mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 09:19:51 +00:00
![Eric Dumazet](/assets/img/avatar_default.png)
For some reason, fq_pie_destroy() did not copy
working code from pie_destroy() and other qdiscs,
thus causing elusive bug.
Before calling del_timer_sync(&q->adapt_timer),
we need to ensure timer will not rearm itself.
rcu: INFO: rcu_preempt self-detected stall on CPU
rcu: 0-....: (4416 ticks this GP) idle=60d/1/0x4000000000000000 softirq=10433/10434 fqs=2579
(t=10501 jiffies g=13085 q=3989)
NMI backtrace for cpu 0
CPU: 0 PID: 13 Comm: ksoftirqd/0 Not tainted 5.16.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
<IRQ>
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106
nmi_cpu_backtrace.cold+0x47/0x144 lib/nmi_backtrace.c:111
nmi_trigger_cpumask_backtrace+0x1b3/0x230 lib/nmi_backtrace.c:62
trigger_single_cpu_backtrace include/linux/nmi.h:164 [inline]
rcu_dump_cpu_stacks+0x25e/0x3f0 kernel/rcu/tree_stall.h:343
print_cpu_stall kernel/rcu/tree_stall.h:627 [inline]
check_cpu_stall kernel/rcu/tree_stall.h:711 [inline]
rcu_pending kernel/rcu/tree.c:3878 [inline]
rcu_sched_clock_irq.cold+0x9d/0x746 kernel/rcu/tree.c:2597
update_process_times+0x16d/0x200 kernel/time/timer.c:1785
tick_sched_handle+0x9b/0x180 kernel/time/tick-sched.c:226
tick_sched_timer+0x1b0/0x2d0 kernel/time/tick-sched.c:1428
__run_hrtimer kernel/time/hrtimer.c:1685 [inline]
__hrtimer_run_queues+0x1c0/0xe50 kernel/time/hrtimer.c:1749
hrtimer_interrupt+0x31c/0x790 kernel/time/hrtimer.c:1811
local_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1086 [inline]
__sysvec_apic_timer_interrupt+0x146/0x530 arch/x86/kernel/apic/apic.c:1103
sysvec_apic_timer_interrupt+0x8e/0xc0 arch/x86/kernel/apic/apic.c:1097
</IRQ>
<TASK>
asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:638
RIP: 0010:write_comp_data kernel/kcov.c:221 [inline]
RIP: 0010:__sanitizer_cov_trace_const_cmp1+0x1d/0x80 kernel/kcov.c:273
Code: 54 c8 20 48 89 10 c3 66 0f 1f 44 00 00 53 41 89 fb 41 89 f1 bf 03 00 00 00 65 48 8b 0c 25 40 70 02 00 48 89 ce 4c 8b 54 24 08 <e8> 4e f7 ff ff 84 c0 74 51 48 8b 81 88 15 00 00 44 8b 81 84 15 00
RSP: 0018:ffffc90000d27b28 EFLAGS: 00000246
RAX: 0000000000000000 RBX: ffff888064bf1bf0 RCX: ffff888011928000
RDX: ffff888011928000 RSI: ffff888011928000 RDI: 0000000000000003
RBP: ffff888064bf1c28 R08: 0000000000000000 R09: 0000000000000000
R10: ffffffff875d8295 R11: 0000000000000000 R12: 0000000000000000
R13: ffff8880783dd300 R14: 0000000000000000 R15: 0000000000000000
pie_calculate_probability+0x405/0x7c0 net/sched/sch_pie.c:418
fq_pie_timer+0x170/0x2a0 net/sched/sch_fq_pie.c:383
call_timer_fn+0x1a5/0x6b0 kernel/time/timer.c:1421
expire_timers kernel/time/timer.c:1466 [inline]
__run_timers.part.0+0x675/0xa20 kernel/time/timer.c:1734
__run_timers kernel/time/timer.c:1715 [inline]
run_timer_softirq+0xb3/0x1d0 kernel/time/timer.c:1747
__do_softirq+0x29b/0x9c2 kernel/softirq.c:558
run_ksoftirqd kernel/softirq.c:921 [inline]
run_ksoftirqd+0x2d/0x60 kernel/softirq.c:913
smpboot_thread_fn+0x645/0x9c0 kernel/smpboot.c:164
kthread+0x405/0x4f0 kernel/kthread.c:327
ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295
</TASK>
Fixes: ec97ecf1eb
("net: sched: add Flow Queue PIE packet scheduler")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Mohit P. Tahiliani <tahiliani@nitk.edu.in>
Cc: Sachin D. Patil <sdp.sachin@gmail.com>
Cc: V. Saicharan <vsaicharan1998@gmail.com>
Cc: Mohit Bhasi <mohitbhasi1998@gmail.com>
Cc: Leslie Monis <lesliemonis@gmail.com>
Cc: Gautam Ramakrishnan <gautamramk@gmail.com>
Link: https://lore.kernel.org/r/20211209084937.3500020-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
569 lines
14 KiB
C
569 lines
14 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/* Flow Queue PIE discipline
|
|
*
|
|
* Copyright (C) 2019 Mohit P. Tahiliani <tahiliani@nitk.edu.in>
|
|
* Copyright (C) 2019 Sachin D. Patil <sdp.sachin@gmail.com>
|
|
* Copyright (C) 2019 V. Saicharan <vsaicharan1998@gmail.com>
|
|
* Copyright (C) 2019 Mohit Bhasi <mohitbhasi1998@gmail.com>
|
|
* Copyright (C) 2019 Leslie Monis <lesliemonis@gmail.com>
|
|
* Copyright (C) 2019 Gautam Ramakrishnan <gautamramk@gmail.com>
|
|
*/
|
|
|
|
#include <linux/jhash.h>
|
|
#include <linux/sizes.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <net/pkt_cls.h>
|
|
#include <net/pie.h>
|
|
|
|
/* Flow Queue PIE
|
|
*
|
|
* Principles:
|
|
* - Packets are classified on flows.
|
|
* - This is a Stochastic model (as we use a hash, several flows might
|
|
* be hashed to the same slot)
|
|
* - Each flow has a PIE managed queue.
|
|
* - Flows are linked onto two (Round Robin) lists,
|
|
* so that new flows have priority on old ones.
|
|
* - For a given flow, packets are not reordered.
|
|
* - Drops during enqueue only.
|
|
* - ECN capability is off by default.
|
|
* - ECN threshold (if ECN is enabled) is at 10% by default.
|
|
* - Uses timestamps to calculate queue delay by default.
|
|
*/
|
|
|
|
/**
|
|
* struct fq_pie_flow - contains data for each flow
|
|
* @vars: pie vars associated with the flow
|
|
* @deficit: number of remaining byte credits
|
|
* @backlog: size of data in the flow
|
|
* @qlen: number of packets in the flow
|
|
* @flowchain: flowchain for the flow
|
|
* @head: first packet in the flow
|
|
* @tail: last packet in the flow
|
|
*/
|
|
struct fq_pie_flow {
|
|
struct pie_vars vars;
|
|
s32 deficit;
|
|
u32 backlog;
|
|
u32 qlen;
|
|
struct list_head flowchain;
|
|
struct sk_buff *head;
|
|
struct sk_buff *tail;
|
|
};
|
|
|
|
struct fq_pie_sched_data {
|
|
struct tcf_proto __rcu *filter_list; /* optional external classifier */
|
|
struct tcf_block *block;
|
|
struct fq_pie_flow *flows;
|
|
struct Qdisc *sch;
|
|
struct list_head old_flows;
|
|
struct list_head new_flows;
|
|
struct pie_params p_params;
|
|
u32 ecn_prob;
|
|
u32 flows_cnt;
|
|
u32 quantum;
|
|
u32 memory_limit;
|
|
u32 new_flow_count;
|
|
u32 memory_usage;
|
|
u32 overmemory;
|
|
struct pie_stats stats;
|
|
struct timer_list adapt_timer;
|
|
};
|
|
|
|
static unsigned int fq_pie_hash(const struct fq_pie_sched_data *q,
|
|
struct sk_buff *skb)
|
|
{
|
|
return reciprocal_scale(skb_get_hash(skb), q->flows_cnt);
|
|
}
|
|
|
|
static unsigned int fq_pie_classify(struct sk_buff *skb, struct Qdisc *sch,
|
|
int *qerr)
|
|
{
|
|
struct fq_pie_sched_data *q = qdisc_priv(sch);
|
|
struct tcf_proto *filter;
|
|
struct tcf_result res;
|
|
int result;
|
|
|
|
if (TC_H_MAJ(skb->priority) == sch->handle &&
|
|
TC_H_MIN(skb->priority) > 0 &&
|
|
TC_H_MIN(skb->priority) <= q->flows_cnt)
|
|
return TC_H_MIN(skb->priority);
|
|
|
|
filter = rcu_dereference_bh(q->filter_list);
|
|
if (!filter)
|
|
return fq_pie_hash(q, skb) + 1;
|
|
|
|
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
|
|
result = tcf_classify(skb, NULL, filter, &res, false);
|
|
if (result >= 0) {
|
|
#ifdef CONFIG_NET_CLS_ACT
|
|
switch (result) {
|
|
case TC_ACT_STOLEN:
|
|
case TC_ACT_QUEUED:
|
|
case TC_ACT_TRAP:
|
|
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
|
|
fallthrough;
|
|
case TC_ACT_SHOT:
|
|
return 0;
|
|
}
|
|
#endif
|
|
if (TC_H_MIN(res.classid) <= q->flows_cnt)
|
|
return TC_H_MIN(res.classid);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/* add skb to flow queue (tail add) */
|
|
static inline void flow_queue_add(struct fq_pie_flow *flow,
|
|
struct sk_buff *skb)
|
|
{
|
|
if (!flow->head)
|
|
flow->head = skb;
|
|
else
|
|
flow->tail->next = skb;
|
|
flow->tail = skb;
|
|
skb->next = NULL;
|
|
}
|
|
|
|
static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
|
|
struct sk_buff **to_free)
|
|
{
|
|
struct fq_pie_sched_data *q = qdisc_priv(sch);
|
|
struct fq_pie_flow *sel_flow;
|
|
int ret;
|
|
u8 memory_limited = false;
|
|
u8 enqueue = false;
|
|
u32 pkt_len;
|
|
u32 idx;
|
|
|
|
/* Classifies packet into corresponding flow */
|
|
idx = fq_pie_classify(skb, sch, &ret);
|
|
if (idx == 0) {
|
|
if (ret & __NET_XMIT_BYPASS)
|
|
qdisc_qstats_drop(sch);
|
|
__qdisc_drop(skb, to_free);
|
|
return ret;
|
|
}
|
|
idx--;
|
|
|
|
sel_flow = &q->flows[idx];
|
|
/* Checks whether adding a new packet would exceed memory limit */
|
|
get_pie_cb(skb)->mem_usage = skb->truesize;
|
|
memory_limited = q->memory_usage > q->memory_limit + skb->truesize;
|
|
|
|
/* Checks if the qdisc is full */
|
|
if (unlikely(qdisc_qlen(sch) >= sch->limit)) {
|
|
q->stats.overlimit++;
|
|
goto out;
|
|
} else if (unlikely(memory_limited)) {
|
|
q->overmemory++;
|
|
}
|
|
|
|
if (!pie_drop_early(sch, &q->p_params, &sel_flow->vars,
|
|
sel_flow->backlog, skb->len)) {
|
|
enqueue = true;
|
|
} else if (q->p_params.ecn &&
|
|
sel_flow->vars.prob <= (MAX_PROB / 100) * q->ecn_prob &&
|
|
INET_ECN_set_ce(skb)) {
|
|
/* If packet is ecn capable, mark it if drop probability
|
|
* is lower than the parameter ecn_prob, else drop it.
|
|
*/
|
|
q->stats.ecn_mark++;
|
|
enqueue = true;
|
|
}
|
|
if (enqueue) {
|
|
/* Set enqueue time only when dq_rate_estimator is disabled. */
|
|
if (!q->p_params.dq_rate_estimator)
|
|
pie_set_enqueue_time(skb);
|
|
|
|
pkt_len = qdisc_pkt_len(skb);
|
|
q->stats.packets_in++;
|
|
q->memory_usage += skb->truesize;
|
|
sch->qstats.backlog += pkt_len;
|
|
sch->q.qlen++;
|
|
flow_queue_add(sel_flow, skb);
|
|
if (list_empty(&sel_flow->flowchain)) {
|
|
list_add_tail(&sel_flow->flowchain, &q->new_flows);
|
|
q->new_flow_count++;
|
|
sel_flow->deficit = q->quantum;
|
|
sel_flow->qlen = 0;
|
|
sel_flow->backlog = 0;
|
|
}
|
|
sel_flow->qlen++;
|
|
sel_flow->backlog += pkt_len;
|
|
return NET_XMIT_SUCCESS;
|
|
}
|
|
out:
|
|
q->stats.dropped++;
|
|
sel_flow->vars.accu_prob = 0;
|
|
__qdisc_drop(skb, to_free);
|
|
qdisc_qstats_drop(sch);
|
|
return NET_XMIT_CN;
|
|
}
|
|
|
|
static const struct nla_policy fq_pie_policy[TCA_FQ_PIE_MAX + 1] = {
|
|
[TCA_FQ_PIE_LIMIT] = {.type = NLA_U32},
|
|
[TCA_FQ_PIE_FLOWS] = {.type = NLA_U32},
|
|
[TCA_FQ_PIE_TARGET] = {.type = NLA_U32},
|
|
[TCA_FQ_PIE_TUPDATE] = {.type = NLA_U32},
|
|
[TCA_FQ_PIE_ALPHA] = {.type = NLA_U32},
|
|
[TCA_FQ_PIE_BETA] = {.type = NLA_U32},
|
|
[TCA_FQ_PIE_QUANTUM] = {.type = NLA_U32},
|
|
[TCA_FQ_PIE_MEMORY_LIMIT] = {.type = NLA_U32},
|
|
[TCA_FQ_PIE_ECN_PROB] = {.type = NLA_U32},
|
|
[TCA_FQ_PIE_ECN] = {.type = NLA_U32},
|
|
[TCA_FQ_PIE_BYTEMODE] = {.type = NLA_U32},
|
|
[TCA_FQ_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32},
|
|
};
|
|
|
|
static inline struct sk_buff *dequeue_head(struct fq_pie_flow *flow)
|
|
{
|
|
struct sk_buff *skb = flow->head;
|
|
|
|
flow->head = skb->next;
|
|
skb->next = NULL;
|
|
return skb;
|
|
}
|
|
|
|
static struct sk_buff *fq_pie_qdisc_dequeue(struct Qdisc *sch)
|
|
{
|
|
struct fq_pie_sched_data *q = qdisc_priv(sch);
|
|
struct sk_buff *skb = NULL;
|
|
struct fq_pie_flow *flow;
|
|
struct list_head *head;
|
|
u32 pkt_len;
|
|
|
|
begin:
|
|
head = &q->new_flows;
|
|
if (list_empty(head)) {
|
|
head = &q->old_flows;
|
|
if (list_empty(head))
|
|
return NULL;
|
|
}
|
|
|
|
flow = list_first_entry(head, struct fq_pie_flow, flowchain);
|
|
/* Flow has exhausted all its credits */
|
|
if (flow->deficit <= 0) {
|
|
flow->deficit += q->quantum;
|
|
list_move_tail(&flow->flowchain, &q->old_flows);
|
|
goto begin;
|
|
}
|
|
|
|
if (flow->head) {
|
|
skb = dequeue_head(flow);
|
|
pkt_len = qdisc_pkt_len(skb);
|
|
sch->qstats.backlog -= pkt_len;
|
|
sch->q.qlen--;
|
|
qdisc_bstats_update(sch, skb);
|
|
}
|
|
|
|
if (!skb) {
|
|
/* force a pass through old_flows to prevent starvation */
|
|
if (head == &q->new_flows && !list_empty(&q->old_flows))
|
|
list_move_tail(&flow->flowchain, &q->old_flows);
|
|
else
|
|
list_del_init(&flow->flowchain);
|
|
goto begin;
|
|
}
|
|
|
|
flow->qlen--;
|
|
flow->deficit -= pkt_len;
|
|
flow->backlog -= pkt_len;
|
|
q->memory_usage -= get_pie_cb(skb)->mem_usage;
|
|
pie_process_dequeue(skb, &q->p_params, &flow->vars, flow->backlog);
|
|
return skb;
|
|
}
|
|
|
|
static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct fq_pie_sched_data *q = qdisc_priv(sch);
|
|
struct nlattr *tb[TCA_FQ_PIE_MAX + 1];
|
|
unsigned int len_dropped = 0;
|
|
unsigned int num_dropped = 0;
|
|
int err;
|
|
|
|
if (!opt)
|
|
return -EINVAL;
|
|
|
|
err = nla_parse_nested(tb, TCA_FQ_PIE_MAX, opt, fq_pie_policy, extack);
|
|
if (err < 0)
|
|
return err;
|
|
|
|
sch_tree_lock(sch);
|
|
if (tb[TCA_FQ_PIE_LIMIT]) {
|
|
u32 limit = nla_get_u32(tb[TCA_FQ_PIE_LIMIT]);
|
|
|
|
q->p_params.limit = limit;
|
|
sch->limit = limit;
|
|
}
|
|
if (tb[TCA_FQ_PIE_FLOWS]) {
|
|
if (q->flows) {
|
|
NL_SET_ERR_MSG_MOD(extack,
|
|
"Number of flows cannot be changed");
|
|
goto flow_error;
|
|
}
|
|
q->flows_cnt = nla_get_u32(tb[TCA_FQ_PIE_FLOWS]);
|
|
if (!q->flows_cnt || q->flows_cnt > 65536) {
|
|
NL_SET_ERR_MSG_MOD(extack,
|
|
"Number of flows must range in [1..65536]");
|
|
goto flow_error;
|
|
}
|
|
}
|
|
|
|
/* convert from microseconds to pschedtime */
|
|
if (tb[TCA_FQ_PIE_TARGET]) {
|
|
/* target is in us */
|
|
u32 target = nla_get_u32(tb[TCA_FQ_PIE_TARGET]);
|
|
|
|
/* convert to pschedtime */
|
|
q->p_params.target =
|
|
PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC);
|
|
}
|
|
|
|
/* tupdate is in jiffies */
|
|
if (tb[TCA_FQ_PIE_TUPDATE])
|
|
q->p_params.tupdate =
|
|
usecs_to_jiffies(nla_get_u32(tb[TCA_FQ_PIE_TUPDATE]));
|
|
|
|
if (tb[TCA_FQ_PIE_ALPHA])
|
|
q->p_params.alpha = nla_get_u32(tb[TCA_FQ_PIE_ALPHA]);
|
|
|
|
if (tb[TCA_FQ_PIE_BETA])
|
|
q->p_params.beta = nla_get_u32(tb[TCA_FQ_PIE_BETA]);
|
|
|
|
if (tb[TCA_FQ_PIE_QUANTUM])
|
|
q->quantum = nla_get_u32(tb[TCA_FQ_PIE_QUANTUM]);
|
|
|
|
if (tb[TCA_FQ_PIE_MEMORY_LIMIT])
|
|
q->memory_limit = nla_get_u32(tb[TCA_FQ_PIE_MEMORY_LIMIT]);
|
|
|
|
if (tb[TCA_FQ_PIE_ECN_PROB])
|
|
q->ecn_prob = nla_get_u32(tb[TCA_FQ_PIE_ECN_PROB]);
|
|
|
|
if (tb[TCA_FQ_PIE_ECN])
|
|
q->p_params.ecn = nla_get_u32(tb[TCA_FQ_PIE_ECN]);
|
|
|
|
if (tb[TCA_FQ_PIE_BYTEMODE])
|
|
q->p_params.bytemode = nla_get_u32(tb[TCA_FQ_PIE_BYTEMODE]);
|
|
|
|
if (tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR])
|
|
q->p_params.dq_rate_estimator =
|
|
nla_get_u32(tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR]);
|
|
|
|
/* Drop excess packets if new limit is lower */
|
|
while (sch->q.qlen > sch->limit) {
|
|
struct sk_buff *skb = fq_pie_qdisc_dequeue(sch);
|
|
|
|
len_dropped += qdisc_pkt_len(skb);
|
|
num_dropped += 1;
|
|
rtnl_kfree_skbs(skb, skb);
|
|
}
|
|
qdisc_tree_reduce_backlog(sch, num_dropped, len_dropped);
|
|
|
|
sch_tree_unlock(sch);
|
|
return 0;
|
|
|
|
flow_error:
|
|
sch_tree_unlock(sch);
|
|
return -EINVAL;
|
|
}
|
|
|
|
static void fq_pie_timer(struct timer_list *t)
|
|
{
|
|
struct fq_pie_sched_data *q = from_timer(q, t, adapt_timer);
|
|
struct Qdisc *sch = q->sch;
|
|
spinlock_t *root_lock; /* to lock qdisc for probability calculations */
|
|
u32 idx;
|
|
|
|
root_lock = qdisc_lock(qdisc_root_sleeping(sch));
|
|
spin_lock(root_lock);
|
|
|
|
for (idx = 0; idx < q->flows_cnt; idx++)
|
|
pie_calculate_probability(&q->p_params, &q->flows[idx].vars,
|
|
q->flows[idx].backlog);
|
|
|
|
/* reset the timer to fire after 'tupdate' jiffies. */
|
|
if (q->p_params.tupdate)
|
|
mod_timer(&q->adapt_timer, jiffies + q->p_params.tupdate);
|
|
|
|
spin_unlock(root_lock);
|
|
}
|
|
|
|
static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct fq_pie_sched_data *q = qdisc_priv(sch);
|
|
int err;
|
|
u32 idx;
|
|
|
|
pie_params_init(&q->p_params);
|
|
sch->limit = 10 * 1024;
|
|
q->p_params.limit = sch->limit;
|
|
q->quantum = psched_mtu(qdisc_dev(sch));
|
|
q->sch = sch;
|
|
q->ecn_prob = 10;
|
|
q->flows_cnt = 1024;
|
|
q->memory_limit = SZ_32M;
|
|
|
|
INIT_LIST_HEAD(&q->new_flows);
|
|
INIT_LIST_HEAD(&q->old_flows);
|
|
timer_setup(&q->adapt_timer, fq_pie_timer, 0);
|
|
|
|
if (opt) {
|
|
err = fq_pie_change(sch, opt, extack);
|
|
|
|
if (err)
|
|
return err;
|
|
}
|
|
|
|
err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
|
|
if (err)
|
|
goto init_failure;
|
|
|
|
q->flows = kvcalloc(q->flows_cnt, sizeof(struct fq_pie_flow),
|
|
GFP_KERNEL);
|
|
if (!q->flows) {
|
|
err = -ENOMEM;
|
|
goto init_failure;
|
|
}
|
|
for (idx = 0; idx < q->flows_cnt; idx++) {
|
|
struct fq_pie_flow *flow = q->flows + idx;
|
|
|
|
INIT_LIST_HEAD(&flow->flowchain);
|
|
pie_vars_init(&flow->vars);
|
|
}
|
|
|
|
mod_timer(&q->adapt_timer, jiffies + HZ / 2);
|
|
|
|
return 0;
|
|
|
|
init_failure:
|
|
q->flows_cnt = 0;
|
|
|
|
return err;
|
|
}
|
|
|
|
static int fq_pie_dump(struct Qdisc *sch, struct sk_buff *skb)
|
|
{
|
|
struct fq_pie_sched_data *q = qdisc_priv(sch);
|
|
struct nlattr *opts;
|
|
|
|
opts = nla_nest_start(skb, TCA_OPTIONS);
|
|
if (!opts)
|
|
return -EMSGSIZE;
|
|
|
|
/* convert target from pschedtime to us */
|
|
if (nla_put_u32(skb, TCA_FQ_PIE_LIMIT, sch->limit) ||
|
|
nla_put_u32(skb, TCA_FQ_PIE_FLOWS, q->flows_cnt) ||
|
|
nla_put_u32(skb, TCA_FQ_PIE_TARGET,
|
|
((u32)PSCHED_TICKS2NS(q->p_params.target)) /
|
|
NSEC_PER_USEC) ||
|
|
nla_put_u32(skb, TCA_FQ_PIE_TUPDATE,
|
|
jiffies_to_usecs(q->p_params.tupdate)) ||
|
|
nla_put_u32(skb, TCA_FQ_PIE_ALPHA, q->p_params.alpha) ||
|
|
nla_put_u32(skb, TCA_FQ_PIE_BETA, q->p_params.beta) ||
|
|
nla_put_u32(skb, TCA_FQ_PIE_QUANTUM, q->quantum) ||
|
|
nla_put_u32(skb, TCA_FQ_PIE_MEMORY_LIMIT, q->memory_limit) ||
|
|
nla_put_u32(skb, TCA_FQ_PIE_ECN_PROB, q->ecn_prob) ||
|
|
nla_put_u32(skb, TCA_FQ_PIE_ECN, q->p_params.ecn) ||
|
|
nla_put_u32(skb, TCA_FQ_PIE_BYTEMODE, q->p_params.bytemode) ||
|
|
nla_put_u32(skb, TCA_FQ_PIE_DQ_RATE_ESTIMATOR,
|
|
q->p_params.dq_rate_estimator))
|
|
goto nla_put_failure;
|
|
|
|
return nla_nest_end(skb, opts);
|
|
|
|
nla_put_failure:
|
|
nla_nest_cancel(skb, opts);
|
|
return -EMSGSIZE;
|
|
}
|
|
|
|
static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
|
|
{
|
|
struct fq_pie_sched_data *q = qdisc_priv(sch);
|
|
struct tc_fq_pie_xstats st = {
|
|
.packets_in = q->stats.packets_in,
|
|
.overlimit = q->stats.overlimit,
|
|
.overmemory = q->overmemory,
|
|
.dropped = q->stats.dropped,
|
|
.ecn_mark = q->stats.ecn_mark,
|
|
.new_flow_count = q->new_flow_count,
|
|
.memory_usage = q->memory_usage,
|
|
};
|
|
struct list_head *pos;
|
|
|
|
sch_tree_lock(sch);
|
|
list_for_each(pos, &q->new_flows)
|
|
st.new_flows_len++;
|
|
|
|
list_for_each(pos, &q->old_flows)
|
|
st.old_flows_len++;
|
|
sch_tree_unlock(sch);
|
|
|
|
return gnet_stats_copy_app(d, &st, sizeof(st));
|
|
}
|
|
|
|
static void fq_pie_reset(struct Qdisc *sch)
|
|
{
|
|
struct fq_pie_sched_data *q = qdisc_priv(sch);
|
|
u32 idx;
|
|
|
|
INIT_LIST_HEAD(&q->new_flows);
|
|
INIT_LIST_HEAD(&q->old_flows);
|
|
for (idx = 0; idx < q->flows_cnt; idx++) {
|
|
struct fq_pie_flow *flow = q->flows + idx;
|
|
|
|
/* Removes all packets from flow */
|
|
rtnl_kfree_skbs(flow->head, flow->tail);
|
|
flow->head = NULL;
|
|
|
|
INIT_LIST_HEAD(&flow->flowchain);
|
|
pie_vars_init(&flow->vars);
|
|
}
|
|
|
|
sch->q.qlen = 0;
|
|
sch->qstats.backlog = 0;
|
|
}
|
|
|
|
static void fq_pie_destroy(struct Qdisc *sch)
|
|
{
|
|
struct fq_pie_sched_data *q = qdisc_priv(sch);
|
|
|
|
tcf_block_put(q->block);
|
|
q->p_params.tupdate = 0;
|
|
del_timer_sync(&q->adapt_timer);
|
|
kvfree(q->flows);
|
|
}
|
|
|
|
static struct Qdisc_ops fq_pie_qdisc_ops __read_mostly = {
|
|
.id = "fq_pie",
|
|
.priv_size = sizeof(struct fq_pie_sched_data),
|
|
.enqueue = fq_pie_qdisc_enqueue,
|
|
.dequeue = fq_pie_qdisc_dequeue,
|
|
.peek = qdisc_peek_dequeued,
|
|
.init = fq_pie_init,
|
|
.destroy = fq_pie_destroy,
|
|
.reset = fq_pie_reset,
|
|
.change = fq_pie_change,
|
|
.dump = fq_pie_dump,
|
|
.dump_stats = fq_pie_dump_stats,
|
|
.owner = THIS_MODULE,
|
|
};
|
|
|
|
static int __init fq_pie_module_init(void)
|
|
{
|
|
return register_qdisc(&fq_pie_qdisc_ops);
|
|
}
|
|
|
|
static void __exit fq_pie_module_exit(void)
|
|
{
|
|
unregister_qdisc(&fq_pie_qdisc_ops);
|
|
}
|
|
|
|
module_init(fq_pie_module_init);
|
|
module_exit(fq_pie_module_exit);
|
|
|
|
MODULE_DESCRIPTION("Flow Queue Proportional Integral controller Enhanced (FQ-PIE)");
|
|
MODULE_AUTHOR("Mohit P. Tahiliani");
|
|
MODULE_LICENSE("GPL");
|