From 1dedefd1a066a795a87afca9c0236e1a94de9bf6 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 19 May 2010 12:01:23 -0700 Subject: [PATCH 1/5] x86: detect scattered cpuid features earlier Some extra CPU features such as ARAT is needed in early boot so that x86_init function pointers can be set up properly. http://lkml.org/lkml/2010/5/18/519 At start_kernel() level, this patch moves init_scattered_cpuid_features() from check_bugs() to setup_arch() -> early_cpu_init() which is earlier than platform specific x86_init layer setup. Suggested by HPA. Signed-off-by: Jacob Pan LKML-Reference: <1274295685-6774-2-git-send-email-jacob.jun.pan@linux.intel.com> Acked-by: Thomas Gleixner Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c1c00d0b1692..284bf89ddae2 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -576,6 +576,7 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x80000007) c->x86_power = cpuid_edx(0x80000007); + init_scattered_cpuid_features(c); } static void __cpuinit identify_cpu_without_cpuid(struct cpuinfo_x86 *c) @@ -731,7 +732,6 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c) get_model_name(c); /* Default name */ - init_scattered_cpuid_features(c); detect_nopl(c); } From a0c173bd8a3fd0541be8e4ef962170e48d8811c7 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 19 May 2010 12:01:24 -0700 Subject: [PATCH 2/5] x86, mrst: add cpu type detection Medfield is the follow-up of Moorestown, it is treated under the same HW sub-architecture. However, we do need to know the CPU type in order for some of the driver to act accordingly. We also have different optimal clock configuration for each CPU type. Signed-off-by: Jacob Pan LKML-Reference: <1274295685-6774-3-git-send-email-jacob.jun.pan@linux.intel.com> Acked-by: Thomas Gleixner Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/mrst.h | 19 +++++++++++++++++++ arch/x86/kernel/mrst.c | 26 ++++++++++++++++++++++++++ 2 files changed, 45 insertions(+) diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h index 451d30e7f62d..dc5c8500bfc7 100644 --- a/arch/x86/include/asm/mrst.h +++ b/arch/x86/include/asm/mrst.h @@ -11,8 +11,27 @@ #ifndef _ASM_X86_MRST_H #define _ASM_X86_MRST_H extern int pci_mrst_init(void); +extern int mrst_identify_cpu(void); int __init sfi_parse_mrtc(struct sfi_table_header *table); +/* + * Medfield is the follow-up of Moorestown, it combines two chip solution into + * one. Other than that it also added always-on and constant tsc and lapic + * timers. Medfield is the platform name, and the chip name is called Penwell + * we treat Medfield/Penwell as a variant of Moorestown. Penwell can be + * identified via MSRs. + */ +enum mrst_cpu_type { + MRST_CPU_CHIP_LINCROFT = 1, + MRST_CPU_CHIP_PENWELL, +}; + +enum mrst_timer_options { + MRST_TIMER_DEFAULT, + MRST_TIMER_APBT_ONLY, + MRST_TIMER_LAPIC_APBT, +}; + #define SFI_MTMR_MAX_NUM 8 #define SFI_MRTC_MAX 8 diff --git a/arch/x86/kernel/mrst.c b/arch/x86/kernel/mrst.c index e796448f0eb5..ceaebeb5866f 100644 --- a/arch/x86/kernel/mrst.c +++ b/arch/x86/kernel/mrst.c @@ -27,6 +27,8 @@ static u32 sfi_mtimer_usage[SFI_MTMR_MAX_NUM]; static struct sfi_timer_table_entry sfi_mtimer_array[SFI_MTMR_MAX_NUM]; +static int mrst_cpu_chip; + int sfi_mtimer_num; struct sfi_rtc_table_entry sfi_mrtc_array[SFI_MRTC_MAX]; @@ -216,6 +218,28 @@ static void __init mrst_setup_boot_clock(void) setup_boot_APIC_clock(); }; +int mrst_identify_cpu(void) +{ + return mrst_cpu_chip; +} +EXPORT_SYMBOL_GPL(mrst_identify_cpu); + +void __cpuinit mrst_arch_setup(void) +{ + if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x27) + mrst_cpu_chip = MRST_CPU_CHIP_PENWELL; + else if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x26) + mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT; + else { + pr_err("Unknown Moorestown CPU (%d:%d), default to Lincroft\n", + boot_cpu_data.x86, boot_cpu_data.x86_model); + mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT; + } + pr_debug("Moorestown CPU %s identified\n", + (mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT) ? + "Lincroft" : "Penwell"); +} + /* * Moorestown specific x86_init function overrides and early setup * calls. @@ -230,6 +254,8 @@ void __init x86_mrst_early_setup(void) x86_init.irqs.pre_vector_init = x86_init_noop; + x86_init.oem.arch_setup = mrst_arch_setup; + x86_cpuinit.setup_percpu_clockev = mrst_setup_secondary_clock; x86_platform.calibrate_tsc = mrst_calibrate_tsc; From a875c01944f0d750eeb1ef3133feceb13f13c4b3 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 19 May 2010 12:01:25 -0700 Subject: [PATCH 3/5] x86, mrst: add more timer config options Always-on local APIC timer (ARAT) has been introduced to Medfield, along with the platform APB timers we have more timer configuration options between Moorestown and Medfield. This patch adds run-time detection of avaiable timer features so that we can treat Medfield as a variant of Moorestown and set up the optimal timer options for each platform. i.e. Medfield: per cpu always-on local APIC timer Moorestown: per cpu APB timer Manual override is possible via cmdline option x86_mrst_timer. Signed-off-by: Jacob Pan LKML-Reference: <1274295685-6774-4-git-send-email-jacob.jun.pan@linux.intel.com> Acked-by: Thomas Gleixner Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/apb_timer.h | 1 - arch/x86/include/asm/mrst.h | 1 + arch/x86/kernel/apb_timer.c | 37 +++----------- arch/x86/kernel/mrst.c | 88 +++++++++++++++++++++++--------- 4 files changed, 72 insertions(+), 55 deletions(-) diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h index c74a2eebe570..a69b1ac9eaf8 100644 --- a/arch/x86/include/asm/apb_timer.h +++ b/arch/x86/include/asm/apb_timer.h @@ -55,7 +55,6 @@ extern unsigned long apbt_quick_calibrate(void); extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu); extern void apbt_setup_secondary_clock(void); extern unsigned int boot_cpu_id; -extern int disable_apbt_percpu; extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint); extern void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr); diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h index dc5c8500bfc7..67ad31545778 100644 --- a/arch/x86/include/asm/mrst.h +++ b/arch/x86/include/asm/mrst.h @@ -12,6 +12,7 @@ #define _ASM_X86_MRST_H extern int pci_mrst_init(void); extern int mrst_identify_cpu(void); +extern int mrst_timer_options __cpuinitdata; int __init sfi_parse_mrtc(struct sfi_table_header *table); /* diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index a35347501d36..8dd77800ff5d 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -43,10 +43,11 @@ #include #include +#include #define APBT_MASK CLOCKSOURCE_MASK(32) #define APBT_SHIFT 22 -#define APBT_CLOCKEVENT_RATING 150 +#define APBT_CLOCKEVENT_RATING 110 #define APBT_CLOCKSOURCE_RATING 250 #define APBT_MIN_DELTA_USEC 200 @@ -83,8 +84,6 @@ struct apbt_dev { char name[10]; }; -int disable_apbt_percpu __cpuinitdata; - static DEFINE_PER_CPU(struct apbt_dev, cpu_apbt_dev); #ifdef CONFIG_SMP @@ -194,29 +193,6 @@ static struct clock_event_device apbt_clockevent = { .rating = APBT_CLOCKEVENT_RATING, }; -/* - * if user does not want to use per CPU apb timer, just give it a lower rating - * than local apic timer and skip the late per cpu timer init. - */ -static inline int __init setup_x86_mrst_timer(char *arg) -{ - if (!arg) - return -EINVAL; - - if (strcmp("apbt_only", arg) == 0) - disable_apbt_percpu = 0; - else if (strcmp("lapic_and_apbt", arg) == 0) - disable_apbt_percpu = 1; - else { - pr_warning("X86 MRST timer option %s not recognised" - " use x86_mrst_timer=apbt_only or lapic_and_apbt\n", - arg); - return -EINVAL; - } - return 0; -} -__setup("x86_mrst_timer=", setup_x86_mrst_timer); - /* * start count down from 0xffff_ffff. this is done by toggling the enable bit * then load initial load count to ~0. @@ -335,7 +311,7 @@ static int __init apbt_clockevent_register(void) adev->num = smp_processor_id(); memcpy(&adev->evt, &apbt_clockevent, sizeof(struct clock_event_device)); - if (disable_apbt_percpu) { + if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) { apbt_clockevent.rating = APBT_CLOCKEVENT_RATING - 100; global_clock_event = &adev->evt; printk(KERN_DEBUG "%s clockevent registered as global\n", @@ -429,7 +405,8 @@ static int apbt_cpuhp_notify(struct notifier_block *n, static __init int apbt_late_init(void) { - if (disable_apbt_percpu || !apb_timer_block_enabled) + if (mrst_timer_options == MRST_TIMER_LAPIC_APBT || + !apb_timer_block_enabled) return 0; /* This notifier should be called after workqueue is ready */ hotcpu_notifier(apbt_cpuhp_notify, -20); @@ -450,6 +427,8 @@ static void apbt_set_mode(enum clock_event_mode mode, int timer_num; struct apbt_dev *adev = EVT_TO_APBT_DEV(evt); + BUG_ON(!apbt_virt_address); + timer_num = adev->num; pr_debug("%s CPU %d timer %d mode=%d\n", __func__, first_cpu(*evt->cpumask), timer_num, mode); @@ -676,7 +655,7 @@ void __init apbt_time_init(void) } #ifdef CONFIG_SMP /* kernel cmdline disable apb timer, so we will use lapic timers */ - if (disable_apbt_percpu) { + if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) { printk(KERN_INFO "apbt: disabled per cpu timer\n"); return; } diff --git a/arch/x86/kernel/mrst.c b/arch/x86/kernel/mrst.c index ceaebeb5866f..636b53bd4198 100644 --- a/arch/x86/kernel/mrst.c +++ b/arch/x86/kernel/mrst.c @@ -25,6 +25,29 @@ #include #include +/* + * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock, + * cmdline option x86_mrst_timer can be used to override the configuration + * to prefer one or the other. + * at runtime, there are basically three timer configurations: + * 1. per cpu apbt clock only + * 2. per cpu always-on lapic clocks only, this is Penwell/Medfield only + * 3. per cpu lapic clock (C3STOP) and one apbt clock, with broadcast. + * + * by default (without cmdline option), platform code first detects cpu type + * to see if we are on lincroft or penwell, then set up both lapic or apbt + * clocks accordingly. + * i.e. by default, medfield uses configuration #2, moorestown uses #1. + * config #3 is supported but not recommended on medfield. + * + * rating and feature summary: + * lapic (with C3STOP) --------- 100 + * apbt (always-on) ------------ 110 + * lapic (always-on,ARAT) ------ 150 + */ + +int mrst_timer_options __cpuinitdata; + static u32 sfi_mtimer_usage[SFI_MTMR_MAX_NUM]; static struct sfi_timer_table_entry sfi_mtimer_array[SFI_MTMR_MAX_NUM]; static int mrst_cpu_chip; @@ -169,18 +192,6 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table) return 0; } -/* - * the secondary clock in Moorestown can be APBT or LAPIC clock, default to - * APBT but cmdline option can also override it. - */ -static void __cpuinit mrst_setup_secondary_clock(void) -{ - /* restore default lapic clock if disabled by cmdline */ - if (disable_apbt_percpu) - return setup_secondary_APIC_clock(); - apbt_setup_secondary_clock(); -} - static unsigned long __init mrst_calibrate_tsc(void) { unsigned long flags, fast_calibrate; @@ -197,6 +208,21 @@ static unsigned long __init mrst_calibrate_tsc(void) void __init mrst_time_init(void) { + switch (mrst_timer_options) { + case MRST_TIMER_APBT_ONLY: + break; + case MRST_TIMER_LAPIC_APBT: + x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock; + x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock; + break; + default: + if (!boot_cpu_has(X86_FEATURE_ARAT)) + break; + x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock; + x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock; + return; + } + /* we need at least one APB timer */ sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr); pre_init_apic_IRQ0(); apbt_time_init(); @@ -207,17 +233,6 @@ void __init mrst_rtc_init(void) sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc); } -/* - * if we use per cpu apb timer, the bootclock already setup. if we use lapic - * timer and one apbt timer for broadcast, we need to set up lapic boot clock. - */ -static void __init mrst_setup_boot_clock(void) -{ - pr_info("%s: per cpu apbt flag %d \n", __func__, disable_apbt_percpu); - if (disable_apbt_percpu) - setup_boot_APIC_clock(); -}; - int mrst_identify_cpu(void) { return mrst_cpu_chip; @@ -250,13 +265,13 @@ void __init x86_mrst_early_setup(void) x86_init.resources.reserve_resources = x86_init_noop; x86_init.timers.timer_init = mrst_time_init; - x86_init.timers.setup_percpu_clockev = mrst_setup_boot_clock; + x86_init.timers.setup_percpu_clockev = x86_init_noop; x86_init.irqs.pre_vector_init = x86_init_noop; x86_init.oem.arch_setup = mrst_arch_setup; - x86_cpuinit.setup_percpu_clockev = mrst_setup_secondary_clock; + x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock; x86_platform.calibrate_tsc = mrst_calibrate_tsc; x86_init.pci.init = pci_mrst_init; @@ -269,3 +284,26 @@ void __init x86_mrst_early_setup(void) x86_init.mpparse.get_smp_config = x86_init_uint_noop; } + +/* + * if user does not want to use per CPU apb timer, just give it a lower rating + * than local apic timer and skip the late per cpu timer init. + */ +static inline int __init setup_x86_mrst_timer(char *arg) +{ + if (!arg) + return -EINVAL; + + if (strcmp("apbt_only", arg) == 0) + mrst_timer_options = MRST_TIMER_APBT_ONLY; + else if (strcmp("lapic_and_apbt", arg) == 0) + mrst_timer_options = MRST_TIMER_LAPIC_APBT; + else { + pr_warning("X86 MRST timer option %s not recognised" + " use x86_mrst_timer=apbt_only or lapic_and_apbt\n", + arg); + return -EINVAL; + } + return 0; +} +__setup("x86_mrst_timer=", setup_x86_mrst_timer); From a75af580bb1fd261bf63cc00e4b324e17ceb15cf Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Wed, 19 May 2010 13:40:14 -0700 Subject: [PATCH 4/5] x86, mrst: make mrst_identify_cpu() an inline returning enum We have an enum, might as well use it. While we're at it, make it an inline... there is really no point in calling a function for this stuff. LKML-Reference: <1274295685-6774-3-git-send-email-jacob.jun.pan@linux.intel.com> Signed-off-by: H. Peter Anvin Acked-by: Thomas Gleixner Cc: Jacob Pan --- arch/x86/include/asm/mrst.h | 7 ++++++- arch/x86/kernel/mrst.c | 17 ++++++----------- 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h index 67ad31545778..1869c18d15ca 100644 --- a/arch/x86/include/asm/mrst.h +++ b/arch/x86/include/asm/mrst.h @@ -11,7 +11,6 @@ #ifndef _ASM_X86_MRST_H #define _ASM_X86_MRST_H extern int pci_mrst_init(void); -extern int mrst_identify_cpu(void); extern int mrst_timer_options __cpuinitdata; int __init sfi_parse_mrtc(struct sfi_table_header *table); @@ -27,6 +26,12 @@ enum mrst_cpu_type { MRST_CPU_CHIP_PENWELL, }; +extern enum mrst_cpu_type __mrst_cpu_chip; +static enum mrst_cpu_type mrst_identify_cpu(void) +{ + return __mrst_cpu_chip; +} + enum mrst_timer_options { MRST_TIMER_DEFAULT, MRST_TIMER_APBT_ONLY, diff --git a/arch/x86/kernel/mrst.c b/arch/x86/kernel/mrst.c index 636b53bd4198..967f2686adb0 100644 --- a/arch/x86/kernel/mrst.c +++ b/arch/x86/kernel/mrst.c @@ -50,7 +50,8 @@ int mrst_timer_options __cpuinitdata; static u32 sfi_mtimer_usage[SFI_MTMR_MAX_NUM]; static struct sfi_timer_table_entry sfi_mtimer_array[SFI_MTMR_MAX_NUM]; -static int mrst_cpu_chip; +enum mrst_cpu_type __mrst_cpu_chip; +EXPORT_SYMBOL_GPL(__mrst_cpu_chip); int sfi_mtimer_num; @@ -233,25 +234,19 @@ void __init mrst_rtc_init(void) sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc); } -int mrst_identify_cpu(void) -{ - return mrst_cpu_chip; -} -EXPORT_SYMBOL_GPL(mrst_identify_cpu); - void __cpuinit mrst_arch_setup(void) { if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x27) - mrst_cpu_chip = MRST_CPU_CHIP_PENWELL; + __mrst_cpu_chip = MRST_CPU_CHIP_PENWELL; else if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x26) - mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT; + __mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT; else { pr_err("Unknown Moorestown CPU (%d:%d), default to Lincroft\n", boot_cpu_data.x86, boot_cpu_data.x86_model); - mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT; + __mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT; } pr_debug("Moorestown CPU %s identified\n", - (mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT) ? + (__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT) ? "Lincroft" : "Penwell"); } From 14671386dcbafb3086bbda3cb6f9f27d34c7bf6d Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Wed, 19 May 2010 14:37:40 -0700 Subject: [PATCH 5/5] x86, mrst: make mrst_timer_options an enum We have an enum mrst_timer_options, use it so that the kernel knows if we're missing something from a switch statement or equivalent. Signed-off-by: H. Peter Anvin LKML-Reference: <1274295685-6774-4-git-send-email-jacob.jun.pan@linux.intel.com> Cc: Thomas Gleixner Cc: Jacob Pan --- arch/x86/include/asm/mrst.h | 3 ++- arch/x86/kernel/mrst.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h index 1869c18d15ca..16350740edf6 100644 --- a/arch/x86/include/asm/mrst.h +++ b/arch/x86/include/asm/mrst.h @@ -11,7 +11,6 @@ #ifndef _ASM_X86_MRST_H #define _ASM_X86_MRST_H extern int pci_mrst_init(void); -extern int mrst_timer_options __cpuinitdata; int __init sfi_parse_mrtc(struct sfi_table_header *table); /* @@ -38,6 +37,8 @@ enum mrst_timer_options { MRST_TIMER_LAPIC_APBT, }; +extern enum mrst_timer_options mrst_timer_options; + #define SFI_MTMR_MAX_NUM 8 #define SFI_MRTC_MAX 8 diff --git a/arch/x86/kernel/mrst.c b/arch/x86/kernel/mrst.c index 967f2686adb0..7ee4ed901baf 100644 --- a/arch/x86/kernel/mrst.c +++ b/arch/x86/kernel/mrst.c @@ -46,7 +46,7 @@ * lapic (always-on,ARAT) ------ 150 */ -int mrst_timer_options __cpuinitdata; +__cpuinitdata enum mrst_timer_options mrst_timer_options; static u32 sfi_mtimer_usage[SFI_MTMR_MAX_NUM]; static struct sfi_timer_table_entry sfi_mtimer_array[SFI_MTMR_MAX_NUM];