1 files changed, 192 insertions, 75 deletions

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 08a30986d47..d9156ceecdf 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -18,15 +18,19 @@
 
 #include <linux/clocksource.h>
 #include <linux/kvm_para.h>
-#include <asm/arch_hooks.h>
+#include <asm/pvclock.h>
 #include <asm/msr.h>
 #include <asm/apic.h>
 #include <linux/percpu.h>
-#include <asm/reboot.h>
+#include <linux/hardirq.h>
+#include <linux/memblock.h>
 
-#define KVM_SCALE 22
+#include <asm/x86_init.h>
+#include <asm/reboot.h>
 
 static int kvmclock = 1;
+static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
+static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
 
 static int parse_no_kvmclock(char *arg)
 {
@@ -36,101 +40,146 @@ static int parse_no_kvmclock(char *arg)
 early_param("no-kvmclock", parse_no_kvmclock);
 
 /* The hypervisor will put information about time periodically here */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct kvm_vcpu_time_info, hv_clock);
-#define get_clock(cpu, field) per_cpu(hv_clock, cpu).field
-
-static inline u64 kvm_get_delta(u64 last_tsc)
-{
-	int cpu = smp_processor_id();
-	u64 delta = native_read_tsc() - last_tsc;
-	return (delta * get_clock(cpu, tsc_to_system_mul)) >> KVM_SCALE;
-}
+static struct pvclock_vsyscall_time_info *hv_clock;
+static struct pvclock_wall_clock wall_clock;
 
-static struct kvm_wall_clock wall_clock;
-static cycle_t kvm_clock_read(void);
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
  * 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)
 {
-	u32 wc_sec, wc_nsec;
-	u64 delta;
-	struct timespec ts;
-	int version, nsec;
+	struct pvclock_vcpu_time_info *vcpu_time;
 	int low, high;
+	int cpu;
 
-	low = (int)__pa(&wall_clock);
-	high = ((u64)__pa(&wall_clock) >> 32);
+	low = (int)__pa_symbol(&wall_clock);
+	high = ((u64)__pa_symbol(&wall_clock) >> 32);
 
-	delta = kvm_clock_read();
+	native_write_msr(msr_kvm_wall_clock, low, high);
 
-	native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
-	do {
-		version = wall_clock.wc_version;
-		rmb();
-		wc_sec = wall_clock.wc_sec;
-		wc_nsec = wall_clock.wc_nsec;
-		rmb();
-	} while ((wall_clock.wc_version != version) || (version & 1));
+	preempt_disable();
+	cpu = smp_processor_id();
 
-	delta = kvm_clock_read() - delta;
-	delta += wc_nsec;
-	nsec = do_div(delta, NSEC_PER_SEC);
-	set_normalized_timespec(&ts, wc_sec + delta, nsec);
-	/*
-	 * Of all mechanisms of time adjustment I've tested, this one
-	 * was the champion!
-	 */
-	return ts.tv_sec + 1;
+	vcpu_time = &hv_clock[cpu].pvti;
+	pvclock_read_wallclock(&wall_clock, vcpu_time, now);
+
+	preempt_enable();
 }
 
-static int kvm_set_wallclock(unsigned long now)
+static int kvm_set_wallclock(const struct timespec *now)
 {
-	return 0;
+	return -1;
+}
+
+static cycle_t kvm_clock_read(void)
+{
+	struct pvclock_vcpu_time_info *src;
+	cycle_t ret;
+	int cpu;
+
+	preempt_disable_notrace();
+	cpu = smp_processor_id();
+	src = &hv_clock[cpu].pvti;
+	ret = pvclock_clocksource_read(src);
+	preempt_enable_notrace();
+	return ret;
+}
+
+static cycle_t kvm_clock_get_cycles(struct clocksource *cs)
+{
+	return kvm_clock_read();
 }
 
 /*
- * This is our read_clock function. The host puts an tsc timestamp each time
- * it updates a new time. Without the tsc adjustment, we can have a situation
- * in which a vcpu starts to run earlier (smaller system_time), but probes
- * time later (compared to another vcpu), leading to backwards time
+ * If we don't do that, there is the possibility that the guest
+ * will calibrate under heavy load - thus, getting a lower lpj -
+ * and execute the delays themselves without load. This is wrong,
+ * because no delay loop can finish beforehand.
+ * Any heuristics is subject to fail, because ultimately, a large
+ * poll of guests can be running and trouble each other. So we preset
+ * lpj here
  */
-static cycle_t kvm_clock_read(void)
+static unsigned long kvm_get_tsc_khz(void)
 {
-	u64 last_tsc, now;
+	struct pvclock_vcpu_time_info *src;
 	int cpu;
+	unsigned long tsc_khz;
 
 	preempt_disable();
 	cpu = smp_processor_id();
+	src = &hv_clock[cpu].pvti;
+	tsc_khz = pvclock_tsc_khz(src);
+	preempt_enable();
+	return tsc_khz;
+}
 
-	last_tsc = get_clock(cpu, tsc_timestamp);
-	now = get_clock(cpu, system_time);
+static void kvm_get_preset_lpj(void)
+{
+	unsigned long khz;
+	u64 lpj;
 
-	now += kvm_get_delta(last_tsc);
-	preempt_enable();
+	khz = kvm_get_tsc_khz();
 
-	return now;
+	lpj = ((u64)khz * 1000);
+	do_div(lpj, HZ);
+	preset_lpj = lpj;
 }
+
+bool kvm_check_and_clear_guest_paused(void)
+{
+	bool ret = false;
+	struct pvclock_vcpu_time_info *src;
+	int cpu = smp_processor_id();
+
+	if (!hv_clock)
+		return ret;
+
+	src = &hv_clock[cpu].pvti;
+	if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) {
+		src->flags &= ~PVCLOCK_GUEST_STOPPED;
+		pvclock_touch_watchdogs();
+		ret = true;
+	}
+
+	return ret;
+}
+
 static struct clocksource kvm_clock = {
 	.name = "kvm-clock",
-	.read = kvm_clock_read,
+	.read = kvm_clock_get_cycles,
 	.rating = 400,
 	.mask = CLOCKSOURCE_MASK(64),
-	.mult = 1 << KVM_SCALE,
-	.shift = KVM_SCALE,
 	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static int kvm_register_clock(void)
+int kvm_register_clock(char *txt)
 {
 	int cpu = smp_processor_id();
-	int low, high;
-	low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1;
-	high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32);
+	int low, high, ret;
+	struct pvclock_vcpu_time_info *src;
+
+	if (!hv_clock)
+		return 0;
+
+	src = &hv_clock[cpu].pvti;
+	low = (int)slow_virt_to_phys(src) | 1;
+	high = ((u64)slow_virt_to_phys(src) >> 32);
+	ret = native_write_msr_safe(msr_kvm_system_time, low, high);
+	printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
+	       cpu, high, low, txt);
+
+	return ret;
+}
 
-	return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high);
+static void kvm_save_sched_clock_state(void)
+{
+}
+
+static void kvm_restore_sched_clock_state(void)
+{
+	kvm_register_clock("primary cpu clock, resume");
 }
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -140,9 +189,7 @@ static void kvm_setup_secondary_clock(void)
 	 * Now that the first cpu already had this clocksource initialized,
 	 * we shouldn't fail.
 	 */
-	WARN_ON(kvm_register_clock());
-	/* ok, done with our trickery, call native */
-	setup_secondary_APIC_clock();
+	WARN_ON(kvm_register_clock("secondary cpu clock"));
 }
 #endif
 
@@ -157,35 +204,105 @@ static void kvm_setup_secondary_clock(void)
 #ifdef CONFIG_KEXEC
 static void kvm_crash_shutdown(struct pt_regs *regs)
 {
-	native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0);
+	native_write_msr(msr_kvm_system_time, 0, 0);
+	kvm_disable_steal_time();
 	native_machine_crash_shutdown(regs);
 }
 #endif
 
 static void kvm_shutdown(void)
 {
-	native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0);
+	native_write_msr(msr_kvm_system_time, 0, 0);
+	kvm_disable_steal_time();
 	native_machine_shutdown();
 }
 
 void __init kvmclock_init(void)
 {
+	unsigned long mem;
+	int size;
+
+	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
+
 	if (!kvm_para_available())
 		return;
 
-	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
-		if (kvm_register_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;
+	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
+		msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
+		msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
+	} else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)))
+		return;
+
+	printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
+		msr_kvm_system_time, msr_kvm_wall_clock);
+
+	mem = memblock_alloc(size, PAGE_SIZE);
+	if (!mem)
+		return;
+	hv_clock = __va(mem);
+	memset(hv_clock, 0, size);
+
+	if (kvm_register_clock("primary cpu clock")) {
+		hv_clock = NULL;
+		memblock_free(mem, size);
+		return;
+	}
+	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
-		pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock;
+	x86_cpuinit.early_percpu_clock_init =
+		kvm_setup_secondary_clock;
 #endif
-		machine_ops.shutdown  = kvm_shutdown;
+	x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
+	x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
+	machine_ops.shutdown  = kvm_shutdown;
 #ifdef CONFIG_KEXEC
-		machine_ops.crash_shutdown  = kvm_crash_shutdown;
+	machine_ops.crash_shutdown  = kvm_crash_shutdown;
 #endif
-		clocksource_register(&kvm_clock);
+	kvm_get_preset_lpj();
+	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
+	pv_info.paravirt_enabled = 1;
+	pv_info.name = "KVM";
+
+	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
+		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
+}
+
+int __init kvm_setup_vsyscall_timeinfo(void)
+{
+#ifdef CONFIG_X86_64
+	int cpu;
+	int ret;
+	u8 flags;
+	struct pvclock_vcpu_time_info *vcpu_time;
+	unsigned int size;
+
+	if (!hv_clock)
+		return 0;
+
+	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
+
+	preempt_disable();
+	cpu = smp_processor_id();
+
+	vcpu_time = &hv_clock[cpu].pvti;
+	flags = pvclock_read_flags(vcpu_time);
+
+	if (!(flags & PVCLOCK_TSC_STABLE_BIT)) {
+		preempt_enable();
+		return 1;
 	}
+
+	if ((ret = pvclock_init_vsyscall(hv_clock, size))) {
+		preempt_enable();
+		return ret;
+	}
+
+	preempt_enable();
+
+	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
+#endif
+	return 0;
 }