x86_64: convert to clock events

Finally switch to the clockevents code. Share code with i386 for
hpet and PIT.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>

5 files changed, 65 insertions, 186 deletions

diff --git a/arch/x86/kernel/Makefile_64 b/arch/x86/kernel/Makefile_64
index 3ab017a0a3b9..080154e31502 100644
--- a/arch/x86/kernel/Makefile_64
+++ b/arch/x86/kernel/Makefile_64
@@ -8,8 +8,8 @@ obj-y	:= process_64.o signal_64.o entry_64.o traps_64.o irq_64.o \
                 ptrace_64.o time_64.o ioport_64.o ldt_64.o setup_64.o i8259_64.o sys_x86_64.o \
                 x8664_ksyms_64.o i387_64.o syscall_64.o vsyscall_64.o \
                 setup64.o bootflag.o e820_64.o reboot_64.o quirks.o i8237.o \
-                pci-dma_64.o pci-nommu_64.o alternative.o hpet_64.o tsc_64.o bugs_64.o \
-                perfctr-watchdog.o
+                pci-dma_64.o pci-nommu_64.o alternative.o hpet_32.o tsc_64.o bugs_64.o \
+                perfctr-watchdog.o i8253_32.o
 
 obj-$(CONFIG_STACKTRACE)        += stacktrace.o
 obj-$(CONFIG_X86_MCE)           += mce_64.o therm_throt.o
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 2c2807abe1d4..b0237caff712 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -857,25 +857,12 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 
 static void setup_APIC_timer(void)
 {
-        unsigned long flags;
-        int irqen;
+        struct clock_event_device *levt = &__get_cpu_var(lapic_events);
 
-        local_irq_save(flags);
+        memcpy(levt, &lapic_clockevent, sizeof(*levt));
+        levt->cpumask = cpumask_of_cpu(smp_processor_id());
 
-        irqen = ! cpu_isset(smp_processor_id(),
-                            timer_interrupt_broadcast_ipi_mask);
-        __setup_APIC_LVTT(calibration_result, 0, irqen);
-        /* Turn off PIT interrupt if we use APIC timer as main timer.
-           Only works with the PM timer right now
-           TBD fix it for HPET too. */
-        if ((pmtmr_ioport != 0) &&
-                smp_processor_id() == boot_cpu_id &&
-                apic_runs_main_timer == 1 &&
-                !cpu_isset(boot_cpu_id, timer_interrupt_broadcast_ipi_mask)) {
-                stop_timer_interrupt();
-                apic_runs_main_timer++;
-        }
-        local_irq_restore(flags);
+        clockevents_register_device(levt);
 }
 
 /*
@@ -950,18 +937,34 @@ static void __init calibrate_APIC_clock(void)
 
 void __init setup_boot_APIC_clock (void)
 {
+        /*
+         * The local apic timer can be disabled via the kernel commandline.
+         * Register the lapic timer as a dummy clock event source on SMP
+         * systems, so the broadcast mechanism is used. On UP systems simply
+         * ignore it.
+         */
         if (disable_apic_timer) {
                 printk(KERN_INFO "Disabling APIC timer\n");
+                /* No broadcast on UP ! */
+                if (num_possible_cpus() > 1)
+                        setup_APIC_timer();
                 return;
         }
 
         printk(KERN_INFO "Using local APIC timer interrupts.\n");
-        using_apic_timer = 1;
-
         calibrate_APIC_clock();
+
         /*
-         * Now set up the timer for real.
+         * If nmi_watchdog is set to IO_APIC, we need the
+         * PIT/HPET going.  Otherwise register lapic as a dummy
+         * device.
          */
+        if (nmi_watchdog != NMI_IO_APIC)
+                lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
+        else
+                printk(KERN_WARNING "APIC timer registered as dummy,"
+                       " due to nmi_watchdog=1!\n");
+
         setup_APIC_timer();
 }
 
@@ -1073,22 +1076,34 @@ void setup_APIC_extended_lvt(unsigned char lvt_off, unsigned char vector,
 
 void smp_local_timer_interrupt(void)
 {
-        profile_tick(CPU_PROFILING);
-#ifdef CONFIG_SMP
-        update_process_times(user_mode(get_irq_regs()));
-#endif
-        if (apic_runs_main_timer > 1 && smp_processor_id() == boot_cpu_id)
-                main_timer_handler();
+        int cpu = smp_processor_id();
+        struct clock_event_device *evt = &per_cpu(lapic_events, cpu);
+
         /*
-         * We take the 'long' return path, and there every subsystem
-         * grabs the appropriate locks (kernel lock/ irq lock).
-         *
-         * We might want to decouple profiling from the 'long path',
-         * and do the profiling totally in assembly.
+         * Normally we should not be here till LAPIC has been initialized but
+         * in some cases like kdump, its possible that there is a pending LAPIC
+         * timer interrupt from previous kernel's context and is delivered in
+         * new kernel the moment interrupts are enabled.
          *
-         * Currently this isn't too much of an issue (performance wise),
-         * we can take more than 100K local irqs per second on a 100 MHz P5.
+         * Interrupts are enabled early and LAPIC is setup much later, hence
+         * its possible that when we get here evt->event_handler is NULL.
+         * Check for event_handler being NULL and discard the interrupt as
+         * spurious.
          */
+        if (!evt->event_handler) {
+                printk(KERN_WARNING
+                       "Spurious LAPIC timer interrupt on cpu %d\n", cpu);
+                /* Switch it off */
+                lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt);
+                return;
+        }
+
+        /*
+         * the NMI deadlock-detector uses this.
+         */
+        add_pda(apic_timer_irqs, 1);
+
+        evt->event_handler(evt);
 }
 
 /*
@@ -1104,11 +1119,6 @@ void smp_apic_timer_interrupt(struct pt_regs *regs)
         struct pt_regs *old_regs = set_irq_regs(regs);
 
         /*
-         * the NMI deadlock-detector uses this.
-         */
-        add_pda(apic_timer_irqs, 1);
-
-        /*
          * NOTE! We'd better ACK the irq immediately,
          * because timer handling can be slow.
          */
@@ -1291,7 +1301,7 @@ static __init int setup_noapictimer(char *str)
 static __init int setup_apicmaintimer(char *str)
 {
         apic_runs_main_timer = 1;
-        nohpet = 1;
+
         return 1;
 }
 __setup("apicmaintimer", setup_apicmaintimer);
@@ -1307,7 +1317,7 @@ static __init int setup_apicpmtimer(char *s)
 {
         apic_calibrate_pmtmr = 1;
         notsc_setup(NULL);
-        return setup_apicmaintimer(NULL);
+        return 0;
 }
 __setup("apicpmtimer", setup_apicpmtimer);
 
diff --git a/arch/x86/kernel/i8259_64.c b/arch/x86/kernel/i8259_64.c
index 948cae646099..eb72976cc13c 100644
--- a/arch/x86/kernel/i8259_64.c
+++ b/arch/x86/kernel/i8259_64.c
@@ -444,46 +444,6 @@ void __init init_ISA_irqs (void)
         }
 }
 
-static void setup_timer_hardware(void)
-{
-        outb_p(0x34,0x43);              /* binary, mode 2, LSB/MSB, ch 0 */
-        udelay(10);
-        outb_p(LATCH & 0xff , 0x40);    /* LSB */
-        udelay(10);
-        outb(LATCH >> 8 , 0x40);        /* MSB */
-}
-
-static int timer_resume(struct sys_device *dev)
-{
-        setup_timer_hardware();
-        return 0;
-}
-
-void i8254_timer_resume(void)
-{
-        setup_timer_hardware();
-}
-
-static struct sysdev_class timer_sysclass = {
-        set_kset_name("timer_pit"),
-        .resume         = timer_resume,
-};
-
-static struct sys_device device_timer = {
-        .id             = 0,
-        .cls            = &timer_sysclass,
-};
-
-static int __init init_timer_sysfs(void)
-{
-        int error = sysdev_class_register(&timer_sysclass);
-        if (!error)
-                error = sysdev_register(&device_timer);
-        return error;
-}
-
-device_initcall(init_timer_sysfs);
-
 void __init init_IRQ(void)
 {
         int i;
@@ -533,12 +493,6 @@ void __init init_IRQ(void)
         set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
         set_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
 
-        /*
-         * Set the clock to HZ Hz, we already have a valid
-         * vector now:
-         */
-        setup_timer_hardware();
-
         if (!acpi_ioapic)
                 setup_irq(2, &irq2);
 }
diff --git a/arch/x86/kernel/smpboot_64.c b/arch/x86/kernel/smpboot_64.c
index 32f50783edc8..57ccf7cb6b91 100644
--- a/arch/x86/kernel/smpboot_64.c
+++ b/arch/x86/kernel/smpboot_64.c
@@ -223,8 +223,6 @@ void __cpuinit smp_callin(void)
         local_irq_disable();
         Dprintk("Stack at about %p\n",&cpuid);
 
-        disable_APIC_timer();
-
         /*
          * Save our processor parameters
          */
@@ -348,8 +346,6 @@ void __cpuinit start_secondary(void)
                 enable_8259A_irq(0);
         }
 
-        enable_APIC_timer();
-
         /*
          * The sibling maps must be set before turing the online map on for
          * this cpu
diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c
index d899216e01ca..7781df1d50e3 100644
--- a/arch/x86/kernel/time_64.c
+++ b/arch/x86/kernel/time_64.c
@@ -28,6 +28,8 @@
 #include <linux/cpu.h>
 #include <linux/kallsyms.h>
 #include <linux/acpi.h>
+#include <linux/clockchips.h>
+
 #ifdef CONFIG_ACPI
 #include <acpi/achware.h>       /* for PM timer frequency */
 #include <acpi/acpi_bus.h>
@@ -46,12 +48,8 @@
 #include <asm/nmi.h>
 #include <asm/vgtod.h>
 
-static char *timename = NULL;
-
 DEFINE_SPINLOCK(rtc_lock);
 EXPORT_SYMBOL(rtc_lock);
-DEFINE_SPINLOCK(i8253_lock);
-EXPORT_SYMBOL(i8253_lock);
 
 volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
 
@@ -194,6 +192,13 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
         return IRQ_HANDLED;
 }
 
+static irqreturn_t timer_event_interrupt(int irq, void *dev_id)
+{
+        global_clock_event->event_handler(global_clock_event);
+
+        return IRQ_HANDLED;
+}
+
 unsigned long read_persistent_clock(void)
 {
         unsigned int year, mon, day, hour, min, sec;
@@ -291,42 +296,8 @@ static unsigned int __init tsc_calibrate_cpu_khz(void)
         return pmc_now * tsc_khz / (tsc_now - tsc_start);
 }
 
-static void __pit_init(int val, u8 mode)
-{
-        unsigned long flags;
-
-        spin_lock_irqsave(&i8253_lock, flags);
-        outb_p(mode, PIT_MODE);
-        outb_p(val & 0xff, PIT_CH0);    /* LSB */
-        outb_p(val >> 8, PIT_CH0);      /* MSB */
-        spin_unlock_irqrestore(&i8253_lock, flags);
-}
-
-void __init pit_init(void)
-{
-        __pit_init(LATCH, 0x34); /* binary, mode 2, LSB/MSB, ch 0 */
-}
-
-void pit_stop_interrupt(void)
-{
-        __pit_init(0, 0x30); /* mode 0 */
-}
-
-void stop_timer_interrupt(void)
-{
-        char *name;
-        if (hpet_address) {
-                name = "HPET";
-                hpet_timer_stop_set_go(0);
-        } else {
-                name = "PIT";
-                pit_stop_interrupt();
-        }
-        printk(KERN_INFO "timer: %s interrupt stopped.\n", name);
-}
-
 static struct irqaction irq0 = {
-        .handler        = timer_interrupt,
+        .handler        = timer_event_interrupt,
         .flags          = IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING,
         .mask           = CPU_MASK_NONE,
         .name           = "timer"
@@ -334,20 +305,10 @@ static struct irqaction irq0 = {
 
 void __init time_init(void)
 {
-        if (nohpet)
-                hpet_address = 0;
-
-        if (hpet_arch_init())
-                hpet_address = 0;
+        if (!hpet_enable())
+                setup_pit_timer();
 
-        if (hpet_use_timer) {
-                /* set tick_nsec to use the proper rate for HPET */
-                tick_nsec = TICK_NSEC_HPET;
-                timename = "HPET";
-        } else {
-                pit_init();
-                timename = "PIT";
-        }
+        setup_irq(0, &irq0);
 
         tsc_calibrate();
 
@@ -369,46 +330,4 @@ void __init time_init(void)
         printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n",
                 cpu_khz / 1000, cpu_khz % 1000);
         init_tsc_clocksource();
-
-        setup_irq(0, &irq0);
-}
-
-/*
- * sysfs support for the timer.
- */
-
-static int timer_suspend(struct sys_device *dev, pm_message_t state)
-{
-        return 0;
 }
-
-static int timer_resume(struct sys_device *dev)
-{
-        if (hpet_address)
-                hpet_reenable();
-        else
-                i8254_timer_resume();
-        return 0;
-}
-
-static struct sysdev_class timer_sysclass = {
-        .resume = timer_resume,
-        .suspend = timer_suspend,
-        set_kset_name("timer"),
-};
-
-/* XXX this sysfs stuff should probably go elsewhere later -john */
-static struct sys_device device_timer = {
-        .id     = 0,
-        .cls    = &timer_sysclass,
-};
-
-static int time_init_device(void)
-{
-        int error = sysdev_class_register(&timer_sysclass);
-        if (!error)
-                error = sysdev_register(&device_timer);
-        return error;
-}
-
-device_initcall(time_init_device);