Commit 84b13499 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

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
  ...
parents b952e974 37f66bbe

Documentation/virt/kvm/api.rst

+18 −4
Original line number Diff line number Diff line
@@ -6130,7 +6130,7 @@ HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx. 
8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH

-----------------------------------



:Architecture: x86

:Architectures: x86



This capability indicates that KVM running on top of Hyper-V hypervisor

enables Direct TLB flush for its guests meaning that TLB flush
@@ -6143,19 +6143,33 @@ in CPUID and only exposes Hyper-V identification. In this case, guest 
thinks it's running on Hyper-V and only use Hyper-V hypercalls.



8.22 KVM_CAP_S390_VCPU_RESETS

-----------------------------



Architectures: s390

:Architectures: s390



This capability indicates that the KVM_S390_NORMAL_RESET and

KVM_S390_CLEAR_RESET ioctls are available.



8.23 KVM_CAP_S390_PROTECTED

---------------------------



Architecture: s390



:Architectures: s390



This capability indicates that the Ultravisor has been initialized and

KVM can therefore start protected VMs.

This capability governs the KVM_S390_PV_COMMAND ioctl and the

KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE can fail for protected

guests when the state change is invalid.



8.24 KVM_CAP_STEAL_TIME

-----------------------



:Architectures: arm64, x86



This capability indicates that KVM supports steal time accounting.

When steal time accounting is supported it may be enabled with

architecture-specific interfaces.  This capability and the architecture-

specific interfaces must be consistent, i.e. if one says the feature

is supported, than the other should as well and vice versa.  For arm64

see Documentation/virt/kvm/devices/vcpu.rst "KVM_ARM_VCPU_PVTIME_CTRL".

For x86 see Documentation/virt/kvm/msr.rst "MSR_KVM_STEAL_TIME".

arch/arm64/include/asm/kvm_host.h

+1 −1
Original line number Diff line number Diff line
@@ -368,7 +368,6 @@ struct kvm_vcpu_arch { 


	/* Guest PV state */

	struct {

		u64 steal;

		u64 last_steal;

		gpa_t base;

	} steal;
@@ -544,6 +543,7 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu); 
gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);

void kvm_update_stolen_time(struct kvm_vcpu *vcpu);



bool kvm_arm_pvtime_supported(void);

int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,

			    struct kvm_device_attr *attr);

int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,

arch/arm64/kvm/arm.c

+3 −0
Original line number Diff line number Diff line
@@ -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;

arch/arm64/kvm/mmu.c

+7 −1
Original line number Diff line number Diff line
@@ -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);

arch/arm64/kvm/pvtime.c

+13 −16
Original line number Diff line number Diff line
@@ -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);

}
@@ -43,6 +40,7 @@ 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:

		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();

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE