From a9b19443edbaac97c5c094f3cc903c1f1548b3f5 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 Jan 2018 11:46:45 +0100 Subject: net: sched: introduce support for multiple filter chain pointers registration So far, there was possible only to register a single filter chain pointer to block->chain[0]. However, when the blocks will get shareable, we need to allow multiple filter chain pointers registration. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/sch_generic.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index bd9125b0481f..17d8cfd0efda 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -275,8 +275,7 @@ typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv); struct tcf_chain { struct tcf_proto __rcu *filter_chain; - tcf_chain_head_change_t *chain_head_change; - void *chain_head_change_priv; + struct list_head filter_chain_list; struct list_head list; struct tcf_block *block; u32 index; /* chain index */ -- cgit v1.2.3 From 4861738775d70e0165d04fe014f32b41bcb5414a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 Jan 2018 11:46:46 +0100 Subject: net: sched: introduce shared filter blocks infrastructure Allow qdiscs to share filter blocks among them. Each qdisc type has to use block get/put extended modifications that enable sharing. Shared blocks are tracked within each net namespace and identified by u32 index. This index is passed from user during the qdisc creation. If user passes index that is not used by any other qdisc, new block is created. If user passes index that is already used, the existing block will be re-used. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 7 ++ include/net/sch_generic.h | 2 + net/sched/cls_api.c | 167 +++++++++++++++++++++++++++++++++++++++------- 3 files changed, 152 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index cc23c041a6d7..c40d60e6a883 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -29,6 +29,7 @@ struct tcf_block_ext_info { enum tcf_block_binder_type binder_type; tcf_chain_head_change_t *chain_head_change; void *chain_head_change_priv; + u32 block_index; }; struct tcf_block_cb; @@ -48,8 +49,14 @@ void tcf_block_put(struct tcf_block *block); void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, struct tcf_block_ext_info *ei); +static inline bool tcf_block_shared(struct tcf_block *block) +{ + return block->index; +} + static inline struct Qdisc *tcf_block_q(struct tcf_block *block) { + WARN_ON(tcf_block_shared(block)); return block->q; } diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 17d8cfd0efda..cc0c1e4711dc 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -284,6 +284,8 @@ struct tcf_chain { struct tcf_block { struct list_head chain_list; + u32 index; /* block index for shared blocks */ + unsigned int refcnt; struct net *net; struct Qdisc *q; struct list_head cb_list; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index e6b16b300844..ee319b1598b5 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -333,22 +334,44 @@ tcf_chain_head_change_cb_del(struct tcf_chain *chain, WARN_ON(1); } -static struct tcf_chain *tcf_block_chain_zero(struct tcf_block *block) +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) { - return list_first_entry(&block->chain_list, struct tcf_chain, list); + 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; } -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 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; + 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); @@ -360,20 +383,76 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, err = -ENOMEM; goto err_chain_create; } + block->net = qdisc_net(q); + block->refcnt = 1; + block->net = net; + block->q = q; + 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); +} + +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_chain_head_change_cb_add(tcf_block_chain_zero(block), ei, extack); if (err) goto err_chain_head_change_cb_add; - block->net = qdisc_net(q); - block->q = q; tcf_block_offload_bind(block, q, ei); *p_block = block; return 0; -err_chain_create: - kfree(block); err_chain_head_change_cb_add: - kfree(chain); + 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); @@ -407,26 +486,34 @@ 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; tcf_chain_head_change_cb_del(tcf_block_chain_zero(block), ei); - 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); + 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. */ - tcf_chain_put(tcf_block_chain_zero(block)); + /* Finally, put chain 0 and allow block to be freed. */ + tcf_chain_put(tcf_block_chain_zero(block)); + } } EXPORT_SYMBOL(tcf_block_put_ext); @@ -1313,18 +1400,50 @@ 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); -- cgit v1.2.3 From f36fe1c498c8959812415c57b683abaa4527dec5 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 Jan 2018 11:46:48 +0100 Subject: net: sched: introduce block mechanism to handle netif_keep_dst calls Couple of classifiers call netif_keep_dst directly on q->dev. That is not possible to do directly for shared blocke where multiple qdiscs are owning the block. So introduce a infrastructure to keep track of the block owners in list and use this list to implement block variant of netif_keep_dst. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 1 + include/net/sch_generic.h | 2 ++ net/sched/cls_api.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++ net/sched/cls_bpf.c | 4 +-- net/sched/cls_flow.c | 2 +- net/sched/cls_route.c | 2 +- 6 files changed, 76 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index c40d60e6a883..789d818c4a61 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -39,6 +39,7 @@ bool tcf_queue_work(struct work_struct *work); struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, bool create); void tcf_chain_put(struct tcf_chain *chain); +void tcf_block_netif_keep_dst(struct tcf_block *block); int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, struct netlink_ext_ack *extack); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index cc0c1e4711dc..f655e66ce742 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -289,6 +289,8 @@ struct tcf_block { struct net *net; struct Qdisc *q; struct list_head cb_list; + struct list_head owner_list; + bool keep_dst; }; static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 700595abc641..1ca84230f4de 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -375,6 +375,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, } 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); @@ -406,6 +407,65 @@ 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) @@ -435,6 +495,12 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, } } + 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) @@ -444,6 +510,8 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, return 0; 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); @@ -489,6 +557,7 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, if (!block) return; 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)) diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 8d78e7f4ecc3..d79cc5086509 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -392,8 +392,8 @@ 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; } diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 25c2a888e1f0..28cd6fb52c16 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -526,7 +526,7 @@ 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; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index ac9a5b8825b9..a1f2b1b7c014 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -527,7 +527,7 @@ 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); -- cgit v1.2.3 From edf6711c9840fd92e0047f98c411c94114168f19 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 Jan 2018 11:46:49 +0100 Subject: net: sched: remove classid and q fields from tcf_proto Both are no longer used, so remove them. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/sch_generic.h | 2 -- net/sched/cls_api.c | 7 ++----- 2 files changed, 2 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index f655e66ce742..54b9a1ca26bd 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -255,8 +255,6 @@ struct tcf_proto { /* All the rest */ u32 prio; - u32 classid; - struct Qdisc *q; void *data; const struct tcf_proto_ops *ops; struct tcf_chain *chain; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 1ca84230f4de..e36d90c20f04 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -122,8 +122,7 @@ 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 tcf_proto *tp; int err; @@ -157,8 +156,6 @@ 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); @@ -1069,7 +1066,7 @@ 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); if (IS_ERR(tp)) { err = PTR_ERR(tp); goto errout; -- cgit v1.2.3 From caa7260156eb3a1496348a2c69fa68e85183d5d7 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 Jan 2018 11:46:50 +0100 Subject: net: sched: keep track of offloaded filters and check tc offload feature During block bind, we need to check tc offload feature. If it is disabled yet still the block contains offloaded filters, forbid the bind. Also forbid to register callback for a block that already contains offloaded filters, as the play back is not supported now. For keeping track of offloaded filters there is a new counter introduced, alongside with couple of helpers called from cls_* code. These helpers set and clear TCA_CLS_FLAGS_IN_HW flag. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/sch_generic.h | 18 +++++++++++ net/sched/cls_api.c | 80 ++++++++++++++++++++++++++++++++++++++--------- net/sched/cls_bpf.c | 5 ++- net/sched/cls_flower.c | 3 +- net/sched/cls_matchall.c | 3 +- net/sched/cls_u32.c | 13 ++++---- 6 files changed, 99 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 54b9a1ca26bd..bf5cc0a1d0f6 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -289,8 +289,26 @@ struct tcf_block { struct list_head cb_list; struct list_head owner_list; bool keep_dst; + unsigned int offloadcnt; /* Number of oddloaded filters */ + unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */ }; +static inline void tcf_block_offload_inc(struct tcf_block *block, u32 *flags) +{ + if (*flags & TCA_CLS_FLAGS_IN_HW) + return; + *flags |= TCA_CLS_FLAGS_IN_HW; + block->offloadcnt++; +} + +static inline void tcf_block_offload_dec(struct tcf_block *block, u32 *flags) +{ + if (!(*flags & TCA_CLS_FLAGS_IN_HW)) + return; + *flags &= ~TCA_CLS_FLAGS_IN_HW; + block->offloadcnt--; +} + static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) { struct qdisc_skb_cb *qcb; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index e36d90c20f04..03e2fa092d9e 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -265,31 +265,66 @@ 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); } static int @@ -502,10 +537,16 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, ei, extack); if (err) goto err_chain_head_change_cb_add; - tcf_block_offload_bind(block, q, ei); + + 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: @@ -637,9 +678,16 @@ 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; @@ -655,7 +703,7 @@ 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); @@ -685,6 +733,10 @@ 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) { diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index d79cc5086509..cf72aefcf98d 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); } } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 6132a7317efa..f61df19b1026 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)) diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 66d4e0099158..d0e57c86636f 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)) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 507859cdd1cb..020d328d0afd 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); @@ -682,7 +683,7 @@ 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; } -- cgit v1.2.3 From 7960d1daf278cbe23bb48974fe6ae6a1e44c3c15 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 Jan 2018 11:46:51 +0100 Subject: net: sched: use block index as a handle instead of qdisc when block is shared As the tcm_ifindex with value TCM_IFINDEX_MAGIC_BLOCK is invalid ifindex, use it to indicate that we work with block, instead of qdisc. So if tcm_ifindex is set to TCM_IFINDEX_MAGIC_BLOCK, tcm_parent is used to carry block_index. If the block is set to be shared between at least 2 qdiscs, it is forbidden to use the qdisc handle to add/delete filters. In that case, userspace has to pass block_index. Also, for dump of the filters, in case the block is shared in between at least 2 qdiscs, the each filter is dumped with tcm_ifindex value TCM_IFINDEX_MAGIC_BLOCK and tcm_parent set to block_index. That gives the user clear indication, that the filter belongs to a shared block and not only to one qdisc under which it is dumped. Suggested-by: David Ahern Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Acked-by: David Ahern Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 10 ++ net/sched/cls_api.c | 202 ++++++++++++++++++++++++----------------- 2 files changed, 128 insertions(+), 84 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 843e29aa3cac..da878f2e7c39 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -541,9 +541,19 @@ struct tcmsg { int tcm_ifindex; __u32 tcm_handle; __u32 tcm_parent; +/* tcm_block_index is used instead of tcm_parent + * in case tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK + */ +#define tcm_block_index tcm_parent __u32 tcm_info; }; +/* For manipulation of filters in shared block, tcm_ifindex is set to + * TCM_IFINDEX_MAGIC_BLOCK, and tcm_parent is aliased to tcm_block_index + * which is the block index. + */ +#define TCM_IFINDEX_MAGIC_BLOCK (0xFFFFFFFFU) + enum { TCA_UNSPEC, TCA_KIND, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 03e2fa092d9e..e500d11da9cd 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -865,8 +865,9 @@ 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; @@ -879,8 +880,13 @@ 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; @@ -903,8 +909,8 @@ 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; @@ -913,8 +919,8 @@ 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; } @@ -928,8 +934,8 @@ 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 sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; @@ -939,8 +945,8 @@ 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) { kfree_skb(skb); return -EINVAL; } @@ -959,15 +965,16 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, } 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 */ @@ -983,13 +990,11 @@ 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; @@ -1036,41 +1041,58 @@ replay: /* 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) + 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) + return -EINVAL; - /* And the last stroke */ - block = cops->tcf_block(q, cl, extack); - if (!block) { - err = -EINVAL; - goto errout; + if (!cops->tcf_block) + return -EOPNOTSUPP; + + /* Do we search for filter, attached to class? */ + if (TC_H_MIN(parent)) { + cl = cops->find(q, parent); + if (cl == 0) + 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; @@ -1086,7 +1108,7 @@ replay: } 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; @@ -1134,7 +1156,7 @@ 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; @@ -1159,8 +1181,8 @@ replay: } 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); if (err) goto errout; if (last) { @@ -1169,8 +1191,8 @@ 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); goto errout; default: err = -EINVAL; @@ -1183,7 +1205,7 @@ replay: 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) @@ -1203,6 +1225,7 @@ 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; }; @@ -1212,7 +1235,7 @@ 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); @@ -1223,6 +1246,7 @@ 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; @@ -1241,7 +1265,7 @@ 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) @@ -1254,6 +1278,7 @@ 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; @@ -1272,13 +1297,10 @@ 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; @@ -1291,32 +1313,44 @@ 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; } 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; -- cgit v1.2.3 From d47a6b0e7c492a4ba4524d557db388e34fd0a47a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 Jan 2018 11:46:52 +0100 Subject: net: sched: introduce ingress/egress block index attributes for qdisc Introduce two new attributes to be used for qdisc creation and dumping. One for ingress block, one for egress block. Introduce a set of ops that qdisc which supports block sharing would implement. Passing block indexes in qdisc change is not supported yet and it is checked and forbidded. In future, these attributes are to be reused for specifying block indexes for classes as well. As of this moment however, it is not supported so a check is in place to forbid it. Suggested-by: Roopa Prabhu Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/sch_generic.h | 7 +++++ include/uapi/linux/rtnetlink.h | 2 ++ net/sched/sch_api.c | 60 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 69 insertions(+) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index bf5cc0a1d0f6..cfc19d0ba2ad 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -204,6 +204,13 @@ struct Qdisc_ops { int (*dump)(struct Qdisc *, struct sk_buff *); int (*dump_stats)(struct Qdisc *, struct gnet_dump *); + void (*ingress_block_set)(struct Qdisc *sch, + u32 block_index); + void (*egress_block_set)(struct Qdisc *sch, + u32 block_index); + u32 (*ingress_block_get)(struct Qdisc *sch); + u32 (*egress_block_get)(struct Qdisc *sch); + struct module *owner; }; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index da878f2e7c39..9b15005955fa 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -568,6 +568,8 @@ enum { TCA_DUMP_INVISIBLE, TCA_CHAIN, TCA_HW_OFFLOAD, + TCA_INGRESS_BLOCK, + TCA_EGRESS_BLOCK, __TCA_MAX }; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 7dffa9dce28b..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; @@ -1088,6 +1135,10 @@ 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) @@ -1169,6 +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; @@ -1894,6 +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) -- cgit v1.2.3