From b7743970b054a08acf6445cc6d10838e60cdb639 Mon Sep 17 00:00:00 2001 From: Deepak Saxena Date: Tue, 1 Nov 2011 14:25:07 -0700 Subject: time: x86: Remove CLOCK_TICK_RATE from tsc code The tsc code uses CLOCK_TICK_RATE which on x86 is defined to just be the same as PIT_TICK_RATE. This patch updates the code use the later as we want to depecrate and remove the global CLOCK_TICK_RATE symbol. Signed-off-by: Deepak Saxena Signed-off-by: John Stultz --- arch/x86/kernel/tsc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/tsc.c') diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index db483369f10b..1e88c8ef6d6d 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -178,11 +178,11 @@ static unsigned long calc_pmtimer_ref(u64 deltatsc, u64 pm1, u64 pm2) } #define CAL_MS 10 -#define CAL_LATCH (CLOCK_TICK_RATE / (1000 / CAL_MS)) +#define CAL_LATCH (PIT_TICK_RATE / (1000 / CAL_MS)) #define CAL_PIT_LOOPS 1000 #define CAL2_MS 50 -#define CAL2_LATCH (CLOCK_TICK_RATE / (1000 / CAL2_MS)) +#define CAL2_LATCH (PIT_TICK_RATE / (1000 / CAL2_MS)) #define CAL2_PIT_LOOPS 5000 -- cgit v1.2.3 From b565201cf75210614903ef2ae5917b4379681647 Mon Sep 17 00:00:00 2001 From: Jack Steiner Date: Tue, 15 Nov 2011 15:33:56 -0800 Subject: 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 Cc: "H. Peter Anvin" Cc: John Stultz [fix CONFIG_SMP=n build] Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- arch/x86/kernel/smpboot.c | 16 +++++++++++----- arch/x86/kernel/tsc.c | 20 ++++++++++++++++++++ init/calibrate.c | 15 +++++++++++++++ 3 files changed, 46 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel/tsc.c') diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9f548cb4a958..00eef55c8327 100644 --- a/arch/x86/kernel/smpboot.c +++ b/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. diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index db483369f10b..490fb330be87 100644 --- a/arch/x86/kernel/tsc.c +++ b/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 diff --git a/init/calibrate.c b/init/calibrate.c index 24df7976816c..5f117ca9e069 100644 --- a/init/calibrate.c +++ b/init/calibrate.c @@ -246,6 +246,19 @@ recalibrate: 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 " -- cgit v1.2.3 From 28a00184be261e3dc152ba0d664a067bbe235b6a Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Fri, 4 Nov 2011 15:42:17 -0700 Subject: x86, tsc: Skip TSC synchronization checks for tsc=reliable tsc=reliable boot parameter is supposed to skip all the TSC stablility checks during boot time. On a 8-socket system where we want to run an experiment with the "tsc=reliable" boot option, TSC synchronization checks are not getting skipped and marking the TSC as not stable. Check for tsc_clocksource_reliable (which is set via tsc=reliable or for platforms supporting synthetic TSC_RELIABLE feature bit etc) and when set, skip the TSC synchronization tests during boot. Signed-off-by: Suresh Siddha Acked-by: John Stultz Tested-by: Srivatsa S. Bhat Link: http://lkml.kernel.org/r/1320446537.15071.14.camel@sbsiddha-desk.sc.intel.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/tsc.h | 2 ++ arch/x86/kernel/tsc.c | 2 +- arch/x86/kernel/tsc_sync.c | 4 ++-- 3 files changed, 5 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel/tsc.c') diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 83e2efd181e2..15d99153a96d 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -51,6 +51,8 @@ extern int unsynchronized_tsc(void); extern int check_tsc_unstable(void); extern unsigned long native_calibrate_tsc(void); +extern int tsc_clocksource_reliable; + /* * Boot-time check whether the TSCs are synchronized across * all CPUs/cores: diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index db483369f10b..eee465109e16 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -35,7 +35,7 @@ static int __read_mostly tsc_unstable; erroneous rdtsc usage on !cpu_has_tsc processors */ static int __read_mostly tsc_disabled = -1; -static int tsc_clocksource_reliable; +int tsc_clocksource_reliable; /* * Scheduler clock - returns current time in nanosec units. */ diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 0aa5fed8b9e6..9eba29b46cb7 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -113,7 +113,7 @@ void __cpuinit check_tsc_sync_source(int cpu) if (unsynchronized_tsc()) return; - if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) { + if (tsc_clocksource_reliable) { if (cpu == (nr_cpu_ids-1) || system_state != SYSTEM_BOOTING) pr_info( "Skipped synchronization checks as TSC is reliable.\n"); @@ -172,7 +172,7 @@ void __cpuinit check_tsc_sync_target(void) { int cpus = 2; - if (unsynchronized_tsc() || boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) + if (unsynchronized_tsc() || tsc_clocksource_reliable) return; /* -- cgit v1.2.3 From 68f30fbee19cc67849b9fa8e153ede70758afe81 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 17 Jan 2012 15:35:37 -0800 Subject: x86, tsc: Fix SMI induced variation in quick_pit_calibrate() pit_expect_msb() returns success wrongly in the below SMI scenario: a. pit_verify_msb() has not yet seen the MSB transition. b. we are close to the MSB transition though and got a SMI immediately after returning from pit_verify_msb() which didn't see the MSB transition. PIT MSB transition has happened somewhere during SMI execution. c. returned from SMI and we noted down the 'tsc', saw the pit MSB change now and exited the loop to calculate 'deltatsc'. Instead of noting the TSC at the MSB transition, we are way off because of the SMI. And as the SMI happened between the pit_verify_msb() and before the 'tsc' is recorded in the for loop, 'delattsc' (d1/d2 in quick_pit_calibrate()) will be small and quick_pit_calibrate() will not notice this error. Depending on whether SMI disturbance happens while computing d1 or d2, we will see the TSC calibrated value smaller or bigger than the expected value. As a result, in a cluster we were seeing a variation of approximately +/- 20MHz in the calibrated values, resulting in NTP failures. [ As far as the SMI source is concerned, this is a periodic SMI that gets disabled after ACPI is enabled by the OS. But the TSC calibration happens before the ACPI is enabled. ] To address this, change pit_expect_msb() so that - the 'tsc' is the TSC in between the two reads that read the MSB change from the PIT (same as before) - the 'delta' is the difference in TSC from *before* the MSB changed to *after* the MSB changed. Now the delta is twice as big as before (it covers four PIT accesses, roughly 4us) and quick_pit_calibrate() will loop a bit longer to get the calibrated value with in the 500ppm precision. As the delta (d1/d2) covers four PIT accesses, actual calibrated result might be closer to 250ppm precision. As the loop now takes longer to stabilize, double MAX_QUICK_PIT_MS to 50. SMI disturbance will showup as much larger delta's and the loop will take longer than usual for the result to be with in the accepted precision. Or will fallback to slow PIT calibration if it takes more than 50msec. Also while we are at this, remove the calibration correction that aims to get the result to the middle of the error bars. We really don't know which direction to correct into, so remove it. Reported-and-tested-by: Suresh Siddha Signed-off-by: Linus Torvalds Signed-off-by: Suresh Siddha Link: http://lkml.kernel.org/r/1326843337.5291.4.camel@sbsiddha-mobl2 Signed-off-by: H. Peter Anvin --- arch/x86/kernel/tsc.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'arch/x86/kernel/tsc.c') diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 2c9cf0fd78f5..f54694611172 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -290,14 +290,15 @@ static inline int pit_verify_msb(unsigned char val) static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap) { int count; - u64 tsc = 0; + u64 tsc = 0, prev_tsc = 0; for (count = 0; count < 50000; count++) { if (!pit_verify_msb(val)) break; + prev_tsc = tsc; tsc = get_cycles(); } - *deltap = get_cycles() - tsc; + *deltap = get_cycles() - prev_tsc; *tscp = tsc; /* @@ -311,9 +312,9 @@ static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *de * How many MSB values do we want to see? We aim for * a maximum error rate of 500ppm (in practice the * real error is much smaller), but refuse to spend - * more than 25ms on it. + * more than 50ms on it. */ -#define MAX_QUICK_PIT_MS 25 +#define MAX_QUICK_PIT_MS 50 #define MAX_QUICK_PIT_ITERATIONS (MAX_QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256) static unsigned long quick_pit_calibrate(void) @@ -383,15 +384,12 @@ success: * * As a result, we can depend on there not being * any odd delays anywhere, and the TSC reads are - * reliable (within the error). We also adjust the - * delta to the middle of the error bars, just - * because it looks nicer. + * reliable (within the error). * * kHz = ticks / time-in-seconds / 1000; * kHz = (t2 - t1) / (I * 256 / PIT_TICK_RATE) / 1000 * kHz = ((t2 - t1) * PIT_TICK_RATE) / (I * 256 * 1000) */ - delta += (long)(d2 - d1)/2; delta *= PIT_TICK_RATE; do_div(delta, i*256*1000); printk("Fast TSC calibration using PIT\n"); -- cgit v1.2.3