summaryrefslogtreecommitdiffstats
path: root/net/sched
diff options
context:
space:
mode:
Diffstat (limited to 'net/sched')
-rw-r--r--net/sched/act_mirred.c2
-rw-r--r--net/sched/sch_cbq.c2
-rw-r--r--net/sched/sch_drr.c2
-rw-r--r--net/sched/sch_generic.c44
-rw-r--r--net/sched/sch_hfsc.c2
-rw-r--r--net/sched/sch_htb.c82
-rw-r--r--net/sched/sch_qfq.c2
-rw-r--r--net/sched/sch_tbf.c47
8 files changed, 116 insertions, 67 deletions
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 5d676edc22a6..977c10e0631b 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -243,7 +243,7 @@ nla_put_failure:
static int mirred_device_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct tcf_mirred *m;
if (event == NETDEV_UNREGISTER)
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 1bc210ffcba2..71a568862557 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -130,7 +130,7 @@ struct cbq_class {
psched_time_t penalized;
struct gnet_stats_basic_packed bstats;
struct gnet_stats_queue qstats;
- struct gnet_stats_rate_est rate_est;
+ struct gnet_stats_rate_est64 rate_est;
struct tc_cbq_xstats xstats;
struct tcf_proto *filter_list;
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 759b308d1a8d..8302717ea303 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -25,7 +25,7 @@ struct drr_class {
struct gnet_stats_basic_packed bstats;
struct gnet_stats_queue qstats;
- struct gnet_stats_rate_est rate_est;
+ struct gnet_stats_rate_est64 rate_est;
struct list_head alist;
struct Qdisc *qdisc;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 20224086cc28..4626cef4b76e 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -901,37 +901,33 @@ void dev_shutdown(struct net_device *dev)
void psched_ratecfg_precompute(struct psched_ratecfg *r,
const struct tc_ratespec *conf)
{
- u64 factor;
- u64 mult;
- int shift;
-
memset(r, 0, sizeof(*r));
r->overhead = conf->overhead;
- r->rate_bps = (u64)conf->rate << 3;
+ r->rate_bytes_ps = conf->rate;
r->mult = 1;
/*
- * Calibrate mult, shift so that token counting is accurate
- * for smallest packet size (64 bytes). Token (time in ns) is
- * computed as (bytes * 8) * NSEC_PER_SEC / rate_bps. It will
- * work as long as the smallest packet transfer time can be
- * accurately represented in nanosec.
+ * The deal here is to replace a divide by a reciprocal one
+ * in fast path (a reciprocal divide is a multiply and a shift)
+ *
+ * Normal formula would be :
+ * time_in_ns = (NSEC_PER_SEC * len) / rate_bps
+ *
+ * We compute mult/shift to use instead :
+ * time_in_ns = (len * mult) >> shift;
+ *
+ * We try to get the highest possible mult value for accuracy,
+ * but have to make sure no overflows will ever happen.
*/
- if (r->rate_bps > 0) {
- /*
- * Higher shift gives better accuracy. Find the largest
- * shift such that mult fits in 32 bits.
- */
- for (shift = 0; shift < 16; shift++) {
- r->shift = shift;
- factor = 8LLU * NSEC_PER_SEC * (1 << r->shift);
- mult = div64_u64(factor, r->rate_bps);
- if (mult > UINT_MAX)
+ if (r->rate_bytes_ps > 0) {
+ u64 factor = NSEC_PER_SEC;
+
+ for (;;) {
+ r->mult = div64_u64(factor, r->rate_bytes_ps);
+ if (r->mult & (1U << 31) || factor & (1ULL << 63))
break;
+ factor <<= 1;
+ r->shift++;
}
-
- r->shift = shift - 1;
- factor = 8LLU * NSEC_PER_SEC * (1 << r->shift);
- r->mult = div64_u64(factor, r->rate_bps);
}
}
EXPORT_SYMBOL(psched_ratecfg_precompute);
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 9facea03faeb..c4075610502c 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -114,7 +114,7 @@ struct hfsc_class {
struct gnet_stats_basic_packed bstats;
struct gnet_stats_queue qstats;
- struct gnet_stats_rate_est rate_est;
+ struct gnet_stats_rate_est64 rate_est;
unsigned int level; /* class level in hierarchy */
struct tcf_proto *filter_list; /* filter list */
unsigned int filter_cnt; /* filter count */
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index adaedd79389c..7954e73d118a 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -65,6 +65,10 @@ static int htb_hysteresis __read_mostly = 0; /* whether to use mode hysteresis f
module_param (htb_hysteresis, int, 0640);
MODULE_PARM_DESC(htb_hysteresis, "Hysteresis mode, less CPU load, less accurate");
+static int 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 */
@@ -72,23 +76,39 @@ enum htb_cmode {
HTB_CAN_SEND /* class can send */
};
-/* interior & leaf nodes; props specific to leaves are marked L: */
+/* 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;
- /* general class parameters */
- struct gnet_stats_basic_packed bstats;
- struct gnet_stats_queue qstats;
- struct gnet_stats_rate_est rate_est;
- struct tc_htb_xstats xstats; /* our special stats */
- int refcnt; /* usage count of this class */
+ struct psched_ratecfg rate;
+ struct psched_ratecfg ceil;
+ s64 buffer, cbuffer;/* token bucket depth/rate */
+ s64 mbuffer; /* max wait time */
+ int prio; /* these two are used only by leaves... */
+ int quantum; /* but stored for parent-to-leaf return */
+
+ struct tcf_proto *filter_list; /* class attached filters */
+ int filter_cnt;
+ int refcnt; /* usage count of this class */
- /* topology */
- int level; /* our level (see above) */
- unsigned int children;
- struct htb_class *parent; /* parent class */
+ int level; /* our level (see above) */
+ unsigned int children;
+ struct htb_class *parent; /* parent class */
+
+ struct gnet_stats_rate_est64 rate_est;
+
+ /*
+ * Written often fields
+ */
+ struct gnet_stats_basic_packed bstats;
+ struct gnet_stats_queue qstats;
+ struct tc_htb_xstats xstats; /* our special stats */
- int prio; /* these two are used only by leaves... */
- int quantum; /* but stored for parent-to-leaf return */
+ /* token bucket parameters */
+ s64 tokens, ctokens;/* current number of tokens */
+ s64 t_c; /* checkpoint time */
union {
struct htb_class_leaf {
@@ -107,24 +127,12 @@ struct htb_class {
u32 last_ptr_id[TC_HTB_NUMPRIO];
} inner;
} un;
- struct rb_node node[TC_HTB_NUMPRIO]; /* node for self or feed tree */
- struct rb_node pq_node; /* node for event queue */
- s64 pq_key;
-
- int prio_activity; /* for which prios are we active */
- enum htb_cmode cmode; /* current mode of the class */
-
- /* class attached filters */
- struct tcf_proto *filter_list;
- int filter_cnt;
+ s64 pq_key;
- /* token bucket parameters */
- struct psched_ratecfg rate;
- struct psched_ratecfg ceil;
- s64 buffer, cbuffer; /* token bucket depth/rate */
- s64 mbuffer; /* max wait time */
- s64 tokens, ctokens; /* current number of tokens */
- s64 t_c; /* checkpoint time */
+ 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 {
@@ -1366,12 +1374,14 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
if (!cl)
goto failure;
- err = gen_new_estimator(&cl->bstats, &cl->rate_est,
- qdisc_root_sleeping_lock(sch),
- tca[TCA_RATE] ? : &est.nla);
- if (err) {
- kfree(cl);
- goto failure;
+ if (htb_rate_est || tca[TCA_RATE]) {
+ err = gen_new_estimator(&cl->bstats, &cl->rate_est,
+ qdisc_root_sleeping_lock(sch),
+ tca[TCA_RATE] ? : &est.nla);
+ if (err) {
+ kfree(cl);
+ goto failure;
+ }
}
cl->refcnt = 1;
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index d51852bba01c..7c195d972bf0 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -138,7 +138,7 @@ struct qfq_class {
struct gnet_stats_basic_packed bstats;
struct gnet_stats_queue qstats;
- struct gnet_stats_rate_est rate_est;
+ struct gnet_stats_rate_est64 rate_est;
struct Qdisc *qdisc;
struct list_head alist; /* Link for active-classes list. */
struct qfq_aggregate *agg; /* Parent aggregate. */
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index e478d316602b..1aaf1b6e51a2 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -116,14 +116,57 @@ struct tbf_sched_data {
struct qdisc_watchdog watchdog; /* Watchdog timer */
};
+
+/* GSO packet is too big, segment it so that tbf can transmit
+ * each segment in time
+ */
+static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
+{
+ struct tbf_sched_data *q = qdisc_priv(sch);
+ struct sk_buff *segs, *nskb;
+ netdev_features_t features = netif_skb_features(skb);
+ int ret, nb;
+
+ segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+
+ if (IS_ERR_OR_NULL(segs))
+ return qdisc_reshape_fail(skb, sch);
+
+ nb = 0;
+ while (segs) {
+ nskb = segs->next;
+ segs->next = NULL;
+ if (likely(segs->len <= q->max_size)) {
+ qdisc_skb_cb(segs)->pkt_len = segs->len;
+ ret = qdisc_enqueue(segs, q->qdisc);
+ } else {
+ ret = qdisc_reshape_fail(skb, sch);
+ }
+ if (ret != NET_XMIT_SUCCESS) {
+ if (net_xmit_drop_count(ret))
+ sch->qstats.drops++;
+ } else {
+ nb++;
+ }
+ segs = nskb;
+ }
+ sch->q.qlen += nb;
+ if (nb > 1)
+ qdisc_tree_decrease_qlen(sch, 1 - nb);
+ consume_skb(skb);
+ return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
+}
+
static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
struct tbf_sched_data *q = qdisc_priv(sch);
int ret;
- if (qdisc_pkt_len(skb) > q->max_size)
+ if (qdisc_pkt_len(skb) > q->max_size) {
+ if (skb_is_gso(skb))
+ return tbf_segment(skb, sch);
return qdisc_reshape_fail(skb, sch);
-
+ }
ret = qdisc_enqueue(skb, q->qdisc);
if (ret != NET_XMIT_SUCCESS) {
if (net_xmit_drop_count(ret))