path: root/drivers/idle/intel_idle.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * intel_idle.c - native hardware idle loop for modern Intel processors
 *
 * Copyright (c) 2013, Intel Corporation.
 * Len Brown <len.brown@intel.com>
 */

/*
 * intel_idle is a cpuidle driver that loads on specific Intel processors
 * in lieu of the legacy ACPI processor_idle driver.  The intent is to
 * make Linux more efficient on these processors, as intel_idle knows
 * more than ACPI, as well as make Linux more immune to ACPI BIOS bugs.
 */

/*
 * Design Assumptions
 *
 * All CPUs have same idle states as boot CPU
 *
 * Chipset BM_STS (bus master status) bit is a NOP
 *	for preventing entry into deep C-stats
 */

/*
 * Known limitations
 *
 * The driver currently initializes for_each_online_cpu() upon modprobe.
 * It it unaware of subsequent processors hot-added to the system.
 * This means that if you boot with maxcpus=n and later online
 * processors above n, those processors will use C1 only.
 *
 * ACPI has a .suspend hack to turn off deep c-statees during suspend
 * to avoid complications with the lapic timer workaround.
 * Have not seen issues with suspend, but may need same workaround here.
 *
 */

/* un-comment DEBUG to enable pr_debug() statements */
#define DEBUG

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/cpuidle.h>
#include <linux/tick.h>
#include <trace/events/power.h>
#include <linux/sched.h>
#include <linux/sched/smt.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/moduleparam.h>
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#include <asm/nospec-branch.h>
#include <asm/mwait.h>
#include <asm/msr.h>

#define INTEL_IDLE_VERSION "0.4.1"

static struct cpuidle_driver intel_idle_driver = {
	.name = "intel_idle",
	.owner = THIS_MODULE,
};
/* intel_idle.max_cstate=0 disables driver */
static int max_cstate = CPUIDLE_STATE_MAX - 1;

static unsigned int mwait_substates;

#define LAPIC_TIMER_ALWAYS_RELIABLE 0xFFFFFFFF
/* Reliable LAPIC Timer States, bit 1 for C1 etc.  */
static unsigned int lapic_timer_reliable_states = (1 << 1);	 /* Default to only C1 */

struct idle_cpu {
	struct cpuidle_state *state_table;

	/*
	 * Hardware C-state auto-demotion may not always be optimal.
	 * Indicate which enable bits to clear here.
	 */
	unsigned long auto_demotion_disable_flags;
	bool byt_auto_demotion_disable_flag;
	bool disable_promotion_to_c1e;
};

static const struct idle_cpu *icpu;
static struct cpuidle_device __percpu *intel_idle_cpuidle_devices;
static int intel_idle(struct cpuidle_device *dev,
			struct cpuidle_driver *drv, int index);
static void intel_idle_s2idle(struct cpuidle_device *dev,
			      struct cpuidle_driver *drv, int index);
static struct cpuidle_state *cpuidle_state_table;

/*
 * Set this flag for states where the HW flushes the TLB for us
 * and so we don't need cross-calls to keep it consistent.
 * If this flag is set, SW flushes the TLB, so even if the
 * HW doesn't do the flushing, this flag is safe to use.
 */
#define CPUIDLE_FLAG_TLB_FLUSHED	0x10000

/*
 * Disable IBRS across idle (when KERNEL_IBRS), is exclusive vs IRQ_ENABLE
 * above.
 */
#define CPUIDLE_FLAG_IBRS		BIT(16)

/*
 * MWAIT takes an 8-bit "hint" in EAX "suggesting"
 * the C-state (top nibble) and sub-state (bottom nibble)
 * 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc.
 *
 * We store the hint at the top of our "flags" for each state.
 */
#define flg2MWAIT(flags) (((flags) >> 24) & 0xFF)
#define MWAIT2flg(eax) ((eax & 0xFF) << 24)

static __cpuidle int intel_idle_ibrs(struct cpuidle_device *dev,
				     struct cpuidle_driver *drv, int index)
{
	bool smt_active = sched_smt_active();
	u64 spec_ctrl = spec_ctrl_current();
	int ret;

	if (smt_active)
		wrmsrl(MSR_IA32_SPEC_CTRL, 0);

	ret = intel_idle(dev, drv, index);

	if (smt_active)
		wrmsrl(MSR_IA32_SPEC_CTRL, spec_ctrl);

	return ret;
}

/*
 * States are indexed by the cstate number,
 * which is also the index into the MWAIT hint array.
 * Thus C0 is a dummy.
 */
static struct cpuidle_state nehalem_cstates[] = {
	{
		.name = "C1",
		.desc = "MWAIT 0x00",
		.flags = MWAIT2flg(0x00),
		.exit_latency = 3,
		.target_residency = 6,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C1E",
		.desc = "MWAIT 0x01",
		.flags = MWAIT2flg(0x01),
		.exit_latency = 10,
		.target_residency = 20,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C3",
		.desc = "MWAIT 0x10",
		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
		.exit_latency = 20,
		.target_residency = 80,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C6",
		.desc = "MWAIT 0x20",
		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
		.exit_latency = 200,
		.target_residency = 800,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.enter = NULL }
};

static struct cpuidle_state snb_cstates[] = {
	{
		.name = "C1",
		.desc = "MWAIT 0x00",
		.flags = MWAIT2flg(0x00),
		.exit_latency = 2,
		.target_residency = 2,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C1E",
		.desc = "MWAIT 0x01",
		.flags = MWAIT2flg(0x01),
		.exit_latency = 10,
		.target_residency = 20,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C3",
		.desc = "MWAIT 0x10",
		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
		.exit_latency = 80,
		.target_residency = 211,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C6",
		.desc = "MWAIT 0x20",
		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
		.exit_latency = 104,
		.target_residency = 345,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C7",
		.desc = "MWAIT 0x30",
		.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TLB_FLUSHED,
		.exit_latency = 109,
		.target_residency = 345,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.enter = NULL }
};

static struct cpuidle_state byt_cstates[] = {
	{
		.name = "C1",
		.desc = "MWAIT 0x00",
		.flags = MWAIT2flg(0x00),
		.exit_latency = 1,
		.target_residency = 1,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C6N",
		.desc = "MWAIT 0x58",
		.flags = MWAIT2flg(0x58) | CPUIDLE_FLAG_TLB_FLUSHED,
		.exit_latency = 300,
		.target_residency = 275,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C6S",
		.desc = "MWAIT 0x52",
		.flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TLB_FLUSHED,
		.exit_latency = 500,
		.target_residency = 560,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C7",
		.desc = "MWAIT 0x60",
		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
		.exit_latency = 1200,
		.target_residency = 4000,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C7S",
		.desc = "MWAIT 0x64",
		.flags = MWAIT2flg(0x64) | CPUIDLE_FLAG_TLB_FLUSHED,
		.exit_latency = 10000,
		.target_residency = 20000,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.enter = NULL }
};

static struct cpuidle_state cht_cstates[] = {
	{
		.name = "C1",
		.desc = "MWAIT 0x00",
		.flags = MWAIT2flg(0x00),
		.exit_latency = 1,
		.target_residency = 1,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C6N",
		.desc = "MWAIT 0x58",
		.flags = MWAIT2flg(0x58) | CPUIDLE_FLAG_TLB_FLUSHED,
		.exit_latency = 80,
		.target_residency = 275,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C6S",
		.desc = "MWAIT 0x52",
		.flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TLB_FLUSHED,
		.exit_latency = 200,
		.target_residency = 560,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C7",
		.desc = "MWAIT 0x60",
		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
		.exit_latency = 1200,
		.target_residency = 4000,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C7S",
		.desc = "MWAIT 0x64",
		.flags = MWAIT2flg(0x64) | CPUIDLE_FLAG_TLB_FLUSHED,
		.exit_latency = 10000,
		.target_residency = 20000,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.enter = NULL }
};

static struct cpuidle_state ivb_cstates[] = {
	{
		.name = "C1",
		.desc = "MWAIT 0x00",
		.flags = MWAIT2flg(0x00),
		.exit_latency = 1,
		.target_residency = 1,
		.enter = &intel_idle,
		.enter_s2idle = intel_idle_s2idle, },
	{
		.name = "C1E",
		.desc = "MWAIT 0x01",
		.flags = MWAIT2flg(0x01),
		.exit_latency =