x86: Reduce clock calibration time during slave cpu startup

Reduce the startup time for slave cpus.

Adds hooks for an arch-specific function for clock calibration.
These hooks are used on x86.  If a newly started cpu has the
same phys_proc_id as a core already active, uses the TSC for the
delay loop and has a CONSTANT_TSC, use the already-calculated
value of loops_per_jiffy.

This patch reduces the time required to start slave cpus on a
4096 cpu system from: 465 sec OLD 62 sec NEW

This reduces boot time on a 4096p system by almost 7 minutes.
Nice...

Signed-off-by: Jack Steiner <steiner@sgi.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: John Stultz <john.stultz@linaro.org>
[fix CONFIG_SMP=n build]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/kernel/smpboot.c

@@ -207,22 +207,28 @@ static void __cpuinit smp_callin(void)
 	 * Need to setup vector mappings before we enable interrupts.
 	 */
 	setup_vector_irq(smp_processor_id());
+
+	/*
+	 * Save our processor parameters. Note: this information
+	 * is needed for clock calibration.
+	 */
+	smp_store_cpu_info(cpuid);
+
 	/*
 	 * Get our bogomips.
+	 * Update loops_per_jiffy in cpu_data. Previous call to
+	 * smp_store_cpu_info() stored a value that is close but not as
+	 * accurate as the value just calculated.
 	 *
 	 * Need to enable IRQs because it can take longer and then
 	 * the NMI watchdog might kill us.
 	 */
 	local_irq_enable();
 	calibrate_delay();
+	cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy;
 	local_irq_disable();
 	pr_debug("Stack at about %p\n", &cpuid);
 
-	/*
-	 * Save our processor parameters
-	 */
-	smp_store_cpu_info(cpuid);
-
 	/*
 	 * This must be done before setting cpu_online_mask
 	 * or calling notify_cpu_starting.

arch/x86/kernel/tsc.c

@@ -995,3 +995,23 @@ void __init tsc_init(void)
 	check_system_tsc_reliable();
 }
 
+#ifdef CONFIG_SMP
+/*
+ * If we have a constant TSC and are using the TSC for the delay loop,
+ * we can skip clock calibration if another cpu in the same socket has already
+ * been calibrated. This assumes that CONSTANT_TSC applies to all
+ * cpus in the socket - this should be a safe assumption.
+ */
+unsigned long __cpuinit calibrate_delay_is_known(void)
+{
+	int i, cpu = smp_processor_id();
+
+	if (!tsc_disabled && !cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC))
+		return 0;
+
+	for_each_online_cpu(i)
+		if (cpu_data(i).phys_proc_id == cpu_data(cpu).phys_proc_id)
+			return cpu_data(i).loops_per_jiffy;
+	return 0;
+}
+#endif

init/calibrate.c

@@ -246,6 +246,19 @@ static unsigned long __cpuinit calibrate_delay_converge(void)
 
 static DEFINE_PER_CPU(unsigned long, cpu_loops_per_jiffy) = { 0 };
 
+/*
+ * Check if cpu calibration delay is already known. For example,
+ * some processors with multi-core sockets may have all cores
+ * with the same calibration delay.
+ *
+ * Architectures should override this function if a faster calibration
+ * method is available.
+ */
+unsigned long __attribute__((weak)) __cpuinit calibrate_delay_is_known(void)
+{
+	return 0;
+}
+
 void __cpuinit calibrate_delay(void)
 {
 	unsigned long lpj;
@@ -265,6 +278,8 @@ void __cpuinit calibrate_delay(void)
 		lpj = lpj_fine;
 		pr_info("Calibrating delay loop (skipped), "
 			"value calculated using timer frequency.. ");
+	} else if ((lpj = calibrate_delay_is_known())) {
+		;
 	} else if ((lpj = calibrate_delay_direct()) != 0) {
 		if (!printed)
 			pr_info("Calibrating delay using timer "