diff options
Diffstat (limited to 'include')
31 files changed, 849 insertions, 474 deletions
diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 7798d2a9f793..916c0102db5b 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -79,6 +79,7 @@ struct acpi_processor_power { u32 bm_activity; int count; struct acpi_processor_cx states[ACPI_PROCESSOR_MAX_POWER]; + int timer_broadcast_on_state; }; /* Performance Management */ diff --git a/include/asm-i386/apic.h b/include/asm-i386/apic.h index 3a61206fd108..cc6b1652249a 100644 --- a/include/asm-i386/apic.h +++ b/include/asm-i386/apic.h @@ -95,9 +95,7 @@ static inline void ack_APIC_irq(void) apic_write_around(APIC_EOI, 0); } -extern void (*wait_timer_tick)(void); - -extern int get_maxlvt(void); +extern int lapic_get_maxlvt(void); extern void clear_local_APIC(void); extern void connect_bsp_APIC (void); extern void disconnect_bsp_APIC (int virt_wire_setup); @@ -113,14 +111,9 @@ extern void smp_local_timer_interrupt (void); extern void setup_boot_APIC_clock (void); extern void setup_secondary_APIC_clock (void); extern int APIC_init_uniprocessor (void); -extern void disable_APIC_timer(void); -extern void enable_APIC_timer(void); extern void enable_NMI_through_LVT0 (void * dummy); -void smp_send_timer_broadcast_ipi(void); -void switch_APIC_timer_to_ipi(void *cpumask); -void switch_ipi_to_APIC_timer(void *cpumask); #define ARCH_APICTIMER_STOPS_ON_C3 1 extern int timer_over_8254; diff --git a/include/asm-i386/hpet.h b/include/asm-i386/hpet.h index e47be9a56cc2..fc03cf9de5c4 100644 --- a/include/asm-i386/hpet.h +++ b/include/asm-i386/hpet.h @@ -90,16 +90,19 @@ #define HPET_MIN_PERIOD (100000UL) #define HPET_TICK_RATE (HZ * 100000UL) -extern unsigned long hpet_tick; /* hpet clks count per tick */ extern unsigned long hpet_address; /* hpet memory map physical address */ -extern int hpet_use_timer; +extern int is_hpet_enabled(void); +#ifdef CONFIG_X86_64 +extern unsigned long hpet_tick; /* hpet clks count per tick */ +extern int hpet_use_timer; extern int hpet_rtc_timer_init(void); extern int hpet_enable(void); -extern int hpet_reenable(void); -extern int is_hpet_enabled(void); extern int is_hpet_capable(void); extern int hpet_readl(unsigned long a); +#else +extern int hpet_enable(void); +#endif #ifdef CONFIG_HPET_EMULATE_RTC extern int hpet_mask_rtc_irq_bit(unsigned long bit_mask); @@ -110,5 +113,10 @@ extern int hpet_rtc_dropped_irq(void); extern int hpet_rtc_timer_init(void); extern irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id); #endif /* CONFIG_HPET_EMULATE_RTC */ + +#else + +static inline int hpet_enable(void) { return 0; } + #endif /* CONFIG_HPET_TIMER */ #endif /* _I386_HPET_H */ diff --git a/include/asm-i386/i8253.h b/include/asm-i386/i8253.h index 015d8df07690..6cb0dd4dcdde 100644 --- a/include/asm-i386/i8253.h +++ b/include/asm-i386/i8253.h @@ -1,6 +1,21 @@ #ifndef __ASM_I8253_H__ #define __ASM_I8253_H__ +#include <linux/clockchips.h> + extern spinlock_t i8253_lock; +extern struct clock_event_device *global_clock_event; + +/** + * pit_interrupt_hook - hook into timer tick + * @regs: standard registers from interrupt + * + * Call the global clock event handler. + **/ +static inline void pit_interrupt_hook(void) +{ + global_clock_event->event_handler(global_clock_event); +} + #endif /* __ASM_I8253_H__ */ diff --git a/include/asm-i386/mach-default/do_timer.h b/include/asm-i386/mach-default/do_timer.h index 7d606e3364ae..56e5689863ae 100644 --- a/include/asm-i386/mach-default/do_timer.h +++ b/include/asm-i386/mach-default/do_timer.h @@ -1,86 +1,16 @@ /* defines for inline arch setup functions */ +#include <linux/clockchips.h> -#include <asm/apic.h> #include <asm/i8259.h> +#include <asm/i8253.h> /** * do_timer_interrupt_hook - hook into timer tick - * @regs: standard registers from interrupt * - * Description: - * This hook is called immediately after the timer interrupt is ack'd. - * It's primary purpose is to allow architectures that don't possess - * individual per CPU clocks (like the CPU APICs supply) to broadcast the - * timer interrupt as a means of triggering reschedules etc. + * Call the pit clock event handler. see asm/i8253.h **/ static inline void do_timer_interrupt_hook(void) { - do_timer(1); -#ifndef CONFIG_SMP - update_process_times(user_mode_vm(get_irq_regs())); -#endif -/* - * In the SMP case we use the local APIC timer interrupt to do the - * profiling, except when we simulate SMP mode on a uniprocessor - * system, in that case we have to call the local interrupt handler. - */ -#ifndef CONFIG_X86_LOCAL_APIC - profile_tick(CPU_PROFILING); -#else - if (!using_apic_timer) - smp_local_timer_interrupt(); -#endif -} - - -/* you can safely undefine this if you don't have the Neptune chipset */ - -#define BUGGY_NEPTUN_TIMER - -/** - * do_timer_overflow - process a detected timer overflow condition - * @count: hardware timer interrupt count on overflow - * - * Description: - * This call is invoked when the jiffies count has not incremented but - * the hardware timer interrupt has. It means that a timer tick interrupt - * came along while the previous one was pending, thus a tick was missed - **/ -static inline int do_timer_overflow(int count) -{ - int i; - - spin_lock(&i8259A_lock); - /* - * This is tricky when I/O APICs are used; - * see do_timer_interrupt(). - */ - i = inb(0x20); - spin_unlock(&i8259A_lock); - - /* assumption about timer being IRQ0 */ - if (i & 0x01) { - /* - * We cannot detect lost timer interrupts ... - * well, that's why we call them lost, don't we? :) - * [hmm, on the Pentium and Alpha we can ... sort of] - */ - count -= LATCH; - } else { -#ifdef BUGGY_NEPTUN_TIMER - /* - * for the Neptun bug we know that the 'latch' - * command doesn't latch the high and low value - * of the counter atomically. Thus we have to - * substract 256 from the counter - * ... funny, isnt it? :) - */ - - count -= 256; -#else - printk("do_slow_gettimeoffset(): hardware timer problem?\n"); -#endif - } - return count; + pit_interrupt_hook(); } diff --git a/include/asm-i386/mach-voyager/do_timer.h b/include/asm-i386/mach-voyager/do_timer.h index 04e69c104a74..60f9dcc15d54 100644 --- a/include/asm-i386/mach-voyager/do_timer.h +++ b/include/asm-i386/mach-voyager/do_timer.h @@ -1,25 +1,18 @@ /* defines for inline arch setup functions */ +#include <linux/clockchips.h> + #include <asm/voyager.h> +#include <asm/i8253.h> +/** + * do_timer_interrupt_hook - hook into timer tick + * @regs: standard registers from interrupt + * + * Call the pit clock event handler. see asm/i8253.h + **/ static inline void do_timer_interrupt_hook(void) { - do_timer(1); -#ifndef CONFIG_SMP - update_process_times(user_mode_vm(irq_regs)); -#endif - + pit_interrupt_hook(); voyager_timer_interrupt(); } -static inline int do_timer_overflow(int count) -{ - /* can't read the ISR, just assume 1 tick - overflow */ - if(count > LATCH || count < 0) { - printk(KERN_ERR "VOYAGER PROBLEM: count is %d, latch is %d\n", count, LATCH); - count = LATCH; - } - count -= LATCH; - - return count; -} diff --git a/include/asm-i386/mpspec.h b/include/asm-i386/mpspec.h index 770bf6da8c3d..f21349399d14 100644 --- a/include/asm-i386/mpspec.h +++ b/include/asm-i386/mpspec.h @@ -23,7 +23,6 @@ extern struct mpc_config_intsrc mp_irqs [MAX_IRQ_SOURCES]; extern int mpc_default_type; extern unsigned long mp_lapic_addr; extern int pic_mode; -extern int using_apic_timer; #ifdef CONFIG_ACPI extern void mp_register_lapic (u8 id, u8 enabled); diff --git a/include/asm-i386/msr.h b/include/asm-i386/msr.h index 609a3899475c..6db40d0583f1 100644 --- a/include/asm-i386/msr.h +++ b/include/asm-i386/msr.h @@ -307,4 +307,7 @@ static inline void wrmsrl (unsigned long msr, unsigned long long val) #define MSR_CORE_PERF_GLOBAL_CTRL 0x38f #define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x390 +/* Geode defined MSRs */ +#define MSR_GEODE_BUSCONT_CONF0 0x1900 + #endif /* __ASM_MSR_H */ diff --git a/include/asm-i386/tsc.h b/include/asm-i386/tsc.h index c13933185c1c..e997891cc7cc 100644 --- a/include/asm-i386/tsc.h +++ b/include/asm-i386/tsc.h @@ -1,48 +1 @@ -/* - * linux/include/asm-i386/tsc.h - * - * i386 TSC related functions - */ -#ifndef _ASM_i386_TSC_H -#define _ASM_i386_TSC_H - -#include <asm/processor.h> - -/* - * Standard way to access the cycle counter on i586+ CPUs. - * Currently only used on SMP. - * - * If you really have a SMP machine with i486 chips or older, - * compile for that, and this will just always return zero. - * That's ok, it just means that the nicer scheduling heuristics - * won't work for you. - * - * We only use the low 32 bits, and we'd simply better make sure - * that we reschedule before that wraps. Scheduling at least every - * four billion cycles just basically sounds like a good idea, - * regardless of how fast the machine is. - */ -typedef unsigned long long cycles_t; - -extern unsigned int cpu_khz; -extern unsigned int tsc_khz; - -static inline cycles_t get_cycles(void) -{ - unsigned long long ret = 0; - -#ifndef CONFIG_X86_TSC - if (!cpu_has_tsc) - return 0; -#endif - -#if defined(CONFIG_X86_GENERIC) || defined(CONFIG_X86_TSC) - rdtscll(ret); -#endif - return ret; -} - -extern void tsc_init(void); -extern void mark_tsc_unstable(void); - -#endif +#include <asm-x86_64/tsc.h> diff --git a/include/asm-x86_64/hpet.h b/include/asm-x86_64/hpet.h index b39098408b69..59a66f084611 100644 --- a/include/asm-x86_64/hpet.h +++ b/include/asm-x86_64/hpet.h @@ -56,8 +56,15 @@ extern int is_hpet_enabled(void); extern int hpet_rtc_timer_init(void); extern int apic_is_clustered_box(void); +extern int hpet_arch_init(void); +extern int hpet_timer_stop_set_go(unsigned long tick); +extern int hpet_reenable(void); +extern unsigned int hpet_calibrate_tsc(void); extern int hpet_use_timer; +extern unsigned long hpet_address; +extern unsigned long hpet_period; +extern unsigned long hpet_tick; #ifdef CONFIG_HPET_EMULATE_RTC extern int hpet_mask_rtc_irq_bit(unsigned long bit_mask); diff --git a/include/asm-x86_64/proto.h b/include/asm-x86_64/proto.h index a6d2ff5c69b7..f54f3abf93ce 100644 --- a/include/asm-x86_64/proto.h +++ b/include/asm-x86_64/proto.h @@ -45,11 +45,7 @@ extern u32 pmtmr_ioport; #else #define pmtmr_ioport 0 #endif -extern unsigned long long monotonic_base; -extern int sysctl_vsyscall; extern int nohpet; -extern unsigned long vxtime_hz; -extern void time_init_gtod(void); extern void early_printk(const char *fmt, ...) __attribute__((format(printf,1,2))); @@ -91,8 +87,6 @@ extern void check_efer(void); extern int unhandled_signal(struct task_struct *tsk, int sig); -extern int unsynchronized_tsc(void); - extern void select_idle_routine(const struct cpuinfo_x86 *c); extern unsigned long table_start, table_end; diff --git a/include/asm-x86_64/timex.h b/include/asm-x86_64/timex.h index b9e5320b7625..8c6808a3fba4 100644 --- a/include/asm-x86_64/timex.h +++ b/include/asm-x86_64/timex.h @@ -12,38 +12,21 @@ #include <asm/hpet.h> #include <asm/system.h> #include <asm/processor.h> +#include <asm/tsc.h> #include <linux/compiler.h> #define CLOCK_TICK_RATE PIT_TICK_RATE /* Underlying HZ */ -typedef unsigned long long cycles_t; - -static inline cycles_t get_cycles (void) -{ - unsigned long long ret; - - rdtscll(ret); - return ret; -} - -/* Like get_cycles, but make sure the CPU is synchronized. */ -static __always_inline cycles_t get_cycles_sync(void) -{ - unsigned long long ret; - unsigned eax; - /* Don't do an additional sync on CPUs where we know - RDTSC is already synchronous. */ - alternative_io("cpuid", ASM_NOP2, X86_FEATURE_SYNC_RDTSC, - "=a" (eax), "0" (1) : "ebx","ecx","edx","memory"); - rdtscll(ret); - return ret; -} - -extern unsigned int cpu_khz; - extern int read_current_timer(unsigned long *timer_value); #define ARCH_HAS_READ_CURRENT_TIMER 1 -extern struct vxtime_data vxtime; +#define USEC_PER_TICK (USEC_PER_SEC / HZ) +#define NSEC_PER_TICK (NSEC_PER_SEC / HZ) +#define FSEC_PER_TICK (FSEC_PER_SEC / HZ) + +#define NS_SCALE 10 /* 2^10, carefully chosen */ +#define US_SCALE 32 /* 2^32, arbitralrily chosen */ +extern void mark_tsc_unstable(void); +extern void set_cyc2ns_scale(unsigned long khz); #endif diff --git a/include/asm-x86_64/tsc.h b/include/asm-x86_64/tsc.h new file mode 100644 index 000000000000..9a0a368852c7 --- /dev/null +++ b/include/asm-x86_64/tsc.h @@ -0,0 +1,66 @@ +/* + * linux/include/asm-x86_64/tsc.h + * + * x86_64 TSC related functions + */ +#ifndef _ASM_x86_64_TSC_H +#define _ASM_x86_64_TSC_H + +#include <asm/processor.h> + +/* + * Standard way to access the cycle counter. + */ +typedef unsigned long long cycles_t; + +extern unsigned int cpu_khz; +extern unsigned int tsc_khz; + +static inline cycles_t get_cycles(void) +{ + unsigned long long ret = 0; + +#ifndef CONFIG_X86_TSC + if (!cpu_has_tsc) + return 0; +#endif + +#if defined(CONFIG_X86_GENERIC) || defined(CONFIG_X86_TSC) + rdtscll(ret); +#endif + return ret; +} + +/* Like get_cycles, but make sure the CPU is synchronized. */ +static __always_inline cycles_t get_cycles_sync(void) +{ + unsigned long long ret; +#ifdef X86_FEATURE_SYNC_RDTSC + unsigned eax; + + /* + * Don't do an additional sync on CPUs where we know + * RDTSC is already synchronous: + */ + alternative_io("cpuid", ASM_NOP2, X86_FEATURE_SYNC_RDTSC, + "=a" (eax), "0" (1) : "ebx","ecx","edx","memory"); +#else + sync_core(); +#endif + rdtscll(ret); + + return ret; +} + +extern void tsc_init(void); +extern void mark_tsc_unstable(void); +extern int unsynchronized_tsc(void); + +/* + * Boot-time check whether the TSCs are synchronized across + * all CPUs/cores: + */ +extern void check_tsc_sync_source(int cpu); +extern void check_tsc_sync_target(void); + +#endif diff --git a/include/asm-x86_64/vsyscall.h b/include/asm-x86_64/vsyscall.h index 0c7847165eae..82b4afe65c91 100644 --- a/include/asm-x86_64/vsyscall.h +++ b/include/asm-x86_64/vsyscall.h @@ -16,46 +16,27 @@ enum vsyscall_num { #ifdef __KERNEL__ #include <linux/seqlock.h> -#define __section_vxtime __attribute__ ((unused, __section__ (".vxtime"), aligned(16))) #define __section_vgetcpu_mode __attribute__ ((unused, __section__ (".vgetcpu_mode"), aligned(16))) #define __section_jiffies __attribute__ ((unused, __section__ (".jiffies"), aligned(16))) -#define __section_sys_tz __attribute__ ((unused, __section__ (".sys_tz"), aligned(16))) -#define __section_sysctl_vsyscall __attribute__ ((unused, __section__ (".sysctl_vsyscall"), aligned(16))) -#define __section_xtime __attribute__ ((unused, __section__ (".xtime"), aligned(16))) -#define __section_xtime_lock __attribute__ ((unused, __section__ (".xtime_lock"), aligned(16))) -#define VXTIME_TSC 1 -#define VXTIME_HPET 2 -#define VXTIME_PMTMR 3 +/* Definitions for CONFIG_GENERIC_TIME definitions */ +#define __section_vsyscall_gtod_data __attribute__ \ + ((unused, __section__ (".vsyscall_gtod_data"),aligned(16))) +#define __vsyscall_fn __attribute__ ((unused,__section__(".vsyscall_fn"))) #define VGETCPU_RDTSCP 1 #define VGETCPU_LSL 2 -struct vxtime_data { - long hpet_address; /* HPET base address */ - int last; - unsigned long last_tsc; - long quot; - long tsc_quot; - int mode; -}; - #define hpet_readl(a) readl((const void __iomem *)fix_to_virt(FIX_HPET_BASE) + a) #define hpet_writel(d,a) writel(d, (void __iomem *)fix_to_virt(FIX_HPET_BASE) + a) -/* vsyscall space (readonly) */ -extern struct vxtime_data __vxtime; extern int __vgetcpu_mode; -extern struct timespec __xtime; extern volatile unsigned long __jiffies; -extern struct timezone __sys_tz; -extern seqlock_t __xtime_lock; /* kernel space (writeable) */ -extern struct vxtime_data vxtime; extern int vgetcpu_mode; extern struct timezone sys_tz; -extern int sysctl_vsyscall; +extern struct vsyscall_gtod_data_t vsyscall_gtod_data; #endif /* __KERNEL__ */ diff --git a/include/linux/acpi_pmtmr.h b/include/linux/acpi_pmtmr.h new file mode 100644 index 000000000000..1d0ef1ae8036 --- /dev/null +++ b/include/linux/acpi_pmtmr.h @@ -0,0 +1,38 @@ +#ifndef _ACPI_PMTMR_H_ +#define _ACPI_PMTMR_H_ + +#include <linux/clocksource.h> + +/* Number of PMTMR ticks expected during calibration run */ +#define PMTMR_TICKS_PER_SEC 3579545 + +/* limit it to 24 bits */ +#define ACPI_PM_MASK CLOCKSOURCE_MASK(24) + +/* Overrun value */ +#define ACPI_PM_OVRRUN (1<<24) + +#ifdef CONFIG_X86_PM_TIMER + +extern u32 acpi_pm_read_verified(void); +extern u32 pmtmr_ioport; + +static inline u32 acpi_pm_read_early(void) +{ + if (!pmtmr_ioport) + return 0; + /* mask the output to 24 bits */ + return acpi_pm_read_verified() & ACPI_PM_MASK; +} + +#else + +static inline u32 acpi_pm_read_early(void) +{ + return 0; +} + +#endif + +#endif + diff --git a/include/linux/agp_backend.h b/include/linux/agp_backend.h index a5c8bb5d80ba..abc521cfb084 100644 --- a/include/linux/agp_backend.h +++ b/include/linux/agp_backend.h @@ -87,10 +87,15 @@ struct agp_memory { u32 physical; u8 is_bound; u8 is_flushed; + u8 vmalloc_flag; }; #define AGP_NORMAL_MEMORY 0 +#define AGP_USER_TYPES (1 << 16) +#define AGP_USER_MEMORY (AGP_USER_TYPES) +#define AGP_USER_CACHED_MEMORY (AGP_USER_TYPES + 1) + extern struct agp_bridge_data *agp_bridge; extern struct list_head agp_bridges; diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h new file mode 100644 index 000000000000..4ea7e7bcfafe --- /dev/null +++ b/include/linux/clockchips.h @@ -0,0 +1,142 @@ +/* linux/include/linux/clockchips.h + * + * This file contains the structure definitions for clockchips. + * + * If you are not a clockchip, or the time of day code, you should + * not be including this file! + */ +#ifndef _LINUX_CLOCKCHIPS_H +#define _LINUX_CLOCKCHIPS_H + +#ifdef CONFIG_GENERIC_CLOCKEVENTS + +#include <linux/clocksource.h> +#include <linux/cpumask.h> +#include <linux/ktime.h> +#include <linux/notifier.h> + +struct clock_event_device; + +/* Clock event mode commands */ +enum clock_event_mode { + CLOCK_EVT_MODE_UNUSED = 0, + CLOCK_EVT_MODE_SHUTDOWN, + CLOCK_EVT_MODE_PERIODIC, + CLOCK_EVT_MODE_ONESHOT, +}; + +/* Clock event notification values */ +enum clock_event_nofitiers { + CLOCK_EVT_NOTIFY_ADD, + CLOCK_EVT_NOTIFY_BROADCAST_ON, + CLOCK_EVT_NOTIFY_BROADCAST_OFF, + CLOCK_EVT_NOTIFY_BROADCAST_ENTER, + CLOCK_EVT_NOTIFY_BROADCAST_EXIT, + CLOCK_EVT_NOTIFY_SUSPEND, + CLOCK_EVT_NOTIFY_RESUME, + CLOCK_EVT_NOTIFY_CPU_DEAD, +}; + +/* + * Clock event features + */ +#define CLOCK_EVT_FEAT_PERIODIC 0x000001 +#define CLOCK_EVT_FEAT_ONESHOT 0x000002 +/* + * x86(64) specific misfeatures: + * + * - Clockevent source stops in C3 State and needs broadcast support. + * - Local APIC timer is used as a dummy device. + */ +#define CLOCK_EVT_FEAT_C3STOP 0x000004 +#define CLOCK_EVT_FEAT_DUMMY 0x000008 + +/** + * struct clock_event_device - clock event device descriptor + * @name: ptr to clock event name + * @hints: usage hints + * @max_delta_ns: maximum delta value in ns + * @min_delta_ns: minimum delta value in ns + * @mult: nanosecond to cycles multiplier + * @shift: nanoseconds to cycles divisor (power of two) + * @rating: variable to rate clock event devices + * @irq: irq number (only for non cpu local devices) + * @cpumask: cpumask to indicate for which cpus this device works + * @set_next_event: set next event + * @set_mode: set mode function + * @evthandler: Assigned by the framework to be called by the low + * level handler of the event source + * @broadcast: function to broadcast events + * @list: list head for the management code + * @mode: operating mode assigned by the management code + * @next_event: local storage for the next event in oneshot mode + */ +struct clock_event_device { + const char *name; + unsigned int features; + unsigned long max_delta_ns; + unsigned long min_delta_ns; + unsigned long mult; + int shift; + int rating; + int irq; + cpumask_t cpumask; + int (*set_next_event)(unsigned long evt, + struct clock_event_device *); + void (*set_mode)(enum clock_event_mode mode, + struct clock_event_device *); + void (*event_handler)(struct clock_event_device *); + void (*broadcast)(cpumask_t mask); + struct list_head list; + enum clock_event_mode mode; + ktime_t next_event; +}; + +/* + * Calculate a multiplication factor for scaled math, which is used to convert + * nanoseconds based values to clock ticks: + * + * clock_ticks = (nanoseconds * factor) >> shift. + * + * div_sc is the rearranged equation to calculate a factor from a given clock + * ticks / nanoseconds ratio: + * + * factor = (clock_ticks << shift) / nanoseconds + */ +static inline unsigned long div_sc(unsigned long ticks, unsigned long nsec, + int shift) +{ + uint64_t tmp = ((uint64_t)ticks) << shift; + + do_div(tmp, nsec); + return (unsigned long) tmp; +} + +/* Clock event layer functions */ +extern unsigned long clockevent_delta2ns(unsigned long latch, + struct clock_event_device *evt); +extern void clockevents_register_device(struct clock_event_device *dev); + +extern void clockevents_exchange_device(struct clock_event_device *old, + struct clock_event_device *new); +extern +struct clock_event_device *clockevents_request_device(unsigned int features, + cpumask_t cpumask); +extern void clockevents_release_device(struct clock_event_device *dev); +extern void clockevents_set_mode(struct clock_event_device *dev, + enum clock_event_mode mode); +extern int clockevents_register_notifier(struct notifier_block *nb); +extern void clockevents_unregister_notifier(struct notifier_block *nb); +extern int clockevents_program_event(struct clock_event_device *dev, + ktime_t expires, ktime_t now); + +extern void clockevents_notify(unsigned long reason, void *arg); + +#else + +static inline void clockevents_resume_events(void) { } +#define clockevents_notify(reason, arg) do { } while (0) + +#endif + +#endif diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 1622d23a8dc3..daa4940cc0f1 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -12,11 +12,13 @@ #include <linux/timex.h> #include <linux/time.h> #include <linux/list.h> +#include <linux/timer.h> #include <asm/div64.h> #include <asm/io.h> /* clocksource cycle base type */ typedef u64 cycle_t; +struct clocksource; /** * struct clocksource - hardware abstraction for a free running counter @@ -44,8 +46,8 @@ typedef u64 cycle_t; * subtraction of non 64 bit counters * @mult: cycle to nanosecond multiplier * @shift: cycle to nanosecond divisor (power of two) - * @update_callback: called when safe to alter clocksource values - * @is_continuous: defines if clocksource is free-running. + * @flags: flags describing special properties + * @vread: vsyscall based read * @cycle_interval: Used internally by timekeeping core, please ignore. * @xtime_interval: Used internally by timekeeping core, please ignore. */ @@ -57,15 +59,30 @@ struct clocksource { cycle_t mask; u32 mult; u32 shift; - int (*update_callback)(void); - int is_continuous; + unsigned long flags; + cycle_t (*vread)(void); /* timekeeping specific data, ignore */ cycle_t cycle_last, cycle_interval; u64 xtime_nsec, xtime_interval; s64 error; + +#ifdef CONFIG_CLOCKSOURCE_WATCHDOG + /* Watchdog related data, used by the framework */ + struct list_head wd_list; + cycle_t wd_last; +#endif }; +/* + * Clock source flags bits:: + */ +#define CLOCK_SOURCE_IS_CONTINUOUS 0x01 +#define CLOCK_SOURCE_MUST_VERIFY 0x02 + +#define CLOCK_SOURCE_WATCHDOG 0x10 +#define CLOCK_SOURCE_VALID_FOR_HRES 0x20 + /* simplify initialization of mask field */ #define CLOCKSOURCE_MASK(bits) (cycle_t)(bits<64 ? ((1ULL<<bits)-1) : -1) @@ -178,8 +195,16 @@ static inline void clocksource_calculate_interval(struct clocksource *c, /* used to install a new clocksource */ -int clocksource_register(struct clocksource*); -void clocksource_reselect(void); -struct clocksource* clocksource_get_next(void); +extern int clocksource_register(struct clocksource*); +extern struct clocksource* clocksource_get_next(void); +extern void clocksource_change_rating(struct clocksource *cs, int rating); + +#ifdef CONFIG_GENERIC_TIME_VSYSCALL +extern void update_vsyscall(struct timespec *ts, struct clocksource *c); +#else +static inline void update_vsyscall(struct timespec *ts, struct clocksource *c) +{ +} +#endif #endif /* _LINUX_CLOCKSOURCE_H */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 7f008f6bfdc3..0899e2cdcdd1 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -84,9 +84,6 @@ struct cpufreq_policy { unsigned int policy; /* see above */ struct cpufreq_governor *governor; /* see below */ - struct mutex lock; /* CPU ->setpolicy or ->target may - only be called once a time */ - struct work_struct update; /* if update_policy() needs to be * called, but you're in IRQ context */ @@ -172,11 +169,16 @@ extern int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int relation); -extern int cpufreq_driver_getavg(struct cpufreq_policy *policy); +extern int __cpufreq_driver_getavg(struct cpufreq_policy *policy); int cpufreq_register_governor(struct cpufreq_governor *governor); void cpufreq_unregister_governor(struct cpufreq_governor *governor); +int lock_policy_rwsem_read(int cpu); +int lock_policy_rwsem_write(int cpu); +void unlock_policy_rwsem_read(int cpu); +void unlock_policy_rwsem_write(int cpu); + /********************************************************************* * CPUFREQ DRIVER INTERFACE * diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 612472aaa79c..7803014f3a11 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -106,7 +106,7 @@ static inline void account_system_vtime(struct task_struct *tsk) * always balanced, so the interrupted value of ->hardirq_context * will always be restored. */ -#define irq_enter() \ +#define __irq_enter() \ do { \ account_system_vtime(current); \ add_preempt_count(HARDIRQ_OFFSET); \ @@ -114,6 +114,11 @@ static inline void account_system_vtime(struct task_struct *tsk) } while (0) /* + * Enter irq context (on NO_HZ, update jiffies): + */ +extern void irq_enter(void); + +/* * Exit irq context without processing softirqs: */ #define __irq_exit() \ @@ -128,7 +133,7 @@ static inline void account_system_vtime(struct task_struct *tsk) */ extern void irq_exit(void); -#define nmi_enter() do { lockdep_off(); irq_enter(); } while (0) +#define nmi_enter() do { lockdep_off(); __irq_enter(); } while (0) #define nmi_exit() do { __irq_exit(); lockdep_on(); } while (0) #endif /* LINUX_HARDIRQ_H */ diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index fca93025ab51..37f9279192a9 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -21,22 +21,72 @@ #include <linux/list.h> #include <linux/wait.h> +struct hrtimer_clock_base; +struct hrtimer_cpu_base; + /* * Mode arguments of xxx_hrtimer functions: */ enum hrtimer_mode { - HRTIMER_ABS, /* Time value is absolute */ - HRTIMER_REL, /* Time value is relative to now */ + HRTIMER_MODE_ABS, /* Time value is absolute */ + HRTIMER_MODE_REL, /* Time value is relative to now */ }; +/* + * Return values for the callback function + */ enum hrtimer_restart { - HRTIMER_NORESTART, - HRTIMER_RESTART, + HRTIMER_NORESTART, /* Timer is not restarted */ + HRTIMER_RESTART, /* Timer must be restarted */ }; -#define HRTIMER_INACTIVE ((void *)1UL) +/* + * hrtimer callback modes: + * + * HRTIMER_CB_SOFTIRQ: Callback must run in softirq context + * HRTIMER_CB_IRQSAFE: Callback may run in hardirq context + * HRTIMER_CB_IRQSAFE_NO_RESTART: Callback may run in hardirq context and + * does not restart the timer + * HRTIMER_CB_IRQSAFE_NO_SOFTIRQ: Callback must run in softirq context + * Special mode for tick emultation + */ +enum hrtimer_cb_mode { + HRTIMER_CB_SOFTIRQ, + HRTIMER_CB_IRQSAFE, + HRTIMER_CB_IRQSAFE_NO_RESTART, + HRTIMER_CB_IRQSAFE_NO_SOFTIRQ, +}; -struct hrtimer_base; +/* + * Values to track state of the timer + * + * Possible states: + * + * 0x00 inactive + * 0x01 enqueued into rbtree + * 0x02 callback function running + * 0x04 callback pending (high resolution mode) + * + * Special case: + * 0x03 callback function running and enqueued + * (was requeued on another CPU) + * The "callback function running and enqueued" status is only possible on + * SMP. It happens for example when a posix timer expired and the callback + * queued a signal. Between dropping the lock which protects the posix timer + * and reacquiring the base lock of the hrtimer, another CPU can deliver the + * signal and rearm the timer. We have to preserve the callback running state, + * as otherwise the timer could be removed before the softirq code finishes the + * the handling of the timer. + * + * The HRTIMER_STATE_ENQUEUE bit is always or'ed to the current state to + * preserve the HRTIMER_STATE_CALLBACK bit in the above scenario. + * + * All state transitions are protected by cpu_base->lock. + */ +#define HRTIMER_STATE_INACTIVE 0x00 +#define HRTIMER_STATE_ENQUEUED 0x01 +#define HRTIMER_STATE_CALLBACK 0x02 +#define HRTIMER_STATE_PENDING 0x04 /** * struct hrtimer - the basic hrtimer structure @@ -46,14 +96,34 @@ struct hrtimer_base; * which the timer is based. * @function: timer expiry callback function * @base: pointer to the timer base (per cpu and per clock) + * @state: state information (See bit values above) + * @cb_mode: high resolution timer feature to select the callback execution + * mode + * @cb_entry: list head to enqueue an expired timer into the callback list + * @start_site: timer statistics field to store the site where the timer + * was started + * @start_comm: timer statistics field to store the name of the process which + * started the timer + * @start_pid: timer statistics field to store the pid of the task which + * started the timer * - * The hrtimer structure must be initialized by init_hrtimer_#CLOCKTYPE() + * The hrtimer structure must be initialized by hrtimer_init() */ struct hrtimer { - struct rb_node node; - ktime_t expires; - int (*function)(struct hrtimer *); - struct hrtimer_base *base; + struct rb_node node; + ktime_t expires; + enum hrtimer_restart (*function)(struct hrtimer *); + struct hrtimer_clock_base *base; + unsigned long state; +#ifdef CONFIG_HIGH_RES_TIMERS + enum hrtimer_cb_mode cb_mode; + struct list_head cb_entry; +#endif +#ifdef CONFIG_TIMER_STATS + void *start_site; + char start_comm[16]; + int start_pid; +#endif }; /** @@ -70,37 +140,114 @@ struct hrtimer_sleeper { /** * struct hrtimer_base - the timer base for a specific clock - * @index: clock type index for per_cpu support when moving a timer - * to a base on another cpu. - * @lock: lock protecting the base and associated timers + * @index: clock type index for per_cpu support when moving a + * timer to a base on another cpu. * @active: red black tree root node for the active timers * @first: pointer to the timer node which expires first * @resolution: the resolution of the clock, in nanoseconds * @get_time: function to retrieve the current time of the clock * @get_softirq_time: function to retrieve the current time from the softirq - * @curr_timer: the timer which is executing a callback right now * @softirq_time: the time when running the hrtimer queue in the softirq - * @lock_key: the lock_class_key for use with lockdep + * @cb_pending: list of timers where the callback is pending + * @offset: offset of this clock to the monotonic base + * @reprogram: function to reprogram the timer event */ -struct hrtimer_base { +struct hrtimer_clock_base { + struct hrtimer_cpu_base *cpu_base; clockid_t index; - spinlock_t lock; struct rb_root active; struct rb_node *first; ktime_t resolution; ktime_t (*get_time)(void); ktime_t (*get_softirq_time)(void); - struct hrtimer *curr_timer; ktime_t softirq_time; - struct lock_class_key lock_key; +#ifdef CONFIG_HIGH_RES_TIMERS + ktime_t offset; + int (*reprogram)(struct hrtimer *t, + struct hrtimer_clock_base *b, + ktime_t n); +#endif +}; + +#define HRTIMER_MAX_CLOCK_BASES 2 + +/* + * struct hrtimer_cpu_base - the per cpu clock bases + * @lock: lock protecting the base and associated clock bases + * and timers + * @lock_key: the lock_class_key for use with lockdep + * @clock_base: array of clock bases for this cpu + * @curr_timer: the timer which is executing a callback right now + * @expires_next: absolute time of the next event which was scheduled + * via clock_set_next_event() + * @hres_active: State of high resolution mode + * @check_clocks: Indictator, when set evaluate time source and clock + * event devices whether high resolution mode can be + * activated. + * @cb_pending: Expired timers are moved from the rbtree to this + * list in the timer interrupt. The list is processed + * in the softirq. + * @nr_events: Total number of timer interrupt events + */ +struct hrtimer_cpu_base { + spinlock_t lock; + struct lock_class_key lock_key; + struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; +#ifdef CONFIG_HIGH_RES_TIMERS + ktime_t expires_next; + int hres_active; + struct list_head cb_pending; + unsigned long nr_events; +#endif }; +#ifdef CONFIG_HIGH_RES_TIMERS +struct clock_event_device; + +extern void clock_was_set(void); +extern void hrtimer_interrupt(struct clock_event_device *dev); + +/* + * In high resolution mode the time reference must be read accurate + */ +static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer) +{ + return timer->base->get_time(); +} + +/* + * The resolution of the clocks. The resolution value is returned in + * the clock_getres() system call to give application programmers an + * idea of the (in)accuracy of timers. Timer values are rounded up to + * this resolution values. + */ +# define KTIME_HIGH_RES (ktime_t) { .tv64 = 1 } +# define KTIME_MONOTONIC_RES KTIME_HIGH_RES + +#else + +# define KTIME_MONOTONIC_RES KTIME_LOW_RES + /* * clock_was_set() is a NOP for non- high-resolution systems. The * time-sorted order guarantees that a timer does not expire early and * is expired in the next softirq when the clock was advanced. */ -#define clock_was_set() do { } while (0) +static inline void clock_was_set(void) { } + +/* + * In non high resolution mode the time reference is taken from + * the base softirq time variable. + */ +static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer) +{ + return timer->base->softirq_time; +} + +#endif + +extern ktime_t ktime_get(void); +extern ktime_t ktime_get_real(void); /* Exported timer functions: */ @@ -114,19 +261,33 @@ extern int hrtimer_start(struct hrtimer *timer, ktime_t tim, extern int hrtimer_cancel(struct hrtimer *timer); extern int hrtimer_try_to_cancel(struct hrtimer *timer); -#define hrtimer_restart(timer) hrtimer_start((timer), (timer)->expires, HRTIMER_ABS) +static inline int hrtimer_restart(struct hrtimer *timer) +{ + return hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS); +} /* Query timers: */ extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer); extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp); -#ifdef CONFIG_NO_IDLE_HZ extern ktime_t hrtimer_get_next_event(void); -#endif +/* + * A timer is active, when it is enqueued into the rbtree or the callback + * function is running. + */ static inline int hrtimer_active(const struct hrtimer *timer) { - return rb_parent(&timer->node) != &timer->node; + return timer->state != HRTIMER_STATE_INACTIVE; +} + +/* + * Helper function to check, whether the timer is on one of the queues + */ +static inline int hrtimer_is_queued(struct hrtimer *timer) +{ + return timer->state & + (HRTIMER_STATE_ENQUEUED | HRTIMER_STATE_PENDING); } /* Forward a hrtimer so it expires after now: */ @@ -149,4 +310,53 @@ extern void hrtimer_run_queues(void); /* Bootup initialization: */ extern void __init hrtimers_init(void); +#if BITS_PER_LONG < 64 +extern unsigned long ktime_divns(const ktime_t kt, s64 div); +#else /* BITS_PER_LONG < 64 */ +# define ktime_divns(kt, div) (unsigned long)((kt).tv64 / (div)) +#endif + +/* Show pending timers: */ +extern void sysrq_timer_list_show(void); + +/* + * Timer-statistics info: + */ +#ifdef CONFIG_TIMER_STATS + +extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf, + void *timerf, char * comm); + +static inline void timer_stats_account_hrtimer(struct hrtimer *timer) +{ + timer_stats_update_stats(timer, timer->start_pid, timer->start_site, + timer->function, timer->start_comm); +} + +extern void __timer_stats_hrtimer_set_start_info(struct hrtimer *timer, + void *addr); + +static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer) +{ + __timer_stats_hrtimer_set_start_info(timer, __builtin_return_address(0)); +} + +static inline void timer_stats_hrtimer_clear_start_info(struct hrtimer *timer) +{ + timer->start_site = NULL; +} +#else +static inline void timer_stats_account_hrtimer(struct hrtimer *timer) +{ +} + +static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer) +{ +} + +static inline void timer_stats_hrtimer_clear_start_info(struct hrtimer *timer) +{ +} +#endif + #endif diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 5a8ba0b8ccba..e5ea1411050b 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -42,6 +42,8 @@ * IRQF_SHARED - allow sharing the irq among several devices * IRQF_PROBE_SHARED - set by callers when they expect sharing mismatches to occur * IRQF_TIMER - Flag to mark this interrupt as timer interrupt + * IRQF_PERCPU - Interrupt is per cpu + * IRQF_NOBALANCING - Flag to exclude this interrupt from irq balancing */ #define IRQF_DISABLED 0x00000020 #define IRQF_SAMPLE_RANDOM 0x00000040 @@ -49,6 +51,7 @@ #define IRQF_PROBE_SHARED 0x00000100 #define IRQF_TIMER 0x00000200 #define IRQF_PERCPU 0x00000400 +#define IRQF_NOBALANCING 0x00000800 /* * Migration helpers. Scheduled for removal in 1/2007 @@ -239,6 +242,9 @@ enum BLOCK_SOFTIRQ, TASKLET_SOFTIRQ, SCHED_SOFTIRQ, +#ifdef CONFIG_HIGH_RES_TIMERS + HRTIMER_SOFTIRQ, +#endif }; /* softirq mask and active fields moved to irq_cpustat_t in diff --git a/include/linux/irq.h b/include/linux/irq.h index 5504b671357f..1939d42c21d2 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -31,7 +31,7 @@ typedef void fastcall (*irq_flow_handler_t)(unsigned int irq, /* * IRQ line status. * - * Bits 0-16 are reserved for the IRQF_* bits in linux/interrupt.h + * Bits 0-7 are reserved for the IRQF_* bits in linux/interrupt.h * * IRQ types */ @@ -45,28 +45,30 @@ typedef void fastcall (*irq_flow_handler_t)(unsigned int irq, #define IRQ_TYPE_PROBE 0x00000010 /* Probing in progress */ /* Internal flags */ -#define IRQ_INPROGRESS 0x00010000 /* IRQ handler active - do not enter! */ -#define IRQ_DISABLED 0x00020000 /* IRQ disabled - do not enter! */ -#define IRQ_PENDING 0x00040000 /* IRQ pending - replay on enable */ -#define IRQ_REPLAY 0x00080000 /* IRQ has been replayed but not acked yet */ -#define IRQ_AUTODETECT 0x00100000 /* IRQ is being autodetected */ -#define IRQ_WAITING 0x00200000 /* IRQ not yet seen - for autodetection */ -#define IRQ_LEVEL 0x00400000 /* IRQ level triggered */ -#define IRQ_MASKED 0x00800000 /* IRQ masked - shouldn't be seen again */ -#define IRQ_PER_CPU 0x01000000 /* IRQ is per CPU */ +#define IRQ_INPROGRESS 0x00000100 /* IRQ handler active - do not enter! */ +#define IRQ_DISABLED 0x00000200 /* IRQ disabled - do not enter! */ +#define IRQ_PENDING 0x00000400 /* IRQ pending - replay on enable */ +#define IRQ_REPLAY 0x00000800 /* IRQ has been replayed but not acked yet */ +#define IRQ_AUTODETECT 0x00001000 /* IRQ is being autodetected */ +#define IRQ_WAITING 0x00002000 /* IRQ not yet seen - for autodetection */ +#define IRQ_LEVEL 0x00004000 /* IRQ level triggered */ +#define IRQ_MASKED 0x00008000 /* IRQ masked - shouldn't be seen again */ +#define IRQ_PER_CPU 0x00010000 /* IRQ is per CPU */ +#define IRQ_NOPROBE 0x00020000 /* IRQ is not valid for probing */ +#define IRQ_NOREQUEST 0x00040000 /* IRQ cannot be requested */ +#define IRQ_NOAUTOEN 0x00080000 /* IRQ will not be enabled on request irq */ +#define IRQ_WAKEUP 0x00100000 /* IRQ triggers system wakeup */ +#define IRQ_MOVE_PENDING 0x00200000 /* need to re-target IRQ destination */ +#define IRQ_NO_BALANCING 0x00400000 /* IRQ is excluded from balancing */ + #ifdef CONFIG_IRQ_PER_CPU # define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU) +# define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) #else # define CHECK_IRQ_PER_CPU(var) 0 +# define IRQ_NO_BALANCING_MASK IRQ_NO_BALANCING #endif -#define IRQ_NOPROBE 0x02000000 /* IRQ is not valid for probing */ -#define IRQ_NOREQUEST 0x04000000 /* IRQ cannot be requested */ -#define IRQ_NOAUTOEN 0x08000000 /* IRQ will not be enabled on request irq */ -#define IRQ_DELAYED_DISABLE 0x10000000 /* IRQ disable (masking) happens delayed. */ -#define IRQ_WAKEUP 0x20000000 /* IRQ triggers system wakeup */ -#define IRQ_MOVE_PENDING 0x40000000 /* need to re-target IRQ destination */ - struct proc_dir_entry; struct msi_desc; @@ -127,6 +129,7 @@ struct irq_chip { * * @handle_irq: highlevel irq-events handler [if NULL, __do_IRQ()] * @chip: low level interrupt hardware access + * @msi_desc: MSI descriptor * @handler_data: per-IRQ data for the irq_chip methods * @chip_data: platform-specific per-chip private data for the chip * methods, to allow shared chip implementations @@ -235,11 +238,21 @@ static inline void set_pending_irq(unsigned int irq, cpumask_t mask) #endif /* CONFIG_GENERIC_PENDING_IRQ */ +extern int irq_set_affinity(unsigned int irq, cpumask_t cpumask); +extern int irq_can_set_affinity(unsigned int irq); + #else /* CONFIG_SMP */ #define move_native_irq(x) #define move_masked_irq(x) +static inline int irq_set_affinity(unsigned int irq, cpumask_t cpumask) +{ + return -EINVAL; +} + +static inline int irq_can_set_affinity(unsigned int irq) { return 0; } + #endif /* CONFIG_SMP */ #ifdef CONFIG_IRQBALANCE @@ -261,6 +274,11 @@ static inline int select_smp_affinity(unsigned int irq) extern int no_irq_affinity; +static inline int irq_balancing_disabled(unsigned int irq) +{ + return irq_desc[irq].status & IRQ_NO_BALANCING_MASK; +} + /* Handle irq action chains: */ extern int handle_IRQ_event(unsigned int irq, struct irqaction *action); diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 0ec6e28bccd2..c080f61fb024 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -142,13 +142,13 @@ static inline u64 get_jiffies_64(void) * * And some not so obvious. * - * Note that we don't want to return MAX_LONG, because + * Note that we don't want to return LONG_MAX, because * for various timeout reasons we often end up having * to wait "jiffies+1" in order to guarantee that we wait * at _least_ "jiffies" - so "jiffies+1" had better still * be positive. */ -#define MAX_JIFFY_OFFSET ((~0UL >> 1)-1) +#define MAX_JIFFY_OFFSET ((LONG_MAX >> 1)-1) /* * We want to do realistic conversions of time so we need to use the same @@ -259,207 +259,23 @@ static inline u64 get_jiffies_64(void) #endif /* - * Convert jiffies to milliseconds and back. - * - * Avoid unnecessary multiplications/divisions in the - * two most common HZ cases: - */ -static inline unsigned int jiffies_to_msecs(const unsigned long j) -{ -#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) - return (MSEC_PER_SEC / HZ) * j; -#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) - return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC); -#else - return (j * MSEC_PER_SEC) / HZ; -#endif -} - -static inline unsigned int jiffies_to_usecs(const unsigned long j) -{ -#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ) - return (USEC_PER_SEC / HZ) * j; -#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC) - return (j + (HZ / USEC_PER_SEC) - 1)/(HZ / USEC_PER_SEC); -#else - return (j * USEC_PER_SEC) / HZ; -#endif -} - -static inline unsigned long msecs_to_jiffies(const unsigned int m) -{ - if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) - return MAX_JIFFY_OFFSET; -#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) - return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ); -#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) - return m * (HZ / MSEC_PER_SEC); -#else - return (m * HZ + MSEC_PER_SEC - 1) / MSEC_PER_SEC; -#endif -} - -static inline unsigned long usecs_to_jiffies(const unsigned int u) -{ - if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) - return MAX_JIFFY_OFFSET; -#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ) - return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ); -#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC) - return u * (HZ / USEC_PER_SEC); -#else - return (u * HZ + USEC_PER_SEC - 1) / USEC_PER_SEC; -#endif -} - -/* - * The TICK_NSEC - 1 rounds up the value to the next resolution. Note - * that a remainder subtract here would not do the right thing as the - * resolution values don't fall on second boundries. I.e. the line: - * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. - * - * Rather, we just shift the bits off the right. - * - * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec - * value to a scaled second value. - */ -static __inline__ unsigned long -timespec_to_jiffies(const struct timespec *value) -{ - unsigned long sec = value->tv_sec; - long nsec = value->tv_nsec + TICK_NSEC - 1; - - if (sec >= MAX_SEC_IN_JIFFIES){ - sec = MAX_SEC_IN_JIFFIES; - nsec = 0; - } - return (((u64)sec * SEC_CONVERSION) + - (((u64)nsec * NSEC_CONVERSION) >> - (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; - -} - -static __inline__ void -jiffies_to_timespec(const unsigned long jiffies, struct timespec *value) -{ - /* - * Convert jiffies to nanoseconds and separate with - * one divide. - */ - u64 nsec = (u64)jiffies * TICK_NSEC; - value->tv_sec = div_long_long_rem(nsec, NSEC_PER_SEC, &value->tv_nsec); -} - -/* Same for "timeval" - * - * Well, almost. The problem here is that the real system resolution is - * in nanoseconds and the value being converted is in micro seconds. - * Also for some machines (those that use HZ = 1024, in-particular), - * there is a LARGE error in the tick size in microseconds. - - * The solution we use is to do the rounding AFTER we convert the - * microsecond part. Thus the USEC_ROUND, the bits to be shifted off. - * Instruction wise, this should cost only an additional add with carry - * instruction above the way it was done above. - */ -static __inline__ unsigned long -timeval_to_jiffies(const struct timeval *value) -{ - unsigned long sec = value->tv_sec; - long usec = value->tv_usec; - - if (sec >= MAX_SEC_IN_JIFFIES){ - sec = MAX_SEC_IN_JIFFIES; - usec = 0; - } - return (((u64)sec * SEC_CONVERSION) + - (((u64)usec * USEC_CONVERSION + USEC_ROUND) >> - (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; -} - -static __inline__ void -jiffies_to_timeval(const unsigned long jiffies, struct timeval *value) -{ - /* - * Convert jiffies to nanoseconds and separate with - * one divide. - */ - u64 nsec = (u64)jiffies * TICK_NSEC; - long tv_usec; - - value->tv_sec = div_long_long_rem(nsec, NSEC_PER_SEC, &tv_usec); - tv_usec /= NSEC_PER_USEC; - value->tv_usec = tv_usec; -} - -/* - * Convert jiffies/jiffies_64 to clock_t and back. + * Convert various time units to each other: */ -static inline clock_t jiffies_to_clock_t(long x) -{ -#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 - return x / (HZ / USER_HZ); -#else - u64 tmp = (u64)x * TICK_NSEC; - do_div(tmp, (NSEC_PER_SEC / USER_HZ)); - return (long)tmp; -#endif -} - -static inline unsigned long clock_t_to_jiffies(unsigned long x) -{ -#if (HZ % USER_HZ)==0 - if (x >= ~0UL / (HZ / USER_HZ)) - return ~0UL; - return x * (HZ / USER_HZ); -#else - u64 jif; - - /* Don't worry about loss of precision here .. */ - if (x >= ~0UL / HZ * USER_HZ) - return ~0UL; - - /* .. but do try to contain it here */ - jif = x * (u64) HZ; - do_div(jif, USER_HZ); - return jif; -#endif -} - -static inline u64 jiffies_64_to_clock_t(u64 x) -{ -#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 - do_div(x, HZ / USER_HZ); -#else - /* - * There are better ways that don't overflow early, - * but even this doesn't overflow in hundreds of years - * in 64 bits, so.. - */ - x *= TICK_NSEC; - do_div(x, (NSEC_PER_SEC / USER_HZ)); -#endif - return x; -} - -static inline u64 nsec_to_clock_t(u64 x) -{ -#if (NSEC_PER_SEC % USER_HZ) == 0 - do_div(x, (NSEC_PER_SEC / USER_HZ)); -#elif (USER_HZ % 512) == 0 - x *= USER_HZ/512; - do_div(x, (NSEC_PER_SEC / 512)); -#else - /* - * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024, - * overflow after 64.99 years. - * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ... - */ - x *= 9; - do_div(x, (unsigned long)((9ull * NSEC_PER_SEC + (USER_HZ/2)) - / USER_HZ)); -#endif - return x; -} +extern unsigned int jiffies_to_msecs(const unsigned long j); +extern unsigned int jiffies_to_usecs(const unsigned long j); +extern unsigned long msecs_to_jiffies(const unsigned int m); +extern unsigned long usecs_to_jiffies(const unsigned int u); +extern unsigned long timespec_to_jiffies(const struct timespec *value); +extern void jiffies_to_timespec(const unsigned long jiffies, + struct timespec *value); +extern unsigned long timeval_to_jiffies(const struct timeval *value); +extern void jiffies_to_timeval(const unsigned long jiffies, + struct timeval *value); +extern clock_t jiffies_to_clock_t(long x); +extern unsigned long clock_t_to_jiffies(unsigned long x); +extern u64 jiffies_64_to_clock_t(u64 x); +extern u64 nsec_to_clock_t(u64 x); + +#define TIMESTAMP_SIZE 30 #endif diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 7444a6326231..c68c7ac6b232 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -261,8 +261,7 @@ static inline s64 ktime_to_ns(const ktime_t kt) * idea of the (in)accuracy of timers. Timer values are rounded up to * this resolution values. */ -#define KTIME_REALTIME_RES (ktime_t){ .tv64 = TICK_NSEC } -#define KTIME_MONOTONIC_RES (ktime_t){ .tv64 = TICK_NSEC } +#define KTIME_LOW_RES (ktime_t){ .tv64 = TICK_NSEC } /* Get the monotonic time in timespec format: */ extern void ktime_get_ts(struct timespec *ts); diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index db05182ca0e8..1be5be88debe 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -105,12 +105,11 @@ struct nfs4_ace { uint32_t access_mask; int whotype; uid_t who; - struct list_head l_ace; }; struct nfs4_acl { uint32_t naces; - struct list_head ace_head; + struct nfs4_ace aces[0]; }; typedef struct { char data[NFS4_VERIFIER_SIZE]; } nfs4_verifier; diff --git a/include/linux/nfs4_acl.h b/include/linux/nfs4_acl.h index 22aff4d01f20..409b6e02f337 100644 --- a/include/linux/nfs4_acl.h +++ b/include/linux/nfs4_acl.h @@ -39,9 +39,12 @@ #include <linux/posix_acl.h> -struct nfs4_acl *nfs4_acl_new(void); -void nfs4_acl_free(struct nfs4_acl *); -int nfs4_acl_add_ace(struct nfs4_acl *, u32, u32, u32, int, uid_t); +/* Maximum ACL we'll accept from client; chosen (somewhat arbitrarily) to + * fit in a page: */ +#define NFS4_ACL_MAX 170 + +struct nfs4_acl *nfs4_acl_new(int); +void nfs4_acl_add_ace(struct nfs4_acl *, u32, u32, u32, int, uid_t); int nfs4_acl_get_whotype(char *, u32); int nfs4_acl_write_who(int who, char *p); int nfs4_acl_permission(struct nfs4_acl *acl, uid_t owner, gid_t group, diff --git a/include/linux/tick.h b/include/linux/tick.h new file mode 100644 index 000000000000..9a7252e089b9 --- /dev/null +++ b/include/linux/tick.h @@ -0,0 +1,109 @@ +/* linux/include/linux/tick.h + * + * This file contains the structure definitions for tick related functions + * + */ +#ifndef _LINUX_TICK_H +#define _LINUX_TICK_H + +#include <linux/clockchips.h> + +#ifdef CONFIG_GENERIC_CLOCKEVENTS + +enum tick_device_mode { + TICKDEV_MODE_PERIODIC, + TICKDEV_MODE_ONESHOT, +}; + +struct tick_device { + struct clock_event_device *evtdev; + enum tick_device_mode mode; +}; + +enum tick_nohz_mode { + NOHZ_MODE_INACTIVE, + NOHZ_MODE_LOWRES, + NOHZ_MODE_HIGHRES, +}; + +/** + * struct tick_sched - sched tick emulation and no idle tick control/stats + * @sched_timer: hrtimer to schedule the periodic tick in high + * resolution mode + * @idle_tick: Store the last idle tick expiry time when the tick + * timer is modified for idle sleeps. This is necessary + * to resume the tick timer operation in the timeline + * when the CPU returns from idle + * @tick_stopped: Indicator that the idle tick has been stopped + * @idle_jiffies: jiffies at the entry to idle for idle time accounting + * @idle_calls: Total number of idle calls + * @idle_sleeps: Number of idle calls, where the sched tick was stopped + * @idle_entrytime: Time when the idle call was entered + * @idle_sleeptime: Sum of the time slept in idle with sched tick stopped + */ +struct tick_sched { + struct hrtimer sched_timer; + unsigned long check_clocks; + enum tick_nohz_mode nohz_mode; + ktime_t idle_tick; + int tick_stopped; + unsigned long idle_jiffies; + unsigned long idle_calls; + unsigned long idle_sleeps; + ktime_t idle_entrytime; + ktime_t idle_sleeptime; + unsigned long last_jiffies; + unsigned long next_jiffies; + ktime_t idle_expires; +}; + +extern void __init tick_init(void); +extern int tick_is_oneshot_available(void); +extern struct tick_device *tick_get_device(int cpu); + +# ifdef CONFIG_HIGH_RES_TIMERS +extern int tick_init_highres(void); +extern int tick_program_event(ktime_t expires, int force); +extern void tick_setup_sched_timer(void); +extern void tick_cancel_sched_timer(int cpu); +# else +static inline void tick_cancel_sched_timer(int cpu) { } +# endif /* HIGHRES */ + +# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +extern struct tick_device *tick_get_broadcast_device(void); +extern cpumask_t *tick_get_broadcast_mask(void); + +# ifdef CONFIG_TICK_ONESHOT +extern cpumask_t *tick_get_broadcast_oneshot_mask(void); +# endif + +# endif /* BROADCAST */ + +# ifdef CONFIG_TICK_ONESHOT +extern void tick_clock_notify(void); +extern int tick_check_oneshot_change(int allow_nohz); +extern struct tick_sched *tick_get_tick_sched(int cpu); +# else +static inline void tick_clock_notify(void) { } +static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } +# endif + +#else /* CONFIG_GENERIC_CLOCKEVENTS */ +static inline void tick_init(void) { } +static inline void tick_cancel_sched_timer(int cpu) { } +static inline void tick_clock_notify(void) { } +static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } +#endif /* !CONFIG_GENERIC_CLOCKEVENTS */ + +# ifdef CONFIG_NO_HZ +extern void tick_nohz_stop_sched_tick(void); +extern void tick_nohz_restart_sched_tick(void); +extern void tick_nohz_update_jiffies(void); +# else +static inline void tick_nohz_stop_sched_tick(void) { } +static inline void tick_nohz_restart_sched_tick(void) { } +static inline void tick_nohz_update_jiffies(void) { } +# endif /* !NO_HZ */ + +#endif diff --git a/include/linux/time.h b/include/linux/time.h index eceb1a59b078..8ea8dea713c7 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -92,6 +92,7 @@ extern struct timespec xtime; extern struct timespec wall_to_monotonic; extern seqlock_t xtime_lock __attribute__((weak)); +extern unsigned long read_persistent_clock(void); void timekeeping_init(void); static inline unsigned long get_seconds(void) diff --git a/include/linux/timer.h b/include/linux/timer.h index fb5edaaf0ebd..719113b652dd 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -2,6 +2,7 @@ #define _LINUX_TIMER_H #include <linux/list.h> +#include <linux/ktime.h> #include <linux/spinlock.h> #include <linux/stddef.h> @@ -15,6 +16,11 @@ struct timer_list { unsigned long data; struct tvec_t_base_s *base; +#ifdef CONFIG_TIMER_STATS + void *start_site; + char start_comm[16]; + int start_pid; +#endif }; extern struct tvec_t_base_s boot_tvec_bases; @@ -61,7 +67,65 @@ extern int del_timer(struct timer_list * timer); extern int __mod_timer(struct timer_list *timer, unsigned long expires); extern int mod_timer(struct timer_list *timer, unsigned long expires); +/* + * Return when the next timer-wheel timeout occurs (in absolute jiffies), + * locks the timer base: + */ extern unsigned long next_timer_interrupt(void); +/* + * Return when the next timer-wheel timeout occurs (in absolute jiffies), + * locks the timer base and does the comparison against the given + * jiffie. + */ +extern unsigned long get_next_timer_interrupt(unsigned long now); + +/* + * Timer-statistics info: + */ +#ifdef CONFIG_TIMER_STATS + +extern void init_timer_stats(void); + +extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf, + void *timerf, char * comm); + +static inline void timer_stats_account_timer(struct timer_list *timer) +{ + timer_stats_update_stats(timer, timer->start_pid, timer->start_site, + timer->function, timer->start_comm); +} + +extern void __timer_stats_timer_set_start_info(struct timer_list *timer, + void *addr); + +static inline void timer_stats_timer_set_start_info(struct timer_list *timer) +{ + __timer_stats_timer_set_start_info(timer, __builtin_return_address(0)); +} + +static inline void timer_stats_timer_clear_start_info(struct timer_list *timer) +{ + timer->start_site = NULL; +} +#else +static inline void init_timer_stats(void) +{ +} + +static inline void timer_stats_account_timer(struct timer_list *timer) +{ +} + +static inline void timer_stats_timer_set_start_info(struct timer_list *timer) +{ +} + +static inline void timer_stats_timer_clear_start_info(struct timer_list *timer) +{ +} +#endif + +extern void delayed_work_timer_fn(unsigned long __data); /** * add_timer - start a timer @@ -96,7 +160,7 @@ static inline void add_timer(struct timer_list *timer) extern void init_timers(void); extern void run_local_timers(void); struct hrtimer; -extern int it_real_fn(struct hrtimer *); +extern enum hrtimer_restart it_real_fn(struct hrtimer *); unsigned long __round_jiffies(unsigned long j, int cpu); unsigned long __round_jiffies_relative(unsigned long j, int cpu); diff --git a/include/linux/timex.h b/include/linux/timex.h index 9a24e500c311..da929dbbea2a 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -286,6 +286,13 @@ static inline void time_interpolator_update(long delta_nsec) #define TICK_LENGTH_SHIFT 32 +#ifdef CONFIG_NO_HZ +#define NTP_INTERVAL_FREQ (2) +#else +#define NTP_INTERVAL_FREQ (HZ) +#endif +#define NTP_INTERVAL_LENGTH (NSEC_PER_SEC/NTP_INTERVAL_FREQ) + /* Returns how long ticks are at present, in ns / 2^(SHIFT_SCALE-10). */ extern u64 current_tick_length(void); |