diff options
Diffstat (limited to 'net/sched')
-rw-r--r-- | net/sched/cls_api.c | 1 | ||||
-rw-r--r-- | net/sched/cls_flower.c | 587 | ||||
-rw-r--r-- | net/sched/sch_api.c | 15 | ||||
-rw-r--r-- | net/sched/sch_cbs.c | 98 | ||||
-rw-r--r-- | net/sched/sch_generic.c | 70 | ||||
-rw-r--r-- | net/sched/sch_taprio.c | 160 |
6 files changed, 670 insertions, 261 deletions
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 99ae30c177c7..9115f053883f 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3229,7 +3229,6 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->tunnel = tcf_tunnel_info(act); } else if (is_tcf_tunnel_release(act)) { entry->id = FLOW_ACTION_TUNNEL_DECAP; - entry->tunnel = tcf_tunnel_info(act); } else if (is_tcf_pedit(act)) { for (k = 0; k < tcf_pedit_nkeys(act); k++) { switch (tcf_pedit_cmd(act, k)) { diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index c04247b403ed..0d8968803e98 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/rhashtable.h> #include <linux/workqueue.h> +#include <linux/refcount.h> #include <linux/if_ether.h> #include <linux/in6.h> @@ -75,6 +76,7 @@ struct fl_flow_mask { struct list_head filters; struct rcu_work rwork; struct list_head list; + refcount_t refcnt; }; struct fl_flow_tmplt { @@ -86,7 +88,9 @@ struct fl_flow_tmplt { struct cls_fl_head { struct rhashtable ht; + spinlock_t masks_lock; /* Protect masks list */ struct list_head masks; + struct list_head hw_filters; struct rcu_work rwork; struct idr handle_idr; }; @@ -99,11 +103,18 @@ struct cls_fl_filter { struct tcf_result res; struct fl_flow_key key; struct list_head list; + struct list_head hw_list; u32 handle; u32 flags; u32 in_hw_count; struct rcu_work rwork; struct net_device *hw_dev; + /* Flower classifier is unlocked, which means that its reference counter + * can be changed concurrently without any kind of external + * synchronization. Use atomic reference counter to be concurrency-safe. + */ + refcount_t refcnt; + bool deleted; }; static const struct rhashtable_params mask_ht_params = { @@ -304,7 +315,9 @@ static int fl_init(struct tcf_proto *tp) if (!head) return -ENOBUFS; + spin_lock_init(&head->masks_lock); INIT_LIST_HEAD_RCU(&head->masks); + INIT_LIST_HEAD(&head->hw_filters); rcu_assign_pointer(tp->root, head); idr_init(&head->handle_idr); @@ -313,6 +326,7 @@ static int fl_init(struct tcf_proto *tp) static void fl_mask_free(struct fl_flow_mask *mask) { + WARN_ON(!list_empty(&mask->filters)); rhashtable_destroy(&mask->ht); kfree(mask); } @@ -325,22 +339,32 @@ static void fl_mask_free_work(struct work_struct *work) fl_mask_free(mask); } -static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask, - bool async) +static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask) { - if (!list_empty(&mask->filters)) + if (!refcount_dec_and_test(&mask->refcnt)) return false; rhashtable_remove_fast(&head->ht, &mask->ht_node, mask_ht_params); + + spin_lock(&head->masks_lock); list_del_rcu(&mask->list); - if (async) - tcf_queue_work(&mask->rwork, fl_mask_free_work); - else - fl_mask_free(mask); + spin_unlock(&head->masks_lock); + + tcf_queue_work(&mask->rwork, fl_mask_free_work); return true; } +static struct cls_fl_head *fl_head_dereference(struct tcf_proto *tp) +{ + /* Flower classifier only changes root pointer during init and destroy. + * Users must obtain reference to tcf_proto instance before calling its + * API, so tp->root pointer is protected from concurrent call to + * fl_destroy() by reference counting. + */ + return rcu_dereference_raw(tp->root); +} + static void __fl_destroy_filter(struct cls_fl_filter *f) { tcf_exts_destroy(&f->exts); @@ -353,37 +377,50 @@ static void fl_destroy_filter_work(struct work_struct *work) struct cls_fl_filter *f = container_of(to_rcu_work(work), struct cls_fl_filter, rwork); - rtnl_lock(); __fl_destroy_filter(f); - rtnl_unlock(); } static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct tc_cls_flower_offload cls_flower = {}; struct tcf_block *block = tp->chain->block; + if (!rtnl_held) + rtnl_lock(); + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); cls_flower.command = TC_CLSFLOWER_DESTROY; cls_flower.cookie = (unsigned long) f; tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); + spin_lock(&tp->lock); + list_del_init(&f->hw_list); tcf_block_offload_dec(block, &f->flags); + spin_unlock(&tp->lock); + + if (!rtnl_held) + rtnl_unlock(); } static int fl_hw_replace_filter(struct tcf_proto *tp, - struct cls_fl_filter *f, + struct cls_fl_filter *f, bool rtnl_held, struct netlink_ext_ack *extack) { + struct cls_fl_head *head = fl_head_dereference(tp); struct tc_cls_flower_offload cls_flower = {}; struct tcf_block *block = tp->chain->block; bool skip_sw = tc_skip_sw(f->flags); - int err; + int err = 0; + + if (!rtnl_held) + rtnl_lock(); cls_flower.rule = flow_rule_alloc(tcf_exts_num_actions(&f->exts)); - if (!cls_flower.rule) - return -ENOMEM; + if (!cls_flower.rule) { + err = -ENOMEM; + goto errout; + } tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); cls_flower.command = TC_CLSFLOWER_REPLACE; @@ -396,35 +433,51 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts); if (err) { kfree(cls_flower.rule); - if (skip_sw) { + if (skip_sw) NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action"); - return err; - } - return 0; + else + err = 0; + goto errout; } err = tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, skip_sw); kfree(cls_flower.rule); if (err < 0) { - fl_hw_destroy_filter(tp, f, NULL); - return err; + fl_hw_destroy_filter(tp, f, true, NULL); + goto errout; } else if (err > 0) { f->in_hw_count = err; + err = 0; + spin_lock(&tp->lock); tcf_block_offload_inc(block, &f->flags); + spin_unlock(&tp->lock); } - if (skip_sw && !(f->flags & TCA_CLS_FLAGS_IN_HW)) - return -EINVAL; + if (skip_sw && !(f->flags & TCA_CLS_FLAGS_IN_HW)) { + err = -EINVAL; + goto errout; + } - return 0; + spin_lock(&tp->lock); + list_add(&f->hw_list, &head->hw_filters); + spin_unlock(&tp->lock); +errout: + if (!rtnl_held) + rtnl_unlock(); + + return err; } -static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) +static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f, + bool rtnl_held) { struct tc_cls_flower_offload cls_flower = {}; struct tcf_block *block = tp->chain->block; + if (!rtnl_held) + rtnl_lock(); + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, NULL); cls_flower.command = TC_CLSFLOWER_STATS; cls_flower.cookie = (unsigned long) f; @@ -435,27 +488,81 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) tcf_exts_stats_update(&f->exts, cls_flower.stats.bytes, cls_flower.stats.pkts, cls_flower.stats.lastused); + + if (!rtnl_held) + rtnl_unlock(); } -static bool __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, - struct netlink_ext_ack *extack) +static void __fl_put(struct cls_fl_filter *f) { - struct cls_fl_head *head = rtnl_dereference(tp->root); - bool async = tcf_exts_get_net(&f->exts); - bool last; + if (!refcount_dec_and_test(&f->refcnt)) + return; + + if (tcf_exts_get_net(&f->exts)) + tcf_queue_work(&f->rwork, fl_destroy_filter_work); + else + __fl_destroy_filter(f); +} + +static struct cls_fl_filter *__fl_get(struct cls_fl_head *head, u32 handle) +{ + struct cls_fl_filter *f; + rcu_read_lock(); + f = idr_find(&head->handle_idr, handle); + if (f && !refcount_inc_not_zero(&f->refcnt)) + f = NULL; + rcu_read_unlock(); + + return f; +} + +static struct cls_fl_filter *fl_get_next_filter(struct tcf_proto *tp, + unsigned long *handle) +{ + struct cls_fl_head *head = fl_head_dereference(tp); + struct cls_fl_filter *f; + + rcu_read_lock(); + while ((f = idr_get_next_ul(&head->handle_idr, handle))) { + /* don't return filters that are being deleted */ + if (refcount_inc_not_zero(&f->refcnt)) + break; + ++(*handle); + } + rcu_read_unlock(); + + return f; +} + +static int __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, + bool *last, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + struct cls_fl_head *head = fl_head_dereference(tp); + + *last = false; + + spin_lock(&tp->lock); + if (f->deleted) { + spin_unlock(&tp->lock); + return -ENOENT; + } + + f->deleted = true; + rhashtable_remove_fast(&f->mask->ht, &f->ht_node, + f->mask->filter_ht_params); idr_remove(&head->handle_idr, f->handle); list_del_rcu(&f->list); - last = fl_mask_put(head, f->mask, async); + spin_unlock(&tp->lock); + + *last = fl_mask_put(head, f->mask); if (!tc_skip_hw(f->flags)) - fl_hw_destroy_filter(tp, f, extack); + fl_hw_destroy_filter(tp, f, rtnl_held, extack); tcf_unbind_filter(tp, &f->res); - if (async) - tcf_queue_work(&f->rwork, fl_destroy_filter_work); - else - __fl_destroy_filter(f); + __fl_put(f); - return last; + return 0; } static void fl_destroy_sleepable(struct work_struct *work) @@ -472,13 +579,15 @@ static void fl_destroy_sleepable(struct work_struct *work) static void fl_destroy(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { - struct cls_fl_head *head = rtnl_dereference(tp->root); + struct cls_fl_head *head = fl_head_dereference(tp); struct fl_flow_mask *mask, *next_mask; struct cls_fl_filter *f, *next; + bool last; list_for_each_entry_safe(mask, next_mask, &head->masks, list) { list_for_each_entry_safe(f, next, &mask->filters, list) { - if (__fl_delete(tp, f, extack)) + __fl_delete(tp, f, &last, rtnl_held, extack); + if (last) break; } } @@ -488,11 +597,18 @@ static void fl_destroy(struct tcf_proto *tp, bool rtnl_held, tcf_queue_work(&head->rwork, fl_destroy_sleepable); } +static void fl_put(struct tcf_proto *tp, void *arg) +{ + struct cls_fl_filter *f = arg; + + __fl_put(f); +} + static void *fl_get(struct tcf_proto *tp, u32 handle) { - struct cls_fl_head *head = rtnl_dereference(tp->root); + struct cls_fl_head *head = fl_head_dereference(tp); - return idr_find(&head->handle_idr, handle); + return __fl_get(head, handle); } static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { @@ -1227,12 +1343,18 @@ static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head, INIT_LIST_HEAD_RCU(&newmask->filters); - err = rhashtable_insert_fast(&head->ht, &newmask->ht_node, - mask_ht_params); + refcount_set(&newmask->refcnt, 1); + err = rhashtable_replace_fast(&head->ht, &mask->ht_node, + &newmask->ht_node, mask_ht_params); if (err) goto errout_destroy; + /* Wait until any potential concurrent users of mask are finished */ + synchronize_rcu(); + + spin_lock(&head->masks_lock); list_add_tail_rcu(&newmask->list, &head->masks); + spin_unlock(&head->masks_lock); return newmask; @@ -1250,41 +1372,77 @@ static int fl_check_assign_mask(struct cls_fl_head *head, struct fl_flow_mask *mask) { struct fl_flow_mask *newmask; + int ret = 0; + + rcu_read_lock(); - fnew->mask = rhashtable_lookup_fast(&head->ht, mask, mask_ht_params); + /* Insert mask as temporary node to prevent concurrent creation of mask + * with same key. Any concurrent lookups with same key will return + * -EAGAIN because mask's refcnt is zero. It is safe to insert + * stack-allocated 'mask' to masks hash table because we call + * synchronize_rcu() before returning from this function (either in case + * of error or after replacing it with heap-allocated mask in + * fl_create_new_mask()). + */ + fnew->mask = rhashtable_lookup_get_insert_fast(&head->ht, + &mask->ht_node, + mask_ht_params); if (!fnew->mask) { - if (fold) - return -EINVAL; + rcu_read_unlock(); + + if (fold) { + ret = -EINVAL; + goto errout_cleanup; + } newmask = fl_create_new_mask(head, mask); - if (IS_ERR(newmask)) - return PTR_ERR(newmask); + if (IS_ERR(newmask)) { + ret = PTR_ERR(newmask); + goto errout_cleanup; + } fnew->mask = newmask; + return 0; + } else if (IS_ERR(fnew->mask)) { + ret = PTR_ERR(fnew->mask); } else if (fold && fold->mask != fnew->mask) { - return -EINVAL; + ret = -EINVAL; + } else if (!refcount_inc_not_zero(&fnew->mask->refcnt)) { + /* Mask was deleted concurrently, try again */ + ret = -EAGAIN; } + rcu_read_unlock(); + return ret; - return 0; +errout_cleanup: + rhashtable_remove_fast(&head->ht, &mask->ht_node, + mask_ht_params); + /* Wait until any potential concurrent users of mask are finished */ + synchronize_rcu(); + return ret; } 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 fl_flow_tmplt *tmplt, + struct fl_flow_tmplt *tmplt, bool rtnl_held, struct netlink_ext_ack *extack) { int err; - err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, true, + err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, rtnl_held, extack); if (err < 0) return err; if (tb[TCA_FLOWER_CLASSID]) { f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); + if (!rtnl_held) + rtnl_lock(); tcf_bind_filter(tp, &f->res, base); + if (!rtnl_held) + rtnl_unlock(); } err = fl_set_key(net, tb, &f->key, &mask->key, extack); @@ -1302,25 +1460,52 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp, return 0; } +static int fl_ht_insert_unique(struct cls_fl_filter *fnew, + struct cls_fl_filter *fold, + bool *in_ht) +{ + struct fl_flow_mask *mask = fnew->mask; + int err; + + err = rhashtable_lookup_insert_fast(&mask->ht, + &fnew->ht_node, + mask->filter_ht_params); + if (err) { + *in_ht = false; + /* It is okay if filter with same key exists when + * overwriting. + */ + return fold && err == -EEXIST ? 0 : err; + } + + *in_ht = true; + return 0; +} + 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, bool rtnl_held, struct netlink_ext_ack *extack) { - struct cls_fl_head *head = rtnl_dereference(tp->root); + struct cls_fl_head *head = fl_head_dereference(tp); struct cls_fl_filter *fold = *arg; struct cls_fl_filter *fnew; struct fl_flow_mask *mask; struct nlattr **tb; + bool in_ht; int err; - if (!tca[TCA_OPTIONS]) - return -EINVAL; + if (!tca[TCA_OPTIONS]) { + err = -EINVAL; + goto errout_fold; + } mask = kzalloc(sizeof(struct fl_flow_mask), GFP_KERNEL); - if (!mask) - return -ENOBUFS; + if (!mask) { + err = -ENOBUFS; + goto errout_fold; + } tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL); if (!tb) { @@ -1343,6 +1528,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, err = -ENOBUFS; goto errout_tb; } + INIT_LIST_HEAD(&fnew->hw_list); + refcount_set(&fnew->refcnt, 1); err = tcf_exts_init(&fnew->exts, net, TCA_FLOWER_ACT, 0); if (err < 0) @@ -1358,7 +1545,7 @@ 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, - tp->chain->tmplt_priv, extack); + tp->chain->tmplt_priv, rtnl_held, extack); if (err) goto errout; @@ -1366,169 +1553,247 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (err) goto errout; - if (!handle) { - handle = 1; - err = idr_alloc_u32(&head->handle_idr, fnew, &handle, - INT_MAX, GFP_KERNEL); - } else if (!fold) { - /* user specifies a handle and it doesn't exist */ - err = idr_alloc_u32(&head->handle_idr, fnew, &handle, - handle, GFP_KERNEL); - } + err = fl_ht_insert_unique(fnew, fold, &in_ht); if (err) goto errout_mask; - fnew->handle = handle; - - if (!fold && __fl_lookup(fnew->mask, &fnew->mkey)) { - err = -EEXIST; - goto errout_idr; - } - - err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node, - fnew->mask->filter_ht_params); - if (err) - goto errout_idr; if (!tc_skip_hw(fnew->flags)) { - err = fl_hw_replace_filter(tp, fnew, extack); + err = fl_hw_replace_filter(tp, fnew, rtnl_held, extack); if (err) - goto errout_mask_ht; + goto errout_ht; } if (!tc_in_hw(fnew->flags)) fnew->flags |= TCA_CLS_FLAGS_NOT_IN_HW; + spin_lock(&tp->lock); + + /* tp was deleted concurrently. -EAGAIN will cause caller to lookup + * proto again or create new one, if necessary. + */ + if (tp->deleting) { + err = -EAGAIN; + goto errout_hw; + } + if (fold) { + /* Fold filter was deleted concurrently. Retry lookup. */ + if (fold->deleted) { + err = -EAGAIN; + goto errout_hw; + } + + fnew->handle = handle; + + if (!in_ht) { + struct rhashtable_params params = + fnew->mask->filter_ht_params; + + err = rhashtable_insert_fast(&fnew->mask->ht, + &fnew->ht_node, + params); + if (err) + goto errout_hw; + in_ht = true; + } + + refcount_inc(&fnew->refcnt); rhashtable_remove_fast(&fold->mask->ht, &fold->ht_node, fold->mask->filter_ht_params); - if (!tc_skip_hw(fold->flags)) - fl_hw_destroy_filter(tp, fold, NULL); - } - - *arg = fnew; - - if (fold) { idr_replace(&head->handle_idr, fnew, fnew->handle); list_replace_rcu(&fold->list, &fnew->list); + fold->deleted = true; + + spin_unlock(&tp->lock); + + fl_mask_put(head, fold->mask); + if (!tc_skip_hw(fold->flags)) + fl_hw_destroy_filter(tp, fold, rtnl_held, NULL); tcf_unbind_filter(tp, &fold->res); - tcf_exts_get_net(&fold->exts); - tcf_queue_work(&fold->rwork, fl_destroy_filter_work); + /* Caller holds reference to fold, so refcnt is always > 0 + * after this. + */ + refcount_dec(&fold->refcnt); + __fl_put(fold); } else { + if (handle) { + /* user specifies a handle and it doesn't exist */ + err = idr_alloc_u32(&head->handle_idr, fnew, &handle, + handle, GFP_ATOMIC); + + /* Filter with specified handle was concurrently + * inserted after initial check in cls_api. This is not + * necessarily an error if NLM_F_EXCL is not set in + * message flags. Returning EAGAIN will cause cls_api to + * try to update concurrently inserted rule. + */ + if (err == -ENOSPC) + err = -EAGAIN; + } else { + handle = 1; + err = idr_alloc_u32(&head->handle_idr, fnew, &handle, + INT_MAX, GFP_ATOMIC); + } + if (err) + goto errout_hw; + + refcount_inc(&fnew->refcnt); + fnew->handle = handle; list_add_tail_rcu(&fnew->list, &fnew->mask->filters); + spin_unlock(&tp->lock); } + *arg = fnew; + kfree(tb); kfree(mask); return 0; -errout_mask_ht: - rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node, - fnew->mask->filter_ht_params); - -errout_idr: - if (!fold) - idr_remove(&head->handle_idr, fnew->handle); - +errout_ht: + spin_lock(&tp->lock); +errout_hw: + fnew->deleted = true; + spin_unlock(&tp->lock); + if (!tc_skip_hw(fnew->flags)) + fl_hw_destroy_filter(tp, fnew, rtnl_held, NULL); + if (in_ht) + rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node, + fnew->mask->filter_ht_params); errout_mask: - fl_mask_put(head, fnew->mask, false); - + fl_mask_put(head, fnew->mask); errout: - tcf_exts_destroy(&fnew->exts); - kfree(fnew); + __fl_put(fnew); errout_tb: kfree(tb); errout_mask_alloc: kfree(mask); +errout_fold: + if (fold) + __fl_put(fold); return err; } static int fl_delete(struct tcf_proto *tp, void *arg, bool *last, bool rtnl_held, struct netlink_ext_ack *extack) { - struct cls_fl_head *head = rtnl_dereference(tp->root); + struct cls_fl_head *head = fl_head_dereference(tp); struct cls_fl_filter *f = arg; + bool last_on_mask; + int err = 0; - rhashtable_remove_fast(&f->mask->ht, &f->ht_node, - f->mask->filter_ht_params); - __fl_delete(tp, f, extack); + err = __fl_delete(tp, f, &last_on_mask, rtnl_held, extack); *last = list_empty(&head->masks); - return 0; + __fl_put(f); + + return err; } static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held) { - struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f; arg->count = arg->skip; - while ((f = idr_get_next_ul(&head->handle_idr, - &arg->cookie)) != NULL) { + while ((f = fl_get_next_filter(tp, &arg->cookie)) != NULL) { if (arg->fn(tp, f, arg) < 0) { + __fl_put(f); arg->stop = 1; break; } - arg->cookie = f->handle + 1; + __fl_put(f); + arg->cookie++; arg->count++; } } +static struct cls_fl_filter * +fl_get_next_hw_filter(struct tcf_proto *tp, struct cls_fl_filter *f, bool add) +{ + struct cls_fl_head *head = fl_head_dereference(tp); + + spin_lock(&tp->lock); + if (list_empty(&head->hw_filters)) { + spin_unlock(&tp->lock); + return NULL; + } + + if (!f) + f = list_entry(&head->hw_filters, struct cls_fl_filter, + hw_list); + list_for_each_entry_continue(f, &head->hw_filters, hw_list) { + if (!(add && f->deleted) && refcount_inc_not_zero(&f->refcnt)) { + spin_unlock(&tp->lock); + return f; + } + } + + spin_unlock(&tp->lock); + return NULL; +} + static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { - struct cls_fl_head *head = rtnl_dereference(tp->root); struct tc_cls_flower_offload cls_flower = {}; struct tcf_block *block = tp->chain->block; - struct fl_flow_mask *mask; - struct cls_fl_filter *f; + struct cls_fl_filter *f = NULL; int err; - list_for_each_entry(mask, &head->masks, list) { - list_for_each_entry(f, &mask->filters, list) { - if (tc_skip_hw(f->flags)) - continue; - - cls_flower.rule = - flow_rule_alloc(tcf_exts_num_actions(&f->exts)); - if (!cls_flower.rule) - return -ENOMEM; - - tc_cls_common_offload_init(&cls_flower.common, tp, - f->flags, extack); - cls_flower.command = add ? - TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY; - cls_flower.cookie = (unsigned long)f; - cls_flower.rule->match.dissector = &mask->dissector; - cls_flower.rule->match.mask = &mask->key; - cls_flower.rule->match.key = &f->mkey; - - err = tc_setup_flow_action(&cls_flower.rule->action, - &f->exts); - if (err) { - kfree(cls_flower.rule); - if (tc_skip_sw(f->flags)) { - NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action"); - return err; - } - continue; + /* hw_filters list can only be changed by hw offload functions after + * obtaining rtnl lock. Make sure it is not changed while reoffload is + * iterating it. + */ + ASSERT_RTNL(); + + while ((f = fl_get_next_hw_filter(tp, f, add))) { + cls_flower.rule = + flow_rule_alloc(tcf_exts_num_actions(&f->exts)); + if (!cls_flower.rule) { + __fl_put(f); + return -ENOMEM; + } + + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, + extack); + cls_flower.command = add ? + TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY; + cls_flower.cookie = (unsigned long)f; + cls_flower.rule->match.dissector = &f->mask->dissector; + cls_flower.rule->match.mask = &f->mask->key; + cls_flower.rule->match.key = &f->mkey; + + err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts); + if (err) { + kfree(cls_flower.rule); + if (tc_skip_sw(f->flags)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action"); + __fl_put(f); + return err; } + goto next_flow; + } - cls_flower.classid = f->res.classid; + cls_flower.classid = f->res.classid; - err = cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv); - kfree(cls_flower.rule); + err = cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv); + kfree(cls_flower.rule); - if (err) { - if (add && tc_skip_sw(f->flags)) - return err; - continue; + if (err) { + if (add && tc_skip_sw(f->flags)) { + __fl_put(f); + return err; } - - tc_cls_offload_cnt_update(block, &f->in_hw_count, - &f->flags, add); + goto next_flow; } + + spin_lock(&tp->lock); + tc_cls_offload_cnt_update(block, &f->in_hw_count, &f->flags, + add); + spin_unlock(&tp->lock); +next_flow: + __fl_put(f); } return 0; @@ -2061,6 +2326,7 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, struct cls_fl_filter *f = fh; struct nlattr *nest; struct fl_flow_key *key, *mask; + bool skip_hw; if (!f) return skb->len; @@ -2071,21 +2337,26 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, if (!nest) goto nla_put_failure; + spin_lock(&tp->lock); + if (f->res.classid && nla_put_u32(skb, TCA_FLOWER_CLASSID, f->res.classid)) - goto nla_put_failure; + goto nla_put_failure_locked; key = &f->key; mask = &f->mask->key; + skip_hw = tc_skip_hw(f->flags); if (fl_dump_key(skb, net, key, mask)) - goto nla_put_failure; - - if (!tc_skip_hw(f->flags)) - fl_hw_update_stats(tp, f); + goto nla_put_failure_locked; if (f->flags && nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags)) - goto nla_put_failure; + goto nla_put_failure_locked; + + spin_unlock(&tp->lock); + + if (!skip_hw) + fl_hw_update_stats(tp, f, rtnl_held); if (nla_put_u32(skb, TCA_FLOWER_IN_HW_COUNT, f->in_hw_count)) goto nla_put_failure; @@ -2100,6 +2371,8 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, return skb->len; +nla_put_failure_locked: + spin_unlock(&tp->lock); nla_put_failure: nla_nest_cancel(skb, nest); return -1; @@ -2144,6 +2417,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = { .init = fl_init, .destroy = fl_destroy, .get = fl_get, + .put = fl_put, .change = fl_change, .delete = fl_delete, .walk = fl_walk, @@ -2154,6 +2428,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = { .tmplt_destroy = fl_tmplt_destroy, .tmplt_dump = fl_tmplt_dump, .owner = THIS_MODULE, + .flags = TCF_PROTO_OPS_DOIT_UNLOCKED, }; static int __init cls_fl_init(void) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index fb8f138b9776..c126b9f78d6e 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -998,6 +998,19 @@ static void notify_and_destroy(struct net *net, struct sk_buff *skb, qdisc_put(old); } +static void qdisc_clear_nolock(struct Qdisc *sch) +{ + sch->flags &= ~TCQ_F_NOLOCK; + if (!(sch->flags & TCQ_F_CPUSTATS)) + return; + + free_percpu(sch->cpu_bstats); + free_percpu(sch->cpu_qstats); + sch->cpu_bstats = NULL; + sch->cpu_qstats = NULL; + sch->flags &= ~TCQ_F_CPUSTATS; +} + /* Graft qdisc "new" to class "classid" of qdisc "parent" or * to device "dev". * @@ -1076,7 +1089,7 @@ skip: /* Only support running class lockless if parent is lockless */ if (new && (new->flags & TCQ_F_NOLOCK) && parent && !(parent->flags & TCQ_F_NOLOCK)) - new->flags &= ~TCQ_F_NOLOCK; + qdisc_clear_nolock(new); if (!cops || !cops->graft) return -EOPNOTSUPP; diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index c6a502933fe7..f68fd7a0e038 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -61,16 +61,20 @@ #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> +#include <net/netevent.h> #include <net/netlink.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> +static LIST_HEAD(cbs_list); +static DEFINE_SPINLOCK(cbs_list_lock); + #define BYTES_PER_KBIT (1000LL / 8) struct cbs_sched_data { bool offload; int queue; - s64 port_rate; /* in bytes/s */ + atomic64_t port_rate; /* in bytes/s */ s64 last; /* timestamp in ns */ s64 credits; /* in bytes */ s32 locredit; /* in bytes */ @@ -82,6 +86,7 @@ struct cbs_sched_data { struct sk_buff **to_free); struct sk_buff *(*dequeue)(struct Qdisc *sch); struct Qdisc *qdisc; + struct list_head cbs_list; }; static int cbs_child_enqueue(struct sk_buff *skb, struct Qdisc *sch, @@ -181,6 +186,11 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) s64 credits; int len; + if (atomic64_read(&q->port_rate) == -1) { + WARN_ONCE(1, "cbs: dequeue() called with unknown port rate."); + return NULL; + } + if (q->credits < 0) { credits = timediff_to_credits(now - q->last, q->idleslope); @@ -207,7 +217,8 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) /* As sendslope is a negative number, this will decrease the * amount of q->credits. */ - credits = credits_from_len(len, q->sendslope, q->port_rate); + credits = credits_from_len(len, q->sendslope, + atomic64_read(&q->port_rate)); credits += q->credits; q->credits = max_t(s64, credits, q->locredit); @@ -294,6 +305,50 @@ static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q, return 0; } +static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q) +{ + struct ethtool_link_ksettings ecmd; + int port_rate = -1; + + if (!__ethtool_get_link_ksettings(dev, &ecmd) && + ecmd.base.speed != SPEED_UNKNOWN) + port_rate = ecmd.base.speed * 1000 * BYTES_PER_KBIT; + + atomic64_set(&q->port_rate, port_rate); + netdev_dbg(dev, "cbs: set %s's port_rate to: %lld, linkspeed: %d\n", + dev->name, (long long)atomic64_read(&q->port_rate), + ecmd.base.speed); +} + +static int cbs_dev_notifier(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct cbs_sched_data *q; + struct net_device *qdev; + bool found = false; + + ASSERT_RTNL(); + + if (event != NETDEV_UP && event != NETDEV_CHANGE) + return NOTIFY_DONE; + + spin_lock(&cbs_list_lock); + list_for_each_entry(q, &cbs_list, cbs_list) { + qdev = qdisc_dev(q->qdisc); + if (qdev == dev) { + found = true; + break; + } + } + spin_unlock(&cbs_list_lock); + + if (found) + cbs_set_port_rate(dev, q); + + return NOTIFY_DONE; +} + static int cbs_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -315,16 +370,7 @@ static int cbs_change(struct Qdisc *sch, struct nlattr *opt, qopt = nla_data(tb[TCA_CBS_PARMS]); if (!qopt->offload) { - struct ethtool_link_ksettings ecmd; - s64 link_speed; - - if (!__ethtool_get_link_ksettings(dev, &ecmd)) - link_speed = ecmd.base.speed; - else - link_speed = SPEED_1000; - - q->port_rate = link_speed * 1000 * BYTES_PER_KBIT; - + cbs_set_port_rate(dev, q); cbs_disable_offload(dev, q); } else { err = cbs_enable_offload(dev, q, qopt, extack); @@ -347,6 +393,7 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt, { struct cbs_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); + int err; if (!opt) { NL_SET_ERR_MSG(extack, "Missing CBS qdisc options which are mandatory"); @@ -367,7 +414,17 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt, qdisc_watchdog_init(&q->watchdog, sch); - return cbs_change(sch, opt, extack); + err = cbs_change(sch, opt, extack); + if (err) + return err; + + if (!q->offload) { + spin_lock(&cbs_list_lock); + list_add(&q->cbs_list, &cbs_list); + spin_unlock(&cbs_list_lock); + } + + return 0; } static void cbs_destroy(struct Qdisc *sch) @@ -375,8 +432,11 @@ static void cbs_destroy(struct Qdisc *sch) struct cbs_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); - qdisc_watchdog_cancel(&q->watchdog); + spin_lock(&cbs_list_lock); + list_del(&q->cbs_list); + spin_unlock(&cbs_list_lock); + qdisc_watchdog_cancel(&q->watchdog); cbs_disable_offload(dev, q); if (q->qdisc) @@ -487,14 +547,24 @@ static struct Qdisc_ops cbs_qdisc_ops __read_mostly = { .owner = THIS_MODULE, }; +static struct notifier_block cbs_device_notifier = { + .notifier_call = cbs_dev_notifier, +}; + static int __init cbs_module_init(void) { + int err = register_netdevice_notifier(&cbs_device_notifier); + + if (err) + return err; + return register_qdisc(&cbs_qdisc_ops); } static void __exit cbs_module_exit(void) { unregister_qdisc(&cbs_qdisc_ops); + unregister_netdevice_notifier(&cbs_device_notifier); } module_init(cbs_module_init) module_exit(cbs_module_exit) diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index a117d9260558..848aab3693bd 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -68,7 +68,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q) skb = __skb_dequeue(&q->skb_bad_txq); if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_dec(q, skb); - qdisc_qstats_atomic_qlen_dec(q); + qdisc_qstats_cpu_qlen_dec(q); } else { qdisc_qstats_backlog_dec(q, skb); q->q.qlen--; @@ -108,7 +108,7 @@ static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q, if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_inc(q, skb); - qdisc_qstats_atomic_qlen_inc(q); + qdisc_qstats_cpu_qlen_inc(q); } else { qdisc_qstats_backlog_inc(q, skb); q->q.qlen++; @@ -118,52 +118,36 @@ static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q, spin_unlock(lock); } -static inline int __dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) +static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) { - while (skb) { - struct sk_buff *next = skb->next; - - __skb_queue_tail(&q->gso_skb, skb); - q->qstats.requeues++; - qdisc_qstats_backlog_inc(q, skb); - q->q.qlen++; /* it's still part of the queue */ + spinlock_t *lock = NULL; - skb = next; + if (q->flags & TCQ_F_NOLOCK) { + lock = qdisc_lock(q); + spin_lock(lock); } - __netif_schedule(q); - return 0; -} - -static inline int dev_requeue_skb_locked(struct sk_buff *skb, struct Qdisc *q) -{ - spinlock_t *lock = qdisc_lock(q); - - spin_lock(lock); while (skb) { struct sk_buff *next = skb->next; __skb_queue_tail(&q->gso_skb, skb); - qdisc_qstats_cpu_requeues_inc(q); - qdisc_qstats_cpu_backlog_inc(q, skb); - qdisc_qstats_atomic_qlen_inc(q); + /* it's still part of the queue */ + if (qdisc_is_percpu_stats(q)) { + qdisc_qstats_cpu_requeues_inc(q); + qdisc_qstats_cpu_backlog_inc(q, skb); + qdisc_qstats_cpu_qlen_inc(q); + } else { + q->qstats.requeues++; + qdisc_qstats_backlog_inc(q, skb); + q->q.qlen++; + } skb = next; } - spin_unlock(lock); - + if (lock) + spin_unlock(lock); __netif_schedule(q); - - return 0; -} - -static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) -{ - if (q->flags & TCQ_F_NOLOCK) - return dev_requeue_skb_locked(skb, q); - else - return __dev_requeue_skb(skb, q); } static void try_bulk_dequeue_skb(struct Qdisc *q, @@ -252,7 +236,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, skb = __skb_dequeue(&q->gso_skb); if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_dec(q, skb); - qdisc_qstats_atomic_qlen_dec(q); + qdisc_qstats_cpu_qlen_dec(q); } else { qdisc_qstats_backlog_dec(q, skb); q->q.qlen--; @@ -645,11 +629,7 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, if (unlikely(err)) return qdisc_drop_cpu(skb, qdisc, to_free); - qdisc_qstats_atomic_qlen_inc(qdisc); - /* Note: skb can not be used after skb_array_produce(), - * so we better not use qdisc_qstats_cpu_backlog_inc() - */ - this_cpu_add(qdisc->cpu_qstats->backlog, pkt_len); + qdisc_update_stats_at_enqueue(qdisc, pkt_len); return NET_XMIT_SUCCESS; } @@ -668,9 +648,9 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) skb = __skb_array_consume(q); } if (likely(skb)) { - qdisc_qstats_cpu_backlog_dec(qdisc, skb); - qdisc_bstats_cpu_update(qdisc, skb); - qdisc_qstats_atomic_qlen_dec(qdisc); + qdisc_update_stats_at_dequeue(qdisc, skb); + } else { + qdisc->empty = true; } return skb; @@ -714,6 +694,7 @@ static void pfifo_fast_reset(struct Qdisc *qdisc) struct gnet_stats_queue *q = per_cpu_ptr(qdisc->cpu_qstats, i); q->backlog = 0; + q->qlen = 0; } } @@ -880,6 +861,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; + sch->empty = true; dev_hold(dev); refcount_set(&sch->refcnt, 1); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index c7041999eb5d..df848a36b222 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -13,6 +13,7 @@ #include <linux/list.h> #include <linux/errno.h> #include <linux/skbuff.h> +#include <linux/math64.h> #include <linux/module.h> #include <linux/spinlock.h> #include <net/netlink.h> @@ -20,6 +21,9 @@ #include <net/pkt_cls.h> #include <net/sch_generic.h> +static LIST_HEAD(taprio_list); +static DEFINE_SPINLOCK(taprio_list_lock); + #define TAPRIO_ALL_GATES_OPEN -1 struct sched_entry { @@ -42,9 +46,9 @@ struct taprio_sched { struct Qdisc *root; s64 base_time; int clockid; - int picos_per_byte; /* Using picoseconds because for 10Gbps+ - * speeds it's sub-nanoseconds per byte - */ + atomic64_t picos_per_byte; /* Using picoseconds because for 10Gbps+ + * speeds it's sub-nanoseconds per byte + */ size_t num_entries; /* Protects the update side of the RCU protected current_entry */ @@ -53,6 +57,7 @@ struct taprio_sched { struct list_head entries; ktime_t (*get_time)(void); struct hrtimer advance_timer; + struct list_head taprio_list; }; static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, @@ -85,7 +90,7 @@ static struct sk_buff *taprio_peek(struct Qdisc *sch) rcu_read_lock(); entry = rcu_dereference(q->current_entry); - gate_mask = entry ? entry->gate_mask : -1; + gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; rcu_read_unlock(); if (!gate_mask) @@ -107,7 +112,7 @@ static struct sk_buff *taprio_peek(struct Qdisc *sch) tc = netdev_get_prio_tc_map(dev, prio); if (!(gate_mask & BIT(tc))) - return NULL; + continue; return skb; } @@ -117,7 +122,14 @@ static struct sk_buff *taprio_peek(struct Qdisc *sch) static inline int length_to_duration(struct taprio_sched *q, int len) { - return (len * q->picos_per_byte) / 1000; + return div_u64(len * atomic64_read(&q->picos_per_byte), 1000); +} + +static void taprio_set_budget(struct taprio_sched *q, struct sched_entry *entry) +{ + atomic_set(&entry->budget, + div64_u64((u64)entry->interval * 1000, + atomic64_read(&q->picos_per_byte))); } static struct sk_buff *taprio_dequeue(struct Qdisc *sch) @@ -129,6 +141,11 @@ static struct sk_buff *taprio_dequeue(struct Qdisc *sch) u32 gate_mask; int i; + if (atomic64_read(&q->picos_per_byte) == -1) { + WARN_ONCE(1, "taprio: dequeue() called with unknown picos per byte."); + return NULL; + } + rcu_read_lock(); entry = rcu_dereference(q->current_entry); /* if there's no entry, it means that the schedule didn't @@ -171,12 +188,12 @@ static struct sk_buff *taprio_dequeue(struct Qdisc *sch) */ if (gate_mask != TAPRIO_ALL_GATES_OPEN && ktime_after(guard, entry->close_time)) - return NULL; + continue; /* ... and no budget. */ if (gate_mask != TAPRIO_ALL_GATES_OPEN && atomic_sub_return(len, &entry->budget) < 0) - return NULL; + continue; skb = child->ops->dequeue(child); if (unlikely(!skb)) @@ -192,14 +209,6 @@ static struct sk_buff *taprio_dequeue(struct Qdisc *sch) return NULL; } -static bool should_restart_cycle(const struct taprio_sched *q, - const struct sched_entry *entry) -{ - WARN_ON(!entry); - - return list_is_last(&entry->list, &q->entries); -} - static enum hrtimer_restart advance_sched(struct hrtimer *timer) { struct taprio_sched *q = container_of(timer, struct taprio_sched, @@ -223,7 +232,7 @@ static enum hrtimer_restart advance_sched(struct hrtimer *timer) goto first_run; } - if (should_restart_cycle(q, entry)) + if (list_is_last(&entry->list, &q->entries)) next = list_first_entry(&q->entries, struct sched_entry, list); else @@ -232,8 +241,7 @@ static enum hrtimer_restart advance_sched(struct hrtimer *timer) close_time = ktime_add_ns(entry->close_time, next->interval); next->close_time = close_time; - atomic_set(&next->budget, - (next->interval * 1000) / q->picos_per_byte); + taprio_set_budget(q, next); first_run: rcu_assign_pointer(q->current_entry, next); @@ -523,7 +531,7 @@ static int taprio_parse_mqprio_opt(struct net_device *dev, return 0; } -static ktime_t taprio_get_start_time(struct Qdisc *sch) +static int taprio_get_start_time(struct Qdisc *sch, ktime_t *start) { struct taprio_sched *q = qdisc_priv(sch); struct sched_entry *entry; @@ -531,27 +539,33 @@ static ktime_t taprio_get_start_time(struct Qdisc *sch) s64 n; base = ns_to_ktime(q->base_time); - cycle = 0; + now = q->get_time(); + + if (ktime_after(base, now)) { + *start = base; + return 0; + } /* Calculate the cycle_time, by summing all the intervals. */ + cycle = 0; list_for_each_entry(entry, &q->entries, list) cycle = ktime_add_ns(cycle, entry->interval); - if (!cycle) - return base; - - now = q->get_time(); - - if (ktime_after(base, now)) - return base; + /* The qdisc is expected to have at least one sched_entry. Moreover, + * any entry must have 'interval' > 0. Thus if the cycle time is zero, + * something went really wrong. In that case, we should warn about this + * inconsistent state and return error. + */ + if (WARN_ON(!cycle)) + return -EFAULT; /* Schedule the start time for the beginning of the next * cycle. */ n = div64_s64(ktime_sub_ns(now, base), cycle); - - return ktime_add_ns(base, (n + 1) * cycle); + *start = ktime_add_ns(base, (n + 1) * cycle); + return 0; } static void taprio_start_sched(struct Qdisc *sch, ktime_t start) @@ -566,8 +580,7 @@ static void taprio_start_sched(struct Qdisc *sch, ktime_t start) list); first->close_time = ktime_add_ns(start, first->interval); - atomic_set(&first->budget, - (first->interval * 1000) / q->picos_per_byte); + taprio_set_budget(q, first); rcu_assign_pointer(q->current_entry, NULL); spin_unlock_irqrestore(&q->current_entry_lock, flags); @@ -575,6 +588,52 @@ static void taprio_start_sched(struct Qdisc *sch, ktime_t start) hrtimer_start(&q->advance_timer, start, HRTIMER_MODE_ABS); } +static void taprio_set_picos_per_byte(struct net_device *dev, + struct taprio_sched *q) +{ + struct ethtool_link_ksettings ecmd; + int picos_per_byte = -1; + + if (!__ethtool_get_link_ksettings(dev, &ecmd) && + ecmd.base.speed != SPEED_UNKNOWN) + picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8, + ecmd.base.speed * 1000 * 1000); + + atomic64_set(&q->picos_per_byte, picos_per_byte); + netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n", + dev->name, (long long)atomic64_read(&q->picos_per_byte), + ecmd.base.speed); +} + +static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net_device *qdev; + struct taprio_sched *q; + bool found = false; + + ASSERT_RTNL(); + + if (event != NETDEV_UP && event != NETDEV_CHANGE) + return NOTIFY_DONE; + + spin_lock(&taprio_list_lock); + list_for_each_entry(q, &taprio_list, taprio_list) { + qdev = qdisc_dev(q->root); + if (qdev == dev) { + found = true; + break; + } + } + spin_unlock(&taprio_list_lock); + + if (found) + taprio_set_picos_per_byte(dev, q); + + return NOTIFY_DONE; +} + static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -582,9 +641,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct tc_mqprio_qopt *mqprio = NULL; - struct ethtool_link_ksettings ecmd; int i, err, size; - s64 link_speed; ktime_t start; err = nla_parse_nested(tb, TCA_TAPRIO_ATTR_MAX, opt, @@ -592,7 +649,6 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, if (err < 0) return err; - err = -EINVAL; if (tb[TCA_TAPRIO_ATTR_PRIOMAP]) mqprio = nla_data(tb[TCA_TAPRIO_ATTR_PRIOMAP]); @@ -657,17 +713,13 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, mqprio->prio_tc_map[i]); } - if (!__ethtool_get_link_ksettings(dev, &ecmd)) - link_speed = ecmd.base.speed; - else - link_speed = SPEED_1000; - - q->picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8, - link_speed * 1000 * 1000); + taprio_set_picos_per_byte(dev, q); - start = taprio_get_start_time(sch); - if (!start) - return 0; + err = taprio_get_start_time(sch, &start); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Internal error: failed get start time"); + return err; + } taprio_start_sched(sch, start); @@ -681,6 +733,10 @@ static void taprio_destroy(struct Qdisc *sch) struct sched_entry *entry, *n; unsigned int i; + spin_lock(&taprio_list_lock); + list_del(&q->taprio_list); + spin_unlock(&taprio_list_lock); + hrtimer_cancel(&q->advance_timer); if (q->qdiscs) { @@ -735,6 +791,10 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt, if (!opt) return -EINVAL; + spin_lock(&taprio_list_lock); + list_add(&q->taprio_list, &taprio_list); + spin_unlock(&taprio_list_lock); + return taprio_change(sch, opt, extack); } @@ -947,14 +1007,24 @@ static struct Qdisc_ops taprio_qdisc_ops __read_mostly = { .owner = THIS_MODULE, }; +static struct notifier_block taprio_device_notifier = { + .notifier_call = taprio_dev_notifier, +}; + static int __init taprio_module_init(void) { + int err = register_netdevice_notifier(&taprio_device_notifier); + + if (err) + return err; + return register_qdisc(&taprio_qdisc_ops); } static void __exit taprio_module_exit(void) { unregister_qdisc(&taprio_qdisc_ops); + unregister_netdevice_notifier(&taprio_device_notifier); } module_init(taprio_module_init); |