Message-ID: <20071207124034.GA30052@elte.hu>
Date:	Fri, 7 Dec 2007 13:40:34 +0100
From:	Ingo Molnar <mingo@...e.hu>
To:	stefano.brivio@...imi.it
Cc:	Nick Piggin <nickpiggin@...oo.com.au>, Robert Love <rml@...h9.net>,
	linux-kernel@...r.kernel.org, Dave Jones <davej@...hat.com>,
	"Rafael J. Wysocki" <rjw@...k.pl>, Michael Buesch <mb@...sch.de>,
	Thomas Gleixner <tglx@...utronix.de>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Len Brown <lenb@...nel.org>,
	Guillaume Chazarain <guichaz@...oo.fr>
Subject: Re: [PATCH] scheduler: fix x86 regression in native_sched_clock


* Ingo Molnar <mingo@...e.hu> wrote:

> > Stefano, could you try this ontop of a recent-ish Linus tree - does 
> > this resolve all issues? (without introducing new ones ;-)
> 
> updated version attached below.

third update. the cpufreq callbacks are not quite OK yet.

	Ingo

Index: linux/arch/arm/kernel/time.c
===================================================================
--- linux.orig/arch/arm/kernel/time.c
+++ linux/arch/arm/kernel/time.c
@@ -79,17 +79,6 @@ static unsigned long dummy_gettimeoffset
 }
 #endif
 
-/*
- * An implementation of printk_clock() independent from
- * sched_clock().  This avoids non-bootable kernels when
- * printk_clock is enabled.
- */
-unsigned long long printk_clock(void)
-{
-	return (unsigned long long)(jiffies - INITIAL_JIFFIES) *
-			(1000000000 / HZ);
-}
-
 static unsigned long next_rtc_update;
 
 /*
Index: linux/arch/ia64/kernel/time.c
===================================================================
--- linux.orig/arch/ia64/kernel/time.c
+++ linux/arch/ia64/kernel/time.c
@@ -344,33 +344,6 @@ udelay (unsigned long usecs)
 }
 EXPORT_SYMBOL(udelay);
 
-static unsigned long long ia64_itc_printk_clock(void)
-{
-	if (ia64_get_kr(IA64_KR_PER_CPU_DATA))
-		return sched_clock();
-	return 0;
-}
-
-static unsigned long long ia64_default_printk_clock(void)
-{
-	return (unsigned long long)(jiffies_64 - INITIAL_JIFFIES) *
-		(1000000000/HZ);
-}
-
-unsigned long long (*ia64_printk_clock)(void) = &ia64_default_printk_clock;
-
-unsigned long long printk_clock(void)
-{
-	return ia64_printk_clock();
-}
-
-void __init
-ia64_setup_printk_clock(void)
-{
-	if (!(sal_platform_features & IA64_SAL_PLATFORM_FEATURE_ITC_DRIFT))
-		ia64_printk_clock = ia64_itc_printk_clock;
-}
-
 /* IA64 doesn't cache the timezone */
 void update_vsyscall_tz(void)
 {
Index: linux/arch/x86/kernel/process_32.c
===================================================================
--- linux.orig/arch/x86/kernel/process_32.c
+++ linux/arch/x86/kernel/process_32.c
@@ -113,10 +113,19 @@ void default_idle(void)
 		smp_mb();
 
 		local_irq_disable();
-		if (!need_resched())
+		if (!need_resched()) {
+			ktime_t t0, t1;
+			u64 t0n, t1n;
+
+			t0 = ktime_get();
+			t0n = ktime_to_ns(t0);
 			safe_halt();	/* enables interrupts racelessly */
-		else
-			local_irq_enable();
+			local_irq_disable();
+			t1 = ktime_get();
+			t1n = ktime_to_ns(t1);
+			sched_clock_idle_wakeup_event(t1n - t0n);
+		}
+		local_irq_enable();
 		current_thread_info()->status |= TS_POLLING;
 	} else {
 		/* loop is done by the caller */
Index: linux/arch/x86/lib/delay_32.c
===================================================================
--- linux.orig/arch/x86/lib/delay_32.c
+++ linux/arch/x86/lib/delay_32.c
@@ -38,17 +38,21 @@ static void delay_loop(unsigned long loo
 		:"0" (loops));
 }
 
-/* TSC based delay: */
+/* cpu_clock() [TSC] based delay: */
 static void delay_tsc(unsigned long loops)
 {
-	unsigned long bclock, now;
+	unsigned long long start, stop, now;
+	int this_cpu;
+
+	preempt_disable();
+
+	this_cpu = smp_processor_id();
+	start = now = cpu_clock(this_cpu);
+	stop = start + loops;
+
+	while ((long long)(stop - now) > 0)
+		now = cpu_clock(this_cpu);
 
-	preempt_disable();		/* TSC's are per-cpu */
-	rdtscl(bclock);
-	do {
-		rep_nop();
-		rdtscl(now);
-	} while ((now-bclock) < loops);
 	preempt_enable();
 }
 
Index: linux/arch/x86/lib/delay_64.c
===================================================================
--- linux.orig/arch/x86/lib/delay_64.c
+++ linux/arch/x86/lib/delay_64.c
@@ -26,19 +26,28 @@ int read_current_timer(unsigned long *ti
 	return 0;
 }
 
-void __delay(unsigned long loops)
+/* cpu_clock() [TSC] based delay: */
+static void delay_tsc(unsigned long loops)
 {
-	unsigned bclock, now;
+	unsigned long long start, stop, now;
+	int this_cpu;
+
+	preempt_disable();
+
+	this_cpu = smp_processor_id();
+	start = now = cpu_clock(this_cpu);
+	stop = start + loops;
+
+	while ((long long)(stop - now) > 0)
+		now = cpu_clock(this_cpu);
 
-	preempt_disable();		/* TSC's are pre-cpu */
-	rdtscl(bclock);
-	do {
-		rep_nop(); 
-		rdtscl(now);
-	}
-	while ((now-bclock) < loops);
 	preempt_enable();
 }
+
+void __delay(unsigned long loops)
+{
+	delay_tsc(loops);
+}
 EXPORT_SYMBOL(__delay);
 
 inline void __const_udelay(unsigned long xloops)
Index: linux/drivers/acpi/processor_idle.c
===================================================================
--- linux.orig/drivers/acpi/processor_idle.c
+++ linux/drivers/acpi/processor_idle.c
@@ -531,6 +531,11 @@ static void acpi_processor_idle(void)
 
 	case ACPI_STATE_C3:
 		/*
+		 * Must be done before busmaster disable as we might
+		 * need to access HPET !
+		 */
+		acpi_state_timer_broadcast(pr, cx, 1);
+		/*
 		 * disable bus master
 		 * bm_check implies we need ARB_DIS
 		 * !bm_check implies we need cache flush
@@ -557,7 +562,6 @@ static void acpi_processor_idle(void)
 		/* Get start time (ticks) */
 		t1 = inl(acpi_gbl_FADT.xpm_timer_block.address);
 		/* Invoke C3 */
-		acpi_state_timer_broadcast(pr, cx, 1);
 		/* Tell the scheduler that we are going deep-idle: */
 		sched_clock_idle_sleep_event();
 		acpi_cstate_enter(cx);
@@ -1401,9 +1405,6 @@ static int acpi_idle_enter_simple(struct
 	if (acpi_idle_suspend)
 		return(acpi_idle_enter_c1(dev, state));
 
-	if (pr->flags.bm_check)
-		acpi_idle_update_bm_rld(pr, cx);
-
 	local_irq_disable();
 	current_thread_info()->status &= ~TS_POLLING;
 	/*
@@ -1418,13 +1419,21 @@ static int acpi_idle_enter_simple(struct
 		return 0;
 	}
 
+	/*
+	 * Must be done before busmaster disable as we might need to
+	 * access HPET !
+	 */
+	acpi_state_timer_broadcast(pr, cx, 1);
+
+	if (pr->flags.bm_check)
+		acpi_idle_update_bm_rld(pr, cx);
+
 	if (cx->type == ACPI_STATE_C3)
 		ACPI_FLUSH_CPU_CACHE();
 
 	t1 = inl(acpi_gbl_FADT.xpm_timer_block.address);
 	/* Tell the scheduler that we are going deep-idle: */
 	sched_clock_idle_sleep_event();
-	acpi_state_timer_broadcast(pr, cx, 1);
 	acpi_idle_do_entry(cx);
 	t2 = inl(acpi_gbl_FADT.xpm_timer_block.address);
 
Index: linux/kernel/hrtimer.c
===================================================================
--- linux.orig/kernel/hrtimer.c
+++ linux/kernel/hrtimer.c
@@ -850,6 +850,14 @@ hrtimer_start(struct hrtimer *timer, kti
 #ifdef CONFIG_TIME_LOW_RES
 		tim = ktime_add(tim, base->resolution);
 #endif
+		/*
+		 * Careful here: User space might have asked for a
+		 * very long sleep, so the add above might result in a
+		 * negative number, which enqueues the timer in front
+		 * of the queue.
+		 */
+		if (tim.tv64 < 0)
+			tim.tv64 = KTIME_MAX;
 	}
 	timer->expires = tim;
 
Index: linux/kernel/lockdep.c
===================================================================
--- linux.orig/kernel/lockdep.c
+++ linux/kernel/lockdep.c
@@ -2654,10 +2654,15 @@ static void check_flags(unsigned long fl
 	if (!debug_locks)
 		return;
 
-	if (irqs_disabled_flags(flags))
-		DEBUG_LOCKS_WARN_ON(current->hardirqs_enabled);
-	else
-		DEBUG_LOCKS_WARN_ON(!current->hardirqs_enabled);
+	if (irqs_disabled_flags(flags)) {
+		if (DEBUG_LOCKS_WARN_ON(current->hardirqs_enabled)) {
+			printk("possible reason: unannotated irqs-off.\n");
+		}
+	} else {
+		if (DEBUG_LOCKS_WARN_ON(!current->hardirqs_enabled)) {
+			printk("possible reason: unannotated irqs-on.\n");
+		}
+	}
 
 	/*
 	 * We dont accurately track softirq state in e.g.
Index: linux/kernel/printk.c
===================================================================
--- linux.orig/kernel/printk.c
+++ linux/kernel/printk.c
@@ -573,11 +573,6 @@ static int __init printk_time_setup(char
 
 __setup("time", printk_time_setup);
 
-__attribute__((weak)) unsigned long long printk_clock(void)
-{
-	return sched_clock();
-}
-
 /* Check if we have any console registered that can be called early in boot. */
 static int have_callable_console(void)
 {
@@ -628,30 +623,57 @@ asmlinkage int printk(const char *fmt, .
 /* cpu currently holding logbuf_lock */
 static volatile unsigned int printk_cpu = UINT_MAX;
 
+const char printk_recursion_bug_msg [] =
+			KERN_CRIT "BUG: recent printk recursion!\n";
+static int printk_recursion_bug;
+
 asmlinkage int vprintk(const char *fmt, va_list args)
 {
+	static int log_level_unknown = 1;
+	static char printk_buf[1024];
+
 	unsigned long flags;
-	int printed_len;
+	int printed_len = 0;
+	int this_cpu;
 	char *p;
-	static char printk_buf[1024];
-	static int log_level_unknown = 1;
 
 	boot_delay_msec();
 
 	preempt_disable();
-	if (unlikely(oops_in_progress) && printk_cpu == smp_processor_id())
-		/* If a crash is occurring during printk() on this CPU,
-		 * make sure we can't deadlock */
-		zap_locks();
-
 	/* This stops the holder of console_sem just where we want him */
 	raw_local_irq_save(flags);
+	this_cpu = smp_processor_id();
+
+	/*
+	 * Ouch, printk recursed into itself!
+	 */
+	if (unlikely(printk_cpu == this_cpu)) {
+		/*
+		 * If a crash is occurring during printk() on this CPU,
+		 * then try to get the crash message out but make sure
+		 * we can't deadlock. Otherwise just return to avoid the
+		 * recursion and return - but flag the recursion so that
+		 * it can be printed at the next appropriate moment:
+		 */
+		if (!oops_in_progress) {
+			printk_recursion_bug = 1;
+			goto out_restore_irqs;
+		}
+		zap_locks();
+	}
+
 	lockdep_off();
 	spin_lock(&logbuf_lock);
-	printk_cpu = smp_processor_id();
+	printk_cpu = this_cpu;
 
+	if (printk_recursion_bug) {
+		printk_recursion_bug = 0;
+		strcpy(printk_buf, printk_recursion_bug_msg);
+		printed_len = sizeof(printk_recursion_bug_msg);
+	}
 	/* Emit the output into the temporary buffer */
-	printed_len = vscnprintf(printk_buf, sizeof(printk_buf), fmt, args);
+	printed_len += vscnprintf(printk_buf + printed_len,
+				  sizeof(printk_buf), fmt, args);
 
 	/*
 	 * Copy the output into log_buf.  If the caller didn't provide
@@ -680,7 +702,11 @@ asmlinkage int vprintk(const char *fmt, 
 					loglev_char = default_message_loglevel
 						+ '0';
 				}
-				t = printk_clock();
+				if (panic_timeout) {
+					panic_timeout = 0;
+					printk("recurse!\n");
+				}
+				t = cpu_clock(printk_cpu);
 				nanosec_rem = do_div(t, 1000000000);
 				tlen = sprintf(tbuf,
 						"<%c>[%5lu.%06lu] ",
@@ -744,6 +770,7 @@ asmlinkage int vprintk(const char *fmt, 
 		printk_cpu = UINT_MAX;
 		spin_unlock(&logbuf_lock);
 		lockdep_on();
+out_restore_irqs:
 		raw_local_irq_restore(flags);
 	}
 
Index: linux/kernel/sched.c
===================================================================
--- linux.orig/kernel/sched.c
+++ linux/kernel/sched.c
@@ -488,7 +488,12 @@ unsigned long long cpu_clock(int cpu)
 
 	local_irq_save(flags);
 	rq = cpu_rq(cpu);
-	update_rq_clock(rq);
+	/*
+	 * Only call sched_clock() if the scheduler has already been
+	 * initialized (some code might call cpu_clock() very early):
+	 */
+	if (rq->idle)
+		update_rq_clock(rq);
 	now = rq->clock;
 	local_irq_restore(flags);
 
Index: linux/kernel/sched_fair.c
===================================================================
--- linux.orig/kernel/sched_fair.c
+++ linux/kernel/sched_fair.c
@@ -511,8 +511,7 @@ place_entity(struct cfs_rq *cfs_rq, stru
 
 	if (!initial) {
 		/* sleeps upto a single latency don't count. */
-		if (sched_feat(NEW_FAIR_SLEEPERS) && entity_is_task(se) &&
-				task_of(se)->policy != SCHED_BATCH)
+		if (sched_feat(NEW_FAIR_SLEEPERS) && entity_is_task(se))
 			vruntime -= sysctl_sched_latency;
 
 		/* ensure we never gain time by being placed backwards. */
Index: linux/kernel/time/clockevents.c
===================================================================
--- linux.orig/kernel/time/clockevents.c
+++ linux/kernel/time/clockevents.c
@@ -78,6 +78,11 @@ int clockevents_program_event(struct clo
 	unsigned long long clc;
 	int64_t delta;
 
+	if (unlikely(expires.tv64 < 0)) {
+		WARN_ON_ONCE(1);
+		return -ETIME;
+	}
+
 	delta = ktime_to_ns(ktime_sub(expires, now));
 
 	if (delta <= 0)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists