aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-02-20 11:26:56 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2013-02-20 11:26:56 -0800
commit8793422fd9ac5037f5047f80473007301df3689f (patch)
treef5aa3b3a564f053e1b5604c45db80193abc734a4 /arch/x86/kernel
parentb3cdda2b4f541439ca4205793040aa2e1c852e3b (diff)
parent10baf04e95fbf7eb6089410220a547211dd2ffa7 (diff)
downloadvexpress-lsk-8793422fd9ac5037f5047f80473007301df3689f.tar.gz
Merge tag 'pm+acpi-3.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull ACPI and power management updates from Rafael Wysocki: - Rework of the ACPI namespace scanning code from Rafael J. Wysocki with contributions from Bjorn Helgaas, Jiang Liu, Mika Westerberg, Toshi Kani, and Yinghai Lu. - ACPI power resources handling and ACPI device PM update from Rafael J Wysocki. - ACPICA update to version 20130117 from Bob Moore and Lv Zheng with contributions from Aaron Lu, Chao Guan, Jesper Juhl, and Tim Gardner. - Support for Intel Lynxpoint LPSS from Mika Westerberg. - cpuidle update from Len Brown including Intel Haswell support, C1 state for intel_idle, removal of global pm_idle. - cpuidle fixes and cleanups from Daniel Lezcano. - cpufreq fixes and cleanups from Viresh Kumar and Fabio Baltieri with contributions from Stratos Karafotis and Rickard Andersson. - Intel P-states driver for Sandy Bridge processors from Dirk Brandewie. - cpufreq driver for Marvell Kirkwood SoCs from Andrew Lunn. - cpufreq fixes related to ordering issues between acpi-cpufreq and powernow-k8 from Borislav Petkov and Matthew Garrett. - cpufreq support for Calxeda Highbank processors from Mark Langsdorf and Rob Herring. - cpufreq driver for the Freescale i.MX6Q SoC and cpufreq-cpu0 update from Shawn Guo. - cpufreq Exynos fixes and cleanups from Jonghwan Choi, Sachin Kamat, and Inderpal Singh. - Support for "lightweight suspend" from Zhang Rui. - Removal of the deprecated power trace API from Paul Gortmaker. - Assorted updates from Andreas Fleig, Colin Ian King, Davidlohr Bueso, Joseph Salisbury, Kees Cook, Li Fei, Nishanth Menon, ShuoX Liu, Srinivas Pandruvada, Tejun Heo, Thomas Renninger, and Yasuaki Ishimatsu. * tag 'pm+acpi-3.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (267 commits) PM idle: remove global declaration of pm_idle unicore32 idle: delete stray pm_idle comment openrisc idle: delete pm_idle mn10300 idle: delete pm_idle microblaze idle: delete pm_idle m32r idle: delete pm_idle, and other dead idle code ia64 idle: delete pm_idle cris idle: delete idle and pm_idle ARM64 idle: delete pm_idle ARM idle: delete pm_idle blackfin idle: delete pm_idle sparc idle: rename pm_idle to sparc_idle sh idle: rename global pm_idle to static sh_idle x86 idle: rename global pm_idle to static x86_idle APM idle: register apm_cpu_idle via cpuidle cpufreq / intel_pstate: Add kernel command line option disable intel_pstate. cpufreq / intel_pstate: Change to disallow module build tools/power turbostat: display SMI count by default intel_idle: export both C1 and C1E ACPI / hotplug: Fix concurrency issues and memory leaks ...
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/apm_32.c57
-rw-r--r--arch/x86/kernel/cpu/bugs.c27
-rw-r--r--arch/x86/kernel/cpu/proc.c2
-rw-r--r--arch/x86/kernel/process.c122
-rw-r--r--arch/x86/kernel/smpboot.c2
5 files changed, 52 insertions, 158 deletions
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 8d7012b7f40..66b5faffe14 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -232,6 +232,7 @@
#include <linux/acpi.h>
#include <linux/syscore_ops.h>
#include <linux/i8253.h>
+#include <linux/cpuidle.h>
#include <asm/uaccess.h>
#include <asm/desc.h>
@@ -360,13 +361,35 @@ struct apm_user {
* idle percentage above which bios idle calls are done
*/
#ifdef CONFIG_APM_CPU_IDLE
-#warning deprecated CONFIG_APM_CPU_IDLE will be deleted in 2012
#define DEFAULT_IDLE_THRESHOLD 95
#else
#define DEFAULT_IDLE_THRESHOLD 100
#endif
#define DEFAULT_IDLE_PERIOD (100 / 3)
+static int apm_cpu_idle(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int index);
+
+static struct cpuidle_driver apm_idle_driver = {
+ .name = "apm_idle",
+ .owner = THIS_MODULE,
+ .en_core_tk_irqen = 1,
+ .states = {
+ { /* entry 0 is for polling */ },
+ { /* entry 1 is for APM idle */
+ .name = "APM",
+ .desc = "APM idle",
+ .flags = CPUIDLE_FLAG_TIME_VALID,
+ .exit_latency = 250, /* WAG */
+ .target_residency = 500, /* WAG */
+ .enter = &apm_cpu_idle
+ },
+ },
+ .state_count = 2,
+};
+
+static struct cpuidle_device apm_cpuidle_device;
+
/*
* Local variables
*/
@@ -377,7 +400,6 @@ static struct {
static int clock_slowed;
static int idle_threshold __read_mostly = DEFAULT_IDLE_THRESHOLD;
static int idle_period __read_mostly = DEFAULT_IDLE_PERIOD;
-static int set_pm_idle;
static int suspends_pending;
static int standbys_pending;
static int ignore_sys_suspend;
@@ -884,8 +906,6 @@ static void apm_do_busy(void)
#define IDLE_CALC_LIMIT (HZ * 100)
#define IDLE_LEAKY_MAX 16
-static void (*original_pm_idle)(void) __read_mostly;
-
/**
* apm_cpu_idle - cpu idling for APM capable Linux
*
@@ -894,7 +914,8 @@ static void (*original_pm_idle)(void) __read_mostly;
* Furthermore it calls the system default idle routine.
*/
-static void apm_cpu_idle(void)
+static int apm_cpu_idle(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int index)
{
static int use_apm_idle; /* = 0 */
static unsigned int last_jiffies; /* = 0 */
@@ -905,7 +926,6 @@ static void apm_cpu_idle(void)
unsigned int jiffies_since_last_check = jiffies - last_jiffies;
unsigned int bucket;
- WARN_ONCE(1, "deprecated apm_cpu_idle will be deleted in 2012");
recalc:
task_cputime(current, NULL, &stime);
if (jiffies_since_last_check > IDLE_CALC_LIMIT) {
@@ -951,10 +971,7 @@ recalc:
break;
}
}
- if (original_pm_idle)
- original_pm_idle();
- else
- default_idle();
+ default_idle();
local_irq_disable();
jiffies_since_last_check = jiffies - last_jiffies;
if (jiffies_since_last_check > idle_period)
@@ -964,7 +981,7 @@ recalc:
if (apm_idle_done)
apm_do_busy();
- local_irq_enable();
+ return index;
}
/**
@@ -2382,9 +2399,9 @@ static int __init apm_init(void)
if (HZ != 100)
idle_period = (idle_period * HZ) / 100;
if (idle_threshold < 100) {
- original_pm_idle = pm_idle;
- pm_idle = apm_cpu_idle;
- set_pm_idle = 1;
+ if (!cpuidle_register_driver(&apm_idle_driver))
+ if (cpuidle_register_device(&apm_cpuidle_device))
+ cpuidle_unregister_driver(&apm_idle_driver);
}
return 0;
@@ -2394,15 +2411,9 @@ static void __exit apm_exit(void)
{
int error;
- if (set_pm_idle) {
- pm_idle = original_pm_idle;
- /*
- * We are about to unload the current idle thread pm callback
- * (pm_idle), Wait for all processors to update cached/local
- * copies of pm_idle before proceeding.
- */
- kick_all_cpus_sync();
- }
+ cpuidle_unregister_device(&apm_cpuidle_device);
+ cpuidle_unregister_driver(&apm_idle_driver);
+
if (((apm_info.bios.flags & APM_BIOS_DISENGAGED) == 0)
&& (apm_info.connection_version > 0x0100)) {
error = apm_engage_power_management(APM_DEVICE_ALL, 0);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 92dfec986a4..af6455e3fcc 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -17,15 +17,6 @@
#include <asm/paravirt.h>
#include <asm/alternative.h>
-static int __init no_halt(char *s)
-{
- WARN_ONCE(1, "\"no-hlt\" is deprecated, please use \"idle=poll\"\n");
- boot_cpu_data.hlt_works_ok = 0;
- return 1;
-}
-
-__setup("no-hlt", no_halt);
-
static int __init no_387(char *s)
{
boot_cpu_data.hard_math = 0;
@@ -89,23 +80,6 @@ static void __init check_fpu(void)
pr_warn("Hmm, FPU with FDIV bug\n");
}
-static void __init check_hlt(void)
-{
- if (boot_cpu_data.x86 >= 5 || paravirt_enabled())
- return;
-
- pr_info("Checking 'hlt' instruction... ");
- if (!boot_cpu_data.hlt_works_ok) {
- pr_cont("disabled\n");
- return;
- }
- halt();
- halt();
- halt();
- halt();
- pr_cont("OK\n");
-}
-
/*
* Check whether we are able to run this kernel safely on SMP.
*
@@ -129,7 +103,6 @@ void __init check_bugs(void)
print_cpu_info(&boot_cpu_data);
#endif
check_config();
- check_hlt();
init_utsname()->machine[1] =
'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
alternative_instructions();
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 3286a92e662..e280253f6f9 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -28,7 +28,6 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c)
{
seq_printf(m,
"fdiv_bug\t: %s\n"
- "hlt_bug\t\t: %s\n"
"f00f_bug\t: %s\n"
"coma_bug\t: %s\n"
"fpu\t\t: %s\n"
@@ -36,7 +35,6 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c)
"cpuid level\t: %d\n"
"wp\t\t: %s\n",
c->fdiv_bug ? "yes" : "no",
- c->hlt_works_ok ? "no" : "yes",
c->f00f_bug ? "yes" : "no",
c->coma_bug ? "yes" : "no",
c->hard_math ? "yes" : "no",
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 2ed787f15bf..14ae10031ff 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -268,13 +268,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE;
EXPORT_SYMBOL(boot_option_idle_override);
-/*
- * Powermanagement idle function, if any..
- */
-void (*pm_idle)(void);
-#ifdef CONFIG_APM_MODULE
-EXPORT_SYMBOL(pm_idle);
-#endif
+static void (*x86_idle)(void);
#ifndef CONFIG_SMP
static inline void play_dead(void)
@@ -351,7 +345,7 @@ void cpu_idle(void)
rcu_idle_enter();
if (cpuidle_idle_call())
- pm_idle();
+ x86_idle();
rcu_idle_exit();
start_critical_timings();
@@ -375,7 +369,6 @@ void cpu_idle(void)
*/
void default_idle(void)
{
- trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id());
trace_cpu_idle_rcuidle(1, smp_processor_id());
current_thread_info()->status &= ~TS_POLLING;
/*
@@ -389,21 +382,22 @@ void default_idle(void)
else
local_irq_enable();
current_thread_info()->status |= TS_POLLING;
- trace_power_end_rcuidle(smp_processor_id());
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
}
#ifdef CONFIG_APM_MODULE
EXPORT_SYMBOL(default_idle);
#endif
-bool set_pm_idle_to_default(void)
+#ifdef CONFIG_XEN
+bool xen_set_default_idle(void)
{
- bool ret = !!pm_idle;
+ bool ret = !!x86_idle;
- pm_idle = default_idle;
+ x86_idle = default_idle;
return ret;
}
+#endif
void stop_this_cpu(void *dummy)
{
local_irq_disable();
@@ -413,31 +407,8 @@ void stop_this_cpu(void *dummy)
set_cpu_online(smp_processor_id(), false);
disable_local_APIC();
- for (;;) {
- if (hlt_works(smp_processor_id()))
- halt();
- }
-}
-
-/* Default MONITOR/MWAIT with no hints, used for default C1 state */
-static void mwait_idle(void)
-{
- if (!need_resched()) {
- trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id());
- trace_cpu_idle_rcuidle(1, smp_processor_id());
- if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
- clflush((void *)&current_thread_info()->flags);
-
- __monitor((void *)&current_thread_info()->flags, 0, 0);
- smp_mb();
- if (!need_resched())
- __sti_mwait(0, 0);
- else
- local_irq_enable();
- trace_power_end_rcuidle(smp_processor_id());
- trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
- } else
- local_irq_enable();
+ for (;;)
+ halt();
}
/*
@@ -447,62 +418,13 @@ static void mwait_idle(void)
*/
static void poll_idle(void)
{
- trace_power_start_rcuidle(POWER_CSTATE, 0, smp_processor_id());
trace_cpu_idle_rcuidle(0, smp_processor_id());
local_irq_enable();
while (!need_resched())
cpu_relax();
- trace_power_end_rcuidle(smp_processor_id());
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
}
-/*
- * mwait selection logic:
- *
- * It depends on the CPU. For AMD CPUs that support MWAIT this is
- * wrong. Family 0x10 and 0x11 CPUs will enter C1 on HLT. Powersavings
- * then depend on a clock divisor and current Pstate of the core. If
- * all cores of a processor are in halt state (C1) the processor can
- * enter the C1E (C1 enhanced) state. If mwait is used this will never
- * happen.
- *
- * idle=mwait overrides this decision and forces the usage of mwait.
- */
-
-#define MWAIT_INFO 0x05
-#define MWAIT_ECX_EXTENDED_INFO 0x01
-#define MWAIT_EDX_C1 0xf0
-
-int mwait_usable(const struct cpuinfo_x86 *c)
-{
- u32 eax, ebx, ecx, edx;
-
- /* Use mwait if idle=mwait boot option is given */
- if (boot_option_idle_override == IDLE_FORCE_MWAIT)
- return 1;
-
- /*
- * Any idle= boot option other than idle=mwait means that we must not
- * use mwait. Eg: idle=halt or idle=poll or idle=nomwait
- */
- if (boot_option_idle_override != IDLE_NO_OVERRIDE)
- return 0;
-
- if (c->cpuid_level < MWAIT_INFO)
- return 0;
-
- cpuid(MWAIT_INFO, &eax, &ebx, &ecx, &edx);
- /* Check, whether EDX has extended info about MWAIT */
- if (!(ecx & MWAIT_ECX_EXTENDED_INFO))
- return 1;
-
- /*
- * edx enumeratios MONITOR/MWAIT extensions. Check, whether
- * C1 supports MWAIT
- */
- return (edx & MWAIT_EDX_C1);
-}
-
bool amd_e400_c1e_detected;
EXPORT_SYMBOL(amd_e400_c1e_detected);
@@ -567,31 +489,24 @@ static void amd_e400_idle(void)
void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
- if (pm_idle == poll_idle && smp_num_siblings > 1) {
+ if (x86_idle == poll_idle && smp_num_siblings > 1)
pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n");
- }
#endif
- if (pm_idle)
+ if (x86_idle)
return;
- if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
- /*
- * One CPU supports mwait => All CPUs supports mwait
- */
- pr_info("using mwait in idle threads\n");
- pm_idle = mwait_idle;
- } else if (cpu_has_amd_erratum(amd_erratum_400)) {
+ if (cpu_has_amd_erratum(amd_erratum_400)) {
/* E400: APIC timer interrupt does not wake up CPU from C1e */
pr_info("using AMD E400 aware idle routine\n");
- pm_idle = amd_e400_idle;
+ x86_idle = amd_e400_idle;
} else
- pm_idle = default_idle;
+ x86_idle = default_idle;
}
void __init init_amd_e400_c1e_mask(void)
{
/* If we're using amd_e400_idle, we need to allocate amd_e400_c1e_mask. */
- if (pm_idle == amd_e400_idle)
+ if (x86_idle == amd_e400_idle)
zalloc_cpumask_var(&amd_e400_c1e_mask, GFP_KERNEL);
}
@@ -602,11 +517,8 @@ static int __init idle_setup(char *str)
if (!strcmp(str, "poll")) {
pr_info("using polling idle threads\n");
- pm_idle = poll_idle;
+ x86_idle = poll_idle;
boot_option_idle_override = IDLE_POLL;
- } else if (!strcmp(str, "mwait")) {
- boot_option_idle_override = IDLE_FORCE_MWAIT;
- WARN_ONCE(1, "\"idle=mwait\" will be removed in 2012\n");
} else if (!strcmp(str, "halt")) {
/*
* When the boot option of idle=halt is added, halt is
@@ -615,7 +527,7 @@ static int __init idle_setup(char *str)
* To continue to load the CPU idle driver, don't touch
* the boot_option_idle_override.
*/
- pm_idle = default_idle;
+ x86_idle = default_idle;
boot_option_idle_override = IDLE_HALT;
} else if (!strcmp(str, "nomwait")) {
/*
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ed0fe385289..a6ceaedc396 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1369,7 +1369,7 @@ static inline void mwait_play_dead(void)
void *mwait_ptr;
struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info);
- if (!(this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c)))
+ if (!this_cpu_has(X86_FEATURE_MWAIT))
return;
if (!this_cpu_has(X86_FEATURE_CLFLSH))
return;