[PATCH] x86_64: Allow to run main time keeping from the local APIC interrupt

Another piece from the no-idle-tick patch.

This can be enabled with the "apicmaintimer" option.

This is mainly useful when the PIT/HPET interrupt is unreliable.
Note there are some systems that are known to stop the APIC
timer in C3. For those it will never work, but this case
should be automatically detected.

It also only works with PM timer right now. When HPET is used
the way the main timer handler computes the delay doesn't work.

It should be a bit more efficient because there is one less
regular interrupt to process on the boot processor.

Requires earlier bugfix from Venkatesh
Signed-off-by: NAndi Kleen <ak@suse.de>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Documentation/x86_64/boot-options.txt

@@ -40,6 +40,13 @@ APICs
    no_timer_check Don't check the IO-APIC timer. This can work around
 		 problems with incorrect timer initialization on some boards.
 
+   apicmaintimer Run time keeping from the local APIC timer instead
+                 of using the PIT/HPET interrupt for this. This is useful
+                 when the PIT/HPET interrupts are unreliable.
+
+   noapicmaintimer  Don't do time keeping using the APIC timer.
+		 Useful when this option was auto selected, but doesn't work.
+
 Early Console
 
    syntax: earlyprintk=vga

arch/x86_64/kernel/apic.c

@@ -35,8 +35,11 @@
 #include <asm/mach_apic.h>
 #include <asm/nmi.h>
 #include <asm/idle.h>
+#include <asm/proto.h>
+#include <asm/timex.h>
 
 int apic_verbosity;
+int apic_runs_main_timer;
 
 int disable_apic_timer __initdata;
 
@@ -702,9 +705,17 @@ static void setup_APIC_timer(unsigned int clocks)
 			c2 |= inb_p(0x40) << 8;
 		} while (c2 - c1 < 300);
 	}
-
 	__setup_APIC_LVTT(clocks);
-
+	/* 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 (vxtime.mode == VXTIME_PMTMR &&
+		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);
 }
 
@@ -872,6 +883,8 @@ void smp_local_timer_interrupt(struct pt_regs *regs)
 #ifdef CONFIG_SMP
 	update_process_times(user_mode(regs));
 #endif
+	if (apic_runs_main_timer > 1 && smp_processor_id() == boot_cpu_id)
+		main_timer_handler(regs);
 	/*
 	 * We take the 'long' return path, and there every subsystem
 	 * grabs the appropriate locks (kernel lock/ irq lock).
@@ -1081,10 +1094,27 @@ static __init int setup_nolapic(char *str)
 
 static __init int setup_noapictimer(char *str) 
 { 
+	if (str[0] != ' ' && str[0] != 0)
+		return -1;
 	disable_apic_timer = 1;
 	return 0;
 } 
 
+static __init int setup_apicmaintimer(char *str)
+{
+	apic_runs_main_timer = 1;
+	nohpet = 1;
+	return 0;
+}
+__setup("apicmaintimer", setup_apicmaintimer);
+
+static __init int setup_noapicmaintimer(char *str)
+{
+	apic_runs_main_timer = -1;
+	return 0;
+}
+__setup("noapicmaintimer", setup_noapicmaintimer);
+
 /* dummy parsing: see setup.c */
 
 __setup("disableapic", setup_disableapic); 

arch/x86_64/kernel/time.c

@@ -51,7 +51,7 @@ extern int using_apic_timer;
 DEFINE_SPINLOCK(rtc_lock);
 DEFINE_SPINLOCK(i8253_lock);
 
-static int nohpet __initdata = 0;
+int nohpet __initdata = 0;
 static int notsc __initdata = 0;
 
 #undef HPET_HACK_ENABLE_DANGEROUS
@@ -345,7 +345,7 @@ static noinline void handle_lost_ticks(int lost, struct pt_regs *regs)
 #endif
 }
 
-static irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+void main_timer_handler(struct pt_regs *regs)
 {
 	static unsigned long rtc_update = 0;
 	unsigned long tsc;
@@ -458,12 +458,17 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
 	}
  
 	write_sequnlock(&xtime_lock);
+}
 
+static irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+{
+	if (apic_runs_main_timer > 1)
+		return IRQ_HANDLED;
+	main_timer_handler(regs);
 #ifdef CONFIG_X86_LOCAL_APIC
 	if (using_apic_timer)
 		smp_send_timer_broadcast_ipi();
 #endif
-
 	return IRQ_HANDLED;
 }
 
@@ -843,17 +848,43 @@ static int hpet_reenable(void)
 	return hpet_timer_stop_set_go(hpet_tick);
 }
 
-void __init pit_init(void)
+#define PIT_MODE 0x43
+#define PIT_CH0  0x40
+
+static void __init __pit_init(int val, u8 mode)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&i8253_lock, flags);
-	outb_p(0x34, 0x43);		/* binary, mode 2, LSB/MSB, ch 0 */
-	outb_p(LATCH & 0xff, 0x40);	/* LSB */
-	outb_p(LATCH >> 8, 0x40);	/* MSB */
+	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 __init pit_stop_interrupt(void)
+{
+	__pit_init(0, 0x30); /* mode 0 */
+}
+
+void __init stop_timer_interrupt(void)
+{
+	char *name;
+	if (vxtime.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);
+}
+
 int __init time_setup(char *str)
 {
 	report_lost_ticks = 1;

include/asm-x86_64/apic.h

@@ -17,6 +17,7 @@
 #define APIC_DEBUG   2
 
 extern int apic_verbosity;
+extern int apic_runs_main_timer;
 
 /*
  * Define the default level of output to be very little

include/asm-x86_64/proto.h

@@ -49,6 +49,8 @@ extern u32 pmtmr_ioport;
 #endif
 extern unsigned long long monotonic_base;
 extern int sysctl_vsyscall;
+extern int nohpet;
+extern unsigned long vxtime_hz;
 
 extern void do_softirq_thunk(void);
 
@@ -69,6 +71,9 @@ extern void free_bootmem_generic(unsigned long phys, unsigned len);
 
 extern void load_gs_index(unsigned gs);
 
+extern void stop_timer_interrupt(void);
+extern void main_timer_handler(struct pt_regs *regs);
+
 extern unsigned long end_pfn_map; 
 
 extern void show_trace(unsigned long * rsp);