From 3a0d7256a6fb8c13f9fac6cd63250f97a8f0d8de Mon Sep 17 00:00:00 2001
From: Glauber Costa <glommer@redhat.com>
Date: Tue, 11 May 2010 12:17:45 -0400
Subject: [PATCH] x86, paravirt: don't compute pvclock adjustments if we trust
 the tsc

If the HV told us we can fully trust the TSC, skip any
correction

Signed-off-by: Glauber Costa <glommer@redhat.com>
Acked-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/include/asm/kvm_para.h    | 5 +++++
 arch/x86/include/asm/pvclock-abi.h | 1 +
 arch/x86/kernel/kvmclock.c         | 3 +++
 arch/x86/kernel/pvclock.c          | 4 ++++
 4 files changed, 13 insertions(+)

diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index f019f8cb182e..05eba5e9a8e8 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -21,6 +21,11 @@
  */
 #define KVM_FEATURE_CLOCKSOURCE2        3
 
+/* The last 8 bits are used to indicate how to interpret the flags field
+ * in pvclock structure. If no bits are set, all flags are ignored.
+ */
+#define KVM_FEATURE_CLOCKSOURCE_STABLE_BIT	24
+
 #define MSR_KVM_WALL_CLOCK  0x11
 #define MSR_KVM_SYSTEM_TIME 0x12
 
diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
index ec5c41ac4bef..35f2d1948ada 100644
--- a/arch/x86/include/asm/pvclock-abi.h
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -39,5 +39,6 @@ struct pvclock_wall_clock {
 	u32   nsec;
 } __attribute__((__packed__));
 
+#define PVCLOCK_TSC_STABLE_BIT	(1 << 0)
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 59c740fcb9b3..eb9b76c716c2 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -215,4 +215,7 @@ void __init kvmclock_init(void)
 	clocksource_register(&kvm_clock);
 	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);
 }
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index f5bc40e1697e..239427ca02af 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -135,6 +135,10 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 		barrier();
 	} while (version != src->version);
 
+	if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) &&
+		(shadow.flags & PVCLOCK_TSC_STABLE_BIT))
+		return ret;
+
 	/*
 	 * Assumption here is that last_value, a global accumulator, always goes
 	 * forward. If we are less than that, we should not be much smaller.