From 01573e231f18eb2d99162747186f59511f56b64d Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 08 Dec 2023 10:40:48 +0000
Subject: [PATCH] 移去rt
---
kernel/arch/powerpc/kernel/time.c | 251 ++++++++++++++++++++++++++------------------------
1 files changed, 130 insertions(+), 121 deletions(-)
diff --git a/kernel/arch/powerpc/kernel/time.c b/kernel/arch/powerpc/kernel/time.c
index f6c21f6..7e0a497 100644
--- a/kernel/arch/powerpc/kernel/time.c
+++ b/kernel/arch/powerpc/kernel/time.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Common time routines among all ppc machines.
*
@@ -24,11 +25,6 @@
*
* 1997-09-10 Updated NTP code according to technical memorandum Jan '96
* "A Kernel Model for Precision Timekeeping" by Dave Mills
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
*/
#include <linux/errno.h>
@@ -43,7 +39,6 @@
#include <linux/timex.h>
#include <linux/kernel_stat.h>
#include <linux/time.h>
-#include <linux/clockchips.h>
#include <linux/init.h>
#include <linux/profile.h>
#include <linux/cpu.h>
@@ -55,10 +50,10 @@
#include <linux/irq.h>
#include <linux/delay.h>
#include <linux/irq_work.h>
-#include <linux/clk-provider.h>
+#include <linux/of_clk.h>
#include <linux/suspend.h>
-#include <linux/rtc.h>
#include <linux/sched/cputime.h>
+#include <linux/sched/clock.h>
#include <linux/processor.h>
#include <asm/trace.h>
@@ -81,15 +76,6 @@
#include <linux/clockchips.h>
#include <linux/timekeeper_internal.h>
-static u64 rtc_read(struct clocksource *);
-static struct clocksource clocksource_rtc = {
- .name = "rtc",
- .rating = 400,
- .flags = CLOCK_SOURCE_IS_CONTINUOUS,
- .mask = CLOCKSOURCE_MASK(64),
- .read = rtc_read,
-};
-
static u64 timebase_read(struct clocksource *);
static struct clocksource clocksource_timebase = {
.name = "timebase",
@@ -111,6 +97,7 @@
.rating = 200,
.irq = 0,
.set_next_event = decrementer_set_next_event,
+ .set_state_oneshot_stopped = decrementer_shutdown,
.set_state_shutdown = decrementer_shutdown,
.tick_resume = decrementer_shutdown,
.features = CLOCK_EVT_FEAT_ONESHOT |
@@ -151,6 +138,8 @@
unsigned long ppc_tb_freq;
EXPORT_SYMBOL_GPL(ppc_tb_freq);
+bool tb_invalid;
+
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
/*
* Factor for converting from cputime_t (timebase ticks) to
@@ -175,7 +164,7 @@
* Read the SPURR on systems that have it, otherwise the PURR,
* or if that doesn't exist return the timebase value passed in.
*/
-static unsigned long read_spurr(unsigned long tb)
+static inline unsigned long read_spurr(unsigned long tb)
{
if (cpu_has_feature(CPU_FTR_SPURR))
return mfspr(SPRN_SPURR);
@@ -185,6 +174,8 @@
}
#ifdef CONFIG_PPC_SPLPAR
+
+#include <asm/dtl.h>
/*
* Scan the dispatch trace log and count up the stolen time.
@@ -281,26 +272,17 @@
* Account time for a transition between system, hard irq
* or soft irq state.
*/
-static unsigned long vtime_delta(struct task_struct *tsk,
- unsigned long *stime_scaled,
- unsigned long *steal_time)
+static unsigned long vtime_delta_scaled(struct cpu_accounting_data *acct,
+ unsigned long now, unsigned long stime)
{
- unsigned long now, nowscaled, deltascaled;
- unsigned long stime;
+ unsigned long stime_scaled = 0;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+ unsigned long nowscaled, deltascaled;
unsigned long utime, utime_scaled;
- struct cpu_accounting_data *acct = get_accounting(tsk);
- WARN_ON_ONCE(!irqs_disabled());
-
- now = mftb();
nowscaled = read_spurr(now);
- stime = now - acct->starttime;
- acct->starttime = now;
deltascaled = nowscaled - acct->startspurr;
acct->startspurr = nowscaled;
-
- *steal_time = calculate_stolen_time(now);
-
utime = acct->utime - acct->utime_sspurr;
acct->utime_sspurr = acct->utime;
@@ -314,60 +296,124 @@
* the user ticks get saved up in paca->user_time_scaled to be
* used by account_process_tick.
*/
- *stime_scaled = stime;
+ stime_scaled = stime;
utime_scaled = utime;
if (deltascaled != stime + utime) {
if (utime) {
- *stime_scaled = deltascaled * stime / (stime + utime);
- utime_scaled = deltascaled - *stime_scaled;
+ stime_scaled = deltascaled * stime / (stime + utime);
+ utime_scaled = deltascaled - stime_scaled;
} else {
- *stime_scaled = deltascaled;
+ stime_scaled = deltascaled;
}
}
acct->utime_scaled += utime_scaled;
+#endif
+
+ return stime_scaled;
+}
+
+static unsigned long vtime_delta(struct cpu_accounting_data *acct,
+ unsigned long *stime_scaled,
+ unsigned long *steal_time)
+{
+ unsigned long now, stime;
+
+ WARN_ON_ONCE(!irqs_disabled());
+
+ now = mftb();
+ stime = now - acct->starttime;
+ acct->starttime = now;
+
+ *stime_scaled = vtime_delta_scaled(acct, now, stime);
+
+ *steal_time = calculate_stolen_time(now);
return stime;
}
-void vtime_account_system(struct task_struct *tsk)
+static void vtime_delta_kernel(struct cpu_accounting_data *acct,
+ unsigned long *stime, unsigned long *stime_scaled)
{
- unsigned long stime, stime_scaled, steal_time;
- struct cpu_accounting_data *acct = get_accounting(tsk);
+ unsigned long steal_time;
- stime = vtime_delta(tsk, &stime_scaled, &steal_time);
-
- stime -= min(stime, steal_time);
+ *stime = vtime_delta(acct, stime_scaled, &steal_time);
+ *stime -= min(*stime, steal_time);
acct->steal_time += steal_time;
+}
- if ((tsk->flags & PF_VCPU) && !irq_count()) {
+void vtime_account_kernel(struct task_struct *tsk)
+{
+ struct cpu_accounting_data *acct = get_accounting(tsk);
+ unsigned long stime, stime_scaled;
+
+ vtime_delta_kernel(acct, &stime, &stime_scaled);
+
+ if (tsk->flags & PF_VCPU) {
acct->gtime += stime;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
acct->utime_scaled += stime_scaled;
+#endif
} else {
- if (hardirq_count())
- acct->hardirq_time += stime;
- else if (in_serving_softirq())
- acct->softirq_time += stime;
- else
- acct->stime += stime;
-
+ acct->stime += stime;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
acct->stime_scaled += stime_scaled;
+#endif
}
}
-EXPORT_SYMBOL_GPL(vtime_account_system);
+EXPORT_SYMBOL_GPL(vtime_account_kernel);
void vtime_account_idle(struct task_struct *tsk)
{
unsigned long stime, stime_scaled, steal_time;
struct cpu_accounting_data *acct = get_accounting(tsk);
- stime = vtime_delta(tsk, &stime_scaled, &steal_time);
+ stime = vtime_delta(acct, &stime_scaled, &steal_time);
acct->idle_time += stime + steal_time;
+}
+
+static void vtime_account_irq_field(struct cpu_accounting_data *acct,
+ unsigned long *field)
+{
+ unsigned long stime, stime_scaled;
+
+ vtime_delta_kernel(acct, &stime, &stime_scaled);
+ *field += stime;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+ acct->stime_scaled += stime_scaled;
+#endif
+}
+
+void vtime_account_softirq(struct task_struct *tsk)
+{
+ struct cpu_accounting_data *acct = get_accounting(tsk);
+ vtime_account_irq_field(acct, &acct->softirq_time);
+}
+
+void vtime_account_hardirq(struct task_struct *tsk)
+{
+ struct cpu_accounting_data *acct = get_accounting(tsk);
+ vtime_account_irq_field(acct, &acct->hardirq_time);
+}
+
+static void vtime_flush_scaled(struct task_struct *tsk,
+ struct cpu_accounting_data *acct)
+{
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+ if (acct->utime_scaled)
+ tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled);
+ if (acct->stime_scaled)
+ tsk->stimescaled += cputime_to_nsecs(acct->stime_scaled);
+
+ acct->utime_scaled = 0;
+ acct->utime_sspurr = 0;
+ acct->stime_scaled = 0;
+#endif
}
/*
* Account the whole cputime accumulated in the paca
* Must be called with interrupts disabled.
- * Assumes that vtime_account_system/idle() has been called
+ * Assumes that vtime_account_kernel/idle() has been called
* recently (i.e. since the last entry from usermode) so that
* get_paca()->user_time_scaled is up to date.
*/
@@ -378,14 +424,13 @@
if (acct->utime)
account_user_time(tsk, cputime_to_nsecs(acct->utime));
- if (acct->utime_scaled)
- tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled);
-
if (acct->gtime)
account_guest_time(tsk, cputime_to_nsecs(acct->gtime));
- if (acct->steal_time)
+ if (IS_ENABLED(CONFIG_PPC_SPLPAR) && acct->steal_time) {
account_steal_time(cputime_to_nsecs(acct->steal_time));
+ acct->steal_time = 0;
+ }
if (acct->idle_time)
account_idle_time(cputime_to_nsecs(acct->idle_time));
@@ -393,8 +438,6 @@
if (acct->stime)
account_system_index_time(tsk, cputime_to_nsecs(acct->stime),
CPUTIME_SYSTEM);
- if (acct->stime_scaled)
- tsk->stimescaled += cputime_to_nsecs(acct->stime_scaled);
if (acct->hardirq_time)
account_system_index_time(tsk, cputime_to_nsecs(acct->hardirq_time),
@@ -403,14 +446,12 @@
account_system_index_time(tsk, cputime_to_nsecs(acct->softirq_time),
CPUTIME_SOFTIRQ);
+ vtime_flush_scaled(tsk, acct);
+
acct->utime = 0;
- acct->utime_scaled = 0;
- acct->utime_sspurr = 0;
acct->gtime = 0;
- acct->steal_time = 0;
acct->idle_time = 0;
acct->stime = 0;
- acct->stime_scaled = 0;
acct->hardirq_time = 0;
acct->softirq_time = 0;
}
@@ -422,21 +463,18 @@
void __delay(unsigned long loops)
{
unsigned long start;
- int diff;
spin_begin();
- if (__USE_RTC()) {
- start = get_rtcl();
- do {
- /* the RTCL register wraps at 1000000000 */
- diff = get_rtcl() - start;
- if (diff < 0)
- diff += 1000000000;
- spin_cpu_relax();
- } while (diff < loops);
+ if (tb_invalid) {
+ /*
+ * TB is in error state and isn't ticking anymore.
+ * HMI handler was unable to recover from TB error.
+ * Return immediately, so that kernel won't get stuck here.
+ */
+ spin_cpu_relax();
} else {
- start = get_tbl();
- while (get_tbl() - start < loops)
+ start = mftb();
+ while (mftb() - start < loops)
spin_cpu_relax();
}
spin_end();
@@ -539,14 +577,11 @@
struct pt_regs *old_regs;
u64 now;
- /* Some implementations of hotplug will get timer interrupts while
- * offline, just ignore these and we also need to set
- * decrementers_next_tb as MAX to make sure __check_irq_replay
- * don't replay timer interrupt when return, otherwise we'll trap
- * here infinitely :(
+ /*
+ * Some implementations of hotplug will get timer interrupts while
+ * offline, just ignore these.
*/
if (unlikely(!cpu_online(smp_processor_id()))) {
- *next_tb = ~(u64)0;
set_dec(decrementer_max);
return;
}
@@ -582,7 +617,7 @@
irq_work_run();
}
- now = get_tb_or_rtc();
+ now = get_tb();
if (now >= *next_tb) {
*next_tb = ~(u64)0;
if (evt->event_handler)
@@ -614,15 +649,6 @@
__this_cpu_inc(irq_stat.broadcast_irqs_event);
}
#endif
-
-/*
- * Hypervisor decrementer interrupts shouldn't occur but are sometimes
- * left pending on exit from a KVM guest. We don't need to do anything
- * to clear them, as they are edge-triggered.
- */
-void hdec_interrupt(struct pt_regs *regs)
-{
-}
#ifdef CONFIG_SUSPEND
static void generic_suspend_disable_irqs(void)
@@ -673,8 +699,6 @@
*/
notrace unsigned long long sched_clock(void)
{
- if (__USE_RTC())
- return get_rtc();
return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift;
}
@@ -824,11 +848,6 @@
}
/* clocksource code */
-static notrace u64 rtc_read(struct clocksource *cs)
-{
- return (u64)get_rtc();
-}
-
static notrace u64 timebase_read(struct clocksource *cs)
{
return (u64)get_tb();
@@ -837,7 +856,7 @@
void update_vsyscall(struct timekeeper *tk)
{
- struct timespec xt;
+ struct timespec64 xt;
struct clocksource *clock = tk->tkr_mono.clock;
u32 mult = tk->tkr_mono.mult;
u32 shift = tk->tkr_mono.shift;
@@ -909,7 +928,8 @@
vdso_data->tb_to_xs = new_tb_to_xs;
vdso_data->wtom_clock_sec = tk->wall_to_monotonic.tv_sec;
vdso_data->wtom_clock_nsec = tk->wall_to_monotonic.tv_nsec;
- vdso_data->stamp_xtime = xt;
+ vdso_data->stamp_xtime_sec = xt.tv_sec;
+ vdso_data->stamp_xtime_nsec = xt.tv_nsec;
vdso_data->stamp_sec_fraction = frac_sec;
vdso_data->hrtimer_res = hrtimer_resolution;
smp_wmb();
@@ -924,12 +944,7 @@
static void __init clocksource_init(void)
{
- struct clocksource *clock;
-
- if (__USE_RTC())
- clock = &clocksource_rtc;
- else
- clock = &clocksource_timebase;
+ struct clocksource *clock = &clocksource_timebase;
if (clocksource_register_hz(clock, tb_ticks_per_sec)) {
printk(KERN_ERR "clocksource: %s is already registered\n",
@@ -944,7 +959,7 @@
static int decrementer_set_next_event(unsigned long evt,
struct clock_event_device *dev)
{
- __this_cpu_write(decrementers_next_tb, get_tb_or_rtc() + evt);
+ __this_cpu_write(decrementers_next_tb, get_tb() + evt);
set_dec(evt);
/* We may have raced with new irq work */
@@ -1047,17 +1062,12 @@
u64 scale;
unsigned shift;
- if (__USE_RTC()) {
- /* 601 processor: dec counts down by 128 every 128ns */
- ppc_tb_freq = 1000000000;
- } else {
- /* Normal PowerPC with timebase register */
- ppc_md.calibrate_decr();
- printk(KERN_DEBUG "time_init: decrementer frequency = %lu.%.6lu MHz\n",
- ppc_tb_freq / 1000000, ppc_tb_freq % 1000000);
- printk(KERN_DEBUG "time_init: processor frequency = %lu.%.6lu MHz\n",
- ppc_proc_freq / 1000000, ppc_proc_freq % 1000000);
- }
+ /* Normal PowerPC with timebase register */
+ ppc_md.calibrate_decr();
+ printk(KERN_DEBUG "time_init: decrementer frequency = %lu.%.6lu MHz\n",
+ ppc_tb_freq / 1000000, ppc_tb_freq % 1000000);
+ printk(KERN_DEBUG "time_init: processor frequency = %lu.%.6lu MHz\n",
+ ppc_proc_freq / 1000000, ppc_proc_freq % 1000000);
tb_ticks_per_jiffy = ppc_tb_freq / HZ;
tb_ticks_per_sec = ppc_tb_freq;
@@ -1083,7 +1093,7 @@
tb_to_ns_scale = scale;
tb_to_ns_shift = shift;
/* Save the current timebase to pretty up CONFIG_PRINTK_TIME */
- boot_tb = get_tb_or_rtc();
+ boot_tb = get_tb();
/* If platform provided a timezone (pmac), we correct the time */
if (timezone_offset) {
@@ -1109,9 +1119,8 @@
init_decrementer_clockevent();
tick_setup_hrtimer_broadcast();
-#ifdef CONFIG_COMMON_CLK
of_clk_init(NULL);
-#endif
+ enable_sched_clock_irqtime();
}
/*
--
Gitblit v1.6.2