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

Pull kvm fixes from Paolo Bonzini:
 "ARM64:

   - Fix constant sign extension affecting TCR_EL2 and preventing
     running on ARMv8.7 models due to spurious bits being set

   - Fix use of helpers using PSTATE early on exit by always sampling it
     as soon as the exit takes place

   - Move pkvm's 32bit handling into a common helper

  RISC-V:

   - Fix incorrect KVM_MAX_VCPUS value

   - Unmap stage2 mapping when deleting/moving a memslot

  x86:

   - Fix and downgrade BUG_ON due to uninitialized cache

   - Many APICv and MOVE_ENC_CONTEXT_FROM fixes

   - Correctly emulate TLB flushes around nested vmentry/vmexit and when
     the nested hypervisor uses VPID

   - Prevent modifications to CPUID after the VM has run

   - Other smaller bugfixes

  Generic:

   - Memslot handling bugfixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (44 commits)
  KVM: fix avic_set_running for preemptable kernels
  KVM: VMX: clear vmx_x86_ops.sync_pir_to_irr if APICv is disabled
  KVM: SEV: accept signals in sev_lock_two_vms
  KVM: SEV: do not take kvm->lock when destroying
  KVM: SEV: Prohibit migration of a VM that has mirrors
  KVM: SEV: Do COPY_ENC_CONTEXT_FROM with both VMs locked
  selftests: sev_migrate_tests: add tests for KVM_CAP_VM_COPY_ENC_CONTEXT_FROM
  KVM: SEV: move mirror status to destination of KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM
  KVM: SEV: initialize regions_list of a mirror VM
  KVM: SEV: cleanup locking for KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM
  KVM: SEV: do not use list_replace_init on an empty list
  KVM: x86: Use a stable condition around all VT-d PI paths
  KVM: x86: check PIR even for vCPUs with disabled APICv
  KVM: VMX: prepare sync_pir_to_irr for running with APICv disabled
  KVM: selftests: page_table_test: fix calculation of guest_test_phys_mem
  KVM: x86/mmu: Handle "default" period when selectively waking kthread
  KVM: MMU: shadow nested paging does not have PKU
  KVM: x86/mmu: Remove spurious TLB flushes in TDP MMU zap collapsible path
  KVM: x86/mmu: Use yield-safe TDP MMU root iter in MMU notifier unmapping
  KVM: X86: Use vcpu->arch.walk_mmu for kvm_mmu_invlpg()
  ...

Author: torvalds

arch/arm64/include/asm/kvm_arm.h

@@ -91,7 +91,7 @@
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
 /* TCR_EL2 Registers bits */
-#define TCR_EL2_RES1		((1 << 31) | (1 << 23))
+#define TCR_EL2_RES1		((1U << 31) | (1 << 23))
 #define TCR_EL2_TBI		(1 << 20)
 #define TCR_EL2_PS_SHIFT	16
 #define TCR_EL2_PS_MASK		(7 << TCR_EL2_PS_SHIFT)
@@ -276,7 +276,7 @@
 #define CPTR_EL2_TFP_SHIFT 10
 
 /* Hyp Coprocessor Trap Register */
-#define CPTR_EL2_TCPAC	(1 << 31)
+#define CPTR_EL2_TCPAC	(1U << 31)
 #define CPTR_EL2_TAM	(1 << 30)
 #define CPTR_EL2_TTA	(1 << 20)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -403,6 +403,8 @@ typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *);
 
 static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu);
 
+static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code);
+
 /*
  * Allow the hypervisor to handle the exit with an exit handler if it has one.
  *
@@ -429,6 +431,18 @@ static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
  */
 static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
+	/*
+	 * Save PSTATE early so that we can evaluate the vcpu mode
+	 * early on.
+	 */
+	vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR);
+
+	/*
+	 * Check whether we want to repaint the state one way or
+	 * another.
+	 */
+	early_exit_filter(vcpu, exit_code);
+
 	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
 		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
 

arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h

@@ -70,7 +70,12 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->regs.pc			= read_sysreg_el2(SYS_ELR);
-	ctxt->regs.pstate		= read_sysreg_el2(SYS_SPSR);
+	/*
+	 * Guest PSTATE gets saved at guest fixup time in all
+	 * cases. We still need to handle the nVHE host side here.
+	 */
+	if (!has_vhe() && ctxt->__hyp_running_vcpu)
+		ctxt->regs.pstate	= read_sysreg_el2(SYS_SPSR);
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
 		ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2);

arch/arm64/kvm/hyp/nvhe/switch.c

@@ -233,7 +233,7 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
  * Returns false if the guest ran in AArch32 when it shouldn't have, and
  * thus should exit to the host, or true if a the guest run loop can continue.
  */
-static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code)
+static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
 
@@ -248,10 +248,7 @@ static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code)
 		vcpu->arch.target = -1;
 		*exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT);
 		*exit_code |= ARM_EXCEPTION_IL;
-		return false;
 	}
-
-	return true;
 }
 
 /* Switch to the guest for legacy non-VHE systems */
@@ -316,9 +313,6 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 		/* Jump in the fire! */
 		exit_code = __guest_enter(vcpu);
 
-		if (unlikely(!handle_aarch32_guest(vcpu, &exit_code)))
-			break;
-
 		/* And we're baaack! */
 	} while (fixup_guest_exit(vcpu, &exit_code));
 

arch/arm64/kvm/hyp/vhe/switch.c

@@ -112,6 +112,10 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
 	return hyp_exit_handlers;
 }
 
+static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+}
+
 /* Switch to the guest for VHE systems running in EL2 */
 static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 {

arch/riscv/include/asm/kvm_host.h

@@ -12,14 +12,12 @@
 #include <linux/types.h>
 #include <linux/kvm.h>
 #include <linux/kvm_types.h>
+#include <asm/csr.h>
 #include <asm/kvm_vcpu_fp.h>
 #include <asm/kvm_vcpu_timer.h>
 
-#ifdef CONFIG_64BIT
-#define KVM_MAX_VCPUS			(1U << 16)
-#else
-#define KVM_MAX_VCPUS			(1U << 9)
-#endif
+#define KVM_MAX_VCPUS			\
+	((HGATP_VMID_MASK >> HGATP_VMID_SHIFT) + 1)
 
 #define KVM_HALT_POLL_NS_DEFAULT	500000
 

arch/riscv/kvm/mmu.c

@@ -453,6 +453,12 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
+	gpa_t gpa = slot->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = slot->npages << PAGE_SHIFT;
+
+	spin_lock(&kvm->mmu_lock);
+	stage2_unmap_range(kvm, gpa, size, false);
+	spin_unlock(&kvm->mmu_lock);
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,

arch/x86/kvm/ioapic.h

@@ -81,7 +81,6 @@ struct kvm_ioapic {
 	unsigned long irq_states[IOAPIC_NUM_PINS];
 	struct kvm_io_device dev;
 	struct kvm *kvm;
-	void (*ack_notifier)(void *opaque, int irq);
 	spinlock_t lock;
 	struct rtc_status rtc_status;
 	struct delayed_work eoi_inject;

arch/x86/kvm/irq.h

@@ -56,7 +56,6 @@ struct kvm_pic {
 	struct kvm_io_device dev_master;
 	struct kvm_io_device dev_slave;
 	struct kvm_io_device dev_elcr;
-	void (*ack_notifier)(void *opaque, int irq);
 	unsigned long irq_states[PIC_NUM_PINS];
 };
 

arch/x86/kvm/lapic.c

@@ -707,7 +707,7 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
 static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr)
 {
 	int highest_irr;
-	if (apic->vcpu->arch.apicv_active)
+	if (kvm_x86_ops.sync_pir_to_irr)
 		highest_irr = static_call(kvm_x86_sync_pir_to_irr)(apic->vcpu);
 	else
 		highest_irr = apic_find_highest_irr(apic);