// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_htb.c Hierarchical token bucket, feed tree version * * Authors: Martin Devera, <devik@cdi.cz> * * Credits (in time order) for older HTB versions: * Stef Coene <stef.coene@docum.org> * HTB support at LARTC mailing list * Ondrej Kraus, <krauso@barr.cz> * found missing INIT_QDISC(htb) * Vladimir Smelhaus, Aamer Akhter, Bert Hubert * helped a lot to locate nasty class stall bug * Andi Kleen, Jamal Hadi, Bert Hubert * code review and helpful comments on shaping * Tomasz Wrona, <tw@eter.tym.pl> * created test case so that I was able to fix nasty bug * Wilfried Weissmann * spotted bug in dequeue code and helped with fix * Jiri Fojtasek * fixed requeue routine * and many others. thanks.
*/ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/list.h> #include <linux/compiler.h> #include <linux/rbtree.h> #include <linux/workqueue.h> #include <linux/slab.h> #include <net/netlink.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h>
/* HTB algorithm. Author: devik@cdi.cz ======================================================================== HTB is like TBF with multiple classes. It is also similar to CBQ because it allows to assign priority to each class in hierarchy. In fact it is another implementation of Floyd's formal sharing.
Levels: Each class is assigned level. Leaf has ALWAYS level 0 and root classes have level TC_HTB_MAXDEPTH-1. Interior nodes has level one less than their parent.
*/
staticint htb_hysteresis __read_mostly = 0; /* whether to use mode hysteresis for speedup */ #define HTB_VER 0x30011 /* major must be matched with number supplied by TC as version */
/* Module parameter and sysfs export */
module_param (htb_hysteresis, int, 0640);
MODULE_PARM_DESC(htb_hysteresis, "Hysteresis mode, less CPU load, less accurate");
staticint htb_rate_est = 0; /* htb classes have a default rate estimator */
module_param(htb_rate_est, int, 0640);
MODULE_PARM_DESC(htb_rate_est, "setup a default rate estimator (4sec 16sec) for htb classes");
/* used internaly to keep status of single class */ enum htb_cmode {
HTB_CANT_SEND, /* class can't send and can't borrow */
HTB_MAY_BORROW, /* class can't send but may borrow */
HTB_CAN_SEND /* class can send */
};
struct htb_prio { union { struct rb_root row; struct rb_root feed;
}; struct rb_node *ptr; /* When class changes from state 1->2 and disconnects from * parent's feed then we lost ptr value and start from the * first child again. Here we store classid of the * last valid ptr (used when ptr is NULL).
*/
u32 last_ptr_id;
};
/* interior & leaf nodes; props specific to leaves are marked L: * To reduce false sharing, place mostly read fields at beginning, * and mostly written ones at the end.
*/ struct htb_class { struct Qdisc_class_common common; struct psched_ratecfg rate; struct psched_ratecfg ceil;
s64 buffer, cbuffer;/* token bucket depth/rate */
s64 mbuffer; /* max wait time */
u32 prio; /* these two are used only by leaves... */ int quantum; /* but stored for parent-to-leaf return */
int prio_activity; /* for which prios are we active */ enum htb_cmode cmode; /* current mode of the class */ struct rb_node pq_node; /* node for event queue */ struct rb_node node[TC_HTB_NUMPRIO]; /* node for self or feed tree */
struct htb_sched { struct Qdisc_class_hash clhash; int defcls; /* class where unclassified flows go to */ int rate2quantum; /* quant = rate / rate2quantum */
/** * htb_classify - classify a packet into class * @skb: the socket buffer * @sch: the active queue discipline * @qerr: pointer for returned status code * * It returns NULL if the packet should be dropped or -1 if the packet * should be passed directly thru. In all other cases leaf class is returned. * We allow direct class selection by classid in priority. The we examine * filters in qdisc and in inner nodes (if higher filter points to the inner * node). If we end up with classid MAJOR:0 we enqueue the skb into special * internal fifo (direct). These packets then go directly thru. If we still * have no valid leaf we try to use MAJOR:default leaf. It still unsuccessful * then finish and return direct queue.
*/ staticstruct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
{ struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl; struct tcf_result res; struct tcf_proto *tcf; int result;
/* allow to select class by setting skb->priority to valid classid; * note that nfmark can be used too by attaching filter fw with no * rules in it
*/ if (skb->priority == sch->handle) return HTB_DIRECT; /* X:0 (direct flow) selected */
cl = htb_find(skb->priority, sch); if (cl) { if (cl->level == 0) return cl; /* Start with inner filter chain if a non-leaf class is selected */
tcf = rcu_dereference_bh(cl->filter_list);
} else {
tcf = rcu_dereference_bh(q->filter_list);
}
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; while (tcf && (result = tcf_classify(skb, NULL, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: case TC_ACT_STOLEN: case TC_ACT_TRAP:
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
fallthrough; case TC_ACT_SHOT: return NULL;
} #endif
cl = (void *)res.class; if (!cl) { if (res.classid == sch->handle) return HTB_DIRECT; /* X:0 (direct flow) */
cl = htb_find(res.classid, sch); if (!cl) break; /* filter selected invalid classid */
} if (!cl->level) return cl; /* we hit leaf; return it */
/* we have got inner class; apply inner filter chain */
tcf = rcu_dereference_bh(cl->filter_list);
} /* classification failed; try to use default class */
cl = htb_find(TC_H_MAKE(TC_H_MAJ(sch->handle), q->defcls), sch); if (!cl || cl->level) return HTB_DIRECT; /* bad default .. this is safe bet */ return cl;
}
/** * htb_add_to_id_tree - adds class to the round robin list * @root: the root of the tree * @cl: the class to add * @prio: the give prio in class * * Routine adds class to the list (actually tree) sorted by classid. * Make sure that class is not already on such list for given prio.
*/ staticvoid htb_add_to_id_tree(struct rb_root *root, struct htb_class *cl, int prio)
{ struct rb_node **p = &root->rb_node, *parent = NULL;
while (*p) { struct htb_class *c;
parent = *p;
c = rb_entry(parent, struct htb_class, node[prio]);
if (cl->common.classid > c->common.classid)
p = &parent->rb_right; else
p = &parent->rb_left;
}
rb_link_node(&cl->node[prio], parent, p);
rb_insert_color(&cl->node[prio], root);
}
/** * htb_add_to_wait_tree - adds class to the event queue with delay * @q: the priority event queue * @cl: the class to add * @delay: delay in microseconds * * The class is added to priority event queue to indicate that class will * change its mode in cl->pq_key microseconds. Make sure that class is not * already in the queue.
*/ staticvoid htb_add_to_wait_tree(struct htb_sched *q, struct htb_class *cl, s64 delay)
{ struct rb_node **p = &q->hlevel[cl->level].wait_pq.rb_node, *parent = NULL;
cl->pq_key = q->now + delay; if (cl->pq_key == q->now)
cl->pq_key++;
/* update the nearest event cache */ if (q->near_ev_cache[cl->level] > cl->pq_key)
q->near_ev_cache[cl->level] = cl->pq_key;
while (*p) { struct htb_class *c;
parent = *p;
c = rb_entry(parent, struct htb_class, pq_node); if (cl->pq_key >= c->pq_key)
p = &parent->rb_right; else
p = &parent->rb_left;
}
rb_link_node(&cl->pq_node, parent, p);
rb_insert_color(&cl->pq_node, &q->hlevel[cl->level].wait_pq);
}
/** * htb_next_rb_node - finds next node in binary tree * @n: the current node in binary tree * * When we are past last key we return NULL. * Average complexity is 2 steps per call.
*/ staticinlinevoid htb_next_rb_node(struct rb_node **n)
{ if (*n)
*n = rb_next(*n);
}
/** * htb_add_class_to_row - add class to its row * @q: the priority event queue * @cl: the class to add * @mask: the given priorities in class in bitmap * * The class is added to row at priorities marked in mask. * It does nothing if mask == 0.
*/ staticinlinevoid htb_add_class_to_row(struct htb_sched *q, struct htb_class *cl, int mask)
{
q->row_mask[cl->level] |= mask; while (mask) { int prio = ffz(~mask);
mask &= ~(1 << prio);
htb_add_to_id_tree(&q->hlevel[cl->level].hprio[prio].row, cl, prio);
}
}
/* If this triggers, it is a bug in this code, but it need not be fatal */ staticvoid htb_safe_rb_erase(struct rb_node *rb, struct rb_root *root)
{ if (RB_EMPTY_NODE(rb)) {
WARN_ON(1);
} else {
rb_erase(rb, root);
RB_CLEAR_NODE(rb);
}
}
/** * htb_remove_class_from_row - removes class from its row * @q: the priority event queue * @cl: the class to add * @mask: the given priorities in class in bitmap * * The class is removed from row at priorities marked in mask. * It does nothing if mask == 0.
*/ staticinlinevoid htb_remove_class_from_row(struct htb_sched *q, struct htb_class *cl, int mask)
{ int m = 0; struct htb_level *hlevel = &q->hlevel[cl->level];
while (mask) { int prio = ffz(~mask); struct htb_prio *hprio = &hlevel->hprio[prio];
htb_safe_rb_erase(cl->node + prio, &hprio->row); if (!hprio->row.rb_node)
m |= 1 << prio;
}
q->row_mask[cl->level] &= ~m;
}
/** * htb_activate_prios - creates active classe's feed chain * @q: the priority event queue * @cl: the class to activate * * The class is connected to ancestors and/or appropriate rows * for priorities it is participating on. cl->cmode must be new * (activated) mode. It does nothing if cl->prio_activity == 0.
*/ staticvoid htb_activate_prios(struct htb_sched *q, struct htb_class *cl)
{ struct htb_class *p = cl->parent; long m, mask = cl->prio_activity;
while (cl->cmode == HTB_MAY_BORROW && p && mask) {
m = mask; while (m) { unsignedint prio = ffz(~m);
if (WARN_ON_ONCE(prio >= ARRAY_SIZE(p->inner.clprio))) break;
m &= ~(1 << prio);
if (p->inner.clprio[prio].feed.rb_node) /* parent already has its feed in use so that * reset bit in mask as parent is already ok
*/
mask &= ~(1 << prio);
/** * htb_deactivate_prios - remove class from feed chain * @q: the priority event queue * @cl: the class to deactivate * * cl->cmode must represent old mode (before deactivation). It does * nothing if cl->prio_activity == 0. Class is removed from all feed * chains and rows.
*/ staticvoid htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl)
{ struct htb_class *p = cl->parent; long m, mask = cl->prio_activity;
while (cl->cmode == HTB_MAY_BORROW && p && mask) {
m = mask;
mask = 0; while (m) { int prio = ffz(~m);
m &= ~(1 << prio);
if (p->inner.clprio[prio].ptr == cl->node + prio) { /* we are removing child which is pointed to from * parent feed - forget the pointer but remember * classid
*/
p->inner.clprio[prio].last_ptr_id = cl->common.classid;
p->inner.clprio[prio].ptr = NULL;
}
/** * htb_class_mode - computes and returns current class mode * @cl: the target class * @diff: diff time in microseconds * * It computes cl's mode at time cl->t_c+diff and returns it. If mode * is not HTB_CAN_SEND then cl->pq_key is updated to time difference * from now to time when cl will change its state. * Also it is worth to note that class mode doesn't change simply * at cl->{c,}tokens == 0 but there can rather be hysteresis of * 0 .. -cl->{c,}buffer range. It is meant to limit number of * mode transitions per time unit. The speed gain is about 1/6.
*/ staticinlineenum htb_cmode
htb_class_mode(struct htb_class *cl, s64 *diff)
{
s64 toks;
if ((toks = (cl->tokens + *diff)) >= htb_hiwater(cl)) return HTB_CAN_SEND;
*diff = -toks; return HTB_MAY_BORROW;
}
/** * htb_change_class_mode - changes classe's mode * @q: the priority event queue * @cl: the target class * @diff: diff time in microseconds * * This should be the only way how to change classe's mode under normal * circumstances. Routine will update feed lists linkage, change mode * and add class to the wait event queue if appropriate. New mode should * be different from old one and cl->pq_key has to be valid if changing * to mode other than HTB_CAN_SEND (see htb_add_to_wait_tree).
*/ staticvoid
htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff)
{ enum htb_cmode new_mode = htb_class_mode(cl, diff);
if (new_mode == cl->cmode) return;
if (new_mode == HTB_CANT_SEND) {
cl->overlimits++;
q->overlimits++;
}
if (cl->prio_activity) { /* not necessary: speed optimization */ if (cl->cmode != HTB_CANT_SEND)
htb_deactivate_prios(q, cl);
cl->cmode = new_mode; if (new_mode != HTB_CANT_SEND)
htb_activate_prios(q, cl);
} else
cl->cmode = new_mode;
}
/** * htb_activate - inserts leaf cl into appropriate active feeds * @q: the priority event queue * @cl: the target class * * Routine learns (new) priority of leaf and activates feed chain * for the prio. It can be called on already active leaf safely. * It also adds leaf into droplist.
*/ staticinlinevoid htb_activate(struct htb_sched *q, struct htb_class *cl)
{
WARN_ON(cl->level || !cl->leaf.q);
/** * htb_deactivate - remove leaf cl from active feeds * @q: the priority event queue * @cl: the target class * * Make sure that leaf is active. In the other words it can't be called * with non-active leaf. It also removes class from the drop list.
*/ staticinlinevoid htb_deactivate(struct htb_sched *q, struct htb_class *cl)
{ if (!cl->prio_activity) return;
htb_deactivate_prios(q, cl);
cl->prio_activity = 0;
}
staticinlinevoid htb_accnt_tokens(struct htb_class *cl, int bytes, s64 diff)
{
s64 toks = diff + cl->tokens;
if (toks > cl->buffer)
toks = cl->buffer;
toks -= (s64) psched_l2t_ns(&cl->rate, bytes); if (toks <= -cl->mbuffer)
toks = 1 - cl->mbuffer;
cl->tokens = toks;
}
staticinlinevoid htb_accnt_ctokens(struct htb_class *cl, int bytes, s64 diff)
{
s64 toks = diff + cl->ctokens;
if (toks > cl->cbuffer)
toks = cl->cbuffer;
toks -= (s64) psched_l2t_ns(&cl->ceil, bytes); if (toks <= -cl->mbuffer)
toks = 1 - cl->mbuffer;
cl->ctokens = toks;
}
/** * htb_charge_class - charges amount "bytes" to leaf and ancestors * @q: the priority event queue * @cl: the class to start iterate * @level: the minimum level to account * @skb: the socket buffer * * Routine assumes that packet "bytes" long was dequeued from leaf cl * borrowing from "level". It accounts bytes to ceil leaky bucket for * leaf and all ancestors and to rate bucket for ancestors at levels * "level" and higher. It also handles possible change of mode resulting * from the update. Note that mode can also increase here (MAY_BORROW to * CAN_SEND) because we can use more precise clock that event queue here. * In such case we remove class from event queue first.
*/ staticvoid htb_charge_class(struct htb_sched *q, struct htb_class *cl, int level, struct sk_buff *skb)
{ int bytes = qdisc_pkt_len(skb); enum htb_cmode old_mode;
s64 diff;
while (cl) {
diff = min_t(s64, q->now - cl->t_c, cl->mbuffer); if (cl->level >= level) { if (cl->level == level)
cl->xstats.lends++;
htb_accnt_tokens(cl, bytes, diff);
} else {
cl->xstats.borrows++;
cl->tokens += diff; /* we moved t_c; update tokens */
}
htb_accnt_ctokens(cl, bytes, diff);
cl->t_c = q->now;
old_mode = cl->cmode;
diff = 0;
htb_change_class_mode(q, cl, &diff); if (old_mode != cl->cmode) { if (old_mode != HTB_CAN_SEND)
htb_safe_rb_erase(&cl->pq_node, &q->hlevel[cl->level].wait_pq); if (cl->cmode != HTB_CAN_SEND)
htb_add_to_wait_tree(q, cl, diff);
}
/* update basic stats except for leaves which are already updated */ if (cl->level)
bstats_update(&cl->bstats, skb);
cl = cl->parent;
}
}
/** * htb_do_events - make mode changes to classes at the level * @q: the priority event queue * @level: which wait_pq in 'q->hlevel' * @start: start jiffies * * Scans event queue for pending events and applies them. Returns time of * next pending event (0 for no event in pq, q->now for too many events). * Note: Applied are events whose have cl->pq_key <= q->now.
*/ static s64 htb_do_events(struct htb_sched *q, constint level, unsignedlong start)
{ /* don't run for longer than 2 jiffies; 2 is used instead of * 1 to simplify things when jiffy is going to be incremented * too soon
*/ unsignedlong stop_at = start + 2; struct rb_root *wait_pq = &q->hlevel[level].wait_pq;
/* too much load - let's continue after a break for scheduling */ if (!(q->warned & HTB_WARN_TOOMANYEVENTS)) {
pr_warn("htb: too many events!\n");
q->warned |= HTB_WARN_TOOMANYEVENTS;
}
return q->now;
}
/* Returns class->node+prio from id-tree where classe's id is >= id. NULL * is no such one exists.
*/ staticstruct rb_node *htb_id_find_next_upper(int prio, struct rb_node *n,
u32 id)
{ struct rb_node *r = NULL; while (n) { struct htb_class *cl =
rb_entry(n, struct htb_class, node[prio]);
if (id > cl->common.classid) {
n = n->rb_right;
} elseif (id < cl->common.classid) {
r = n;
n = n->rb_left;
} else { return n;
}
} return r;
}
/** * htb_lookup_leaf - returns next leaf class in DRR order * @hprio: the current one * @prio: which prio in class * * Find leaf where current feed pointers points to.
*/ staticstruct htb_class *htb_lookup_leaf(struct htb_prio *hprio, constint prio)
{ int i; struct { struct rb_node *root; struct rb_node **pptr;
u32 *pid;
} stk[TC_HTB_MAXDEPTH], *sp = stk;
for (i = 0; i < 65535; i++) { if (!*sp->pptr && *sp->pid) { /* ptr was invalidated but id is valid - try to recover * the original or next ptr
*/
*sp->pptr =
htb_id_find_next_upper(prio, sp->root, *sp->pid);
}
*sp->pid = 0; /* ptr is valid now so that remove this hint as it * can become out of date quickly
*/ if (!*sp->pptr) { /* we are at right end; rewind & go up */
*sp->pptr = sp->root; while ((*sp->pptr)->rb_left)
*sp->pptr = (*sp->pptr)->rb_left; if (sp > stk) {
sp--; if (!*sp->pptr) {
WARN_ON(1); return NULL;
}
htb_next_rb_node(sp->pptr);
}
} else { struct htb_class *cl; struct htb_prio *clp;
/* dequeues packet at given priority and level; call only if * you are sure that there is active class at prio/level
*/ staticstruct sk_buff *htb_dequeue_tree(struct htb_sched *q, constint prio, constint level)
{ struct sk_buff *skb = NULL; struct htb_class *cl, *start; struct htb_level *hlevel = &q->hlevel[level]; struct htb_prio *hprio = &hlevel->hprio[prio];
/* look initial class up in the row */
start = cl = htb_lookup_leaf(hprio, prio);
do {
next: if (unlikely(!cl)) return NULL;
/* class can be empty - it is unlikely but can be true if leaf * qdisc drops packets in enqueue routine or if someone used * graft operation on the leaf since last dequeue; * simply deactivate and skip such class
*/ if (unlikely(cl->leaf.q->q.qlen == 0)) { struct htb_class *next;
htb_deactivate(q, cl);
/* row/level might become empty */ if ((q->row_mask[level] & (1 << prio)) == 0) return NULL;
next = htb_lookup_leaf(hprio, prio);
if (cl == start) /* fix start if we just deleted it */
start = next;
cl = next; goto next;
}
skb = cl->leaf.q->dequeue(cl->leaf.q); if (likely(skb != NULL)) break;
if (likely(skb != NULL)) {
bstats_update(&cl->bstats, skb);
cl->leaf.deficit[level] -= qdisc_pkt_len(skb); if (cl->leaf.deficit[level] < 0) {
cl->leaf.deficit[level] += cl->quantum;
htb_next_rb_node(level ? &cl->parent->inner.clprio[prio].ptr :
&q->hlevel[0].hprio[prio].ptr);
} /* this used to be after charge_class but this constelation * gives us slightly better performance
*/ if (!cl->leaf.q->q.qlen)
htb_deactivate(q, cl);
htb_charge_class(q, cl, level, skb);
} return skb;
}
/* try to dequeue direct packets as high prio (!) to minimize cpu work */
skb = __qdisc_dequeue_head(&q->direct_queue); if (skb != NULL) {
ok:
qdisc_bstats_update(sch, skb);
qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--; return skb;
}
if (!sch->q.qlen) goto fin;
q->now = ktime_get_ns();
start_at = jiffies;
next_event = q->now + 5LLU * NSEC_PER_SEC;
for (level = 0; level < TC_HTB_MAXDEPTH; level++) { /* common case optimization - skip event handler quickly */ int m;
s64 event = q->near_ev_cache[level];
if (offload) { if (sch->parent != TC_H_ROOT) {
NL_SET_ERR_MSG(extack, "HTB must be the root qdisc to use offload"); return -EOPNOTSUPP;
}
if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) {
NL_SET_ERR_MSG(extack, "hw-tc-offload ethtool feature flag must be on"); return -EOPNOTSUPP;
}
/* Its safe to not acquire qdisc lock. As we hold RTNL, * no change can happen on the class parameters.
*/
tcm->tcm_parent = cl->parent ? cl->parent->common.classid : TC_H_ROOT;
tcm->tcm_handle = cl->common.classid; if (!cl->level && cl->leaf.q)
tcm->tcm_info = cl->leaf.q->handle;
nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure;
staticinlineint htb_parent_last_child(struct htb_class *cl)
{ if (!cl->parent) /* the root class */ return 0; if (cl->parent->children > 1) /* not the last child */ return 0; return 1;
}
/* One ref for cl->leaf.q, the other for dev_queue->qdisc. */ if (new_q)
qdisc_refcount_inc(new_q);
old_q = htb_graft_helper(dev_queue, new_q);
WARN_ON(!(old_q->flags & TCQ_F_BUILTIN));
}
WARN_ON(!q);
dev_queue = htb_offload_get_queue(cl); /* When destroying, caller qdisc_graft grafts the new qdisc and invokes * qdisc_put for the qdisc being destroyed. htb_destroy_class_offload * does not need to graft or qdisc_put the qdisc being destroyed.
*/ if (!destroying) {
old = htb_graft_helper(dev_queue, NULL); /* Last qdisc grafted should be the same as cl->leaf.q when * calling htb_delete.
*/
WARN_ON(old != q);
}
if (cl->parent) {
_bstats_update(&cl->parent->bstats_bias,
u64_stats_read(&q->bstats.bytes),
u64_stats_read(&q->bstats.packets));
}
cancel_work_sync(&q->work);
qdisc_watchdog_cancel(&q->watchdog); /* This line used to be after htb_destroy_class call below * and surprisingly it worked in 2.4. But it must precede it * because filter need its target class alive to be able to call * unbind_filter on it (without Oops).
*/
tcf_block_put(q->block);
for (i = 0; i < q->clhash.hashsize; i++) {
hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) {
tcf_block_put(cl->block);
cl->block = NULL;
}
}
do {
nonempty = false;
changed = false; for (i = 0; i < q->clhash.hashsize; i++) {
hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i],
common.hnode) { bool last_child;
if (!q->offload) {
htb_destroy_class(sch, cl); continue;
}
nonempty = true;
if (cl->level) continue;
changed = true;
last_child = htb_parent_last_child(cl);
htb_destroy_class_offload(sch, cl, last_child, true, NULL);
qdisc_class_hash_remove(&q->clhash,
&cl->common); if (cl->parent)
cl->parent->children--; if (last_child)
htb_parent_to_leaf(sch, cl, NULL);
htb_destroy_class(sch, cl);
}
}
} while (changed);
WARN_ON(nonempty);
if (!q->direct_qdiscs) return; for (i = 0; i < q->num_direct_qdiscs && q->direct_qdiscs[i]; i++)
qdisc_put(q->direct_qdiscs[i]);
kfree(q->direct_qdiscs);
}
/* TODO: why don't allow to delete subtree ? references ? does * tc subsys guarantee us that in htb_destroy it holds no class * refs so that we can remove children safely there ?
*/ if (cl->children || qdisc_class_in_use(&cl->common)) {
NL_SET_ERR_MSG(extack, "HTB class in use"); return -EBUSY;
}
if (!cl->level && htb_parent_last_child(cl))
last_child = 1;
if (q->offload) {
err = htb_destroy_class_offload(sch, cl, last_child, false,
extack); if (err) return err;
}
if (last_child) { struct netdev_queue *dev_queue = sch->dev_queue;
if (q->offload)
dev_queue = htb_offload_get_queue(cl);
/* delete from hash and active; remainder in destroy_class */
qdisc_class_hash_remove(&q->clhash, &cl->common); if (cl->parent)
cl->parent->children--;
htb_deactivate(q, cl);
if (cl->cmode != HTB_CAN_SEND)
htb_safe_rb_erase(&cl->pq_node,
&q->hlevel[cl->level].wait_pq);
if (last_child)
htb_parent_to_leaf(sch, cl, new_q);
hopt = nla_data(tb[TCA_HTB_PARMS]); if (!hopt->rate.rate || !hopt->ceil.rate) goto failure;
if (q->offload) { /* Options not supported by the offload. */ if (hopt->rate.overhead || hopt->ceil.overhead) {
NL_SET_ERR_MSG(extack, "HTB offload doesn't support the overhead parameter"); goto failure;
} if (hopt->rate.mpu || hopt->ceil.mpu) {
NL_SET_ERR_MSG(extack, "HTB offload doesn't support the mpu parameter"); goto failure;
}
}
/* Keeping backward compatible with rate_table based iproute2 tc */ if (hopt->rate.linklayer == TC_LINKLAYER_UNAWARE)
qdisc_put_rtab(qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB],
NULL));
if (hopt->ceil.linklayer == TC_LINKLAYER_UNAWARE)
qdisc_put_rtab(qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB],
NULL));
/* set class to be in HTB_CAN_SEND state */
cl->tokens = PSCHED_TICKS2NS(hopt->buffer);
cl->ctokens = PSCHED_TICKS2NS(hopt->cbuffer);
cl->mbuffer = 60ULL * NSEC_PER_SEC; /* 1min */
cl->t_c = ktime_get_ns();
cl->cmode = HTB_CAN_SEND;
/* attach to the hash list and parent's family */
qdisc_class_hash_insert(&q->clhash, &cl->common); if (parent)
parent->children++; if (cl->leaf.q != &noop_qdisc)
qdisc_hash_add(cl->leaf.q, true);
} else { if (tca[TCA_RATE]) {
err = gen_replace_estimator(&cl->bstats, NULL,
&cl->rate_est,
NULL, true,
tca[TCA_RATE]); if (err) return err;
}
if (q->offload) { struct net_device *dev = qdisc_dev(sch);
offload_opt = (struct tc_htb_qopt_offload) {
.command = TC_HTB_NODE_MODIFY,
.classid = cl->common.classid,
.rate = max_t(u64, hopt->rate.rate, rate64),
.ceil = max_t(u64, hopt->ceil.rate, ceil64),
.prio = hopt->prio,
.quantum = hopt->quantum,
.extack = extack,
};
err = htb_offload(dev, &offload_opt); if (err) /* Estimator was replaced, and rollback may fail * as well, so we don't try to recover it, and * the estimator won't work property with the * offload anyway, because bstats are updated * only when the stats are queried.
*/ return err;
}
/* it used to be a nasty bug here, we have to check that node * is really leaf before changing cl->leaf !
*/ if (!cl->level) {
u64 quantum = cl->rate.rate_bytes_ps;
/*if (cl && !cl->level) return 0; * The line above used to be there to prevent attaching filters to * leaves. But at least tc_index filter uses this just to get class * for other reasons so that we have to allow for it. * ---- * 19.6.2002 As Werner explained it is ok - bind filter is just * another way to "lock" the class - unlike "get" this lock can * be broken by class during destroy IIUC.
*/ if (cl)
qdisc_class_get(&cl->common); return (unsignedlong)cl;
}
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.