From 1be396794897f80bfc8774719ba60309a9e3d374 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 14 Aug 2009 15:47:20 +0200 Subject: timekeeping: Move reset of cycle_last for tsc clocksource to tsc change_clocksource resets the cycle_last value to zero then sets it to a value read from the clocksource. The reset to zero is required only for the TSC clocksource to make the read_tsc function work after a resume. The reason is that the TSC read function uses cycle_last to detect backwards going TSCs. In the resume case cycle_last contains the TSC value from the last update before the suspend. On resume the TSC starts counting from 0 again and would trip over the cycle_last comparison. This is subtle and surprising. Move the reset to a resume function in the tsc code. Signed-off-by: Martin Schwidefsky Acked-by: Thomas Gleixner Acked-by: John Stultz Cc: Daniel Walker LKML-Reference: <20090814134808.142191175@de.ibm.com> Signed-off-by: Thomas Gleixner --- arch/x86/kernel/tsc.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 71f4368b357..968425422c4 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -744,10 +744,16 @@ static cycle_t __vsyscall_fn vread_tsc(void) } #endif +static void resume_tsc(void) +{ + clocksource_tsc.cycle_last = 0; +} + static struct clocksource clocksource_tsc = { .name = "tsc", .rating = 300, .read = read_tsc, + .resume = resume_tsc, .mask = CLOCKSOURCE_MASK(64), .shift = 22, .flags = CLOCK_SOURCE_IS_CONTINUOUS | -- cgit v1.2.3-70-g09d2 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/m68knommu/kernel/time.c | 5 ++-- arch/mips/dec/time.c | 5 ++-- arch/mips/lasat/ds1603.c | 5 ++-- arch/mips/lasat/sysctl.c | 8 ++++-- arch/mips/lemote/lm2e/setup.c | 5 ++-- arch/mips/mti-malta/malta-time.c | 5 ++-- arch/mips/pmc-sierra/yosemite/setup.c | 5 ++-- arch/mips/sibyte/swarm/setup.c | 15 +++++++--- arch/mips/sni/time.c | 5 ++-- arch/powerpc/kernel/time.c | 7 +++-- arch/s390/kernel/time.c | 22 +++------------ arch/sh/kernel/time.c | 6 ++-- arch/x86/kernel/rtc.c | 5 ++-- arch/xtensa/kernel/time.c | 5 ++-- include/linux/time.h | 2 +- kernel/time/timekeeping.c | 52 +++++++++++++++++++---------------- 16 files changed, 83 insertions(+), 74 deletions(-) (limited to 'arch/x86') diff --git a/arch/m68knommu/kernel/time.c b/arch/m68knommu/kernel/time.c index d182b2f7221..68432248515 100644 --- a/arch/m68knommu/kernel/time.c +++ b/arch/m68knommu/kernel/time.c @@ -72,9 +72,10 @@ static unsigned long read_rtc_mmss(void) return mktime(year, mon, day, hour, min, sec);; } -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { - return read_rtc_mmss(); + ts->tv_sec = read_rtc_mmss(); + ts->tv_nsec = 0; } int update_persistent_clock(struct timespec now) diff --git a/arch/mips/dec/time.c b/arch/mips/dec/time.c index 463136e6685..02f505f23c3 100644 --- a/arch/mips/dec/time.c +++ b/arch/mips/dec/time.c @@ -18,7 +18,7 @@ #include #include -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { unsigned int year, mon, day, hour, min, sec, real_year; unsigned long flags; @@ -53,7 +53,8 @@ unsigned long read_persistent_clock(void) year += real_year - 72 + 2000; - return mktime(year, mon, day, hour, min, sec); + ts->tv_sec = mktime(year, mon, day, hour, min, sec); + ts->tv_nsec = 0; } /* diff --git a/arch/mips/lasat/ds1603.c b/arch/mips/lasat/ds1603.c index 52cb1436a12..c6fd96ff118 100644 --- a/arch/mips/lasat/ds1603.c +++ b/arch/mips/lasat/ds1603.c @@ -135,7 +135,7 @@ static void rtc_end_op(void) lasat_ndelay(1000); } -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { unsigned long word; unsigned long flags; @@ -147,7 +147,8 @@ unsigned long read_persistent_clock(void) rtc_end_op(); spin_unlock_irqrestore(&rtc_lock, flags); - return word; + ts->tv_sec = word; + ts->tv_nsec = 0; } int rtc_mips_set_mmss(unsigned long time) diff --git a/arch/mips/lasat/sysctl.c b/arch/mips/lasat/sysctl.c index 8f88886feb1..3f04d4c406b 100644 --- a/arch/mips/lasat/sysctl.c +++ b/arch/mips/lasat/sysctl.c @@ -92,10 +92,12 @@ static int rtctmp; int proc_dolasatrtc(ctl_table *table, int write, struct file *filp, void *buffer, size_t *lenp, loff_t *ppos) { + struct timespec ts; int r; if (!write) { - rtctmp = read_persistent_clock(); + read_persistent_clock(&ts); + rtctmp = ts.tv_sec; /* check for time < 0 and set to 0 */ if (rtctmp < 0) rtctmp = 0; @@ -134,9 +136,11 @@ int sysctl_lasat_rtc(ctl_table *table, void *oldval, size_t *oldlenp, void *newval, size_t newlen) { + struct timespec ts; int r; - rtctmp = read_persistent_clock(); + read_persistent_clock(&ts); + rtctmp = ts.tv_sec; if (rtctmp < 0) rtctmp = 0; r = sysctl_intvec(table, oldval, oldlenp, newval, newlen); diff --git a/arch/mips/lemote/lm2e/setup.c b/arch/mips/lemote/lm2e/setup.c index ebd6ceaef2f..24b355df612 100644 --- a/arch/mips/lemote/lm2e/setup.c +++ b/arch/mips/lemote/lm2e/setup.c @@ -54,9 +54,10 @@ void __init plat_time_init(void) mips_hpt_frequency = cpu_clock_freq / 2; } -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { - return mc146818_get_cmos_time(); + ts->tv_sec = mc146818_get_cmos_time(); + ts->tv_nsec = 0; } void (*__wbflush)(void); diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c index 0b97d47691f..3c6f190aa61 100644 --- a/arch/mips/mti-malta/malta-time.c +++ b/arch/mips/mti-malta/malta-time.c @@ -100,9 +100,10 @@ static unsigned int __init estimate_cpu_frequency(void) return count; } -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { - return mc146818_get_cmos_time(); + ts->tv_sec = mc146818_get_cmos_time(); + ts->tv_nsec = 0; } static void __init plat_perf_setup(void) diff --git a/arch/mips/pmc-sierra/yosemite/setup.c b/arch/mips/pmc-sierra/yosemite/setup.c index 2d3c0dca275..3498ac9c35a 100644 --- a/arch/mips/pmc-sierra/yosemite/setup.c +++ b/arch/mips/pmc-sierra/yosemite/setup.c @@ -70,7 +70,7 @@ void __init bus_error_init(void) } -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { unsigned int year, month, day, hour, min, sec; unsigned long flags; @@ -92,7 +92,8 @@ unsigned long read_persistent_clock(void) m48t37_base->control = 0x00; spin_unlock_irqrestore(&rtc_lock, flags); - return mktime(year, month, day, hour, min, sec); + ts->tv_sec = mktime(year, month, day, hour, min, sec); + ts->tv_nsec = 0; } int rtc_mips_set_time(unsigned long tim) diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c index 672e45d495a..623ffc933c4 100644 --- a/arch/mips/sibyte/swarm/setup.c +++ b/arch/mips/sibyte/swarm/setup.c @@ -87,19 +87,26 @@ enum swarm_rtc_type { enum swarm_rtc_type swarm_rtc_type; -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { + unsigned long sec; + switch (swarm_rtc_type) { case RTC_XICOR: - return xicor_get_time(); + sec = xicor_get_time(); + break; case RTC_M4LT81: - return m41t81_get_time(); + sec = m41t81_get_time(); + break; case RTC_NONE: default: - return mktime(2000, 1, 1, 0, 0, 0); + sec = mktime(2000, 1, 1, 0, 0, 0); + break; } + ts->tv_sec = sec; + tv->tv_nsec = 0; } int rtc_mips_set_time(unsigned long sec) diff --git a/arch/mips/sni/time.c b/arch/mips/sni/time.c index 0d9ec1a5c24..62df6a598e0 100644 --- a/arch/mips/sni/time.c +++ b/arch/mips/sni/time.c @@ -182,7 +182,8 @@ void __init plat_time_init(void) setup_pit_timer(); } -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { - return -1; + ts->tv_sec = -1; + ts->tv_nsec = 0; } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index eae4511ceea..ad63f30fe3d 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 */ diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index e76c2e7a8b9..a94ec48587b 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -182,12 +182,9 @@ static void timing_alert_interrupt(__u16 code) static void etr_reset(void); static void stp_reset(void); -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { - struct timespec ts; - - tod_to_timeval(get_clock() - TOD_UNIX_EPOCH, &ts); - return ts.tv_sec; + tod_to_timeval(get_clock() - TOD_UNIX_EPOCH, ts); } static cycle_t read_tod_clock(struct clocksource *cs) @@ -248,7 +245,6 @@ void __init time_init(void) { struct timespec ts; unsigned long flags; - cycle_t now; /* Reset time synchronization interfaces. */ etr_reset(); @@ -266,20 +262,10 @@ void __init time_init(void) panic("Could not register TOD clock source"); /* - * The TOD clock is an accurate clock. The xtime should be - * initialized in a way that the difference between TOD and - * xtime is reasonably small. Too bad that timekeeping_init - * sets xtime.tv_nsec to zero. In addition the clock source - * change from the jiffies clock source to the TOD clock - * source add another error of up to 1/HZ second. The same - * function sets wall_to_monotonic to a value that is too - * small for /proc/uptime to be accurate. - * Reset xtime and wall_to_monotonic to sane values. + * Reset wall_to_monotonic to the initial timestamp created + * in head.S to get a precise value in /proc/uptime. */ write_seqlock_irqsave(&xtime_lock, flags); - now = get_clock(); - tod_to_timeval(now - TOD_UNIX_EPOCH, &xtime); - clocksource_tod.cycle_last = now; tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, &ts); set_normalized_timespec(&wall_to_monotonic, -ts.tv_sec, -ts.tv_nsec); write_sequnlock_irqrestore(&xtime_lock, flags); diff --git a/arch/sh/kernel/time.c b/arch/sh/kernel/time.c index 9b352a1e3fb..3f4706aa975 100644 --- a/arch/sh/kernel/time.c +++ b/arch/sh/kernel/time.c @@ -39,11 +39,9 @@ void (*rtc_sh_get_time)(struct timespec *) = null_rtc_get_time; int (*rtc_sh_set_time)(const time_t) = null_rtc_set_time; #ifdef CONFIG_GENERIC_CMOS_UPDATE -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { - struct timespec tv; - rtc_sh_get_time(&tv); - return tv.tv_sec; + rtc_sh_get_time(&ts); } int update_persistent_clock(struct timespec now) diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 5d465b207e7..bf67dcb4a44 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -178,7 +178,7 @@ static int set_rtc_mmss(unsigned long nowtime) } /* not static: needed by APM */ -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { unsigned long retval, flags; @@ -186,7 +186,8 @@ unsigned long read_persistent_clock(void) retval = get_wallclock(); spin_unlock_irqrestore(&rtc_lock, flags); - return retval; + ts->tv_sec = retval; + ts->tv_nsec = 0; } int update_persistent_clock(struct timespec now) diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index 8848120d291..19085ff0484 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -59,9 +59,8 @@ static struct irqaction timer_irqaction = { void __init time_init(void) { - xtime.tv_nsec = 0; - xtime.tv_sec = read_persistent_clock(); - + /* FIXME: xtime&wall_to_monotonic are set in timekeeping_init. */ + read_persistent_clock(&xtime); set_normalized_timespec(&wall_to_monotonic, -xtime.tv_sec, -xtime.tv_nsec); diff --git a/include/linux/time.h b/include/linux/time.h index e7c84455888..53a3216f0d1 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -101,7 +101,7 @@ extern struct timespec xtime; extern struct timespec wall_to_monotonic; extern seqlock_t xtime_lock; -extern unsigned long read_persistent_clock(void); +extern void read_persistent_clock(struct timespec *ts); extern int update_persistent_clock(struct timespec now); extern int no_sync_cmos_clock __read_mostly; void timekeeping_init(void); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 41579e7fcf9..f1a21ce491e 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -154,7 +154,7 @@ __cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock); */ struct timespec xtime __attribute__ ((aligned (16))); struct timespec wall_to_monotonic __attribute__ ((aligned (16))); -static unsigned long total_sleep_time; /* seconds */ +static struct timespec total_sleep_time; /* * The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. @@ -487,17 +487,18 @@ int timekeeping_valid_for_hres(void) } /** - * read_persistent_clock - Return time in seconds from the persistent clock. + * read_persistent_clock - Return time from the persistent clock. * * Weak dummy function for arches that do not yet support it. - * Returns seconds from epoch using the battery backed persistent clock. - * Returns zero if unsupported. + * Reads the time from the battery backed persistent clock. + * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. * * XXX - Do be sure to remove it once all arches implement it. */ -unsigned long __attribute__((weak)) read_persistent_clock(void) +void __attribute__((weak)) read_persistent_clock(struct timespec *ts) { - return 0; + ts->tv_sec = 0; + ts->tv_nsec = 0; } /* @@ -507,7 +508,9 @@ void __init timekeeping_init(void) { struct clocksource *clock; unsigned long flags; - unsigned long sec = read_persistent_clock(); + struct timespec now; + + read_persistent_clock(&now); write_seqlock_irqsave(&xtime_lock, flags); @@ -518,19 +521,20 @@ void __init timekeeping_init(void) clock->enable(clock); timekeeper_setup_internals(clock); - xtime.tv_sec = sec; - xtime.tv_nsec = 0; + xtime.tv_sec = now.tv_sec; + xtime.tv_nsec = now.tv_nsec; raw_time.tv_sec = 0; raw_time.tv_nsec = 0; set_normalized_timespec(&wall_to_monotonic, -xtime.tv_sec, -xtime.tv_nsec); update_xtime_cache(0); - total_sleep_time = 0; + total_sleep_time.tv_sec = 0; + total_sleep_time.tv_nsec = 0; write_sequnlock_irqrestore(&xtime_lock, flags); } /* time in seconds when suspend began */ -static unsigned long timekeeping_suspend_time; +static struct timespec timekeeping_suspend_time; /** * timekeeping_resume - Resumes the generic timekeeping subsystem. @@ -543,18 +547,19 @@ static unsigned long timekeeping_suspend_time; static int timekeeping_resume(struct sys_device *dev) { unsigned long flags; - unsigned long now = read_persistent_clock(); + struct timespec ts; + + read_persistent_clock(&ts); clocksource_resume(); write_seqlock_irqsave(&xtime_lock, flags); - if (now && (now > timekeeping_suspend_time)) { - unsigned long sleep_length = now - timekeeping_suspend_time; - - xtime.tv_sec += sleep_length; - wall_to_monotonic.tv_sec -= sleep_length; - total_sleep_time += sleep_length; + if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) { + ts = timespec_sub(ts, timekeeping_suspend_time); + xtime = timespec_add_safe(xtime, ts); + wall_to_monotonic = timespec_sub(wall_to_monotonic, ts); + total_sleep_time = timespec_add_safe(total_sleep_time, ts); } update_xtime_cache(0); /* re-base the last cycle value */ @@ -577,7 +582,7 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state) { unsigned long flags; - timekeeping_suspend_time = read_persistent_clock(); + read_persistent_clock(&timekeeping_suspend_time); write_seqlock_irqsave(&xtime_lock, flags); timekeeping_forward_now(); @@ -801,9 +806,10 @@ void update_wall_time(void) */ void getboottime(struct timespec *ts) { - set_normalized_timespec(ts, - - (wall_to_monotonic.tv_sec + total_sleep_time), - - wall_to_monotonic.tv_nsec); + struct timespec boottime; + + boottime = timespec_add_safe(wall_to_monotonic, total_sleep_time); + set_normalized_timespec(ts, -boottime.tv_sec, -boottime.tv_nsec); } /** @@ -812,7 +818,7 @@ void getboottime(struct timespec *ts) */ void monotonic_to_bootbased(struct timespec *ts) { - ts->tv_sec += total_sleep_time; + *ts = timespec_add_safe(*ts, total_sleep_time); } unsigned long get_seconds(void) -- cgit v1.2.3-70-g09d2 From 8cab02dc3c58a12235c6d463ce684dded9696848 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 18:19:45 +0200 Subject: x86: Do not unregister PIT clocksource on PIT oneshot setup/shutdown This basically reverts commit 1a0c009ac (x86: unregister PIT clocksource when PIT is disabled) because the problem which was tried to address with that patch has been solved by commit 3f68535ada (clocksource: sanity check sysfs clocksource changes). The problem addressed by the original patch is that PIT could be selected as clocksource after the system switched the PIT off or set the PIT into one shot mode which would result in complete timekeeping wreckage. Now with the sysfs sanity check in place PIT cannot be selected again when the system is in oneshot mode. The system will not switch to one shot mode as long as PIT is installed because PIT is not suitable for one shot. The shutdown case which happens when the lapic timer is installed is covered by the fact that init_pit_clocksource() is called after the lapic timer take over and then does not install the PIT clocksource at all. We should have done the sanity checks back then, but ... This also solves the locking problem which was reported vs. the clocksource rework. LKML-Reference: Cc: Martin Schwidefsky Cc: john stultz Signed-off-by: Thomas Gleixner --- arch/x86/kernel/i8253.c | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 5cf36c053ac..23c167925a5 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -19,12 +19,6 @@ DEFINE_SPINLOCK(i8253_lock); EXPORT_SYMBOL(i8253_lock); -#ifdef CONFIG_X86_32 -static void pit_disable_clocksource(void); -#else -static inline void pit_disable_clocksource(void) { } -#endif - /* * HPET replaces the PIT, when enabled. So we need to know, which of * the two timers is used @@ -57,12 +51,10 @@ static void init_pit_timer(enum clock_event_mode mode, outb_pit(0, PIT_CH0); outb_pit(0, PIT_CH0); } - pit_disable_clocksource(); break; case CLOCK_EVT_MODE_ONESHOT: /* One shot setup */ - pit_disable_clocksource(); outb_pit(0x38, PIT_MODE); break; @@ -200,17 +192,6 @@ static struct clocksource pit_cs = { .shift = 20, }; -static void pit_disable_clocksource(void) -{ - /* - * Use mult to check whether it is registered or not - */ - if (pit_cs.mult) { - clocksource_unregister(&pit_cs); - pit_cs.mult = 0; - } -} - static int __init init_pit_clocksource(void) { /* -- cgit v1.2.3-70-g09d2 From da15cfdae03351c689736f8d142618592e3cebc3 Mon Sep 17 00:00:00 2001 From: john stultz Date: Wed, 19 Aug 2009 19:13:34 -0700 Subject: time: Introduce CLOCK_REALTIME_COARSE After talking with some application writers who want very fast, but not fine-grained timestamps, I decided to try to implement new clock_ids to clock_gettime(): CLOCK_REALTIME_COARSE and CLOCK_MONOTONIC_COARSE which returns the time at the last tick. This is very fast as we don't have to access any hardware (which can be very painful if you're using something like the acpi_pm clocksource), and we can even use the vdso clock_gettime() method to avoid the syscall. The only trade off is you only get low-res tick grained time resolution. This isn't a new idea, I know Ingo has a patch in the -rt tree that made the vsyscall gettimeofday() return coarse grained time when the vsyscall64 sysctrl was set to 2. However this affects all applications on a system. With this method, applications can choose the proper speed/granularity trade-off for themselves. Signed-off-by: John Stultz Cc: Andi Kleen Cc: nikolag@ca.ibm.com Cc: Darren Hart Cc: arjan@infradead.org Cc: jonathan@jonmasters.org LKML-Reference: <1250734414.6897.5.camel@localhost.localdomain> Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/vgtod.h | 1 + arch/x86/kernel/vsyscall_64.c | 1 + arch/x86/vdso/vclock_gettime.c | 39 ++++++++++++++++++++++++++++++++++++--- include/linux/time.h | 4 ++++ kernel/posix-timers.c | 35 +++++++++++++++++++++++++++++++++++ kernel/time/timekeeping.c | 21 +++++++++++++++++++++ 6 files changed, 98 insertions(+), 3 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index dc27a69e5d2..3d61e204826 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -21,6 +21,7 @@ struct vsyscall_gtod_data { u32 shift; } clock; struct timespec wall_to_monotonic; + struct timespec wall_time_coarse; }; extern struct vsyscall_gtod_data __vsyscall_gtod_data __section_vsyscall_gtod_data; diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 25ee06a80aa..cf53a78e2dc 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -87,6 +87,7 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock) vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec; vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec; vsyscall_gtod_data.wall_to_monotonic = wall_to_monotonic; + vsyscall_gtod_data.wall_time_coarse = __current_kernel_time(); write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags); } diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 6a40b78b46a..ee55754cc3c 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -86,14 +86,47 @@ notrace static noinline int do_monotonic(struct timespec *ts) return 0; } +notrace static noinline int do_realtime_coarse(struct timespec *ts) +{ + unsigned long seq; + do { + seq = read_seqbegin(>od->lock); + ts->tv_sec = gtod->wall_time_coarse.tv_sec; + ts->tv_nsec = gtod->wall_time_coarse.tv_nsec; + } while (unlikely(read_seqretry(>od->lock, seq))); + return 0; +} + +notrace static noinline int do_monotonic_coarse(struct timespec *ts) +{ + unsigned long seq, ns, secs; + do { + seq = read_seqbegin(>od->lock); + secs = gtod->wall_time_coarse.tv_sec; + ns = gtod->wall_time_coarse.tv_nsec; + secs += gtod->wall_to_monotonic.tv_sec; + ns += gtod->wall_to_monotonic.tv_nsec; + } while (unlikely(read_seqretry(>od->lock, seq))); + vset_normalized_timespec(ts, secs, ns); + return 0; +} + notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) { - if (likely(gtod->sysctl_enabled && gtod->clock.vread)) + if (likely(gtod->sysctl_enabled)) switch (clock) { case CLOCK_REALTIME: - return do_realtime(ts); + if (likely(gtod->clock.vread)) + return do_realtime(ts); + break; case CLOCK_MONOTONIC: - return do_monotonic(ts); + if (likely(gtod->clock.vread)) + return do_monotonic(ts); + break; + case CLOCK_REALTIME_COARSE: + return do_realtime_coarse(ts); + case CLOCK_MONOTONIC_COARSE: + return do_monotonic_coarse(ts); } return vdso_fallback_gettime(clock, ts); } diff --git a/include/linux/time.h b/include/linux/time.h index f505988398e..256232f7e5e 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -110,6 +110,8 @@ extern int timekeeping_suspended; unsigned long get_seconds(void); struct timespec current_kernel_time(void); +struct timespec __current_kernel_time(void); /* does not hold xtime_lock */ +struct timespec get_monotonic_coarse(void); #define CURRENT_TIME (current_kernel_time()) #define CURRENT_TIME_SEC ((struct timespec) { get_seconds(), 0 }) @@ -243,6 +245,8 @@ struct itimerval { #define CLOCK_PROCESS_CPUTIME_ID 2 #define CLOCK_THREAD_CPUTIME_ID 3 #define CLOCK_MONOTONIC_RAW 4 +#define CLOCK_REALTIME_COARSE 5 +#define CLOCK_MONOTONIC_COARSE 6 /* * The IDs of various hardware clocks: diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index d089d052c4a..495440779ce 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -242,6 +242,25 @@ static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp) return 0; } + +static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec *tp) +{ + *tp = current_kernel_time(); + return 0; +} + +static int posix_get_monotonic_coarse(clockid_t which_clock, + struct timespec *tp) +{ + *tp = get_monotonic_coarse(); + return 0; +} + +int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp) +{ + *tp = ktime_to_timespec(KTIME_LOW_RES); + return 0; +} /* * Initialize everything, well, just everything in Posix clocks/timers ;) */ @@ -262,10 +281,26 @@ static __init int init_posix_timers(void) .timer_create = no_timer_create, .nsleep = no_nsleep, }; + struct k_clock clock_realtime_coarse = { + .clock_getres = posix_get_coarse_res, + .clock_get = posix_get_realtime_coarse, + .clock_set = do_posix_clock_nosettime, + .timer_create = no_timer_create, + .nsleep = no_nsleep, + }; + struct k_clock clock_monotonic_coarse = { + .clock_getres = posix_get_coarse_res, + .clock_get = posix_get_monotonic_coarse, + .clock_set = do_posix_clock_nosettime, + .timer_create = no_timer_create, + .nsleep = no_nsleep, + }; register_posix_clock(CLOCK_REALTIME, &clock_realtime); register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic); register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw); + register_posix_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse); + register_posix_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse); posix_timers_cache = kmem_cache_create("posix_timers_cache", sizeof (struct k_itimer), 0, SLAB_PANIC, diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 15e06defca5..03cbeb34d14 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -847,6 +847,10 @@ unsigned long get_seconds(void) } EXPORT_SYMBOL(get_seconds); +struct timespec __current_kernel_time(void) +{ + return xtime_cache; +} struct timespec current_kernel_time(void) { @@ -862,3 +866,20 @@ struct timespec current_kernel_time(void) return now; } EXPORT_SYMBOL(current_kernel_time); + +struct timespec get_monotonic_coarse(void) +{ + struct timespec now, mono; + unsigned long seq; + + do { + seq = read_seqbegin(&xtime_lock); + + now = xtime_cache; + mono = wall_to_monotonic; + } while (read_seqretry(&xtime_lock, seq)); + + set_normalized_timespec(&now, now.tv_sec + mono.tv_sec, + now.tv_nsec + mono.tv_nsec); + return now; +} -- cgit v1.2.3-70-g09d2 From 57844a8f8e29802f37ad9a0f94eb11d6ae358603 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 19 Aug 2009 14:48:38 +0200 Subject: x86: Add x86_init infrastructure The upcoming Moorestown support brings the embedded world to x86. The setup code of x86 has already a couple of hooks which are either x86_quirks or paravirt ops. Some of those setup hooks are pretty convoluted like the timer setup and the tsc calibration code. But there are other places which could do with a cleanup. Instead of having inline functions/macros which are modified at compile time I decided to introduce x86_init ops which are unconditional in the code and make it clear that they can be changed either during compile time or in the early boot process. The function pointers are initialized by default functions which can be noops so that the pointer can be called unconditionally in the most cases. This also allows us to remove 32bit/64bit, paravirt and other #ifdeffery. paravirt guests are just a hardware platform in the setup code, so we should treat them as such and not hide all behind multiple layers of indirection and compile time dependencies. It's more obvious that x86_init.timers.timer_init() is a function pointer than the late_time_init = choose_time_init() obscurity. It's also way simpler to grep for x86_init.timers.timer_init and find all the places which modify that function pointer instead of analyzing weak functions, macros and paravirt indirections. Note. This is not a general paravirt_ops replacement. It just will move setup related hooks which are potentially useful for other platform setup purposes as well out of the paravirt domain. Add the base infrastructure without any functionality. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/setup.h | 2 ++ arch/x86/include/asm/x86_init.h | 15 +++++++++++++++ arch/x86/kernel/Makefile | 2 +- arch/x86/kernel/x86_init.c | 17 +++++++++++++++++ 4 files changed, 35 insertions(+), 1 deletion(-) create mode 100644 arch/x86/include/asm/x86_init.h create mode 100644 arch/x86/kernel/x86_init.c (limited to 'arch/x86') diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 4093d1ed6db..741e2956f3c 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -7,6 +7,8 @@ #ifndef __ASSEMBLY__ +#include + /* * Any setup quirks to be performed? */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h new file mode 100644 index 00000000000..14d11071675 --- /dev/null +++ b/arch/x86/include/asm/x86_init.h @@ -0,0 +1,15 @@ +#ifndef _ASM_X86_PLATFORM_H +#define _ASM_X86_PLATFORM_H + +/** + * struct x86_init_ops - functions for platform specific setup + * + */ +struct x86_init_ops { +}; + +extern struct x86_init_ops x86_init; + +extern void x86_init_noop(void); + +#endif diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 430d5b24af7..313ed6fca9b 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -32,7 +32,7 @@ GCOV_PROFILE_paravirt.o := n obj-y := process_$(BITS).o signal.o entry_$(BITS).o obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time_$(BITS).o ioport.o ldt.o dumpstack.o -obj-y += setup.o i8259.o irqinit.o +obj-y += setup.o x86_init.o i8259.o irqinit.o obj-$(CONFIG_X86_VISWS) += visws_quirks.o obj-$(CONFIG_X86_32) += probe_roms_32.o obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c new file mode 100644 index 00000000000..82d510c9c99 --- /dev/null +++ b/arch/x86/kernel/x86_init.c @@ -0,0 +1,17 @@ +/* + * Copyright (C) 2009 Thomas Gleixner + * + * For licencing details see kernel-base/COPYING + */ +#include + +#include + +void __cpuinit x86_init_noop(void) { } + +/* + * The platform setup functions are preset with the default functions + * for standard PC hardware. + */ +struct __initdata x86_init_ops x86_init = { +}; -- cgit v1.2.3-70-g09d2 From f7cf5a5b8c0e59eac8d30b62271cb0fa52e53ebc Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 19 Aug 2009 14:43:56 +0200 Subject: x86: Add probe_roms to x86_init probe_roms is only used on 32bit. Add it to the x86_init ops and remove the #ifdefs. Default initializer is x86_init_noop() which is overridden in the 32bit boot code. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/x86_init.h | 10 ++++++++++ arch/x86/kernel/head32.c | 3 +++ arch/x86/kernel/setup.c | 4 +--- arch/x86/kernel/x86_init.c | 4 ++++ 4 files changed, 18 insertions(+), 3 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 14d11071675..75e9e68d635 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -1,11 +1,21 @@ #ifndef _ASM_X86_PLATFORM_H #define _ASM_X86_PLATFORM_H +/** + * struct x86_init_resources - platform specific resource related ops + * @probe_roms: probe BIOS roms + * + */ +struct x86_init_resources { + void (*probe_roms)(void); +}; + /** * struct x86_init_ops - functions for platform specific setup * */ struct x86_init_ops { + struct x86_init_resources resources; }; extern struct x86_init_ops x86_init; diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 3f8579f8d42..4049353152c 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -29,6 +29,9 @@ void __init i386_start_kernel(void) reserve_early(ramdisk_image, ramdisk_end, "RAMDISK"); } #endif + /* Initilize 32bit specific setup functions */ + x86_init.resources.probe_roms = probe_roms; + reserve_ebda_region(); /* diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 63f32d220ef..5796eb158d4 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -835,9 +835,7 @@ void __init setup_arch(char **cmdline_p) */ init_hypervisor(&boot_cpu_data); -#ifdef CONFIG_X86_32 - probe_roms(); -#endif + x86_init.resources.probe_roms(); /* after parse_early_param, so could debug it */ insert_resource(&iomem_resource, &code_resource); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 82d510c9c99..88883f8006c 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -14,4 +14,8 @@ void __cpuinit x86_init_noop(void) { } * for standard PC hardware. */ struct __initdata x86_init_ops x86_init = { + + .resources = { + .probe_roms = x86_init_noop, + }, }; -- cgit v1.2.3-70-g09d2 From 8fee697d990c54976c8dc167270633299e2515d2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 19 Aug 2009 14:55:50 +0200 Subject: x86: Add request_standard_resources to x86_init The 32bit and the 64bit code are slighty different in the reservation of standard resources. Also the upcoming Moorestown support needs its own version of that. Add it to x86_init_ops and initialize it with the 64bit default. 32bit overrides it in early boot. Now moorestown can add it's own override w/o sprinkling the code with more #ifdefs Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/setup.h | 3 +++ arch/x86/include/asm/x86_init.h | 3 +++ arch/x86/kernel/head32.c | 1 + arch/x86/kernel/setup.c | 28 ++++++++++++++++------------ arch/x86/kernel/x86_init.c | 3 ++- 5 files changed, 25 insertions(+), 13 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 741e2956f3c..19769ac6061 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -88,6 +88,9 @@ extern unsigned long saved_video_mode; #define paravirt_post_allocator_init() do {} while (0) #endif +extern void reserve_standard_io_resources(void); +extern void i386_reserve_resources(void); + #ifndef _SETUP /* diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 75e9e68d635..d0d9be25ed9 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -4,10 +4,13 @@ /** * struct x86_init_resources - platform specific resource related ops * @probe_roms: probe BIOS roms + * @reserve_resources: reserve the standard resources for the + * platform * */ struct x86_init_resources { void (*probe_roms)(void); + void (*reserve_resources)(void); }; /** diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 4049353152c..d91c37c0206 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -31,6 +31,7 @@ void __init i386_start_kernel(void) #endif /* Initilize 32bit specific setup functions */ x86_init.resources.probe_roms = probe_roms; + x86_init.resources.reserve_resources = i386_reserve_resources; reserve_ebda_region(); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 5796eb158d4..c2a8090e831 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -171,13 +171,6 @@ static struct resource bss_resource = { #ifdef CONFIG_X86_32 -static struct resource video_ram_resource = { - .name = "Video RAM area", - .start = 0xa0000, - .end = 0xbffff, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM -}; - /* cpu data as detected by the assembly code in head.S */ struct cpuinfo_x86 new_cpu_data __cpuinitdata = {0, 0, 0, 0, -1, 1, 0, 0, -1}; /* common cpu data for all cpus */ @@ -605,7 +598,7 @@ static struct resource standard_io_resources[] = { .flags = IORESOURCE_BUSY | IORESOURCE_IO } }; -static void __init reserve_standard_io_resources(void) +void __init reserve_standard_io_resources(void) { int i; @@ -1013,10 +1006,7 @@ void __init setup_arch(char **cmdline_p) e820_reserve_resources(); e820_mark_nosave_regions(max_low_pfn); -#ifdef CONFIG_X86_32 - request_resource(&iomem_resource, &video_ram_resource); -#endif - reserve_standard_io_resources(); + x86_init.resources.reserve_resources(); e820_setup_gap(); @@ -1102,4 +1092,18 @@ void __init x86_quirk_time_init(void) irq0.mask = cpumask_of_cpu(0); setup_irq(0, &irq0); } + +static struct resource video_ram_resource = { + .name = "Video RAM area", + .start = 0xa0000, + .end = 0xbffff, + .flags = IORESOURCE_BUSY | IORESOURCE_MEM +}; + +void __init i386_reserve_resources(void) +{ + request_resource(&iomem_resource, &video_ram_resource); + reserve_standard_io_resources(); +} + #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 88883f8006c..68c093b67ec 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -5,7 +5,7 @@ */ #include -#include +#include void __cpuinit x86_init_noop(void) { } @@ -17,5 +17,6 @@ struct __initdata x86_init_ops x86_init = { .resources = { .probe_roms = x86_init_noop, + .reserve_resources = reserve_standard_io_resources, }, }; -- cgit v1.2.3-70-g09d2 From 816c25e7d4fb6fd40022a376e8b7f45b1edf5a89 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 19 Aug 2009 14:36:27 +0200 Subject: x86: Add reserve_ebda_region to x86_init_ops reserve_ebda_region needs to be called befor start_kernel. Moorestown needs to override it. Make it a x86_init_ops function and initialize it with the default reserve_ebda_region. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/x86_init.h | 2 ++ arch/x86/kernel/head32.c | 4 ++-- arch/x86/kernel/head64.c | 3 +-- arch/x86/kernel/x86_init.c | 2 ++ 4 files changed, 7 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index d0d9be25ed9..8a971cb3dd3 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -6,11 +6,13 @@ * @probe_roms: probe BIOS roms * @reserve_resources: reserve the standard resources for the * platform + * @reserve_ebda_region: reserve the extended bios data area * */ struct x86_init_resources { void (*probe_roms)(void); void (*reserve_resources)(void); + void (*reserve_ebda_region)(void); }; /** diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index d91c37c0206..921a23b6c14 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include void __init i386_start_kernel(void) @@ -33,7 +33,7 @@ void __init i386_start_kernel(void) x86_init.resources.probe_roms = probe_roms; x86_init.resources.reserve_resources = i386_reserve_resources; - reserve_ebda_region(); + x86_init.resources.reserve_ebda_region(); /* * At this point everything still needed from the boot loader diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 70eaa852c73..cead8149c3d 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -23,7 +23,6 @@ #include #include #include -#include #include static void __init zap_identity_mappings(void) @@ -112,7 +111,7 @@ void __init x86_64_start_reservations(char *real_mode_data) } #endif - reserve_ebda_region(); + x86_init.resources.reserve_ebda_region(); /* * At this point everything still needed from the boot loader diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 68c093b67ec..1fff49a6858 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -5,6 +5,7 @@ */ #include +#include #include void __cpuinit x86_init_noop(void) { } @@ -18,5 +19,6 @@ struct __initdata x86_init_ops x86_init = { .resources = { .probe_roms = x86_init_noop, .reserve_resources = reserve_standard_io_resources, + .reserve_ebda_region = reserve_ebda_region, }, }; -- cgit v1.2.3-70-g09d2 From 6b18ae3e2ff62daa9f181401759161dd8de0aadf Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 10:19:54 +0200 Subject: x86: Move memory_setup to x86_init_ops memory_setup is overridden by x86_quirks and by paravirts with weak functions and quirks. Unify the whole mess and make it an unconditional x86_init_ops function which defaults to the standard function and can be overridden by the early platform code. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/e820.h | 2 -- arch/x86/include/asm/paravirt_types.h | 1 - arch/x86/include/asm/setup.h | 1 - arch/x86/include/asm/x86_init.h | 2 ++ arch/x86/kernel/apic/numaq_32.c | 1 - arch/x86/kernel/e820.c | 19 +------------------ arch/x86/kernel/paravirt.c | 6 ------ arch/x86/kernel/visws_quirks.c | 3 ++- arch/x86/kernel/x86_init.c | 2 ++ arch/x86/lguest/boot.c | 3 ++- arch/x86/xen/enlighten.c | 3 ++- 11 files changed, 11 insertions(+), 32 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 7ecba4d8508..40b4e614fe7 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -126,8 +126,6 @@ extern void e820_reserve_resources(void); extern void e820_reserve_resources_late(void); extern void setup_memory_map(void); extern char *default_machine_specific_memory_setup(void); -extern char *machine_specific_memory_setup(void); -extern char *memory_setup(void); #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 2b3371bae29..6d668968b6b 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -81,7 +81,6 @@ struct pv_init_ops { /* Basic arch-specific setup */ void (*arch_setup)(void); - char *(*memory_setup)(void); void (*post_allocator_init)(void); /* Print a banner to identify the environment */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 19769ac6061..9cba9d6ca88 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -22,7 +22,6 @@ struct x86_quirks { int (*arch_pre_intr_init)(void); int (*arch_intr_init)(void); int (*arch_trap_init)(void); - char * (*arch_memory_setup)(void); int (*mach_get_smp_config)(unsigned int early); int (*mach_find_smp_config)(unsigned int reserve); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 8a971cb3dd3..6c084f2a6c3 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -7,12 +7,14 @@ * @reserve_resources: reserve the standard resources for the * platform * @reserve_ebda_region: reserve the extended bios data area + * @memory_setup: platform specific memory setup * */ struct x86_init_resources { void (*probe_roms)(void); void (*reserve_resources)(void); void (*reserve_ebda_region)(void); + char *(*memory_setup)(void); }; /** diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index ca96e68f0d2..403c062f69e 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -260,7 +260,6 @@ static struct x86_quirks numaq_x86_quirks __initdata = { .arch_pre_time_init = numaq_pre_time_init, .arch_time_init = NULL, .arch_pre_intr_init = NULL, - .arch_memory_setup = NULL, .arch_intr_init = NULL, .arch_trap_init = NULL, .mach_get_smp_config = NULL, diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 5cb5725b2ba..0d804b907e8 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1455,28 +1455,11 @@ char *__init default_machine_specific_memory_setup(void) return who; } -char *__init __attribute__((weak)) machine_specific_memory_setup(void) -{ - if (x86_quirks->arch_memory_setup) { - char *who = x86_quirks->arch_memory_setup(); - - if (who) - return who; - } - return default_machine_specific_memory_setup(); -} - -/* Overridden in paravirt.c if CONFIG_PARAVIRT */ -char * __init __attribute__((weak)) memory_setup(void) -{ - return machine_specific_memory_setup(); -} - void __init setup_memory_map(void) { char *who; - who = memory_setup(); + who = x86_init.resources.memory_setup(); memcpy(&e820_saved, &e820, sizeof(struct e820map)); printk(KERN_INFO "BIOS-provided physical RAM map:\n"); e820_print_map(who); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 70ec9b951d7..532c9a2626c 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -60,11 +60,6 @@ static void __init default_banner(void) pv_info.name); } -char *memory_setup(void) -{ - return pv_init_ops.memory_setup(); -} - /* Simple instruction patching code. */ #define DEF_NATIVE(ops, name, code) \ extern const char start_##ops##_##name[], end_##ops##_##name[]; \ @@ -322,7 +317,6 @@ struct pv_init_ops pv_init_ops = { .patch = native_patch, .banner = default_banner, .arch_setup = paravirt_nop, - .memory_setup = machine_specific_memory_setup, }; struct pv_time_ops pv_time_ops = { diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c index 31ffc24eec4..97c670df1ae 100644 --- a/arch/x86/kernel/visws_quirks.c +++ b/arch/x86/kernel/visws_quirks.c @@ -239,7 +239,6 @@ static int visws_trap_init(void); static struct x86_quirks visws_x86_quirks __initdata = { .arch_time_init = visws_time_init, .arch_pre_intr_init = visws_pre_intr_init, - .arch_memory_setup = visws_memory_setup, .arch_intr_init = NULL, .arch_trap_init = visws_trap_init, .mach_get_smp_config = visws_get_smp_config, @@ -263,6 +262,8 @@ void __init visws_early_detect(void) */ x86_quirks = &visws_x86_quirks; + x86_init.resources.memory_setup = visws_memory_setup; + /* * Install reboot quirks: */ diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 1fff49a6858..1965bff3489 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -7,6 +7,7 @@ #include #include +#include void __cpuinit x86_init_noop(void) { } @@ -20,5 +21,6 @@ struct __initdata x86_init_ops x86_init = { .probe_roms = x86_init_noop, .reserve_resources = reserve_standard_io_resources, .reserve_ebda_region = reserve_ebda_region, + .memory_setup = default_machine_specific_memory_setup, }, }; diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index d677fa9ca65..11445c176de 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1270,7 +1270,6 @@ __init void lguest_init(void) pv_irq_ops.safe_halt = lguest_safe_halt; /* Setup operations */ - pv_init_ops.memory_setup = lguest_memory_setup; pv_init_ops.patch = lguest_patch; /* Intercepts of various CPU instructions */ @@ -1325,6 +1324,8 @@ __init void lguest_init(void) pv_time_ops.time_init = lguest_time_init; pv_time_ops.get_tsc_khz = lguest_tsc_khz; + x86_init.resources.memory_setup = lguest_memory_setup; + /* * Now is a good time to look at the implementations of these functions * before returning to the rest of lguest_init(). diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index e90540a46a0..50b20c64f0b 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -841,7 +841,6 @@ static const struct pv_init_ops xen_init_ops __initdata = { .patch = xen_patch, .banner = xen_banner, - .memory_setup = xen_memory_setup, .arch_setup = xen_arch_setup, .post_allocator_init = xen_post_allocator_init, }; @@ -982,6 +981,8 @@ asmlinkage void __init xen_start_kernel(void) pv_apic_ops = xen_apic_ops; pv_mmu_ops = xen_mmu_ops; + x86_init.resources.memory_setup = xen_memory_setup; + #ifdef CONFIG_X86_64 /* * Setup percpu state. We only need to do this for 64-bit -- cgit v1.2.3-70-g09d2 From f4848472cd99487e182b64fb2a5d0e4fedbe86ad Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 12:05:01 +0200 Subject: x86: Sanitize smp_record and move it to x86_init_ops The x86 quirkification introduced an extra ugly hackery with a variable pointer in the mpparse code. If the pointer is initialized then it is dereferenced and the variable set to 0 or incremented. Create a x86_init_ops function and let the affected numaq code hold the function. Default init is a setup noop. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/setup.h | 1 - arch/x86/include/asm/x86_init.h | 12 +++++++++++- arch/x86/kernel/apic/numaq_32.c | 19 ++++++++++++++++--- arch/x86/kernel/mpparse.c | 6 ++---- arch/x86/kernel/x86_init.c | 5 +++++ 5 files changed, 34 insertions(+), 9 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 9cba9d6ca88..bbf2dfd59b4 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -25,7 +25,6 @@ struct x86_quirks { int (*mach_get_smp_config)(unsigned int early); int (*mach_find_smp_config)(unsigned int reserve); - int *mpc_record; int (*mpc_apic_id)(struct mpc_cpu *m); void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name); void (*mpc_oem_pci_bus)(struct mpc_bus *m); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 6c084f2a6c3..10b297b1881 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -1,6 +1,14 @@ #ifndef _ASM_X86_PLATFORM_H #define _ASM_X86_PLATFORM_H +/** + * struct x86_init_mpparse - platform specific mpparse ops + * @mpc_record: platform specific mpc record accounting + */ +struct x86_init_mpparse { + void (*mpc_record)(unsigned int mode); +}; + /** * struct x86_init_resources - platform specific resource related ops * @probe_roms: probe BIOS roms @@ -22,11 +30,13 @@ struct x86_init_resources { * */ struct x86_init_ops { - struct x86_init_resources resources; + struct x86_init_resources resources; + struct x86_init_mpparse mpparse; }; extern struct x86_init_ops x86_init; extern void x86_init_noop(void); +extern void x86_init_uint_noop(unsigned int unused); #endif diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index 403c062f69e..b5f0b1dc7dd 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -66,7 +66,6 @@ struct mpc_trans { unsigned short trans_reserved; }; -/* x86_quirks member */ static int mpc_record; static struct mpc_trans *translation_table[MAX_MPC_ENTRY]; @@ -177,6 +176,19 @@ static void mpc_oem_pci_bus(struct mpc_bus *m) quad_local_to_mp_bus_id[quad][local] = m->busid; } +/* + * Called from mpparse code. + * mode = 0: prescan + * mode = 1: one mpc entry scanned + */ +static void numaq_mpc_record(unsigned int mode) +{ + if (!mode) + mpc_record = 0; + else + mpc_record++; +} + static void __init MP_translation_info(struct mpc_trans *m) { printk(KERN_INFO @@ -264,7 +276,6 @@ static struct x86_quirks numaq_x86_quirks __initdata = { .arch_trap_init = NULL, .mach_get_smp_config = NULL, .mach_find_smp_config = NULL, - .mpc_record = &mpc_record, .mpc_apic_id = mpc_apic_id, .mpc_oem_bus_info = mpc_oem_bus_info, .mpc_oem_pci_bus = mpc_oem_pci_bus, @@ -285,8 +296,10 @@ static __init void early_check_numaq(void) if (smp_found_config) early_get_smp_config(); - if (found_numaq) + if (found_numaq) { x86_quirks = &numaq_x86_quirks; + x86_init.mpparse.mpc_record = numaq_mpc_record; + } } int __init get_memcfg_numaq(void) diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 651c93b2886..b2179fdf0ff 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -320,8 +320,7 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) /* * Now process the configuration blocks. */ - if (x86_quirks->mpc_record) - *x86_quirks->mpc_record = 0; + x86_init.mpparse.mpc_record(0); while (count < mpc->length) { switch (*mpt) { @@ -353,8 +352,7 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) count = mpc->length; break; } - if (x86_quirks->mpc_record) - (*x86_quirks->mpc_record)++; + x86_init.mpparse.mpc_record(1); } #ifdef CONFIG_X86_BIGSMP diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 1965bff3489..83bd5db376b 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -10,6 +10,7 @@ #include void __cpuinit x86_init_noop(void) { } +void __init x86_init_uint_noop(unsigned int unused) { } /* * The platform setup functions are preset with the default functions @@ -23,4 +24,8 @@ struct __initdata x86_init_ops x86_init = { .reserve_ebda_region = reserve_ebda_region, .memory_setup = default_machine_specific_memory_setup, }, + + .mpparse = { + .mpc_record = x86_init_uint_noop, + }, }; -- cgit v1.2.3-70-g09d2 From de93410310952fb7b705f784ef22493c8362dbe8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 09:27:29 +0200 Subject: x86: Move ioapic_ids_setup to x86_init_ops 32bit and also the numaq code have special requirements on the ioapic_id setup. Convert it to a x86_init_ops function and get rid of the quirks and #ifdefs Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/io_apic.h | 3 ++- arch/x86/include/asm/setup.h | 1 - arch/x86/include/asm/x86_init.h | 2 ++ arch/x86/kernel/apic/io_apic.c | 11 ++++------- arch/x86/kernel/apic/numaq_32.c | 8 +------- arch/x86/kernel/head32.c | 3 +++ arch/x86/kernel/x86_init.c | 1 + 7 files changed, 13 insertions(+), 16 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 330ee807f89..2b8aeb89933 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -177,12 +177,13 @@ extern int setup_ioapic_entry(int apic, int irq, int polarity, int vector, int pin); extern void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e); +extern void setup_ioapic_ids_from_mpc(void); #else /* !CONFIG_X86_IO_APIC */ #define io_apic_assign_pci_irqs 0 +#define setup_ioapic_ids_from_mpc x86_init_noop static const int timer_through_8259 = 0; static inline void ioapic_init_mappings(void) { } static inline void ioapic_insert_resources(void) { } - static inline void probe_nr_irqs_gsi(void) { } #endif diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index bbf2dfd59b4..cc8b4b0550e 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -30,7 +30,6 @@ struct x86_quirks { void (*mpc_oem_pci_bus)(struct mpc_bus *m); void (*smp_read_mpc_oem)(struct mpc_oemtable *oemtable, unsigned short oemsize); - int (*setup_ioapic_ids)(void); }; extern void x86_quirk_intr_init(void); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 10b297b1881..65985730b37 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -4,9 +4,11 @@ /** * struct x86_init_mpparse - platform specific mpparse ops * @mpc_record: platform specific mpc record accounting + * @setup_ioapic_ids: platform specific ioapic id override */ struct x86_init_mpparse { void (*mpc_record)(unsigned int mode); + void (*setup_ioapic_ids)(void); }; /** diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index d2ed6c5ddc8..5f4687187ce 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2014,7 +2014,7 @@ void disable_IO_APIC(void) * by Matt Domsch Tue Dec 21 12:25:05 CST 1999 */ -static void __init setup_ioapic_ids_from_mpc(void) +void __init setup_ioapic_ids_from_mpc(void) { union IO_APIC_reg_00 reg_00; physid_mask_t phys_id_present_map; @@ -2023,9 +2023,8 @@ static void __init setup_ioapic_ids_from_mpc(void) unsigned char old_id; unsigned long flags; - if (x86_quirks->setup_ioapic_ids && x86_quirks->setup_ioapic_ids()) + if (acpi_ioapic) return; - /* * Don't check I/O APIC IDs for xAPIC systems. They have * no meaning without the serial APIC bus. @@ -3061,10 +3060,8 @@ void __init setup_IO_APIC(void) /* * Set up IO-APIC IRQ routing. */ -#ifdef CONFIG_X86_32 - if (!acpi_ioapic) - setup_ioapic_ids_from_mpc(); -#endif + x86_init.mpparse.setup_ioapic_ids(); + sync_Arb_IDs(); setup_IO_APIC_irqs(); init_IO_APIC_traps(); diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index b5f0b1dc7dd..f3717659265 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -262,12 +262,6 @@ static void __init } } -static int __init numaq_setup_ioapic_ids(void) -{ - /* so can skip it */ - return 1; -} - static struct x86_quirks numaq_x86_quirks __initdata = { .arch_pre_time_init = numaq_pre_time_init, .arch_time_init = NULL, @@ -280,7 +274,6 @@ static struct x86_quirks numaq_x86_quirks __initdata = { .mpc_oem_bus_info = mpc_oem_bus_info, .mpc_oem_pci_bus = mpc_oem_pci_bus, .smp_read_mpc_oem = smp_read_mpc_oem, - .setup_ioapic_ids = numaq_setup_ioapic_ids, }; static __init void early_check_numaq(void) @@ -299,6 +292,7 @@ static __init void early_check_numaq(void) if (found_numaq) { x86_quirks = &numaq_x86_quirks; x86_init.mpparse.mpc_record = numaq_mpc_record; + x86_init.mpparse.setup_ioapic_ids = x86_init_noop; } } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 921a23b6c14..a21398fac4f 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -13,6 +13,8 @@ #include #include #include +#include +#include void __init i386_start_kernel(void) { @@ -32,6 +34,7 @@ void __init i386_start_kernel(void) /* Initilize 32bit specific setup functions */ x86_init.resources.probe_roms = probe_roms; x86_init.resources.reserve_resources = i386_reserve_resources; + x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc; x86_init.resources.reserve_ebda_region(); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 83bd5db376b..f4a32b3ab02 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -27,5 +27,6 @@ struct __initdata x86_init_ops x86_init = { .mpparse = { .mpc_record = x86_init_uint_noop, + .setup_ioapic_ids = x86_init_noop, }, }; -- cgit v1.2.3-70-g09d2 From fd6c6661492226bb82f422157c535ac573cbecbd Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 10:41:58 +0200 Subject: x86: Move mpc_apic_id to x86_init_ops The mpc_apic_id setup is handled by a x86_quirk. Make it a x86_init_ops function with a default implementation. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/mpspec.h | 2 ++ arch/x86/include/asm/setup.h | 2 -- arch/x86/include/asm/x86_init.h | 4 ++++ arch/x86/kernel/apic/numaq_32.c | 2 +- arch/x86/kernel/mpparse.c | 10 ++++++---- arch/x86/kernel/x86_init.c | 2 ++ 6 files changed, 15 insertions(+), 7 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index e2a1bb6d71e..03c6a92bfd4 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -62,10 +62,12 @@ extern void get_smp_config(void); extern void find_smp_config(void); extern void early_reserve_e820_mpc_new(void); extern int enable_update_mptable; +extern int default_mpc_apic_id(struct mpc_cpu *m); #else static inline void find_smp_config(void) { } static inline void early_reserve_e820_mpc_new(void) { } #define enable_update_mptable 0 +#define default_mpc_apic_id NULL #endif void __cpuinit generic_processor_info(int apicid, int version); diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index cc8b4b0550e..7c7f44f3e4d 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -12,7 +12,6 @@ /* * Any setup quirks to be performed? */ -struct mpc_cpu; struct mpc_bus; struct mpc_oemtable; @@ -25,7 +24,6 @@ struct x86_quirks { int (*mach_get_smp_config)(unsigned int early); int (*mach_find_smp_config)(unsigned int reserve); - int (*mpc_apic_id)(struct mpc_cpu *m); void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name); void (*mpc_oem_pci_bus)(struct mpc_bus *m); void (*smp_read_mpc_oem)(struct mpc_oemtable *oemtable, diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 65985730b37..f2be2a78018 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -1,14 +1,18 @@ #ifndef _ASM_X86_PLATFORM_H #define _ASM_X86_PLATFORM_H +struct mpc_cpu; + /** * struct x86_init_mpparse - platform specific mpparse ops * @mpc_record: platform specific mpc record accounting * @setup_ioapic_ids: platform specific ioapic id override + * @mpc_apic_id: platform specific mpc apic id assignment */ struct x86_init_mpparse { void (*mpc_record)(unsigned int mode); void (*setup_ioapic_ids)(void); + int (*mpc_apic_id)(struct mpc_cpu *m); }; /** diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index f3717659265..222413f7e79 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -270,7 +270,6 @@ static struct x86_quirks numaq_x86_quirks __initdata = { .arch_trap_init = NULL, .mach_get_smp_config = NULL, .mach_find_smp_config = NULL, - .mpc_apic_id = mpc_apic_id, .mpc_oem_bus_info = mpc_oem_bus_info, .mpc_oem_pci_bus = mpc_oem_pci_bus, .smp_read_mpc_oem = smp_read_mpc_oem, @@ -293,6 +292,7 @@ static __init void early_check_numaq(void) x86_quirks = &numaq_x86_quirks; x86_init.mpparse.mpc_record = numaq_mpc_record; x86_init.mpparse.setup_ioapic_ids = x86_init_noop; + x86_init.mpparse.mpc_apic_id = mpc_apic_id; } } diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index b2179fdf0ff..04560860a72 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -45,6 +45,11 @@ static int __init mpf_checksum(unsigned char *mp, int len) return sum & 0xFF; } +int __init default_mpc_apic_id(struct mpc_cpu *m) +{ + return m->apicid; +} + static void __init MP_processor_info(struct mpc_cpu *m) { int apicid; @@ -55,10 +60,7 @@ static void __init MP_processor_info(struct mpc_cpu *m) return; } - if (x86_quirks->mpc_apic_id) - apicid = x86_quirks->mpc_apic_id(m); - else - apicid = m->apicid; + apicid = x86_init.mpparse.mpc_apic_id(m); if (m->cpuflag & CPU_BOOTPROCESSOR) { bootup_cpu = " (Bootup-CPU)"; diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index f4a32b3ab02..08749f2612f 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -6,6 +6,7 @@ #include #include +#include #include #include @@ -28,5 +29,6 @@ struct __initdata x86_init_ops x86_init = { .mpparse = { .mpc_record = x86_init_uint_noop, .setup_ioapic_ids = x86_init_noop, + .mpc_apic_id = default_mpc_apic_id, }, }; -- cgit v1.2.3-70-g09d2 From 72302142e165313ee58af81bd76708c12b58d7ab Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 12:18:32 +0200 Subject: x86: Move smp_read_mpc_oem to x86_init_ops. Move smp_read_mpc_oem from quirks to x86_init. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/mpspec.h | 2 ++ arch/x86/include/asm/setup.h | 3 --- arch/x86/include/asm/x86_init.h | 3 +++ arch/x86/kernel/apic/numaq_32.c | 6 +++--- arch/x86/kernel/mpparse.c | 8 ++++---- arch/x86/kernel/x86_init.c | 1 + 6 files changed, 13 insertions(+), 10 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 03c6a92bfd4..5de8e92be2d 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -63,11 +63,13 @@ extern void find_smp_config(void); extern void early_reserve_e820_mpc_new(void); extern int enable_update_mptable; extern int default_mpc_apic_id(struct mpc_cpu *m); +extern void default_smp_read_mpc_oem(struct mpc_table *mpc); #else static inline void find_smp_config(void) { } static inline void early_reserve_e820_mpc_new(void) { } #define enable_update_mptable 0 #define default_mpc_apic_id NULL +#define default_smp_read_mpc_oem NULL #endif void __cpuinit generic_processor_info(int apicid, int version); diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 7c7f44f3e4d..adb5d44d990 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -13,7 +13,6 @@ * Any setup quirks to be performed? */ struct mpc_bus; -struct mpc_oemtable; struct x86_quirks { int (*arch_pre_time_init)(void); @@ -26,8 +25,6 @@ struct x86_quirks { void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name); void (*mpc_oem_pci_bus)(struct mpc_bus *m); - void (*smp_read_mpc_oem)(struct mpc_oemtable *oemtable, - unsigned short oemsize); }; extern void x86_quirk_intr_init(void); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index f2be2a78018..fc0eef2f5fd 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -2,17 +2,20 @@ #define _ASM_X86_PLATFORM_H struct mpc_cpu; +struct mpc_table; /** * struct x86_init_mpparse - platform specific mpparse ops * @mpc_record: platform specific mpc record accounting * @setup_ioapic_ids: platform specific ioapic id override * @mpc_apic_id: platform specific mpc apic id assignment + * @smp_read_mpc_oem: platform specific oem mpc table setup */ struct x86_init_mpparse { void (*mpc_record)(unsigned int mode); void (*setup_ioapic_ids)(void); int (*mpc_apic_id)(struct mpc_cpu *m); + void (*smp_read_mpc_oem)(struct mpc_table *mpc); }; /** diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index 222413f7e79..1bd3b0ed240 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -218,9 +218,9 @@ static int __init mpf_checksum(unsigned char *mp, int len) /* * Read/parse the MPC oem tables */ -static void __init - smp_read_mpc_oem(struct mpc_oemtable *oemtable, unsigned short oemsize) +static void __init smp_read_mpc_oem(struct mpc_table *mpc) { + struct mpc_oemtable *oemtable = (void *)(long)mpc->oemptr; int count = sizeof(*oemtable); /* the header size */ unsigned char *oemptr = ((unsigned char *)oemtable) + count; @@ -272,7 +272,6 @@ static struct x86_quirks numaq_x86_quirks __initdata = { .mach_find_smp_config = NULL, .mpc_oem_bus_info = mpc_oem_bus_info, .mpc_oem_pci_bus = mpc_oem_pci_bus, - .smp_read_mpc_oem = smp_read_mpc_oem, }; static __init void early_check_numaq(void) @@ -293,6 +292,7 @@ static __init void early_check_numaq(void) x86_init.mpparse.mpc_record = numaq_mpc_record; x86_init.mpparse.setup_ioapic_ids = x86_init_noop; x86_init.mpparse.mpc_apic_id = mpc_apic_id; + x86_init.mpparse.smp_read_mpc_oem = smp_read_mpc_oem; } } diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 04560860a72..45abdf63edc 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -293,6 +293,8 @@ static void __init smp_dump_mptable(struct mpc_table *mpc, unsigned char *mpt) 1, mpc, mpc->length, 1); } +void __init default_smp_read_mpc_oem(struct mpc_table *mpc) { } + static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) { char str[16]; @@ -314,10 +316,8 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) if (early) return 1; - if (mpc->oemptr && x86_quirks->smp_read_mpc_oem) { - struct mpc_oemtable *oem_table = (void *)(long)mpc->oemptr; - x86_quirks->smp_read_mpc_oem(oem_table, mpc->oemsize); - } + if (mpc->oemptr) + x86_init.mpparse.smp_read_mpc_oem(mpc); /* * Now process the configuration blocks. diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 08749f2612f..fb5d93c077d 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -30,5 +30,6 @@ struct __initdata x86_init_ops x86_init = { .mpc_record = x86_init_uint_noop, .setup_ioapic_ids = x86_init_noop, .mpc_apic_id = default_mpc_apic_id, + .smp_read_mpc_oem = default_smp_read_mpc_oem, }, }; -- cgit v1.2.3-70-g09d2 From 52fdb5684660f9fd7129f7bbbe279a02893bacb8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 12:45:33 +0200 Subject: x86: Move mpc_oem_pci_bus to x86_init_ops Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/setup.h | 1 - arch/x86/include/asm/x86_init.h | 3 +++ arch/x86/kernel/apic/numaq_32.c | 2 +- arch/x86/kernel/mpparse.c | 4 ++-- 4 files changed, 6 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index adb5d44d990..fd2267baba1 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -24,7 +24,6 @@ struct x86_quirks { int (*mach_find_smp_config)(unsigned int reserve); void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name); - void (*mpc_oem_pci_bus)(struct mpc_bus *m); }; extern void x86_quirk_intr_init(void); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index fc0eef2f5fd..404e2d2b06d 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -1,6 +1,7 @@ #ifndef _ASM_X86_PLATFORM_H #define _ASM_X86_PLATFORM_H +struct mpc_bus; struct mpc_cpu; struct mpc_table; @@ -10,12 +11,14 @@ struct mpc_table; * @setup_ioapic_ids: platform specific ioapic id override * @mpc_apic_id: platform specific mpc apic id assignment * @smp_read_mpc_oem: platform specific oem mpc table setup + * @mpc_oem_pci_bus: platform specific pci bus setup (default NULL) */ struct x86_init_mpparse { void (*mpc_record)(unsigned int mode); void (*setup_ioapic_ids)(void); int (*mpc_apic_id)(struct mpc_cpu *m); void (*smp_read_mpc_oem)(struct mpc_table *mpc); + void (*mpc_oem_pci_bus)(struct mpc_bus *m); }; /** diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index 1bd3b0ed240..feebe8eed7d 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -271,7 +271,6 @@ static struct x86_quirks numaq_x86_quirks __initdata = { .mach_get_smp_config = NULL, .mach_find_smp_config = NULL, .mpc_oem_bus_info = mpc_oem_bus_info, - .mpc_oem_pci_bus = mpc_oem_pci_bus, }; static __init void early_check_numaq(void) @@ -293,6 +292,7 @@ static __init void early_check_numaq(void) x86_init.mpparse.setup_ioapic_ids = x86_init_noop; x86_init.mpparse.mpc_apic_id = mpc_apic_id; x86_init.mpparse.smp_read_mpc_oem = smp_read_mpc_oem; + x86_init.mpparse.mpc_oem_pci_bus = mpc_oem_pci_bus; } } diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 45abdf63edc..72e1140723c 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -98,8 +98,8 @@ static void __init MP_bus_info(struct mpc_bus *m) mp_bus_id_to_type[m->busid] = MP_BUS_ISA; #endif } else if (strncmp(str, BUSTYPE_PCI, sizeof(BUSTYPE_PCI) - 1) == 0) { - if (x86_quirks->mpc_oem_pci_bus) - x86_quirks->mpc_oem_pci_bus(m); + if (x86_init.mpparse.mpc_oem_pci_bus) + x86_init.mpparse.mpc_oem_pci_bus(m); clear_bit(m->busid, mp_bus_not_pci); #if defined(CONFIG_EISA) || defined(CONFIG_MCA) -- cgit v1.2.3-70-g09d2 From 90e1c6969d8711edb888a00ec54c74370f125c8f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 12:34:47 +0200 Subject: x86: Move oem_bus_info to x86_init_ops Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/mpspec.h | 6 ++++++ arch/x86/include/asm/setup.h | 3 --- arch/x86/include/asm/x86_init.h | 2 ++ arch/x86/kernel/apic/numaq_32.c | 2 +- arch/x86/kernel/mpparse.c | 14 ++++++++------ arch/x86/kernel/x86_init.c | 1 + 6 files changed, 18 insertions(+), 10 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 5de8e92be2d..e3c579efde7 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -64,12 +64,18 @@ extern void early_reserve_e820_mpc_new(void); extern int enable_update_mptable; extern int default_mpc_apic_id(struct mpc_cpu *m); extern void default_smp_read_mpc_oem(struct mpc_table *mpc); +# ifdef CONFIG_X86_IO_APIC +extern void default_mpc_oem_bus_info(struct mpc_bus *m, char *str); +# else +# define default_mpc_oem_bus_info NULL +# endif #else static inline void find_smp_config(void) { } static inline void early_reserve_e820_mpc_new(void) { } #define enable_update_mptable 0 #define default_mpc_apic_id NULL #define default_smp_read_mpc_oem NULL +#define default_mpc_oem_bus_info NULL #endif void __cpuinit generic_processor_info(int apicid, int version); diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index fd2267baba1..6121a8ac7b0 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -12,7 +12,6 @@ /* * Any setup quirks to be performed? */ -struct mpc_bus; struct x86_quirks { int (*arch_pre_time_init)(void); @@ -22,8 +21,6 @@ struct x86_quirks { int (*arch_trap_init)(void); int (*mach_get_smp_config)(unsigned int early); int (*mach_find_smp_config)(unsigned int reserve); - - void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name); }; extern void x86_quirk_intr_init(void); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 404e2d2b06d..2833a873a90 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -12,6 +12,7 @@ struct mpc_table; * @mpc_apic_id: platform specific mpc apic id assignment * @smp_read_mpc_oem: platform specific oem mpc table setup * @mpc_oem_pci_bus: platform specific pci bus setup (default NULL) + * @mpc_oem_bus_info: platform specific mpc bus info */ struct x86_init_mpparse { void (*mpc_record)(unsigned int mode); @@ -19,6 +20,7 @@ struct x86_init_mpparse { int (*mpc_apic_id)(struct mpc_cpu *m); void (*smp_read_mpc_oem)(struct mpc_table *mpc); void (*mpc_oem_pci_bus)(struct mpc_bus *m); + void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name); }; /** diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index feebe8eed7d..700273dca68 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -270,7 +270,6 @@ static struct x86_quirks numaq_x86_quirks __initdata = { .arch_trap_init = NULL, .mach_get_smp_config = NULL, .mach_find_smp_config = NULL, - .mpc_oem_bus_info = mpc_oem_bus_info, }; static __init void early_check_numaq(void) @@ -293,6 +292,7 @@ static __init void early_check_numaq(void) x86_init.mpparse.mpc_apic_id = mpc_apic_id; x86_init.mpparse.smp_read_mpc_oem = smp_read_mpc_oem; x86_init.mpparse.mpc_oem_pci_bus = mpc_oem_pci_bus; + x86_init.mpparse.mpc_oem_bus_info = mpc_oem_bus_info; } } diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 72e1140723c..a42f23f1dc7 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -72,16 +72,18 @@ static void __init MP_processor_info(struct mpc_cpu *m) } #ifdef CONFIG_X86_IO_APIC -static void __init MP_bus_info(struct mpc_bus *m) +void __init default_mpc_oem_bus_info(struct mpc_bus *m, char *str) { - char str[7]; memcpy(str, m->bustype, 6); str[6] = 0; + apic_printk(APIC_VERBOSE, "Bus #%d is %s\n", m->busid, str); +} + +static void __init MP_bus_info(struct mpc_bus *m) +{ + char str[7]; - if (x86_quirks->mpc_oem_bus_info) - x86_quirks->mpc_oem_bus_info(m, str); - else - apic_printk(APIC_VERBOSE, "Bus #%d is %s\n", m->busid, str); + x86_init.mpparse.mpc_oem_bus_info(m, str); #if MAX_MP_BUSSES < 256 if (m->busid >= MAX_MP_BUSSES) { diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index fb5d93c077d..27685edc546 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -31,5 +31,6 @@ struct __initdata x86_init_ops x86_init = { .setup_ioapic_ids = x86_init_noop, .mpc_apic_id = default_mpc_apic_id, .smp_read_mpc_oem = default_smp_read_mpc_oem, + .mpc_oem_bus_info = default_mpc_oem_bus_info, }, }; -- cgit v1.2.3-70-g09d2 From 7285dd7fd375763bfb8ab1ac9cf3f1206f503c16 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 28 Aug 2009 20:25:24 +0200 Subject: clocksource: Resolve cpu hotplug dead lock with TSC unstable Martin Schwidefsky analyzed it: To register a clocksource the clocksource_mutex is acquired and if necessary timekeeping_notify is called to install the clocksource as the timekeeper clock. timekeeping_notify uses stop_machine which needs to take cpu_add_remove_lock mutex. Starting a new cpu is done with the cpu_add_remove_lock mutex held. native_cpu_up checks the tsc of the new cpu and if the tsc is no good clocksource_change_rating is called. Which needs the clocksource_mutex and the deadlock is complete. The solution is to replace the TSC via the clocksource watchdog mechanism. Mark the TSC as unstable and schedule the watchdog work so it gets removed in the watchdog thread context. Signed-off-by: Thomas Gleixner LKML-Reference: Cc: Martin Schwidefsky Cc: John Stultz --- arch/x86/kernel/tsc.c | 8 +++++--- include/linux/clocksource.h | 1 + kernel/time/clocksource.c | 33 ++++++++++++++++++++++++++++++--- 3 files changed, 36 insertions(+), 6 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 968425422c4..fc3672a303d 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -767,12 +767,14 @@ void mark_tsc_unstable(char *reason) { if (!tsc_unstable) { tsc_unstable = 1; - printk("Marking TSC unstable due to %s\n", reason); + printk(KERN_INFO "Marking TSC unstable due to %s\n", reason); /* Change only the rating, when not registered */ if (clocksource_tsc.mult) - clocksource_change_rating(&clocksource_tsc, 0); - else + clocksource_mark_unstable(&clocksource_tsc); + else { + clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE; clocksource_tsc.rating = 0; + } } } diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 9ea40ff26f0..83d2fbd81b9 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -277,6 +277,7 @@ extern struct clocksource* clocksource_get_next(void); extern void clocksource_change_rating(struct clocksource *cs, int rating); extern void clocksource_resume(void); extern struct clocksource * __init __weak clocksource_default_clock(void); +extern void clocksource_mark_unstable(struct clocksource *cs); #ifdef CONFIG_GENERIC_TIME_VSYSCALL extern void update_vsyscall(struct timespec *ts, struct clocksource *c); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index e0c86ad6e9f..a0af4ffcb6e 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -149,15 +149,42 @@ static void clocksource_watchdog_work(struct work_struct *work) kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog"); } -static void clocksource_unstable(struct clocksource *cs, int64_t delta) +static void __clocksource_unstable(struct clocksource *cs) { - printk(KERN_WARNING "Clocksource %s unstable (delta = %Ld ns)\n", - cs->name, delta); cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); cs->flags |= CLOCK_SOURCE_UNSTABLE; schedule_work(&watchdog_work); } +static void clocksource_unstable(struct clocksource *cs, int64_t delta) +{ + printk(KERN_WARNING "Clocksource %s unstable (delta = %Ld ns)\n", + cs->name, delta); + __clocksource_unstable(cs); +} + +/** + * clocksource_mark_unstable - mark clocksource unstable via watchdog + * @cs: clocksource to be marked unstable + * + * This function is called instead of clocksource_change_rating from + * cpu hotplug code to avoid a deadlock between the clocksource mutex + * and the cpu hotplug mutex. It defers the update of the clocksource + * to the watchdog thread. + */ +void clocksource_mark_unstable(struct clocksource *cs) +{ + unsigned long flags; + + spin_lock_irqsave(&watchdog_lock, flags); + if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) { + if (list_empty(&cs->wd_list)) + list_add(&cs->wd_list, &watchdog_list); + __clocksource_unstable(cs); + } + spin_unlock_irqrestore(&watchdog_lock, flags); +} + static void clocksource_watchdog(unsigned long data) { struct clocksource *cs; -- cgit v1.2.3-70-g09d2 From b3f1b617f49447df6c3f5fac9c225aaea8b724ea Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 11:11:52 +0200 Subject: x86: Move get/find_smp_config to x86_init_ops Replace the quirk machinery by a x86_init_ops function which defaults to the standard implementation. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/mpspec.h | 37 ++++++++++++++++++++++++++++++------- arch/x86/include/asm/setup.h | 2 -- arch/x86/include/asm/x86_init.h | 4 ++++ arch/x86/kernel/apic/numaq_32.c | 2 -- arch/x86/kernel/mpparse.c | 33 ++------------------------------- arch/x86/kernel/setup.c | 2 -- arch/x86/kernel/visws_quirks.c | 14 ++++---------- arch/x86/kernel/x86_init.c | 2 ++ 8 files changed, 42 insertions(+), 54 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index e3c579efde7..79c94500c0b 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -4,6 +4,7 @@ #include #include +#include extern int apic_version[MAX_APICS]; extern int pic_mode; @@ -41,9 +42,6 @@ extern int quad_local_to_mp_bus_id [NR_CPUS/4][4]; #endif /* CONFIG_X86_64 */ -extern void early_find_smp_config(void); -extern void early_get_smp_config(void); - #if defined(CONFIG_MCA) || defined(CONFIG_EISA) extern int mp_bus_id_to_type[MAX_MP_BUSSES]; #endif @@ -52,14 +50,36 @@ extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES); extern unsigned int boot_cpu_physical_apicid; extern unsigned int max_physical_apicid; -extern int smp_found_config; extern int mpc_default_type; extern unsigned long mp_lapic_addr; -extern void get_smp_config(void); +#ifdef CONFIG_X86_LOCAL_APIC +extern int smp_found_config; +#else +# define smp_found_config 0 +#endif + +static inline void get_smp_config(void) +{ + x86_init.mpparse.get_smp_config(0); +} + +static inline void early_get_smp_config(void) +{ + x86_init.mpparse.get_smp_config(1); +} + +static inline void find_smp_config(void) +{ + x86_init.mpparse.find_smp_config(1); +} + +static inline void early_find_smp_config(void) +{ + x86_init.mpparse.find_smp_config(0); +} #ifdef CONFIG_X86_MPPARSE -extern void find_smp_config(void); extern void early_reserve_e820_mpc_new(void); extern int enable_update_mptable; extern int default_mpc_apic_id(struct mpc_cpu *m); @@ -69,13 +89,16 @@ extern void default_mpc_oem_bus_info(struct mpc_bus *m, char *str); # else # define default_mpc_oem_bus_info NULL # endif +extern void default_find_smp_config(unsigned int reserve); +extern void default_get_smp_config(unsigned int early); #else -static inline void find_smp_config(void) { } static inline void early_reserve_e820_mpc_new(void) { } #define enable_update_mptable 0 #define default_mpc_apic_id NULL #define default_smp_read_mpc_oem NULL #define default_mpc_oem_bus_info NULL +#define default_find_smp_config x86_init_uint_noop +#define default_get_smp_config x86_init_uint_noop #endif void __cpuinit generic_processor_info(int apicid, int version); diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 6121a8ac7b0..345a2551af9 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -19,8 +19,6 @@ struct x86_quirks { int (*arch_pre_intr_init)(void); int (*arch_intr_init)(void); int (*arch_trap_init)(void); - int (*mach_get_smp_config)(unsigned int early); - int (*mach_find_smp_config)(unsigned int reserve); }; extern void x86_quirk_intr_init(void); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 2833a873a90..e0d4729c905 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -13,6 +13,8 @@ struct mpc_table; * @smp_read_mpc_oem: platform specific oem mpc table setup * @mpc_oem_pci_bus: platform specific pci bus setup (default NULL) * @mpc_oem_bus_info: platform specific mpc bus info + * @find_smp_config: find the smp configuration + * @get_smp_config: get the smp configuration */ struct x86_init_mpparse { void (*mpc_record)(unsigned int mode); @@ -21,6 +23,8 @@ struct x86_init_mpparse { void (*smp_read_mpc_oem)(struct mpc_table *mpc); void (*mpc_oem_pci_bus)(struct mpc_bus *m); void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name); + void (*find_smp_config)(unsigned int reserve); + void (*get_smp_config)(unsigned int early); }; /** diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index 700273dca68..3dd5fd76534 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -268,8 +268,6 @@ static struct x86_quirks numaq_x86_quirks __initdata = { .arch_pre_intr_init = NULL, .arch_intr_init = NULL, .arch_trap_init = NULL, - .mach_get_smp_config = NULL, - .mach_find_smp_config = NULL, }; static __init void early_check_numaq(void) diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index a42f23f1dc7..75357647b6e 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -610,7 +610,7 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early) /* * Scan the memory blocks for an SMP configuration block. */ -static void __init __get_smp_config(unsigned int early) +void __init default_get_smp_config(unsigned int early) { struct mpf_intel *mpf = mpf_found; @@ -627,11 +627,6 @@ static void __init __get_smp_config(unsigned int early) if (acpi_lapic && acpi_ioapic) return; - if (x86_quirks->mach_get_smp_config) { - if (x86_quirks->mach_get_smp_config(early)) - return; - } - printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n", mpf->specification); #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32) @@ -672,16 +667,6 @@ static void __init __get_smp_config(unsigned int early) */ } -void __init early_get_smp_config(void) -{ - __get_smp_config(1); -} - -void __init get_smp_config(void) -{ - __get_smp_config(0); -} - static void __init smp_reserve_bootmem(struct mpf_intel *mpf) { unsigned long size = get_mpc_size(mpf->physptr); @@ -747,14 +732,10 @@ static int __init smp_scan_config(unsigned long base, unsigned long length, return 0; } -static void __init __find_smp_config(unsigned int reserve) +void __init default_find_smp_config(unsigned int reserve) { unsigned int address; - if (x86_quirks->mach_find_smp_config) { - if (x86_quirks->mach_find_smp_config(reserve)) - return; - } /* * FIXME: Linux assumes you have 640K of base ram.. * this continues the error... @@ -789,16 +770,6 @@ static void __init __find_smp_config(unsigned int reserve) smp_scan_config(address, 0x400, reserve); } -void __init early_find_smp_config(void) -{ - __find_smp_config(0); -} - -void __init find_smp_config(void) -{ - __find_smp_config(1); -} - #ifdef CONFIG_X86_IO_APIC static u8 __initdata irq_used[MAX_IRQ_SOURCES]; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c2a8090e831..54043cb7ba6 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -981,13 +981,11 @@ void __init setup_arch(char **cmdline_p) */ acpi_boot_init(); -#if defined(CONFIG_X86_MPPARSE) || defined(CONFIG_X86_VISWS) /* * get boot-time SMP configuration: */ if (smp_found_config) get_smp_config(); -#endif prefill_possible_map(); diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c index 97c670df1ae..31e828118f8 100644 --- a/arch/x86/kernel/visws_quirks.c +++ b/arch/x86/kernel/visws_quirks.c @@ -156,12 +156,8 @@ static void visws_machine_power_off(void) outl(PIIX_SPECIAL_STOP, 0xCFC); } -static int __init visws_get_smp_config(unsigned int early) +static void __init visws_get_smp_config(unsigned int early) { - /* - * Prevent MP-table parsing by the generic code: - */ - return 1; } /* @@ -208,7 +204,7 @@ static void __init MP_processor_info(struct mpc_cpu *m) apic_version[m->apicid] = ver; } -static int __init visws_find_smp_config(unsigned int reserve) +static void __init visws_find_smp_config(unsigned int reserve) { struct mpc_cpu *mp = phys_to_virt(CO_CPU_TAB_PHYS); unsigned short ncpus = readw(phys_to_virt(CO_CPU_NUM_PHYS)); @@ -230,8 +226,6 @@ static int __init visws_find_smp_config(unsigned int reserve) MP_processor_info(mp++); mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; - - return 1; } static int visws_trap_init(void); @@ -241,8 +235,6 @@ static struct x86_quirks visws_x86_quirks __initdata = { .arch_pre_intr_init = visws_pre_intr_init, .arch_intr_init = NULL, .arch_trap_init = visws_trap_init, - .mach_get_smp_config = visws_get_smp_config, - .mach_find_smp_config = visws_find_smp_config, }; void __init visws_early_detect(void) @@ -263,6 +255,8 @@ void __init visws_early_detect(void) x86_quirks = &visws_x86_quirks; x86_init.resources.memory_setup = visws_memory_setup; + x86_init.mpparse.get_smp_config = visws_get_smp_config; + x86_init.mpparse.find_smp_config = visws_find_smp_config; /* * Install reboot quirks: diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 27685edc546..3488fb62ac0 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -32,5 +32,7 @@ struct __initdata x86_init_ops x86_init = { .mpc_apic_id = default_mpc_apic_id, .smp_read_mpc_oem = default_smp_read_mpc_oem, .mpc_oem_bus_info = default_mpc_oem_bus_info, + .find_smp_config = default_find_smp_config, + .get_smp_config = default_get_smp_config, }, }; -- cgit v1.2.3-70-g09d2 From d9112f43021554ded2ef2b9bea5f88ba4b52abe0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 09:41:38 +0200 Subject: x86: Move pre_intr_init to x86_init_ops Replace the quirk machinery by a x86_init_ops function which defaults to the standard implementation. This is also a preparatory patch for Moorestown support which needs to replace the default init_ISA_irqs as well. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/irq.h | 2 ++ arch/x86/include/asm/setup.h | 1 - arch/x86/include/asm/x86_init.h | 10 ++++++++++ arch/x86/kernel/apic/numaq_32.c | 1 - arch/x86/kernel/irqinit.c | 24 ++---------------------- arch/x86/kernel/visws_quirks.c | 10 +++------- arch/x86/kernel/x86_init.c | 5 +++++ 7 files changed, 22 insertions(+), 31 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index f38481bcd45..8fe2782a253 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -47,4 +47,6 @@ extern unsigned int do_IRQ(struct pt_regs *regs); extern DECLARE_BITMAP(used_vectors, NR_VECTORS); extern int vector_used_by_percpu_irq(unsigned int vector); +extern void init_ISA_irqs(void); + #endif /* _ASM_X86_IRQ_H */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 345a2551af9..66a319709d6 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -16,7 +16,6 @@ struct x86_quirks { int (*arch_pre_time_init)(void); int (*arch_time_init)(void); - int (*arch_pre_intr_init)(void); int (*arch_intr_init)(void); int (*arch_trap_init)(void); }; diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index e0d4729c905..65e3394c77f 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -43,6 +43,15 @@ struct x86_init_resources { char *(*memory_setup)(void); }; +/** + * struct x86_init_irqs - platform specific interrupt setup + * @pre_vector_init: init code to run before interrupt vectors + * are set up. + */ +struct x86_init_irqs { + void (*pre_vector_init)(void); +}; + /** * struct x86_init_ops - functions for platform specific setup * @@ -50,6 +59,7 @@ struct x86_init_resources { struct x86_init_ops { struct x86_init_resources resources; struct x86_init_mpparse mpparse; + struct x86_init_irqs irqs; }; extern struct x86_init_ops x86_init; diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index 3dd5fd76534..ec8b3113716 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -265,7 +265,6 @@ static void __init smp_read_mpc_oem(struct mpc_table *mpc) static struct x86_quirks numaq_x86_quirks __initdata = { .arch_pre_time_init = numaq_pre_time_init, .arch_time_init = NULL, - .arch_pre_intr_init = NULL, .arch_intr_init = NULL, .arch_trap_init = NULL, }; diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 92b7703d3d5..acdf088c758 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -116,7 +116,7 @@ int vector_used_by_percpu_irq(unsigned int vector) return 0; } -static void __init init_ISA_irqs(void) +void __init init_ISA_irqs(void) { int i; @@ -213,32 +213,12 @@ static void __init apic_intr_init(void) #endif } -/** - * x86_quirk_pre_intr_init - initialisation prior to setting up interrupt vectors - * - * Description: - * Perform any necessary interrupt initialisation prior to setting up - * the "ordinary" interrupt call gates. For legacy reasons, the ISA - * interrupts should be initialised here if the machine emulates a PC - * in any way. - **/ -static void __init x86_quirk_pre_intr_init(void) -{ -#ifdef CONFIG_X86_32 - if (x86_quirks->arch_pre_intr_init) { - if (x86_quirks->arch_pre_intr_init()) - return; - } -#endif - init_ISA_irqs(); -} - void __init native_init_IRQ(void) { int i; /* Execute any quirks before the call gates are initialised: */ - x86_quirk_pre_intr_init(); + x86_init.irqs.pre_vector_init(); apic_intr_init(); diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c index 31e828118f8..1d6309d70df 100644 --- a/arch/x86/kernel/visws_quirks.c +++ b/arch/x86/kernel/visws_quirks.c @@ -73,14 +73,10 @@ static int __init visws_time_init(void) return 0; } -static int __init visws_pre_intr_init(void) +/* Replaces the default init_ISA_irqs in the generic setup */ +static void __init visws_pre_intr_init(void) { init_VISWS_APIC_irqs(); - - /* - * We dont want ISA irqs to be set up by the generic code: - */ - return 1; } /* Quirk for machine specific memory setup. */ @@ -232,7 +228,6 @@ static int visws_trap_init(void); static struct x86_quirks visws_x86_quirks __initdata = { .arch_time_init = visws_time_init, - .arch_pre_intr_init = visws_pre_intr_init, .arch_intr_init = NULL, .arch_trap_init = visws_trap_init, }; @@ -257,6 +252,7 @@ void __init visws_early_detect(void) x86_init.resources.memory_setup = visws_memory_setup; x86_init.mpparse.get_smp_config = visws_get_smp_config; x86_init.mpparse.find_smp_config = visws_find_smp_config; + x86_init.irqs.pre_vector_init = visws_pre_intr_init; /* * Install reboot quirks: diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 3488fb62ac0..f2abe2136da 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -9,6 +9,7 @@ #include #include #include +#include void __cpuinit x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } @@ -35,4 +36,8 @@ struct __initdata x86_init_ops x86_init = { .find_smp_config = default_find_smp_config, .get_smp_config = default_get_smp_config, }, + + .irqs = { + .pre_vector_init = init_ISA_irqs, + }, }; -- cgit v1.2.3-70-g09d2 From 66bcaf0bde100a4b54b82fc6fea6ceee2212ffb4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 09:59:09 +0200 Subject: x86: Move irq_init to x86_init_ops irq_init is overridden by x86_quirks and by paravirts. Unify the whole mess and make it an unconditional x86_init_ops function which defaults to the standard function and can be overridden by the early platform code. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/irq.h | 1 - arch/x86/include/asm/paravirt_types.h | 2 -- arch/x86/include/asm/setup.h | 3 --- arch/x86/include/asm/x86_init.h | 2 ++ arch/x86/kernel/apic/numaq_32.c | 1 - arch/x86/kernel/irqinit.c | 12 ++++-------- arch/x86/kernel/paravirt.c | 6 ------ arch/x86/kernel/setup.c | 17 ----------------- arch/x86/kernel/visws_quirks.c | 1 - arch/x86/kernel/x86_init.c | 1 + arch/x86/lguest/boot.c | 2 +- arch/x86/xen/irq.c | 5 +++-- 12 files changed, 11 insertions(+), 42 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 8fe2782a253..ddda6cbed6f 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -37,7 +37,6 @@ extern void fixup_irqs(void); #endif extern void (*generic_interrupt_extension)(void); -extern void init_IRQ(void); extern void native_init_IRQ(void); extern bool handle_irq(unsigned irq, struct pt_regs *regs); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 6d668968b6b..25922afb634 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -201,8 +201,6 @@ struct pv_cpu_ops { }; struct pv_irq_ops { - void (*init_IRQ)(void); - /* * Get/set interrupt state. save_fl and restore_fl are only * expected to use X86_EFLAGS_IF; all other bits diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 66a319709d6..404086f9411 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -16,12 +16,9 @@ struct x86_quirks { int (*arch_pre_time_init)(void); int (*arch_time_init)(void); - int (*arch_intr_init)(void); int (*arch_trap_init)(void); }; -extern void x86_quirk_intr_init(void); - extern void x86_quirk_trap_init(void); extern void x86_quirk_pre_time_init(void); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 65e3394c77f..8d7be65ccf7 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -47,9 +47,11 @@ struct x86_init_resources { * struct x86_init_irqs - platform specific interrupt setup * @pre_vector_init: init code to run before interrupt vectors * are set up. + * @intr_init: interrupt init code */ struct x86_init_irqs { void (*pre_vector_init)(void); + void (*intr_init)(void); }; /** diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index ec8b3113716..eafd341e42d 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -265,7 +265,6 @@ static void __init smp_read_mpc_oem(struct mpc_table *mpc) static struct x86_quirks numaq_x86_quirks __initdata = { .arch_pre_time_init = numaq_pre_time_init, .arch_time_init = NULL, - .arch_intr_init = NULL, .arch_trap_init = NULL, }; diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index acdf088c758..e0142cda239 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -140,8 +140,10 @@ void __init init_ISA_irqs(void) } } -/* Overridden in paravirt.c */ -void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ"))); +void init_IRQ(void) +{ + x86_init.irqs.intr_init(); +} static void __init smp_intr_init(void) { @@ -237,12 +239,6 @@ void __init native_init_IRQ(void) setup_irq(2, &irq2); #ifdef CONFIG_X86_32 - /* - * Call quirks after call gates are initialised (usually add in - * the architecture specific gates): - */ - x86_quirk_intr_init(); - /* * External FPU? Set up irq13 if so, for * original braindamaged IBM FERR coupling. diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 532c9a2626c..d76bfbec71a 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -183,11 +183,6 @@ unsigned paravirt_patch_insns(void *insnbuf, unsigned len, return insn_len; } -void init_IRQ(void) -{ - pv_irq_ops.init_IRQ(); -} - static void native_flush_tlb(void) { __native_flush_tlb(); @@ -328,7 +323,6 @@ struct pv_time_ops pv_time_ops = { }; struct pv_irq_ops pv_irq_ops = { - .init_IRQ = native_init_IRQ, .save_fl = __PV_IS_CALLEE_SAVE(native_save_fl), .restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl), .irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable), diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 54043cb7ba6..d3da0f7333f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1020,23 +1020,6 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_X86_32 -/** - * x86_quirk_intr_init - post gate setup interrupt initialisation - * - * Description: - * Fill in any interrupts that may have been left out by the general - * init_IRQ() routine. interrupts having to do with the machine rather - * than the devices on the I/O bus (like APIC interrupts in intel MP - * systems) are started here. - **/ -void __init x86_quirk_intr_init(void) -{ - if (x86_quirks->arch_intr_init) { - if (x86_quirks->arch_intr_init()) - return; - } -} - /** * x86_quirk_trap_init - initialise system specific traps * diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c index 1d6309d70df..a49013716da 100644 --- a/arch/x86/kernel/visws_quirks.c +++ b/arch/x86/kernel/visws_quirks.c @@ -228,7 +228,6 @@ static int visws_trap_init(void); static struct x86_quirks visws_x86_quirks __initdata = { .arch_time_init = visws_time_init, - .arch_intr_init = NULL, .arch_trap_init = visws_trap_init, }; diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index f2abe2136da..8cb59332e3b 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -39,5 +39,6 @@ struct __initdata x86_init_ops x86_init = { .irqs = { .pre_vector_init = init_ISA_irqs, + .intr_init = native_init_IRQ, }, }; diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 11445c176de..1ff986511f1 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1262,7 +1262,6 @@ __init void lguest_init(void) */ /* Interrupt-related operations */ - pv_irq_ops.init_IRQ = lguest_init_IRQ; pv_irq_ops.save_fl = PV_CALLEE_SAVE(save_fl); pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(lg_restore_fl); pv_irq_ops.irq_disable = PV_CALLEE_SAVE(irq_disable); @@ -1325,6 +1324,7 @@ __init void lguest_init(void) pv_time_ops.get_tsc_khz = lguest_tsc_khz; x86_init.resources.memory_setup = lguest_memory_setup; + x86_init.irqs.intr_init = lguest_init_IRQ; /* * Now is a good time to look at the implementations of these functions diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index cfd17799bd6..9d30105a0c4 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -1,5 +1,7 @@ #include +#include + #include #include #include @@ -112,8 +114,6 @@ static void xen_halt(void) } static const struct pv_irq_ops xen_irq_ops __initdata = { - .init_IRQ = xen_init_IRQ, - .save_fl = PV_CALLEE_SAVE(xen_save_fl), .restore_fl = PV_CALLEE_SAVE(xen_restore_fl), .irq_disable = PV_CALLEE_SAVE(xen_irq_disable), @@ -129,4 +129,5 @@ static const struct pv_irq_ops xen_irq_ops __initdata = { void __init xen_init_irq_ops() { pv_irq_ops = xen_irq_ops; + x86_init.irqs.intr_init = xen_init_IRQ; } -- cgit v1.2.3-70-g09d2 From 428cf9025b15573e16e658032f2b963283e34ae0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 10:35:46 +0200 Subject: x86: Move traps_init to x86_init_ops Replace the quirks by a simple x86_init_ops function. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/setup.h | 3 --- arch/x86/include/asm/x86_init.h | 2 ++ arch/x86/kernel/apic/numaq_32.c | 1 - arch/x86/kernel/setup.c | 15 --------------- arch/x86/kernel/traps.c | 5 ++--- arch/x86/kernel/visws_quirks.c | 8 +++----- arch/x86/kernel/x86_init.c | 1 + 7 files changed, 8 insertions(+), 27 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 404086f9411..7751d1f92bc 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -16,11 +16,8 @@ struct x86_quirks { int (*arch_pre_time_init)(void); int (*arch_time_init)(void); - int (*arch_trap_init)(void); }; -extern void x86_quirk_trap_init(void); - extern void x86_quirk_pre_time_init(void); extern void x86_quirk_time_init(void); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 8d7be65ccf7..07c37bd879f 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -48,10 +48,12 @@ struct x86_init_resources { * @pre_vector_init: init code to run before interrupt vectors * are set up. * @intr_init: interrupt init code + * @trap_init: platform specific trap setup */ struct x86_init_irqs { void (*pre_vector_init)(void); void (*intr_init)(void); + void (*trap_init)(void); }; /** diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index eafd341e42d..71c5ea64586 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -265,7 +265,6 @@ static void __init smp_read_mpc_oem(struct mpc_table *mpc) static struct x86_quirks numaq_x86_quirks __initdata = { .arch_pre_time_init = numaq_pre_time_init, .arch_time_init = NULL, - .arch_trap_init = NULL, }; static __init void early_check_numaq(void) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d3da0f7333f..bf3b87f1f7d 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1020,21 +1020,6 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_X86_32 -/** - * x86_quirk_trap_init - initialise system specific traps - * - * Description: - * Called as the final act of trap_init(). Used in VISWS to initialise - * the various board specific APIC traps. - **/ -void __init x86_quirk_trap_init(void) -{ - if (x86_quirks->arch_trap_init) { - if (x86_quirks->arch_trap_init()) - return; - } -} - static struct irqaction irq0 = { .handler = timer_interrupt, .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 7e4b1f5dec8..ed96ed53f69 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -59,6 +59,7 @@ #include #ifdef CONFIG_X86_64 +#include #include #include #else @@ -980,7 +981,5 @@ void __init trap_init(void) */ cpu_init(); -#ifdef CONFIG_X86_32 - x86_quirk_trap_init(); -#endif + x86_init.irqs.trap_init(); } diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c index a49013716da..2719091b335 100644 --- a/arch/x86/kernel/visws_quirks.c +++ b/arch/x86/kernel/visws_quirks.c @@ -224,11 +224,10 @@ static void __init visws_find_smp_config(unsigned int reserve) mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; } -static int visws_trap_init(void); +static void visws_trap_init(void); static struct x86_quirks visws_x86_quirks __initdata = { .arch_time_init = visws_time_init, - .arch_trap_init = visws_trap_init, }; void __init visws_early_detect(void) @@ -252,6 +251,7 @@ void __init visws_early_detect(void) x86_init.mpparse.get_smp_config = visws_get_smp_config; x86_init.mpparse.find_smp_config = visws_find_smp_config; x86_init.irqs.pre_vector_init = visws_pre_intr_init; + x86_init.irqs.trap_init = visws_trap_init; /* * Install reboot quirks: @@ -390,12 +390,10 @@ static __init void cobalt_init(void) co_apic_read(CO_APIC_ID)); } -static int __init visws_trap_init(void) +static void __init visws_trap_init(void) { lithium_init(); cobalt_init(); - - return 1; } /* diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 8cb59332e3b..9f2b775dc72 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -40,5 +40,6 @@ struct __initdata x86_init_ops x86_init = { .irqs = { .pre_vector_init = init_ISA_irqs, .intr_init = native_init_IRQ, + .trap_init = x86_init_noop, }, }; -- cgit v1.2.3-70-g09d2 From 42bbdb43b16d233b2dacb4cd76e28f61c2a86dc6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 13:04:10 +0200 Subject: x86: Replace ARCH_SETUP by a proper x86_init_ops ARCH_SETUP is a horrible leftover from the old arch/i386 mach support code. It still has a lonely user in xen. Move it to x86_init_ops. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/paravirt.h | 1 - arch/x86/include/asm/paravirt_types.h | 1 - arch/x86/include/asm/x86_init.h | 9 +++++++++ arch/x86/kernel/paravirt.c | 1 - arch/x86/kernel/setup.c | 6 +----- arch/x86/kernel/x86_init.c | 4 ++++ arch/x86/xen/enlighten.c | 2 +- 7 files changed, 15 insertions(+), 9 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 6a07af432c8..22cb3872f6d 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -24,7 +24,6 @@ static inline void load_sp0(struct tss_struct *tss, PVOP_VCALL2(pv_cpu_ops.load_sp0, tss, thread); } -#define ARCH_SETUP pv_init_ops.arch_setup(); static inline unsigned long get_wallclock(void) { return PVOP_CALL0(unsigned long, pv_time_ops.get_wallclock); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 25922afb634..a05085e5fdb 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -80,7 +80,6 @@ struct pv_init_ops { unsigned long addr, unsigned len); /* Basic arch-specific setup */ - void (*arch_setup)(void); void (*post_allocator_init)(void); /* Print a banner to identify the environment */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 07c37bd879f..ceffbf358fc 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -56,6 +56,14 @@ struct x86_init_irqs { void (*trap_init)(void); }; +/** + * struct x86_init_oem - oem platform specific customizing functions + * @arch_setup: platform specific architecure setup + */ +struct x86_init_oem { + void (*arch_setup)(void); +}; + /** * struct x86_init_ops - functions for platform specific setup * @@ -64,6 +72,7 @@ struct x86_init_ops { struct x86_init_resources resources; struct x86_init_mpparse mpparse; struct x86_init_irqs irqs; + struct x86_init_oem oem; }; extern struct x86_init_ops x86_init; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index d76bfbec71a..80275ef1651 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -311,7 +311,6 @@ struct pv_info pv_info = { struct pv_init_ops pv_init_ops = { .patch = native_patch, .banner = default_banner, - .arch_setup = paravirt_nop, }; struct pv_time_ops pv_time_ops = { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index bf3b87f1f7d..d12aa82c9c3 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -108,10 +108,6 @@ #include #endif -#ifndef ARCH_SETUP -#define ARCH_SETUP -#endif - /* * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries. * The direct mapping extends to max_pfn_mapped, so that we can directly access @@ -750,7 +746,7 @@ void __init setup_arch(char **cmdline_p) } #endif - ARCH_SETUP + x86_init.oem.arch_setup(); setup_memory_map(); parse_setup_data(); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 9f2b775dc72..fa2d849be35 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -42,4 +42,8 @@ struct __initdata x86_init_ops x86_init = { .intr_init = native_init_IRQ, .trap_init = x86_init_noop, }, + + .oem = { + .arch_setup = x86_init_noop, + }, }; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 50b20c64f0b..73c7b1d610f 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -841,7 +841,6 @@ static const struct pv_init_ops xen_init_ops __initdata = { .patch = xen_patch, .banner = xen_banner, - .arch_setup = xen_arch_setup, .post_allocator_init = xen_post_allocator_init, }; @@ -982,6 +981,7 @@ asmlinkage void __init xen_start_kernel(void) pv_mmu_ops = xen_mmu_ops; x86_init.resources.memory_setup = xen_memory_setup; + x86_init.oem.arch_setup = xen_arch_setup; #ifdef CONFIG_X86_64 /* -- cgit v1.2.3-70-g09d2 From 6f30c1ac3fcf11e08f00670f293546a112cdf4e3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 13:19:57 +0200 Subject: x86: Move paravirt banner printout to x86_init_ops Replace another obscure paravirt magic and move it to x86_init_ops. Such a hook is also useful for embedded and special hardware. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/paravirt.h | 6 +++++- arch/x86/include/asm/paravirt_types.h | 3 --- arch/x86/include/asm/x86_init.h | 2 ++ arch/x86/kernel/paravirt.c | 10 +--------- arch/x86/kernel/setup.c | 1 + arch/x86/kernel/x86_init.c | 2 ++ arch/x86/xen/enlighten.c | 2 +- 7 files changed, 12 insertions(+), 14 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 22cb3872f6d..3de6435a106 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -918,6 +918,8 @@ static inline unsigned long __raw_local_irq_save(void) #undef PVOP_VCALL4 #undef PVOP_CALL4 +extern void default_banner(void); + #else /* __ASSEMBLY__ */ #define _PVSITE(ptype, clobbers, ops, word, algn) \ @@ -1058,5 +1060,7 @@ static inline unsigned long __raw_local_irq_save(void) #endif /* CONFIG_X86_32 */ #endif /* __ASSEMBLY__ */ -#endif /* CONFIG_PARAVIRT */ +#else /* CONFIG_PARAVIRT */ +# define default_banner x86_init_noop +#endif /* !CONFIG_PARAVIRT */ #endif /* _ASM_X86_PARAVIRT_H */ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index a05085e5fdb..ce7723c81a1 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -81,9 +81,6 @@ struct pv_init_ops { /* Basic arch-specific setup */ void (*post_allocator_init)(void); - - /* Print a banner to identify the environment */ - void (*banner)(void); }; diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index ceffbf358fc..ee7c59df781 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -59,9 +59,11 @@ struct x86_init_irqs { /** * struct x86_init_oem - oem platform specific customizing functions * @arch_setup: platform specific architecure setup + * @banner: print a platform specific banner */ struct x86_init_oem { void (*arch_setup)(void); + void (*banner)(void); }; /** diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 80275ef1651..f7a5fb79d18 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -54,7 +54,7 @@ u64 _paravirt_ident_64(u64 x) return x; } -static void __init default_banner(void) +void __init default_banner(void) { printk(KERN_INFO "Booting paravirtualized kernel on %s\n", pv_info.name); @@ -208,13 +208,6 @@ extern void native_irq_enable_sysexit(void); extern void native_usergs_sysret32(void); extern void native_usergs_sysret64(void); -static int __init print_banner(void) -{ - pv_init_ops.banner(); - return 0; -} -core_initcall(print_banner); - static struct resource reserve_ioports = { .start = 0, .end = IO_SPACE_LIMIT, @@ -310,7 +303,6 @@ struct pv_info pv_info = { struct pv_init_ops pv_init_ops = { .patch = native_patch, - .banner = default_banner, }; struct pv_time_ops pv_time_ops = { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d12aa82c9c3..bc5f0e561cf 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1012,6 +1012,7 @@ void __init setup_arch(char **cmdline_p) conswitchp = &dummy_con; #endif #endif + x86_init.oem.banner(); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index fa2d849be35..08fea49d59a 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -6,6 +6,7 @@ #include #include +#include #include #include #include @@ -45,5 +46,6 @@ struct __initdata x86_init_ops x86_init = { .oem = { .arch_setup = x86_init_noop, + .banner = default_banner, }, }; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 73c7b1d610f..46e23cde143 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -840,7 +840,6 @@ static const struct pv_info xen_info __initdata = { static const struct pv_init_ops xen_init_ops __initdata = { .patch = xen_patch, - .banner = xen_banner, .post_allocator_init = xen_post_allocator_init, }; @@ -982,6 +981,7 @@ asmlinkage void __init xen_start_kernel(void) x86_init.resources.memory_setup = xen_memory_setup; x86_init.oem.arch_setup = xen_arch_setup; + x86_init.oem.banner = xen_banner; #ifdef CONFIG_X86_64 /* -- cgit v1.2.3-70-g09d2 From 030cb6c00d242c20e92a3327d0cac17ce02d0cc3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 14:30:02 +0200 Subject: x86: Move paravirt pagetable_setup to x86_init_ops Replace more paravirt hackery by proper x86_init_ops. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/paravirt.h | 10 ---------- arch/x86/include/asm/paravirt_types.h | 9 --------- arch/x86/include/asm/pgtable.h | 10 ---------- arch/x86/include/asm/pgtable_types.h | 4 ++-- arch/x86/include/asm/x86_init.h | 13 +++++++++++++ arch/x86/kernel/paravirt.c | 7 ------- arch/x86/kernel/setup.c | 4 ++-- arch/x86/kernel/x86_init.c | 6 ++++++ arch/x86/xen/enlighten.c | 2 +- arch/x86/xen/mmu.c | 11 +++++++---- arch/x86/xen/mmu.h | 2 +- 11 files changed, 32 insertions(+), 46 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 3de6435a106..1caf25b91e6 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -351,16 +351,6 @@ static inline void paravirt_post_allocator_init(void) (*pv_init_ops.post_allocator_init)(); } -static inline void paravirt_pagetable_setup_start(pgd_t *base) -{ - (*pv_mmu_ops.pagetable_setup_start)(base); -} - -static inline void paravirt_pagetable_setup_done(pgd_t *base) -{ - (*pv_mmu_ops.pagetable_setup_done)(base); -} - #ifdef CONFIG_SMP static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip, unsigned long start_esp) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index ce7723c81a1..4039eefd3eb 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -231,15 +231,6 @@ struct pv_apic_ops { }; struct pv_mmu_ops { - /* - * Called before/after init_mm pagetable setup. setup_start - * may reset %cr3, and may pre-install parts of the pagetable; - * pagetable setup is expected to preserve any existing - * mapping. - */ - void (*pagetable_setup_start)(pgd_t *pgd_base); - void (*pagetable_setup_done)(pgd_t *pgd_base); - unsigned long (*read_cr2)(void); void (*write_cr2)(unsigned long); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 16748077559..60d422adf70 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -56,16 +56,6 @@ extern struct list_head pgd_list; #define pte_update(mm, addr, ptep) do { } while (0) #define pte_update_defer(mm, addr, ptep) do { } while (0) -static inline void __init paravirt_pagetable_setup_start(pgd_t *base) -{ - native_pagetable_setup_start(base); -} - -static inline void __init paravirt_pagetable_setup_done(pgd_t *base) -{ - native_pagetable_setup_done(base); -} - #define pgd_val(x) native_pgd_val(x) #define __pgd(x) native_make_pgd(x) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 54cb697f490..7b467bf3c68 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -299,8 +299,8 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pte); extern void native_pagetable_setup_start(pgd_t *base); extern void native_pagetable_setup_done(pgd_t *base); #else -static inline void native_pagetable_setup_start(pgd_t *base) {} -static inline void native_pagetable_setup_done(pgd_t *base) {} +#define native_pagetable_setup_start x86_init_pgd_noop +#define native_pagetable_setup_done x86_init_pgd_noop #endif struct seq_file; diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index ee7c59df781..b9bb4faefc4 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_PLATFORM_H #define _ASM_X86_PLATFORM_H +#include + struct mpc_bus; struct mpc_cpu; struct mpc_table; @@ -66,6 +68,16 @@ struct x86_init_oem { void (*banner)(void); }; +/** + * struct x86_init_paging - platform specific paging functions + * @pagetable_setup_start: platform specific pre paging_init() call + * @pagetable_setup_done: platform specific post paging_init() call + */ +struct x86_init_paging { + void (*pagetable_setup_start)(pgd_t *base); + void (*pagetable_setup_done)(pgd_t *base); +}; + /** * struct x86_init_ops - functions for platform specific setup * @@ -75,6 +87,7 @@ struct x86_init_ops { struct x86_init_mpparse mpparse; struct x86_init_irqs irqs; struct x86_init_oem oem; + struct x86_init_paging paging; }; extern struct x86_init_ops x86_init; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index f7a5fb79d18..8167be0b68c 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -402,13 +402,6 @@ struct pv_apic_ops pv_apic_ops = { #endif struct pv_mmu_ops pv_mmu_ops = { -#ifndef CONFIG_X86_64 - .pagetable_setup_start = native_pagetable_setup_start, - .pagetable_setup_done = native_pagetable_setup_done, -#else - .pagetable_setup_start = paravirt_nop, - .pagetable_setup_done = paravirt_nop, -#endif .read_cr2 = native_read_cr2, .write_cr2 = native_write_cr2, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index bc5f0e561cf..4952d63dd67 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -959,9 +959,9 @@ void __init setup_arch(char **cmdline_p) kvmclock_init(); #endif - paravirt_pagetable_setup_start(swapper_pg_dir); + x86_init.paging.pagetable_setup_start(swapper_pg_dir); paging_init(); - paravirt_pagetable_setup_done(swapper_pg_dir); + x86_init.paging.pagetable_setup_done(swapper_pg_dir); paravirt_post_allocator_init(); #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 08fea49d59a..7df020e6740 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -14,6 +14,7 @@ void __cpuinit x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } +void __init x86_init_pgd_noop(pgd_t *unused) { } /* * The platform setup functions are preset with the default functions @@ -48,4 +49,9 @@ struct __initdata x86_init_ops x86_init = { .arch_setup = x86_init_noop, .banner = default_banner, }, + + .paging = { + .pagetable_setup_start = native_pagetable_setup_start, + .pagetable_setup_done = native_pagetable_setup_done, + }, }; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 46e23cde143..12ea09ec39b 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -977,7 +977,6 @@ asmlinkage void __init xen_start_kernel(void) pv_time_ops = xen_time_ops; pv_cpu_ops = xen_cpu_ops; pv_apic_ops = xen_apic_ops; - pv_mmu_ops = xen_mmu_ops; x86_init.resources.memory_setup = xen_memory_setup; x86_init.oem.arch_setup = xen_arch_setup; @@ -991,6 +990,7 @@ asmlinkage void __init xen_start_kernel(void) load_percpu_segment(0); #endif + xen_init_mmu_ops(); xen_init_irq_ops(); xen_init_cpuid_mask(); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 4ceb2858165..dbec51da930 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1875,10 +1875,7 @@ static void xen_leave_lazy_mmu(void) preempt_enable(); } -const struct pv_mmu_ops xen_mmu_ops __initdata = { - .pagetable_setup_start = xen_pagetable_setup_start, - .pagetable_setup_done = xen_pagetable_setup_done, - +static const struct pv_mmu_ops xen_mmu_ops __initdata = { .read_cr2 = xen_read_cr2, .write_cr2 = xen_write_cr2, @@ -1954,6 +1951,12 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = { .set_fixmap = xen_set_fixmap, }; +void __init xen_init_mmu_ops(void) +{ + x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start; + x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done; + pv_mmu_ops = xen_mmu_ops; +} #ifdef CONFIG_XEN_DEBUG_FS diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index da730262489..5fe6bc7f5ec 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -59,5 +59,5 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, unsigned long xen_read_cr2_direct(void); -extern const struct pv_mmu_ops xen_mmu_ops; +extern void xen_init_mmu_ops(void); #endif /* _XEN_MMU_H */ -- cgit v1.2.3-70-g09d2 From f1d7062a235d057e5d85ed2860bef609e0160cde Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 13:13:52 +0200 Subject: x86: Move xen_post_allocator_init into xen_pagetable_setup_done We really do not need two paravirt/x86_init_ops functions which are called in two consecutive source lines. Move the only user of post_allocator_init into the already existing pagetable_setup_done function. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/paravirt.h | 6 ------ arch/x86/include/asm/paravirt_types.h | 3 --- arch/x86/include/asm/setup.h | 4 ---- arch/x86/kernel/setup.c | 1 - arch/x86/xen/enlighten.c | 2 -- arch/x86/xen/mmu.c | 5 ++++- arch/x86/xen/xen-ops.h | 2 -- 7 files changed, 4 insertions(+), 19 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 1caf25b91e6..7ce415e844b 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -345,12 +345,6 @@ static inline void setup_secondary_clock(void) } #endif -static inline void paravirt_post_allocator_init(void) -{ - if (pv_init_ops.post_allocator_init) - (*pv_init_ops.post_allocator_init)(); -} - #ifdef CONFIG_SMP static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip, unsigned long start_esp) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 4039eefd3eb..ecc74e5ad40 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -78,9 +78,6 @@ struct pv_init_ops { */ unsigned (*patch)(u8 type, u16 clobber, void *insnbuf, unsigned long addr, unsigned len); - - /* Basic arch-specific setup */ - void (*post_allocator_init)(void); }; diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 7751d1f92bc..58b58952b80 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -63,10 +63,6 @@ static inline int is_visws_box(void) { return 0; } extern struct x86_quirks *x86_quirks; extern unsigned long saved_video_mode; -#ifndef CONFIG_PARAVIRT -#define paravirt_post_allocator_init() do {} while (0) -#endif - extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 4952d63dd67..43ec6aa175b 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -962,7 +962,6 @@ void __init setup_arch(char **cmdline_p) x86_init.paging.pagetable_setup_start(swapper_pg_dir); paging_init(); x86_init.paging.pagetable_setup_done(swapper_pg_dir); - paravirt_post_allocator_init(); #ifdef CONFIG_X86_64 map_vsyscall(); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 12ea09ec39b..a924caa168d 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -839,8 +839,6 @@ static const struct pv_info xen_info __initdata = { static const struct pv_init_ops xen_init_ops __initdata = { .patch = xen_patch, - - .post_allocator_init = xen_post_allocator_init, }; static const struct pv_time_ops xen_time_ops __initdata = { diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index dbec51da930..093dd59b538 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1229,9 +1229,12 @@ static __init void xen_pagetable_setup_start(pgd_t *base) { } +static void xen_post_allocator_init(void); + static __init void xen_pagetable_setup_done(pgd_t *base) { xen_setup_shared_info(); + xen_post_allocator_init(); } static void xen_write_cr2(unsigned long cr2) @@ -1841,7 +1844,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) #endif } -__init void xen_post_allocator_init(void) +static __init void xen_post_allocator_init(void) { pv_mmu_ops.set_pte = xen_set_pte; pv_mmu_ops.set_pmd = xen_set_pmd; diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 22494fd4c9b..355fa6b99c9 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -30,8 +30,6 @@ pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn); void xen_ident_map_ISA(void); void xen_reserve_top(void); -void xen_post_allocator_init(void); - char * __init xen_memory_setup(void); void __init xen_arch_setup(void); void __init xen_init_IRQ(void); -- cgit v1.2.3-70-g09d2 From 736decac643e8982655e22ac7f0e5e61c5b7f9bd Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 19 Aug 2009 12:35:53 +0200 Subject: x86: Move percpu clockevents setup to x86_init_ops paravirt overrides the setup of the default apic timers as per cpu timers. Moorestown needs to override that as well. Move it to x86_init_ops setup and create a separate x86_cpuinit struct which holds the function for the secondary evtl. hotplugabble CPUs. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/apic.h | 5 ++--- arch/x86/include/asm/paravirt.h | 12 ------------ arch/x86/include/asm/paravirt_types.h | 3 --- arch/x86/include/asm/x86_init.h | 19 +++++++++++++++++++ arch/x86/kernel/apic/apic.c | 3 ++- arch/x86/kernel/kvmclock.c | 5 ++++- arch/x86/kernel/paravirt.c | 2 -- arch/x86/kernel/smpboot.c | 4 ++-- arch/x86/kernel/vmi_32.c | 4 ++-- arch/x86/kernel/x86_init.c | 9 +++++++++ arch/x86/xen/enlighten.c | 4 ++-- 11 files changed, 42 insertions(+), 28 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index bb7d4792584..6f15b29005a 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -70,9 +70,6 @@ static inline void default_inquire_remote_apic(int apicid) */ #ifdef CONFIG_PARAVIRT #include -#else -#define setup_boot_clock setup_boot_APIC_clock -#define setup_secondary_clock setup_secondary_APIC_clock #endif #ifdef CONFIG_X86_64 @@ -245,6 +242,8 @@ static inline void lapic_shutdown(void) { } static inline void init_apic_mappings(void) { } static inline void disable_local_APIC(void) { } static inline void apic_disable(void) { } +# define setup_boot_APIC_clock x86_init_noop +# define setup_secondary_APIC_clock x86_init_noop #endif /* !CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_64 diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 7ce415e844b..825674a968d 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -333,18 +333,6 @@ static inline void slow_down_io(void) #endif } -#ifdef CONFIG_X86_LOCAL_APIC -static inline void setup_boot_clock(void) -{ - PVOP_VCALL0(pv_apic_ops.setup_boot_clock); -} - -static inline void setup_secondary_clock(void) -{ - PVOP_VCALL0(pv_apic_ops.setup_secondary_clock); -} -#endif - #ifdef CONFIG_SMP static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip, unsigned long start_esp) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index ecc74e5ad40..1da89276d14 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -218,9 +218,6 @@ struct pv_irq_ops { struct pv_apic_ops { #ifdef CONFIG_X86_LOCAL_APIC - void (*setup_boot_clock)(void); - void (*setup_secondary_clock)(void); - void (*startup_ipi_hook)(int phys_apicid, unsigned long start_eip, unsigned long start_esp); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index b9bb4faefc4..b7d258f4c40 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -78,6 +78,15 @@ struct x86_init_paging { void (*pagetable_setup_done)(pgd_t *base); }; +/** + * struct x86_init_timers - platform specific timer setup + * @setup_perpcu_clockev: set up the per cpu clock event device for the + * boot cpu + */ +struct x86_init_timers { + void (*setup_percpu_clockev)(void); +}; + /** * struct x86_init_ops - functions for platform specific setup * @@ -88,9 +97,19 @@ struct x86_init_ops { struct x86_init_irqs irqs; struct x86_init_oem oem; struct x86_init_paging paging; + struct x86_init_timers timers; +}; + +/** + * struct x86_cpuinit_ops - platform specific cpu hotplug setups + * @setup_percpu_clockev: set up the per cpu clock event device + */ +struct x86_cpuinit_ops { + void (*setup_percpu_clockev)(void); }; extern struct x86_init_ops x86_init; +extern struct x86_cpuinit_ops x86_cpuinit; extern void x86_init_noop(void); extern void x86_init_uint_noop(unsigned int unused); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 0a1c2830ec6..ce0098066e9 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -36,6 +36,7 @@ #include #include +#include #include #include #include @@ -1701,7 +1702,7 @@ int __init APIC_init_uniprocessor(void) localise_nmi_watchdog(); #endif - setup_boot_clock(); + x86_init.timers.setup_percpu_clockev(); #ifdef CONFIG_X86_64 check_nmi_watchdog(); #endif diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 223af43f152..64e9b5f59d2 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -22,6 +22,8 @@ #include #include #include + +#include #include #define KVM_SCALE 22 @@ -187,7 +189,8 @@ void __init kvmclock_init(void) pv_time_ops.sched_clock = kvm_clock_read; pv_time_ops.get_tsc_khz = kvm_get_tsc_khz; #ifdef CONFIG_X86_LOCAL_APIC - pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock; + x86_cpuinit.setup_percpu_clockev = + kvm_setup_secondary_clock; #endif #ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 8167be0b68c..1ed32c79679 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -387,8 +387,6 @@ struct pv_cpu_ops pv_cpu_ops = { struct pv_apic_ops pv_apic_ops = { #ifdef CONFIG_X86_LOCAL_APIC - .setup_boot_clock = setup_boot_APIC_clock, - .setup_secondary_clock = setup_secondary_APIC_clock, .startup_ipi_hook = paravirt_nop, #endif }; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 2fecda69ee6..6eb81a87b4b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -323,7 +323,7 @@ notrace static void __cpuinit start_secondary(void *unused) /* enable local interrupts */ local_irq_enable(); - setup_secondary_clock(); + x86_cpuinit.setup_percpu_clockev(); wmb(); cpu_idle(); @@ -1112,7 +1112,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) printk(KERN_INFO "CPU%d: ", 0); print_cpu_info(&cpu_data(0)); - setup_boot_clock(); + x86_init.timers.setup_percpu_clockev(); if (is_uv_system()) uv_system_init(); diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index 95a7289e4b0..b43b6685cae 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -821,8 +821,8 @@ static inline int __init activate_vmi(void) pv_time_ops.get_wallclock = vmi_get_wallclock; pv_time_ops.set_wallclock = vmi_set_wallclock; #ifdef CONFIG_X86_LOCAL_APIC - pv_apic_ops.setup_boot_clock = vmi_time_bsp_init; - pv_apic_ops.setup_secondary_clock = vmi_time_ap_init; + x86_init.timers.setup_percpu_clockev = vmi_time_bsp_init; + x86_cpuinit.setup_percpu_clockev = vmi_time_ap_init; #endif pv_time_ops.sched_clock = vmi_sched_clock; pv_time_ops.get_tsc_khz = vmi_tsc_khz; diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 7df020e6740..e666a98db7c 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -54,4 +55,12 @@ struct __initdata x86_init_ops x86_init = { .pagetable_setup_start = native_pagetable_setup_start, .pagetable_setup_done = native_pagetable_setup_done, }, + + .timers = { + .setup_percpu_clockev = setup_boot_APIC_clock, + }, +}; + +__cpuinitdata struct x86_cpuinit_ops x86_cpuinit = { + .setup_percpu_clockev = setup_secondary_APIC_clock, }; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index a924caa168d..14e597e0c16 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -912,8 +912,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = { static const struct pv_apic_ops xen_apic_ops __initdata = { #ifdef CONFIG_X86_LOCAL_APIC - .setup_boot_clock = paravirt_nop, - .setup_secondary_clock = paravirt_nop, .startup_ipi_hook = paravirt_nop, #endif }; @@ -979,6 +977,8 @@ asmlinkage void __init xen_start_kernel(void) x86_init.resources.memory_setup = xen_memory_setup; x86_init.oem.arch_setup = xen_arch_setup; x86_init.oem.banner = xen_banner; + x86_init.timers.setup_percpu_clockev = x86_init_noop; + x86_cpuinit.setup_percpu_clockev = x86_init_noop; #ifdef CONFIG_X86_64 /* -- cgit v1.2.3-70-g09d2 From 845b3944bbdf9e9247849bf037f27ff3a3f26d87 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 19 Aug 2009 15:37:03 +0200 Subject: x86: Add timer_init to x86_init_ops The timer init code is convoluted with several quirks and the paravirt timer chooser. Figuring out which code path is actually taken is not for the faint hearted. Move the numaq TSC quirk to tsc_pre_init x86_init_ops function and replace the paravirt time chooser and the remaining x86 quirk with a simple x86_init_ops function. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/paravirt.h | 5 ---- arch/x86/include/asm/paravirt_types.h | 2 -- arch/x86/include/asm/setup.h | 21 ++--------------- arch/x86/include/asm/time.h | 1 - arch/x86/include/asm/timer.h | 3 +-- arch/x86/include/asm/x86_init.h | 4 ++++ arch/x86/kernel/apic/numaq_32.c | 10 ++------ arch/x86/kernel/paravirt.c | 1 - arch/x86/kernel/setup.c | 43 ----------------------------------- arch/x86/kernel/time_32.c | 34 ++++++++++++++++++--------- arch/x86/kernel/time_64.c | 9 ++++++-- arch/x86/kernel/tsc.c | 2 ++ arch/x86/kernel/visws_quirks.c | 20 ++++------------ arch/x86/kernel/vmi_32.c | 2 +- arch/x86/kernel/x86_init.c | 3 +++ arch/x86/lguest/boot.c | 2 +- arch/x86/xen/enlighten.c | 4 ++-- 17 files changed, 53 insertions(+), 113 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 825674a968d..11a4ba7b209 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -34,11 +34,6 @@ static inline int set_wallclock(unsigned long nowtime) return PVOP_CALL1(int, pv_time_ops.set_wallclock, nowtime); } -static inline void (*choose_time_init(void))(void) -{ - return pv_time_ops.time_init; -} - /* The paravirtualized CPUID instruction. */ static inline void __cpuid(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 1da89276d14..0d812e592e3 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -88,8 +88,6 @@ struct pv_lazy_ops { }; struct pv_time_ops { - void (*time_init)(void); - /* Set and set time of day */ unsigned long (*get_wallclock)(void); int (*set_wallclock)(unsigned long); diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 58b58952b80..861e1fe2303 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -5,24 +5,6 @@ #define COMMAND_LINE_SIZE 2048 -#ifndef __ASSEMBLY__ - -#include - -/* - * Any setup quirks to be performed? - */ - -struct x86_quirks { - int (*arch_pre_time_init)(void); - int (*arch_time_init)(void); -}; - -extern void x86_quirk_pre_time_init(void); -extern void x86_quirk_time_init(void); - -#endif /* __ASSEMBLY__ */ - #ifdef __i386__ #include @@ -42,6 +24,7 @@ extern void x86_quirk_time_init(void); #ifndef __ASSEMBLY__ #include +#include /* Interrupt control for vSMPowered x86_64 systems */ #ifdef CONFIG_X86_64 @@ -60,11 +43,11 @@ static inline void visws_early_detect(void) { } static inline int is_visws_box(void) { return 0; } #endif -extern struct x86_quirks *x86_quirks; extern unsigned long saved_video_mode; extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); +extern void setup_default_timer_irq(void); #ifndef _SETUP diff --git a/arch/x86/include/asm/time.h b/arch/x86/include/asm/time.h index 50c733aac42..91bb162b5a3 100644 --- a/arch/x86/include/asm/time.h +++ b/arch/x86/include/asm/time.h @@ -54,7 +54,6 @@ extern void time_init(void); #define get_wallclock() native_get_wallclock() #define set_wallclock(x) native_set_wallclock(x) -#define choose_time_init() hpet_time_init #endif /* CONFIG_PARAVIRT */ diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 20ca9c4d468..e854c7ab416 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -12,8 +12,7 @@ unsigned long native_calibrate_tsc(void); #ifdef CONFIG_X86_32 extern int timer_ack; -extern irqreturn_t timer_interrupt(int irq, void *dev_id); -#endif /* CONFIG_X86_32 */ +#endif extern int recalibrate_cpu_khz(void); extern int no_timer_check; diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index b7d258f4c40..f8bdd2271a0 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -82,9 +82,13 @@ struct x86_init_paging { * struct x86_init_timers - platform specific timer setup * @setup_perpcu_clockev: set up the per cpu clock event device for the * boot cpu + * @tsc_pre_init: platform function called before TSC init + * @timer_init: initialize the platform timer (default PIT/HPET) */ struct x86_init_timers { void (*setup_percpu_clockev)(void); + void (*tsc_pre_init)(void); + void (*timer_init)(void); }; /** diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index 71c5ea64586..f1ebed6bd15 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -129,10 +129,9 @@ void __cpuinit numaq_tsc_disable(void) } } -static int __init numaq_pre_time_init(void) +static void __init numaq_tsc_init(void) { numaq_tsc_disable(); - return 0; } static inline int generate_logical_apicid(int quad, int phys_apicid) @@ -262,11 +261,6 @@ static void __init smp_read_mpc_oem(struct mpc_table *mpc) } } -static struct x86_quirks numaq_x86_quirks __initdata = { - .arch_pre_time_init = numaq_pre_time_init, - .arch_time_init = NULL, -}; - static __init void early_check_numaq(void) { /* @@ -281,13 +275,13 @@ static __init void early_check_numaq(void) early_get_smp_config(); if (found_numaq) { - x86_quirks = &numaq_x86_quirks; x86_init.mpparse.mpc_record = numaq_mpc_record; x86_init.mpparse.setup_ioapic_ids = x86_init_noop; x86_init.mpparse.mpc_apic_id = mpc_apic_id; x86_init.mpparse.smp_read_mpc_oem = smp_read_mpc_oem; x86_init.mpparse.mpc_oem_pci_bus = mpc_oem_pci_bus; x86_init.mpparse.mpc_oem_bus_info = mpc_oem_bus_info; + x86_init.timers.tsc_pre_init = numaq_tsc_init; } } diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 1ed32c79679..9c0e644a76d 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -306,7 +306,6 @@ struct pv_init_ops pv_init_ops = { }; struct pv_time_ops pv_time_ops = { - .time_init = hpet_time_init, .get_wallclock = native_get_wallclock, .set_wallclock = native_set_wallclock, .sched_clock = native_sched_clock, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 43ec6aa175b..bb207a47c63 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -626,10 +626,6 @@ static int __init setup_elfcorehdr(char *arg) early_param("elfcorehdr", setup_elfcorehdr); #endif -static struct x86_quirks default_x86_quirks __initdata; - -struct x86_quirks *x86_quirks __initdata = &default_x86_quirks; - #ifdef CONFIG_X86_RESERVE_LOW_64K static int __init dmi_low_memory_corruption(const struct dmi_system_id *d) { @@ -1016,45 +1012,6 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_X86_32 -static struct irqaction irq0 = { - .handler = timer_interrupt, - .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, - .name = "timer" -}; - -/** - * x86_quirk_pre_time_init - do any specific initialisations before. - * - **/ -void __init x86_quirk_pre_time_init(void) -{ - if (x86_quirks->arch_pre_time_init) - x86_quirks->arch_pre_time_init(); -} - -/** - * x86_quirk_time_init - do any specific initialisations for the system timer. - * - * Description: - * Must plug the system timer interrupt source at HZ into the IRQ listed - * in irq_vectors.h:TIMER_IRQ - **/ -void __init x86_quirk_time_init(void) -{ - if (x86_quirks->arch_time_init) { - /* - * A nonzero return code does not mean failure, it means - * that the architecture quirk does not want any - * generic (timer) setup to be performed after this: - */ - if (x86_quirks->arch_time_init()) - return; - } - - irq0.mask = cpumask_of_cpu(0); - setup_irq(0, &irq0); -} - static struct resource video_ram_resource = { .name = "Video RAM area", .start = 0xa0000, diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c index 5c5d87f0b2e..89bbb52218b 100644 --- a/arch/x86/kernel/time_32.c +++ b/arch/x86/kernel/time_32.c @@ -72,7 +72,7 @@ EXPORT_SYMBOL(profile_pc); * Time Stamp Counter value at the time of the timer interrupt, so that * we later on can estimate the time of day more exactly. */ -irqreturn_t timer_interrupt(int irq, void *dev_id) +static irqreturn_t timer_interrupt(int irq, void *dev_id) { /* Keep nmi watchdog up to date */ inc_irq_stat(irq0_irqs); @@ -113,25 +113,37 @@ irqreturn_t timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -/* Duplicate of time_init() below, with hpet_enable part added */ +static struct irqaction irq0 = { + .handler = timer_interrupt, + .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, + .name = "timer" +}; + +void __init setup_default_timer_irq(void) +{ + irq0.mask = cpumask_of_cpu(0); + setup_irq(0, &irq0); +} + +/* Default timer init function */ void __init hpet_time_init(void) { if (!hpet_enable()) setup_pit_timer(); - x86_quirk_time_init(); + setup_default_timer_irq(); +} + +static void x86_late_time_init(void) +{ + x86_init.timers.timer_init(); } /* - * This is called directly from init code; we must delay timer setup in the - * HPET case as we can't make the decision to turn on HPET this early in the - * boot process. - * - * The chosen time_init function will usually be hpet_time_init, above, but - * in the case of virtual hardware, an alternative function may be substituted. + * Initialize TSC and delay the periodic timer init to + * late x86_late_time_init() so ioremap works. */ void __init time_init(void) { - x86_quirk_pre_time_init(); tsc_init(); - late_time_init = choose_time_init(); + late_time_init = x86_late_time_init; } diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c index 5ba343e6184..38a7df94c10 100644 --- a/arch/x86/kernel/time_64.c +++ b/arch/x86/kernel/time_64.c @@ -19,6 +19,7 @@ #include #include +#include #include #include #include @@ -127,9 +128,13 @@ void __init hpet_time_init(void) setup_irq(0, &irq0); } +static void x86_late_time_init(void) +{ + x86_init.timers.timer_init(); +} + void __init time_init(void) { tsc_init(); - - late_time_init = choose_time_init(); + late_time_init = x86_late_time_init; } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 71f4368b357..652bc214eeb 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -857,6 +857,8 @@ void __init tsc_init(void) u64 lpj; int cpu; + x86_init.timers.tsc_pre_init(); + if (!cpu_has_tsc) return; diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c index 2719091b335..f068553a1b1 100644 --- a/arch/x86/kernel/visws_quirks.c +++ b/arch/x86/kernel/visws_quirks.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include @@ -53,7 +54,7 @@ int is_visws_box(void) return visws_board_type >= 0; } -static int __init visws_time_init(void) +static void __init visws_time_init(void) { printk(KERN_INFO "Starting Cobalt Timer system clock\n"); @@ -66,11 +67,7 @@ static int __init visws_time_init(void) /* Enable (unmask) the timer interrupt */ co_cpu_write(CO_CPU_CTRL, co_cpu_read(CO_CPU_CTRL) & ~CO_CTRL_TIMEMASK); - /* - * Zero return means the generic timer setup code will set up - * the standard vector: - */ - return 0; + setup_default_timer_irq(); } /* Replaces the default init_ISA_irqs in the generic setup */ @@ -226,10 +223,6 @@ static void __init visws_find_smp_config(unsigned int reserve) static void visws_trap_init(void); -static struct x86_quirks visws_x86_quirks __initdata = { - .arch_time_init = visws_time_init, -}; - void __init visws_early_detect(void) { int raw; @@ -241,17 +234,14 @@ void __init visws_early_detect(void) return; /* - * Install special quirks for timer, interrupt and memory setup: - * Fall back to generic behavior for traps: - * Override generic MP-table parsing: + * Override the default platform setup functions */ - x86_quirks = &visws_x86_quirks; - x86_init.resources.memory_setup = visws_memory_setup; x86_init.mpparse.get_smp_config = visws_get_smp_config; x86_init.mpparse.find_smp_config = visws_find_smp_config; x86_init.irqs.pre_vector_init = visws_pre_intr_init; x86_init.irqs.trap_init = visws_trap_init; + x86_init.timers.timer_init = visws_time_init; /* * Install reboot quirks: diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index b43b6685cae..cd7d0fbbf66 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -817,7 +817,7 @@ static inline int __init activate_vmi(void) vmi_timer_ops.set_alarm = vmi_get_function(VMI_CALL_SetAlarm); vmi_timer_ops.cancel_alarm = vmi_get_function(VMI_CALL_CancelAlarm); - pv_time_ops.time_init = vmi_time_init; + x86_init.timers.timer_init = vmi_time_init; pv_time_ops.get_wallclock = vmi_get_wallclock; pv_time_ops.set_wallclock = vmi_set_wallclock; #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index e666a98db7c..4790b92714a 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -11,6 +11,7 @@ #include #include #include +#include #include void __cpuinit x86_init_noop(void) { } @@ -58,6 +59,8 @@ struct __initdata x86_init_ops x86_init = { .timers = { .setup_percpu_clockev = setup_boot_APIC_clock, + .tsc_pre_init = x86_init_noop, + .timer_init = hpet_time_init, }, }; diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 1ff986511f1..6caa8c0c793 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1320,11 +1320,11 @@ __init void lguest_init(void) /* Time operations */ pv_time_ops.get_wallclock = lguest_get_wallclock; - pv_time_ops.time_init = lguest_time_init; pv_time_ops.get_tsc_khz = lguest_tsc_khz; x86_init.resources.memory_setup = lguest_memory_setup; x86_init.irqs.intr_init = lguest_init_IRQ; + x86_init.timers.timer_init = lguest_time_init; /* * Now is a good time to look at the implementations of these functions diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 14e597e0c16..84826b842b5 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -842,8 +842,6 @@ static const struct pv_init_ops xen_init_ops __initdata = { }; static const struct pv_time_ops xen_time_ops __initdata = { - .time_init = xen_time_init, - .set_wallclock = xen_set_wallclock, .get_wallclock = xen_get_wallclock, .get_tsc_khz = xen_tsc_khz, @@ -977,6 +975,8 @@ asmlinkage void __init xen_start_kernel(void) x86_init.resources.memory_setup = xen_memory_setup; x86_init.oem.arch_setup = xen_arch_setup; x86_init.oem.banner = xen_banner; + + x86_init.timers.timer_init = xen_time_init; x86_init.timers.setup_percpu_clockev = x86_init_noop; x86_cpuinit.setup_percpu_clockev = x86_init_noop; -- cgit v1.2.3-70-g09d2 From ecce85089e6d31eed7535b68f5acdd194265690c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 15:28:50 +0200 Subject: x86: Remove do_timer hook This is a left over of the old x86 sub arch support. Remove it and open code it like we do in time_64.c Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/do_timer.h | 16 ---------------- arch/x86/kernel/time_32.c | 7 ++++--- 2 files changed, 4 insertions(+), 19 deletions(-) delete mode 100644 arch/x86/include/asm/do_timer.h (limited to 'arch/x86') diff --git a/arch/x86/include/asm/do_timer.h b/arch/x86/include/asm/do_timer.h deleted file mode 100644 index 23ecda0b28a..00000000000 --- a/arch/x86/include/asm/do_timer.h +++ /dev/null @@ -1,16 +0,0 @@ -/* defines for inline arch setup functions */ -#include - -#include -#include - -/** - * do_timer_interrupt_hook - hook into timer tick - * - * Call the pit clock event handler. see asm/i8253.h - **/ - -static inline void do_timer_interrupt_hook(void) -{ - global_clock_event->event_handler(global_clock_event); -} diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c index 89bbb52218b..6fef4ea1e7a 100644 --- a/arch/x86/kernel/time_32.c +++ b/arch/x86/kernel/time_32.c @@ -28,6 +28,7 @@ * serialize accesses to xtime/lost_ticks). */ +#include #include #include #include @@ -37,8 +38,8 @@ #include #include #include - -#include +#include +#include int timer_ack; @@ -92,7 +93,7 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) } #endif - do_timer_interrupt_hook(); + global_clock_event->event_handler(global_clock_event); #ifdef CONFIG_MCA if (MCA_bus) { -- cgit v1.2.3-70-g09d2 From dd3e6e8c6e7a2294f137c4dbccb3e73e7fa8ba15 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 15:35:23 +0200 Subject: x86: Prepare unification of time_32/64.c Unify the top comment and the includes. Signed-off-by: Thomas Gleixner --- arch/x86/kernel/time_32.c | 44 +++++++++++++------------------------------- arch/x86/kernel/time_64.c | 13 +++++-------- 2 files changed, 18 insertions(+), 39 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c index 6fef4ea1e7a..acbaefd61e8 100644 --- a/arch/x86/kernel/time_32.c +++ b/arch/x86/kernel/time_32.c @@ -1,45 +1,27 @@ /* - * Copyright (C) 1991, 1992, 1995 Linus Torvalds + * Copyright (c) 1991,1992,1995 Linus Torvalds + * Copyright (c) 1994 Alan Modra + * Copyright (c) 1995 Markus Kuhn + * Copyright (c) 1996 Ingo Molnar + * Copyright (c) 1998 Andrea Arcangeli + * Copyright (c) 2002,2006 Vojtech Pavlik + * Copyright (c) 2003 Andi Kleen * - * This file contains the PC-specific time handling details: - * reading the RTC at bootup, etc.. - * 1994-07-02 Alan Modra - * fixed set_rtc_mmss, fixed time.year for >= 2000, new mktime - * 1995-03-26 Markus Kuhn - * fixed 500 ms bug at call to set_rtc_mmss, fixed DS12887 - * precision CMOS clock update - * 1996-05-03 Ingo Molnar - * fixed time warps in do_[slow|fast]_gettimeoffset() - * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 - * "A Kernel Model for Precision Timekeeping" by Dave Mills - * 1998-09-05 (Various) - * More robust do_fast_gettimeoffset() algorithm implemented - * (works with APM, Cyrix 6x86MX and Centaur C6), - * monotonic gettimeofday() with fast_get_timeoffset(), - * drift-proof precision TSC calibration on boot - * (C. Scott Ananian , Andrew D. - * Balsa , Philip Gladstone ; - * ported from 2.0.35 Jumbo-9 by Michael Krause ). - * 1998-12-16 Andrea Arcangeli - * Fixed Jumbo-9 code in 2.1.131: do_gettimeofday was missing 1 jiffy - * because was not accounting lost_ticks. - * 1998-12-24 Copyright (C) 1998 Andrea Arcangeli - * Fixed a xtime SMP race (we need the xtime_lock rw spinlock to - * serialize accesses to xtime/lost_ticks). */ #include -#include #include #include #include -#include -#include -#include -#include +#include +#include #include #include +#include +#include +#include +#include int timer_ack; diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c index 38a7df94c10..45914f8844a 100644 --- a/arch/x86/kernel/time_64.c +++ b/arch/x86/kernel/time_64.c @@ -1,6 +1,4 @@ /* - * "High Precision Event Timer" based timekeeping. - * * Copyright (c) 1991,1992,1995 Linus Torvalds * Copyright (c) 1994 Alan Modra * Copyright (c) 1995 Markus Kuhn @@ -8,23 +6,22 @@ * Copyright (c) 1998 Andrea Arcangeli * Copyright (c) 2002,2006 Vojtech Pavlik * Copyright (c) 2003 Andi Kleen - * RTC support code taken from arch/i386/kernel/timers/time_hpet.c + * */ #include -#include #include -#include #include #include -#include +#include #include +#include #include +#include #include -#include #include -#include +#include volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; -- cgit v1.2.3-70-g09d2 From 64fcbac1f38882d8ae82c44a1c2a676cfa5e79e1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 15:54:21 +0200 Subject: x86: Simplify timer_ack magic in time_32.c Let the compiler optimize the timer_ack magic away in the 32bit timer interrupt and put the same code into time_64.c. It's optimized out for CONFIG_X86_IO_APIC on 32bit and for 64bit because timer_ack is const 0 in both cases. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/timer.h | 6 ++++-- arch/x86/kernel/time_32.c | 5 +++-- arch/x86/kernel/time_64.c | 14 ++++++++++++++ 3 files changed, 21 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index e854c7ab416..65228ccc5f0 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -9,11 +9,13 @@ unsigned long long native_sched_clock(void); unsigned long native_calibrate_tsc(void); +extern int recalibrate_cpu_khz(void); -#ifdef CONFIG_X86_32 +#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC) extern int timer_ack; +#else +# define timer_ack (0) #endif -extern int recalibrate_cpu_khz(void); extern int no_timer_check; diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c index acbaefd61e8..7a26bcf887f 100644 --- a/arch/x86/kernel/time_32.c +++ b/arch/x86/kernel/time_32.c @@ -23,7 +23,9 @@ #include #include +#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC) int timer_ack; +#endif unsigned long profile_pc(struct pt_regs *regs) { @@ -60,7 +62,7 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) /* Keep nmi watchdog up to date */ inc_irq_stat(irq0_irqs); -#ifdef CONFIG_X86_IO_APIC + /* Optimized out for !IO_APIC and x86_64 */ if (timer_ack) { /* * Subtle, when I/O APICs are used we have to ack timer IRQ @@ -73,7 +75,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) inb(PIC_MASTER_POLL); spin_unlock(&i8259A_lock); } -#endif global_clock_event->event_handler(global_clock_event); diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c index 45914f8844a..35e0a925da5 100644 --- a/arch/x86/kernel/time_64.c +++ b/arch/x86/kernel/time_64.c @@ -51,6 +51,20 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) { inc_irq_stat(irq0_irqs); + /* Optimized out for !IO_APIC and x86_64 */ + if (timer_ack) { + /* + * Subtle, when I/O APICs are used we have to ack timer IRQ + * manually to deassert NMI lines for the watchdog if run + * on an 82489DX-based system. + */ + spin_lock(&i8259A_lock); + outb(0x0c, PIC_MASTER_OCW3); + /* Ack the IRQ; AEOI will end it automatically. */ + inb(PIC_MASTER_POLL); + spin_unlock(&i8259A_lock); + } + global_clock_event->event_handler(global_clock_event); #ifdef CONFIG_MCA -- cgit v1.2.3-70-g09d2 From 0be6939422eb2f54df4b3d8763c569c6759c1a42 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 15:59:35 +0200 Subject: x86: Remove mca bus ifdef from timer interrupt MCA_bus is constant 0 when CONFIG_MCA=n. So the compiler removes that code w/o needing an extra #ifdef Signed-off-by: Thomas Gleixner --- arch/x86/kernel/time_32.c | 18 +++--------------- arch/x86/kernel/time_64.c | 9 +++------ 2 files changed, 6 insertions(+), 21 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c index 7a26bcf887f..ec729cdcfa3 100644 --- a/arch/x86/kernel/time_32.c +++ b/arch/x86/kernel/time_32.c @@ -78,21 +78,9 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) global_clock_event->event_handler(global_clock_event); -#ifdef CONFIG_MCA - if (MCA_bus) { - /* The PS/2 uses level-triggered interrupts. You can't - turn them off, nor would you want to (any attempt to - enable edge-triggered interrupts usually gets intercepted by a - special hardware circuit). Hence we have to acknowledge - the timer interrupt. Through some incredibly stupid - design idea, the reset for IRQ 0 is done by setting the - high bit of the PPI port B (0x61). Note that some PS/2s, - notably the 55SX, work fine if this is removed. */ - - u8 irq_v = inb_p(0x61); /* read the current state */ - outb_p(irq_v | 0x80, 0x61); /* reset the IRQ */ - } -#endif + /* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */ + if (MCA_bus) + outb_p(inb_p(0x61)| 0x80, 0x61); return IRQ_HANDLED; } diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c index 35e0a925da5..7db3912b869 100644 --- a/arch/x86/kernel/time_64.c +++ b/arch/x86/kernel/time_64.c @@ -67,12 +67,9 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) global_clock_event->event_handler(global_clock_event); -#ifdef CONFIG_MCA - if (MCA_bus) { - u8 irq_v = inb_p(0x61); /* read the current state */ - outb_p(irq_v|0x80, 0x61); /* reset the IRQ */ - } -#endif + /* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */ + if (MCA_bus) + outb_p(inb_p(0x61)| 0x80, 0x61); return IRQ_HANDLED; } -- cgit v1.2.3-70-g09d2 From 454ede7eebf91b92ab1eafe10c6b6ed04de29bf8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 16:07:40 +0200 Subject: x86: Make timer setup and global variables the same in time_32/64.c The timer and timer irq setup code is identical in 32 and 64 bit. Make it the same formatting as well. Also add the global variables under the necessary ifdefs to both files. Signed-off-by: Thomas Gleixner --- arch/x86/kernel/time_32.c | 8 +++++--- arch/x86/kernel/time_64.c | 38 ++++++++++++++++++++++++++++++-------- 2 files changed, 35 insertions(+), 11 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c index ec729cdcfa3..186abc577b2 100644 --- a/arch/x86/kernel/time_32.c +++ b/arch/x86/kernel/time_32.c @@ -27,6 +27,10 @@ int timer_ack; #endif +#ifdef CONFIG_X86_64 +volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; +#endif + unsigned long profile_pc(struct pt_regs *regs) { unsigned long pc = instruction_pointer(regs); @@ -53,9 +57,7 @@ unsigned long profile_pc(struct pt_regs *regs) EXPORT_SYMBOL(profile_pc); /* - * This is the same as the above, except we _also_ save the current - * Time Stamp Counter value at the time of the timer interrupt, so that - * we later on can estimate the time of day more exactly. + * Default timer interrupt handler for PIT/HPET */ static irqreturn_t timer_interrupt(int irq, void *dev_id) { diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c index 7db3912b869..78cbdf5c006 100644 --- a/arch/x86/kernel/time_64.c +++ b/arch/x86/kernel/time_64.c @@ -23,7 +23,13 @@ #include #include +#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC) +int timer_ack; +#endif + +#ifdef CONFIG_X86_64 volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; +#endif unsigned long profile_pc(struct pt_regs *regs) { @@ -47,8 +53,12 @@ unsigned long profile_pc(struct pt_regs *regs) } EXPORT_SYMBOL(profile_pc); +/* + * Default timer interrupt handler for PIT/HPET + */ static irqreturn_t timer_interrupt(int irq, void *dev_id) { + /* Keep nmi watchdog up to date */ inc_irq_stat(irq0_irqs); /* Optimized out for !IO_APIC and x86_64 */ @@ -74,8 +84,10 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -/* calibrate_cpu is used on systems with fixed rate TSCs to determine - * processor frequency */ +/* + * calibrate_cpu is used on systems with fixed rate TSCs to determine + * processor frequency + */ #define TICK_COUNT 100000000 unsigned long __init calibrate_cpu(void) { @@ -122,18 +134,24 @@ unsigned long __init calibrate_cpu(void) return pmc_now * tsc_khz / (tsc_now - tsc_start); } -static struct irqaction irq0 = { - .handler = timer_interrupt, - .flags = IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING | IRQF_TIMER, - .name = "timer" +static struct irqaction irq0 = { + .handler = timer_interrupt, + .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, + .name = "timer" }; +void __init setup_default_timer_irq(void) +{ + irq0.mask = cpumask_of_cpu(0); + setup_irq(0, &irq0); +} + +/* Default timer init function */ void __init hpet_time_init(void) { if (!hpet_enable()) setup_pit_timer(); - - setup_irq(0, &irq0); + setup_default_timer_irq(); } static void x86_late_time_init(void) @@ -141,6 +159,10 @@ static void x86_late_time_init(void) x86_init.timers.timer_init(); } +/* + * Initialize TSC and delay the periodic timer init to + * late x86_late_time_init() so ioremap works. + */ void __init time_init(void) { tsc_init(); -- cgit v1.2.3-70-g09d2 From 08047c4f1740c7cee75d58e2919d48c09f951649 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 16:27:41 +0200 Subject: x86: Move calibrate_cpu to tsc.c Move the code where it's only user is. Also we need to look whether this hardwired hackery might interfere with perfcounters. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/time.h | 2 -- arch/x86/kernel/time_32.c | 1 - arch/x86/kernel/time_64.c | 51 ---------------------------------------- arch/x86/kernel/tsc.c | 57 +++++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 55 insertions(+), 56 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/time.h b/arch/x86/include/asm/time.h index 91bb162b5a3..9c5608b21c2 100644 --- a/arch/x86/include/asm/time.h +++ b/arch/x86/include/asm/time.h @@ -57,6 +57,4 @@ extern void time_init(void); #endif /* CONFIG_PARAVIRT */ -extern unsigned long __init calibrate_cpu(void); - #endif /* _ASM_X86_TIME_H */ diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c index 186abc577b2..fd876cc7748 100644 --- a/arch/x86/kernel/time_32.c +++ b/arch/x86/kernel/time_32.c @@ -21,7 +21,6 @@ #include #include #include -#include #if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC) int timer_ack; diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c index 78cbdf5c006..e59a40ebff1 100644 --- a/arch/x86/kernel/time_64.c +++ b/arch/x86/kernel/time_64.c @@ -21,7 +21,6 @@ #include #include #include -#include #if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC) int timer_ack; @@ -84,56 +83,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -/* - * calibrate_cpu is used on systems with fixed rate TSCs to determine - * processor frequency - */ -#define TICK_COUNT 100000000 -unsigned long __init calibrate_cpu(void) -{ - int tsc_start, tsc_now; - int i, no_ctr_free; - unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0; - unsigned long flags; - - for (i = 0; i < 4; i++) - if (avail_to_resrv_perfctr_nmi_bit(i)) - break; - no_ctr_free = (i == 4); - if (no_ctr_free) { - WARN(1, KERN_WARNING "Warning: AMD perfctrs busy ... " - "cpu_khz value may be incorrect.\n"); - i = 3; - rdmsrl(MSR_K7_EVNTSEL3, evntsel3); - wrmsrl(MSR_K7_EVNTSEL3, 0); - rdmsrl(MSR_K7_PERFCTR3, pmc3); - } else { - reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i); - reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i); - } - local_irq_save(flags); - /* start measuring cycles, incrementing from 0 */ - wrmsrl(MSR_K7_PERFCTR0 + i, 0); - wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76); - rdtscl(tsc_start); - do { - rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now); - tsc_now = get_cycles(); - } while ((tsc_now - tsc_start) < TICK_COUNT); - - local_irq_restore(flags); - if (no_ctr_free) { - wrmsrl(MSR_K7_EVNTSEL3, 0); - wrmsrl(MSR_K7_PERFCTR3, pmc3); - wrmsrl(MSR_K7_EVNTSEL3, evntsel3); - } else { - release_perfctr_nmi(MSR_K7_PERFCTR0 + i); - release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); - } - - return pmc_now * tsc_khz / (tsc_now - tsc_start); -} - static struct irqaction irq0 = { .handler = timer_interrupt, .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 652bc214eeb..97a0bcbad10 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -17,6 +17,7 @@ #include #include #include +#include unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -852,6 +853,60 @@ static void __init init_tsc_clocksource(void) clocksource_register(&clocksource_tsc); } +#ifdef CONFIG_X86_64 +/* + * calibrate_cpu is used on systems with fixed rate TSCs to determine + * processor frequency + */ +#define TICK_COUNT 100000000 +static unsigned long __init calibrate_cpu(void) +{ + int tsc_start, tsc_now; + int i, no_ctr_free; + unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0; + unsigned long flags; + + for (i = 0; i < 4; i++) + if (avail_to_resrv_perfctr_nmi_bit(i)) + break; + no_ctr_free = (i == 4); + if (no_ctr_free) { + WARN(1, KERN_WARNING "Warning: AMD perfctrs busy ... " + "cpu_khz value may be incorrect.\n"); + i = 3; + rdmsrl(MSR_K7_EVNTSEL3, evntsel3); + wrmsrl(MSR_K7_EVNTSEL3, 0); + rdmsrl(MSR_K7_PERFCTR3, pmc3); + } else { + reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i); + reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i); + } + local_irq_save(flags); + /* start measuring cycles, incrementing from 0 */ + wrmsrl(MSR_K7_PERFCTR0 + i, 0); + wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76); + rdtscl(tsc_start); + do { + rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now); + tsc_now = get_cycles(); + } while ((tsc_now - tsc_start) < TICK_COUNT); + + local_irq_restore(flags); + if (no_ctr_free) { + wrmsrl(MSR_K7_EVNTSEL3, 0); + wrmsrl(MSR_K7_PERFCTR3, pmc3); + wrmsrl(MSR_K7_EVNTSEL3, evntsel3); + } else { + release_perfctr_nmi(MSR_K7_PERFCTR0 + i); + release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); + } + + return pmc_now * tsc_khz / (tsc_now - tsc_start); +} +#else +static inline unsigned long calibrate_cpu(void) { return cpu_khz; } +#endif + void __init tsc_init(void) { u64 lpj; @@ -870,11 +925,9 @@ void __init tsc_init(void) return; } -#ifdef CONFIG_X86_64 if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) && (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)) cpu_khz = calibrate_cpu(); -#endif printk("Detected %lu.%03lu MHz processor.\n", (unsigned long)cpu_khz / 1000, -- cgit v1.2.3-70-g09d2 From ef4512882dbe9978e7a18ccbcb4cb45705ce5560 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 21 Aug 2009 13:24:08 +0200 Subject: x86: time_32/64.c unify profile_pc The code is identical except for the formatting and a useless #ifdef. Make it the same. Signed-off-by: Thomas Gleixner --- arch/x86/kernel/time_32.c | 13 ++++++------- arch/x86/kernel/time_64.c | 8 +++++--- 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c index fd876cc7748..fda0c34da75 100644 --- a/arch/x86/kernel/time_32.c +++ b/arch/x86/kernel/time_32.c @@ -34,23 +34,22 @@ unsigned long profile_pc(struct pt_regs *regs) { unsigned long pc = instruction_pointer(regs); -#ifdef CONFIG_SMP if (!user_mode_vm(regs) && in_lock_functions(pc)) { #ifdef CONFIG_FRAME_POINTER return *(unsigned long *)(regs->bp + sizeof(long)); #else - unsigned long *sp = (unsigned long *)®s->sp; - - /* Return address is either directly at stack pointer - or above a saved flags. Eflags has bits 22-31 zero, - kernel addresses don't. */ + unsigned long *sp = (unsigned long *)regs->sp; + /* + * Return address is either directly at stack pointer + * or above a saved flags. Eflags has bits 22-31 zero, + * kernel addresses don't. + */ if (sp[0] >> 22) return sp[0]; if (sp[1] >> 22) return sp[1]; #endif } -#endif return pc; } EXPORT_SYMBOL(profile_pc); diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c index e59a40ebff1..fda0c34da75 100644 --- a/arch/x86/kernel/time_64.c +++ b/arch/x86/kernel/time_64.c @@ -34,14 +34,16 @@ unsigned long profile_pc(struct pt_regs *regs) { unsigned long pc = instruction_pointer(regs); - /* Assume the lock function has either no stack frame or a copy - of flags from PUSHF - Eflags always has bits 22 and up cleared unlike kernel addresses. */ if (!user_mode_vm(regs) && in_lock_functions(pc)) { #ifdef CONFIG_FRAME_POINTER return *(unsigned long *)(regs->bp + sizeof(long)); #else unsigned long *sp = (unsigned long *)regs->sp; + /* + * Return address is either directly at stack pointer + * or above a saved flags. Eflags has bits 22-31 zero, + * kernel addresses don't. + */ if (sp[0] >> 22) return sp[0]; if (sp[1] >> 22) -- cgit v1.2.3-70-g09d2 From 47926214d8b2bef13b2be57c500194a804f16198 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 16:47:19 +0200 Subject: x86: Replace the now identical time_32/64.c by time.c Remove the redundant copy. Signed-off-by: Thomas Gleixner --- arch/x86/kernel/Makefile | 2 +- arch/x86/kernel/time.c | 121 ++++++++++++++++++++++++++++++++++++++++++++++ arch/x86/kernel/time_32.c | 121 ---------------------------------------------- arch/x86/kernel/time_64.c | 121 ---------------------------------------------- 4 files changed, 122 insertions(+), 243 deletions(-) create mode 100644 arch/x86/kernel/time.c delete mode 100644 arch/x86/kernel/time_32.c delete mode 100644 arch/x86/kernel/time_64.c (limited to 'arch/x86') diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 313ed6fca9b..ccf3db607c2 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -31,7 +31,7 @@ GCOV_PROFILE_paravirt.o := n obj-y := process_$(BITS).o signal.o entry_$(BITS).o obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o -obj-y += time_$(BITS).o ioport.o ldt.o dumpstack.o +obj-y += time.o ioport.o ldt.o dumpstack.o obj-y += setup.o x86_init.o i8259.o irqinit.o obj-$(CONFIG_X86_VISWS) += visws_quirks.o obj-$(CONFIG_X86_32) += probe_roms_32.o diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c new file mode 100644 index 00000000000..fda0c34da75 --- /dev/null +++ b/arch/x86/kernel/time.c @@ -0,0 +1,121 @@ +/* + * Copyright (c) 1991,1992,1995 Linus Torvalds + * Copyright (c) 1994 Alan Modra + * Copyright (c) 1995 Markus Kuhn + * Copyright (c) 1996 Ingo Molnar + * Copyright (c) 1998 Andrea Arcangeli + * Copyright (c) 2002,2006 Vojtech Pavlik + * Copyright (c) 2003 Andi Kleen + * + */ + +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC) +int timer_ack; +#endif + +#ifdef CONFIG_X86_64 +volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; +#endif + +unsigned long profile_pc(struct pt_regs *regs) +{ + unsigned long pc = instruction_pointer(regs); + + if (!user_mode_vm(regs) && in_lock_functions(pc)) { +#ifdef CONFIG_FRAME_POINTER + return *(unsigned long *)(regs->bp + sizeof(long)); +#else + unsigned long *sp = (unsigned long *)regs->sp; + /* + * Return address is either directly at stack pointer + * or above a saved flags. Eflags has bits 22-31 zero, + * kernel addresses don't. + */ + if (sp[0] >> 22) + return sp[0]; + if (sp[1] >> 22) + return sp[1]; +#endif + } + return pc; +} +EXPORT_SYMBOL(profile_pc); + +/* + * Default timer interrupt handler for PIT/HPET + */ +static irqreturn_t timer_interrupt(int irq, void *dev_id) +{ + /* Keep nmi watchdog up to date */ + inc_irq_stat(irq0_irqs); + + /* Optimized out for !IO_APIC and x86_64 */ + if (timer_ack) { + /* + * Subtle, when I/O APICs are used we have to ack timer IRQ + * manually to deassert NMI lines for the watchdog if run + * on an 82489DX-based system. + */ + spin_lock(&i8259A_lock); + outb(0x0c, PIC_MASTER_OCW3); + /* Ack the IRQ; AEOI will end it automatically. */ + inb(PIC_MASTER_POLL); + spin_unlock(&i8259A_lock); + } + + global_clock_event->event_handler(global_clock_event); + + /* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */ + if (MCA_bus) + outb_p(inb_p(0x61)| 0x80, 0x61); + + return IRQ_HANDLED; +} + +static struct irqaction irq0 = { + .handler = timer_interrupt, + .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, + .name = "timer" +}; + +void __init setup_default_timer_irq(void) +{ + irq0.mask = cpumask_of_cpu(0); + setup_irq(0, &irq0); +} + +/* Default timer init function */ +void __init hpet_time_init(void) +{ + if (!hpet_enable()) + setup_pit_timer(); + setup_default_timer_irq(); +} + +static void x86_late_time_init(void) +{ + x86_init.timers.timer_init(); +} + +/* + * Initialize TSC and delay the periodic timer init to + * late x86_late_time_init() so ioremap works. + */ +void __init time_init(void) +{ + tsc_init(); + late_time_init = x86_late_time_init; +} diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c deleted file mode 100644 index fda0c34da75..00000000000 --- a/arch/x86/kernel/time_32.c +++ /dev/null @@ -1,121 +0,0 @@ -/* - * Copyright (c) 1991,1992,1995 Linus Torvalds - * Copyright (c) 1994 Alan Modra - * Copyright (c) 1995 Markus Kuhn - * Copyright (c) 1996 Ingo Molnar - * Copyright (c) 1998 Andrea Arcangeli - * Copyright (c) 2002,2006 Vojtech Pavlik - * Copyright (c) 2003 Andi Kleen - * - */ - -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include - -#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC) -int timer_ack; -#endif - -#ifdef CONFIG_X86_64 -volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; -#endif - -unsigned long profile_pc(struct pt_regs *regs) -{ - unsigned long pc = instruction_pointer(regs); - - if (!user_mode_vm(regs) && in_lock_functions(pc)) { -#ifdef CONFIG_FRAME_POINTER - return *(unsigned long *)(regs->bp + sizeof(long)); -#else - unsigned long *sp = (unsigned long *)regs->sp; - /* - * Return address is either directly at stack pointer - * or above a saved flags. Eflags has bits 22-31 zero, - * kernel addresses don't. - */ - if (sp[0] >> 22) - return sp[0]; - if (sp[1] >> 22) - return sp[1]; -#endif - } - return pc; -} -EXPORT_SYMBOL(profile_pc); - -/* - * Default timer interrupt handler for PIT/HPET - */ -static irqreturn_t timer_interrupt(int irq, void *dev_id) -{ - /* Keep nmi watchdog up to date */ - inc_irq_stat(irq0_irqs); - - /* Optimized out for !IO_APIC and x86_64 */ - if (timer_ack) { - /* - * Subtle, when I/O APICs are used we have to ack timer IRQ - * manually to deassert NMI lines for the watchdog if run - * on an 82489DX-based system. - */ - spin_lock(&i8259A_lock); - outb(0x0c, PIC_MASTER_OCW3); - /* Ack the IRQ; AEOI will end it automatically. */ - inb(PIC_MASTER_POLL); - spin_unlock(&i8259A_lock); - } - - global_clock_event->event_handler(global_clock_event); - - /* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */ - if (MCA_bus) - outb_p(inb_p(0x61)| 0x80, 0x61); - - return IRQ_HANDLED; -} - -static struct irqaction irq0 = { - .handler = timer_interrupt, - .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, - .name = "timer" -}; - -void __init setup_default_timer_irq(void) -{ - irq0.mask = cpumask_of_cpu(0); - setup_irq(0, &irq0); -} - -/* Default timer init function */ -void __init hpet_time_init(void) -{ - if (!hpet_enable()) - setup_pit_timer(); - setup_default_timer_irq(); -} - -static void x86_late_time_init(void) -{ - x86_init.timers.timer_init(); -} - -/* - * Initialize TSC and delay the periodic timer init to - * late x86_late_time_init() so ioremap works. - */ -void __init time_init(void) -{ - tsc_init(); - late_time_init = x86_late_time_init; -} diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c deleted file mode 100644 index fda0c34da75..00000000000 --- a/arch/x86/kernel/time_64.c +++ /dev/null @@ -1,121 +0,0 @@ -/* - * Copyright (c) 1991,1992,1995 Linus Torvalds - * Copyright (c) 1994 Alan Modra - * Copyright (c) 1995 Markus Kuhn - * Copyright (c) 1996 Ingo Molnar - * Copyright (c) 1998 Andrea Arcangeli - * Copyright (c) 2002,2006 Vojtech Pavlik - * Copyright (c) 2003 Andi Kleen - * - */ - -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include - -#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC) -int timer_ack; -#endif - -#ifdef CONFIG_X86_64 -volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; -#endif - -unsigned long profile_pc(struct pt_regs *regs) -{ - unsigned long pc = instruction_pointer(regs); - - if (!user_mode_vm(regs) && in_lock_functions(pc)) { -#ifdef CONFIG_FRAME_POINTER - return *(unsigned long *)(regs->bp + sizeof(long)); -#else - unsigned long *sp = (unsigned long *)regs->sp; - /* - * Return address is either directly at stack pointer - * or above a saved flags. Eflags has bits 22-31 zero, - * kernel addresses don't. - */ - if (sp[0] >> 22) - return sp[0]; - if (sp[1] >> 22) - return sp[1]; -#endif - } - return pc; -} -EXPORT_SYMBOL(profile_pc); - -/* - * Default timer interrupt handler for PIT/HPET - */ -static irqreturn_t timer_interrupt(int irq, void *dev_id) -{ - /* Keep nmi watchdog up to date */ - inc_irq_stat(irq0_irqs); - - /* Optimized out for !IO_APIC and x86_64 */ - if (timer_ack) { - /* - * Subtle, when I/O APICs are used we have to ack timer IRQ - * manually to deassert NMI lines for the watchdog if run - * on an 82489DX-based system. - */ - spin_lock(&i8259A_lock); - outb(0x0c, PIC_MASTER_OCW3); - /* Ack the IRQ; AEOI will end it automatically. */ - inb(PIC_MASTER_POLL); - spin_unlock(&i8259A_lock); - } - - global_clock_event->event_handler(global_clock_event); - - /* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */ - if (MCA_bus) - outb_p(inb_p(0x61)| 0x80, 0x61); - - return IRQ_HANDLED; -} - -static struct irqaction irq0 = { - .handler = timer_interrupt, - .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, - .name = "timer" -}; - -void __init setup_default_timer_irq(void) -{ - irq0.mask = cpumask_of_cpu(0); - setup_irq(0, &irq0); -} - -/* Default timer init function */ -void __init hpet_time_init(void) -{ - if (!hpet_enable()) - setup_pit_timer(); - setup_default_timer_irq(); -} - -static void x86_late_time_init(void) -{ - x86_init.timers.timer_init(); -} - -/* - * Initialize TSC and delay the periodic timer init to - * late x86_late_time_init() so ioremap works. - */ -void __init time_init(void) -{ - tsc_init(); - late_time_init = x86_late_time_init; -} -- cgit v1.2.3-70-g09d2 From 2d826404f0bdcac2a4dd7e3c446b70d6a3b63b78 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 17:06:25 +0200 Subject: x86: Move tsc_calibration to x86_init_ops TSC calibration is modified by the vmware hypervisor and paravirt by separate means. Moorestown wants to add its own calibration routine as well. So make calibrate_tsc a proper x86_init_ops function and override it by paravirt or by the early setup of the vmware hypervisor. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/hypervisor.h | 2 +- arch/x86/include/asm/paravirt.h | 1 - arch/x86/include/asm/timer.h | 5 ----- arch/x86/include/asm/tsc.h | 3 ++- arch/x86/include/asm/vmware.h | 2 +- arch/x86/include/asm/x86_init.h | 9 +++++++++ arch/x86/kernel/cpu/hypervisor.c | 14 +++++++------- arch/x86/kernel/cpu/vmware.c | 21 ++++++++++++--------- arch/x86/kernel/kvmclock.c | 2 +- arch/x86/kernel/paravirt.c | 1 - arch/x86/kernel/setup.c | 2 +- arch/x86/kernel/tsc.c | 13 ++++--------- arch/x86/kernel/vmi_32.c | 2 +- arch/x86/kernel/vmiclock_32.c | 2 +- arch/x86/kernel/x86_init.c | 5 +++++ arch/x86/lguest/boot.c | 2 +- arch/x86/xen/enlighten.c | 3 ++- 17 files changed, 48 insertions(+), 41 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 369f5c5d09a..b78c0941e42 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -20,7 +20,7 @@ #ifndef ASM_X86__HYPERVISOR_H #define ASM_X86__HYPERVISOR_H -extern unsigned long get_hypervisor_tsc_freq(void); extern void init_hypervisor(struct cpuinfo_x86 *c); +extern void init_hypervisor_platform(void); #endif diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 11a4ba7b209..1e458a55330 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -210,7 +210,6 @@ static inline unsigned long long paravirt_sched_clock(void) { return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock); } -#define calibrate_tsc() (pv_time_ops.get_tsc_khz()) static inline unsigned long long paravirt_read_pmc(int counter) { diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 65228ccc5f0..5469630b27f 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -8,7 +8,6 @@ #define TICK_SIZE (tick_nsec / 1000) unsigned long long native_sched_clock(void); -unsigned long native_calibrate_tsc(void); extern int recalibrate_cpu_khz(void); #if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC) @@ -19,10 +18,6 @@ extern int timer_ack; extern int no_timer_check; -#ifndef CONFIG_PARAVIRT -#define calibrate_tsc() native_calibrate_tsc() -#endif - /* Accelerators for sched_clock() * convert from cycles(64bits) => nanoseconds (64bits) * basic equation: diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 38ae163cc91..c0427295e8f 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -48,7 +48,8 @@ static __always_inline cycles_t vget_cycles(void) extern void tsc_init(void); extern void mark_tsc_unstable(char *reason); extern int unsynchronized_tsc(void); -int check_tsc_unstable(void); +extern int check_tsc_unstable(void); +extern unsigned long native_calibrate_tsc(void); /* * Boot-time check whether the TSCs are synchronized across diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h index c11b7e100d8..e49ed6d2fd4 100644 --- a/arch/x86/include/asm/vmware.h +++ b/arch/x86/include/asm/vmware.h @@ -20,7 +20,7 @@ #ifndef ASM_X86__VMWARE_H #define ASM_X86__VMWARE_H -extern unsigned long vmware_get_tsc_khz(void); +extern void vmware_platform_setup(void); extern int vmware_platform(void); extern void vmware_set_feature_bits(struct cpuinfo_x86 *c); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index f8bdd2271a0..20df5187171 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -112,8 +112,17 @@ struct x86_cpuinit_ops { void (*setup_percpu_clockev)(void); }; +/** + * struct x86_platform_ops - platform specific runtime functions + * @calibrate_tsc: calibrate TSC + */ +struct x86_platform_ops { + unsigned long (*calibrate_tsc)(void); +}; + extern struct x86_init_ops x86_init; extern struct x86_cpuinit_ops x86_cpuinit; +extern struct x86_platform_ops x86_platform; extern void x86_init_noop(void); extern void x86_init_uint_noop(unsigned int unused); diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index 93ba8eeb100..08be922de33 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -34,13 +34,6 @@ detect_hypervisor_vendor(struct cpuinfo_x86 *c) c->x86_hyper_vendor = X86_HYPER_VENDOR_NONE; } -unsigned long get_hypervisor_tsc_freq(void) -{ - if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE) - return vmware_get_tsc_khz(); - return 0; -} - static inline void __cpuinit hypervisor_set_feature_bits(struct cpuinfo_x86 *c) { @@ -55,3 +48,10 @@ void __cpuinit init_hypervisor(struct cpuinfo_x86 *c) detect_hypervisor_vendor(c); hypervisor_set_feature_bits(c); } + +void __init init_hypervisor_platform(void) +{ + init_hypervisor(&boot_cpu_data); + if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE) + vmware_platform_setup(); +} diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index bc24f514ec9..0a46b4df5d8 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -24,6 +24,7 @@ #include #include #include +#include #define CPUID_VMWARE_INFO_LEAF 0x40000000 #define VMWARE_HYPERVISOR_MAGIC 0x564D5868 @@ -47,21 +48,29 @@ static inline int __vmware_platform(void) return eax != (uint32_t)-1 && ebx == VMWARE_HYPERVISOR_MAGIC; } -static unsigned long __vmware_get_tsc_khz(void) +static unsigned long vmware_get_tsc_khz(void) { uint64_t tsc_hz; uint32_t eax, ebx, ecx, edx; VMWARE_PORT(GETHZ, eax, ebx, ecx, edx); - if (ebx == UINT_MAX) - return 0; tsc_hz = eax | (((uint64_t)ebx) << 32); do_div(tsc_hz, 1000); BUG_ON(tsc_hz >> 32); return tsc_hz; } +void __init vmware_platform_setup(void) +{ + uint32_t eax, ebx, ecx, edx; + + VMWARE_PORT(GETHZ, eax, ebx, ecx, edx); + + if (ebx != UINT_MAX) + x86_platform.calibrate_tsc = vmware_get_tsc_khz; +} + /* * While checking the dmi string infomation, just checking the product * serial key should be enough, as this will always have a VMware @@ -87,12 +96,6 @@ int vmware_platform(void) return 0; } -unsigned long vmware_get_tsc_khz(void) -{ - BUG_ON(!vmware_platform()); - return __vmware_get_tsc_khz(); -} - /* * VMware hypervisor takes care of exporting a reliable TSC to the guest. * Still, due to timing difference when running on virtual cpus, the TSC can diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 64e9b5f59d2..75a21b61b86 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -187,7 +187,7 @@ void __init kvmclock_init(void) pv_time_ops.get_wallclock = kvm_get_wallclock; pv_time_ops.set_wallclock = kvm_set_wallclock; pv_time_ops.sched_clock = kvm_clock_read; - pv_time_ops.get_tsc_khz = kvm_get_tsc_khz; + x86_platform.calibrate_tsc = kvm_get_tsc_khz; #ifdef CONFIG_X86_LOCAL_APIC x86_cpuinit.setup_percpu_clockev = kvm_setup_secondary_clock; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 9c0e644a76d..7cbf898d839 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -309,7 +309,6 @@ struct pv_time_ops pv_time_ops = { .get_wallclock = native_get_wallclock, .set_wallclock = native_set_wallclock, .sched_clock = native_sched_clock, - .get_tsc_khz = native_calibrate_tsc, }; struct pv_irq_ops pv_irq_ops = { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index bb207a47c63..2d93026af7c 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -818,7 +818,7 @@ void __init setup_arch(char **cmdline_p) * VMware detection requires dmi to be available, so this * needs to be done after dmi_scan_machine, for the BP. */ - init_hypervisor(&boot_cpu_data); + init_hypervisor_platform(); x86_init.resources.probe_roms(); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 97a0bcbad10..9917632a8b4 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -18,6 +18,7 @@ #include #include #include +#include unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -401,15 +402,9 @@ unsigned long native_calibrate_tsc(void) { u64 tsc1, tsc2, delta, ref1, ref2; unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX; - unsigned long flags, latch, ms, fast_calibrate, hv_tsc_khz; + unsigned long flags, latch, ms, fast_calibrate; int hpet = is_hpet_enabled(), i, loopmin; - hv_tsc_khz = get_hypervisor_tsc_freq(); - if (hv_tsc_khz) { - printk(KERN_INFO "TSC: Frequency read from the hypervisor\n"); - return hv_tsc_khz; - } - local_irq_save(flags); fast_calibrate = quick_pit_calibrate(); local_irq_restore(flags); @@ -567,7 +562,7 @@ int recalibrate_cpu_khz(void) unsigned long cpu_khz_old = cpu_khz; if (cpu_has_tsc) { - tsc_khz = calibrate_tsc(); + tsc_khz = x86_platform.calibrate_tsc(); cpu_khz = tsc_khz; cpu_data(0).loops_per_jiffy = cpufreq_scale(cpu_data(0).loops_per_jiffy, @@ -917,7 +912,7 @@ void __init tsc_init(void) if (!cpu_has_tsc) return; - tsc_khz = calibrate_tsc(); + tsc_khz = x86_platform.calibrate_tsc(); cpu_khz = tsc_khz; if (!tsc_khz) { diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index cd7d0fbbf66..052ae81ee08 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -825,7 +825,7 @@ static inline int __init activate_vmi(void) x86_cpuinit.setup_percpu_clockev = vmi_time_ap_init; #endif pv_time_ops.sched_clock = vmi_sched_clock; - pv_time_ops.get_tsc_khz = vmi_tsc_khz; + x86_platform.calibrate_tsc = vmi_tsc_khz; /* We have true wallclock functions; disable CMOS clock sync */ no_sync_cmos_clock = 1; diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c index 2b3eb82efee..611b9e2360d 100644 --- a/arch/x86/kernel/vmiclock_32.c +++ b/arch/x86/kernel/vmiclock_32.c @@ -68,7 +68,7 @@ unsigned long long vmi_sched_clock(void) return cycles_2_ns(vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE)); } -/* paravirt_ops.get_tsc_khz = vmi_tsc_khz */ +/* x86_platform.calibrate_tsc = vmi_tsc_khz */ unsigned long vmi_tsc_khz(void) { unsigned long long khz; diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 4790b92714a..13081b92191 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -13,6 +13,7 @@ #include #include #include +#include void __cpuinit x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } @@ -67,3 +68,7 @@ struct __initdata x86_init_ops x86_init = { __cpuinitdata struct x86_cpuinit_ops x86_cpuinit = { .setup_percpu_clockev = setup_secondary_APIC_clock, }; + +struct x86_platform_ops x86_platform = { + .calibrate_tsc = native_calibrate_tsc, +}; diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 6caa8c0c793..fabe745513d 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1320,11 +1320,11 @@ __init void lguest_init(void) /* Time operations */ pv_time_ops.get_wallclock = lguest_get_wallclock; - pv_time_ops.get_tsc_khz = lguest_tsc_khz; x86_init.resources.memory_setup = lguest_memory_setup; x86_init.irqs.intr_init = lguest_init_IRQ; x86_init.timers.timer_init = lguest_time_init; + x86_platform.calibrate_tsc = lguest_tsc_khz; /* * Now is a good time to look at the implementations of these functions diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 84826b842b5..ee8cac77c8a 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -844,7 +844,6 @@ static const struct pv_init_ops xen_init_ops __initdata = { static const struct pv_time_ops xen_time_ops __initdata = { .set_wallclock = xen_set_wallclock, .get_wallclock = xen_get_wallclock, - .get_tsc_khz = xen_tsc_khz, .sched_clock = xen_sched_clock, }; @@ -980,6 +979,8 @@ asmlinkage void __init xen_start_kernel(void) x86_init.timers.setup_percpu_clockev = x86_init_noop; x86_cpuinit.setup_percpu_clockev = x86_init_noop; + x86_platform.calibrate_tsc = xen_tsc_khz; + #ifdef CONFIG_X86_64 /* * Setup percpu state. We only need to do this for 64-bit -- cgit v1.2.3-70-g09d2 From dd0a70c8f921708eba29ef9f30dde1f14a74af05 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 20 Aug 2009 16:51:07 +0200 Subject: x86: Move tsc_init to late_time_init We do not need the TSC before late_time_init. Move the tsc_init to the late time init code so we can also utilize HPET for calibration (which we claimed to do but never did except in some older kernel version). This also helps Moorestown to calibrate the TSC with the AHBT timer which needs to be initialized in late_time_init like HPET. Signed-off-by: Thomas Gleixner --- arch/x86/kernel/time.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index fda0c34da75..fcece00356a 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -108,6 +108,7 @@ void __init hpet_time_init(void) static void x86_late_time_init(void) { x86_init.timers.timer_init(); + tsc_init(); } /* @@ -116,6 +117,5 @@ static void x86_late_time_init(void) */ void __init time_init(void) { - tsc_init(); late_time_init = x86_late_time_init; } -- cgit v1.2.3-70-g09d2 From 47a3d5da70f411bc044ecd3c0593b158b09d0efa Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 29 Aug 2009 15:03:59 +0200 Subject: x86: Add early platform detection Platforms like Moorestown require early setup and want to avoid the call to reserve_ebda_region. The x86_init override is too late when the MRST detection happens in setup_arch. Move the default i386 x86_init overrides and the call to reserve_ebda_region into a separate function which is called as the default of a switch case depending on the hardware_subarch id in boot params. This allows us to add a case for MRST and let MRST have its own early setup function. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/x86_init.h | 3 +-- arch/x86/kernel/head32.c | 22 +++++++++++++++++----- arch/x86/kernel/head64.c | 3 ++- arch/x86/kernel/x86_init.c | 1 - 4 files changed, 20 insertions(+), 9 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 20df5187171..b6c89428137 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -2,6 +2,7 @@ #define _ASM_X86_PLATFORM_H #include +#include struct mpc_bus; struct mpc_cpu; @@ -34,14 +35,12 @@ struct x86_init_mpparse { * @probe_roms: probe BIOS roms * @reserve_resources: reserve the standard resources for the * platform - * @reserve_ebda_region: reserve the extended bios data area * @memory_setup: platform specific memory setup * */ struct x86_init_resources { void (*probe_roms)(void); void (*reserve_resources)(void); - void (*reserve_ebda_region)(void); char *(*memory_setup)(void); }; diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index a21398fac4f..441c075e2b8 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -15,6 +15,17 @@ #include #include #include +#include + +static void __init i386_default_early_setup(void) +{ + /* Initilize 32bit specific setup functions */ + x86_init.resources.probe_roms = probe_roms; + x86_init.resources.reserve_resources = i386_reserve_resources; + x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc; + + reserve_ebda_region(); +} void __init i386_start_kernel(void) { @@ -31,12 +42,13 @@ void __init i386_start_kernel(void) reserve_early(ramdisk_image, ramdisk_end, "RAMDISK"); } #endif - /* Initilize 32bit specific setup functions */ - x86_init.resources.probe_roms = probe_roms; - x86_init.resources.reserve_resources = i386_reserve_resources; - x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc; - x86_init.resources.reserve_ebda_region(); + /* Call the subarch specific early setup function */ + switch (boot_params.hdr.hardware_subarch) { + default: + i386_default_early_setup(); + break; + } /* * At this point everything still needed from the boot loader diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index cead8149c3d..0b06cd778fd 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -24,6 +24,7 @@ #include #include #include +#include static void __init zap_identity_mappings(void) { @@ -111,7 +112,7 @@ void __init x86_64_start_reservations(char *real_mode_data) } #endif - x86_init.resources.reserve_ebda_region(); + reserve_ebda_region(); /* * At this point everything still needed from the boot loader diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 13081b92191..24be7f39789 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -28,7 +28,6 @@ struct __initdata x86_init_ops x86_init = { .resources = { .probe_roms = x86_init_noop, .reserve_resources = reserve_standard_io_resources, - .reserve_ebda_region = reserve_ebda_region, .memory_setup = default_machine_specific_memory_setup, }, -- cgit v1.2.3-70-g09d2 From 162bc7ab01a00eba1c5d614e64a51e1268ee3f96 Mon Sep 17 00:00:00 2001 From: "Pan, Jacob jun" Date: Fri, 28 Aug 2009 14:52:47 -0700 Subject: x86: Add hardware_subarch ID for Moorestown x86 bootprotocol 2.07 has introduced hardware_subarch ID in the boot parameters provided by FW. We use it to identify Moorestown platforms. [ tglx: Cleanup and paravirt fix ] Signed-off-by: Jacob Pan Signed-off-by: Thomas Gleixner --- Documentation/x86/boot.txt | 1 + arch/x86/include/asm/bootparam.h | 10 ++++++++++ arch/x86/kernel/head_32.S | 1 + 3 files changed, 12 insertions(+) (limited to 'arch/x86') diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt index 8da3a795083..30b43e1b269 100644 --- a/Documentation/x86/boot.txt +++ b/Documentation/x86/boot.txt @@ -599,6 +599,7 @@ Protocol: 2.07+ 0x00000000 The default x86/PC environment 0x00000001 lguest 0x00000002 Xen + 0x00000003 Moorestown MID Field name: hardware_subarch_data Type: write (subarch-dependent) diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h index 1724e8de317..283a9a1b3ef 100644 --- a/arch/x86/include/asm/bootparam.h +++ b/arch/x86/include/asm/bootparam.h @@ -109,4 +109,14 @@ struct boot_params { __u8 _pad9[276]; /* 0xeec */ } __attribute__((packed)); +enum { + X86_SUBARCH_PC = 0, + X86_SUBARCH_LGUEST, + X86_SUBARCH_XEN, + X86_SUBARCH_MRST, + X86_NR_SUBARCHS, +}; + + + #endif /* _ASM_X86_BOOTPARAM_H */ diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index cc827ac9e8d..304e3f3d747 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -157,6 +157,7 @@ subarch_entries: .long default_entry /* normal x86/PC */ .long lguest_entry /* lguest hypervisor */ .long xen_entry /* Xen hypervisor */ + .long default_entry /* Moorestown MID */ num_subarch_entries = (. - subarch_entries) / 4 .previous #endif /* CONFIG_PARAVIRT */ -- cgit v1.2.3-70-g09d2 From 3f4110a48a749a1aa1c54fb807afb3f32f49711c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 29 Aug 2009 14:54:20 +0200 Subject: x86: Add Moorestown early detection Moorestown MID devices need to be detected early in the boot process to setup and do not call x86_default_early_setup as there is no EBDA region to reserve. [ Copied the minimal code from Jacobs latest MRST series ] Signed-off-by: Thomas Gleixner Cc: Jacob Pan --- arch/x86/Kconfig | 13 +++++++++++++ arch/x86/include/asm/setup.h | 6 ++++++ arch/x86/kernel/Makefile | 1 + arch/x86/kernel/head32.c | 3 +++ arch/x86/kernel/mrst.c | 24 ++++++++++++++++++++++++ 5 files changed, 47 insertions(+) create mode 100644 arch/x86/kernel/mrst.c (limited to 'arch/x86') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 13ffa5df37d..586d84557f7 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -318,6 +318,7 @@ config X86_EXTENDED_PLATFORM SGI 320/540 (Visual Workstation) Summit/EXA (IBM x440) Unisys ES7000 IA32 series + Moorestown MID devices If you have one of these systems, or if you want to build a generic distribution kernel, say Y here - otherwise say N. @@ -377,6 +378,18 @@ config X86_ELAN If unsure, choose "PC-compatible" instead. +config X86_MRST + bool "Moorestown MID platform" + depends on X86_32 + depends on X86_EXTENDED_PLATFORM + ---help--- + Moorestown is Intel's Low Power Intel Architecture (LPIA) based Moblin + Internet Device(MID) platform. Moorestown consists of two chips: + Lincroft (CPU core, graphics, and memory controller) and Langwell IOH. + Unlike standard x86 PCs, Moorestown does not have many legacy devices + nor standard legacy replacement devices/features. e.g. Moorestown does + not contain i8259, i8254, HPET, legacy BIOS, most of the io ports. + config X86_RDC321X bool "RDC R-321x SoC" depends on X86_32 diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 861e1fe2303..18e496c98ff 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -49,6 +49,12 @@ extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); extern void setup_default_timer_irq(void); +#ifdef CONFIG_X86_MRST +extern void x86_mrst_early_setup(void); +#else +static inline void x86_mrst_early_setup(void) { } +#endif + #ifndef _SETUP /* diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index ccf3db607c2..5f33316610d 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -104,6 +104,7 @@ obj-$(CONFIG_SCx200) += scx200.o scx200-y += scx200_32.o obj-$(CONFIG_OLPC) += olpc.o +obj-$(CONFIG_X86_MRST) += mrst.o microcode-y := microcode_core.o microcode-$(CONFIG_MICROCODE_INTEL) += microcode_intel.o diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 441c075e2b8..4f8e2507e8f 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -45,6 +45,9 @@ void __init i386_start_kernel(void) /* Call the subarch specific early setup function */ switch (boot_params.hdr.hardware_subarch) { + case X86_SUBARCH_MRST: + x86_mrst_early_setup(); + break; default: i386_default_early_setup(); break; diff --git a/arch/x86/kernel/mrst.c b/arch/x86/kernel/mrst.c new file mode 100644 index 00000000000..3b7078abc87 --- /dev/null +++ b/arch/x86/kernel/mrst.c @@ -0,0 +1,24 @@ +/* + * mrst.c: Intel Moorestown platform specific setup code + * + * (C) Copyright 2008 Intel Corporation + * Author: Jacob Pan (jacob.jun.pan@intel.com) + * + * 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; version 2 + * of the License. + */ +#include + +#include + +/* + * Moorestown specific x86_init function overrides and early setup + * calls. + */ +void __init x86_mrst_early_setup(void) +{ + x86_init.resources.probe_roms = x86_init_noop; + x86_init.resources.reserve_resources = x86_init_noop; +} -- cgit v1.2.3-70-g09d2 From bc07844a33734c4b2f32ef26d942d2f3ef9302ea Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 29 Aug 2009 18:09:57 +0200 Subject: x86: Distangle ioapic and i8259 The proposed Moorestown support patches use an extra feature flag mechanism to make the ioapic work w/o an i8259. There is a much simpler solution. Most i8259 specific functions are already called dependend on the irq number less than NR_IRQS_LEGACY. Replacing that constant by a read_mostly variable which can be set to 0 by the platform setup code allows us to achieve the same without any special feature flags. That trivial change allows us to proceed with MRST w/o doing a full blown overhaul of the ioapic code which would delay MRST unduly. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/io_apic.h | 2 ++ arch/x86/kernel/apic/io_apic.c | 41 +++++++++++++++++++++++++++++------------ 2 files changed, 31 insertions(+), 12 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 2b8aeb89933..e1f89a1a07e 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -143,6 +143,8 @@ extern int noioapicreroute; /* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */ extern int timer_through_8259; +extern void io_apic_disable_legacy(void); + /* * If we use the IO-APIC for IRQ routing, disable automatic * assignment of PCI IRQ's. diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 5f4687187ce..6c961290a5f 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -91,6 +91,11 @@ struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES]; /* # of MP IRQ source entries */ int mp_irq_entries; +/* Number of legacy interrupts */ +static int nr_legacy_irqs __read_mostly = NR_IRQS_LEGACY; +/* GSI interrupts */ +static int nr_irqs_gsi = NR_IRQS_LEGACY; + #if defined (CONFIG_MCA) || defined (CONFIG_EISA) int mp_bus_id_to_type[MAX_MP_BUSSES]; #endif @@ -172,6 +177,12 @@ static struct irq_cfg irq_cfgx[NR_IRQS] = { [15] = { .vector = IRQ15_VECTOR, }, }; +void __init io_apic_disable_legacy(void) +{ + nr_legacy_irqs = 0; + nr_irqs_gsi = 0; +} + int __init arch_early_irq_init(void) { struct irq_cfg *cfg; @@ -189,7 +200,7 @@ int __init arch_early_irq_init(void) desc->chip_data = &cfg[i]; zalloc_cpumask_var_node(&cfg[i].domain, GFP_NOWAIT, node); zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_NOWAIT, node); - if (i < NR_IRQS_LEGACY) + if (i < nr_legacy_irqs) cpumask_setall(cfg[i].domain); } @@ -883,7 +894,7 @@ static int __init find_isa_irq_apic(int irq, int type) */ static int EISA_ELCR(unsigned int irq) { - if (irq < NR_IRQS_LEGACY) { + if (irq < nr_legacy_irqs) { unsigned int port = 0x4d0 + (irq >> 3); return (inb(port) >> (irq & 7)) & 1; } @@ -1480,7 +1491,7 @@ static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq } ioapic_register_intr(irq, desc, trigger); - if (irq < NR_IRQS_LEGACY) + if (irq < nr_legacy_irqs) disable_8259A_irq(irq); ioapic_write_entry(apic_id, pin, entry); @@ -1851,7 +1862,7 @@ __apicdebuginit(void) print_PIC(void) unsigned int v; unsigned long flags; - if (apic_verbosity == APIC_QUIET) + if (apic_verbosity == APIC_QUIET || !nr_legacy_irqs) return; printk(KERN_DEBUG "\nprinting PIC contents\n"); @@ -1914,6 +1925,10 @@ void __init enable_IO_APIC(void) spin_unlock_irqrestore(&ioapic_lock, flags); nr_ioapic_registers[apic] = reg_01.bits.entries+1; } + + if (!nr_legacy_irqs) + return; + for(apic = 0; apic < nr_ioapics; apic++) { int pin; /* See if any of the pins is in ExtINT mode */ @@ -1968,6 +1983,9 @@ void disable_IO_APIC(void) */ clear_IO_APIC(); + if (!nr_legacy_irqs) + return; + /* * If the i8259 is routed through an IOAPIC * Put that IOAPIC in virtual wire mode @@ -2198,7 +2216,7 @@ static unsigned int startup_ioapic_irq(unsigned int irq) struct irq_cfg *cfg; spin_lock_irqsave(&ioapic_lock, flags); - if (irq < NR_IRQS_LEGACY) { + if (irq < nr_legacy_irqs) { disable_8259A_irq(irq); if (i8259A_irq_pending(irq)) was_pending = 1; @@ -2709,7 +2727,7 @@ static inline void init_IO_APIC_traps(void) * so default to an old-fashioned 8259 * interrupt if we can.. */ - if (irq < NR_IRQS_LEGACY) + if (irq < nr_legacy_irqs) make_8259A_irq(irq); else /* Strange. Oh, well.. */ @@ -3045,7 +3063,7 @@ out: * the I/O APIC in all cases now. No actual device should request * it anyway. --macro */ -#define PIC_IRQS (1 << PIC_CASCADE_IR) +#define PIC_IRQS (1UL << PIC_CASCADE_IR) void __init setup_IO_APIC(void) { @@ -3053,8 +3071,7 @@ void __init setup_IO_APIC(void) /* * calling enable_IO_APIC() is moved to setup_local_APIC for BP */ - - io_apic_irqs = ~PIC_IRQS; + io_apic_irqs = nr_legacy_irqs ? ~PIC_IRQS : ~0UL; apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n"); /* @@ -3065,7 +3082,8 @@ void __init setup_IO_APIC(void) sync_Arb_IDs(); setup_IO_APIC_irqs(); init_IO_APIC_traps(); - check_timer(); + if (nr_legacy_irqs) + check_timer(); } /* @@ -3166,7 +3184,6 @@ static int __init ioapic_init_sysfs(void) device_initcall(ioapic_init_sysfs); -static int nr_irqs_gsi = NR_IRQS_LEGACY; /* * Dynamic irq allocate and deallocation */ @@ -3907,7 +3924,7 @@ static int __io_apic_set_pci_routing(struct device *dev, int irq, /* * IRQs < 16 are already in the irq_2_pin[] map */ - if (irq >= NR_IRQS_LEGACY) { + if (irq >= nr_legacy_irqs) { cfg = desc->chip_data; add_pin_to_irq_node(cfg, node, ioapic, pin); } -- cgit v1.2.3-70-g09d2 From e11dadabf443dc3101f28b74d8b9d56870a87db4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 31 Aug 2009 15:18:40 +0200 Subject: x86: apic namespace cleanup boot_cpu_physical_apicid is a global variable and used as function argument as well. Rename the function arguments to avoid confusion. Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/apic.h | 14 +++++++------- arch/x86/kernel/apic/bigsmp_32.c | 2 +- arch/x86/kernel/apic/numaq_32.c | 2 +- arch/x86/kernel/apic/summit_32.c | 2 +- arch/x86/kernel/setup.c | 4 ++-- 5 files changed, 12 insertions(+), 12 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 6f15b29005a..d6a0f2636a6 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -292,7 +292,7 @@ struct apic { int (*cpu_present_to_apicid)(int mps_cpu); physid_mask_t (*apicid_to_cpu_present)(int phys_apicid); void (*setup_portio_remap)(void); - int (*check_phys_apicid_present)(int boot_cpu_physical_apicid); + int (*check_phys_apicid_present)(int phys_apicid); void (*enable_apic_mode)(void); int (*phys_pkg_id)(int cpuid_apic, int index_msb); @@ -426,7 +426,7 @@ extern struct apic apic_x2apic_uv_x; DECLARE_PER_CPU(int, x2apic_extra_bits); extern int default_cpu_present_to_apicid(int mps_cpu); -extern int default_check_phys_apicid_present(int boot_cpu_physical_apicid); +extern int default_check_phys_apicid_present(int phys_apicid); #endif static inline void default_wait_for_init_deassert(atomic_t *deassert) @@ -542,9 +542,9 @@ static inline int __default_cpu_present_to_apicid(int mps_cpu) } static inline int -__default_check_phys_apicid_present(int boot_cpu_physical_apicid) +__default_check_phys_apicid_present(int phys_apicid) { - return physid_isset(boot_cpu_physical_apicid, phys_cpu_present_map); + return physid_isset(phys_apicid, phys_cpu_present_map); } #ifdef CONFIG_X86_32 @@ -554,13 +554,13 @@ static inline int default_cpu_present_to_apicid(int mps_cpu) } static inline int -default_check_phys_apicid_present(int boot_cpu_physical_apicid) +default_check_phys_apicid_present(int phys_apicid) { - return __default_check_phys_apicid_present(boot_cpu_physical_apicid); + return __default_check_phys_apicid_present(phys_apicid); } #else extern int default_cpu_present_to_apicid(int mps_cpu); -extern int default_check_phys_apicid_present(int boot_cpu_physical_apicid); +extern int default_check_phys_apicid_present(int phys_apicid); #endif static inline physid_mask_t default_apicid_to_cpu_present(int phys_apicid) diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 676cdac385c..77a06413b6b 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -112,7 +112,7 @@ static physid_mask_t bigsmp_ioapic_phys_id_map(physid_mask_t phys_map) return physids_promote(0xFFL); } -static int bigsmp_check_phys_apicid_present(int boot_cpu_physical_apicid) +static int bigsmp_check_phys_apicid_present(int phys_apicid) { return 1; } diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index f1ebed6bd15..efa00e2b850 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -413,7 +413,7 @@ static inline physid_mask_t numaq_apicid_to_cpu_present(int logical_apicid) /* Where the IO area was mapped on multiquad, always 0 otherwise */ void *xquad_portio; -static inline int numaq_check_phys_apicid_present(int boot_cpu_physical_apicid) +static inline int numaq_check_phys_apicid_present(int phys_apicid) { return 1; } diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index eafdfbd1ea9..645ecc4ff0b 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -272,7 +272,7 @@ static physid_mask_t summit_apicid_to_cpu_present(int apicid) return physid_mask_of_physid(0); } -static int summit_check_phys_apicid_present(int boot_cpu_physical_apicid) +static int summit_check_phys_apicid_present(int physical_apicid) { return 1; } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 2d93026af7c..fda22ec1a93 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -129,9 +129,9 @@ int default_cpu_present_to_apicid(int mps_cpu) return __default_cpu_present_to_apicid(mps_cpu); } -int default_check_phys_apicid_present(int boot_cpu_physical_apicid) +int default_check_phys_apicid_present(int phys_apicid) { - return __default_check_phys_apicid_present(boot_cpu_physical_apicid); + return __default_check_phys_apicid_present(phys_apicid); } #endif -- cgit v1.2.3-70-g09d2 From db39d5529d347de5e2eec1a72d67fcfacae6c5a2 Mon Sep 17 00:00:00 2001 From: Mark Langsdorf Date: Fri, 21 Aug 2009 19:15:28 -0500 Subject: [CPUFREQ] Powernow-k8: Enable more than 2 low P-states Remove an obsolete check that used to prevent there being more than 2 low P-states. Now that low-to-low P-states changes are enabled, it prevents otherwise workable configurations with multiple low P-states. Signed-off-by: Mark Langsdorf Tested-by: Krists Krilovs Signed-off-by: Dave Jones --- arch/x86/kernel/cpu/cpufreq/powernow-k8.c | 29 ++++------------------------- 1 file changed, 4 insertions(+), 25 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 2a50ef89100..0cbce0481a5 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -854,6 +854,10 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) goto err_out; } + /* fill in data */ + data->numps = data->acpi_data.state_count; + powernow_k8_acpi_pst_values(data, 0); + if (cpu_family == CPU_HW_PSTATE) ret_val = fill_powernow_table_pstate(data, powernow_table); else @@ -866,11 +870,8 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) powernow_table[data->acpi_data.state_count].index = 0; data->powernow_table = powernow_table; - /* fill in data */ - data->numps = data->acpi_data.state_count; if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu) print_basics(data); - powernow_k8_acpi_pst_values(data, 0); /* notify BIOS that we exist */ acpi_processor_notify_smm(THIS_MODULE); @@ -941,7 +942,6 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table) { int i; - int cntlofreq = 0; for (i = 0; i < data->acpi_data.state_count; i++) { u32 fid; @@ -982,27 +982,6 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, continue; } - /* verify only 1 entry from the lo frequency table */ - if (fid < HI_FID_TABLE_BOTTOM) { - if (cntlofreq) { - /* if both entries are the same, - * ignore this one ... */ - if ((freq != powernow_table[cntlofreq].frequency) || - (index != powernow_table[cntlofreq].index)) { - printk(KERN_ERR PFX - "Too many lo freq table " - "entries\n"); - return 1; - } - - dprintk("double low frequency table entry, " - "ignoring it.\n"); - invalidate_entry(data, i); - continue; - } else - cntlofreq = i; - } - if (freq != (data->acpi_data.states[i].core_frequency * 1000)) { printk(KERN_INFO PFX "invalid freq entries " "%u kHz vs. %u kHz\n", freq, -- cgit v1.2.3-70-g09d2 From 1a8e42fa81e62d47cc471f7764f906bb42b27a54 Mon Sep 17 00:00:00 2001 From: Prarit Bhargava Date: Wed, 26 Aug 2009 13:19:37 -0400 Subject: [CPUFREQ] Create a blacklist for processors that should not load the acpi-cpufreq module. Create a blacklist for processors that should not load the acpi-cpufreq module. The initial entry in the blacklist function is the Intel 0f68 processor. It's specification update mentions errata AL30 which implies that cpufreq should not run on this processor. Signed-off-by: Prarit Bhargava Signed-off-by: Dave Jones --- arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index ae9b503220c..badce508406 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -588,6 +588,21 @@ static const struct dmi_system_id sw_any_bug_dmi_table[] = { }, { } }; + +static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c) +{ + /* http://www.intel.com/Assets/PDF/specupdate/314554.pdf + * AL30: A Machine Check Exception (MCE) Occurring during an + * Enhanced Intel SpeedStep Technology Ratio Change May Cause + * Both Processor Cores to Lock Up when HT is enabled*/ + if (c->x86_vendor == X86_VENDOR_INTEL) { + if ((c->x86 == 15) && + (c->x86_model == 6) && + (c->x86_mask == 8) && smt_capable()) + return -ENODEV; + } + return 0; +} #endif static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) @@ -602,6 +617,12 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) dprintk("acpi_cpufreq_cpu_init\n"); +#ifdef CONFIG_SMP + result = acpi_cpufreq_blacklist(c); + if (result) + return result; +#endif + data = kzalloc(sizeof(struct acpi_cpufreq_data), GFP_KERNEL); if (!data) return -ENOMEM; -- cgit v1.2.3-70-g09d2 From 54e2603f1a85b9725aa13518d69148b6e7061aa9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Sep 2009 08:42:26 +0200 Subject: x86: platform: Fix section annotations init_IRQ() and x86_late_time_init() are missing __init annotations. The x86 platform ops variables are annotated, but the annotation needs to be put between the variable name and the "=" of the initializer. Signed-off-by: Thomas Gleixner --- arch/x86/kernel/irqinit.c | 2 +- arch/x86/kernel/time.c | 2 +- arch/x86/kernel/x86_init.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index e0142cda239..73b16649b7d 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -140,7 +140,7 @@ void __init init_ISA_irqs(void) } } -void init_IRQ(void) +void __init init_IRQ(void) { x86_init.irqs.intr_init(); } diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index fcece00356a..e293ac56c72 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -105,7 +105,7 @@ void __init hpet_time_init(void) setup_default_timer_irq(); } -static void x86_late_time_init(void) +static __init void x86_late_time_init(void) { x86_init.timers.timer_init(); tsc_init(); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 24be7f39789..68824c7be4e 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -23,7 +23,7 @@ void __init x86_init_pgd_noop(pgd_t *unused) { } * The platform setup functions are preset with the default functions * for standard PC hardware. */ -struct __initdata x86_init_ops x86_init = { +struct x86_init_ops x86_init __initdata = { .resources = { .probe_roms = x86_init_noop, @@ -64,7 +64,7 @@ struct __initdata x86_init_ops x86_init = { }, }; -__cpuinitdata struct x86_cpuinit_ops x86_cpuinit = { +struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = { .setup_percpu_clockev = setup_secondary_APIC_clock, }; -- cgit v1.2.3-70-g09d2 From 7bd867dfb4e0357e06a3211ab2bd0e714110def3 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Thu, 10 Sep 2009 10:48:56 +0800 Subject: x86: Move get/set_wallclock to x86_platform_ops get/set_wallclock() have already a set of platform dependent implementations (default, EFI, paravirt). MRST will add another variant. Moving them to platform ops simplifies the existing code and minimizes the effort to integrate new variants. Signed-off-by: Feng Tang LKML-Reference: Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/paravirt.h | 10 ------- arch/x86/include/asm/paravirt_types.h | 4 --- arch/x86/include/asm/time.h | 50 ----------------------------------- arch/x86/include/asm/x86_init.h | 4 +++ arch/x86/kernel/efi.c | 4 +++ arch/x86/kernel/kvmclock.c | 4 +-- arch/x86/kernel/paravirt.c | 2 -- arch/x86/kernel/rtc.c | 12 +++------ arch/x86/kernel/vmi_32.c | 4 +-- arch/x86/kernel/x86_init.c | 2 ++ arch/x86/lguest/boot.c | 4 +-- arch/x86/xen/enlighten.c | 4 +-- 12 files changed, 21 insertions(+), 83 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 1e458a55330..a69ae87bd7d 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -24,16 +24,6 @@ static inline void load_sp0(struct tss_struct *tss, PVOP_VCALL2(pv_cpu_ops.load_sp0, tss, thread); } -static inline unsigned long get_wallclock(void) -{ - return PVOP_CALL0(unsigned long, pv_time_ops.get_wallclock); -} - -static inline int set_wallclock(unsigned long nowtime) -{ - return PVOP_CALL1(int, pv_time_ops.set_wallclock, nowtime); -} - /* The paravirtualized CPUID instruction. */ static inline void __cpuid(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 0d812e592e3..c25d5e3bdf9 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -88,10 +88,6 @@ struct pv_lazy_ops { }; struct pv_time_ops { - /* Set and set time of day */ - unsigned long (*get_wallclock)(void); - int (*set_wallclock)(unsigned long); - unsigned long long (*sched_clock)(void); unsigned long (*get_tsc_khz)(void); }; diff --git a/arch/x86/include/asm/time.h b/arch/x86/include/asm/time.h index 9c5608b21c2..7bdec4e9b73 100644 --- a/arch/x86/include/asm/time.h +++ b/arch/x86/include/asm/time.h @@ -4,57 +4,7 @@ extern void hpet_time_init(void); #include -#ifdef CONFIG_X86_32 -#include - -static inline unsigned long native_get_wallclock(void) -{ - unsigned long retval; - - if (efi_enabled) - retval = efi_get_time(); - else - retval = mach_get_cmos_time(); - - return retval; -} - -static inline int native_set_wallclock(unsigned long nowtime) -{ - int retval; - - if (efi_enabled) - retval = efi_set_rtc_mmss(nowtime); - else - retval = mach_set_rtc_mmss(nowtime); - - return retval; -} - -#else -extern void native_time_init_hook(void); - -static inline unsigned long native_get_wallclock(void) -{ - return mach_get_cmos_time(); -} - -static inline int native_set_wallclock(unsigned long nowtime) -{ - return mach_set_rtc_mmss(nowtime); -} - -#endif extern void time_init(void); -#ifdef CONFIG_PARAVIRT -#include -#else /* !CONFIG_PARAVIRT */ - -#define get_wallclock() native_get_wallclock() -#define set_wallclock(x) native_set_wallclock(x) - -#endif /* CONFIG_PARAVIRT */ - #endif /* _ASM_X86_TIME_H */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index b6c89428137..2c756fd4ab0 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -114,9 +114,13 @@ struct x86_cpuinit_ops { /** * struct x86_platform_ops - platform specific runtime functions * @calibrate_tsc: calibrate TSC + * @get_wallclock: get time from HW clock like RTC etc. + * @set_wallclock: set time back to HW clock */ struct x86_platform_ops { unsigned long (*calibrate_tsc)(void); + unsigned long (*get_wallclock)(void); + int (*set_wallclock)(unsigned long nowtime); }; extern struct x86_init_ops x86_init; diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c index fe26ba3e345..ad5bd988fb7 100644 --- a/arch/x86/kernel/efi.c +++ b/arch/x86/kernel/efi.c @@ -42,6 +42,7 @@ #include #include #include +#include #define EFI_DEBUG 1 #define PFX "EFI: " @@ -453,6 +454,9 @@ void __init efi_init(void) if (add_efi_memmap) do_add_efi_memmap(); + x86_platform.get_wallclock = efi_get_time; + x86_platform.set_wallclock = efi_set_rtc_mmss; + /* Setup for EFI runtime service */ reboot_type = BOOT_EFI; diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 75a21b61b86..59ab94db12e 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -184,10 +184,10 @@ void __init kvmclock_init(void) if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { if (kvm_register_clock("boot clock")) return; - pv_time_ops.get_wallclock = kvm_get_wallclock; - pv_time_ops.set_wallclock = kvm_set_wallclock; pv_time_ops.sched_clock = kvm_clock_read; x86_platform.calibrate_tsc = kvm_get_tsc_khz; + x86_platform.get_wallclock = kvm_get_wallclock; + x86_platform.set_wallclock = kvm_set_wallclock; #ifdef CONFIG_X86_LOCAL_APIC x86_cpuinit.setup_percpu_clockev = kvm_setup_secondary_clock; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 7cbf898d839..c0fb85aed43 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -306,8 +306,6 @@ struct pv_init_ops pv_init_ops = { }; struct pv_time_ops pv_time_ops = { - .get_wallclock = native_get_wallclock, - .set_wallclock = native_set_wallclock, .sched_clock = native_sched_clock, }; diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 5d465b207e7..b8652f2e685 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -8,6 +8,7 @@ #include #include +#include #include #ifdef CONFIG_X86_32 @@ -165,13 +166,13 @@ void rtc_cmos_write(unsigned char val, unsigned char addr) } EXPORT_SYMBOL(rtc_cmos_write); -static int set_rtc_mmss(unsigned long nowtime) +int update_persistent_clock(struct timespec now) { unsigned long flags; int retval; spin_lock_irqsave(&rtc_lock, flags); - retval = set_wallclock(nowtime); + retval = x86_platform.set_wallclock(now.tv_sec); spin_unlock_irqrestore(&rtc_lock, flags); return retval; @@ -183,17 +184,12 @@ unsigned long read_persistent_clock(void) unsigned long retval, flags; spin_lock_irqsave(&rtc_lock, flags); - retval = get_wallclock(); + retval = x86_platform.get_wallclock(); spin_unlock_irqrestore(&rtc_lock, flags); return retval; } -int update_persistent_clock(struct timespec now) -{ - return set_rtc_mmss(now.tv_sec); -} - unsigned long long native_read_tsc(void) { return __native_read_tsc(); diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index 052ae81ee08..31e6f6cfe53 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -818,14 +818,14 @@ static inline int __init activate_vmi(void) vmi_timer_ops.cancel_alarm = vmi_get_function(VMI_CALL_CancelAlarm); x86_init.timers.timer_init = vmi_time_init; - pv_time_ops.get_wallclock = vmi_get_wallclock; - pv_time_ops.set_wallclock = vmi_set_wallclock; #ifdef CONFIG_X86_LOCAL_APIC x86_init.timers.setup_percpu_clockev = vmi_time_bsp_init; x86_cpuinit.setup_percpu_clockev = vmi_time_ap_init; #endif pv_time_ops.sched_clock = vmi_sched_clock; x86_platform.calibrate_tsc = vmi_tsc_khz; + x86_platform.get_wallclock = vmi_get_wallclock; + x86_platform.set_wallclock = vmi_set_wallclock; /* We have true wallclock functions; disable CMOS clock sync */ no_sync_cmos_clock = 1; diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 68824c7be4e..4449a4a2c2e 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -70,4 +70,6 @@ struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = { struct x86_platform_ops x86_platform = { .calibrate_tsc = native_calibrate_tsc, + .get_wallclock = mach_get_cmos_time, + .set_wallclock = mach_set_rtc_mmss, }; diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index fabe745513d..4cb7d5d18b8 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1318,13 +1318,11 @@ __init void lguest_init(void) set_lguest_basic_apic_ops(); #endif - /* Time operations */ - pv_time_ops.get_wallclock = lguest_get_wallclock; - x86_init.resources.memory_setup = lguest_memory_setup; x86_init.irqs.intr_init = lguest_init_IRQ; x86_init.timers.timer_init = lguest_time_init; x86_platform.calibrate_tsc = lguest_tsc_khz; + x86_platform.get_wallclock = lguest_get_wallclock; /* * Now is a good time to look at the implementations of these functions diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index ee8cac77c8a..b5bf8b9119a 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -842,8 +842,6 @@ static const struct pv_init_ops xen_init_ops __initdata = { }; static const struct pv_time_ops xen_time_ops __initdata = { - .set_wallclock = xen_set_wallclock, - .get_wallclock = xen_get_wallclock, .sched_clock = xen_sched_clock, }; @@ -980,6 +978,8 @@ asmlinkage void __init xen_start_kernel(void) x86_cpuinit.setup_percpu_clockev = x86_init_noop; x86_platform.calibrate_tsc = xen_tsc_khz; + x86_platform.get_wallclock = xen_get_wallclock; + x86_platform.set_wallclock = xen_set_wallclock; #ifdef CONFIG_X86_64 /* -- cgit v1.2.3-70-g09d2 From f0adb134d8dc9993a9998dc50845ec4f6ff4fadc Mon Sep 17 00:00:00 2001 From: Kurt Roeckx Date: Wed, 16 Sep 2009 11:09:32 -0400 Subject: [CPUFREQ] Fix NULL ptr regression in powernow-k8 Fixes bugzilla #13780 From: Kurt Roeckx Signed-off-by: Dave Jones --- arch/x86/kernel/cpu/cpufreq/powernow-k8.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 0cbce0481a5..6394aa5c798 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -605,9 +605,10 @@ static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst, return 0; } -static void invalidate_entry(struct powernow_k8_data *data, unsigned int entry) +static void invalidate_entry(struct cpufreq_frequency_table *powernow_table, + unsigned int entry) { - data->powernow_table[entry].frequency = CPUFREQ_ENTRY_INVALID; + powernow_table[entry].frequency = CPUFREQ_ENTRY_INVALID; } static void print_basics(struct powernow_k8_data *data) @@ -915,13 +916,13 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, "bad value %d.\n", i, index); printk(KERN_ERR PFX "Please report to BIOS " "manufacturer\n"); - invalidate_entry(data, i); + invalidate_entry(powernow_table, i); continue; } rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi); if (!(hi & HW_PSTATE_VALID_MASK)) { dprintk("invalid pstate %d, ignoring\n", index); - invalidate_entry(data, i); + invalidate_entry(powernow_table, i); continue; } @@ -970,7 +971,7 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, /* verify frequency is OK */ if ((freq > (MAX_FREQ * 1000)) || (freq < (MIN_FREQ * 1000))) { dprintk("invalid freq %u kHz, ignoring\n", freq); - invalidate_entry(data, i); + invalidate_entry(powernow_table, i); continue; } @@ -978,7 +979,7 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, * BIOSs are using "off" to indicate invalid */ if (vid == VID_OFF) { dprintk("invalid vid %u, ignoring\n", vid); - invalidate_entry(data, i); + invalidate_entry(powernow_table, i); continue; } @@ -988,7 +989,7 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, (unsigned int) (data->acpi_data.states[i].core_frequency * 1000)); - invalidate_entry(data, i); + invalidate_entry(powernow_table, i); continue; } } -- cgit v1.2.3-70-g09d2