.read = timebase_read,
};
-#define DECREMENTER_MAX 0x7fffffff
+#define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF
+u64 decrementer_max = DECREMENTER_DEFAULT_MAX;
static int decrementer_set_next_event(unsigned long evt,
struct clock_event_device *dev);
cputime_t cputime_one_jiffy;
+#ifdef CONFIG_PPC_SPLPAR
void (*dtl_consumer)(struct dtl_entry *, u64);
+#endif
+
+#ifdef CONFIG_PPC64
+#define get_accounting(tsk) (&get_paca()->accounting)
+#else
+#define get_accounting(tsk) (&task_thread_info(tsk)->accounting)
+#endif
static void calc_cputime_factors(void)
{
* Read the SPURR on systems that have it, otherwise the PURR,
* or if that doesn't exist return the timebase value passed in.
*/
-static u64 read_spurr(u64 tb)
+static unsigned long read_spurr(unsigned long tb)
{
if (cpu_has_feature(CPU_FTR_SPURR))
return mfspr(SPRN_SPURR);
void accumulate_stolen_time(void)
{
u64 sst, ust;
-
u8 save_soft_enabled = local_paca->soft_enabled;
+ struct cpu_accounting_data *acct = &local_paca->accounting;
/* We are called early in the exception entry, before
* soft/hard_enabled are sync'ed to the expected state
*/
local_paca->soft_enabled = 0;
- sst = scan_dispatch_log(local_paca->starttime_user);
- ust = scan_dispatch_log(local_paca->starttime);
- local_paca->system_time -= sst;
- local_paca->user_time -= ust;
+ sst = scan_dispatch_log(acct->starttime_user);
+ ust = scan_dispatch_log(acct->starttime);
+ acct->system_time -= sst;
+ acct->user_time -= ust;
local_paca->stolen_time += ust + sst;
local_paca->soft_enabled = save_soft_enabled;
if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) {
stolen = scan_dispatch_log(stop_tb);
- get_paca()->system_time -= stolen;
+ get_paca()->accounting.system_time -= stolen;
}
stolen += get_paca()->stolen_time;
* Account time for a transition between system, hard irq
* or soft irq state.
*/
-static u64 vtime_delta(struct task_struct *tsk,
- u64 *sys_scaled, u64 *stolen)
+static unsigned long vtime_delta(struct task_struct *tsk,
+ unsigned long *sys_scaled,
+ unsigned long *stolen)
{
- u64 now, nowscaled, deltascaled;
- u64 udelta, delta, user_scaled;
+ unsigned long now, nowscaled, deltascaled;
+ unsigned long udelta, delta, user_scaled;
+ struct cpu_accounting_data *acct = get_accounting(tsk);
WARN_ON_ONCE(!irqs_disabled());
now = mftb();
nowscaled = read_spurr(now);
- get_paca()->system_time += now - get_paca()->starttime;
- get_paca()->starttime = now;
- deltascaled = nowscaled - get_paca()->startspurr;
- get_paca()->startspurr = nowscaled;
+ acct->system_time += now - acct->starttime;
+ acct->starttime = now;
+ deltascaled = nowscaled - acct->startspurr;
+ acct->startspurr = nowscaled;
*stolen = calculate_stolen_time(now);
- delta = get_paca()->system_time;
- get_paca()->system_time = 0;
- udelta = get_paca()->user_time - get_paca()->utime_sspurr;
- get_paca()->utime_sspurr = get_paca()->user_time;
+ delta = acct->system_time;
+ acct->system_time = 0;
+ udelta = acct->user_time - acct->utime_sspurr;
+ acct->utime_sspurr = acct->user_time;
/*
* Because we don't read the SPURR on every kernel entry/exit,
*sys_scaled = deltascaled;
}
}
- get_paca()->user_time_scaled += user_scaled;
+ acct->user_time_scaled += user_scaled;
return delta;
}
void vtime_account_system(struct task_struct *tsk)
{
- u64 delta, sys_scaled, stolen;
+ unsigned long delta, sys_scaled, stolen;
delta = vtime_delta(tsk, &sys_scaled, &stolen);
account_system_time(tsk, 0, delta, sys_scaled);
void vtime_account_idle(struct task_struct *tsk)
{
- u64 delta, sys_scaled, stolen;
+ unsigned long delta, sys_scaled, stolen;
delta = vtime_delta(tsk, &sys_scaled, &stolen);
account_idle_time(delta + stolen);
void vtime_account_user(struct task_struct *tsk)
{
cputime_t utime, utimescaled;
+ struct cpu_accounting_data *acct = get_accounting(tsk);
- utime = get_paca()->user_time;
- utimescaled = get_paca()->user_time_scaled;
- get_paca()->user_time = 0;
- get_paca()->user_time_scaled = 0;
- get_paca()->utime_sspurr = 0;
+ utime = acct->user_time;
+ utimescaled = acct->user_time_scaled;
+ acct->user_time = 0;
+ acct->user_time_scaled = 0;
+ acct->utime_sspurr = 0;
account_user_time(tsk, utime, utimescaled);
}
+#ifdef CONFIG_PPC32
+/*
+ * Called from the context switch with interrupts disabled, to charge all
+ * accumulated times to the current process, and to prepare accounting on
+ * the next process.
+ */
+void arch_vtime_task_switch(struct task_struct *prev)
+{
+ struct cpu_accounting_data *acct = get_accounting(current);
+
+ acct->starttime = get_accounting(prev)->starttime;
+ acct->system_time = 0;
+ acct->user_time = 0;
+}
+#endif /* CONFIG_PPC32 */
+
#else /* ! CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
#define calc_cputime_factors()
#endif
__this_cpu_inc(irq_stat.timer_irqs_event);
} else {
now = *next_tb - now;
- if (now <= DECREMENTER_MAX)
- set_dec((int)now);
+ if (now <= decrementer_max)
+ set_dec(now);
/* We may have raced with new irq work */
if (test_irq_work_pending())
set_dec(1);
/* Ensure a positive value is written to the decrementer, or else
* some CPUs will continue to take decrementer exceptions.
*/
- set_dec(DECREMENTER_MAX);
+ set_dec(decrementer_max);
/* Some implementations of hotplug will get timer interrupts while
* offline, just ignore these and we also need to set
* with suspending.
*/
- set_dec(DECREMENTER_MAX);
+ set_dec(decrementer_max);
local_irq_disable();
- set_dec(DECREMENTER_MAX);
+ set_dec(decrementer_max);
}
static void generic_suspend_enable_irqs(void)
static int decrementer_shutdown(struct clock_event_device *dev)
{
- decrementer_set_next_event(DECREMENTER_MAX, dev);
+ decrementer_set_next_event(decrementer_max, dev);
return 0;
}
clockevents_register_device(dec);
}
+static void enable_large_decrementer(void)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ return;
+
+ if (decrementer_max <= DECREMENTER_DEFAULT_MAX)
+ return;
+
+ /*
+ * If we're running as the hypervisor we need to enable the LD manually
+ * otherwise firmware should have done it for us.
+ */
+ if (cpu_has_feature(CPU_FTR_HVMODE))
+ mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_LD);
+}
+
+static void __init set_decrementer_max(void)
+{
+ struct device_node *cpu;
+ u32 bits = 32;
+
+ /* Prior to ISAv3 the decrementer is always 32 bit */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ return;
+
+ cpu = of_find_node_by_type(NULL, "cpu");
+
+ if (of_property_read_u32(cpu, "ibm,dec-bits", &bits) == 0) {
+ if (bits > 64 || bits < 32) {
+ pr_warn("time_init: firmware supplied invalid ibm,dec-bits");
+ bits = 32;
+ }
+
+ /* calculate the signed maximum given this many bits */
+ decrementer_max = (1ul << (bits - 1)) - 1;
+ }
+
+ of_node_put(cpu);
+
+ pr_info("time_init: %u bit decrementer (max: %llx)\n",
+ bits, decrementer_max);
+}
+
static void __init init_decrementer_clockevent(void)
{
int cpu = smp_processor_id();
clockevents_calc_mult_shift(&decrementer_clockevent, ppc_tb_freq, 4);
decrementer_clockevent.max_delta_ns =
- clockevent_delta2ns(DECREMENTER_MAX, &decrementer_clockevent);
+ clockevent_delta2ns(decrementer_max, &decrementer_clockevent);
decrementer_clockevent.min_delta_ns =
clockevent_delta2ns(2, &decrementer_clockevent);
void secondary_cpu_time_init(void)
{
+ /* Enable and test the large decrementer for this cpu */
+ enable_large_decrementer();
+
/* Start the decrementer on CPUs that have manual control
* such as BookE
*/
vdso_data->tb_update_count = 0;
vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
+ /* initialise and enable the large decrementer (if we have one) */
+ set_decrementer_max();
+ enable_large_decrementer();
+
/* Start the decrementer on CPUs that have manual control
* such as BookE
*/