[PATCH 1/3] x86: increase precision of x86_platform.get/set_wallclock()

From: David Vrabel
Date: Mon May 13 2013 - 13:56:44 EST


From: David Vrabel <david.vrabel@xxxxxxxxxx>

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 <david.vrabel@xxxxxxxxxx>
---
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 ++++++-------------
include/linux/efi.h | 4 ++--
8 files changed, 32 insertions(+), 41 deletions(-)

diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h
index d354fb7..a55c7ef 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 d8d9922..828a156 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 d2c3812..0db81ab 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 198eb20..0aa2939 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 7114c63..8424d5a 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 55856b2..dd3b825 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 3d88bfd..a1947ac 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 = {
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 2bc0ad7..0068bba 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -594,8 +594,8 @@ extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size);
extern int __init efi_uart_console_only (void);
extern void efi_initialize_iomem_resources(struct resource *code_resource,
struct resource *data_resource, struct resource *bss_resource);
-extern unsigned long efi_get_time(void);
-extern int efi_set_rtc_mmss(unsigned long nowtime);
+extern void efi_get_time(struct timespec *now);
+extern int efi_set_rtc_mmss(const struct timespec *now);
extern void efi_reserve_boot_services(void);
extern struct efi_memory_map memmap;

--
1.7.2.5

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