In-Reply-To: <200705172142.26739.sshtylyov@ru.mvista.com>
References: <200705172142.26739.sshtylyov@ru.mvista.com>
Mime-Version: 1.0 (Apple Message framework v752.2)
Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed
Message-Id: <8E44DB06-767D-4864-8D2C-6132E4D4370B@kernel.crashing.org>
Cc: tglx@linutronix.de, mingo@elte.hu, linuxppc-dev@ozlabs.org,
       linux-kernel@vger.kernel.org
Content-Transfer-Encoding: 7bit
From: Kumar Gala <galak@kernel.crashing.org>
Subject: Re: [PATCH 2.6.21-rt2] PowerPC: decrementer clockevent driver
Date: Thu, 17 May 2007 12:47:42 -0500
To: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 8640
Lines: 281


On May 17, 2007, at 12:42 PM, Sergei Shtylyov wrote:

> Add PowerPC decrementer clock event driver.
>
> Every effort has been made to support the different implementations  
> of the
> decrementer: the classic one (with 970 series variation), 40x and  
> Book E
> specific ones.
>
> I had to make CONFIG_GENERIC_CLOCKEVENTS option selectable for the
> compatibility reasons -- this option is not compatible with the PPC64
> deterministic time accounting.
>
> Thanks to Daniel Walker and Thomas Gleixner for the suggestions  
> they made...
>
> Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
>
> ---
> This patch has been reworked against the 2.6.21 clockevents framework.
> It has only been tested on the Book E 32-bit CPU this time, so re- 
> testing on
> "classic" PowerPC CPUs is needed (used to work as of 2.6.18-rt7)...
>
> CONFIG_PPC_MULTIPLATFORM was the best option I was able to come up  
> with
> to cover machines built on 970 series CPUs...
>
>  arch/powerpc/Kconfig       |   12 +++-
>  arch/powerpc/kernel/time.c |  124 +++++++++++++++++++++++++++++++++ 
> +++++++++++-
>  2 files changed, 134 insertions(+), 2 deletions(-)
>
> Index: linux-2.6/arch/powerpc/Kconfig
> ===================================================================
> --- linux-2.6.orig/arch/powerpc/Kconfig
> +++ linux-2.6/arch/powerpc/Kconfig
> @@ -317,7 +317,7 @@ config PPC_STD_MMU_32
>
>  config VIRT_CPU_ACCOUNTING
>  	bool "Deterministic task and CPU time accounting"
> -	depends on PPC64
> +	depends on PPC64 && !GENERIC_CLOCKEVENTS
>  	default y
>  	help
>  	  Select this option to enable more accurate task and CPU time
> @@ -760,6 +760,16 @@ config HIGHMEM
>  	depends on PPC32
>
>  source kernel/Kconfig.hz
> +
> +config GENERIC_CLOCKEVENTS
> +	bool "Clock event devices support"
> +	default n
> +	help
> +	  Enable support for the clock event devices necessary for the
> +	  high-resolution timers and the tickless system support.
> +	  NOTE: This is not compatible with the deterministic time  
> accounting
> +	  option on PPC64.
> +
>  source kernel/Kconfig.preempt
>
>  config RWSEM_GENERIC_SPINLOCK
> Index: linux-2.6/arch/powerpc/kernel/time.c
> ===================================================================
> --- linux-2.6.orig/arch/powerpc/kernel/time.c
> +++ linux-2.6/arch/powerpc/kernel/time.c
> @@ -52,6 +52,7 @@
>  #include <linux/jiffies.h>
>  #include <linux/posix-timers.h>
>  #include <linux/irq.h>
> +#include <linux/clockchips.h>
>
>  #include <asm/io.h>
>  #include <asm/processor.h>
> @@ -128,6 +129,83 @@ unsigned long ppc_tb_freq;
>  static u64 tb_last_jiffy __cacheline_aligned_in_smp;
>  static DEFINE_PER_CPU(u64, last_jiffy);
>
> +#ifdef CONFIG_GENERIC_CLOCKEVENTS
> +
> +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
> +#define DECREMENTER_MAX 0xffffffff
> +#else
> +#define DECREMENTER_MAX 0x7fffffff /* setting MSB triggers an  
> interrupt */
> +#endif
> +
> +static int decrementer_set_next_event(unsigned long evt,
> +				      struct clock_event_device *dev)
> +{
> +#if defined(CONFIG_40x)
> +	mtspr(SPRN_PIT, evt);	/* 40x has a hidden PIT auto-reload  
> register */
> +#elif defined(CONFIG_BOOKE)
> +	mtspr(SPRN_DECAR, evt); /* Book E has  separate auto-reload  
> register */
> +	set_dec(evt);

what's the point of setting decar if you're just going to set_dec as  
well?

> +#else
> +	set_dec(evt - 1);	/* Classic decrementer interrupts at -1 */
> +#endif
> +	return 0;
> +}
> +
> +static void decrementer_set_mode(enum	clock_event_mode   mode,
> +				 struct clock_event_device *dev)
> +{
> +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
> +	u32 tcr = mfspr(SPRN_TCR);
> +
> +	tcr |= TCR_DIE;
> +	switch (mode) {
> +	case CLOCK_EVT_MODE_PERIODIC:
> +		tcr |=  TCR_ARE;
> +		break;
> +	case CLOCK_EVT_MODE_ONESHOT:
> +		tcr &= ~TCR_ARE;
> +		break;
> +	case CLOCK_EVT_MODE_UNUSED:
> +	case CLOCK_EVT_MODE_SHUTDOWN:
> +		tcr &= ~TCR_DIE;
> +		break;
> +	}
> +	mtspr(SPRN_TCR, tcr);
> +#endif
> +	if (mode == CLOCK_EVT_MODE_PERIODIC)
> +		decrementer_set_next_event(tb_ticks_per_jiffy, dev);
> +}
> +
> +static struct clock_event_device decrementer_clockevent = {
> +	.name		= "decrementer",
> +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
> +	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
> +#else
> +	.features	= CLOCK_EVT_FEAT_ONESHOT,
> +#endif
> +	.shift		= 32,
> +	.rating		= 200,
> +	.irq		= -1,
> +	.set_next_event	= decrementer_set_next_event,
> +	.set_mode	= decrementer_set_mode,
> +};
> +
> +static DEFINE_PER_CPU(struct clock_event_device, decrementers);
> +
> +static void register_decrementer(void)
> +{
> +	int cpu = smp_processor_id();
> +	struct clock_event_device *decrementer = &per_cpu(decrementers,  
> cpu);
> +
> +	memcpy(decrementer, &decrementer_clockevent, sizeof(*decrementer));
> +
> +	decrementer->cpumask = cpumask_of_cpu(cpu);
> +
> +	clockevents_register_device(decrementer);
> +}
> +
> +#endif /* CONFIG_GENERIC_CLOCKEVENTS */
> +
>  #ifdef CONFIG_VIRT_CPU_ACCOUNTING
>  /*
>   * Factors for converting from cputime_t (timebase ticks) to
> @@ -313,6 +391,9 @@ void snapshot_timebase(void)
>  {
>  	__get_cpu_var(last_jiffy) = get_tb();
>  	snapshot_purr();
> +#ifdef CONFIG_GENERIC_CLOCKEVENTS
> +	register_decrementer();
> +#endif
>  }
>
>  void __delay(unsigned long loops)
> @@ -470,7 +551,31 @@ void timer_interrupt(struct pt_regs * re
>  	old_regs = set_irq_regs(regs);
>  	irq_enter();
>
> +#ifdef CONFIG_GENERIC_CLOCKEVENTS
> +#ifdef CONFIG_PPC_MULTIPLATFORM
> +	/*
> +	 * We must write a positive value to the decrementer to clear
> +	 * the interrupt on the IBM 970 CPU series.  In periodic mode,
> +	 * this happens when the decrementer gets reloaded later, but
> +	 * in one-shot mode, we have to do it here since an event handler
> +	 * may skip loading the new value...
> +	 */
> +	if (per_cpu(decrementers, cpu).mode != CLOCK_EVT_MODE_PERIODIC)
> +		set_dec(DECREMENTER_MAX);
> +#endif
> +	/*
> +	 * We can't disable the decrementer, so in the period between
> +	 * CPU being marked offline and calling stop-self, it's taking
> +	 * timer interrupts...
> +	 */
> +	if (!cpu_is_offline(cpu)) {
> +		struct clock_event_device *dev = &per_cpu(decrementers, cpu);
> +
> +		dev->event_handler(dev);
> +	}
> +#else
>  	profile_tick(CPU_PROFILING);
> +#endif
>  	calculate_steal_time();
>
>  #ifdef CONFIG_PPC_ISERIES
> @@ -486,6 +591,7 @@ void timer_interrupt(struct pt_regs * re
>  		if (__USE_RTC() && per_cpu(last_jiffy, cpu) >= 1000000000)
>  			per_cpu(last_jiffy, cpu) -= 1000000000;
>
> +#ifndef CONFIG_GENERIC_CLOCKEVENTS
>  		/*
>  		 * We cannot disable the decrementer, so in the period
>  		 * between this cpu's being marked offline in cpu_online_map
> @@ -495,6 +601,7 @@ void timer_interrupt(struct pt_regs * re
>  		 */
>  		if (!cpu_is_offline(cpu))
>  			account_process_time(regs);
> +#endif
>
>  		/*
>  		 * No need to check whether cpu is offline here; boot_cpuid
> @@ -507,15 +614,19 @@ void timer_interrupt(struct pt_regs * re
>  		tb_next_jiffy = tb_last_jiffy + tb_ticks_per_jiffy;
>  		if (per_cpu(last_jiffy, cpu) >= tb_next_jiffy) {
>  			tb_last_jiffy = tb_next_jiffy;
> +#ifndef CONFIG_GENERIC_CLOCKEVENTS
>  			do_timer(1);
> +#endif
>  			/*timer_recalc_offset(tb_last_jiffy);*/
>  			timer_check_rtc();
>  		}
>  		write_sequnlock(&xtime_lock);
>  	}
> -	
> +
> +#ifndef CONFIG_GENERIC_CLOCKEVENTS
>  	next_dec = tb_ticks_per_jiffy - ticks;
>  	set_dec(next_dec);
> +#endif
>
>  #ifdef CONFIG_PPC_ISERIES
>  	if (firmware_has_feature(FW_FEATURE_ISERIES) &&  
> hvlpevent_is_pending())
> @@ -770,8 +881,19 @@ void __init time_init(void)
>  	                        -xtime.tv_sec, -xtime.tv_nsec);
>  	write_sequnlock_irqrestore(&xtime_lock, flags);
>
> +#ifdef CONFIG_GENERIC_CLOCKEVENTS
> +	decrementer_clockevent.mult = div_sc(ppc_tb_freq, NSEC_PER_SEC,
> +					     decrementer_clockevent.shift);
> +	decrementer_clockevent.max_delta_ns =
> +		clockevent_delta2ns(DECREMENTER_MAX, &decrementer_clockevent);
> +	decrementer_clockevent.min_delta_ns =
> +		clockevent_delta2ns(0xf, &decrementer_clockevent);
> +
> +	register_decrementer();
> +#else
>  	/* Not exact, but the timer interrupt takes care of this */
>  	set_dec(tb_ticks_per_jiffy);
> +#endif
>  }
>
>  #define FEBRUARY	2
>
> _______________________________________________
> Linuxppc-dev mailing list
> Linuxppc-dev@ozlabs.org
> https://ozlabs.org/mailman/listinfo/linuxppc-dev

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/