Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758200AbZJPJoA (ORCPT ); Fri, 16 Oct 2009 05:44:00 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1757693AbZJPJn6 (ORCPT ); Fri, 16 Oct 2009 05:43:58 -0400 Received: from e28smtp02.in.ibm.com ([59.145.155.2]:53285 "EHLO e28smtp02.in.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752414AbZJPJnz (ORCPT ); Fri, 16 Oct 2009 05:43:55 -0400 Date: Fri, 16 Oct 2009 15:13:08 +0530 From: Arun R Bharadwaj To: Peter Zijlstra , Benjamin Herrenschmidt , Ingo Molnar , Vaidyanathan Srinivasan , Dipankar Sarma , Balbir Singh , Andi Kleen , Arun Bharadwaj Cc: linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, linux-arch@vger.kernel.org, linux-acpi@vger.kernel.org Subject: [v9 PATCH 4/9]: x86: refactor x86 idle power management code and remove all instances of pm_idle. Message-ID: <20091016094308.GF27350@linux.vnet.ibm.com> Reply-To: arun@linux.vnet.ibm.com References: <20091016093850.GB27350@linux.vnet.ibm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline In-Reply-To: <20091016093850.GB27350@linux.vnet.ibm.com> User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 12214 Lines: 439 * Arun R Bharadwaj [2009-10-16 15:08:50]: This patch cleans up x86 of all instances of pm_idle. pm_idle which was earlier called from cpu_idle() idle loop is replaced by cpuidle_idle_call. x86 also registers to cpuidle when the idle routine is selected, by populating the cpuidle_device data structure for each cpu. This is replicated for apm module and for xen, which also used pm_idle. Signed-off-by: Arun R Bharadwaj --- arch/x86/kernel/apm_32.c | 55 ++++++++++++++++++++++++- arch/x86/kernel/process.c | 90 ++++++++++++++++++++++++++++++++---------- arch/x86/kernel/process_32.c | 3 - arch/x86/kernel/process_64.c | 3 - arch/x86/xen/setup.c | 40 ++++++++++++++++++ drivers/acpi/processor_core.c | 9 ++-- drivers/cpuidle/cpuidle.c | 16 +++++-- 7 files changed, 182 insertions(+), 34 deletions(-) Index: linux.trees.git/arch/x86/kernel/process.c =================================================================== --- linux.trees.git.orig/arch/x86/kernel/process.c +++ linux.trees.git/arch/x86/kernel/process.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -246,12 +247,6 @@ int sys_vfork(struct pt_regs *regs) unsigned long boot_option_idle_override = 0; EXPORT_SYMBOL(boot_option_idle_override); -/* - * Powermanagement idle function, if any.. - */ -void (*pm_idle)(void); -EXPORT_SYMBOL(pm_idle); - #ifdef CONFIG_X86_32 /* * This halt magic was a workaround for ancient floppy DMA @@ -331,17 +326,15 @@ static void do_nothing(void *unused) } /* - * cpu_idle_wait - Used to ensure that all the CPUs discard old value of - * pm_idle and update to new pm_idle value. Required while changing pm_idle - * handler on SMP systems. + * cpu_idle_wait - Required while changing idle routine handler on SMP systems. * - * Caller must have changed pm_idle to the new value before the call. Old - * pm_idle value will not be used by any CPU after the return of this function. + * Caller must have changed idle routine to the new value before the call. Old + * value will not be used by any CPU after the return of this function. */ void cpu_idle_wait(void) { smp_mb(); - /* kick all the CPUs so that they exit out of pm_idle */ + /* kick all the CPUs so that they exit out of idle loop */ smp_call_function(do_nothing, NULL, 1); } EXPORT_SYMBOL_GPL(cpu_idle_wait); @@ -520,15 +513,70 @@ static void c1e_idle(void) default_idle(); } +static void (*local_idle)(void); + +#ifndef CONFIG_CPU_IDLE +void cpuidle_idle_call(void) +{ + if (local_idle) + local_idle(); + else + default_idle(); +} +#endif + +DEFINE_PER_CPU(struct cpuidle_device, idle_devices); + +struct cpuidle_driver cpuidle_default_driver = { + .name = "cpuidle_default", +}; + +static int local_idle_loop(struct cpuidle_device *dev, struct cpuidle_state *st) +{ + ktime_t t1, t2; + s64 diff; + int ret; + + t1 = ktime_get(); + local_idle(); + t2 = ktime_get(); + + diff = ktime_to_us(ktime_sub(t2, t1)); + if (diff > INT_MAX) + diff = INT_MAX; + ret = (int) diff; + + return ret; +} + +static int setup_cpuidle_simple(void) +{ + struct cpuidle_device *dev; + int cpu; + + if (!cpuidle_curr_driver) + cpuidle_register_driver(&cpuidle_default_driver); + + for_each_online_cpu(cpu) { + dev = &per_cpu(idle_devices, cpu); + dev->cpu = cpu; + dev->states[0].enter = local_idle_loop; + dev->state_count = 1; + cpuidle_register_device(dev); + } + return 0; +} +device_initcall(setup_cpuidle_simple); + void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP - if (pm_idle == poll_idle && smp_num_siblings > 1) { + if (local_idle == poll_idle && smp_num_siblings > 1) { printk(KERN_WARNING "WARNING: polling idle and HT enabled," " performance may degrade.\n"); } #endif - if (pm_idle) + if (local_idle) return; if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) { @@ -536,18 +584,20 @@ void __cpuinit select_idle_routine(const * One CPU supports mwait => All CPUs supports mwait */ printk(KERN_INFO "using mwait in idle threads.\n"); - pm_idle = mwait_idle; + local_idle = mwait_idle; } else if (check_c1e_idle(c)) { printk(KERN_INFO "using C1E aware idle routine\n"); - pm_idle = c1e_idle; + local_idle = c1e_idle; } else - pm_idle = default_idle; + local_idle = default_idle; + + return; } void __init init_c1e_mask(void) { /* If we're using c1e_idle, we need to allocate c1e_mask. */ - if (pm_idle == c1e_idle) + if (local_idle == c1e_idle) zalloc_cpumask_var(&c1e_mask, GFP_KERNEL); } @@ -558,7 +608,7 @@ static int __init idle_setup(char *str) if (!strcmp(str, "poll")) { printk("using polling idle threads.\n"); - pm_idle = poll_idle; + local_idle = poll_idle; } else if (!strcmp(str, "mwait")) force_mwait = 1; else if (!strcmp(str, "halt")) { @@ -569,7 +619,7 @@ 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; + local_idle = default_idle; idle_halt = 1; return 0; } else if (!strcmp(str, "nomwait")) { Index: linux.trees.git/arch/x86/kernel/process_32.c =================================================================== --- linux.trees.git.orig/arch/x86/kernel/process_32.c +++ linux.trees.git/arch/x86/kernel/process_32.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include @@ -113,7 +114,7 @@ void cpu_idle(void) local_irq_disable(); /* Don't trace irqs off for idle */ stop_critical_timings(); - pm_idle(); + cpuidle_idle_call(); start_critical_timings(); } tick_nohz_restart_sched_tick(); Index: linux.trees.git/arch/x86/kernel/process_64.c =================================================================== --- linux.trees.git.orig/arch/x86/kernel/process_64.c +++ linux.trees.git/arch/x86/kernel/process_64.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include @@ -142,7 +143,7 @@ void cpu_idle(void) enter_idle(); /* Don't trace irqs off for idle */ stop_critical_timings(); - pm_idle(); + cpuidle_idle_call(); start_critical_timings(); /* In many cases the interrupt that ended idle has already called exit_idle. But some idle Index: linux.trees.git/arch/x86/kernel/apm_32.c =================================================================== --- linux.trees.git.orig/arch/x86/kernel/apm_32.c +++ linux.trees.git/arch/x86/kernel/apm_32.c @@ -2255,6 +2255,56 @@ static struct dmi_system_id __initdata a { } }; +DEFINE_PER_CPU(struct cpuidle_device, apm_idle_devices); + +struct cpuidle_driver cpuidle_apm_driver = { + .name = "cpuidle_apm", +}; + +static int apm_idle_loop(struct cpuidle_device *dev, struct cpuidle_state *st) +{ + ktime_t t1, t2; + s64 diff; + int ret; + + t1 = ktime_get(); + apm_cpu_idle(); + t2 = ktime_get(); + + diff = ktime_to_us(ktime_sub(t2, t1)); + if (diff > INT_MAX) + diff = INT_MAX; + ret = (int) diff; + + return ret; +} + +void __cpuinit setup_cpuidle_apm(void) +{ + struct cpuidle_device *dev; + + if (!cpuidle_curr_driver) + cpuidle_register_driver(&cpuidle_apm_driver); + + dev = &per_cpu(apm_idle_devices, smp_processor_id()); + dev->cpu = smp_processor_id(); + dev->states[0].enter = apm_idle_loop; + dev->state_count = 1; + cpuidle_register_device(dev); +} + +void exit_cpuidle_apm(void) +{ + struct cpuidle_device *dev; + int cpu; + + for_each_online_cpu(cpu) { + dev = &per_cpu(apm_idle_devices, cpu); + cpuidle_unregister_device(dev); + } +} + + /* * Just start the APM thread. We do NOT want to do APM BIOS * calls from anything but the APM thread, if for no other reason @@ -2392,8 +2442,7 @@ 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; + setup_cpuidle_apm(); set_pm_idle = 1; } @@ -2405,7 +2454,7 @@ static void __exit apm_exit(void) int error; if (set_pm_idle) { - pm_idle = original_pm_idle; + exit_cpuidle_apm(); /* * We are about to unload the current idle thread pm callback * (pm_idle), Wait for all processors to update cached/local Index: linux.trees.git/arch/x86/xen/setup.c =================================================================== --- linux.trees.git.orig/arch/x86/xen/setup.c +++ linux.trees.git/arch/x86/xen/setup.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -151,6 +152,43 @@ void __cpuinit xen_enable_syscall(void) #endif /* CONFIG_X86_64 */ } +DEFINE_PER_CPU(struct cpuidle_device, xen_idle_devices); +struct cpuidle_driver cpuidle_xen_driver = { + .name = "cpuidle_xen", +}; + +static int xen_idle_loop(struct cpuidle_device *dev, struct cpuidle_state *st) +{ + ktime_t t1, t2; + s64 diff; + int ret; + + t1 = ktime_get(); + xen_idle(); + t2 = ktime_get(); + + diff = ktime_to_us(ktime_sub(t2, t1)); + if (diff > INT_MAX) + diff = INT_MAX; + ret = (int) diff; + + return ret; +} + +void __cpuinit setup_cpuidle_xen(void) +{ + struct cpuidle_device *dev; + + if (!cpuidle_curr_driver) + cpuidle_register_driver(&cpuidle_xen_driver); + + dev = &per_cpu(xen_idle_devices, smp_processor_id()); + dev->cpu = smp_processor_id(); + dev->states[0].enter = xen_idle_loop; + dev->state_count = 1; + cpuidle_register_device(dev); +} + void __init xen_arch_setup(void) { struct physdev_set_iopl set_iopl; @@ -186,7 +224,7 @@ void __init xen_arch_setup(void) MAX_GUEST_CMDLINE > COMMAND_LINE_SIZE ? COMMAND_LINE_SIZE : MAX_GUEST_CMDLINE); - pm_idle = xen_idle; + setup_cpuidle_xen(); paravirt_disable_iospace(); Index: linux.trees.git/drivers/acpi/processor_core.c =================================================================== --- linux.trees.git.orig/drivers/acpi/processor_core.c +++ linux.trees.git/drivers/acpi/processor_core.c @@ -1150,9 +1150,12 @@ static int __init acpi_processor_init(vo * should not use mwait for CPU-states. */ dmi_check_system(processor_idle_dmi_table); - result = cpuidle_register_driver(&acpi_idle_driver); - if (result < 0) - goto out_proc; + + if (!boot_option_idle_override) { + result = cpuidle_register_driver(&acpi_idle_driver); + if (result < 0) + goto out_proc; + } result = acpi_bus_register_driver(&acpi_processor_driver); if (result < 0) Index: linux.trees.git/drivers/cpuidle/cpuidle.c =================================================================== --- linux.trees.git.orig/drivers/cpuidle/cpuidle.c +++ linux.trees.git/drivers/cpuidle/cpuidle.c @@ -225,16 +225,22 @@ void cpuidle_disable_device(struct cpuid EXPORT_SYMBOL_GPL(cpuidle_disable_device); #ifdef CONFIG_ARCH_HAS_CPU_RELAX -static int poll_idle(struct cpuidle_device *dev, struct cpuidle_state *st) +static void poll_idle(void) +{ + local_irq_enable(); + while (!need_resched()) + cpu_relax(); +} + +static int poll_idle_loop(struct cpuidle_device *dev, struct cpuidle_state *st) { ktime_t t1, t2; s64 diff; int ret; t1 = ktime_get(); - local_irq_enable(); - while (!need_resched()) - cpu_relax(); + + poll_idle(); t2 = ktime_get(); diff = ktime_to_us(ktime_sub(t2, t1)); @@ -257,7 +263,7 @@ static void poll_idle_init(struct cpuidl state->target_residency = 0; state->power_usage = -1; state->flags = CPUIDLE_FLAG_POLL; - state->enter = poll_idle; + state->enter = poll_idle_loop; } #else static void poll_idle_init(struct cpuidle_device *dev) {} -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/