From 3565184ed0c1ea46bea5b792da5f72a83c43e49b Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Mon, 13 May 2013 18:56:06 +0100 Subject: x86: Increase precision of x86_platform.get/set_wallclock() All the virtualized platforms (KVM, lguest and Xen) have persistent wallclocks that have more than one second of precision. read_persistent_wallclock() and update_persistent_wallclock() allow for nanosecond precision but their implementation on x86 with x86_platform.get/set_wallclock() only allows for one second precision. This means guests may see a wallclock time that is off by up to 1 second. Make set_wallclock() and get_wallclock() take a struct timespec parameter (which allows for nanosecond precision) so KVM and Xen guests may start with a more accurate wallclock time and a Xen dom0 can maintain a more accurate wallclock for guests. Signed-off-by: David Vrabel Signed-off-by: John Stultz --- arch/x86/include/asm/mc146818rtc.h | 4 ++-- arch/x86/include/asm/x86_init.h | 6 ++++-- arch/x86/kernel/kvmclock.c | 9 +++------ arch/x86/kernel/rtc.c | 17 +++++++---------- arch/x86/lguest/boot.c | 4 ++-- arch/x86/platform/efi/efi.c | 10 ++++++---- arch/x86/xen/time.c | 19 ++++++------------- 7 files changed, 30 insertions(+), 39 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h index d354fb781c57..a55c7efcc4ed 100644 --- a/arch/x86/include/asm/mc146818rtc.h +++ b/arch/x86/include/asm/mc146818rtc.h @@ -95,8 +95,8 @@ static inline unsigned char current_lock_cmos_reg(void) unsigned char rtc_cmos_read(unsigned char addr); void rtc_cmos_write(unsigned char val, unsigned char addr); -extern int mach_set_rtc_mmss(unsigned long nowtime); -extern unsigned long mach_get_cmos_time(void); +extern int mach_set_rtc_mmss(const struct timespec *now); +extern void mach_get_cmos_time(struct timespec *now); #define RTC_IRQ 8 diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index d8d99222b36a..828a1565ba57 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -142,6 +142,8 @@ struct x86_cpuinit_ops { void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node); }; +struct timespec; + /** * struct x86_platform_ops - platform specific runtime functions * @calibrate_tsc: calibrate TSC @@ -156,8 +158,8 @@ struct x86_cpuinit_ops { */ struct x86_platform_ops { unsigned long (*calibrate_tsc)(void); - unsigned long (*get_wallclock)(void); - int (*set_wallclock)(unsigned long nowtime); + void (*get_wallclock)(struct timespec *ts); + int (*set_wallclock)(const struct timespec *ts); void (*iommu_shutdown)(void); bool (*is_untracked_pat_range)(u64 start, u64 end); void (*nmi_init)(void); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index d2c381280e3c..0db81ab511cc 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -48,10 +48,9 @@ static struct pvclock_wall_clock wall_clock; * have elapsed since the hypervisor wrote the data. So we try to account for * that with system time */ -static unsigned long kvm_get_wallclock(void) +static void kvm_get_wallclock(struct timespec *now) { struct pvclock_vcpu_time_info *vcpu_time; - struct timespec ts; int low, high; int cpu; @@ -64,14 +63,12 @@ static unsigned long kvm_get_wallclock(void) cpu = smp_processor_id(); vcpu_time = &hv_clock[cpu].pvti; - pvclock_read_wallclock(&wall_clock, vcpu_time, &ts); + pvclock_read_wallclock(&wall_clock, vcpu_time, now); preempt_enable(); - - return ts.tv_sec; } -static int kvm_set_wallclock(unsigned long now) +static int kvm_set_wallclock(const struct timespec *now) { return -1; } diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 198eb201ed3b..0aa29394ed6f 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -38,8 +38,9 @@ EXPORT_SYMBOL(rtc_lock); * jump to the next second precisely 500 ms later. Check the Motorola * MC146818A or Dallas DS12887 data sheet for details. */ -int mach_set_rtc_mmss(unsigned long nowtime) +int mach_set_rtc_mmss(const struct timespec *now) { + unsigned long nowtime = now->tv_sec; struct rtc_time tm; int retval = 0; @@ -58,7 +59,7 @@ int mach_set_rtc_mmss(unsigned long nowtime) return retval; } -unsigned long mach_get_cmos_time(void) +void mach_get_cmos_time(struct timespec *now) { unsigned int status, year, mon, day, hour, min, sec, century = 0; unsigned long flags; @@ -107,7 +108,8 @@ unsigned long mach_get_cmos_time(void) } else year += CMOS_YEARS_OFFS; - return mktime(year, mon, day, hour, min, sec); + now->tv_sec = mktime(year, mon, day, hour, min, sec); + now->tv_nsec = 0; } /* Routines for accessing the CMOS RAM/RTC. */ @@ -135,18 +137,13 @@ EXPORT_SYMBOL(rtc_cmos_write); int update_persistent_clock(struct timespec now) { - return x86_platform.set_wallclock(now.tv_sec); + return x86_platform.set_wallclock(&now); } /* not static: needed by APM */ void read_persistent_clock(struct timespec *ts) { - unsigned long retval; - - retval = x86_platform.get_wallclock(); - - ts->tv_sec = retval; - ts->tv_nsec = 0; + x86_platform.get_wallclock(ts); } diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 7114c63f047d..8424d5adcfa2 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -882,9 +882,9 @@ int lguest_setup_irq(unsigned int irq) * It would be far better for everyone if the Guest had its own clock, but * until then the Host gives us the time on every interrupt. */ -static unsigned long lguest_get_wallclock(void) +static void lguest_get_wallclock(struct timespec *now) { - return lguest_data.time.tv_sec; + *now = lguest_data.time; } /* diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 55856b2310d3..dd3b82530145 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -352,8 +352,9 @@ static efi_status_t __init phys_efi_get_time(efi_time_t *tm, return status; } -int efi_set_rtc_mmss(unsigned long nowtime) +int efi_set_rtc_mmss(const struct timespec *now) { + unsigned long nowtime = now->tv_sec; efi_status_t status; efi_time_t eft; efi_time_cap_t cap; @@ -388,7 +389,7 @@ int efi_set_rtc_mmss(unsigned long nowtime) return 0; } -unsigned long efi_get_time(void) +void efi_get_time(struct timespec *now) { efi_status_t status; efi_time_t eft; @@ -398,8 +399,9 @@ unsigned long efi_get_time(void) if (status != EFI_SUCCESS) pr_err("Oops: efitime: can't read time!\n"); - return mktime(eft.year, eft.month, eft.day, eft.hour, - eft.minute, eft.second); + now->tv_sec = mktime(eft.year, eft.month, eft.day, eft.hour, + eft.minute, eft.second); + now->tv_nsec = 0; } /* diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 3d88bfdf9e1c..a1947ac2da82 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -191,32 +191,25 @@ static void xen_read_wallclock(struct timespec *ts) put_cpu_var(xen_vcpu); } -static unsigned long xen_get_wallclock(void) +static void xen_get_wallclock(struct timespec *now) { - struct timespec ts; - - xen_read_wallclock(&ts); - return ts.tv_sec; + xen_read_wallclock(now); } -static int xen_set_wallclock(unsigned long now) +static int xen_set_wallclock(const struct timespec *now) { struct xen_platform_op op; - int rc; /* do nothing for domU */ if (!xen_initial_domain()) return -1; op.cmd = XENPF_settime; - op.u.settime.secs = now; - op.u.settime.nsecs = 0; + op.u.settime.secs = now->tv_sec; + op.u.settime.nsecs = now->tv_nsec; op.u.settime.system_time = xen_clocksource_read(); - rc = HYPERVISOR_dom0_op(&op); - WARN(rc != 0, "XENPF_settime failed: now=%ld\n", now); - - return rc; + return HYPERVISOR_dom0_op(&op); } static struct clocksource xen_clocksource __read_mostly = { -- cgit v1.2.3 From ce0b098981544d9f4e910ea48f3af3e726ca6d6b Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 28 May 2013 17:03:09 -0700 Subject: x86: Fix vrtc_get_time/set_mmss to use new timespec interface The patch "x86: Increase precision of x86_platform.get/set_wallclock" changed the x86 platform set_wallclock/get_wallclock interfaces to use nsec granular timespecs instead of a second granular interface. However, that patch missed converting the vrtc code, so this patch converts those functions to use timespecs. Many thanks to the kbuild test robot for finding this! Reported-by: kbuild test robot Signed-off-by: John Stultz --- arch/x86/include/asm/mrst-vrtc.h | 4 ++-- arch/x86/platform/mrst/vrtc.c | 11 ++++++----- 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/mrst-vrtc.h b/arch/x86/include/asm/mrst-vrtc.h index 73668abdbedf..1e69a75412a4 100644 --- a/arch/x86/include/asm/mrst-vrtc.h +++ b/arch/x86/include/asm/mrst-vrtc.h @@ -3,7 +3,7 @@ extern unsigned char vrtc_cmos_read(unsigned char reg); extern void vrtc_cmos_write(unsigned char val, unsigned char reg); -extern unsigned long vrtc_get_time(void); -extern int vrtc_set_mmss(unsigned long nowtime); +extern void vrtc_get_time(struct timespec *now); +extern int vrtc_set_mmss(const struct timespec *now); #endif diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c index d62b0a3b5c14..5e355b134ba4 100644 --- a/arch/x86/platform/mrst/vrtc.c +++ b/arch/x86/platform/mrst/vrtc.c @@ -56,7 +56,7 @@ void vrtc_cmos_write(unsigned char val, unsigned char reg) } EXPORT_SYMBOL_GPL(vrtc_cmos_write); -unsigned long vrtc_get_time(void) +void vrtc_get_time(struct timespec *now) { u8 sec, min, hour, mday, mon; unsigned long flags; @@ -82,17 +82,18 @@ unsigned long vrtc_get_time(void) printk(KERN_INFO "vRTC: sec: %d min: %d hour: %d day: %d " "mon: %d year: %d\n", sec, min, hour, mday, mon, year); - return mktime(year, mon, mday, hour, min, sec); + now->tv_sec = mktime(year, mon, mday, hour, min, sec); + now->tv_nsec = 0; } -int vrtc_set_mmss(unsigned long nowtime) +int vrtc_set_mmss(const struct timespec *now) { unsigned long flags; struct rtc_time tm; int year; int retval = 0; - rtc_time_to_tm(nowtime, &tm); + rtc_time_to_tm(now->tv_sec, &tm); if (!rtc_valid_tm(&tm) && tm.tm_year >= 72) { /* * tm.year is the number of years since 1900, and the @@ -110,7 +111,7 @@ int vrtc_set_mmss(unsigned long nowtime) } else { printk(KERN_ERR "%s: Invalid vRTC value: write of %lx to vRTC failed\n", - __FUNCTION__, nowtime); + __FUNCTION__, now->tv_sec); retval = -EINVAL; } return retval; -- cgit v1.2.3 From 5584880e44e49c587059801faa2a9f7d22619c48 Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Thu, 27 Jun 2013 11:35:47 +0100 Subject: x86: xen: Sync the wallclock when the system time is set Currently the Xen wallclock is only updated every 11 minutes if NTP is synchronized to its clock source (using the sync_cmos_clock() work). If a guest is started before NTP is synchronized it may see an incorrect wallclock time. Use the pvclock_gtod notifier chain to receive a notification when the system time has changed and update the wallclock to match. This chain is called on every timer tick and we want to avoid an extra (expensive) hypercall on every tick. Because dom0 has historically never provided a very accurate wallclock and guests do not expect one, we can do this simply: the wallclock is only updated if the clock was set. Signed-off-by: David Vrabel Cc: Konrad Rzeszutek Wilk Cc: John Stultz Cc: Link: http://lkml.kernel.org/r/1372329348-20841-5-git-send-email-david.vrabel@citrix.com Signed-off-by: Thomas Gleixner --- arch/x86/xen/time.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index a1947ac2da82..3364850d23e6 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -212,6 +213,30 @@ static int xen_set_wallclock(const struct timespec *now) return HYPERVISOR_dom0_op(&op); } +static int xen_pvclock_gtod_notify(struct notifier_block *nb, unsigned long was_set, + void *priv) +{ + struct timespec now; + struct xen_platform_op op; + + if (!was_set) + return NOTIFY_OK; + + now = __current_kernel_time(); + + op.cmd = XENPF_settime; + op.u.settime.secs = now.tv_sec; + op.u.settime.nsecs = now.tv_nsec; + op.u.settime.system_time = xen_clocksource_read(); + + (void)HYPERVISOR_dom0_op(&op); + return NOTIFY_OK; +} + +static struct notifier_block xen_pvclock_gtod_notifier = { + .notifier_call = xen_pvclock_gtod_notify, +}; + static struct clocksource xen_clocksource __read_mostly = { .name = "xen", .rating = 400, @@ -473,6 +498,9 @@ static void __init xen_time_init(void) xen_setup_runstate_info(cpu); xen_setup_timer(cpu); xen_setup_cpu_clockevents(); + + if (xen_initial_domain()) + pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier); } void __init xen_init_time_ops(void) -- cgit v1.2.3 From 47433b8c9d7480a3eebd99df38e857ce85a37cee Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Thu, 27 Jun 2013 11:35:48 +0100 Subject: x86: xen: Sync the CMOS RTC as well as the Xen wallclock Adjustments to Xen's persistent clock via update_persistent_clock() don't actually persist, as the Xen wallclock is a software only clock and modifications to it do not modify the underlying CMOS RTC. The x86_platform.set_wallclock hook is there to keep the hardware RTC synchronized. On a guest this is pointless. On Dom0 we can use the native implementaion which actually updates the hardware RTC, but we still need to keep the software emulation of RTC for the guests up to date. The subscription to the pvclock_notifier allows us to emulate this easily. The notifier is called at every tick and when the clock was set. Right now we only use that notifier when the clock was set, but due to the fact that it is called periodically from the timekeeping update code, we can utilize it to emulate the NTP driven drift compensation of update_persistant_clock() for the Xen wall (software) clock. Add a 11 minutes periodic update to the pvclock_gtod notifier callback to achieve that. The static variable 'next' which maintains that 11 minutes update cycle is protected by the core code serialization so there is no need to add a Xen specific serialization mechanism. [ tglx: Massaged changelog and added a few comments ] Signed-off-by: David Vrabel Cc: Konrad Rzeszutek Wilk Cc: John Stultz Cc: Link: http://lkml.kernel.org/r/1372329348-20841-6-git-send-email-david.vrabel@citrix.com Signed-off-by: Thomas Gleixner --- arch/x86/xen/time.c | 45 ++++++++++++++++++++++++++------------------- 1 file changed, 26 insertions(+), 19 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 3364850d23e6..7a5671b4fec6 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -199,37 +199,42 @@ static void xen_get_wallclock(struct timespec *now) static int xen_set_wallclock(const struct timespec *now) { - struct xen_platform_op op; - - /* do nothing for domU */ - if (!xen_initial_domain()) - return -1; - - op.cmd = XENPF_settime; - op.u.settime.secs = now->tv_sec; - op.u.settime.nsecs = now->tv_nsec; - op.u.settime.system_time = xen_clocksource_read(); - - return HYPERVISOR_dom0_op(&op); + return -1; } -static int xen_pvclock_gtod_notify(struct notifier_block *nb, unsigned long was_set, - void *priv) +static int xen_pvclock_gtod_notify(struct notifier_block *nb, + unsigned long was_set, void *priv) { - struct timespec now; - struct xen_platform_op op; + /* Protected by the calling core code serialization */ + static struct timespec next_sync; - if (!was_set) - return NOTIFY_OK; + struct xen_platform_op op; + struct timespec now; now = __current_kernel_time(); + /* + * We only take the expensive HV call when the clock was set + * or when the 11 minutes RTC synchronization time elapsed. + */ + if (!was_set && timespec_compare(&now, &next_sync) < 0) + return NOTIFY_OK; + op.cmd = XENPF_settime; op.u.settime.secs = now.tv_sec; op.u.settime.nsecs = now.tv_nsec; op.u.settime.system_time = xen_clocksource_read(); (void)HYPERVISOR_dom0_op(&op); + + /* + * Move the next drift compensation time 11 minutes + * ahead. That's emulating the sync_cmos_clock() update for + * the hardware RTC. + */ + next_sync = now; + next_sync.tv_sec += 11 * 60; + return NOTIFY_OK; } @@ -513,7 +518,9 @@ void __init xen_init_time_ops(void) x86_platform.calibrate_tsc = xen_tsc_khz; x86_platform.get_wallclock = xen_get_wallclock; - x86_platform.set_wallclock = xen_set_wallclock; + /* Dom0 uses the native method to set the hardware RTC. */ + if (!xen_initial_domain()) + x86_platform.set_wallclock = xen_set_wallclock; } #ifdef CONFIG_XEN_PVHVM -- cgit v1.2.3