summaryrefslogtreecommitdiffstats
path: root/net/sched
diff options
context:
space:
mode:
Diffstat (limited to 'net/sched')
-rw-r--r--net/sched/Kconfig14
-rw-r--r--net/sched/Makefile1
-rw-r--r--net/sched/cls_cgroup.c39
-rw-r--r--net/sched/sch_api.c94
-rw-r--r--net/sched/sch_atm.c1
-rw-r--r--net/sched/sch_cbq.c1
-rw-r--r--net/sched/sch_choke.c3
-rw-r--r--net/sched/sch_fq.c793
-rw-r--r--net/sched/sch_generic.c28
-rw-r--r--net/sched/sch_htb.c15
-rw-r--r--net/sched/sch_mq.c2
-rw-r--r--net/sched/sch_mqprio.c2
-rw-r--r--net/sched/sch_netem.c5
-rw-r--r--net/sched/sch_qfq.c85
14 files changed, 1020 insertions, 63 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 235e01acac5..c03a32a0418 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -272,6 +272,20 @@ config NET_SCH_FQ_CODEL
If unsure, say N.
+config NET_SCH_FQ
+ tristate "Fair Queue"
+ help
+ Say Y here if you want to use the FQ packet scheduling algorithm.
+
+ FQ does flow separation, and is able to respect pacing requirements
+ set by TCP stack into sk->sk_pacing_rate (for localy generated
+ traffic)
+
+ To compile this driver as a module, choose M here: the module
+ will be called sch_fq.
+
+ If unsure, say N.
+
config NET_SCH_INGRESS
tristate "Ingress Qdisc"
depends on NET_CLS_ACT
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 978cbf004e8..e5f9abe9a5d 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o
obj-$(CONFIG_NET_SCH_QFQ) += sch_qfq.o
obj-$(CONFIG_NET_SCH_CODEL) += sch_codel.o
obj-$(CONFIG_NET_SCH_FQ_CODEL) += sch_fq_codel.o
+obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o
obj-$(CONFIG_NET_CLS_U32) += cls_u32.o
obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 3a294eb98d6..867b4a3e398 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -23,19 +23,18 @@
#include <net/sock.h>
#include <net/cls_cgroup.h>
-static inline struct cgroup_cls_state *cgrp_cls_state(struct cgroup *cgrp)
+static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css)
{
- return container_of(cgroup_subsys_state(cgrp, net_cls_subsys_id),
- struct cgroup_cls_state, css);
+ return css ? container_of(css, struct cgroup_cls_state, css) : NULL;
}
static inline struct cgroup_cls_state *task_cls_state(struct task_struct *p)
{
- return container_of(task_subsys_state(p, net_cls_subsys_id),
- struct cgroup_cls_state, css);
+ return css_cls_state(task_css(p, net_cls_subsys_id));
}
-static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp)
+static struct cgroup_subsys_state *
+cgrp_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct cgroup_cls_state *cs;
@@ -45,17 +44,19 @@ static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp)
return &cs->css;
}
-static int cgrp_css_online(struct cgroup *cgrp)
+static int cgrp_css_online(struct cgroup_subsys_state *css)
{
- if (cgrp->parent)
- cgrp_cls_state(cgrp)->classid =
- cgrp_cls_state(cgrp->parent)->classid;
+ struct cgroup_cls_state *cs = css_cls_state(css);
+ struct cgroup_cls_state *parent = css_cls_state(css_parent(css));
+
+ if (parent)
+ cs->classid = parent->classid;
return 0;
}
-static void cgrp_css_free(struct cgroup *cgrp)
+static void cgrp_css_free(struct cgroup_subsys_state *css)
{
- kfree(cgrp_cls_state(cgrp));
+ kfree(css_cls_state(css));
}
static int update_classid(const void *v, struct file *file, unsigned n)
@@ -67,12 +68,13 @@ static int update_classid(const void *v, struct file *file, unsigned n)
return 0;
}
-static void cgrp_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+static void cgrp_attach(struct cgroup_subsys_state *css,
+ struct cgroup_taskset *tset)
{
struct task_struct *p;
void *v;
- cgroup_taskset_for_each(p, cgrp, tset) {
+ cgroup_taskset_for_each(p, css, tset) {
task_lock(p);
v = (void *)(unsigned long)task_cls_classid(p);
iterate_fd(p->files, 0, update_classid, v);
@@ -80,14 +82,15 @@ static void cgrp_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
}
}
-static u64 read_classid(struct cgroup *cgrp, struct cftype *cft)
+static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft)
{
- return cgrp_cls_state(cgrp)->classid;
+ return css_cls_state(css)->classid;
}
-static int write_classid(struct cgroup *cgrp, struct cftype *cft, u64 value)
+static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
+ u64 value)
{
- cgrp_cls_state(cgrp)->classid = (u32) value;
+ css_cls_state(css)->classid = (u32) value;
return 0;
}
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 281c1bded1f..2adda7fa2d3 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -200,6 +200,58 @@ int unregister_qdisc(struct Qdisc_ops *qops)
}
EXPORT_SYMBOL(unregister_qdisc);
+/* Get default qdisc if not otherwise specified */
+void qdisc_get_default(char *name, size_t len)
+{
+ read_lock(&qdisc_mod_lock);
+ strlcpy(name, default_qdisc_ops->id, len);
+ read_unlock(&qdisc_mod_lock);
+}
+
+static struct Qdisc_ops *qdisc_lookup_default(const char *name)
+{
+ struct Qdisc_ops *q = NULL;
+
+ for (q = qdisc_base; q; q = q->next) {
+ if (!strcmp(name, q->id)) {
+ if (!try_module_get(q->owner))
+ q = NULL;
+ break;
+ }
+ }
+
+ return q;
+}
+
+/* Set new default qdisc to use */
+int qdisc_set_default(const char *name)
+{
+ const struct Qdisc_ops *ops;
+
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ write_lock(&qdisc_mod_lock);
+ ops = qdisc_lookup_default(name);
+ if (!ops) {
+ /* Not found, drop lock and try to load module */
+ write_unlock(&qdisc_mod_lock);
+ request_module("sch_%s", name);
+ write_lock(&qdisc_mod_lock);
+
+ ops = qdisc_lookup_default(name);
+ }
+
+ if (ops) {
+ /* Set new default */
+ module_put(default_qdisc_ops->owner);
+ default_qdisc_ops = ops;
+ }
+ write_unlock(&qdisc_mod_lock);
+
+ return ops ? 0 : -ENOENT;
+}
+
/* We know handle. Find qdisc among all qdisc's attached to device
(root qdisc, all its children, children of children etc.)
*/
@@ -285,6 +337,45 @@ static struct Qdisc_ops *qdisc_lookup_ops(struct nlattr *kind)
return q;
}
+/* The linklayer setting were not transferred from iproute2, in older
+ * versions, and the rate tables lookup systems have been dropped in
+ * the kernel. To keep backward compatible with older iproute2 tc
+ * utils, we detect the linklayer setting by detecting if the rate
+ * table were modified.
+ *
+ * For linklayer ATM table entries, the rate table will be aligned to
+ * 48 bytes, thus some table entries will contain the same value. The
+ * mpu (min packet unit) is also encoded into the old rate table, thus
+ * starting from the mpu, we find low and high table entries for
+ * mapping this cell. If these entries contain the same value, when
+ * the rate tables have been modified for linklayer ATM.
+ *
+ * This is done by rounding mpu to the nearest 48 bytes cell/entry,
+ * and then roundup to the next cell, calc the table entry one below,
+ * and compare.
+ */
+static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab)
+{
+ int low = roundup(r->mpu, 48);
+ int high = roundup(low+1, 48);
+ int cell_low = low >> r->cell_log;
+ int cell_high = (high >> r->cell_log) - 1;
+
+ /* rtab is too inaccurate at rates > 100Mbit/s */
+ if ((r->rate > (100000000/8)) || (rtab[0] == 0)) {
+ pr_debug("TC linklayer: Giving up ATM detection\n");
+ return TC_LINKLAYER_ETHERNET;
+ }
+
+ if ((cell_high > cell_low) && (cell_high < 256)
+ && (rtab[cell_low] == rtab[cell_high])) {
+ pr_debug("TC linklayer: Detected ATM, low(%d)=high(%d)=%u\n",
+ cell_low, cell_high, rtab[cell_high]);
+ return TC_LINKLAYER_ATM;
+ }
+ return TC_LINKLAYER_ETHERNET;
+}
+
static struct qdisc_rate_table *qdisc_rtab_list;
struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab)
@@ -308,6 +399,8 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *ta
rtab->rate = *r;
rtab->refcnt = 1;
memcpy(rtab->data, nla_data(tab), 1024);
+ if (r->linklayer == TC_LINKLAYER_UNAWARE)
+ r->linklayer = __detect_linklayer(r, rtab->data);
rtab->next = qdisc_rtab_list;
qdisc_rtab_list = rtab;
}
@@ -1813,6 +1906,7 @@ static int __init pktsched_init(void)
return err;
}
+ register_qdisc(&pfifo_fast_ops);
register_qdisc(&pfifo_qdisc_ops);
register_qdisc(&bfifo_qdisc_ops);
register_qdisc(&pfifo_head_drop_qdisc_ops);
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index ca8e0a57d94..1f9c31411f1 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -605,6 +605,7 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl,
struct sockaddr_atmpvc pvc;
int state;
+ memset(&pvc, 0, sizeof(pvc));
pvc.sap_family = AF_ATMPVC;
pvc.sap_addr.itf = flow->vcc->dev ? flow->vcc->dev->number : -1;
pvc.sap_addr.vpi = flow->vcc->vpi;
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 71a56886255..7a42c81a19e 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1465,6 +1465,7 @@ static int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl)
unsigned char *b = skb_tail_pointer(skb);
struct tc_cbq_wrropt opt;
+ memset(&opt, 0, sizeof(opt));
opt.flags = 0;
opt.allot = cl->allot;
opt.priority = cl->priority + 1;
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index ef53ab8d0aa..ddd73cb2d7b 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -438,7 +438,8 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
if (mask != q->tab_mask) {
struct sk_buff **ntab;
- ntab = kcalloc(mask + 1, sizeof(struct sk_buff *), GFP_KERNEL);
+ ntab = kcalloc(mask + 1, sizeof(struct sk_buff *),
+ GFP_KERNEL | __GFP_NOWARN);
if (!ntab)
ntab = vzalloc((mask + 1) * sizeof(struct sk_buff *));
if (!ntab)
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
new file mode 100644
index 00000000000..32ad015ee8c
--- /dev/null
+++ b/net/sched/sch_fq.c
@@ -0,0 +1,793 @@
+/*
+ * net/sched/sch_fq.c Fair Queue Packet Scheduler (per flow pacing)
+ *
+ * Copyright (C) 2013 Eric Dumazet <edumazet@google.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Meant to be mostly used for localy generated traffic :
+ * Fast classification depends on skb->sk being set before reaching us.
+ * If not, (router workload), we use rxhash as fallback, with 32 bits wide hash.
+ * All packets belonging to a socket are considered as a 'flow'.
+ *
+ * Flows are dynamically allocated and stored in a hash table of RB trees
+ * They are also part of one Round Robin 'queues' (new or old flows)
+ *
+ * Burst avoidance (aka pacing) capability :
+ *
+ * Transport (eg TCP) can set in sk->sk_pacing_rate a rate, enqueue a
+ * bunch of packets, and this packet scheduler adds delay between
+ * packets to respect rate limitation.
+ *
+ * enqueue() :
+ * - lookup one RB tree (out of 1024 or more) to find the flow.
+ * If non existent flow, create it, add it to the tree.
+ * Add skb to the per flow list of skb (fifo).
+ * - Use a special fifo for high prio packets
+ *
+ * dequeue() : serves flows in Round Robin
+ * Note : When a flow becomes empty, we do not immediately remove it from
+ * rb trees, for performance reasons (its expected to send additional packets,
+ * or SLAB cache will reuse socket for another flow)
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/jiffies.h>
+#include <linux/string.h>
+#include <linux/in.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/rbtree.h>
+#include <linux/hash.h>
+#include <linux/prefetch.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <net/sock.h>
+#include <net/tcp_states.h>
+
+/*
+ * Per flow structure, dynamically allocated
+ */
+struct fq_flow {
+ struct sk_buff *head; /* list of skbs for this flow : first skb */
+ union {
+ struct sk_buff *tail; /* last skb in the list */
+ unsigned long age; /* jiffies when flow was emptied, for gc */
+ };
+ struct rb_node fq_node; /* anchor in fq_root[] trees */
+ struct sock *sk;
+ int qlen; /* number of packets in flow queue */
+ int credit;
+ u32 socket_hash; /* sk_hash */
+ struct fq_flow *next; /* next pointer in RR lists, or &detached */
+
+ struct rb_node rate_node; /* anchor in q->delayed tree */
+ u64 time_next_packet;
+};
+
+struct fq_flow_head {
+ struct fq_flow *first;
+ struct fq_flow *last;
+};
+
+struct fq_sched_data {
+ struct fq_flow_head new_flows;
+
+ struct fq_flow_head old_flows;
+
+ struct rb_root delayed; /* for rate limited flows */
+ u64 time_next_delayed_flow;
+
+ struct fq_flow internal; /* for non classified or high prio packets */
+ u32 quantum;
+ u32 initial_quantum;
+ u32 flow_default_rate;/* rate per flow : bytes per second */
+ u32 flow_max_rate; /* optional max rate per flow */
+ u32 flow_plimit; /* max packets per flow */
+ struct rb_root *fq_root;
+ u8 rate_enable;
+ u8 fq_trees_log;
+
+ u32 flows;
+ u32 inactive_flows;
+ u32 throttled_flows;
+
+ u64 stat_gc_flows;
+ u64 stat_internal_packets;
+ u64 stat_tcp_retrans;
+ u64 stat_throttled;
+ u64 stat_flows_plimit;
+ u64 stat_pkts_too_long;
+ u64 stat_allocation_errors;
+ struct qdisc_watchdog watchdog;
+};
+
+/* special value to mark a detached flow (not on old/new list) */
+static struct fq_flow detached, throttled;
+
+static void fq_flow_set_detached(struct fq_flow *f)
+{
+ f->next = &detached;
+}
+
+static bool fq_flow_is_detached(const struct fq_flow *f)
+{
+ return f->next == &detached;
+}
+
+static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f)
+{
+ struct rb_node **p = &q->delayed.rb_node, *parent = NULL;
+
+ while (*p) {
+ struct fq_flow *aux;
+
+ parent = *p;
+ aux = container_of(parent, struct fq_flow, rate_node);
+ if (f->time_next_packet >= aux->time_next_packet)
+ p = &parent->rb_right;
+ else
+ p = &parent->rb_left;
+ }
+ rb_link_node(&f->rate_node, parent, p);
+ rb_insert_color(&f->rate_node, &q->delayed);
+ q->throttled_flows++;
+ q->stat_throttled++;
+
+ f->next = &throttled;
+ if (q->time_next_delayed_flow > f->time_next_packet)
+ q->time_next_delayed_flow = f->time_next_packet;
+}
+
+
+static struct kmem_cache *fq_flow_cachep __read_mostly;
+
+static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow)
+{
+ if (head->first)
+ head->last->next = flow;
+ else
+ head->first = flow;
+ head->last = flow;
+ flow->next = NULL;
+}
+
+/* limit number of collected flows per round */
+#define FQ_GC_MAX 8
+#define FQ_GC_AGE (3*HZ)
+
+static bool fq_gc_candidate(const struct fq_flow *f)
+{
+ return fq_flow_is_detached(f) &&
+ time_after(jiffies, f->age + FQ_GC_AGE);
+}
+
+static void fq_gc(struct fq_sched_data *q,
+ struct rb_root *root,
+ struct sock *sk)
+{
+ struct fq_flow *f, *tofree[FQ_GC_MAX];
+ struct rb_node **p, *parent;
+ int fcnt = 0;
+
+ p = &root->rb_node;
+ parent = NULL;
+ while (*p) {
+ parent = *p;
+
+ f = container_of(parent, struct fq_flow, fq_node);
+ if (f->sk == sk)
+ break;
+
+ if (fq_gc_candidate(f)) {
+ tofree[fcnt++] = f;
+ if (fcnt == FQ_GC_MAX)
+ break;
+ }
+
+ if (f->sk > sk)
+ p = &parent->rb_right;
+ else
+ p = &parent->rb_left;
+ }
+
+ q->flows -= fcnt;
+ q->inactive_flows -= fcnt;
+ q->stat_gc_flows += fcnt;
+ while (fcnt) {
+ struct fq_flow *f = tofree[--fcnt];
+
+ rb_erase(&f->fq_node, root);
+ kmem_cache_free(fq_flow_cachep, f);
+ }
+}
+
+static const u8 prio2band[TC_PRIO_MAX + 1] = {
+ 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1
+};
+
+static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
+{
+ struct rb_node **p, *parent;
+ struct sock *sk = skb->sk;
+ struct rb_root *root;
+ struct fq_flow *f;
+ int band;
+
+ /* warning: no starvation prevention... */
+ band = prio2band[skb->priority & TC_PRIO_MAX];
+ if (unlikely(band == 0))
+ return &q->internal;
+
+ if (unlikely(!sk)) {
+ /* By forcing low order bit to 1, we make sure to not
+ * collide with a local flow (socket pointers are word aligned)
+ */
+ sk = (struct sock *)(skb_get_rxhash(skb) | 1L);
+ }
+
+ root = &q->fq_root[hash_32((u32)(long)sk, q->fq_trees_log)];
+
+ if (q->flows >= (2U << q->fq_trees_log) &&
+ q->inactive_flows > q->flows/2)
+ fq_gc(q, root, sk);
+
+ p = &root->rb_node;
+ parent = NULL;
+ while (*p) {
+ parent = *p;
+
+ f = container_of(parent, struct fq_flow, fq_node);
+ if (f->sk == sk) {
+ /* socket might have been reallocated, so check
+ * if its sk_hash is the same.
+ * It not, we need to refill credit with
+ * initial quantum
+ */
+ if (unlikely(skb->sk &&
+ f->socket_hash != sk->sk_hash)) {
+ f->credit = q->initial_quantum;
+ f->socket_hash = sk->sk_hash;
+ }
+ return f;
+ }
+ if (f->sk > sk)
+ p = &parent->rb_right;
+ else
+ p = &parent->rb_left;
+ }
+
+ f = kmem_cache_zalloc(fq_flow_cachep, GFP_ATOMIC | __GFP_NOWARN);
+ if (unlikely(!f)) {
+ q->stat_allocation_errors++;
+ return &q->internal;
+ }
+ fq_flow_set_detached(f);
+ f->sk = sk;
+ if (skb->sk)
+ f->socket_hash = sk->sk_hash;
+ f->credit = q->initial_quantum;
+
+ rb_link_node(&f->fq_node, parent, p);
+ rb_insert_color(&f->fq_node, root);
+
+ q->flows++;
+ q->inactive_flows++;
+ return f;
+}
+
+
+/* remove one skb from head of flow queue */
+static struct sk_buff *fq_dequeue_head(struct fq_flow *flow)
+{
+ struct sk_buff *skb = flow->head;
+
+ if (skb) {
+ flow->head = skb->next;
+ skb->next = NULL;
+ flow->qlen--;
+ }
+ return skb;
+}
+
+/* We might add in the future detection of retransmits
+ * For the time being, just return false
+ */
+static bool skb_is_retransmit(struct sk_buff *skb)
+{
+ return false;
+}
+
+/* add skb to flow queue
+ * flow queue is a linked list, kind of FIFO, except for TCP retransmits
+ * We special case tcp retransmits to be transmitted before other packets.
+ * We rely on fact that TCP retransmits are unlikely, so we do not waste
+ * a separate queue or a pointer.
+ * head-> [retrans pkt 1]
+ * [retrans pkt 2]
+ * [ normal pkt 1]
+ * [ normal pkt 2]
+ * [ normal pkt 3]
+ * tail-> [ normal pkt 4]
+ */
+static void flow_queue_add(struct fq_flow *flow, struct sk_buff *skb)
+{
+ struct sk_buff *prev, *head = flow->head;
+
+ skb->next = NULL;
+ if (!head) {
+ flow->head = skb;
+ flow->tail = skb;
+ return;
+ }
+ if (likely(!skb_is_retransmit(skb))) {
+ flow->tail->next = skb;
+ flow->tail = skb;
+ return;
+ }
+
+ /* This skb is a tcp retransmit,
+ * find the last retrans packet in the queue
+ */
+ prev = NULL;
+ while (skb_is_retransmit(head)) {
+ prev = head;
+ head = head->next;
+ if (!head)
+ break;
+ }
+ if (!prev) { /* no rtx packet in queue, become the new head */
+ skb->next = flow->head;
+ flow->head = skb;
+ } else {
+ if (prev == flow->tail)
+ flow->tail = skb;
+ else
+ skb->next = prev->next;
+ prev->next = skb;
+ }
+}
+
+static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+{
+ struct fq_sched_data *q = qdisc_priv(sch);
+ struct fq_flow *f;
+
+ if (unlikely(sch->q.qlen >= sch->limit))
+ return qdisc_drop(skb, sch);
+
+ f = fq_classify(skb, q);
+ if (unlikely(f->qlen >= q->flow_plimit && f != &q->internal)) {
+ q->stat_flows_plimit++;
+ return qdisc_drop(skb, sch);
+ }
+
+ f->qlen++;
+ flow_queue_add(f, skb);
+ if (skb_is_retransmit(skb))
+ q->stat_tcp_retrans++;
+ sch->qstats.backlog += qdisc_pkt_len(skb);
+ if (fq_flow_is_detached(f)) {
+ fq_flow_add_tail(&q->new_flows, f);
+ if (q->quantum > f->credit)
+ f->credit = q->quantum;
+ q->inactive_flows--;
+ qdisc_unthrottled(sch);
+ }
+ if (unlikely(f == &q->internal)) {
+ q->stat_internal_packets++;
+ qdisc_unthrottled(sch);
+ }
+ sch->q.qlen++;
+
+ return NET_XMIT_SUCCESS;
+}
+
+static void fq_check_throttled(struct fq_sched_data *q, u64 now)
+{
+ struct rb_node *p;
+
+ if (q->time_next_delayed_flow > now)
+ return;
+
+ q->time_next_delayed_flow = ~0ULL;
+ while ((p = rb_first(&q->delayed)) != NULL) {
+ struct fq_flow *f = container_of(p, struct fq_flow, rate_node);
+
+ if (f->time_next_packet > now) {
+ q->time_next_delayed_flow = f->time_next_packet;
+ break;
+ }
+ rb_erase(p, &q->delayed);
+ q->throttled_flows--;
+ fq_flow_add_tail(&q->old_flows, f);
+ }
+}
+
+static struct sk_buff *fq_dequeue(struct Qdisc *sch)
+{
+ struct fq_sched_data *q = qdisc_priv(sch);
+ u64 now = ktime_to_ns(ktime_get());
+ struct fq_flow_head *head;
+ struct sk_buff *skb;
+ struct fq_flow *f;
+
+ skb = fq_dequeue_head(&q->internal);
+ if (skb)
+ goto out;
+ fq_check_throttled(q, now);
+begin:
+ head = &q->new_flows;
+ if (!head->first) {
+ head = &q->old_flows;
+ if (!head->first) {
+ if (q->time_next_delayed_flow != ~0ULL)
+ qdisc_watchdog_schedule_ns(&q->watchdog,
+ q->time_next_delayed_flow);
+ return NULL;
+ }
+ }
+ f = head->first;
+
+ if (f->credit <= 0) {
+ f->credit += q->quantum;
+ head->first = f->next;
+ fq_flow_add_tail(&q->old_flows, f);
+ goto begin;
+ }
+
+ if (unlikely(f->head && now < f->time_next_packet)) {
+ head->first = f->next;
+ fq_flow_set_throttled(q, f);
+ goto begin;
+ }
+
+ skb = fq_dequeue_head(f);
+ if (!skb) {
+ head->first = f->next;
+ /* force a pass through old_flows to prevent starvation */
+ if ((head == &q->new_flows) && q->old_flows.first) {
+ fq_flow_add_tail(&q->old_flows, f);
+ } else {
+ fq_flow_set_detached(f);
+ f->age = jiffies;
+ q->inactive_flows++;
+ }
+ goto begin;
+ }
+ prefetch(&skb->end);
+ f->time_next_packet = now;
+ f->credit -= qdisc_pkt_len(skb);
+
+ if (f->credit <= 0 &&
+ q->rate_enable &&
+ skb->sk && skb->sk->sk_state != TCP_TIME_WAIT) {
+ u32 rate = skb->sk->sk_pacing_rate ?: q->flow_default_rate;
+
+ rate = min(rate, q->flow_max_rate);
+ if (rate) {
+ u64 len = (u64)qdisc_pkt_len(skb) * NSEC_PER_SEC;
+
+ do_div(len, rate);
+ /* Since socket rate can change later,
+ * clamp the delay to 125 ms.
+ * TODO: maybe segment the too big skb, as in commit
+ * e43ac79a4bc ("sch_tbf: segment too big GSO packets")
+ */
+ if (unlikely(len > 125 * NSEC_PER_MSEC)) {
+ len = 125 * NSEC_PER_MSEC;
+ q->stat_pkts_too_long++;
+ }
+
+ f->time_next_packet = now + len;
+ }
+ }
+out:
+ sch->qstats.backlog -= qdisc_pkt_len(skb);
+ qdisc_bstats_update(sch, skb);
+ sch->q.qlen--;
+ qdisc_unthrottled(sch);
+ return skb;
+}
+
+static void fq_reset(struct Qdisc *sch)
+{
+ struct sk_buff *skb;
+
+ while ((skb = fq_dequeue(sch)) != NULL)
+ kfree_skb(skb);
+}
+
+static void fq_rehash(struct fq_sched_data *q,
+ struct rb_root *old_array, u32 old_log,
+ struct rb_root *new_array, u32 new_log)
+{
+ struct rb_node *op, **np, *parent;
+ struct rb_root *oroot, *nroot;
+ struct fq_flow *of, *nf;
+ int fcnt = 0;
+ u32 idx;
+
+ for (idx = 0; idx < (1U << old_log); idx++) {
+ oroot = &old_array[idx];
+ while ((op = rb_first(oroot)) != NULL) {
+ rb_erase(op, oroot);
+ of = container_of(op, struct fq_flow, fq_node);
+ if (fq_gc_candidate(of)) {
+ fcnt++;
+ kmem_cache_free(fq_flow_cachep, of);
+ continue;
+ }
+ nroot = &new_array[hash_32((u32)(long)of->sk, new_log)];
+
+ np = &nroot->rb_node;
+ parent = NULL;
+ while (*np) {
+ parent = *np;
+
+ nf = container_of(parent, struct fq_flow, fq_node);
+ BUG_ON(nf->sk == of->sk);
+
+ if (nf->sk > of->sk)
+ np = &parent->rb_right;
+ else
+ np = &parent->rb_left;
+ }
+
+ rb_link_node(&of->fq_node, parent, np);
+ rb_insert_color(&of->fq_node, nroot);
+ }
+ }
+ q->flows -= fcnt;
+ q->inactive_flows -= fcnt;
+ q->stat_gc_flows += fcnt;
+}
+
+static int fq_resize(struct fq_sched_data *q, u32 log)
+{
+ struct rb_root *array;
+ u32 idx;
+
+ if (q->fq_root && log == q->fq_trees_log)
+ return 0;
+
+ array = kmalloc(sizeof(struct rb_root) << log, GFP_KERNEL);
+ if (!array)
+ return -ENOMEM;
+
+ for (idx = 0; idx < (1U << log); idx++)
+ array[idx] = RB_ROOT;
+
+ if (q->fq_root) {
+ fq_rehash(q, q->fq_root, q->fq_trees_log, array, log);
+ kfree(q->fq_root);
+ }
+ q->fq_root = array;
+ q->fq_trees_log = log;
+
+ return 0;
+}
+
+static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = {
+ [TCA_FQ_PLIMIT] = { .type = NLA_U32 },
+ [TCA_FQ_FLOW_PLIMIT] = { .type = NLA_U32 },
+ [TCA_FQ_QUANTUM] = { .type = NLA_U32 },
+ [TCA_FQ_INITIAL_QUANTUM] = { .type = NLA_U32 },
+ [TCA_FQ_RATE_ENABLE] = { .type = NLA_U32 },
+ [TCA_FQ_FLOW_DEFAULT_RATE] = { .type = NLA_U32 },
+ [TCA_FQ_FLOW_MAX_RATE] = { .type = NLA_U32 },
+ [TCA_FQ_BUCKETS_LOG] = { .type = NLA_U32 },
+};
+
+static int fq_change(struct Qdisc *sch, struct nlattr *opt)
+{
+ struct fq_sched_data *q = qdisc_priv(sch);
+ struct nlattr *tb[TCA_FQ_MAX + 1];
+ int err, drop_count = 0;
+ u32 fq_log;
+
+ if (!opt)
+ return -EINVAL;
+
+ err = nla_parse_nested(tb, TCA_FQ_MAX, opt, fq_policy);
+ if (err < 0)
+ return err;
+
+ sch_tree_lock(sch);
+
+ fq_log = q->fq_trees_log;
+
+ if (tb[TCA_FQ_BUCKETS_LOG]) {
+ u32 nval = nla_get_u32(tb[TCA_FQ_BUCKETS_LOG]);
+
+ if (nval >= 1 && nval <= ilog2(256*1024))
+ fq_log = nval;
+ else
+ err = -EINVAL;
+ }
+ if (tb[TCA_FQ_PLIMIT])
+ sch->limit = nla_get_u32(tb[TCA_FQ_PLIMIT]);
+
+ if (tb[TCA_FQ_FLOW_PLIMIT])
+ q->flow_plimit = nla_get_u32(tb[TCA_FQ_FLOW_PLIMIT]);
+
+ if (tb[TCA_FQ_QUANTUM])
+ q->quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]);
+
+ if (tb[TCA_FQ_INITIAL_QUANTUM])
+ q->quantum = nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM]);
+
+ if (tb[TCA_FQ_FLOW_DEFAULT_RATE])
+ q->flow_default_rate = nla_get_u32(tb[TCA_FQ_FLOW_DEFAULT_RATE]);
+
+ if (tb[TCA_FQ_FLOW_MAX_RATE])
+ q->flow_max_rate = nla_get_u32(tb[TCA_FQ_FLOW_MAX_RATE]);
+
+ if (tb[TCA_FQ_RATE_ENABLE]) {
+ u32 enable = nla_get_u32(tb[TCA_FQ_RATE_ENABLE]);
+
+ if (enable <= 1)
+ q->rate_enable = enable;
+ else
+ err = -EINVAL;
+ }
+
+ if (!err)
+ err = fq_resize(q, fq_log);
+
+ while (sch->q.qlen > sch->limit) {
+ struct sk_buff *skb = fq_dequeue(sch);
+
+ kfree_skb(skb);
+ drop_count++;
+ }
+ qdisc_tree_decrease_qlen(sch, drop_count);
+
+ sch_tree_unlock(sch);
+ return err;
+}
+
+static void fq_destroy(struct Qdisc *sch)
+{
+ struct fq_sched_data *q = qdisc_priv(sch);
+ struct rb_root *root;
+ struct rb_node *p;
+ unsigned int idx;
+
+ if (q->fq_root) {
+ for (idx = 0; idx < (1U << q->fq_trees_log); idx++) {
+ root = &q->fq_root[idx];
+ while ((p = rb_first(root)) != NULL) {
+ rb_erase(p, root);
+ kmem_cache_free(fq_flow_cachep,
+ container_of(p, struct fq_flow, fq_node));
+ }
+ }
+ kfree(q->fq_root);
+ }
+ qdisc_watchdog_cancel(&q->watchdog);
+}
+
+static int fq_init(struct Qdisc *sch, struct nlattr *opt)
+{
+ struct fq_sched_data *q = qdisc_priv(sch);
+ int err;
+
+ sch->limit = 10000;
+ q->flow_plimit = 100;
+ q->quantum = 2 * psched_mtu(qdisc_dev(sch));
+ q->initial_quantum = 10 * psched_mtu(qdisc_dev(sch));
+ q->flow_default_rate = 0;
+ q->flow_max_rate = ~0U;
+ q->rate_enable = 1;
+ q->new_flows.first = NULL;
+ q->old_flows.first = NULL;
+ q->delayed = RB_ROOT;
+ q->fq_root = NULL;
+ q->fq_trees_log = ilog2(1024);
+ qdisc_watchdog_init(&q->watchdog, sch);
+
+ if (opt)
+ err = fq_change(sch, opt);
+ else
+ err = fq_resize(q, q->fq_trees_log);
+
+ return err;
+}
+
+static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+ struct fq_sched_data *q = qdisc_priv(sch);
+ struct nlattr *opts;
+
+ opts = nla_nest_start(skb, TCA_OPTIONS);
+ if (opts == NULL)
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_FQ_PLIMIT, sch->limit) ||
+ nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT, q->flow_plimit) ||
+ nla_put_u32(skb, TCA_FQ_QUANTUM, q->quantum) ||
+ nla_put_u32(skb, TCA_FQ_INITIAL_QUANTUM, q->initial_quantum) ||
+ nla_put_u32(skb, TCA_FQ_RATE_ENABLE, q->rate_enable) ||
+ nla_put_u32(skb, TCA_FQ_FLOW_DEFAULT_RATE, q->flow_default_rate) ||
+ nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, q->flow_max_rate) ||
+ nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, opts);
+ return skb->len;
+
+nla_put_failure:
+ return -1;
+}
+
+static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+ struct fq_sched_data *q = qdisc_priv(sch);
+ u64 now = ktime_to_ns(ktime_get());
+ struct tc_fq_qd_stats st = {
+ .gc_flows = q->stat_gc_flows,
+ .highprio_packets = q->stat_internal_packets,
+ .tcp_retrans = q->stat_tcp_retrans,
+ .throttled = q->stat_throttled,
+ .flows_plimit = q->stat_flows_plimit,
+ .pkts_too_long = q->stat_pkts_too_long,
+ .allocation_errors = q->stat_allocation_errors,
+ .flows = q->flows,
+ .inactive_flows = q->inactive_flows,
+ .throttled_flows = q->throttled_flows,
+ .time_next_delayed_flow = q->time_next_delayed_flow - now,
+ };
+
+ return gnet_stats_copy_app(d, &st, sizeof(st));
+}
+
+static struct Qdisc_ops fq_qdisc_ops __read_mostly = {
+ .id = "fq",
+ .priv_size = sizeof(struct fq_sched_data),
+
+ .enqueue = fq_enqueue,
+ .dequeue = fq_dequeue,
+ .peek = qdisc_peek_dequeued,
+ .init = fq_init,
+ .reset = fq_reset,
+ .destroy = fq_destroy,
+ .change = fq_change,
+ .dump = fq_dump,
+ .dump_stats = fq_dump_stats,
+ .owner = THIS_MODULE,
+};
+
+static int __init fq_module_init(void)
+{
+ int ret;
+
+ fq_flow_cachep = kmem_cache_create("fq_flow_cache",
+ sizeof(struct fq_flow),
+ 0, 0, NULL);
+ if (!fq_flow_cachep)
+ return -ENOMEM;
+
+ ret = register_qdisc(&fq_qdisc_ops);
+ if (ret)
+ kmem_cache_destroy(fq_flow_cachep);
+ return ret;
+}
+
+static void __exit fq_module_exit(void)
+{
+ unregister_qdisc(&fq_qdisc_ops);
+ kmem_cache_destroy(fq_flow_cachep);
+}
+
+module_init(fq_module_init)
+module_exit(fq_module_exit)
+MODULE_AUTHOR("Eric Dumazet");
+MODULE_LICENSE("GPL");
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 4626cef4b76..a74e278654a 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -25,10 +25,15 @@
#include <linux/rcupdate.h>
#include <linux/list.h>
#include <linux/slab.h>
+#include <linux/if_vlan.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
#include <net/dst.h>
+/* Qdisc to use by default */
+const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops;
+EXPORT_SYMBOL(default_qdisc_ops);
+
/* Main transmission queue. */
/* Modifications to data participating in scheduling must be protected with
@@ -207,15 +212,19 @@ void __qdisc_run(struct Qdisc *q)
unsigned long dev_trans_start(struct net_device *dev)
{
- unsigned long val, res = dev->trans_start;
+ unsigned long val, res;
unsigned int i;
+ if (is_vlan_dev(dev))
+ dev = vlan_dev_real_dev(dev);
+ res = dev->trans_start;
for (i = 0; i < dev->num_tx_queues; i++) {
val = netdev_get_tx_queue(dev, i)->trans_start;
if (val && time_after(val, res))
res = val;
}
dev->trans_start = res;
+
return res;
}
EXPORT_SYMBOL(dev_trans_start);
@@ -525,12 +534,11 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = {
.dump = pfifo_fast_dump,
.owner = THIS_MODULE,
};
-EXPORT_SYMBOL(pfifo_fast_ops);
static struct lock_class_key qdisc_tx_busylock;
struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
- struct Qdisc_ops *ops)
+ const struct Qdisc_ops *ops)
{
void *p;
struct Qdisc *sch;
@@ -574,10 +582,14 @@ errout:
}
struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
- struct Qdisc_ops *ops, unsigned int parentid)
+ const struct Qdisc_ops *ops,
+ unsigned int parentid)
{
struct Qdisc *sch;
+ if (!try_module_get(ops->owner))
+ goto errout;
+
sch = qdisc_alloc(dev_queue, ops);
if (IS_ERR(sch))
goto errout;
@@ -681,7 +693,7 @@ static void attach_one_default_qdisc(struct net_device *dev,
if (dev->tx_queue_len) {
qdisc = qdisc_create_dflt(dev_queue,
- &pfifo_fast_ops, TC_H_ROOT);
+ default_qdisc_ops, TC_H_ROOT);
if (!qdisc) {
netdev_info(dev, "activation failed\n");
return;
@@ -734,9 +746,8 @@ void dev_activate(struct net_device *dev)
int need_watchdog;
/* No queueing discipline is attached to device;
- create default one i.e. pfifo_fast for devices,
- which need queueing and noqueue_qdisc for
- virtual interfaces
+ * create default one for devices, which need queueing
+ * and noqueue_qdisc for virtual interfaces
*/
if (dev->qdisc == &noop_qdisc)
@@ -904,6 +915,7 @@ void psched_ratecfg_precompute(struct psched_ratecfg *r,
memset(r, 0, sizeof(*r));
r->overhead = conf->overhead;
r->rate_bytes_ps = conf->rate;
+ r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK);
r->mult = 1;
/*
* The deal here is to replace a divide by a reciprocal one
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index c2124ea29f4..c2178b15ca6 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -100,7 +100,7 @@ struct htb_class {
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... */
+ u32 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 */
@@ -1329,6 +1329,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
struct htb_sched *q = qdisc_priv(sch);
struct htb_class *cl = (struct htb_class *)*arg, *parent;
struct nlattr *opt = tca[TCA_OPTIONS];
+ struct qdisc_rate_table *rtab = NULL, *ctab = NULL;
struct nlattr *tb[TCA_HTB_MAX + 1];
struct tc_htb_opt *hopt;
@@ -1350,6 +1351,18 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
if (!hopt->rate.rate || !hopt->ceil.rate)
goto failure;
+ /* Keeping backward compatible with rate_table based iproute2 tc */
+ if (hopt->rate.linklayer == TC_LINKLAYER_UNAWARE) {
+ rtab = qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB]);
+ if (rtab)
+ qdisc_put_rtab(rtab);
+ }
+ if (hopt->ceil.linklayer == TC_LINKLAYER_UNAWARE) {
+ ctab = qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB]);
+ if (ctab)
+ qdisc_put_rtab(ctab);
+ }
+
if (!cl) { /* new class */
struct Qdisc *new_q;
int prio;
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index 5da78a19ac9..2e56185736d 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -57,7 +57,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt)
for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
dev_queue = netdev_get_tx_queue(dev, ntx);
- qdisc = qdisc_create_dflt(dev_queue, &pfifo_fast_ops,
+ qdisc = qdisc_create_dflt(dev_queue, default_qdisc_ops,
TC_H_MAKE(TC_H_MAJ(sch->handle),
TC_H_MIN(ntx + 1)));
if (qdisc == NULL)
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index accec33c454..d44c868cb53 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -124,7 +124,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
for (i = 0; i < dev->num_tx_queues; i++) {
dev_queue = netdev_get_tx_queue(dev, i);
- qdisc = qdisc_create_dflt(dev_queue, &pfifo_fast_ops,
+ qdisc = qdisc_create_dflt(dev_queue, default_qdisc_ops,
TC_H_MAKE(TC_H_MAJ(sch->handle),
TC_H_MIN(i + 1)));
if (qdisc == NULL) {
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 82f6016d89a..a6d788d4521 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -412,12 +412,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
/* If a delay is expected, orphan the skb. (orphaning usually takes
* place at TX completion time, so _before_ the link transit delay)
- * Ideally, this orphaning should be done after the rate limiting
- * module, because this breaks TCP Small Queue, and other mechanisms
- * based on socket sk_wmem_alloc.
*/
if (q->latency || q->jitter)
- skb_orphan(skb);
+ skb_orphan_partial(skb);
/*
* If we need to duplicate packet, then re-insert at top of the
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index a7ab323849b..8056fb4e618 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -113,7 +113,6 @@
#define FRAC_BITS 30 /* fixed point arithmetic */
#define ONE_FP (1UL << FRAC_BITS)
-#define IWSUM (ONE_FP/QFQ_MAX_WSUM)
#define QFQ_MTU_SHIFT 16 /* to support TSO/GSO */
#define QFQ_MIN_LMAX 512 /* see qfq_slot_insert */
@@ -189,6 +188,7 @@ struct qfq_sched {
struct qfq_aggregate *in_serv_agg; /* Aggregate being served. */
u32 num_active_agg; /* Num. of active aggregates */
u32 wsum; /* weight sum */
+ u32 iwsum; /* inverse weight sum */
unsigned long bitmaps[QFQ_MAX_STATE]; /* Group bitmaps. */
struct qfq_group groups[QFQ_MAX_INDEX + 1]; /* The groups. */
@@ -314,6 +314,7 @@ static void qfq_update_agg(struct qfq_sched *q, struct qfq_aggregate *agg,
q->wsum +=
(int) agg->class_weight * (new_num_classes - agg->num_classes);
+ q->iwsum = ONE_FP / q->wsum;
agg->num_classes = new_num_classes;
}
@@ -340,6 +341,10 @@ static void qfq_destroy_agg(struct qfq_sched *q, struct qfq_aggregate *agg)
{
if (!hlist_unhashed(&agg->nonfull_next))
hlist_del_init(&agg->nonfull_next);
+ q->wsum -= agg->class_weight;
+ if (q->wsum != 0)
+ q->iwsum = ONE_FP / q->wsum;
+
if (q->in_serv_agg == agg)
q->in_serv_agg = qfq_choose_next_agg(q);
kfree(agg);
@@ -834,38 +839,60 @@ static void qfq_make_eligible(struct qfq_sched *q)
}
}
-
/*
- * The index of the slot in which the aggregate is to be inserted must
- * not be higher than QFQ_MAX_SLOTS-2. There is a '-2' and not a '-1'
- * because the start time of the group may be moved backward by one
- * slot after the aggregate has been inserted, and this would cause
- * non-empty slots to be right-shifted by one position.
+ * The index of the slot in which the input aggregate agg is to be
+ * inserted must not be higher than QFQ_MAX_SLOTS-2. There is a '-2'
+ * and not a '-1' because the start time of the group may be moved
+ * backward by one slot after the aggregate has been inserted, and
+ * this would cause non-empty slots to be right-shifted by one
+ * position.
+ *
+ * QFQ+ fully satisfies this bound to the slot index if the parameters
+ * of the classes are not changed dynamically, and if QFQ+ never
+ * happens to postpone the service of agg unjustly, i.e., it never
+ * happens that the aggregate becomes backlogged and eligible, or just
+ * eligible, while an aggregate with a higher approximated finish time
+ * is being served. In particular, in this case QFQ+ guarantees that
+ * the timestamps of agg are low enough that the slot index is never
+ * higher than 2. Unfortunately, QFQ+ cannot provide the same
+ * guarantee if it happens to unjustly postpone the service of agg, or
+ * if the parameters of some class are changed.
+ *
+ * As for the first event, i.e., an out-of-order service, the
+ * upper bound to the slot index guaranteed by QFQ+ grows to
+ * 2 +
+ * QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) *
+ * (current_max_weight/current_wsum) <= 2 + 8 * 128 * 1.
*
- * If the weight and lmax (max_pkt_size) of the classes do not change,
- * then QFQ+ does meet the above contraint according to the current
- * values of its parameters. In fact, if the weight and lmax of the
- * classes do not change, then, from the theory, QFQ+ guarantees that
- * the slot index is never higher than
- * 2 + QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) *
- * (QFQ_MAX_WEIGHT/QFQ_MAX_WSUM) = 2 + 8 * 128 * (1 / 64) = 18
+ * The following function deals with this problem by backward-shifting
+ * the timestamps of agg, if needed, so as to guarantee that the slot
+ * index is never higher than QFQ_MAX_SLOTS-2. This backward-shift may
+ * cause the service of other aggregates to be postponed, yet the
+ * worst-case guarantees of these aggregates are not violated. In
+ * fact, in case of no out-of-order service, the timestamps of agg
+ * would have been even lower than they are after the backward shift,
+ * because QFQ+ would have guaranteed a maximum value equal to 2 for
+ * the slot index, and 2 < QFQ_MAX_SLOTS-2. Hence the aggregates whose
+ * service is postponed because of the backward-shift would have
+ * however waited for the service of agg before being served.
*
- * When the weight of a class is increased or the lmax of the class is
- * decreased, a new aggregate with smaller slot size than the original
- * parent aggregate of the class may happen to be activated. The
- * activation of this aggregate should be properly delayed to when the
- * service of the class has finished in the ideal system tracked by
- * QFQ+. If the activation of the aggregate is not delayed to this
- * reference time instant, then this aggregate may be unjustly served
- * before other aggregates waiting for service. This may cause the
- * above bound to the slot index to be violated for some of these
- * unlucky aggregates.
+ * The other event that may cause the slot index to be higher than 2
+ * for agg is a recent change of the parameters of some class. If the
+ * weight of a class is increased or the lmax (max_pkt_size) of the
+ * class is decreased, then a new aggregate with smaller slot size
+ * than the original parent aggregate of the class may happen to be
+ * activated. The activation of this aggregate should be properly
+ * delayed to when the service of the class has finished in the ideal
+ * system tracked by QFQ+. If the activation of the aggregate is not
+ * delayed to this reference time instant, then this aggregate may be
+ * unjustly served before other aggregates waiting for service. This
+ * may cause the above bound to the slot index to be violated for some
+ * of these unlucky aggregates.
*
* Instead of delaying the activation of the new aggregate, which is
- * quite complex, the following inaccurate but simple solution is used:
- * if the slot index is higher than QFQ_MAX_SLOTS-2, then the
- * timestamps of the aggregate are shifted backward so as to let the
- * slot index become equal to QFQ_MAX_SLOTS-2.
+ * quite complex, the above-discussed capping of the slot index is
+ * used to handle also the consequences of a change of the parameters
+ * of a class.
*/
static void qfq_slot_insert(struct qfq_group *grp, struct qfq_aggregate *agg,
u64 roundedS)
@@ -1136,7 +1163,7 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
else
in_serv_agg->budget -= len;
- q->V += (u64)len * IWSUM;
+ q->V += (u64)len * q->iwsum;
pr_debug("qfq dequeue: len %u F %lld now %lld\n",
len, (unsigned long long) in_serv_agg->F,
(unsigned long long) q->V);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-06 03:04:38 +0000