[PATCH] Simplify profile_pc on x86-64

[linux-2.6-omap-h63xx.git] / arch / x86_64 / kernel / time.c

diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index b9ff75992c16d85b8fd1c7b7a2118c7d6847087b..ea00915d393a74a337c9867556370ea7d95e08c8 100644 (file)
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -24,10 +24,13 @@
 #include <linux/device.h>
 #include <linux/sysdev.h>
 #include <linux/bcd.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
 #include <linux/kallsyms.h>
 #include <linux/acpi.h>
 #ifdef CONFIG_ACPI
 #include <acpi/achware.h>      /* for PM timer frequency */
+#include <acpi/acpi_bus.h>
 #endif
 #include <asm/8253pit.h>
 #include <asm/pgtable.h>
@@ -48,7 +51,7 @@ static void cpufreq_delayed_get(void);
 extern void i8254_timer_resume(void);
 extern int using_apic_timer;
 
-static char *time_init_gtod(void);
+static char *timename = NULL;
 
 DEFINE_SPINLOCK(rtc_lock);
 EXPORT_SYMBOL(rtc_lock);
@@ -186,20 +189,15 @@ unsigned long profile_pc(struct pt_regs *regs)
 {
        unsigned long pc = instruction_pointer(regs);
 
-       /* Assume the lock function has either no stack frame or only a single 
-          word.  This checks if the address on the stack looks like a kernel 
-          text address.
-          There is a small window for false hits, but in that case the tick
-          is just accounted to the spinlock function.
-          Better would be to write these functions in assembler again
-          and check exactly. */
-       if (in_lock_functions(pc)) {
-               char *v = *(char **)regs->rsp;
-               if ((v >= _stext && v <= _etext) ||
-                       (v >= _sinittext && v <= _einittext) ||
-                       (v >= (char *)MODULES_VADDR  && v <= (char *)MODULES_END))
-                       return (unsigned long)v;
-               return ((unsigned long *)regs->rsp)[1];
+       /* Assume the lock function has either no stack frame or a copy
+          of eflags from PUSHF
+          Eflags always has bits 22 and up cleared unlike kernel addresses. */
+       if (!user_mode(regs) && in_lock_functions(pc)) {
+               unsigned long *sp = (unsigned long *)regs->rsp;
+               if (sp[0] >> 22)
+                       return sp[0];
+               if (sp[1] >> 22)
+                       return sp[1];
        }
        return pc;
 }
@@ -892,11 +890,17 @@ static struct irqaction irq0 = {
        timer_interrupt, IRQF_DISABLED, CPU_MASK_NONE, "timer", NULL, NULL
 };
 
-void __init time_init(void)
+static int __cpuinit
+time_cpu_notifier(struct notifier_block *nb, unsigned long action, void *hcpu)
 {
-       char *timename;
-       char *gtod;
+       unsigned cpu = (unsigned long) hcpu;
+       if (action == CPU_ONLINE)
+               vsyscall_set_cpu(cpu);
+       return NOTIFY_DONE;
+}
 
+void __init time_init(void)
+{
        if (nohpet)
                vxtime.hpet_address = 0;
 
@@ -930,18 +934,19 @@ void __init time_init(void)
        }
 
        vxtime.mode = VXTIME_TSC;
-       gtod = time_init_gtod();
-
-       printk(KERN_INFO "time.c: Using %ld.%06ld MHz WALL %s GTOD %s timer.\n",
-              vxtime_hz / 1000000, vxtime_hz % 1000000, timename, gtod);
-       printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n",
-               cpu_khz / 1000, cpu_khz % 1000);
        vxtime.quot = (USEC_PER_SEC << US_SCALE) / vxtime_hz;
        vxtime.tsc_quot = (USEC_PER_MSEC << US_SCALE) / cpu_khz;
        vxtime.last_tsc = get_cycles_sync();
        setup_irq(0, &irq0);
 
        set_cyc2ns_scale(cpu_khz);
+
+       hotcpu_notifier(time_cpu_notifier, 0);
+       time_cpu_notifier(NULL, CPU_ONLINE, (void *)(long)smp_processor_id());
+
+#ifndef CONFIG_SMP
+       time_init_gtod();
+#endif
 }
 
 /*
@@ -953,11 +958,18 @@ __cpuinit int unsynchronized_tsc(void)
 #ifdef CONFIG_SMP
        if (apic_is_clustered_box())
                return 1;
-       /* Intel systems are normally all synchronized. Exceptions
-          are handled in the check above. */
-       if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
-               return 0;
 #endif
+       /* Most intel systems have synchronized TSCs except for
+          multi node systems */
+       if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
+#ifdef CONFIG_ACPI
+               /* But TSC doesn't tick in C3 so don't use it there */
+               if (acpi_fadt.length > 0 && acpi_fadt.plvl3_lat < 100)
+                       return 1;
+#endif
+               return 0;
+       }
+
        /* Assume multi socket systems are not synchronized */
        return num_present_cpus() > 1;
 }
@@ -965,12 +977,18 @@ __cpuinit int unsynchronized_tsc(void)
 /*
  * Decide what mode gettimeofday should use.
  */
-__init static char *time_init_gtod(void)
+void time_init_gtod(void)
 {
        char *timetype;
 
        if (unsynchronized_tsc())
                notsc = 1;
+
+       if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP))
+               vgetcpu_mode = VGETCPU_RDTSCP;
+       else
+               vgetcpu_mode = VGETCPU_LSL;
+
        if (vxtime.hpet_address && notsc) {
                timetype = hpet_use_timer ? "HPET" : "PIT/HPET";
                if (hpet_use_timer)
@@ -993,7 +1011,16 @@ __init static char *time_init_gtod(void)
                timetype = hpet_use_timer ? "HPET/TSC" : "PIT/TSC";
                vxtime.mode = VXTIME_TSC;
        }
-       return timetype;
+
+       printk(KERN_INFO "time.c: Using %ld.%06ld MHz WALL %s GTOD %s timer.\n",
+              vxtime_hz / 1000000, vxtime_hz % 1000000, timename, timetype);
+       printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n",
+               cpu_khz / 1000, cpu_khz % 1000);
+       vxtime.quot = (USEC_PER_SEC << US_SCALE) / vxtime_hz;
+       vxtime.tsc_quot = (USEC_PER_MSEC << US_SCALE) / cpu_khz;
+       vxtime.last_tsc = get_cycles_sync();
+
+       set_cyc2ns_scale(cpu_khz);
 }
 
 __setup("report_lost_ticks", time_setup);