From a42548a18866e87092db93b771e6c5b060d78401 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Wed, 29 Jul 2009 12:15:29 +0200 Subject: cputime: Optimize jiffies_to_cputime(1) For powerpc with CONFIG_VIRT_CPU_ACCOUNTING jiffies_to_cputime(1) is not compile time constant and run time calculations are quite expensive. To optimize we use precomputed value. For all other architectures is is preprocessor definition. Signed-off-by: Stanislaw Gruszka Acked-by: Peter Zijlstra Acked-by: Thomas Gleixner Cc: Oleg Nesterov Cc: Andrew Morton Cc: Paul Mackerras Cc: Benjamin Herrenschmidt LKML-Reference: <1248862529-6063-5-git-send-email-sgruszka@redhat.com> Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/time.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch/powerpc/kernel/time.c') diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index eae4511ceeac..211d7b0cd370 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -193,6 +193,8 @@ EXPORT_SYMBOL(__cputime_clockt_factor); DEFINE_PER_CPU(unsigned long, cputime_last_delta); DEFINE_PER_CPU(unsigned long, cputime_scaled_last_delta); +cputime_t cputime_one_jiffy; + static void calc_cputime_factors(void) { struct div_result res; @@ -500,6 +502,7 @@ static int __init iSeries_tb_recal(void) tb_to_xs = divres.result_low; vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; vdso_data->tb_to_xs = tb_to_xs; + setup_cputime_one_jiffy(); } else { printk( "Titan recalibrate: FAILED (difference > 4 percent)\n" @@ -945,6 +948,7 @@ void __init time_init(void) tb_ticks_per_usec = ppc_tb_freq / 1000000; tb_to_us = mulhwu_scale_factor(ppc_tb_freq, 1000000); calc_cputime_factors(); + setup_cputime_one_jiffy(); /* * Calculate the length of each tick in ns. It will not be -- cgit v1.2.3 From d4f587c67fc39e0030ddd718675e252e208da4d7 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 14 Aug 2009 15:47:31 +0200 Subject: timekeeping: Increase granularity of read_persistent_clock() The persistent clock of some architectures (e.g. s390) have a better granularity than seconds. To reduce the delta between the host clock and the guest clock in a virtualized system change the read_persistent_clock function to return a struct timespec. Signed-off-by: Martin Schwidefsky Cc: Ingo Molnar Acked-by: John Stultz Cc: Daniel Walker LKML-Reference: <20090814134811.013873340@de.ibm.com> Signed-off-by: Thomas Gleixner --- arch/powerpc/kernel/time.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/kernel/time.c') diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index eae4511ceeac..ad63f30fe3da 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -769,7 +769,7 @@ int update_persistent_clock(struct timespec now) return ppc_md.set_rtc_time(&tm); } -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { struct rtc_time tm; static int first = 1; @@ -787,8 +787,9 @@ unsigned long read_persistent_clock(void) if (!ppc_md.get_rtc_time) return 0; ppc_md.get_rtc_time(&tm); - return mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday, - tm.tm_hour, tm.tm_min, tm.tm_sec); + ts->tv_sec = mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday, + tm.tm_hour, tm.tm_min, tm.tm_sec); + ts->tv_nsec = 0; } /* clocksource code */ -- cgit v1.2.3 From 14ea58ad797e4e9b7be755aca0fd3925d0713ede Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 1 Aug 2009 22:48:27 +0000 Subject: powerpc: Use DIV_ROUND_CLOSEST in time init code The kernel.h macro DIV_ROUND_CLOSEST performs the computation (x + d/2)/d but is perhaps more readable. The semantic patch that makes this change is as follows: (http://www.emn.fr/x-info/coccinelle/) // @haskernel@ @@ #include @depends on haskernel@ expression x,__divisor; @@ - (((x) + ((__divisor) / 2)) / (__divisor)) + DIV_ROUND_CLOSEST(x,__divisor) // Signed-off-by: Julia Lawall Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/time.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel/time.c') diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index eae4511ceeac..edb1edb36469 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -479,7 +479,8 @@ static int __init iSeries_tb_recal(void) unsigned long tb_ticks = tb - iSeries_recal_tb; unsigned long titan_usec = (titan - iSeries_recal_titan) >> 12; unsigned long new_tb_ticks_per_sec = (tb_ticks * USEC_PER_SEC)/titan_usec; - unsigned long new_tb_ticks_per_jiffy = (new_tb_ticks_per_sec+(HZ/2))/HZ; + unsigned long new_tb_ticks_per_jiffy = + DIV_ROUND_CLOSEST(new_tb_ticks_per_sec, HZ); long tick_diff = new_tb_ticks_per_jiffy - tb_ticks_per_jiffy; char sign = '+'; /* make sure tb_ticks_per_sec and tb_ticks_per_jiffy are consistent */ -- cgit v1.2.3 From d90246cd8e0141332a8ab09c3c1800cc2028a686 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Sat, 22 Aug 2009 22:23:13 +0200 Subject: timekeeping: Increase granularity of read_persistent_clock(), build fix Fix the following build problem on powerpc: arch/powerpc/kernel/time.c: In function 'read_persistent_clock': arch/powerpc/kernel/time.c:788: error: 'return' with a value, in function returning void arch/powerpc/kernel/time.c:791: error: 'return' with a value, in function returning void Reported-by: Ingo Molnar Signed-off-by: Martin Schwidefsky Cc: dwalker@fifo99.com Cc: johnstul@us.ibm.com LKML-Reference: <20090822222313.74b9619c@skybase> Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/time.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/kernel/time.c') diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index ad63f30fe3da..a508388fb87c 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -774,6 +774,7 @@ void read_persistent_clock(struct timespec *ts) struct rtc_time tm; static int first = 1; + ts->tv_nsec = 0; /* XXX this is a litle fragile but will work okay in the short term */ if (first) { first = 0; @@ -781,15 +782,18 @@ void read_persistent_clock(struct timespec *ts) timezone_offset = ppc_md.time_init(); /* get_boot_time() isn't guaranteed to be safe to call late */ - if (ppc_md.get_boot_time) - return ppc_md.get_boot_time() -timezone_offset; + if (ppc_md.get_boot_time) { + ts->tv_sec = ppc_md.get_boot_time() - timezone_offset; + return; + } + } + if (!ppc_md.get_rtc_time) { + ts->tv_sec = 0; + return; } - if (!ppc_md.get_rtc_time) - return 0; ppc_md.get_rtc_time(&tm); ts->tv_sec = mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec); - ts->tv_nsec = 0; } /* clocksource code */ -- cgit v1.2.3 From 77c0a700c1c292edafa11c1e52821ce4636f81b0 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 28 Aug 2009 14:25:04 +1000 Subject: powerpc: Properly start decrementer on BookE secondary CPUs This moves the code to start the decrementer on 40x and BookE into a separate function which is now called from time_init() and secondary_time_init(), before the respective clock sources are registered. We also remove the 85xx specific code for doing it from the platform code. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/time.c | 30 ++++++++++++++++++++++-------- 1 file changed, 22 insertions(+), 8 deletions(-) (limited to 'arch/powerpc/kernel/time.c') diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index edb1edb36469..a180b4f9a4f6 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -727,6 +727,18 @@ static int __init get_freq(char *name, int cells, unsigned long *val) return found; } +/* should become __cpuinit when secondary_cpu_time_init also is */ +void start_cpu_decrementer(void) +{ +#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) + /* Clear any pending timer interrupts */ + mtspr(SPRN_TSR, TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS); + + /* Enable decrementer interrupt */ + mtspr(SPRN_TCR, TCR_DIE); +#endif /* defined(CONFIG_BOOKE) || defined(CONFIG_40x) */ +} + void __init generic_calibrate_decr(void) { ppc_tb_freq = DEFAULT_TB_FREQ; /* hardcoded default */ @@ -746,14 +758,6 @@ void __init generic_calibrate_decr(void) printk(KERN_ERR "WARNING: Estimating processor frequency " "(not found)\n"); } - -#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) - /* Clear any pending timer interrupts */ - mtspr(SPRN_TSR, TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS); - - /* Enable decrementer interrupt */ - mtspr(SPRN_TCR, TCR_DIE); -#endif } int update_persistent_clock(struct timespec now) @@ -914,6 +918,11 @@ static void __init init_decrementer_clockevent(void) void secondary_cpu_time_init(void) { + /* Start the decrementer on CPUs that have manual control + * such as BookE + */ + start_cpu_decrementer(); + /* FIME: Should make unrelatred change to move snapshot_timebase * call here ! */ register_decrementer_clockevent(smp_processor_id()); @@ -1017,6 +1026,11 @@ void __init time_init(void) write_sequnlock_irqrestore(&xtime_lock, flags); + /* Start the decrementer on CPUs that have manual control + * such as BookE + */ + start_cpu_decrementer(); + /* Register the clocksource, if we're not running on iSeries */ if (!firmware_has_feature(FW_FEATURE_ISERIES)) clocksource_init(); -- cgit v1.2.3 From cdd6c482c9ff9c55475ee7392ec8f672eddb7be6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 21 Sep 2009 12:02:48 +0200 Subject: perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian Acked-by: Peter Zijlstra Acked-by: Paul Mackerras Reviewed-by: Arjan van de Ven Cc: Mike Galbraith Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Steven Rostedt Cc: Benjamin Herrenschmidt Cc: David Howells Cc: Kyle McMartin Cc: Martin Schwidefsky Cc: "David S. Miller" Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: LKML-Reference: Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/time.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'arch/powerpc/kernel/time.c') diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 465e498bcb33..df45a7449a66 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -53,7 +53,7 @@ #include #include #include -#include +#include #include #include @@ -527,25 +527,25 @@ void __init iSeries_time_init_early(void) } #endif /* CONFIG_PPC_ISERIES */ -#if defined(CONFIG_PERF_COUNTERS) && defined(CONFIG_PPC32) -DEFINE_PER_CPU(u8, perf_counter_pending); +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_PPC32) +DEFINE_PER_CPU(u8, perf_event_pending); -void set_perf_counter_pending(void) +void set_perf_event_pending(void) { - get_cpu_var(perf_counter_pending) = 1; + get_cpu_var(perf_event_pending) = 1; set_dec(1); - put_cpu_var(perf_counter_pending); + put_cpu_var(perf_event_pending); } -#define test_perf_counter_pending() __get_cpu_var(perf_counter_pending) -#define clear_perf_counter_pending() __get_cpu_var(perf_counter_pending) = 0 +#define test_perf_event_pending() __get_cpu_var(perf_event_pending) +#define clear_perf_event_pending() __get_cpu_var(perf_event_pending) = 0 -#else /* CONFIG_PERF_COUNTERS && CONFIG_PPC32 */ +#else /* CONFIG_PERF_EVENTS && CONFIG_PPC32 */ -#define test_perf_counter_pending() 0 -#define clear_perf_counter_pending() +#define test_perf_event_pending() 0 +#define clear_perf_event_pending() -#endif /* CONFIG_PERF_COUNTERS && CONFIG_PPC32 */ +#endif /* CONFIG_PERF_EVENTS && CONFIG_PPC32 */ /* * For iSeries shared processors, we have to let the hypervisor @@ -573,9 +573,9 @@ void timer_interrupt(struct pt_regs * regs) set_dec(DECREMENTER_MAX); #ifdef CONFIG_PPC32 - if (test_perf_counter_pending()) { - clear_perf_counter_pending(); - perf_counter_do_pending(); + if (test_perf_event_pending()) { + clear_perf_event_pending(); + perf_event_do_pending(); } if (atomic_read(&ppc_n_lost_interrupts) != 0) do_IRQ(regs); -- cgit v1.2.3