diff options
Diffstat (limited to 'arch/x86/kernel/tsc.c')
| -rw-r--r-- | arch/x86/kernel/tsc.c | 97 |
1 files changed, 74 insertions, 23 deletions
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 46b2f41f8b05..714dfba6a1e7 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -2,6 +2,7 @@ #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/sched/clock.h> #include <linux/init.h> #include <linux/export.h> #include <linux/timer.h> @@ -326,9 +327,16 @@ unsigned long long sched_clock(void) { return paravirt_sched_clock(); } + +bool using_native_sched_clock(void) +{ + return pv_time_ops.sched_clock == native_sched_clock; +} #else unsigned long long sched_clock(void) __attribute__((alias("native_sched_clock"))); + +bool using_native_sched_clock(void) { return true; } #endif int check_tsc_unstable(void) @@ -694,6 +702,7 @@ unsigned long native_calibrate_tsc(void) crystal_khz = 24000; /* 24.0 MHz */ break; case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_ATOM_DENVERTON: crystal_khz = 25000; /* 25.0 MHz */ break; case INTEL_FAM6_ATOM_GOLDMONT: @@ -702,6 +711,20 @@ unsigned long native_calibrate_tsc(void) } } + /* + * TSC frequency determined by CPUID is a "hardware reported" + * frequency and is the most accurate one so far we have. This + * is considered a known frequency. + */ + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); + + /* + * For Atom SoCs TSC is the only reliable clocksource. + * Mark TSC reliable so no watchdog on it. + */ + if (boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT) + setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); + return crystal_khz * ebx_numerator / eax_denominator; } @@ -1043,18 +1066,20 @@ static void detect_art(void) if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF) return; - cpuid(ART_CPUID_LEAF, &art_to_tsc_denominator, - &art_to_tsc_numerator, unused, unused+1); - - /* Don't enable ART in a VM, non-stop TSC required */ + /* Don't enable ART in a VM, non-stop TSC and TSC_ADJUST required */ if (boot_cpu_has(X86_FEATURE_HYPERVISOR) || !boot_cpu_has(X86_FEATURE_NONSTOP_TSC) || - art_to_tsc_denominator < ART_MIN_DENOMINATOR) + !boot_cpu_has(X86_FEATURE_TSC_ADJUST)) return; - if (rdmsrl_safe(MSR_IA32_TSC_ADJUST, &art_to_tsc_offset)) + cpuid(ART_CPUID_LEAF, &art_to_tsc_denominator, + &art_to_tsc_numerator, unused, unused+1); + + if (art_to_tsc_denominator < ART_MIN_DENOMINATOR) return; + rdmsrl(MSR_IA32_TSC_ADJUST, art_to_tsc_offset); + /* Make this sticky over multiple CPU init calls */ setup_force_cpu_cap(X86_FEATURE_ART); } @@ -1064,6 +1089,11 @@ static void detect_art(void) static struct clocksource clocksource_tsc; +static void tsc_resume(struct clocksource *cs) +{ + tsc_verify_tsc_adjust(true); +} + /* * We used to compare the TSC to the cycle_last value in the clocksource * structure to avoid a nasty time-warp. This can be observed in a @@ -1080,9 +1110,21 @@ static struct clocksource clocksource_tsc; * checking the result of read_tsc() - cycle_last for being negative. * That works because CLOCKSOURCE_MASK(64) does not mask out any bit. */ -static cycle_t read_tsc(struct clocksource *cs) +static u64 read_tsc(struct clocksource *cs) { - return (cycle_t)rdtsc_ordered(); + return (u64)rdtsc_ordered(); +} + +static void tsc_cs_mark_unstable(struct clocksource *cs) +{ + if (tsc_unstable) + return; + + tsc_unstable = 1; + if (using_native_sched_clock()) + clear_sched_clock_stable(); + disable_sched_clock_irqtime(); + pr_info("Marking TSC unstable due to clocksource watchdog\n"); } /* @@ -1096,22 +1138,26 @@ static struct clocksource clocksource_tsc = { .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_MUST_VERIFY, .archdata = { .vclock_mode = VCLOCK_TSC }, + .resume = tsc_resume, + .mark_unstable = tsc_cs_mark_unstable, }; void mark_tsc_unstable(char *reason) { - if (!tsc_unstable) { - tsc_unstable = 1; + if (tsc_unstable) + return; + + tsc_unstable = 1; + if (using_native_sched_clock()) clear_sched_clock_stable(); - disable_sched_clock_irqtime(); - pr_info("Marking TSC unstable due to %s\n", reason); - /* Change only the rating, when not registered */ - if (clocksource_tsc.mult) - clocksource_mark_unstable(&clocksource_tsc); - else { - clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE; - clocksource_tsc.rating = 0; - } + disable_sched_clock_irqtime(); + pr_info("Marking TSC unstable due to %s\n", reason); + /* Change only the rating, when not registered */ + if (clocksource_tsc.mult) { + clocksource_mark_unstable(&clocksource_tsc); + } else { + clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE; + clocksource_tsc.rating = 0; } } @@ -1170,7 +1216,7 @@ int unsynchronized_tsc(void) /* * Convert ART to TSC given numerator/denominator found in detect_art() */ -struct system_counterval_t convert_art_to_tsc(cycle_t art) +struct system_counterval_t convert_art_to_tsc(u64 art) { u64 tmp, res, rem; @@ -1283,10 +1329,12 @@ static int __init init_tsc_clocksource(void) clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; /* - * Trust the results of the earlier calibration on systems - * exporting a reliable TSC. + * When TSC frequency is known (retrieved via MSR or CPUID), we skip + * the refined calibration and directly register it as a clocksource. */ - if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) { + if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) { + if (boot_cpu_has(X86_FEATURE_ART)) + art_related_clocksource = &clocksource_tsc; clocksource_register_khz(&clocksource_tsc, tsc_khz); return 0; } @@ -1333,6 +1381,9 @@ void __init tsc_init(void) (unsigned long)cpu_khz / 1000, (unsigned long)cpu_khz % 1000); + /* Sanitize TSC ADJUST before cyc2ns gets initialized */ + tsc_store_and_check_tsc_adjust(true); + /* * Secondary CPUs do not run through tsc_init(), so set up * all the scale factors for all CPUs, assuming the same |