diff options
Diffstat (limited to 'drivers/acpi/processor_idle.c')
| -rw-r--r-- | drivers/acpi/processor_idle.c | 1355 |
1 files changed, 762 insertions, 593 deletions
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 0461ccc92c54..89f2f08b2554 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * processor_idle - idle state submodule to the ACPI processor driver * @@ -8,33 +9,22 @@ * - Added processor hotplug support * Copyright (C) 2005 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> * - Added support for C3 on SMP - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or (at - * your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA. - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ +#define pr_fmt(fmt) "ACPI: " fmt #include <linux/module.h> #include <linux/acpi.h> #include <linux/dmi.h> #include <linux/sched.h> /* need_resched() */ -#include <linux/clockchips.h> +#include <linux/tick.h> #include <linux/cpuidle.h> -#include <linux/syscore_ops.h> +#include <linux/cpu.h> +#include <linux/minmax.h> +#include <linux/perf_event.h> +#include <acpi/processor.h> +#include <linux/context_tracking.h> + +#include "internal.h" /* * Include the apic definitions for x86 to have the APIC timer related defines @@ -44,31 +34,37 @@ */ #ifdef CONFIG_X86 #include <asm/apic.h> +#include <asm/cpu.h> #endif -#include <acpi/acpi_bus.h> -#include <acpi/processor.h> - -#define PREFIX "ACPI: " - -#define ACPI_PROCESSOR_CLASS "processor" -#define _COMPONENT ACPI_PROCESSOR_COMPONENT -ACPI_MODULE_NAME("processor_idle"); +#define ACPI_IDLE_STATE_START (IS_ENABLED(CONFIG_ARCH_HAS_CPU_RELAX) ? 1 : 0) static unsigned int max_cstate __read_mostly = ACPI_PROCESSOR_MAX_POWER; -module_param(max_cstate, uint, 0000); -static unsigned int nocst __read_mostly; -module_param(nocst, uint, 0000); -static int bm_check_disable __read_mostly; -module_param(bm_check_disable, uint, 0000); +module_param(max_cstate, uint, 0400); +static bool nocst __read_mostly; +module_param(nocst, bool, 0400); +static bool bm_check_disable __read_mostly; +module_param(bm_check_disable, bool, 0400); static unsigned int latency_factor __read_mostly = 2; module_param(latency_factor, uint, 0644); static DEFINE_PER_CPU(struct cpuidle_device *, acpi_cpuidle_device); -static DEFINE_PER_CPU(struct acpi_processor_cx * [CPUIDLE_STATE_MAX], - acpi_cstate); +struct cpuidle_driver acpi_idle_driver = { + .name = "acpi_idle", + .owner = THIS_MODULE, +}; + +#ifdef CONFIG_ACPI_PROCESSOR_CSTATE +void acpi_idle_rescan_dead_smt_siblings(void) +{ + if (cpuidle_get_driver() == &acpi_idle_driver) + arch_cpu_rescan_dead_smt_siblings(); +} + +static +DEFINE_PER_CPU(struct acpi_processor_cx * [CPUIDLE_STATE_MAX], acpi_cstate); static int disabled_by_idle_boot_param(void) { @@ -87,18 +83,16 @@ static int set_max_cstate(const struct dmi_system_id *id) if (max_cstate > ACPI_PROCESSOR_MAX_POWER) return 0; - printk(KERN_NOTICE PREFIX "%s detected - limiting to C%ld max_cstate." - " Override with \"processor.max_cstate=%d\"\n", id->ident, - (long)id->driver_data, ACPI_PROCESSOR_MAX_POWER + 1); + pr_notice("%s detected - limiting to C%ld max_cstate." + " Override with \"processor.max_cstate=%d\"\n", id->ident, + (long)id->driver_data, ACPI_PROCESSOR_MAX_POWER + 1); max_cstate = (long)id->driver_data; return 0; } -/* Actually this shouldn't be __cpuinitdata, would be better to fix the - callers to only run once -AK */ -static struct dmi_system_id __cpuinitdata processor_power_dmi_table[] = { +static const struct dmi_system_id processor_power_dmi_table[] = { { set_max_cstate, "Clevo 5600D", { DMI_MATCH(DMI_BIOS_VENDOR,"Phoenix Technologies LTD"), DMI_MATCH(DMI_BIOS_VERSION,"SHE845M0.86C.0013.D.0302131307")}, @@ -119,19 +113,12 @@ static struct dmi_system_id __cpuinitdata processor_power_dmi_table[] = { * Callers should disable interrupts before the call and enable * interrupts after return. */ -static void acpi_safe_halt(void) +static void __cpuidle acpi_safe_halt(void) { - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - if (!need_resched()) { - safe_halt(); - local_irq_disable(); + if (!tif_need_resched()) { + raw_safe_halt(); + raw_local_irq_disable(); } - current_thread_info()->status |= TS_POLLING; } #ifdef ARCH_APICTIMER_STOPS_ON_C3 @@ -151,7 +138,7 @@ static void lapic_timer_check_state(int state, struct acpi_processor *pr, if (cpu_has(&cpu_data(pr->id), X86_FEATURE_ARAT)) return; - if (amd_e400_c1e_detected) + if (boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) type = ACPI_STATE_C1; /* @@ -167,13 +154,12 @@ static void lapic_timer_check_state(int state, struct acpi_processor *pr, static void __lapic_timer_propagate_broadcast(void *arg) { - struct acpi_processor *pr = (struct acpi_processor *) arg; - unsigned long reason; - - reason = pr->power.timer_broadcast_on_state < INT_MAX ? - CLOCK_EVT_NOTIFY_BROADCAST_ON : CLOCK_EVT_NOTIFY_BROADCAST_OFF; + struct acpi_processor *pr = arg; - clockevents_notify(reason, &pr->id); + if (pr->power.timer_broadcast_on_state < INT_MAX) + tick_broadcast_enable(); + else + tick_broadcast_disable(); } static void lapic_timer_propagate_broadcast(struct acpi_processor *pr) @@ -183,19 +169,10 @@ static void lapic_timer_propagate_broadcast(struct acpi_processor *pr) } /* Power(C) State timer broadcast control */ -static void lapic_timer_state_broadcast(struct acpi_processor *pr, - struct acpi_processor_cx *cx, - int broadcast) +static bool lapic_timer_needs_broadcast(struct acpi_processor *pr, + struct acpi_processor_cx *cx) { - int state = cx - pr->power.states; - - if (state >= pr->power.timer_broadcast_on_state) { - unsigned long reason; - - reason = broadcast ? CLOCK_EVT_NOTIFY_BROADCAST_ENTER : - CLOCK_EVT_NOTIFY_BROADCAST_EXIT; - clockevents_notify(reason, &pr->id); - } + return cx - pr->power.states >= pr->power.timer_broadcast_on_state; } #else @@ -203,64 +180,31 @@ static void lapic_timer_state_broadcast(struct acpi_processor *pr, static void lapic_timer_check_state(int state, struct acpi_processor *pr, struct acpi_processor_cx *cstate) { } static void lapic_timer_propagate_broadcast(struct acpi_processor *pr) { } -static void lapic_timer_state_broadcast(struct acpi_processor *pr, - struct acpi_processor_cx *cx, - int broadcast) -{ -} -#endif - -#ifdef CONFIG_PM_SLEEP -static u32 saved_bm_rld; - -static int acpi_processor_suspend(void) +static bool lapic_timer_needs_broadcast(struct acpi_processor *pr, + struct acpi_processor_cx *cx) { - acpi_read_bit_register(ACPI_BITREG_BUS_MASTER_RLD, &saved_bm_rld); - return 0; + return false; } -static void acpi_processor_resume(void) -{ - u32 resumed_bm_rld; - - acpi_read_bit_register(ACPI_BITREG_BUS_MASTER_RLD, &resumed_bm_rld); - if (resumed_bm_rld == saved_bm_rld) - return; - - acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, saved_bm_rld); -} - -static struct syscore_ops acpi_processor_syscore_ops = { - .suspend = acpi_processor_suspend, - .resume = acpi_processor_resume, -}; - -void acpi_processor_syscore_init(void) -{ - register_syscore_ops(&acpi_processor_syscore_ops); -} - -void acpi_processor_syscore_exit(void) -{ - unregister_syscore_ops(&acpi_processor_syscore_ops); -} -#endif /* CONFIG_PM_SLEEP */ +#endif #if defined(CONFIG_X86) static void tsc_check_state(int state) { switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_HYGON: case X86_VENDOR_AMD: case X86_VENDOR_INTEL: + case X86_VENDOR_CENTAUR: + case X86_VENDOR_ZHAOXIN: /* * AMD Fam10h TSC will tick in all * C/P/S0/S1 states when this bit is set. */ if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) return; - - /*FALL THROUGH*/ + fallthrough; default: /* TSC could halt in idle, so notify users */ if (state > ACPI_STATE_C1) @@ -274,9 +218,6 @@ static void tsc_check_state(int state) { return; } static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr) { - if (!pr) - return -EINVAL; - if (!pr->pblk) return -ENODEV; @@ -307,8 +248,8 @@ static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr) * 100 microseconds. */ if (acpi_gbl_FADT.c2_latency > ACPI_PROCESSOR_MAX_C2_LATENCY) { - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "C2 latency too large [%d]\n", acpi_gbl_FADT.c2_latency)); + acpi_handle_debug(pr->handle, "C2 latency too large [%d]\n", + acpi_gbl_FADT.c2_latency); /* invalidate C2 */ pr->power.states[ACPI_STATE_C2].address = 0; } @@ -318,16 +259,26 @@ static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr) * 1000 microseconds. */ if (acpi_gbl_FADT.c3_latency > ACPI_PROCESSOR_MAX_C3_LATENCY) { - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "C3 latency too large [%d]\n", acpi_gbl_FADT.c3_latency)); + acpi_handle_debug(pr->handle, "C3 latency too large [%d]\n", + acpi_gbl_FADT.c3_latency); /* invalidate C3 */ pr->power.states[ACPI_STATE_C3].address = 0; } - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "lvl2[0x%08x] lvl3[0x%08x]\n", + acpi_handle_debug(pr->handle, "lvl2[0x%08x] lvl3[0x%08x]\n", pr->power.states[ACPI_STATE_C2].address, - pr->power.states[ACPI_STATE_C3].address)); + pr->power.states[ACPI_STATE_C3].address); + + snprintf(pr->power.states[ACPI_STATE_C2].desc, + ACPI_CX_DESC_LEN, "ACPI P_LVL2 IOPORT 0x%x", + pr->power.states[ACPI_STATE_C2].address); + snprintf(pr->power.states[ACPI_STATE_C3].desc, + ACPI_CX_DESC_LEN, "ACPI P_LVL3 IOPORT 0x%x", + pr->power.states[ACPI_STATE_C3].address); + + if (!pr->power.states[ACPI_STATE_C2].address && + !pr->power.states[ACPI_STATE_C3].address) + return -ENODEV; return 0; } @@ -340,6 +291,9 @@ static int acpi_processor_get_power_info_default(struct acpi_processor *pr) pr->power.states[ACPI_STATE_C1].type = ACPI_STATE_C1; pr->power.states[ACPI_STATE_C1].valid = 1; pr->power.states[ACPI_STATE_C1].entry_method = ACPI_CSTATE_HALT; + + snprintf(pr->power.states[ACPI_STATE_C1].desc, + ACPI_CX_DESC_LEN, "ACPI HLT"); } /* the C0 state only exists as a filler in our array */ pr->power.states[ACPI_STATE_C0].valid = 1; @@ -348,167 +302,20 @@ static int acpi_processor_get_power_info_default(struct acpi_processor *pr) static int acpi_processor_get_power_info_cst(struct acpi_processor *pr) { - acpi_status status = 0; - u64 count; - int current_count; - int i; - struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *cst; - + int ret; if (nocst) return -ENODEV; - current_count = 0; + ret = acpi_processor_evaluate_cst(pr->handle, pr->id, &pr->power); + if (ret) + return ret; - status = acpi_evaluate_object(pr->handle, "_CST", NULL, &buffer); - if (ACPI_FAILURE(status)) { - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "No _CST, giving up\n")); - return -ENODEV; - } - - cst = buffer.pointer; - - /* There must be at least 2 elements */ - if (!cst || (cst->type != ACPI_TYPE_PACKAGE) || cst->package.count < 2) { - printk(KERN_ERR PREFIX "not enough elements in _CST\n"); - status = -EFAULT; - goto end; - } + if (!pr->power.count) + return -EFAULT; - count = cst->package.elements[0].integer.value; - - /* Validate number of power states. */ - if (count < 1 || count != cst->package.count - 1) { - printk(KERN_ERR PREFIX "count given by _CST is not valid\n"); - status = -EFAULT; - goto end; - } - - /* Tell driver that at least _CST is supported. */ pr->flags.has_cst = 1; - - for (i = 1; i <= count; i++) { - union acpi_object *element; - union acpi_object *obj; - struct acpi_power_register *reg; - struct acpi_processor_cx cx; - - memset(&cx, 0, sizeof(cx)); - - element = &(cst->package.elements[i]); - if (element->type != ACPI_TYPE_PACKAGE) - continue; - - if (element->package.count != 4) - continue; - - obj = &(element->package.elements[0]); - - if (obj->type != ACPI_TYPE_BUFFER) - continue; - - reg = (struct acpi_power_register *)obj->buffer.pointer; - - if (reg->space_id != ACPI_ADR_SPACE_SYSTEM_IO && - (reg->space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) - continue; - - /* There should be an easy way to extract an integer... */ - obj = &(element->package.elements[1]); - if (obj->type != ACPI_TYPE_INTEGER) - continue; - - cx.type = obj->integer.value; - /* - * Some buggy BIOSes won't list C1 in _CST - - * Let acpi_processor_get_power_info_default() handle them later - */ - if (i == 1 && cx.type != ACPI_STATE_C1) - current_count++; - - cx.address = reg->address; - cx.index = current_count + 1; - - cx.entry_method = ACPI_CSTATE_SYSTEMIO; - if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) { - if (acpi_processor_ffh_cstate_probe - (pr->id, &cx, reg) == 0) { - cx.entry_method = ACPI_CSTATE_FFH; - } else if (cx.type == ACPI_STATE_C1) { - /* - * C1 is a special case where FIXED_HARDWARE - * can be handled in non-MWAIT way as well. - * In that case, save this _CST entry info. - * Otherwise, ignore this info and continue. - */ - cx.entry_method = ACPI_CSTATE_HALT; - snprintf(cx.desc, ACPI_CX_DESC_LEN, "ACPI HLT"); - } else { - continue; - } - if (cx.type == ACPI_STATE_C1 && - (boot_option_idle_override == IDLE_NOMWAIT)) { - /* - * In most cases the C1 space_id obtained from - * _CST object is FIXED_HARDWARE access mode. - * But when the option of idle=halt is added, - * the entry_method type should be changed from - * CSTATE_FFH to CSTATE_HALT. - * When the option of idle=nomwait is added, - * the C1 entry_method type should be - * CSTATE_HALT. - */ - cx.entry_method = ACPI_CSTATE_HALT; - snprintf(cx.desc, ACPI_CX_DESC_LEN, "ACPI HLT"); - } - } else { - snprintf(cx.desc, ACPI_CX_DESC_LEN, "ACPI IOPORT 0x%x", - cx.address); - } - - if (cx.type == ACPI_STATE_C1) { - cx.valid = 1; - } - - obj = &(element->package.elements[2]); - if (obj->type != ACPI_TYPE_INTEGER) - continue; - - cx.latency = obj->integer.value; - - obj = &(element->package.elements[3]); - if (obj->type != ACPI_TYPE_INTEGER) - continue; - - current_count++; - memcpy(&(pr->power.states[current_count]), &cx, sizeof(cx)); - - /* - * We support total ACPI_PROCESSOR_MAX_POWER - 1 - * (From 1 through ACPI_PROCESSOR_MAX_POWER - 1) - */ - if (current_count >= (ACPI_PROCESSOR_MAX_POWER - 1)) { - printk(KERN_WARNING - "Limiting number of power states to max (%d)\n", - ACPI_PROCESSOR_MAX_POWER); - printk(KERN_WARNING - "Please increase ACPI_PROCESSOR_MAX_POWER if needed.\n"); - break; - } - } - - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found %d power states\n", - current_count)); - - /* Validate number of power states discovered */ - if (current_count < 2) - status = -EFAULT; - - end: - kfree(buffer.pointer); - - return status; + return 0; } static void acpi_processor_power_verify_c3(struct acpi_processor *pr, @@ -528,9 +335,9 @@ static void acpi_processor_power_verify_c3(struct acpi_processor *pr, * the erratum), but this is known to disrupt certain ISA * devices thus we take the conservative approach. */ - else if (errata.piix4.fdma) { - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "C3 not supported on PIIX4 with Type-F DMA\n")); + if (errata.piix4.fdma) { + acpi_handle_debug(pr->handle, + "C3 not supported on PIIX4 with Type-F DMA\n"); return; } @@ -549,13 +356,13 @@ static void acpi_processor_power_verify_c3(struct acpi_processor *pr, if (!pr->flags.bm_control) { if (pr->flags.has_cst != 1) { /* bus mastering control is necessary */ - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "C3 support requires BM control\n")); + acpi_handle_debug(pr->handle, + "C3 support requires BM control\n"); return; } else { /* Here we enter C3 without bus mastering */ - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "C3 support without BM control\n")); + acpi_handle_debug(pr->handle, + "C3 support without BM control\n"); } } } else { @@ -564,9 +371,9 @@ static void acpi_processor_power_verify_c3(struct acpi_processor *pr, * supported on when bm_check is not required. */ if (!(acpi_gbl_FADT.flags & ACPI_FADT_WBINVD)) { - ACPI_DEBUG_PRINT((ACPI_DB_INFO, + acpi_handle_debug(pr->handle, "Cache invalidation should work properly" - " for C3 to be enabled on SMP systems\n")); + " for C3 to be enabled on SMP systems\n"); return; } } @@ -588,14 +395,35 @@ static void acpi_processor_power_verify_c3(struct acpi_processor *pr, * handle BM_RLD is to set it and leave it set. */ acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, 1); +} + +static void acpi_cst_latency_sort(struct acpi_processor_cx *states, size_t length) +{ + int i, j, k; - return; + for (i = 1; i < length; i++) { + if (!states[i].valid) + continue; + + for (j = i - 1, k = i; j >= 0; j--) { + if (!states[j].valid) + continue; + + if (states[j].latency > states[k].latency) + swap(states[j].latency, states[k].latency); + + k = j; + } + } } static int acpi_processor_power_verify(struct acpi_processor *pr) { unsigned int i; unsigned int working = 0; + unsigned int last_latency = 0; + unsigned int last_type = 0; + bool buggy_latency = false; pr->power.timer_broadcast_on_state = INT_MAX; @@ -610,7 +438,7 @@ static int acpi_processor_power_verify(struct acpi_processor *pr) case ACPI_STATE_C2: if (!cx->address) break; - cx->valid = 1; + cx->valid = 1; break; case ACPI_STATE_C3: @@ -619,23 +447,30 @@ static int acpi_processor_power_verify(struct acpi_processor *pr) } if (!cx->valid) continue; + if (cx->type >= last_type && cx->latency < last_latency) + buggy_latency = true; + last_latency = cx->latency; + last_type = cx->type; lapic_timer_check_state(i, pr, cx); tsc_check_state(cx->type); working++; } + if (buggy_latency) { + pr_notice("FW issue: working around C-state latencies out of order\n"); + acpi_cst_latency_sort(&pr->power.states[1], max_cstate); + } + lapic_timer_propagate_broadcast(pr); - return (working); + return working; } -static int acpi_processor_get_power_info(struct acpi_processor *pr) +static int acpi_processor_get_cstate_info(struct acpi_processor *pr) { - unsigned int i; int result; - /* NOTE: the idle thread may not be running while calling * this function */ @@ -652,18 +487,7 @@ static int acpi_processor_get_power_info(struct acpi_processor *pr) acpi_processor_get_power_info_default(pr); pr->power.count = acpi_processor_power_verify(pr); - - /* - * if one state of type C2 or C3 is available, mark this - * CPU as being "idle manageable" - */ - for (i = 1; i < ACPI_PROCESSOR_MAX_POWER; i++) { - if (pr->power.states[i].valid) { - pr->power.count = i; - if (pr->power.states[i].type >= ACPI_STATE_C2) - pr->flags.power = 1; - } - } + pr->flags.power = 1; return 0; } @@ -694,66 +518,67 @@ static int acpi_idle_bm_check(void) return bm_status; } +static __cpuidle void io_idle(unsigned long addr) +{ + /* IO port based C-state */ + inb(addr); + +#ifdef CONFIG_X86 + /* No delay is needed if we are in guest */ + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return; + /* + * Modern (>=Nehalem) Intel systems use ACPI via intel_idle, + * not this code. Assume that any Intel systems using this + * are ancient and may need the dummy wait. This also assumes + * that the motivating chipset issue was Intel-only. + */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return; +#endif + /* + * Dummy wait op - must do something useless after P_LVL2 read + * because chipsets cannot guarantee that STPCLK# signal gets + * asserted in time to freeze execution properly + * + * This workaround has been in place since the original ACPI + * implementation was merged, circa 2002. + * + * If a profile is pointing to this instruction, please first + * consider moving your system to a more modern idle + * mechanism. + */ + inl(acpi_gbl_FADT.xpm_timer_block.address); +} + /** - * acpi_idle_do_entry - a helper function that does C2 and C3 type entry + * acpi_idle_do_entry - enter idle state using the appropriate method * @cx: cstate data * * Caller disables interrupt before call and enables interrupt after return. */ -static inline void acpi_idle_do_entry(struct acpi_processor_cx *cx) +static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx) { - /* Don't trace irqs off for idle */ - stop_critical_timings(); + perf_lopwr_cb(true); + if (cx->entry_method == ACPI_CSTATE_FFH) { /* Call into architectural FFH based C-state */ acpi_processor_ffh_cstate_enter(cx); } else if (cx->entry_method == ACPI_CSTATE_HALT) { acpi_safe_halt(); } else { - /* IO port based C-state */ - inb(cx->address); - /* Dummy wait op - must do something useless after P_LVL2 read - because chipsets cannot guarantee that STPCLK# signal - gets asserted in time to freeze execution properly. */ - inl(acpi_gbl_FADT.xpm_timer_block.address); + io_idle(cx->address); } - start_critical_timings(); -} - -/** - * acpi_idle_enter_c1 - enters an ACPI C1 state-type - * @dev: the target CPU - * @drv: cpuidle driver containing cpuidle state info - * @index: index of target state - * - * This is equivalent to the HALT instruction. - */ -static int acpi_idle_enter_c1(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) -{ - struct acpi_processor *pr; - struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu); - pr = __this_cpu_read(processors); - - if (unlikely(!pr)) - return -EINVAL; - - lapic_timer_state_broadcast(pr, cx, 1); - acpi_idle_do_entry(cx); - - lapic_timer_state_broadcast(pr, cx, 0); - - return index; + perf_lopwr_cb(false); } - /** * acpi_idle_play_dead - enters an ACPI state for long-term idle (i.e. off-lining) * @dev: the target CPU * @index: the index of suggested state */ -static int acpi_idle_play_dead(struct cpuidle_device *dev, int index) +static void acpi_idle_play_dead(struct cpuidle_device *dev, int index) { struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu); @@ -762,70 +587,20 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index) while (1) { if (cx->entry_method == ACPI_CSTATE_HALT) - safe_halt(); + raw_safe_halt(); else if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) { - inb(cx->address); - /* See comment in acpi_idle_do_entry() */ - inl(acpi_gbl_FADT.xpm_timer_block.address); + io_idle(cx->address); + } else if (cx->entry_method == ACPI_CSTATE_FFH) { + acpi_processor_ffh_play_dead(cx); } else - return -ENODEV; + return; } - - /* Never reached */ - return 0; } -/** - * acpi_idle_enter_simple - enters an ACPI state without BM handling - * @dev: the target CPU - * @drv: cpuidle driver with cpuidle state information - * @index: the index of suggested state - */ -static int acpi_idle_enter_simple(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) +static __always_inline bool acpi_idle_fallback_to_c1(struct acpi_processor *pr) { - struct acpi_processor *pr; - struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu); - - pr = __this_cpu_read(processors); - - if (unlikely(!pr)) - return -EINVAL; - - if (cx->entry_method != ACPI_CSTATE_FFH) { - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we test - * NEED_RESCHED: - */ - smp_mb(); - - if (unlikely(need_resched())) { - current_thread_info()->status |= TS_POLLING; - return -EINVAL; - } - } - - /* - * Must be done before busmaster disable as we might need to - * access HPET ! - */ - lapic_timer_state_broadcast(pr, cx, 1); - - if (cx->type == ACPI_STATE_C3) - ACPI_FLUSH_CPU_CACHE(); - - /* Tell the scheduler that we are going deep-idle: */ - sched_clock_idle_sleep_event(); - acpi_idle_do_entry(cx); - - sched_clock_idle_wakeup_event(0); - - if (cx->entry_method != ACPI_CSTATE_FFH) - current_thread_info()->status |= TS_POLLING; - - lapic_timer_state_broadcast(pr, cx, 0); - return index; + return IS_ENABLED(CONFIG_HOTPLUG_CPU) && !pr->flags.has_cst && + !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED); } static int c3_cpu_count; @@ -833,126 +608,135 @@ static DEFINE_RAW_SPINLOCK(c3_lock); /** * acpi_idle_enter_bm - enters C3 with proper BM handling - * @dev: the target CPU - * @drv: cpuidle driver containing state data - * @index: the index of suggested state - * - * If BM is detected, the deepest non-C3 idle state is entered instead. + * @drv: cpuidle driver + * @pr: Target processor + * @cx: Target state context + * @index: index of target state */ -static int acpi_idle_enter_bm(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) +static int __cpuidle acpi_idle_enter_bm(struct cpuidle_driver *drv, + struct acpi_processor *pr, + struct acpi_processor_cx *cx, + int index) { - struct acpi_processor *pr; - struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu); + static struct acpi_processor_cx safe_cx = { + .entry_method = ACPI_CSTATE_HALT, + }; - pr = __this_cpu_read(processors); + /* + * disable bus master + * bm_check implies we need ARB_DIS + * bm_control implies whether we can do ARB_DIS + * + * That leaves a case where bm_check is set and bm_control is not set. + * In that case we cannot do much, we enter C3 without doing anything. + */ + bool dis_bm = pr->flags.bm_control; - if (unlikely(!pr)) - return -EINVAL; + instrumentation_begin(); + /* If we can skip BM, demote to a safe state. */ if (!cx->bm_sts_skip && acpi_idle_bm_check()) { - if (drv->safe_state_index >= 0) { - return drv->states[drv->safe_state_index].enter(dev, - drv, drv->safe_state_index); + dis_bm = false; + index = drv->safe_state_index; + if (index >= 0) { + cx = this_cpu_read(acpi_cstate[index]); } else { - acpi_safe_halt(); - return -EBUSY; + cx = &safe_cx; + index = -EBUSY; } } - if (cx->entry_method != ACPI_CSTATE_FFH) { - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we test - * NEED_RESCHED: - */ - smp_mb(); - - if (unlikely(need_resched())) { - current_thread_info()->status |= TS_POLLING; - return -EINVAL; - } - } - - acpi_unlazy_tlb(smp_processor_id()); - - /* Tell the scheduler that we are going deep-idle: */ - sched_clock_idle_sleep_event(); - /* - * Must be done before busmaster disable as we might need to - * access HPET ! - */ - lapic_timer_state_broadcast(pr, cx, 1); - - /* - * disable bus master - * bm_check implies we need ARB_DIS - * !bm_check implies we need cache flush - * bm_control implies whether we can do ARB_DIS - * - * That leaves a case where bm_check is set and bm_control is - * not set. In that case we cannot do much, we enter C3 - * without doing anything. - */ - if (pr->flags.bm_check && pr->flags.bm_control) { + if (dis_bm) { raw_spin_lock(&c3_lock); c3_cpu_count++; /* Disable bus master arbitration when all CPUs are in C3 */ if (c3_cpu_count == num_online_cpus()) acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 1); raw_spin_unlock(&c3_lock); - } else if (!pr->flags.bm_check) { - ACPI_FLUSH_CPU_CACHE(); } + ct_cpuidle_enter(); + acpi_idle_do_entry(cx); + ct_cpuidle_exit(); + /* Re-enable bus master arbitration */ - if (pr->flags.bm_check && pr->flags.bm_control) { + if (dis_bm) { raw_spin_lock(&c3_lock); acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 0); c3_cpu_count--; raw_spin_unlock(&c3_lock); } - sched_clock_idle_wakeup_event(0); - - if (cx->entry_method != ACPI_CSTATE_FFH) - current_thread_info()->status |= TS_POLLING; + instrumentation_end(); - lapic_timer_state_broadcast(pr, cx, 0); return index; } -struct cpuidle_driver acpi_idle_driver = { - .name = "acpi_idle", - .owner = THIS_MODULE, -}; - -/** - * acpi_processor_setup_cpuidle_cx - prepares and configures CPUIDLE - * device i.e. per-cpu data - * - * @pr: the ACPI processor - * @dev : the cpuidle device - */ -static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr, - struct cpuidle_device *dev) +static int __cpuidle acpi_idle_enter(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { - int i, count = CPUIDLE_DRIVER_STATE_START; - struct acpi_processor_cx *cx; + struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu); + struct acpi_processor *pr; - if (!pr->flags.power_setup_done) + pr = __this_cpu_read(processors); + if (unlikely(!pr)) return -EINVAL; - if (pr->flags.power == 0) { - return -EINVAL; + if (cx->type != ACPI_STATE_C1) { + if (cx->type == ACPI_STATE_C3 && pr->flags.bm_check) + return acpi_idle_enter_bm(drv, pr, cx, index); + + /* C2 to C1 demotion. */ + if (acpi_idle_fallback_to_c1(pr) && num_online_cpus() > 1) { + index = ACPI_IDLE_STATE_START; + cx = per_cpu(acpi_cstate[index], dev->cpu); + } } - if (!dev) - return -EINVAL; + if (cx->type == ACPI_STATE_C3) + ACPI_FLUSH_CPU_CACHE(); - dev->cpu = pr->id; + acpi_idle_do_entry(cx); + + return index; +} + +static int __cpuidle acpi_idle_enter_s2idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu); + + if (cx->type == ACPI_STATE_C3) { + struct acpi_processor *pr = __this_cpu_read(processors); + + if (unlikely(!pr)) + return 0; + + if (pr->flags.bm_check) { + u8 bm_sts_skip = cx->bm_sts_skip; + + /* Don't check BM_STS, do an unconditional ARB_DIS for S2IDLE */ + cx->bm_sts_skip = 1; + acpi_idle_enter_bm(drv, pr, cx, index); + cx->bm_sts_skip = bm_sts_skip; + + return 0; + } else { + ACPI_FLUSH_CPU_CACHE(); + } + } + acpi_idle_do_entry(cx); + + return 0; +} + +static void acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr, + struct cpuidle_device *dev) +{ + int i, count = ACPI_IDLE_STATE_START; + struct acpi_processor_cx *cx; if (max_cstate == 0) max_cstate = 1; @@ -963,98 +747,68 @@ static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr, if (!cx->valid) continue; -#ifdef CONFIG_HOTPLUG_CPU - if ((cx->type != ACPI_STATE_C1) && (num_online_cpus() > 1) && - !pr->flags.has_cst && - !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED)) - continue; -#endif per_cpu(acpi_cstate[count], dev->cpu) = cx; count++; if (count == CPUIDLE_STATE_MAX) break; } - - dev->state_count = count; - - if (!count) - return -EINVAL; - - return 0; } -/** - * acpi_processor_setup_cpuidle states- prepares and configures cpuidle - * global state data i.e. idle routines - * - * @pr: the ACPI processor - */ -static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr) +static void acpi_processor_setup_cstates(struct acpi_processor *pr) { - int i, count = CPUIDLE_DRIVER_STATE_START; + int i, count; struct acpi_processor_cx *cx; struct cpuidle_state *state; struct cpuidle_driver *drv = &acpi_idle_driver; - if (!pr->flags.power_setup_done) - return -EINVAL; - - if (pr->flags.power == 0) - return -EINVAL; - - drv->safe_state_index = -1; - for (i = 0; i < CPUIDLE_STATE_MAX; i++) { - drv->states[i].name[0] = '\0'; - drv->states[i].desc[0] = '\0'; - } - if (max_cstate == 0) max_cstate = 1; + if (IS_ENABLED(CONFIG_ARCH_HAS_CPU_RELAX)) { + cpuidle_poll_state_init(drv); + count = 1; + } else { + count = 0; + } + for (i = 1; i < ACPI_PROCESSOR_MAX_POWER && i <= max_cstate; i++) { cx = &pr->power.states[i]; if (!cx->valid) continue; -#ifdef CONFIG_HOTPLUG_CPU - if ((cx->type != ACPI_STATE_C1) && (num_online_cpus() > 1) && - !pr->flags.has_cst && - !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED)) - continue; -#endif - state = &drv->states[count]; snprintf(state->name, CPUIDLE_NAME_LEN, "C%d", i); - strncpy(state->desc, cx->desc, CPUIDLE_DESC_LEN); + strscpy(state->desc, cx->desc, CPUIDLE_DESC_LEN); state->exit_latency = cx->latency; state->target_residency = cx->latency * latency_factor; + state->enter = acpi_idle_enter; state->flags = 0; - switch (cx->type) { - case ACPI_STATE_C1: - if (cx->entry_method == ACPI_CSTATE_FFH) - state->flags |= CPUIDLE_FLAG_TIME_VALID; - state->enter = acpi_idle_enter_c1; - state->enter_dead = acpi_idle_play_dead; - drv->safe_state_index = count; - break; + state->enter_dead = acpi_idle_play_dead; - case ACPI_STATE_C2: - state->flags |= CPUIDLE_FLAG_TIME_VALID; - state->enter = acpi_idle_enter_simple; - state->enter_dead = acpi_idle_play_dead; + if (cx->type == ACPI_STATE_C1 || cx->type == ACPI_STATE_C2) drv->safe_state_index = count; - break; - case ACPI_STATE_C3: - state->flags |= CPUIDLE_FLAG_TIME_VALID; - state->enter = pr->flags.bm_check ? - acpi_idle_enter_bm : - acpi_idle_enter_simple; - break; + /* + * Halt-induced C1 is not good for ->enter_s2idle, because it + * re-enables interrupts on exit. Moreover, C1 is generally not + * particularly interesting from the suspend-to-idle angle, so + * avoid C1 and the situations in which we may need to fall back + * to it altogether. + */ + if (cx->type != ACPI_STATE_C1 && !acpi_idle_fallback_to_c1(pr)) + state->enter_s2idle = acpi_idle_enter_s2idle; + + if (lapic_timer_needs_broadcast(pr, cx)) + state->flags |= CPUIDLE_FLAG_TIMER_STOP; + + if (cx->type == ACPI_STATE_C3) { + state->flags |= CPUIDLE_FLAG_TLB_FLUSHED; + if (pr->flags.bm_check) + state->flags |= CPUIDLE_FLAG_RCU_IDLE; } count++; @@ -1063,37 +817,473 @@ static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr) } drv->state_count = count; +} + +static inline void acpi_processor_cstate_first_run_checks(void) +{ + static int first_run; + + if (first_run) + return; + dmi_check_system(processor_power_dmi_table); + max_cstate = acpi_processor_cstate_check(max_cstate); + if (max_cstate < ACPI_C_STATES_MAX) + pr_notice("processor limited to max C-state %d\n", max_cstate); + + first_run++; + + if (nocst) + return; + + acpi_processor_claim_cst_control(); +} +#else + +static inline int disabled_by_idle_boot_param(void) { return 0; } +static inline void acpi_processor_cstate_first_run_checks(void) { } +static int acpi_processor_get_cstate_info(struct acpi_processor *pr) +{ + return -ENODEV; +} + +static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr, + struct cpuidle_device *dev) +{ + return -EINVAL; +} + +static int acpi_processor_setup_cstates(struct acpi_processor *pr) +{ + return -EINVAL; +} + +#endif /* CONFIG_ACPI_PROCESSOR_CSTATE */ - if (!count) +struct acpi_lpi_states_array { + unsigned int size; + unsigned int composite_states_size; + struct acpi_lpi_state *entries; + struct acpi_lpi_state *composite_states[ACPI_PROCESSOR_MAX_POWER]; +}; + +static int obj_get_integer(union acpi_object *obj, u32 *value) +{ + if (obj->type != ACPI_TYPE_INTEGER) return -EINVAL; + *value = obj->integer.value; return 0; } -int acpi_processor_hotplug(struct acpi_processor *pr) +static int acpi_processor_evaluate_lpi(acpi_handle handle, + struct acpi_lpi_states_array *info) { + acpi_status status; int ret = 0; - struct cpuidle_device *dev; + int pkg_count, state_idx = 1, loop; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + union acpi_object *lpi_data; + struct acpi_lpi_state *lpi_state; - if (disabled_by_idle_boot_param()) - return 0; + status = acpi_evaluate_object(handle, "_LPI", NULL, &buffer); + if (ACPI_FAILURE(status)) { + acpi_handle_debug(handle, "No _LPI, giving up\n"); + return -ENODEV; + } + + lpi_data = buffer.pointer; + + /* There must be at least 4 elements = 3 elements + 1 package */ + if (!lpi_data || lpi_data->type != ACPI_TYPE_PACKAGE || + lpi_data->package.count < 4) { + pr_debug("not enough elements in _LPI\n"); + ret = -ENODATA; + goto end; + } + + pkg_count = lpi_data->package.elements[2].integer.value; + + /* Validate number of power states. */ + if (pkg_count < 1 || pkg_count != lpi_data->package.count - 3) { + pr_debug("count given by _LPI is not valid\n"); + ret = -ENODATA; + goto end; + } + + lpi_state = kcalloc(pkg_count, sizeof(*lpi_state), GFP_KERNEL); + if (!lpi_state) { + ret = -ENOMEM; + goto end; + } + + info->size = pkg_count; + info->entries = lpi_state; + + /* LPI States start at index 3 */ + for (loop = 3; state_idx <= pkg_count; loop++, state_idx++, lpi_state++) { + union acpi_object *element, *pkg_elem, *obj; + + element = &lpi_data->package.elements[loop]; + if (element->type != ACPI_TYPE_PACKAGE || element->package.count < 7) + continue; + + pkg_elem = element->package.elements; + + obj = pkg_elem + 6; + if (obj->type == ACPI_TYPE_BUFFER) { + struct acpi_power_register *reg; + + reg = (struct acpi_power_register *)obj->buffer.pointer; + if (reg->space_id != ACPI_ADR_SPACE_SYSTEM_IO && + reg->space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) + continue; + + lpi_state->address = reg->address; + lpi_state->entry_method = + reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE ? + ACPI_CSTATE_FFH : ACPI_CSTATE_SYSTEMIO; + } else if (obj->type == ACPI_TYPE_INTEGER) { + lpi_state->entry_method = ACPI_CSTATE_INTEGER; + lpi_state->address = obj->integer.value; + } else { + continue; + } + + /* elements[7,8] skipped for now i.e. Residency/Usage counter*/ + + obj = pkg_elem + 9; + if (obj->type == ACPI_TYPE_STRING) + strscpy(lpi_state->desc, obj->string.pointer, + ACPI_CX_DESC_LEN); + + lpi_state->index = state_idx; + if (obj_get_integer(pkg_elem + 0, &lpi_state->min_residency)) { + pr_debug("No min. residency found, assuming 10 us\n"); + lpi_state->min_residency = 10; + } + + if (obj_get_integer(pkg_elem + 1, &lpi_state->wake_latency)) { + pr_debug("No wakeup residency found, assuming 10 us\n"); + lpi_state->wake_latency = 10; + } + + if (obj_get_integer(pkg_elem + 2, &lpi_state->flags)) + lpi_state->flags = 0; + + if (obj_get_integer(pkg_elem + 3, &lpi_state->arch_flags)) + lpi_state->arch_flags = 0; + + if (obj_get_integer(pkg_elem + 4, &lpi_state->res_cnt_freq)) + lpi_state->res_cnt_freq = 1; + + if (obj_get_integer(pkg_elem + 5, &lpi_state->enable_parent_state)) + lpi_state->enable_parent_state = 0; + } + + acpi_handle_debug(handle, "Found %d power states\n", state_idx); +end: + kfree(buffer.pointer); + return ret; +} + +/** + * combine_lpi_states - combine local and parent LPI states to form a composite LPI state + * + * @local: local LPI state + * @parent: parent LPI state + * @result: composite LPI state + */ +static bool combine_lpi_states(struct acpi_lpi_state *local, + struct acpi_lpi_state *parent, + struct acpi_lpi_state *result) +{ + if (parent->entry_method == ACPI_CSTATE_INTEGER) { + if (!parent->address) /* 0 means autopromotable */ + return false; + result->address = local->address + parent->address; + } else { + result->address = parent->address; + } + + result->min_residency = max(local->min_residency, parent->min_residency); + result->wake_latency = local->wake_latency + parent->wake_latency; + result->enable_parent_state = parent->enable_parent_state; + result->entry_method = local->entry_method; + + result->flags = parent->flags; + result->arch_flags = parent->arch_flags; + result->index = parent->index; + + strscpy(result->desc, local->desc, ACPI_CX_DESC_LEN); + strlcat(result->desc, "+", ACPI_CX_DESC_LEN); + strlcat(result->desc, parent->desc, ACPI_CX_DESC_LEN); + return true; +} + +#define ACPI_LPI_STATE_FLAGS_ENABLED BIT(0) + +static void stash_composite_state(struct acpi_lpi_states_array *curr_level, + struct acpi_lpi_state *t) +{ + curr_level->composite_states[curr_level->composite_states_size++] = t; +} + +static unsigned int flatten_lpi_states(struct acpi_processor *pr, + unsigned int flat_state_cnt, + struct acpi_lpi_states_array *curr_level, + struct acpi_lpi_states_array *prev_level) +{ + int i, j, state_count = curr_level->size; + struct acpi_lpi_state *p, *t = curr_level->entries; + + curr_level->composite_states_size = 0; + for (j = 0; j < state_count; j++, t++) { + struct acpi_lpi_state *flpi; - if (!pr) + if (!(t->flags & ACPI_LPI_STATE_FLAGS_ENABLED)) + continue; + + if (flat_state_cnt >= ACPI_PROCESSOR_MAX_POWER) { + pr_warn("Limiting number of LPI states to max (%d)\n", + ACPI_PROCESSOR_MAX_POWER); + pr_warn("Please increase ACPI_PROCESSOR_MAX_POWER if needed.\n"); + break; + } + + flpi = &pr->power.lpi_states[flat_state_cnt]; + + if (!prev_level) { /* leaf/processor node */ + memcpy(flpi, t, sizeof(*t)); + stash_composite_state(curr_level, flpi); + flat_state_cnt++; + continue; + } + + for (i = 0; i < prev_level->composite_states_size; i++) { + p = prev_level->composite_states[i]; + if (t->index <= p->enable_parent_state && + combine_lpi_states(p, t, flpi)) { + stash_composite_state(curr_level, flpi); + flat_state_cnt++; + flpi++; + } + } + } + + kfree(curr_level->entries); + return flat_state_cnt; +} + +int __weak acpi_processor_ffh_lpi_probe(unsigned int cpu) +{ + return -EOPNOTSUPP; +} + +static int acpi_processor_get_lpi_info(struct acpi_processor *pr) +{ + int ret, i; + acpi_status status; + acpi_handle handle = pr->handle, pr_ahandle; + struct acpi_device *d = NULL; + struct acpi_lpi_states_array info[2], *tmp, *prev, *curr; + unsigned int state_count; + + /* make sure our architecture has support */ + ret = acpi_processor_ffh_lpi_probe(pr->id); + if (ret == -EOPNOTSUPP) + return ret; + + if (!osc_pc_lpi_support_confirmed) + return -EOPNOTSUPP; + + if (!acpi_has_method(handle, "_LPI")) return -EINVAL; - if (nocst) { - return -ENODEV; + prev = &info[0]; + curr = &info[1]; + handle = pr->handle; + ret = acpi_processor_evaluate_lpi(handle, prev); + if (ret) + return ret; + state_count = flatten_lpi_states(pr, 0, prev, NULL); + + status = acpi_get_parent(handle, &pr_ahandle); + while (ACPI_SUCCESS(status)) { + d = acpi_fetch_acpi_dev(pr_ahandle); + if (!d) + break; + + handle = pr_ahandle; + + if (strcmp(acpi_device_hid(d), ACPI_PROCESSOR_CONTAINER_HID)) + break; + + /* can be optional ? */ + if (!acpi_has_method(handle, "_LPI")) + break; + + ret = acpi_processor_evaluate_lpi(handle, curr); + if (ret) + break; + + /* flatten all the LPI states in this level of hierarchy */ + state_count = flatten_lpi_states(pr, state_count, curr, prev); + + tmp = prev, prev = curr, curr = tmp; + + status = acpi_get_parent(handle, &pr_ahandle); + } + + /* reset the index after flattening */ + for (i = 0; i < state_count; i++) + pr->power.lpi_states[i].index = i; + + pr->power.count = state_count; + + /* Tell driver that _LPI is supported. */ + pr->flags.has_lpi = 1; + pr->flags.power = 1; + + return 0; +} + +int __weak acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi) +{ + return -ENODEV; +} + +/** + * acpi_idle_lpi_enter - enters an ACPI any LPI state + * @dev: the target CPU + * @drv: cpuidle driver containing cpuidle state info + * @index: index of target state + * + * Return: 0 for success or negative value for error + */ +static int acpi_idle_lpi_enter(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + struct acpi_processor *pr; + struct acpi_lpi_state *lpi; + + pr = __this_cpu_read(processors); + + if (unlikely(!pr)) + return -EINVAL; + + lpi = &pr->power.lpi_states[index]; + if (lpi->entry_method == ACPI_CSTATE_FFH) + return acpi_processor_ffh_lpi_enter(lpi); + + return -EINVAL; +} + +static int acpi_processor_setup_lpi_states(struct acpi_processor *pr) +{ + int i; + struct acpi_lpi_state *lpi; + struct cpuidle_state *state; + struct cpuidle_driver *drv = &acpi_idle_driver; + + if (!pr->flags.has_lpi) + return -EOPNOTSUPP; + + for (i = 0; i < pr->power.count && i < CPUIDLE_STATE_MAX; i++) { + lpi = &pr->power.lpi_states[i]; + + state = &drv->states[i]; + snprintf(state->name, CPUIDLE_NAME_LEN, "LPI-%d", i); + strscpy(state->desc, lpi->desc, CPUIDLE_DESC_LEN); + state->exit_latency = lpi->wake_latency; + state->target_residency = lpi->min_residency; + state->flags |= arch_get_idle_state_flags(lpi->arch_flags); + if (i != 0 && lpi->entry_method == ACPI_CSTATE_FFH) + state->flags |= CPUIDLE_FLAG_RCU_IDLE; + state->enter = acpi_idle_lpi_enter; + drv->safe_state_index = i; + } + + drv->state_count = i; + + return 0; +} + +/** + * acpi_processor_setup_cpuidle_states- prepares and configures cpuidle + * global state data i.e. idle routines + * + * @pr: the ACPI processor + */ +static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr) +{ + int i; + struct cpuidle_driver *drv = &acpi_idle_driver; + + if (!pr->flags.power_setup_done || !pr->flags.power) + return -EINVAL; + + drv->safe_state_index = -1; + for (i = ACPI_IDLE_STATE_START; i < CPUIDLE_STATE_MAX; i++) { + drv->states[i].name[0] = '\0'; + drv->states[i].desc[0] = '\0'; } + if (pr->flags.has_lpi) + return acpi_processor_setup_lpi_states(pr); + + acpi_processor_setup_cstates(pr); + return 0; +} + +/** + * acpi_processor_setup_cpuidle_dev - prepares and configures CPUIDLE + * device i.e. per-cpu data + * + * @pr: the ACPI processor + * @dev : the cpuidle device + */ +static int acpi_processor_setup_cpuidle_dev(struct acpi_processor *pr, + struct cpuidle_device *dev) +{ + if (!pr->flags.power_setup_done || !pr->flags.power || !dev) + return -EINVAL; + + dev->cpu = pr->id; + if (pr->flags.has_lpi) + return acpi_processor_ffh_lpi_probe(pr->id); + + acpi_processor_setup_cpuidle_cx(pr, dev); + return 0; +} + +static int acpi_processor_get_power_info(struct acpi_processor *pr) +{ + int ret; + + ret = acpi_processor_get_lpi_info(pr); + if (ret) + ret = acpi_processor_get_cstate_info(pr); + + return ret; +} + +int acpi_processor_hotplug(struct acpi_processor *pr) +{ + int ret = 0; + struct cpuidle_device *dev; + + if (disabled_by_idle_boot_param()) + return 0; + if (!pr->flags.power_setup_done) return -ENODEV; dev = per_cpu(acpi_cpuidle_device, pr->id); cpuidle_pause_and_lock(); cpuidle_disable_device(dev); - acpi_processor_get_power_info(pr); - if (pr->flags.power) { - acpi_processor_setup_cpuidle_cx(pr, dev); + ret = acpi_processor_get_power_info(pr); + if (!ret && pr->flags.power) { + acpi_processor_setup_cpuidle_dev(pr, dev); ret = cpuidle_enable_device(dev); } cpuidle_resume_and_unlock(); @@ -1101,7 +1291,7 @@ int acpi_processor_hotplug(struct acpi_processor *pr) return ret; } -int acpi_processor_cst_has_changed(struct acpi_processor *pr) +int acpi_processor_power_state_has_changed(struct acpi_processor *pr) { int cpu; struct acpi_processor *_pr; @@ -1110,12 +1300,6 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr) if (disabled_by_idle_boot_param()) return 0; - if (!pr) - return -EINVAL; - - if (nocst) - return -ENODEV; - if (!pr->flags.power_setup_done) return -ENODEV; @@ -1127,9 +1311,9 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr) if (pr->id == 0 && cpuidle_get_driver() == &acpi_idle_driver) { - cpuidle_pause_and_lock(); /* Protect against cpu-hotplug */ - get_online_cpus(); + cpus_read_lock(); + cpuidle_pause_and_lock(); /* Disable all cpuidle devices */ for_each_online_cpu(cpu) { @@ -1152,12 +1336,12 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr) acpi_processor_get_power_info(_pr); if (_pr->flags.power) { dev = per_cpu(acpi_cpuidle_device, cpu); - acpi_processor_setup_cpuidle_cx(_pr, dev); + acpi_processor_setup_cpuidle_dev(_pr, dev); cpuidle_enable_device(dev); } } - put_online_cpus(); cpuidle_resume_and_unlock(); + cpus_read_unlock(); } return 0; @@ -1165,40 +1349,18 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr) static int acpi_processor_registered; -int __cpuinit acpi_processor_power_init(struct acpi_processor *pr) +int acpi_processor_power_init(struct acpi_processor *pr) { - acpi_status status = 0; int retval; struct cpuidle_device *dev; - static int first_run; if (disabled_by_idle_boot_param()) return 0; - if (!first_run) { - dmi_check_system(processor_power_dmi_table); - max_cstate = acpi_processor_cstate_check(max_cstate); - if (max_cstate < ACPI_C_STATES_MAX) - printk(KERN_NOTICE - "ACPI: processor limited to max C-state %d\n", - max_cstate); - first_run++; - } + acpi_processor_cstate_first_run_checks(); - if (!pr) - return -EINVAL; - - if (acpi_gbl_FADT.cst_control && !nocst) { - status = - acpi_os_write_port(acpi_gbl_FADT.smi_command, acpi_gbl_FADT.cst_control, 8); - if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, - "Notifying BIOS of _CST ability failed")); - } - } - - acpi_processor_get_power_info(pr); - pr->flags.power_setup_done = 1; + if (!acpi_processor_get_power_info(pr)) + pr->flags.power_setup_done = 1; /* * Install the idle handler if processor power management is supported. @@ -1212,8 +1374,8 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr) retval = cpuidle_register_driver(&acpi_idle_driver); if (retval) return retval; - printk(KERN_DEBUG "ACPI: %s registered with cpuidle\n", - acpi_idle_driver.name); + pr_debug("%s registered with cpuidle\n", + acpi_idle_driver.name); } dev = kzalloc(sizeof(*dev), GFP_KERNEL); @@ -1221,7 +1383,7 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr) return -ENOMEM; per_cpu(acpi_cpuidle_device, pr->id) = dev; - acpi_processor_setup_cpuidle_cx(pr, dev); + acpi_processor_setup_cpuidle_dev(pr, dev); /* Register per-cpu cpuidle_device. Cpuidle driver * must already be registered before registering device @@ -1230,6 +1392,9 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr) if (retval) { if (acpi_processor_registered == 0) cpuidle_unregister_driver(&acpi_idle_driver); + + per_cpu(acpi_cpuidle_device, pr->id) = NULL; + kfree(dev); return retval; } acpi_processor_registered++; @@ -1249,8 +1414,12 @@ int acpi_processor_power_exit(struct acpi_processor *pr) acpi_processor_registered--; if (acpi_processor_registered == 0) cpuidle_unregister_driver(&acpi_idle_driver); + + kfree(dev); } pr->flags.power_setup_done = 0; return 0; } + +MODULE_IMPORT_NS("ACPI_PROCESSOR_IDLE"); |