UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/include/net/fq_impl.h

391 lines
7.9 KiB
C
Raw Normal View History

treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 257 Based on 1 normalized pattern(s): gpl v2 extracted by the scancode license scanner the SPDX license identifier GPL-2.0-only has been chosen to replace the boilerplate/reference in 19 file(s). Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Allison Randal <allison@lohutok.net> Reviewed-by: Richard Fontana <rfontana@redhat.com> Reviewed-by: Steve Winslow <swinslow@gmail.com> Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Alexios Zavras <alexios.zavras@intel.com> Cc: linux-spdx@vger.kernel.org Link: https://lkml.kernel.org/r/20190529141333.108140152@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-05-29 22:12:31 +08:00
/* SPDX-License-Identifier: GPL-2.0-only */
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
/*
* Copyright (c) 2016 Qualcomm Atheros, Inc
*
* Based on net/sched/sch_fq_codel.c
*/
#ifndef __NET_SCHED_FQ_IMPL_H
#define __NET_SCHED_FQ_IMPL_H
#include <net/fq.h>
/* functions that are embedded into includer */
net/fq_impl: bulk-free packets from a flow on overmemory This is similar to what sch_fq_codel does. It also amortizes the worst case cost of a follow-up patch that changes the selection of the biggest flow for dropping packets Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-1-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:13 +08:00
static void
__fq_adjust_removal(struct fq *fq, struct fq_flow *flow, unsigned int packets,
unsigned int bytes, unsigned int truesize)
{
struct fq_tin *tin = flow->tin;
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
int idx;
net/fq_impl: bulk-free packets from a flow on overmemory This is similar to what sch_fq_codel does. It also amortizes the worst case cost of a follow-up patch that changes the selection of the biggest flow for dropping packets Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-1-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:13 +08:00
tin->backlog_bytes -= bytes;
tin->backlog_packets -= packets;
flow->backlog -= bytes;
fq->backlog -= packets;
fq->memory_usage -= truesize;
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
if (flow->backlog)
return;
if (flow == &tin->default_flow) {
list_del_init(&tin->tin_list);
return;
}
idx = flow - fq->flows;
__clear_bit(idx, fq->flows_bitmap);
net/fq_impl: bulk-free packets from a flow on overmemory This is similar to what sch_fq_codel does. It also amortizes the worst case cost of a follow-up patch that changes the selection of the biggest flow for dropping packets Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-1-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:13 +08:00
}
fq: support filtering a given tin Add to the FQ API a way to filter a given tin, in order to remove frames that fulfil certain criteria according to a filter function. This will be used by mac80211 to remove frames belonging to an AP VLAN interface that's being removed. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Acked-by: Toke Høiland-Jørgensen <toke@toke.dk> Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2017-10-06 17:53:32 +08:00
static void fq_adjust_removal(struct fq *fq,
struct fq_flow *flow,
struct sk_buff *skb)
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
{
net/fq_impl: bulk-free packets from a flow on overmemory This is similar to what sch_fq_codel does. It also amortizes the worst case cost of a follow-up patch that changes the selection of the biggest flow for dropping packets Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-1-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:13 +08:00
__fq_adjust_removal(fq, flow, 1, skb->len, skb->truesize);
fq: support filtering a given tin Add to the FQ API a way to filter a given tin, in order to remove frames that fulfil certain criteria according to a filter function. This will be used by mac80211 to remove frames belonging to an AP VLAN interface that's being removed. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Acked-by: Toke Høiland-Jørgensen <toke@toke.dk> Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2017-10-06 17:53:32 +08:00
}
static struct sk_buff *fq_flow_dequeue(struct fq *fq,
struct fq_flow *flow)
{
struct sk_buff *skb;
lockdep_assert_held(&fq->lock);
skb = __skb_dequeue(&flow->queue);
if (!skb)
return NULL;
fq_adjust_removal(fq, flow, skb);
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
return skb;
}
net/fq_impl: bulk-free packets from a flow on overmemory This is similar to what sch_fq_codel does. It also amortizes the worst case cost of a follow-up patch that changes the selection of the biggest flow for dropping packets Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-1-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:13 +08:00
static int fq_flow_drop(struct fq *fq, struct fq_flow *flow,
fq_skb_free_t free_func)
{
unsigned int packets = 0, bytes = 0, truesize = 0;
struct fq_tin *tin = flow->tin;
struct sk_buff *skb;
int pending;
lockdep_assert_held(&fq->lock);
pending = min_t(int, 32, skb_queue_len(&flow->queue) / 2);
do {
skb = __skb_dequeue(&flow->queue);
if (!skb)
break;
packets++;
bytes += skb->len;
truesize += skb->truesize;
free_func(fq, tin, flow, skb);
} while (packets < pending);
__fq_adjust_removal(fq, flow, packets, bytes, truesize);
return packets;
}
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
static struct sk_buff *fq_tin_dequeue(struct fq *fq,
struct fq_tin *tin,
fq_tin_dequeue_t dequeue_func)
{
struct fq_flow *flow;
struct list_head *head;
struct sk_buff *skb;
lockdep_assert_held(&fq->lock);
begin:
head = &tin->new_flows;
if (list_empty(head)) {
head = &tin->old_flows;
if (list_empty(head))
return NULL;
}
flow = list_first_entry(head, struct fq_flow, flowchain);
if (flow->deficit <= 0) {
flow->deficit += fq->quantum;
list_move_tail(&flow->flowchain,
&tin->old_flows);
goto begin;
}
skb = dequeue_func(fq, tin, flow);
if (!skb) {
/* force a pass through old_flows to prevent starvation */
if ((head == &tin->new_flows) &&
!list_empty(&tin->old_flows)) {
list_move_tail(&flow->flowchain, &tin->old_flows);
} else {
list_del_init(&flow->flowchain);
flow->tin = NULL;
}
goto begin;
}
flow->deficit -= skb->len;
tin->tx_bytes += skb->len;
tin->tx_packets++;
return skb;
}
mac80211: calculate hash for fq without holding fq->lock in itxq enqueue Reduces lock contention on enqueue/dequeue of iTXQ packets Signed-off-by: Felix Fietkau <nbd@nbd.name> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2019-03-17 01:06:32 +08:00
static u32 fq_flow_idx(struct fq *fq, struct sk_buff *skb)
{
net/fq_impl: use skb_get_hash instead of skb_get_hash_perturb This avoids unnecessarily regenerating the skb flow hash Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20200726130947.88145-1-nbd@nbd.name [small commit message fixup] Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-07-26 21:09:46 +08:00
u32 hash = skb_get_hash(skb);
mac80211: calculate hash for fq without holding fq->lock in itxq enqueue Reduces lock contention on enqueue/dequeue of iTXQ packets Signed-off-by: Felix Fietkau <nbd@nbd.name> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2019-03-17 01:06:32 +08:00
return reciprocal_scale(hash, fq->flows_cnt);
}
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
static struct fq_flow *fq_flow_classify(struct fq *fq,
mac80211: calculate hash for fq without holding fq->lock in itxq enqueue Reduces lock contention on enqueue/dequeue of iTXQ packets Signed-off-by: Felix Fietkau <nbd@nbd.name> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2019-03-17 01:06:32 +08:00
struct fq_tin *tin, u32 idx,
net/fq_impl: drop get_default_func, move default flow to fq_tin Simplifies the code and prepares for a rework of scanning for flows on overmemory drop. Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-2-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:14 +08:00
struct sk_buff *skb)
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
{
struct fq_flow *flow;
lockdep_assert_held(&fq->lock);
flow = &fq->flows[idx];
if (flow->tin && flow->tin != tin) {
net/fq_impl: drop get_default_func, move default flow to fq_tin Simplifies the code and prepares for a rework of scanning for flows on overmemory drop. Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-2-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:14 +08:00
flow = &tin->default_flow;
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
tin->collisions++;
fq->collisions++;
}
if (!flow->tin)
tin->flows++;
return flow;
}
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
static struct fq_flow *fq_find_fattest_flow(struct fq *fq)
fq: split out backlog update logic mac80211 (which will be the first user of the fq.h) recently started to support software A-MSDU aggregation. It glues skbuffs together into a single one so the backlog accounting needs to be more fine-grained. To avoid backlog sorting logic duplication split it up for re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27 18:59:13 +08:00
{
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
struct fq_tin *tin;
struct fq_flow *flow = NULL;
u32 len = 0;
int i;
fq: split out backlog update logic mac80211 (which will be the first user of the fq.h) recently started to support software A-MSDU aggregation. It glues skbuffs together into a single one so the backlog accounting needs to be more fine-grained. To avoid backlog sorting logic duplication split it up for re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27 18:59:13 +08:00
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
for_each_set_bit(i, fq->flows_bitmap, fq->flows_cnt) {
struct fq_flow *cur = &fq->flows[i];
unsigned int cur_len;
fq: split out backlog update logic mac80211 (which will be the first user of the fq.h) recently started to support software A-MSDU aggregation. It glues skbuffs together into a single one so the backlog accounting needs to be more fine-grained. To avoid backlog sorting logic duplication split it up for re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27 18:59:13 +08:00
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
cur_len = cur->backlog;
if (cur_len <= len)
continue;
flow = cur;
len = cur_len;
}
list_for_each_entry(tin, &fq->tin_backlog, tin_list) {
unsigned int cur_len = tin->default_flow.backlog;
fq: split out backlog update logic mac80211 (which will be the first user of the fq.h) recently started to support software A-MSDU aggregation. It glues skbuffs together into a single one so the backlog accounting needs to be more fine-grained. To avoid backlog sorting logic duplication split it up for re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27 18:59:13 +08:00
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
if (cur_len <= len)
continue;
flow = &tin->default_flow;
len = cur_len;
}
return flow;
fq: split out backlog update logic mac80211 (which will be the first user of the fq.h) recently started to support software A-MSDU aggregation. It glues skbuffs together into a single one so the backlog accounting needs to be more fine-grained. To avoid backlog sorting logic duplication split it up for re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27 18:59:13 +08:00
}
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
static void fq_tin_enqueue(struct fq *fq,
mac80211: calculate hash for fq without holding fq->lock in itxq enqueue Reduces lock contention on enqueue/dequeue of iTXQ packets Signed-off-by: Felix Fietkau <nbd@nbd.name> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2019-03-17 01:06:32 +08:00
struct fq_tin *tin, u32 idx,
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
struct sk_buff *skb,
net/fq_impl: drop get_default_func, move default flow to fq_tin Simplifies the code and prepares for a rework of scanning for flows on overmemory drop. Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-2-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:14 +08:00
fq_skb_free_t free_func)
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
{
struct fq_flow *flow;
fq_impl: Properly enforce memory limit The fq structure would fail to properly enforce the memory limit in the case where the packet being enqueued was bigger than the packet being removed to bring the memory usage down. So keep dropping packets until the memory usage is back below the limit. Also, fix the statistics for memory limit violations. Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk> Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2017-10-16 23:05:57 +08:00
bool oom;
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
lockdep_assert_held(&fq->lock);
net/fq_impl: drop get_default_func, move default flow to fq_tin Simplifies the code and prepares for a rework of scanning for flows on overmemory drop. Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-2-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:14 +08:00
flow = fq_flow_classify(fq, tin, idx, skb);
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
if (!flow->backlog) {
if (flow != &tin->default_flow)
__set_bit(idx, fq->flows_bitmap);
else if (list_empty(&tin->tin_list))
list_add(&tin->tin_list, &fq->tin_backlog);
}
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
flow->tin = tin;
flow->backlog += skb->len;
tin->backlog_bytes += skb->len;
tin->backlog_packets++;
fq.h: Port memory limit mechanism from fq_codel The reusable fairness queueing implementation (fq.h) lacks the memory usage limit that the fq_codel qdisc has. This means that small devices (e.g. WiFi routers) can run out of memory when flooded with a large number of packets. This ports the memory limit feature from fq_codel to fq.h. Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk> Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2016-09-24 03:59:09 +08:00
fq->memory_usage += skb->truesize;
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
fq->backlog++;
if (list_empty(&flow->flowchain)) {
flow->deficit = fq->quantum;
list_add_tail(&flow->flowchain,
&tin->new_flows);
}
__skb_queue_tail(&flow->queue, skb);
fq_impl: Properly enforce memory limit The fq structure would fail to properly enforce the memory limit in the case where the packet being enqueued was bigger than the packet being removed to bring the memory usage down. So keep dropping packets until the memory usage is back below the limit. Also, fix the statistics for memory limit violations. Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk> Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2017-10-16 23:05:57 +08:00
oom = (fq->memory_usage > fq->memory_limit);
while (fq->backlog > fq->limit || oom) {
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
flow = fq_find_fattest_flow(fq);
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
if (!flow)
return;
net/fq_impl: bulk-free packets from a flow on overmemory This is similar to what sch_fq_codel does. It also amortizes the worst case cost of a follow-up patch that changes the selection of the biggest flow for dropping packets Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-1-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:13 +08:00
if (!fq_flow_drop(fq, flow, free_func))
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
return;
flow->tin->overlimit++;
fq->overlimit++;
fq_impl: Properly enforce memory limit The fq structure would fail to properly enforce the memory limit in the case where the packet being enqueued was bigger than the packet being removed to bring the memory usage down. So keep dropping packets until the memory usage is back below the limit. Also, fix the statistics for memory limit violations. Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk> Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2017-10-16 23:05:57 +08:00
if (oom) {
fq.h: Port memory limit mechanism from fq_codel The reusable fairness queueing implementation (fq.h) lacks the memory usage limit that the fq_codel qdisc has. This means that small devices (e.g. WiFi routers) can run out of memory when flooded with a large number of packets. This ports the memory limit feature from fq_codel to fq.h. Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk> Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2016-09-24 03:59:09 +08:00
fq->overmemory++;
fq_impl: Properly enforce memory limit The fq structure would fail to properly enforce the memory limit in the case where the packet being enqueued was bigger than the packet being removed to bring the memory usage down. So keep dropping packets until the memory usage is back below the limit. Also, fix the statistics for memory limit violations. Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk> Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2017-10-16 23:05:57 +08:00
oom = (fq->memory_usage > fq->memory_limit);
}
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
}
}
fq: support filtering a given tin Add to the FQ API a way to filter a given tin, in order to remove frames that fulfil certain criteria according to a filter function. This will be used by mac80211 to remove frames belonging to an AP VLAN interface that's being removed. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Acked-by: Toke Høiland-Jørgensen <toke@toke.dk> Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2017-10-06 17:53:32 +08:00
static void fq_flow_filter(struct fq *fq,
struct fq_flow *flow,
fq_skb_filter_t filter_func,
void *filter_data,
fq_skb_free_t free_func)
{
struct fq_tin *tin = flow->tin;
struct sk_buff *skb, *tmp;
lockdep_assert_held(&fq->lock);
skb_queue_walk_safe(&flow->queue, skb, tmp) {
if (!filter_func(fq, tin, flow, skb, filter_data))
continue;
__skb_unlink(skb, &flow->queue);
fq_adjust_removal(fq, flow, skb);
free_func(fq, tin, flow, skb);
}
}
static void fq_tin_filter(struct fq *fq,
struct fq_tin *tin,
fq_skb_filter_t filter_func,
void *filter_data,
fq_skb_free_t free_func)
{
struct fq_flow *flow;
lockdep_assert_held(&fq->lock);
list_for_each_entry(flow, &tin->new_flows, flowchain)
fq_flow_filter(fq, flow, filter_func, filter_data, free_func);
list_for_each_entry(flow, &tin->old_flows, flowchain)
fq_flow_filter(fq, flow, filter_func, filter_data, free_func);
}
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
static void fq_flow_reset(struct fq *fq,
struct fq_flow *flow,
fq_skb_free_t free_func)
{
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
struct fq_tin *tin = flow->tin;
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
struct sk_buff *skb;
while ((skb = fq_flow_dequeue(fq, flow)))
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
free_func(fq, tin, flow, skb);
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
if (!list_empty(&flow->flowchain)) {
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
list_del_init(&flow->flowchain);
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
if (list_empty(&tin->new_flows) &&
list_empty(&tin->old_flows))
list_del_init(&tin->tin_list);
}
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
flow->tin = NULL;
WARN_ON_ONCE(flow->backlog);
}
static void fq_tin_reset(struct fq *fq,
struct fq_tin *tin,
fq_skb_free_t free_func)
{
struct list_head *head;
struct fq_flow *flow;
for (;;) {
head = &tin->new_flows;
if (list_empty(head)) {
head = &tin->old_flows;
if (list_empty(head))
break;
}
flow = list_first_entry(head, struct fq_flow, flowchain);
fq_flow_reset(fq, flow, free_func);
}
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
WARN_ON_ONCE(!list_empty(&tin->tin_list));
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
WARN_ON_ONCE(tin->backlog_bytes);
WARN_ON_ONCE(tin->backlog_packets);
}
static void fq_flow_init(struct fq_flow *flow)
{
INIT_LIST_HEAD(&flow->flowchain);
__skb_queue_head_init(&flow->queue);
}
static void fq_tin_init(struct fq_tin *tin)
{
INIT_LIST_HEAD(&tin->new_flows);
INIT_LIST_HEAD(&tin->old_flows);
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
INIT_LIST_HEAD(&tin->tin_list);
net/fq_impl: drop get_default_func, move default flow to fq_tin Simplifies the code and prepares for a rework of scanning for flows on overmemory drop. Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-2-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:14 +08:00
fq_flow_init(&tin->default_flow);
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
}
static int fq_init(struct fq *fq, int flows_cnt)
{
int i;
memset(fq, 0, sizeof(fq[0]));
spin_lock_init(&fq->lock);
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
INIT_LIST_HEAD(&fq->tin_backlog);
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
fq->flows_cnt = max_t(u32, flows_cnt, 1);
fq->quantum = 300;
fq->limit = 8192;
fq.h: Port memory limit mechanism from fq_codel The reusable fairness queueing implementation (fq.h) lacks the memory usage limit that the fq_codel qdisc has. This means that small devices (e.g. WiFi routers) can run out of memory when flooded with a large number of packets. This ports the memory limit feature from fq_codel to fq.h. Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk> Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2016-09-24 03:59:09 +08:00
fq->memory_limit = 16 << 20; /* 16 MBytes */
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
net/fq_impl: Switch to kvmalloc() for memory allocation The FQ implementation used by mac80211 allocates memory using kmalloc(), which can fail; and Johannes reported that this actually happens in practice. To avoid this, switch the allocation to kvmalloc() instead; this also brings fq_impl in line with all the FQ qdiscs. Fixes: 557fc4a09803 ("fq: add fair queuing framework") Reported-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/r/20191105155750.547379-1-toke@redhat.com Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2019-11-05 23:57:50 +08:00
fq->flows = kvcalloc(fq->flows_cnt, sizeof(fq->flows[0]), GFP_KERNEL);
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
if (!fq->flows)
return -ENOMEM;
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
fq->flows_bitmap = kcalloc(BITS_TO_LONGS(fq->flows_cnt), sizeof(long),
GFP_KERNEL);
if (!fq->flows_bitmap) {
kvfree(fq->flows);
fq->flows = NULL;
return -ENOMEM;
}
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
for (i = 0; i < fq->flows_cnt; i++)
fq_flow_init(&fq->flows[i]);
return 0;
}
static void fq_reset(struct fq *fq,
fq_skb_free_t free_func)
{
int i;
for (i = 0; i < fq->flows_cnt; i++)
fq_flow_reset(fq, &fq->flows[i], free_func);
net/fq_impl: Switch to kvmalloc() for memory allocation The FQ implementation used by mac80211 allocates memory using kmalloc(), which can fail; and Johannes reported that this actually happens in practice. To avoid this, switch the allocation to kvmalloc() instead; this also brings fq_impl in line with all the FQ qdiscs. Fixes: 557fc4a09803 ("fq: add fair queuing framework") Reported-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/r/20191105155750.547379-1-toke@redhat.com Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2019-11-05 23:57:50 +08:00
kvfree(fq->flows);
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
fq->flows = NULL;
net/fq_impl: do not maintain a backlog-sorted list of flows A sorted flow list is only needed to drop packets in the biggest flow when hitting the overmemory condition. By scanning flows only when needed, we can avoid paying the cost of maintaining the list under normal conditions In order to avoid scanning lots of empty flows and touching too many cold cache lines, a bitmap of flows with backlog is maintained Signed-off-by: Felix Fietkau <nbd@nbd.name> Link: https://lore.kernel.org/r/20201218184718.93650-3-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg@intel.com>
2020-12-19 02:47:15 +08:00
kfree(fq->flows_bitmap);
fq->flows_bitmap = NULL;
fq: add fair queuing framework This works on the same implementation principle as codel*.h, i.e. there's a generic header with structures and macros and a implementation header carrying function definitions to include in given, e.g. driver or module. The fairness logic comes from net/sched/sch_fq_codel.c but is generalized so it is more flexible and easier to re-use. Signed-off-by: Michal Kazior <michal.kazior@tieto.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-22 20:20:13 +08:00
}
#endif