mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-25 02:09:42 +00:00
![Matteo Croce](/assets/img/avatar_default.png)
In the sysctl code the proc_dointvec_minmax() function is often used to validate the user supplied value between an allowed range. This function uses the extra1 and extra2 members from struct ctl_table as minimum and maximum allowed value. On sysctl handler declaration, in every source file there are some readonly variables containing just an integer which address is assigned to the extra1 and extra2 members, so the sysctl range is enforced. The special values 0, 1 and INT_MAX are very often used as range boundary, leading duplication of variables like zero=0, one=1, int_max=INT_MAX in different source files: $ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l 248 Add a const int array containing the most commonly used values, some macros to refer more easily to the correct array member, and use them instead of creating a local one for every object file. This is the bloat-o-meter output comparing the old and new binary compiled with the default Fedora config: # scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164) Data old new delta sysctl_vals - 12 +12 __kstrtab_sysctl_vals - 12 +12 max 14 10 -4 int_max 16 - -16 one 68 - -68 zero 128 28 -100 Total: Before=20583249, After=20583085, chg -0.00% [mcroce@redhat.com: tipc: remove two unused variables] Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com [akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c] [arnd@arndb.de: proc/sysctl: make firmware loader table conditional] Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de [akpm@linux-foundation.org: fix fs/eventpoll.c] Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com Signed-off-by: Matteo Croce <mcroce@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Kees Cook <keescook@chromium.org> Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
206 lines
5.1 KiB
C
206 lines
5.1 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* itmt.c: Support Intel Turbo Boost Max Technology 3.0
|
|
*
|
|
* (C) Copyright 2016 Intel Corporation
|
|
* Author: Tim Chen <tim.c.chen@linux.intel.com>
|
|
*
|
|
* On platforms supporting Intel Turbo Boost Max Technology 3.0, (ITMT),
|
|
* the maximum turbo frequencies of some cores in a CPU package may be
|
|
* higher than for the other cores in the same package. In that case,
|
|
* better performance can be achieved by making the scheduler prefer
|
|
* to run tasks on the CPUs with higher max turbo frequencies.
|
|
*
|
|
* This file provides functions and data structures for enabling the
|
|
* scheduler to favor scheduling on cores can be boosted to a higher
|
|
* frequency under ITMT.
|
|
*/
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/cpuset.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/sysctl.h>
|
|
#include <linux/nodemask.h>
|
|
|
|
static DEFINE_MUTEX(itmt_update_mutex);
|
|
DEFINE_PER_CPU_READ_MOSTLY(int, sched_core_priority);
|
|
|
|
/* Boolean to track if system has ITMT capabilities */
|
|
static bool __read_mostly sched_itmt_capable;
|
|
|
|
/*
|
|
* Boolean to control whether we want to move processes to cpu capable
|
|
* of higher turbo frequency for cpus supporting Intel Turbo Boost Max
|
|
* Technology 3.0.
|
|
*
|
|
* It can be set via /proc/sys/kernel/sched_itmt_enabled
|
|
*/
|
|
unsigned int __read_mostly sysctl_sched_itmt_enabled;
|
|
|
|
static int sched_itmt_update_handler(struct ctl_table *table, int write,
|
|
void __user *buffer, size_t *lenp,
|
|
loff_t *ppos)
|
|
{
|
|
unsigned int old_sysctl;
|
|
int ret;
|
|
|
|
mutex_lock(&itmt_update_mutex);
|
|
|
|
if (!sched_itmt_capable) {
|
|
mutex_unlock(&itmt_update_mutex);
|
|
return -EINVAL;
|
|
}
|
|
|
|
old_sysctl = sysctl_sched_itmt_enabled;
|
|
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
|
|
|
|
if (!ret && write && old_sysctl != sysctl_sched_itmt_enabled) {
|
|
x86_topology_update = true;
|
|
rebuild_sched_domains();
|
|
}
|
|
|
|
mutex_unlock(&itmt_update_mutex);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static struct ctl_table itmt_kern_table[] = {
|
|
{
|
|
.procname = "sched_itmt_enabled",
|
|
.data = &sysctl_sched_itmt_enabled,
|
|
.maxlen = sizeof(unsigned int),
|
|
.mode = 0644,
|
|
.proc_handler = sched_itmt_update_handler,
|
|
.extra1 = SYSCTL_ZERO,
|
|
.extra2 = SYSCTL_ONE,
|
|
},
|
|
{}
|
|
};
|
|
|
|
static struct ctl_table itmt_root_table[] = {
|
|
{
|
|
.procname = "kernel",
|
|
.mode = 0555,
|
|
.child = itmt_kern_table,
|
|
},
|
|
{}
|
|
};
|
|
|
|
static struct ctl_table_header *itmt_sysctl_header;
|
|
|
|
/**
|
|
* sched_set_itmt_support() - Indicate platform supports ITMT
|
|
*
|
|
* This function is used by the OS to indicate to scheduler that the platform
|
|
* is capable of supporting the ITMT feature.
|
|
*
|
|
* The current scheme has the pstate driver detects if the system
|
|
* is ITMT capable and call sched_set_itmt_support.
|
|
*
|
|
* This must be done only after sched_set_itmt_core_prio
|
|
* has been called to set the cpus' priorities.
|
|
* It must not be called with cpu hot plug lock
|
|
* held as we need to acquire the lock to rebuild sched domains
|
|
* later.
|
|
*
|
|
* Return: 0 on success
|
|
*/
|
|
int sched_set_itmt_support(void)
|
|
{
|
|
mutex_lock(&itmt_update_mutex);
|
|
|
|
if (sched_itmt_capable) {
|
|
mutex_unlock(&itmt_update_mutex);
|
|
return 0;
|
|
}
|
|
|
|
itmt_sysctl_header = register_sysctl_table(itmt_root_table);
|
|
if (!itmt_sysctl_header) {
|
|
mutex_unlock(&itmt_update_mutex);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
sched_itmt_capable = true;
|
|
|
|
sysctl_sched_itmt_enabled = 1;
|
|
|
|
x86_topology_update = true;
|
|
rebuild_sched_domains();
|
|
|
|
mutex_unlock(&itmt_update_mutex);
|
|
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* sched_clear_itmt_support() - Revoke platform's support of ITMT
|
|
*
|
|
* This function is used by the OS to indicate that it has
|
|
* revoked the platform's support of ITMT feature.
|
|
*
|
|
* It must not be called with cpu hot plug lock
|
|
* held as we need to acquire the lock to rebuild sched domains
|
|
* later.
|
|
*/
|
|
void sched_clear_itmt_support(void)
|
|
{
|
|
mutex_lock(&itmt_update_mutex);
|
|
|
|
if (!sched_itmt_capable) {
|
|
mutex_unlock(&itmt_update_mutex);
|
|
return;
|
|
}
|
|
sched_itmt_capable = false;
|
|
|
|
if (itmt_sysctl_header) {
|
|
unregister_sysctl_table(itmt_sysctl_header);
|
|
itmt_sysctl_header = NULL;
|
|
}
|
|
|
|
if (sysctl_sched_itmt_enabled) {
|
|
/* disable sched_itmt if we are no longer ITMT capable */
|
|
sysctl_sched_itmt_enabled = 0;
|
|
x86_topology_update = true;
|
|
rebuild_sched_domains();
|
|
}
|
|
|
|
mutex_unlock(&itmt_update_mutex);
|
|
}
|
|
|
|
int arch_asym_cpu_priority(int cpu)
|
|
{
|
|
return per_cpu(sched_core_priority, cpu);
|
|
}
|
|
|
|
/**
|
|
* sched_set_itmt_core_prio() - Set CPU priority based on ITMT
|
|
* @prio: Priority of cpu core
|
|
* @core_cpu: The cpu number associated with the core
|
|
*
|
|
* The pstate driver will find out the max boost frequency
|
|
* and call this function to set a priority proportional
|
|
* to the max boost frequency. CPU with higher boost
|
|
* frequency will receive higher priority.
|
|
*
|
|
* No need to rebuild sched domain after updating
|
|
* the CPU priorities. The sched domains have no
|
|
* dependency on CPU priorities.
|
|
*/
|
|
void sched_set_itmt_core_prio(int prio, int core_cpu)
|
|
{
|
|
int cpu, i = 1;
|
|
|
|
for_each_cpu(cpu, topology_sibling_cpumask(core_cpu)) {
|
|
int smt_prio;
|
|
|
|
/*
|
|
* Ensure that the siblings are moved to the end
|
|
* of the priority chain and only used when
|
|
* all other high priority cpus are out of capacity.
|
|
*/
|
|
smt_prio = prio * smp_num_siblings / i;
|
|
per_cpu(sched_core_priority, cpu) = smt_prio;
|
|
i++;
|
|
}
|
|
}
|