5 files changed, 52 insertions, 152 deletions

diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index d65464e43503..9f4bc6a1164d 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 */
@@ -904,7 +925,6 @@ 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:
         if (jiffies_since_last_check > IDLE_CALC_LIMIT) {
                 use_apm_idle = 0;
@@ -950,10 +970,7 @@ 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)
@@ -963,7 +980,7 @@ recalc:
         if (apm_idle_done)
                 apm_do_busy();
 
-        local_irq_enable();
+        return index;
 }
 
 /**
@@ -2381,9 +2398,9 @@ 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;
@@ -2393,15 +2410,9 @@ 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 92dfec986a48..af6455e3fcc9 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 3286a92e662a..e280253f6f94 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 dcfc1f410dc4..14ae10031ff0 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();
@@ -394,14 +388,16 @@ void default_idle(void)
 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();
@@ -411,29 +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_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_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
-        } else
-                local_irq_enable();
+        for (;;)
+                halt();
 }
 
 /*
@@ -450,53 +425,6 @@ static void poll_idle(void)
         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);
 
@@ -561,31 +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);
 }
 
@@ -596,11 +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
@@ -609,7 +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 ed0fe385289d..a6ceaedc396a 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;