Re: v2.6.19-rt6, yum/rpm

[Sergei Shtylyov <sshtylyov@ru.mvista.com>]

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

>>* Sergei Shtylyov <sshtylyov@ru.mvista.com> wrote:

>>>>could you resend them to me please?

>>>   Seeing that GENERIC_TIME has been thrown out from the -rt patch, 
>>>[...]

>>hm, i did that accidentally during a rebase. That was certainly not 
>>meant to be a persistent condition.

> ok, the delta below is what i've managed to restore from your PPC 
> patches so far. Looks like this was truly a comedy of errors: i 
> accidentally dropped the big ppc-gtod patch,

   I can't take credit for this one -- it's (and the vsyscall breakage :-) 
courtesy of John Stultz.

> which made your later fix 
> patches not apply, etc., etc. The one below still likely wont build 
> right away, but should be a more useful base for you and for Thomas too.

> 	Ingo
> 
> --------------->
> Index: linux/Makefile
> ===================================================================
> --- linux.orig/Makefile
> +++ linux/Makefile
> @@ -1,7 +1,7 @@
>  VERSION = 2
>  PATCHLEVEL = 6
>  SUBLEVEL = 20
> -EXTRAVERSION =-rc7-rt3
> +EXTRAVERSION =-rc7-rt4
>  NAME = Homicidal Dwarf Hamster
>  
>  # *DOCUMENTATION*
> Index: linux/arch/powerpc/Kconfig
> ===================================================================
> --- linux.orig/arch/powerpc/Kconfig
> +++ linux/arch/powerpc/Kconfig
> @@ -26,6 +26,10 @@ config MMU
>  	bool
>  	default y
>  
> +config GENERIC_TIME
> +	bool
> +	default y
> +
>  config GENERIC_HARDIRQS
>  	bool
>  	default y
> Index: linux/arch/powerpc/kernel/time.c
> ===================================================================
> --- linux.orig/arch/powerpc/kernel/time.c
> +++ linux/arch/powerpc/kernel/time.c
> @@ -119,8 +119,6 @@ EXPORT_SYMBOL_GPL(rtc_lock);
>  u64 tb_to_ns_scale;
>  unsigned tb_to_ns_shift;
>  
> -struct gettimeofday_struct do_gtod;
> -
>  extern struct timezone sys_tz;
>  static long timezone_offset;
>  
> @@ -378,160 +376,6 @@ static __inline__ void timer_check_rtc(v
>          }
>  }
>  
> -/*
> - * This version of gettimeofday has microsecond resolution.
> - */
> -static inline void __do_gettimeofday(struct timeval *tv)
> -{
> -	unsigned long sec, usec;
> -	u64 tb_ticks, xsec;
> -	struct gettimeofday_vars *temp_varp;
> -	u64 temp_tb_to_xs, temp_stamp_xsec;
> -
> -	/*
> -	 * These calculations are faster (gets rid of divides)
> -	 * if done in units of 1/2^20 rather than microseconds.
> -	 * The conversion to microseconds at the end is done
> -	 * without a divide (and in fact, without a multiply)
> -	 */
> -	temp_varp = do_gtod.varp;
> -
> -	/* Sampling the time base must be done after loading
> -	 * do_gtod.varp in order to avoid racing with update_gtod.
> -	 */
> -	data_barrier(temp_varp);
> -	tb_ticks = get_tb() - temp_varp->tb_orig_stamp;
> -	temp_tb_to_xs = temp_varp->tb_to_xs;
> -	temp_stamp_xsec = temp_varp->stamp_xsec;
> -	xsec = temp_stamp_xsec + mulhdu(tb_ticks, temp_tb_to_xs);
> -	sec = xsec / XSEC_PER_SEC;
> -	usec = (unsigned long)xsec & (XSEC_PER_SEC - 1);
> -	usec = SCALE_XSEC(usec, 1000000);
> -
> -	tv->tv_sec = sec;
> -	tv->tv_usec = usec;
> -}
> -
> -void do_gettimeofday(struct timeval *tv)
> -{
> -	if (__USE_RTC()) {
> -		/* do this the old way */
> -		unsigned long flags, seq;
> -		unsigned int sec, nsec, usec;
> -
> -		do {
> -			seq = read_seqbegin_irqsave(&xtime_lock, flags);
> -			sec = xtime.tv_sec;
> -			nsec = xtime.tv_nsec + tb_ticks_since(tb_last_jiffy);
> -		} while (read_seqretry_irqrestore(&xtime_lock, seq, flags));
> -		usec = nsec / 1000;
> -		while (usec >= 1000000) {
> -			usec -= 1000000;
> -			++sec;
> -		}
> -		tv->tv_sec = sec;
> -		tv->tv_usec = usec;
> -		return;
> -	}
> -	__do_gettimeofday(tv);
> -}
> -
> -EXPORT_SYMBOL(do_gettimeofday);
> -
> -/*
> - * There are two copies of tb_to_xs and stamp_xsec so that no
> - * lock is needed to access and use these values in
> - * do_gettimeofday.  We alternate the copies and as long as a
> - * reasonable time elapses between changes, there will never
> - * be inconsistent values.  ntpd has a minimum of one minute
> - * between updates.
> - */
> -static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
> -			       u64 new_tb_to_xs)
> -{
> -	unsigned temp_idx;
> -	struct gettimeofday_vars *temp_varp;
> -
> -	temp_idx = (do_gtod.var_idx == 0);
> -	temp_varp = &do_gtod.vars[temp_idx];
> -
> -	temp_varp->tb_to_xs = new_tb_to_xs;
> -	temp_varp->tb_orig_stamp = new_tb_stamp;
> -	temp_varp->stamp_xsec = new_stamp_xsec;
> -	smp_mb();
> -	do_gtod.varp = temp_varp;
> -	do_gtod.var_idx = temp_idx;
> -
> -	/*
> -	 * tb_update_count is used to allow the userspace gettimeofday code
> -	 * to assure itself that it sees a consistent view of the tb_to_xs and
> -	 * stamp_xsec variables.  It reads the tb_update_count, then reads
> -	 * tb_to_xs and stamp_xsec and then reads tb_update_count again.  If
> -	 * the two values of tb_update_count match and are even then the
> -	 * tb_to_xs and stamp_xsec values are consistent.  If not, then it
> -	 * loops back and reads them again until this criteria is met.
> -	 * We expect the caller to have done the first increment of
> -	 * vdso_data->tb_update_count already.
> -	 */
> -	vdso_data->tb_orig_stamp = new_tb_stamp;
> -	vdso_data->stamp_xsec = new_stamp_xsec;
> -	vdso_data->tb_to_xs = new_tb_to_xs;
> -	vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec;
> -	vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec;
> -	smp_wmb();
> -	++(vdso_data->tb_update_count);
> -}
> -
> -/*
> - * When the timebase - tb_orig_stamp gets too big, we do a manipulation
> - * between tb_orig_stamp and stamp_xsec. The goal here is to keep the
> - * difference tb - tb_orig_stamp small enough to always fit inside a
> - * 32 bits number. This is a requirement of our fast 32 bits userland
> - * implementation in the vdso. If we "miss" a call to this function
> - * (interrupt latency, CPU locked in a spinlock, ...) and we end up
> - * with a too big difference, then the vdso will fallback to calling
> - * the syscall
> - */
> -static __inline__ void timer_recalc_offset(u64 cur_tb)
> -{
> -	unsigned long offset;
> -	u64 new_stamp_xsec;
> -	u64 tlen, t2x;
> -	u64 tb, xsec_old, xsec_new;
> -	struct gettimeofday_vars *varp;
> -
> -	if (__USE_RTC())
> -		return;
> -	tlen = current_tick_length();
> -	offset = cur_tb - do_gtod.varp->tb_orig_stamp;
> -	if (tlen == last_tick_len && offset < 0x80000000u)
> -		return;
> -	if (tlen != last_tick_len) {
> -		t2x = mulhdu(tlen << TICKLEN_SHIFT, ticklen_to_xs);
> -		last_tick_len = tlen;
> -	} else
> -		t2x = do_gtod.varp->tb_to_xs;
> -	new_stamp_xsec = (u64) xtime.tv_nsec * XSEC_PER_SEC;
> -	do_div(new_stamp_xsec, 1000000000);
> -	new_stamp_xsec += (u64) xtime.tv_sec * XSEC_PER_SEC;
> -
> -	++vdso_data->tb_update_count;
> -	smp_mb();
> -
> -	/*
> -	 * Make sure time doesn't go backwards for userspace gettimeofday.
> -	 */
> -	tb = get_tb();
> -	varp = do_gtod.varp;
> -	xsec_old = mulhdu(tb - varp->tb_orig_stamp, varp->tb_to_xs)
> -		+ varp->stamp_xsec;
> -	xsec_new = mulhdu(tb - cur_tb, t2x) + new_stamp_xsec;
> -	if (xsec_new < xsec_old)
> -		new_stamp_xsec += xsec_old - xsec_new;
> -
> -	update_gtod(cur_tb, new_stamp_xsec, t2x);
> -}
> -
>  #ifdef CONFIG_SMP
>  unsigned long notrace profile_pc(struct pt_regs *regs)
>  {
> @@ -581,11 +425,7 @@ static void iSeries_tb_recal(void)
>  				tb_ticks_per_sec   = new_tb_ticks_per_sec;
>  				calc_cputime_factors();
>  				div128_by_32( XSEC_PER_SEC, 0, tb_ticks_per_sec, &divres );
> -				do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
>  				tb_to_xs = divres.result_low;
> -				do_gtod.varp->tb_to_xs = tb_to_xs;
> -				vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
> -				vdso_data->tb_to_xs = tb_to_xs;
>  			}
>  			else {
>  				printk( "Titan recalibrate: FAILED (difference > 4 percent)\n"
> @@ -756,77 +596,6 @@ unsigned long long sched_clock(void)
>  	return mulhdu(get_tb(), tb_to_ns_scale) << tb_to_ns_shift;
>  }
>  
> -int do_settimeofday(struct timespec *tv)
> -{
> -	time_t wtm_sec, new_sec = tv->tv_sec;
> -	long wtm_nsec, new_nsec = tv->tv_nsec;
> -	unsigned long flags;
> -	u64 new_xsec;
> -	unsigned long tb_delta;
> -
> -	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
> -		return -EINVAL;
> -
> -	write_seqlock_irqsave(&xtime_lock, flags);
> -
> -	/*
> -	 * Updating the RTC is not the job of this code. If the time is
> -	 * stepped under NTP, the RTC will be updated after STA_UNSYNC
> -	 * is cleared.  Tools like clock/hwclock either copy the RTC
> -	 * to the system time, in which case there is no point in writing
> -	 * to the RTC again, or write to the RTC but then they don't call
> -	 * settimeofday to perform this operation.
> -	 */
> -#ifdef CONFIG_PPC_ISERIES
> -	if (firmware_has_feature(FW_FEATURE_ISERIES) && first_settimeofday) {
> -		iSeries_tb_recal();
> -		first_settimeofday = 0;
> -	}
> -#endif
> -
> -	/* Make userspace gettimeofday spin until we're done. */
> -	++vdso_data->tb_update_count;
> -	smp_mb();
> -
> -	/*
> -	 * Subtract off the number of nanoseconds since the
> -	 * beginning of the last tick.
> -	 */
> -	tb_delta = tb_ticks_since(tb_last_jiffy);
> -	tb_delta = mulhdu(tb_delta, do_gtod.varp->tb_to_xs); /* in xsec */
> -	new_nsec -= SCALE_XSEC(tb_delta, 1000000000);
> -
> -	wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - new_sec);
> -	wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - new_nsec);
> -
> - 	set_normalized_timespec(&xtime, new_sec, new_nsec);
> -	set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
> -
> -	/* In case of a large backwards jump in time with NTP, we want the 
> -	 * clock to be updated as soon as the PLL is again in lock.
> -	 */
> -	last_rtc_update = new_sec - 658;
> -
> -	ntp_clear();
> -
> -	new_xsec = xtime.tv_nsec;
> -	if (new_xsec != 0) {
> -		new_xsec *= XSEC_PER_SEC;
> -		do_div(new_xsec, NSEC_PER_SEC);
> -	}
> -	new_xsec += (u64)xtime.tv_sec * XSEC_PER_SEC;
> -	update_gtod(tb_last_jiffy, new_xsec, do_gtod.varp->tb_to_xs);
> -
> -	vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
> -	vdso_data->tz_dsttime = sys_tz.tz_dsttime;
> -
> -	write_sequnlock_irqrestore(&xtime_lock, flags);
> -	clock_was_set();
> -	return 0;
> -}
> -
> -EXPORT_SYMBOL(do_settimeofday);
> -
>  static int __init get_freq(char *name, int cells, unsigned long *val)
>  {
>  	struct device_node *cpu;
> @@ -993,20 +762,6 @@ void __init time_init(void)
>  
>  	xtime.tv_sec = tm;
>  	xtime.tv_nsec = 0;
> -	do_gtod.varp = &do_gtod.vars[0];
> -	do_gtod.var_idx = 0;
> -	do_gtod.varp->tb_orig_stamp = tb_last_jiffy;
> -	__get_cpu_var(last_jiffy) = tb_last_jiffy;
> -	do_gtod.varp->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC;
> -	do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
> -	do_gtod.varp->tb_to_xs = tb_to_xs;
> -	do_gtod.tb_to_us = tb_to_us;
> -
> -	vdso_data->tb_orig_stamp = tb_last_jiffy;
> -	vdso_data->tb_update_count = 0;
> -	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
> -	vdso_data->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC;
> -	vdso_data->tb_to_xs = tb_to_xs;
>  
>  	time_freq = 0;
>  
> @@ -1019,7 +774,6 @@ void __init time_init(void)
>  	set_dec(tb_ticks_per_jiffy);
>  }
>  
> -
>  #define FEBRUARY	2
>  #define	STARTOFTIME	1970
>  #define SECDAY		86400L
> @@ -1164,3 +918,36 @@ void div128_by_32(u64 dividend_high, u64
>  	dr->result_low  = ((u64)y << 32) + z;
>  
>  }
> +
> +/* PowerPC clocksource code */
> +
> +#include <linux/clocksource.h>
> +
> +static cycle_t timebase_read(void)
> +{
> +	return (cycle_t)get_tb();
> +}
> +
> +struct clocksource clocksource_timebase = {
> +	.name		= "timebase",
> +	.rating		= 200,
> +	.read		= timebase_read,
> +	.mask		= (cycle_t)-1,
> +	.mult		= 0,
> +	.shift		= 22,
> +	.is_continuous	= 1,
> +};
> +
> +
> +/* XXX - this should be calculated or properly externed! */
> +static int __init init_timebase_clocksource(void)
> +{
> +	if (__USE_RTC())
> +		return -ENODEV;
> +
> +	clocksource_timebase.mult = clocksource_hz2mult(tb_ticks_per_sec,
> +					clocksource_timebase.shift);
> +	return clocksource_register(&clocksource_timebase);
> +}
> +
> +module_init(init_timebase_clocksource);

    Erm, there was one more patch implementing read_prersistent_clock()...

> Index: linux/arch/powerpc/platforms/cell/interrupt.c
> ===================================================================
> --- linux.orig/arch/powerpc/platforms/cell/interrupt.c
> +++ linux/arch/powerpc/platforms/cell/interrupt.c
> @@ -90,6 +90,7 @@ static struct irq_chip iic_chip = {
>  	.typename = " CELL-IIC ",
>  	.mask = iic_mask,
>  	.unmask = iic_unmask,
> +	.ack = iic_eoi,
>  	.eoi = iic_eoi,
>  };
>  
> Index: linux/arch/powerpc/platforms/iseries/irq.c
> ===================================================================
> --- linux.orig/arch/powerpc/platforms/iseries/irq.c
> +++ linux/arch/powerpc/platforms/iseries/irq.c
> @@ -279,6 +279,7 @@ static struct irq_chip iseries_pic = {
>  	.shutdown	= iseries_shutdown_IRQ,
>  	.unmask		= iseries_enable_IRQ,
>  	.mask		= iseries_disable_IRQ,
> +	.ack		= iseries_end_IRQ,
>  	.eoi		= iseries_end_IRQ
>  };
>  
> Index: linux/arch/powerpc/platforms/pseries/xics.c
> ===================================================================
> --- linux.orig/arch/powerpc/platforms/pseries/xics.c
> +++ linux/arch/powerpc/platforms/pseries/xics.c
> @@ -456,6 +456,7 @@ static struct irq_chip xics_pic_direct =
>  	.startup = xics_startup,
>  	.mask = xics_mask_irq,
>  	.unmask = xics_unmask_irq,
> +	.ack = xics_eoi_direct,
>  	.eoi = xics_eoi_direct,
>  	.set_affinity = xics_set_affinity
>  };
> @@ -466,6 +467,7 @@ static struct irq_chip xics_pic_lpar = {
>  	.startup = xics_startup,
>  	.mask = xics_mask_irq,
>  	.unmask = xics_unmask_irq,
> +	.ack = xics_eoi_lpar,
>  	.eoi = xics_eoi_lpar,
>  	.set_affinity = xics_set_affinity
>  };
> Index: linux/arch/powerpc/sysdev/mpic.c
> ===================================================================
> --- linux.orig/arch/powerpc/sysdev/mpic.c
> +++ linux/arch/powerpc/sysdev/mpic.c
> @@ -767,6 +767,7 @@ static int mpic_set_irq_type(unsigned in
>  static struct irq_chip mpic_irq_chip = {
>  	.mask		= mpic_mask_irq,
>  	.unmask		= mpic_unmask_irq,
> +	.ack		= mpic_end_irq,
>  	.eoi		= mpic_end_irq,
>  	.set_type	= mpic_set_irq_type,
>  };

    These changes have been refused in favor of "fasetoi" flow fix.

> Index: linux/drivers/mtd/nand/cafe.c
> ===================================================================
> --- linux.orig/drivers/mtd/nand/cafe.c
> +++ linux/drivers/mtd/nand/cafe.c
> @@ -597,7 +597,8 @@ static int __devinit cafe_nand_probe(str
>  		cafe_writel(cafe, 0xffffffff, NAND_TIMING3);
>  	}
>  	cafe_writel(cafe, 0xffffffff, NAND_IRQ_MASK);
> -	err = request_irq(pdev->irq, &cafe_nand_interrupt, SA_SHIRQ, "CAFE NAND", mtd);
> +	err = request_irq(pdev->irq, &cafe_nand_interrupt, IRQF_SHARED,
> +			"CAFE NAND", mtd);
>  	if (err) {
>  		dev_warn(&pdev->dev, "Could not register IRQ %d\n", pdev->irq);
>  

    Certainly not mine. :-)

> Index: linux/kernel/latency_trace.c
> ===================================================================
> --- linux.orig/kernel/latency_trace.c
> +++ linux/kernel/latency_trace.c
> @@ -1774,8 +1774,8 @@ check_critical_timing(int cpu, struct cp
>  #ifndef CONFIG_CRITICAL_LATENCY_HIST
>  	if (!preempt_thresh && preempt_max_latency > delta) {
>  		printk("bug: updating %016Lx > %016Lx?\n",
> -			preempt_max_latency, delta);
> -		printk("  [%016Lx %016Lx %016Lx]\n", T0, T1, T2);
> +			(u64)preempt_max_latency, (u64)delta);
> +		printk("  [%016Lx %016Lx %016Lx]\n", (u64)T0, (u64)T1, (u64)T2);
>  	}
>  #endif

    IIRC, this is a fragment of my another refused patch (maybe the first take 
on it?)... Should be outdated now.

WBR, Sergei