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

Pull KVM fixes from Paolo Bonzini:
 "ARM fixes:

   - Another state update on exit to userspace fix

   - Prevent the creation of mixed 32/64 VMs

   - Fix regression with irqbypass not restarting the guest on failed
     connect

   - Fix regression with debug register decoding resulting in
     overlapping access

   - Commit exception state on exit to usrspace

   - Fix the MMU notifier return values

   - Add missing 'static' qualifiers in the new host stage-2 code

  x86 fixes:

   - fix guest missed wakeup with assigned devices

   - fix WARN reported by syzkaller

   - do not use BIT() in UAPI headers

   - make the kvm_amd.avic parameter bool

  PPC fixes:

   - make halt polling heuristics consistent with other architectures

  selftests:

   - various fixes

   - new performance selftest memslot_perf_test

   - test UFFD minor faults in demand_paging_test"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (44 commits)
  selftests: kvm: fix overlapping addresses in memslot_perf_test
  KVM: X86: Kill off ctxt->ud
  KVM: X86: Fix warning caused by stale emulation context
  KVM: X86: Use kvm_get_linear_rip() in single-step and #DB/#BP interception
  KVM: x86/mmu: Fix comment mentioning skip_4k
  KVM: VMX: update vcpu posted-interrupt descriptor when assigning device
  KVM: rename KVM_REQ_PENDING_TIMER to KVM_REQ_UNBLOCK
  KVM: x86: add start_assignment hook to kvm_x86_ops
  KVM: LAPIC: Narrow the timer latency between wait_lapic_expire and world switch
  selftests: kvm: do only 1 memslot_perf_test run by default
  KVM: X86: Use _BITUL() macro in UAPI headers
  KVM: selftests: add shared hugetlbfs backing source type
  KVM: selftests: allow using UFFD minor faults for demand paging
  KVM: selftests: create alias mappings when using shared memory
  KVM: selftests: add shmem backing source type
  KVM: selftests: refactor vm_mem_backing_src_type flags
  KVM: selftests: allow different backing source types
  KVM: selftests: compute correct demand paging size
  KVM: selftests: simplify setup_demand_paging error handling
  KVM: selftests: Print a message if /dev/kvm is missing
  ...

Documentation/virt/kvm/vcpu-requests.rst

@@ -118,10 +118,12 @@ KVM_REQ_MMU_RELOAD
   necessary to inform each VCPU to completely refresh the tables.  This
   request is used for that.
 
-KVM_REQ_PENDING_TIMER
+KVM_REQ_UNBLOCK
 
-  This request may be made from a timer handler run on the host on behalf
-  of a VCPU.  It informs the VCPU thread to inject a timer interrupt.
+  This request informs the vCPU to exit kvm_vcpu_block.  It is used for
+  example from timer handlers that run on the host on behalf of a vCPU,
+  or in order to update the interrupt routing and ensure that assigned
+  devices will wake up the vCPU.
 
 KVM_REQ_UNHALT
 

arch/arm64/include/asm/kvm_asm.h

@@ -63,6 +63,7 @@
 #define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector		18
 #define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize		19
 #define __KVM_HOST_SMCCC_FUNC___pkvm_mark_hyp			20
+#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc			21
 
 #ifndef __ASSEMBLY__
 
@@ -201,6 +202,8 @@ extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
+extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu);
+
 extern u64 __vgic_v3_get_gic_config(void);
 extern u64 __vgic_v3_read_vmcr(void);
 extern void __vgic_v3_write_vmcr(u32 vmcr);

arch/arm64/include/asm/kvm_emulate.h

@@ -463,4 +463,9 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
 	vcpu->arch.flags |= KVM_ARM64_INCREMENT_PC;
 }
 
+static inline bool vcpu_has_feature(struct kvm_vcpu *vcpu, int feature)
+{
+	return test_bit(feature, vcpu->arch.features);
+}
+
 #endif /* __ARM64_KVM_EMULATE_H__ */

arch/arm64/kvm/arm.c

@@ -720,11 +720,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			return ret;
 	}
 
-	if (run->immediate_exit)
-		return -EINTR;
-
 	vcpu_load(vcpu);
 
+	if (run->immediate_exit) {
+		ret = -EINTR;
+		goto out;
+	}
+
 	kvm_sigset_activate(vcpu);
 
 	ret = 1;
@@ -897,6 +899,18 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 	kvm_sigset_deactivate(vcpu);
 
+out:
+	/*
+	 * In the unlikely event that we are returning to userspace
+	 * with pending exceptions or PC adjustment, commit these
+	 * adjustments in order to give userspace a consistent view of
+	 * the vcpu state. Note that this relies on __kvm_adjust_pc()
+	 * being preempt-safe on VHE.
+	 */
+	if (unlikely(vcpu->arch.flags & (KVM_ARM64_PENDING_EXCEPTION |
+					 KVM_ARM64_INCREMENT_PC)))
+		kvm_call_hyp(__kvm_adjust_pc, vcpu);
+
 	vcpu_put(vcpu);
 	return ret;
 }

arch/arm64/kvm/hyp/exception.c

@@ -296,7 +296,7 @@ static void enter_exception32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 	*vcpu_pc(vcpu) = vect_offset;
 }
 
-void kvm_inject_exception(struct kvm_vcpu *vcpu)
+static void kvm_inject_exception(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_el1_is_32bit(vcpu)) {
 		switch (vcpu->arch.flags & KVM_ARM64_EXCEPT_MASK) {
@@ -329,3 +329,19 @@ void kvm_inject_exception(struct kvm_vcpu *vcpu)
 		}
 	}
 }
+
+/*
+ * Adjust the guest PC (and potentially exception state) depending on
+ * flags provided by the emulation code.
+ */
+void __kvm_adjust_pc(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.flags & KVM_ARM64_PENDING_EXCEPTION) {
+		kvm_inject_exception(vcpu);
+		vcpu->arch.flags &= ~(KVM_ARM64_PENDING_EXCEPTION |
+				      KVM_ARM64_EXCEPT_MASK);
+	} else 	if (vcpu->arch.flags & KVM_ARM64_INCREMENT_PC) {
+		kvm_skip_instr(vcpu);
+		vcpu->arch.flags &= ~KVM_ARM64_INCREMENT_PC;
+	}
+}

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

@@ -13,8 +13,6 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_host.h>
 
-void kvm_inject_exception(struct kvm_vcpu *vcpu);
-
 static inline void kvm_skip_instr(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_mode_is_32bit(vcpu)) {
@@ -43,22 +41,6 @@ static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu)
 	write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR);
 }
 
-/*
- * Adjust the guest PC on entry, depending on flags provided by EL1
- * for the purpose of emulation (MMIO, sysreg) or exception injection.
- */
-static inline void __adjust_pc(struct kvm_vcpu *vcpu)
-{
-	if (vcpu->arch.flags & KVM_ARM64_PENDING_EXCEPTION) {
-		kvm_inject_exception(vcpu);
-		vcpu->arch.flags &= ~(KVM_ARM64_PENDING_EXCEPTION |
-				      KVM_ARM64_EXCEPT_MASK);
-	} else 	if (vcpu->arch.flags & KVM_ARM64_INCREMENT_PC) {
-		kvm_skip_instr(vcpu);
-		vcpu->arch.flags &= ~KVM_ARM64_INCREMENT_PC;
-	}
-}
-
 /*
  * Skip an instruction while host sysregs are live.
  * Assumes host is always 64-bit.

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -28,6 +28,13 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) =  __kvm_vcpu_run(kern_hyp_va(vcpu));
 }
 
+static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
+
+	__kvm_adjust_pc(kern_hyp_va(vcpu));
+}
+
 static void handle___kvm_flush_vm_context(struct kvm_cpu_context *host_ctxt)
 {
 	__kvm_flush_vm_context();
@@ -170,6 +177,7 @@ typedef void (*hcall_t)(struct kvm_cpu_context *);
 
 static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__kvm_vcpu_run),
+	HANDLE_FUNC(__kvm_adjust_pc),
 	HANDLE_FUNC(__kvm_flush_vm_context),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid),

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

@@ -23,8 +23,8 @@
 extern unsigned long hyp_nr_cpus;
 struct host_kvm host_kvm;
 
-struct hyp_pool host_s2_mem;
-struct hyp_pool host_s2_dev;
+static struct hyp_pool host_s2_mem;
+static struct hyp_pool host_s2_dev;
 
 /*
  * Copies of the host's CPU features registers holding sanitized values.

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

@@ -17,7 +17,6 @@
 #include <nvhe/trap_handler.h>
 
 struct hyp_pool hpool;
-struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops;
 unsigned long hyp_nr_cpus;
 
 #define hyp_percpu_size ((unsigned long)__per_cpu_end - \
@@ -27,6 +26,7 @@ static void *vmemmap_base;
 static void *hyp_pgt_base;
 static void *host_s2_mem_pgt_base;
 static void *host_s2_dev_pgt_base;
+static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops;
 
 static int divide_memory_pool(void *virt, unsigned long size)
 {

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

@@ -4,7 +4,6 @@
  * Author: Marc Zyngier <marc.zyngier@arm.com>
  */
 
-#include <hyp/adjust_pc.h>
 #include <hyp/switch.h>
 #include <hyp/sysreg-sr.h>
 
@@ -201,7 +200,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	 */
 	__debug_save_host_buffers_nvhe(vcpu);
 
-	__adjust_pc(vcpu);
+	__kvm_adjust_pc(vcpu);
 
 	/*
 	 * We must restore the 32-bit state before the sysregs, thanks

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

@@ -4,7 +4,6 @@
  * Author: Marc Zyngier <marc.zyngier@arm.com>
  */
 
-#include <hyp/adjust_pc.h>
 #include <hyp/switch.h>
 
 #include <linux/arm-smccc.h>
@@ -132,7 +131,7 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	__load_guest_stage2(vcpu->arch.hw_mmu);
 	__activate_traps(vcpu);
 
-	__adjust_pc(vcpu);
+	__kvm_adjust_pc(vcpu);
 
 	sysreg_restore_guest_state_vhe(guest_ctxt);
 	__debug_switch_to_guest(vcpu);

arch/arm64/kvm/mmu.c

@@ -1156,21 +1156,21 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	if (!kvm->arch.mmu.pgt)
-		return 0;
+		return false;
 
 	__unmap_stage2_range(&kvm->arch.mmu, range->start << PAGE_SHIFT,
 			     (range->end - range->start) << PAGE_SHIFT,
 			     range->may_block);
 
-	return 0;
+	return false;
 }
 
 bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	kvm_pfn_t pfn = pte_pfn(range->pte);
 
 	if (!kvm->arch.mmu.pgt)
-		return 0;
+		return false;
 
 	WARN_ON(range->end - range->start != 1);
 
@@ -1190,7 +1190,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 			       PAGE_SIZE, __pfn_to_phys(pfn),
 			       KVM_PGTABLE_PROT_R, NULL);
 
-	return 0;
+	return false;
 }
 
 bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
@@ -1200,7 +1200,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	pte_t pte;
 
 	if (!kvm->arch.mmu.pgt)
-		return 0;
+		return false;
 
 	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
 
@@ -1213,7 +1213,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	if (!kvm->arch.mmu.pgt)
-		return 0;
+		return false;
 
 	return kvm_pgtable_stage2_is_young(kvm->arch.mmu.pgt,
 					   range->start << PAGE_SHIFT);

arch/arm64/kvm/reset.c

@@ -166,6 +166,25 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu *tmp;
+	bool is32bit;
+	int i;
+
+	is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT);
+	if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit)
+		return false;
+
+	/* Check that the vcpus are either all 32bit or all 64bit */
+	kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
+		if (vcpu_has_feature(tmp, KVM_ARM_VCPU_EL1_32BIT) != is32bit)
+			return false;
+	}
+
+	return true;
+}
+
 /**
  * kvm_reset_vcpu - sets core registers and sys_regs to reset value
  * @vcpu: The VCPU pointer
@@ -217,13 +236,14 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 		}
 	}
 
+	if (!vcpu_allowed_register_width(vcpu)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	switch (vcpu->arch.target) {
 	default:
 		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
-			if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) {
-				ret = -EINVAL;
-				goto out;
-			}
 			pstate = VCPU_RESET_PSTATE_SVC;
 		} else {
 			pstate = VCPU_RESET_PSTATE_EL1;