--- zzzz-none-000/linux-3.10.107/arch/s390/kernel/vtime.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/s390/kernel/vtime.c 2021-02-04 17:41:59.000000000 +0000 @@ -6,31 +6,30 @@ */ #include -#include -#include #include #include #include #include #include -#include -#include -#include #include #include -#include -#include "entry.h" +#include +#include +#include static void virt_timer_expire(void); -DEFINE_PER_CPU(struct s390_idle_data, s390_idle); - static LIST_HEAD(virt_timer_list); static DEFINE_SPINLOCK(virt_timer_lock); static atomic64_t virt_timer_current; static atomic64_t virt_timer_elapsed; +DEFINE_PER_CPU(u64, mt_cycles[8]); +static DEFINE_PER_CPU(u64, mt_scaling_mult) = { 1 }; +static DEFINE_PER_CPU(u64, mt_scaling_div) = { 1 }; +static DEFINE_PER_CPU(u64, mt_scaling_jiffies); + static inline u64 get_vtimer(void) { u64 timer; @@ -61,6 +60,34 @@ return elapsed >= atomic64_read(&virt_timer_current); } +static void update_mt_scaling(void) +{ + u64 cycles_new[8], *cycles_old; + u64 delta, fac, mult, div; + int i; + + stcctm5(smp_cpu_mtid + 1, cycles_new); + cycles_old = this_cpu_ptr(mt_cycles); + fac = 1; + mult = div = 0; + for (i = 0; i <= smp_cpu_mtid; i++) { + delta = cycles_new[i] - cycles_old[i]; + div += delta; + mult *= i + 1; + mult += delta * fac; + fac *= i + 1; + } + div *= fac; + if (div > 0) { + /* Update scaling factor */ + __this_cpu_write(mt_scaling_mult, mult); + __this_cpu_write(mt_scaling_div, div); + memcpy(cycles_old, cycles_new, + sizeof(u64) * (smp_cpu_mtid + 1)); + } + __this_cpu_write(mt_scaling_jiffies, jiffies_64); +} + /* * Update process times based on virtual cpu times stored by entry.S * to the lowcore fields user_timer, system_timer & steal_clock. @@ -69,26 +96,47 @@ { struct thread_info *ti = task_thread_info(tsk); u64 timer, clock, user, system, steal; + u64 user_scaled, system_scaled; timer = S390_lowcore.last_update_timer; clock = S390_lowcore.last_update_clock; asm volatile( " stpt %0\n" /* Store current cpu timer value */ +#ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES + " stckf %1" /* Store current tod clock value */ +#else " stck %1" /* Store current tod clock value */ +#endif : "=m" (S390_lowcore.last_update_timer), "=m" (S390_lowcore.last_update_clock)); S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer; S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock; + /* Update MT utilization calculation */ + if (smp_cpu_mtid && + time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies))) + update_mt_scaling(); + user = S390_lowcore.user_timer - ti->user_timer; S390_lowcore.steal_timer -= user; ti->user_timer = S390_lowcore.user_timer; - account_user_time(tsk, user, user); system = S390_lowcore.system_timer - ti->system_timer; S390_lowcore.steal_timer -= system; ti->system_timer = S390_lowcore.system_timer; - account_system_time(tsk, hardirq_offset, system, system); + + user_scaled = user; + system_scaled = system; + /* Do MT utilization scaling */ + if (smp_cpu_mtid) { + u64 mult = __this_cpu_read(mt_scaling_mult); + u64 div = __this_cpu_read(mt_scaling_div); + + user_scaled = (user_scaled * mult) / div; + system_scaled = (system_scaled * mult) / div; + } + account_user_time(tsk, user, user_scaled); + account_system_time(tsk, hardirq_offset, system, system_scaled); steal = S390_lowcore.steal_timer; if ((s64) steal > 0) { @@ -130,18 +178,29 @@ void vtime_account_irq_enter(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); - u64 timer, system; - - WARN_ON_ONCE(!irqs_disabled()); + u64 timer, system, system_scaled; timer = S390_lowcore.last_update_timer; S390_lowcore.last_update_timer = get_vtimer(); S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer; + /* Update MT utilization calculation */ + if (smp_cpu_mtid && + time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies))) + update_mt_scaling(); + system = S390_lowcore.system_timer - ti->system_timer; S390_lowcore.steal_timer -= system; ti->system_timer = S390_lowcore.system_timer; - account_system_time(tsk, 0, system, system); + system_scaled = system; + /* Do MT utilization scaling */ + if (smp_cpu_mtid) { + u64 mult = __this_cpu_read(mt_scaling_mult); + u64 div = __this_cpu_read(mt_scaling_div); + + system_scaled = (system_scaled * mult) / div; + } + account_system_time(tsk, 0, system, system_scaled); virt_timer_forward(system); } @@ -151,49 +210,6 @@ __attribute__((alias("vtime_account_irq_enter"))); EXPORT_SYMBOL_GPL(vtime_account_system); -void __kprobes vtime_stop_cpu(void) -{ - struct s390_idle_data *idle = &__get_cpu_var(s390_idle); - unsigned long long idle_time; - unsigned long psw_mask; - - trace_hardirqs_on(); - - /* Wait for external, I/O or machine check interrupt. */ - psw_mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_DAT | - PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; - idle->nohz_delay = 0; - - /* Call the assembler magic in entry.S */ - psw_idle(idle, psw_mask); - - /* Account time spent with enabled wait psw loaded as idle time. */ - idle->sequence++; - smp_wmb(); - idle_time = idle->clock_idle_exit - idle->clock_idle_enter; - idle->clock_idle_enter = idle->clock_idle_exit = 0ULL; - idle->idle_time += idle_time; - idle->idle_count++; - account_idle_time(idle_time); - smp_wmb(); - idle->sequence++; -} - -cputime64_t s390_get_idle_time(int cpu) -{ - struct s390_idle_data *idle = &per_cpu(s390_idle, cpu); - unsigned long long now, idle_enter, idle_exit; - unsigned int sequence; - - do { - now = get_tod_clock(); - sequence = ACCESS_ONCE(idle->sequence); - idle_enter = ACCESS_ONCE(idle->clock_idle_enter); - idle_exit = ACCESS_ONCE(idle->clock_idle_exit); - } while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence)); - return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0; -} - /* * Sorted add to a list. List is linear searched until first bigger * element is found. @@ -371,31 +387,15 @@ /* * Start the virtual CPU timer on the current CPU. */ -void __cpuinit init_cpu_vtimer(void) +void vtime_init(void) { /* set initial cpu timer */ set_vtimer(VTIMER_MAX_SLICE); -} - -static int __cpuinit s390_nohz_notify(struct notifier_block *self, - unsigned long action, void *hcpu) -{ - struct s390_idle_data *idle; - long cpu = (long) hcpu; - - idle = &per_cpu(s390_idle, cpu); - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_DYING: - idle->nohz_delay = 0; - default: - break; + /* Setup initial MT scaling values */ + if (smp_cpu_mtid) { + __this_cpu_write(mt_scaling_jiffies, jiffies); + __this_cpu_write(mt_scaling_mult, 1); + __this_cpu_write(mt_scaling_div, 1); + stcctm5(smp_cpu_mtid + 1, this_cpu_ptr(mt_cycles)); } - return NOTIFY_OK; -} - -void __init vtime_init(void) -{ - /* Enable cpu timer interrupts on the boot cpu. */ - init_cpu_vtimer(); - cpu_notifier(s390_nohz_notify, 0); }