KVM: x86: Add ioctl for KVM_KVMCLOCK_CTRL

Now that we have a flag that will tell the guest it was suspended, create an
interface for that communication using a KVM ioctl.

Signed-off-by: Eric B Munson <emunson@mgebm.net>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

Documentation/virtual/kvm/api.txt

@@ -1669,6 +1669,26 @@ at the memory location pointed to by "addr".
 The list of registers accessible using this interface is identical to the
 list in 4.64.
 
+4.70 KVM_KVMCLOCK_CTRL
+
+Capability: KVM_CAP_KVMCLOCK_CTRL
+Architectures: Any that implement pvclocks (currently x86 only)
+Type: vcpu ioctl
+Parameters: None
+Returns: 0 on success, -1 on error
+
+This signals to the host kernel that the specified guest is being paused by
+userspace.  The host will set a flag in the pvclock structure that is checked
+from the soft lockup watchdog.  The flag is part of the pvclock structure that
+is shared between guest and host, specifically the second bit of the flags
+field of the pvclock_vcpu_time_info structure.  It will be set exclusively by
+the host and read/cleared exclusively by the guest.  The guest operation of
+checking and clearing the flag must an atomic operation so
+load-link/store-conditional, or equivalent must be used.  There are two cases
+where the guest will clear the flag: when the soft lockup watchdog timer resets
+itself or when a soft lockup is detected.  This ioctl can be called any time
+after pausing the vcpu, but before it is resumed.
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by

Documentation/virtual/kvm/msr.txt

@@ -108,6 +108,10 @@ MSR_KVM_SYSTEM_TIME_NEW:  0x4b564d01
 			    |	           | time measures taken across
 		     0      |	   24      | multiple cpus are guaranteed to
 			    |		   | be monotonic
+		-------------------------------------------------------------
+			    |		   | guest vcpu has been paused by
+		     1	    |	  N/A	   | the host
+			    |		   | See 4.70 in api.txt
 		-------------------------------------------------------------
 
 	Availability of this MSR must be checked via bit 3 in 0x4000001 cpuid

arch/x86/kvm/x86.c

@@ -2147,6 +2147,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_ASYNC_PF:
 	case KVM_CAP_GET_TSC_KHZ:
 	case KVM_CAP_PCI_2_3:
+	case KVM_CAP_KVMCLOCK_CTRL:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -2597,6 +2598,23 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
 	return r;
 }
 
+/*
+ * kvm_set_guest_paused() indicates to the guest kernel that it has been
+ * stopped by the hypervisor.  This function will be called from the host only.
+ * EINVAL is returned when the host attempts to set the flag for a guest that
+ * does not support pv clocks.
+ */
+static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
+{
+	struct pvclock_vcpu_time_info *src = &vcpu->arch.hv_clock;
+	if (!vcpu->arch.time_page)
+		return -EINVAL;
+	src->flags |= PVCLOCK_GUEST_STOPPED;
+	mark_page_dirty(vcpu->kvm, vcpu->arch.time >> PAGE_SHIFT);
+	kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
+	return 0;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
@@ -2873,6 +2891,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = vcpu->arch.virtual_tsc_khz;
 		goto out;
 	}
+	case KVM_KVMCLOCK_CTRL: {
+		r = kvm_set_guest_paused(vcpu);
+		goto out;
+	}
 	default:
 		r = -EINVAL;
 	}

include/linux/kvm.h

@@ -589,6 +589,7 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_S390_UCONTROL 73
 #define KVM_CAP_SYNC_REGS 74
 #define KVM_CAP_PCI_2_3 75
+#define KVM_CAP_KVMCLOCK_CTRL 76
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -859,6 +860,8 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_ONE_REG */
 #define KVM_GET_ONE_REG		  _IOW(KVMIO,  0xab, struct kvm_one_reg)
 #define KVM_SET_ONE_REG		  _IOW(KVMIO,  0xac, struct kvm_one_reg)
+/* VM is being stopped by host */
+#define KVM_KVMCLOCK_CTRL	  _IO(KVMIO,   0xad)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)