180,34 @@ static struct tcf_block *clsact_tcf_block(struct Qdisc *sch, unsigned long cl, } } +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) { @@ -197,14 +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; - err = tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info, - extack); - if (err) - return err; - - sch->flags |= TCQ_F_CPUSTATS; - - return 0; + return tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info, extack); } static void clsact_destroy(struct Qdisc *sch) @@ -228,13 +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), - .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_prio.c b/net/sched/sch_prio.c index fe1510eb111f..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) { @@ -149,6 +174,7 @@ 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]); } @@ -204,6 +230,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt, } sch_tree_unlock(sch); + prio_offload(sch, true); return 0; } @@ -223,15 +250,51 @@ static int prio_init(struct Qdisc *sch, struct nlattr *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) { 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; diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index a392eaa4a0b4..16644b3d2362 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -167,6 +167,7 @@ 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; } @@ -322,7 +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; @@ -344,32 +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)); } |