linux/lib/dynamic_queue_limits.c
Linus Torvalds 5bbcc0f595 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...
2017-11-15 11:56:19 -08:00

139 lines
4.3 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Dynamic byte queue limits. See include/linux/dynamic_queue_limits.h
*
* Copyright (c) 2011, Tom Herbert <therbert@google.com>
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/jiffies.h>
#include <linux/dynamic_queue_limits.h>
#include <linux/compiler.h>
#include <linux/export.h>
#define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0)
#define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0)
/* Records completed count and recalculates the queue limit */
void dql_completed(struct dql *dql, unsigned int count)
{
unsigned int inprogress, prev_inprogress, limit;
unsigned int ovlimit, completed, num_queued;
bool all_prev_completed;
num_queued = READ_ONCE(dql->num_queued);
/* Can't complete more than what's in queue */
BUG_ON(count > num_queued - dql->num_completed);
completed = dql->num_completed + count;
limit = dql->limit;
ovlimit = POSDIFF(num_queued - dql->num_completed, limit);
inprogress = num_queued - completed;
prev_inprogress = dql->prev_num_queued - dql->num_completed;
all_prev_completed = AFTER_EQ(completed, dql->prev_num_queued);
if ((ovlimit && !inprogress) ||
(dql->prev_ovlimit && all_prev_completed)) {
/*
* Queue considered starved if:
* - The queue was over-limit in the last interval,
* and there is no more data in the queue.
* OR
* - The queue was over-limit in the previous interval and
* when enqueuing it was possible that all queued data
* had been consumed. This covers the case when queue
* may have becomes starved between completion processing
* running and next time enqueue was scheduled.
*
* When queue is starved increase the limit by the amount
* of bytes both sent and completed in the last interval,
* plus any previous over-limit.
*/
limit += POSDIFF(completed, dql->prev_num_queued) +
dql->prev_ovlimit;
dql->slack_start_time = jiffies;
dql->lowest_slack = UINT_MAX;
} else if (inprogress && prev_inprogress && !all_prev_completed) {
/*
* Queue was not starved, check if the limit can be decreased.
* A decrease is only considered if the queue has been busy in
* the whole interval (the check above).
*
* If there is slack, the amount of execess data queued above
* the the amount needed to prevent starvation, the queue limit
* can be decreased. To avoid hysteresis we consider the
* minimum amount of slack found over several iterations of the
* completion routine.
*/
unsigned int slack, slack_last_objs;
/*
* Slack is the maximum of
* - The queue limit plus previous over-limit minus twice
* the number of objects completed. Note that two times
* number of completed bytes is a basis for an upper bound
* of the limit.
* - Portion of objects in the last queuing operation that
* was not part of non-zero previous over-limit. That is
* "round down" by non-overlimit portion of the last
* queueing operation.
*/
slack = POSDIFF(limit + dql->prev_ovlimit,
2 * (completed - dql->num_completed));
slack_last_objs = dql->prev_ovlimit ?
POSDIFF(dql->prev_last_obj_cnt, dql->prev_ovlimit) : 0;
slack = max(slack, slack_last_objs);
if (slack < dql->lowest_slack)
dql->lowest_slack = slack;
if (time_after(jiffies,
dql->slack_start_time + dql->slack_hold_time)) {
limit = POSDIFF(limit, dql->lowest_slack);
dql->slack_start_time = jiffies;
dql->lowest_slack = UINT_MAX;
}
}
/* Enforce bounds on limit */
limit = clamp(limit, dql->min_limit, dql->max_limit);
if (limit != dql->limit) {
dql->limit = limit;
ovlimit = 0;
}
dql->adj_limit = limit + completed;
dql->prev_ovlimit = ovlimit;
dql->prev_last_obj_cnt = dql->last_obj_cnt;
dql->num_completed = completed;
dql->prev_num_queued = num_queued;
}
EXPORT_SYMBOL(dql_completed);
void dql_reset(struct dql *dql)
{
/* Reset all dynamic values */
dql->limit = 0;
dql->num_queued = 0;
dql->num_completed = 0;
dql->last_obj_cnt = 0;
dql->prev_num_queued = 0;
dql->prev_last_obj_cnt = 0;
dql->prev_ovlimit = 0;
dql->lowest_slack = UINT_MAX;
dql->slack_start_time = jiffies;
}
EXPORT_SYMBOL(dql_reset);
void dql_init(struct dql *dql, unsigned int hold_time)
{
dql->max_limit = DQL_MAX_LIMIT;
dql->min_limit = 0;
dql->slack_hold_time = hold_time;
dql_reset(dql);
}
EXPORT_SYMBOL(dql_init);