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

Pull kvm fixes from Paolo Bonzini:
 "A bit on the bigger side, mostly due to me being on vacation, then
  busy, then on parental leave, but there's nothing worrisome.

  ARM:
   - Multiple stolen time fixes, with a new capability to match x86
   - Fix for hugetlbfs mappings when PUD and PMD are the same level
   - Fix for hugetlbfs mappings when PTE mappings are enforced (dirty
     logging, for example)
   - Fix tracing output of 64bit values

  x86:
   - nSVM state restore fixes
   - Async page fault fixes
   - Lots of small fixes everywhere"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (25 commits)
  KVM: emulator: more strict rsm checks.
  KVM: nSVM: more strict SMM checks when returning to nested guest
  SVM: nSVM: setup nested msr permission bitmap on nested state load
  SVM: nSVM: correctly restore GIF on vmexit from nesting after migration
  x86/kvm: don't forget to ACK async PF IRQ
  x86/kvm: properly use DEFINE_IDTENTRY_SYSVEC() macro
  KVM: VMX: Don't freeze guest when event delivery causes an APIC-access exit
  KVM: SVM: avoid emulation with stale next_rip
  KVM: x86: always allow writing '0' to MSR_KVM_ASYNC_PF_EN
  KVM: SVM: Periodically schedule when unregistering regions on destroy
  KVM: MIPS: Change the definition of kvm type
  kvm x86/mmu: use KVM_REQ_MMU_SYNC to sync when needed
  KVM: nVMX: Fix the update value of nested load IA32_PERF_GLOBAL_CTRL control
  KVM: fix memory leak in kvm_io_bus_unregister_dev()
  KVM: Check the allocation of pv cpu mask
  KVM: nVMX: Update VMCS02 when L2 PAE PDPTE updates detected
  KVM: arm64: Update page shift if stage 2 block mapping not supported
  KVM: arm64: Fix address truncation in traces
  KVM: arm64: Do not try to map PUDs when they are folded into PMD
  arm64/x86: KVM: Introduce steal-time cap
  ...

5 files changed, 34 insertions, 28 deletions

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 46dc3d75cf13..b588c3b5c2f0 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -206,6 +206,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 */
 		r = 1;
 		break;
+	case KVM_CAP_STEAL_TIME:
+		r = kvm_arm_pvtime_supported();
+		break;
 	default:
 		r = kvm_arch_vm_ioctl_check_extension(kvm, ext);
 		break;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index ba00bcc0c884..9a636b8064f1 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1877,6 +1877,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	    !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) {
 		force_pte = true;
 		vma_pagesize = PAGE_SIZE;
+		vma_shift = PAGE_SHIFT;
 	}
 
 	/*
@@ -1970,7 +1971,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		(fault_status == FSC_PERM &&
 		 stage2_is_exec(mmu, fault_ipa, vma_pagesize));
 
-	if (vma_pagesize == PUD_SIZE) {
+	/*
+	 * If PUD_SIZE == PMD_SIZE, there is no real PUD level, and
+	 * all we have is a 2-level page table. Trying to map a PUD in
+	 * this case would be fatally wrong.
+	 */
+	if (PUD_SIZE != PMD_SIZE && vma_pagesize == PUD_SIZE) {
 		pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
 
 		new_pud = kvm_pud_mkhuge(new_pud);
diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c
index f7b52ce1557e..920ac43077ad 100644
--- a/arch/arm64/kvm/pvtime.c
+++ b/arch/arm64/kvm/pvtime.c
@@ -13,25 +13,22 @@
 void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
-	u64 steal;
-	__le64 steal_le;
-	u64 offset;
-	int idx;
 	u64 base = vcpu->arch.steal.base;
+	u64 last_steal = vcpu->arch.steal.last_steal;
+	u64 offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
+	u64 steal = 0;
+	int idx;
 
 	if (base == GPA_INVALID)
 		return;
 
-	/* Let's do the local bookkeeping */
-	steal = vcpu->arch.steal.steal;
-	steal += current->sched_info.run_delay - vcpu->arch.steal.last_steal;
-	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
-	vcpu->arch.steal.steal = steal;
-
-	steal_le = cpu_to_le64(steal);
 	idx = srcu_read_lock(&kvm->srcu);
-	offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
-	kvm_put_guest(kvm, base + offset, steal_le, u64);
+	if (!kvm_get_guest(kvm, base + offset, steal)) {
+		steal = le64_to_cpu(steal);
+		vcpu->arch.steal.last_steal = READ_ONCE(current->sched_info.run_delay);
+		steal += vcpu->arch.steal.last_steal - last_steal;
+		kvm_put_guest(kvm, base + offset, cpu_to_le64(steal));
+	}
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -43,7 +40,8 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
 	switch (feature) {
 	case ARM_SMCCC_HV_PV_TIME_FEATURES:
 	case ARM_SMCCC_HV_PV_TIME_ST:
-		val = SMCCC_RET_SUCCESS;
+		if (vcpu->arch.steal.base != GPA_INVALID)
+			val = SMCCC_RET_SUCCESS;
 		break;
 	}
 
@@ -64,7 +62,6 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	 * Start counting stolen time from the time the guest requests
 	 * the feature enabled.
 	 */
-	vcpu->arch.steal.steal = 0;
 	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
 
 	idx = srcu_read_lock(&kvm->srcu);
@@ -74,7 +71,7 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	return base;
 }
 
-static bool kvm_arm_pvtime_supported(void)
+bool kvm_arm_pvtime_supported(void)
 {
 	return !!sched_info_on();
 }
diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h
index 4691053c5ee4..ff0444352bba 100644
--- a/arch/arm64/kvm/trace_arm.h
+++ b/arch/arm64/kvm/trace_arm.h
@@ -23,7 +23,7 @@ TRACE_EVENT(kvm_entry,
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-	TP_printk("PC: 0x%08lx", __entry->vcpu_pc)
+	TP_printk("PC: 0x%016lx", __entry->vcpu_pc)
 );
 
 TRACE_EVENT(kvm_exit,
@@ -42,7 +42,7 @@ TRACE_EVENT(kvm_exit,
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx",
+	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%016lx",
 		  __print_symbolic(__entry->ret, kvm_arm_exception_type),
 		  __entry->esr_ec,
 		  __print_symbolic(__entry->esr_ec, kvm_arm_exception_class),
@@ -69,7 +69,7 @@ TRACE_EVENT(kvm_guest_fault,
 		__entry->ipa			= ipa;
 	),
 
-	TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx",
+	TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#016lx",
 		  __entry->ipa, __entry->hsr,
 		  __entry->hxfar, __entry->vcpu_pc)
 );
@@ -131,7 +131,7 @@ TRACE_EVENT(kvm_mmio_emulate,
 		__entry->cpsr			= cpsr;
 	),
 
-	TP_printk("Emulate MMIO at: 0x%08lx (instr: %08lx, cpsr: %08lx)",
+	TP_printk("Emulate MMIO at: 0x%016lx (instr: %08lx, cpsr: %08lx)",
 		  __entry->vcpu_pc, __entry->instr, __entry->cpsr)
 );
 
@@ -149,7 +149,7 @@ TRACE_EVENT(kvm_unmap_hva_range,
 		__entry->end		= end;
 	),
 
-	TP_printk("mmu notifier unmap range: %#08lx -- %#08lx",
+	TP_printk("mmu notifier unmap range: %#016lx -- %#016lx",
 		  __entry->start, __entry->end)
 );
 
@@ -165,7 +165,7 @@ TRACE_EVENT(kvm_set_spte_hva,
 		__entry->hva		= hva;
 	),
 
-	TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva)
+	TP_printk("mmu notifier set pte hva: %#016lx", __entry->hva)
 );
 
 TRACE_EVENT(kvm_age_hva,
@@ -182,7 +182,7 @@ TRACE_EVENT(kvm_age_hva,
 		__entry->end		= end;
 	),
 
-	TP_printk("mmu notifier age hva: %#08lx -- %#08lx",
+	TP_printk("mmu notifier age hva: %#016lx -- %#016lx",
 		  __entry->start, __entry->end)
 );
 
@@ -198,7 +198,7 @@ TRACE_EVENT(kvm_test_age_hva,
 		__entry->hva		= hva;
 	),
 
-	TP_printk("mmu notifier test age hva: %#08lx", __entry->hva)
+	TP_printk("mmu notifier test age hva: %#016lx", __entry->hva)
 );
 
 TRACE_EVENT(kvm_set_way_flush,
diff --git a/arch/arm64/kvm/trace_handle_exit.h b/arch/arm64/kvm/trace_handle_exit.h
index 2c56d1e0f5bd..8d78acc4fba7 100644
--- a/arch/arm64/kvm/trace_handle_exit.h
+++ b/arch/arm64/kvm/trace_handle_exit.h
@@ -22,7 +22,7 @@ TRACE_EVENT(kvm_wfx_arm64,
 		__entry->is_wfe  = is_wfe;
 	),
 
-	TP_printk("guest executed wf%c at: 0x%08lx",
+	TP_printk("guest executed wf%c at: 0x%016lx",
 		  __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc)
 );
 
@@ -42,7 +42,7 @@ TRACE_EVENT(kvm_hvc_arm64,
 		__entry->imm = imm;
 	),
 
-	TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx)",
+	TP_printk("HVC at 0x%016lx (r0: 0x%016lx, imm: 0x%lx)",
 		  __entry->vcpu_pc, __entry->r0, __entry->imm)
 );
 
@@ -135,7 +135,7 @@ TRACE_EVENT(trap_reg,
 		__entry->write_value = write_value;
 	),
 
-	TP_printk("%s %s reg %d (0x%08llx)", __entry->fn,  __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value)
+	TP_printk("%s %s reg %d (0x%016llx)", __entry->fn,  __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value)
 );
 
 TRACE_EVENT(kvm_handle_sys_reg,