Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "First batch of KVM changes for 4.4.

  s390:
     A bunch of fixes and optimizations for interrupt and time handling.

  PPC:
     Mostly bug fixes.

  ARM:
     No big features, but many small fixes and prerequisites including:

      - a number of fixes for the arch-timer

      - introducing proper level-triggered semantics for the arch-timers

      - a series of patches to synchronously halt a guest (prerequisite
        for IRQ forwarding)

      - some tracepoint improvements

      - a tweak for the EL2 panic handlers

      - some more VGIC cleanups getting rid of redundant state

  x86:
     Quite a few changes:

      - support for VT-d posted interrupts (i.e. PCI devices can inject
        interrupts directly into vCPUs).  This introduces a new
        component (in virt/lib/) that connects VFIO and KVM together.
        The same infrastructure will be used for ARM interrupt
        forwarding as well.

      - more Hyper-V features, though the main one Hyper-V synthetic
        interrupt controller will have to wait for 4.5.  These will let
        KVM expose Hyper-V devices.

      - nested virtualization now supports VPID (same as PCID but for
        vCPUs) which makes it quite a bit faster

      - for future hardware that supports NVDIMM, there is support for
        clflushopt, clwb, pcommit

      - support for "split irqchip", i.e.  LAPIC in kernel +
        IOAPIC/PIC/PIT in userspace, which reduces the attack surface of
        the hypervisor

      - obligatory smattering of SMM fixes

      - on the guest side, stable scheduler clock support was rewritten
        to not require help from the hypervisor"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (123 commits)
  KVM: VMX: Fix commit which broke PML
  KVM: x86: obey KVM_X86_QUIRK_CD_NW_CLEARED in kvm_set_cr0()
  KVM: x86: allow RSM from 64-bit mode
  KVM: VMX: fix SMEP and SMAP without EPT
  KVM: x86: move kvm_set_irq_inatomic to legacy device assignment
  KVM: device assignment: remove pointless #ifdefs
  KVM: x86: merge kvm_arch_set_irq with kvm_set_msi_inatomic
  KVM: x86: zero apic_arb_prio on reset
  drivers/hv: share Hyper-V SynIC constants with userspace
  KVM: x86: handle SMBASE as physical address in RSM
  KVM: x86: add read_phys to x86_emulate_ops
  KVM: x86: removing unused variable
  KVM: don't pointlessly leave KVM_COMPAT=y in non-KVM configs
  KVM: arm/arm64: Merge vgic_set_lr() and vgic_sync_lr_elrsr()
  KVM: arm/arm64: Clean up vgic_retire_lr() and surroundings
  KVM: arm/arm64: Optimize away redundant LR tracking
  KVM: s390: use simple switch statement as multiplexer
  KVM: s390: drop useless newline in debugging data
  KVM: s390: SCA must not cross page boundaries
  KVM: arm: Do not indent the arguments of DECLARE_BITMAP
  ...

1 files changed, 35 insertions, 11 deletions

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 2c7aafa70702..2bd81e302427 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -32,6 +32,7 @@
 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 cycle_t kvm_sched_clock_offset;
 
 static int parse_no_kvmclock(char *arg)
 {
@@ -92,6 +93,29 @@ static cycle_t kvm_clock_get_cycles(struct clocksource *cs)
 	return kvm_clock_read();
 }
 
+static cycle_t kvm_sched_clock_read(void)
+{
+	return kvm_clock_read() - kvm_sched_clock_offset;
+}
+
+static inline void kvm_sched_clock_init(bool stable)
+{
+	if (!stable) {
+		pv_time_ops.sched_clock = kvm_clock_read;
+		return;
+	}
+
+	kvm_sched_clock_offset = kvm_clock_read();
+	pv_time_ops.sched_clock = kvm_sched_clock_read;
+	set_sched_clock_stable();
+
+	printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n",
+			kvm_sched_clock_offset);
+
+	BUILD_BUG_ON(sizeof(kvm_sched_clock_offset) >
+	         sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time));
+}
+
 /*
  * If we don't do that, there is the possibility that the guest
  * will calibrate under heavy load - thus, getting a lower lpj -
@@ -248,7 +272,17 @@ void __init kvmclock_init(void)
 		memblock_free(mem, size);
 		return;
 	}
-	pv_time_ops.sched_clock = kvm_clock_read;
+
+	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
+		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
+
+	cpu = get_cpu();
+	vcpu_time = &hv_clock[cpu].pvti;
+	flags = pvclock_read_flags(vcpu_time);
+
+	kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT);
+	put_cpu();
+
 	x86_platform.calibrate_tsc = kvm_get_tsc_khz;
 	x86_platform.get_wallclock = kvm_get_wallclock;
 	x86_platform.set_wallclock = kvm_set_wallclock;
@@ -265,16 +299,6 @@ void __init kvmclock_init(void)
 	kvm_get_preset_lpj();
 	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
 	pv_info.name = "KVM";
-
-	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
-		pvclock_set_flags(~0);
-
-	cpu = get_cpu();
-	vcpu_time = &hv_clock[cpu].pvti;
-	flags = pvclock_read_flags(vcpu_time);
-	if (flags & PVCLOCK_COUNTS_FROM_ZERO)
-		set_sched_clock_stable();
-	put_cpu();
 }
 
 int __init kvm_setup_vsyscall_timeinfo(void)