From 1a9e4c564ab174e53ed86def922804a5ddc63e7d Mon Sep 17 00:00:00 2001 From: Nicolai Stange Date: Thu, 14 Jul 2016 17:22:54 +0200 Subject: x86/timers/apic: Fix imprecise timer interrupts by eliminating TSC clockevents frequency roundoff error I noticed the following bug/misbehavior on certain Intel systems: with a single task running on a NOHZ CPU on an Intel Haswell, I recognized that I did not only get the one expected local_timer APIC interrupt, but two per second at minimum. (!) Further tracing showed that the first one precedes the programmed deadline by up to ~50us and hence, it did nothing except for reprogramming the TSC deadline clockevent device to trigger shortly thereafter again. The reason for this is imprecise calibration, the timeout we program into the APIC results in 'too short' timer interrupts. The core (hr)timer code notices this (because it has a precise ktime source and sees the short interrupt) and fixes it up by programming an additional very short interrupt period. This is obviously suboptimal. The reason for the imprecise calibration is twofold, and this patch fixes the first reason: In setup_APIC_timer(), the registered clockevent device's frequency is calculated by first dividing tsc_khz by TSC_DIVISOR and multiplying it with 1000 afterwards: (tsc_khz / TSC_DIVISOR) * 1000 The multiplication with 1000 is done for converting from kHz to Hz and the division by TSC_DIVISOR is carried out in order to make sure that the final result fits into an u32. However, with the order given in this calculation, the roundoff error introduced by the division gets magnified by a factor of 1000 by the following multiplication. To fix it, reversing the order of the division and the multiplication a la: (tsc_khz * 1000) / TSC_DIVISOR ... reduces the roundoff error already. Furthermore, if TSC_DIVISOR divides 1000, associativity holds: (tsc_khz * 1000) / TSC_DIVISOR = tsc_khz * (1000 / TSC_DIVISOR) and thus, the roundoff error even vanishes and the whole operation can be carried out within 32 bits. The powers of two that divide 1000 are 2, 4 and 8. A value of 8 for TSC_DIVISOR still allows for TSC frequencies up to 2^32 / 10^9ns * 8 = 34.4GHz which is way larger than anything to expect in the next years. Thus we also replace the current TSC_DIVISOR value of 32 by 8. Reverse the order of the divison and the multiplication in the calculation of the registered clockevent device's frequency. Signed-off-by: Nicolai Stange Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Paolo Bonzini Acked-by: Thomas Gleixner Cc: Adrian Hunter Cc: Borislav Petkov Cc: Christopher S. Hall Cc: H. Peter Anvin Cc: Hidehiro Kawai Cc: Len Brown Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Viresh Kumar Link: http://lkml.kernel.org/r/20160714152255.18295-2-nicstange@gmail.com [ Improved changelog. ] Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/apic.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/apic/apic.c') diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index ac8d8ad8b009..a315dc404756 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -313,7 +313,7 @@ int lapic_get_maxlvt(void) /* Clock divisor */ #define APIC_DIVISOR 16 -#define TSC_DIVISOR 32 +#define TSC_DIVISOR 8 /* * This function sets up the local APIC timer, with a timeout of @@ -565,7 +565,7 @@ static void setup_APIC_timer(void) CLOCK_EVT_FEAT_DUMMY); levt->set_next_event = lapic_next_deadline; clockevents_config_and_register(levt, - (tsc_khz / TSC_DIVISOR) * 1000, + tsc_khz * (1000 / TSC_DIVISOR), 0xF, ~0UL); } else clockevents_register_device(levt); -- cgit v1.2.2 From 6731b0d611a1274f9e785fa0189ac2aeeabd0591 Mon Sep 17 00:00:00 2001 From: Nicolai Stange Date: Thu, 14 Jul 2016 17:22:55 +0200 Subject: x86/timers/apic: Inform TSC deadline clockevent device about recalibration This patch eliminates a source of imprecise APIC timer interrupts, which imprecision may result in double interrupts or even late interrupts. The TSC deadline clockevent devices' configuration and registration happens before the TSC frequency calibration is refined in tsc_refine_calibration_work(). This results in the TSC clocksource and the TSC deadline clockevent devices being configured with slightly different frequencies: the former gets the refined one and the latter are configured with the inaccurate frequency detected earlier by means of the "Fast TSC calibration using PIT". Within the APIC code, introduce the notifier function lapic_update_tsc_freq() which reconfigures all per-CPU TSC deadline clockevent devices with the current tsc_khz. Call it from the TSC code after TSC calibration refinement has happened. Signed-off-by: Nicolai Stange Signed-off-by: Peter Zijlstra (Intel) Acked-by: Thomas Gleixner Cc: Adrian Hunter Cc: Borislav Petkov Cc: Christopher S. Hall Cc: H. Peter Anvin Cc: Hidehiro Kawai Cc: Len Brown Cc: Linus Torvalds Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Viresh Kumar Link: http://lkml.kernel.org/r/20160714152255.18295-3-nicstange@gmail.com [ Pushed #ifdef CONFIG_X86_LOCAL_APIC into header, improved changelog. ] Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/apic.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'arch/x86/kernel/apic/apic.c') diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index a315dc404756..0fd3d659f13c 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -571,6 +571,30 @@ static void setup_APIC_timer(void) clockevents_register_device(levt); } +/* + * Install the updated TSC frequency from recalibration at the TSC + * deadline clockevent devices. + */ +static void __lapic_update_tsc_freq(void *info) +{ + struct clock_event_device *levt = this_cpu_ptr(&lapic_events); + + if (!this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return; + + clockevents_update_freq(levt, tsc_khz * (1000 / TSC_DIVISOR)); +} + +void lapic_update_tsc_freq(void) +{ + /* + * The clockevent device's ->mult and ->shift can both be + * changed. In order to avoid races, schedule the frequency + * update code on each CPU. + */ + on_each_cpu(__lapic_update_tsc_freq, NULL, 0); +} + /* * In this functions we calibrate APIC bus clocks to the external timer. * -- cgit v1.2.2 From 2e63ad4bd5dd583871e6602f9d398b9322d358d9 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Tue, 23 Aug 2016 20:07:19 +0800 Subject: x86/apic: Do not init irq remapping if ioapic is disabled native_smp_prepare_cpus -> default_setup_apic_routing -> enable_IR_x2apic -> irq_remapping_prepare -> intel_prepare_irq_remapping -> intel_setup_irq_remapping So IR table is setup even if "noapic" boot parameter is added. As a result we crash later when the interrupt affinity is set due to a half initialized remapping infrastructure. Prevent remap initialization when IOAPIC is disabled. Signed-off-by: Wanpeng Li Cc: Peter Zijlstra Cc: Joerg Roedel Link: http://lkml.kernel.org/r/1471954039-3942-1-git-send-email-wanpeng.li@hotmail.com Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner --- arch/x86/kernel/apic/apic.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/x86/kernel/apic/apic.c') diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index cea4fc19e844..50c95af0f017 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1623,6 +1623,9 @@ void __init enable_IR_x2apic(void) unsigned long flags; int ret, ir_stat; + if (skip_ioapic_setup) + return; + ir_stat = irq_remapping_prepare(); if (ir_stat < 0 && !x2apic_supported()) return; -- cgit v1.2.2