Revision 5cbba60596b1f32f637190ca9ed5b1acdadb852c authored by Linus Torvalds on 31 August 2021, 20:21:58 UTC, committed by Linus Torvalds on 31 August 2021, 20:21:58 UTC
Pull power management updates from Rafael Wysocki: "These address some PCI device power management issues, add new hardware support to the RAPL power capping driver, add HWP guaranteed performance change notification support to the intel_pstate driver, replace deprecated CPU-hotplug functions in a few places, update CPU PM notifiers to use raw spinlocks, update the PM domains framework (new DT property support, Kconfig fix), do a couple of cleanups in code related to system sleep, and improve the energy model and the schedutil cpufreq governor. Specifics: - Address 3 PCI device power management issues (Rafael Wysocki). - Add Power Limit4 support for Alder Lake to the Intel RAPL power capping driver (Sumeet Pawnikar). - Add HWP guaranteed performance change notification support to the intel_pstate driver (Srinivas Pandruvada). - Replace deprecated CPU-hotplug functions in code related to power management (Sebastian Andrzej Siewior). - Update CPU PM notifiers to use raw spinlocks (Valentin Schneider). - Add support for 'required-opps' DT property to the generic power domains (genpd) framework and use this property for I2C on ARM64 sc7180 (Rajendra Nayak). - Fix Kconfig issue related to genpd (Geert Uytterhoeven). - Increase energy calculation precision in the Energy Model (Lukasz Luba). - Fix kobject deletion in the exit code of the schedutil cpufreq governor (Kevin Hao). - Unmark some functions as kernel-doc in the PM core to avoid false-positive documentation build warnings (Randy Dunlap). - Check RTC features instead of ops in suspend_test Alexandre Belloni)" * tag 'pm-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: PM: domains: Fix domain attach for CONFIG_PM_OPP=n powercap: Add Power Limit4 support for Alder Lake SoC cpufreq: intel_pstate: Process HWP Guaranteed change notification thermal: intel: Allow processing of HWP interrupt notifier: Remove atomic_notifier_call_chain_robust() PM: cpu: Make notifier chain use a raw_spinlock_t PM: sleep: unmark 'state' functions as kernel-doc arm64: dts: sc7180: Add required-opps for i2c PM: domains: Add support for 'required-opps' to set default perf state opp: Don't print an error if required-opps is missing cpufreq: schedutil: Use kobject release() method to free sugov_tunables PM: EM: Increase energy calculation precision PM: sleep: check RTC features instead of ops in suspend_test PM: sleep: s2idle: Replace deprecated CPU-hotplug functions cpufreq: Replace deprecated CPU-hotplug functions powercap: intel_rapl: Replace deprecated CPU-hotplug functions PCI: PM: Enable PME if it can be signaled from D3cold PCI: PM: Avoid forcing PCI_D0 for wakeup reasons inconsistently PCI: Use pci_update_current_state() in pci_enable_device_flags()
mm_init.c
// SPDX-License-Identifier: GPL-2.0-only
/*
* mm_init.c - Memory initialisation verification and debugging
*
* Copyright 2008 IBM Corporation, 2008
* Author Mel Gorman <mel@csn.ul.ie>
*
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/kobject.h>
#include <linux/export.h>
#include <linux/memory.h>
#include <linux/notifier.h>
#include <linux/sched.h>
#include <linux/mman.h>
#include "internal.h"
#ifdef CONFIG_DEBUG_MEMORY_INIT
int __meminitdata mminit_loglevel;
/* The zonelists are simply reported, validation is manual. */
void __init mminit_verify_zonelist(void)
{
int nid;
if (mminit_loglevel < MMINIT_VERIFY)
return;
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
struct zone *zone;
struct zoneref *z;
struct zonelist *zonelist;
int i, listid, zoneid;
BUILD_BUG_ON(MAX_ZONELISTS > 2);
for (i = 0; i < MAX_ZONELISTS * MAX_NR_ZONES; i++) {
/* Identify the zone and nodelist */
zoneid = i % MAX_NR_ZONES;
listid = i / MAX_NR_ZONES;
zonelist = &pgdat->node_zonelists[listid];
zone = &pgdat->node_zones[zoneid];
if (!populated_zone(zone))
continue;
/* Print information about the zonelist */
printk(KERN_DEBUG "mminit::zonelist %s %d:%s = ",
listid > 0 ? "thisnode" : "general", nid,
zone->name);
/* Iterate the zonelist */
for_each_zone_zonelist(zone, z, zonelist, zoneid)
pr_cont("%d:%s ", zone_to_nid(zone), zone->name);
pr_cont("\n");
}
}
}
void __init mminit_verify_pageflags_layout(void)
{
int shift, width;
unsigned long or_mask, add_mask;
shift = 8 * sizeof(unsigned long);
width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH
- LAST_CPUPID_SHIFT - KASAN_TAG_WIDTH;
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths",
"Section %d Node %d Zone %d Lastcpupid %d Kasantag %d Flags %d\n",
SECTIONS_WIDTH,
NODES_WIDTH,
ZONES_WIDTH,
LAST_CPUPID_WIDTH,
KASAN_TAG_WIDTH,
NR_PAGEFLAGS);
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts",
"Section %d Node %d Zone %d Lastcpupid %d Kasantag %d\n",
SECTIONS_SHIFT,
NODES_SHIFT,
ZONES_SHIFT,
LAST_CPUPID_SHIFT,
KASAN_TAG_WIDTH);
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_pgshifts",
"Section %lu Node %lu Zone %lu Lastcpupid %lu Kasantag %lu\n",
(unsigned long)SECTIONS_PGSHIFT,
(unsigned long)NODES_PGSHIFT,
(unsigned long)ZONES_PGSHIFT,
(unsigned long)LAST_CPUPID_PGSHIFT,
(unsigned long)KASAN_TAG_PGSHIFT);
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodezoneid",
"Node/Zone ID: %lu -> %lu\n",
(unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT),
(unsigned long)ZONEID_PGOFF);
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_usage",
"location: %d -> %d layout %d -> %d unused %d -> %d page-flags\n",
shift, width, width, NR_PAGEFLAGS, NR_PAGEFLAGS, 0);
#ifdef NODE_NOT_IN_PAGE_FLAGS
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
"Node not in page flags");
#endif
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
"Last cpupid not in page flags");
#endif
if (SECTIONS_WIDTH) {
shift -= SECTIONS_WIDTH;
BUG_ON(shift != SECTIONS_PGSHIFT);
}
if (NODES_WIDTH) {
shift -= NODES_WIDTH;
BUG_ON(shift != NODES_PGSHIFT);
}
if (ZONES_WIDTH) {
shift -= ZONES_WIDTH;
BUG_ON(shift != ZONES_PGSHIFT);
}
/* Check for bitmask overlaps */
or_mask = (ZONES_MASK << ZONES_PGSHIFT) |
(NODES_MASK << NODES_PGSHIFT) |
(SECTIONS_MASK << SECTIONS_PGSHIFT);
add_mask = (ZONES_MASK << ZONES_PGSHIFT) +
(NODES_MASK << NODES_PGSHIFT) +
(SECTIONS_MASK << SECTIONS_PGSHIFT);
BUG_ON(or_mask != add_mask);
}
static __init int set_mminit_loglevel(char *str)
{
get_option(&str, &mminit_loglevel);
return 0;
}
early_param("mminit_loglevel", set_mminit_loglevel);
#endif /* CONFIG_DEBUG_MEMORY_INIT */
struct kobject *mm_kobj;
EXPORT_SYMBOL_GPL(mm_kobj);
#ifdef CONFIG_SMP
s32 vm_committed_as_batch = 32;
void mm_compute_batch(int overcommit_policy)
{
u64 memsized_batch;
s32 nr = num_present_cpus();
s32 batch = max_t(s32, nr*2, 32);
unsigned long ram_pages = totalram_pages();
/*
* For policy OVERCOMMIT_NEVER, set batch size to 0.4% of
* (total memory/#cpus), and lift it to 25% for other policies
* to easy the possible lock contention for percpu_counter
* vm_committed_as, while the max limit is INT_MAX
*/
if (overcommit_policy == OVERCOMMIT_NEVER)
memsized_batch = min_t(u64, ram_pages/nr/256, INT_MAX);
else
memsized_batch = min_t(u64, ram_pages/nr/4, INT_MAX);
vm_committed_as_batch = max_t(s32, memsized_batch, batch);
}
static int __meminit mm_compute_batch_notifier(struct notifier_block *self,
unsigned long action, void *arg)
{
switch (action) {
case MEM_ONLINE:
case MEM_OFFLINE:
mm_compute_batch(sysctl_overcommit_memory);
break;
default:
break;
}
return NOTIFY_OK;
}
static struct notifier_block compute_batch_nb __meminitdata = {
.notifier_call = mm_compute_batch_notifier,
.priority = IPC_CALLBACK_PRI, /* use lowest priority */
};
static int __init mm_compute_batch_init(void)
{
mm_compute_batch(sysctl_overcommit_memory);
register_hotmemory_notifier(&compute_batch_nb);
return 0;
}
__initcall(mm_compute_batch_init);
#endif
static int __init mm_sysfs_init(void)
{
mm_kobj = kobject_create_and_add("mm", kernel_kobj);
if (!mm_kobj)
return -ENOMEM;
return 0;
}
postcore_initcall(mm_sysfs_init);
Computing file changes ...