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

Pull KVM fixes from Paolo Bonzini:
 "x86 bug fixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: X86: Narrow down the IPI fastpath to single target IPI
  KVM: LAPIC: Also cancel preemption timer when disarm LAPIC timer
  KVM: VMX: don't allow memory operands for inline asm that modifies SP
  KVM: LAPIC: Mark hrtimer for period or oneshot mode to expire in hard interrupt context
  KVM: SVM: Issue WBINVD after deactivating an SEV guest
  KVM: SVM: document KVM_MEM_ENCRYPT_OP, let userspace detect if SEV is available
  KVM: x86: remove bogus user-triggerable WARN_ON

5 files changed, 54 insertions, 12 deletions

diff --git a/Documentation/virt/kvm/amd-memory-encryption.rst b/Documentation/virt/kvm/amd-memory-encryption.rst
index d18c97b4e140..c3129b9ba5cb 100644
--- a/Documentation/virt/kvm/amd-memory-encryption.rst
+++ b/Documentation/virt/kvm/amd-memory-encryption.rst
@@ -53,6 +53,29 @@ key management interface to perform common hypervisor activities such as
 encrypting bootstrap code, snapshot, migrating and debugging the guest. For more
 information, see the SEV Key Management spec [api-spec]_
 
+The main ioctl to access SEV is KVM_MEM_ENCRYPT_OP.  If the argument
+to KVM_MEM_ENCRYPT_OP is NULL, the ioctl returns 0 if SEV is enabled
+and ``ENOTTY` if it is disabled (on some older versions of Linux,
+the ioctl runs normally even with a NULL argument, and therefore will
+likely return ``EFAULT``).  If non-NULL, the argument to KVM_MEM_ENCRYPT_OP
+must be a struct kvm_sev_cmd::
+
+       struct kvm_sev_cmd {
+               __u32 id;
+               __u64 data;
+               __u32 error;
+               __u32 sev_fd;
+       };
+
+
+The ``id`` field contains the subcommand, and the ``data`` field points to
+another struct containing arguments specific to command.  The ``sev_fd``
+should point to a file descriptor that is opened on the ``/dev/sev``
+device, if needed (see individual commands).
+
+On output, ``error`` is zero on success, or an error code.  Error codes
+are defined in ``<linux/psp-dev.h>`.
+
 KVM implements the following commands to support common lifecycle events of SEV
 guests, such as launching, running, snapshotting, migrating and decommissioning.
 
@@ -90,6 +113,8 @@ Returns: 0 on success, -negative on error
 
 On success, the 'handle' field contains a new handle and on error, a negative value.
 
+KVM_SEV_LAUNCH_START requires the ``sev_fd`` field to be valid.
+
 For more details, see SEV spec Section 6.2.
 
 3. KVM_SEV_LAUNCH_UPDATE_DATA
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index e3099c642fec..7356a56e6282 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1445,6 +1445,8 @@ static void limit_periodic_timer_frequency(struct kvm_lapic *apic)
 	}
 }
 
+static void cancel_hv_timer(struct kvm_lapic *apic);
+
 static void apic_update_lvtt(struct kvm_lapic *apic)
 {
 	u32 timer_mode = kvm_lapic_get_reg(apic, APIC_LVTT) &
@@ -1454,6 +1456,10 @@ static void apic_update_lvtt(struct kvm_lapic *apic)
 		if (apic_lvtt_tscdeadline(apic) != (timer_mode ==
 				APIC_LVT_TIMER_TSCDEADLINE)) {
 			hrtimer_cancel(&apic->lapic_timer.timer);
+			preempt_disable();
+			if (apic->lapic_timer.hv_timer_in_use)
+				cancel_hv_timer(apic);
+			preempt_enable();
 			kvm_lapic_set_reg(apic, APIC_TMICT, 0);
 			apic->lapic_timer.period = 0;
 			apic->lapic_timer.tscdeadline = 0;
@@ -1715,7 +1721,7 @@ static void start_sw_period(struct kvm_lapic *apic)
 
 	hrtimer_start(&apic->lapic_timer.timer,
 		apic->lapic_timer.target_expiration,
-		HRTIMER_MODE_ABS);
+		HRTIMER_MODE_ABS_HARD);
 }
 
 bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 91000501756e..50d1ebafe0b3 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1933,14 +1933,6 @@ static void sev_clflush_pages(struct page *pages[], unsigned long npages)
 static void __unregister_enc_region_locked(struct kvm *kvm,
 					   struct enc_region *region)
 {
-	/*
-	 * The guest may change the memory encryption attribute from C=0 -> C=1
-	 * or vice versa for this memory range. Lets make sure caches are
-	 * flushed to ensure that guest data gets written into memory with
-	 * correct C-bit.
-	 */
-	sev_clflush_pages(region->pages, region->npages);
-
 	sev_unpin_memory(kvm, region->pages, region->npages);
 	list_del(&region->list);
 	kfree(region);
@@ -1971,6 +1963,13 @@ static void sev_vm_destroy(struct kvm *kvm)
 	mutex_lock(&kvm->lock);
 
 	/*
+	 * Ensure that all guest tagged cache entries are flushed before
+	 * releasing the pages back to the system for use. CLFLUSH will
+	 * not do this, so issue a WBINVD.
+	 */
+	wbinvd_on_all_cpus();
+
+	/*
 	 * if userspace was terminated before unregistering the memory regions
 	 * then lets unpin all the registered memory.
 	 */
@@ -7158,6 +7157,9 @@ static int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 	if (!svm_sev_enabled())
 		return -ENOTTY;
 
+	if (!argp)
+		return 0;
+
 	if (copy_from_user(&sev_cmd, argp, sizeof(struct kvm_sev_cmd)))
 		return -EFAULT;
 
@@ -7285,6 +7287,13 @@ static int svm_unregister_enc_region(struct kvm *kvm,
 		goto failed;
 	}
 
+	/*
+	 * Ensure that all guest tagged cache entries are flushed before
+	 * releasing the pages back to the system for use. CLFLUSH will
+	 * not do this, so issue a WBINVD.
+	 */
+	wbinvd_on_all_cpus();
+
 	__unregister_enc_region_locked(kvm, region);
 
 	mutex_unlock(&kvm->lock);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 26f8f31563e9..079d9fbf278e 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6287,7 +6287,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
 #endif
 		ASM_CALL_CONSTRAINT
 		:
-		THUNK_TARGET(entry),
+		[thunk_target]"r"(entry),
 		[ss]"i"(__KERNEL_DS),
 		[cs]"i"(__KERNEL_CS)
 	);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3156e25b0774..cf95c36cb4f4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1554,7 +1554,10 @@ EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr);
  */
 static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data)
 {
-	if (lapic_in_kernel(vcpu) && apic_x2apic_mode(vcpu->arch.apic) &&
+	if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(vcpu->arch.apic))
+		return 1;
+
+	if (((data & APIC_SHORT_MASK) == APIC_DEST_NOSHORT) &&
 		((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) &&
 		((data & APIC_MODE_MASK) == APIC_DM_FIXED)) {
 
@@ -2444,7 +2447,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
 	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
 	vcpu->last_guest_tsc = tsc_timestamp;
-	WARN_ON((s64)vcpu->hv_clock.system_time < 0);
 
 	/* If the host uses TSC clocksource, then it is stable */
 	pvclock_flags = 0;