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
  ...

30 files changed, 175 insertions, 97 deletions

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index cf8df032b9c3..5e9b33cbac51 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/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);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index f612c090f2e4..01b9857757f2 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/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__ */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 1cb39c0803a4..e720148232a0 100644
--- a/arch/arm64/kvm/arm.c
+++ b/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;
 }
diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c
index 73629094f903..11541b94b328 100644
--- a/arch/arm64/kvm/hyp/exception.c
+++ b/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;
+	}
+}
diff --git a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h
index 61716359035d..4fdfeabefeb4 100644
--- a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h
+++ b/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)) {
@@ -44,22 +42,6 @@ static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu)
 }
 
 /*
- * 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.
  */
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index f36420a80474..1632f001f4ed 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/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),
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index e342f7f4f4fb..4b60c0056c04 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/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.
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 7488f53b0aa2..a3d3a275344e 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/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)
 {
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index e9f6ea704d07..f7af9688c1f7 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/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
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 7b8f7db5c1ed..b3229924d243 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/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);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index c5d1f3c87dbd..c10207fed2f3 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1156,13 +1156,13 @@ out_unlock:
 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)
@@ -1170,7 +1170,7 @@ 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);
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 956cdc240148..d37ebee085cf 100644
--- a/arch/arm64/kvm/reset.c
+++ b/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;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 76ea2800c33e..1a7968ad078c 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -399,14 +399,14 @@ static bool trap_bvr(struct kvm_vcpu *vcpu,
 		     struct sys_reg_params *p,
 		     const struct sys_reg_desc *rd)
 {
-	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
+	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm];
 
 	if (p->is_write)
 		reg_to_dbg(vcpu, p, rd, dbg_reg);
 	else
 		dbg_to_reg(vcpu, p, rd, dbg_reg);
 
-	trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg);
+	trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg);
 
 	return true;
 }
@@ -414,7 +414,7 @@ static bool trap_bvr(struct kvm_vcpu *vcpu,
 static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
+	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm];
 
 	if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0)
 		return -EFAULT;
@@ -424,7 +424,7 @@ static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 	const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
+	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm];
 
 	if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0)
 		return -EFAULT;
@@ -434,21 +434,21 @@ static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 static void reset_bvr(struct kvm_vcpu *vcpu,
 		      const struct sys_reg_desc *rd)
 {
-	vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg] = rd->val;
+	vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm] = rd->val;
 }
 
 static bool trap_bcr(struct kvm_vcpu *vcpu,
 		     struct sys_reg_params *p,
 		     const struct sys_reg_desc *rd)
 {
-	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg];
+	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm];
 
 	if (p->is_write)
 		reg_to_dbg(vcpu, p, rd, dbg_reg);
 	else
 		dbg_to_reg(vcpu, p, rd, dbg_reg);
 
-	trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg);
+	trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg);
 
 	return true;
 }
@@ -456,7 +456,7 @@ static bool trap_bcr(struct kvm_vcpu *vcpu,
 static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg];
+	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm];
 
 	if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0)
 		return -EFAULT;
@@ -467,7 +467,7 @@ static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 	const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg];
+	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm];
 
 	if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0)
 		return -EFAULT;
@@ -477,22 +477,22 @@ static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 static void reset_bcr(struct kvm_vcpu *vcpu,
 		      const struct sys_reg_desc *rd)
 {
-	vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg] = rd->val;
+	vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm] = rd->val;
 }
 
 static bool trap_wvr(struct kvm_vcpu *vcpu,
 		     struct sys_reg_params *p,
 		     const struct sys_reg_desc *rd)
 {
-	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg];
+	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm];
 
 	if (p->is_write)
 		reg_to_dbg(vcpu, p, rd, dbg_reg);
 	else
 		dbg_to_reg(vcpu, p, rd, dbg_reg);
 
-	trace_trap_reg(__func__, rd->reg, p->is_write,
-		vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]);
+	trace_trap_reg(__func__, rd->CRm, p->is_write,
+		vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]);
 
 	return true;
 }
@@ -500,7 +500,7 @@ static bool trap_wvr(struct kvm_vcpu *vcpu,
 static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg];
+	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm];
 
 	if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0)
 		return -EFAULT;
@@ -510,7 +510,7 @@ static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 	const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg];
+	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm];
 
 	if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0)
 		return -EFAULT;
@@ -520,21 +520,21 @@ static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 static void reset_wvr(struct kvm_vcpu *vcpu,
 		      const struct sys_reg_desc *rd)
 {
-	vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg] = rd->val;
+	vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm] = rd->val;
 }
 
 static bool trap_wcr(struct kvm_vcpu *vcpu,
 		     struct sys_reg_params *p,
 		     const struct sys_reg_desc *rd)
 {
-	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg];
+	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm];
 
 	if (p->is_write)
 		reg_to_dbg(vcpu, p, rd, dbg_reg);
 	else
 		dbg_to_reg(vcpu, p, rd, dbg_reg);
 
-	trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg);
+	trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg);
 
 	return true;
 }
@@ -542,7 +542,7 @@ static bool trap_wcr(struct kvm_vcpu *vcpu,
 static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg];
+	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm];
 
 	if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0)
 		return -EFAULT;
@@ -552,7 +552,7 @@ static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 	const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg];
+	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm];
 
 	if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0)
 		return -EFAULT;
@@ -562,7 +562,7 @@ static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 static void reset_wcr(struct kvm_vcpu *vcpu,
 		      const struct sys_reg_desc *rd)
 {
-	vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg] = rd->val;
+	vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm] = rd->val;
 }
 
 static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 1e83359f286b..7f2e90db2050 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -51,6 +51,7 @@
 /* PPC-specific vcpu->requests bit members */
 #define KVM_REQ_WATCHDOG	KVM_ARCH_REQ(0)
 #define KVM_REQ_EPR_EXIT	KVM_ARCH_REQ(1)
+#define KVM_REQ_PENDING_TIMER	KVM_ARCH_REQ(2)
 
 #include <linux/mmu_notifier.h>
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 28a80d240b76..7360350e66ff 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3936,7 +3936,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 				break;
 			}
 			cur = ktime_get();
-		} while (single_task_running() && ktime_before(cur, stop));
+		} while (kvm_vcpu_can_poll(cur, stop));
 
 		spin_lock(&vc->lock);
 		vc->vcore_state = VCORE_INACTIVE;
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 323641097f63..e7bef91cee04 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -99,6 +99,7 @@ KVM_X86_OP_NULL(post_block)
 KVM_X86_OP_NULL(vcpu_blocking)
 KVM_X86_OP_NULL(vcpu_unblocking)
 KVM_X86_OP_NULL(update_pi_irte)
+KVM_X86_OP_NULL(start_assignment)
 KVM_X86_OP_NULL(apicv_post_state_restore)
 KVM_X86_OP_NULL(dy_apicv_has_pending_interrupt)
 KVM_X86_OP_NULL(set_hv_timer)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 55efbacfc244..9c7ced0e3171 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1352,6 +1352,7 @@ struct kvm_x86_ops {
 
 	int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
 			      uint32_t guest_irq, bool set);
+	void (*start_assignment)(struct kvm *kvm);
 	void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
 	bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu);
 
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 8a0ccdb56076..5e5de05a8fbf 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -5111,7 +5111,7 @@ done:
 	return rc;
 }
 
-int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
+int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int emulation_type)
 {
 	int rc = X86EMUL_CONTINUE;
 	int mode = ctxt->mode;
@@ -5322,7 +5322,8 @@ done_prefixes:
 
 	ctxt->execute = opcode.u.execute;
 
-	if (unlikely(ctxt->ud) && likely(!(ctxt->d & EmulateOnUD)))
+	if (unlikely(emulation_type & EMULTYPE_TRAP_UD) &&
+	    likely(!(ctxt->d & EmulateOnUD)))
 		return EMULATION_FAILED;
 
 	if (unlikely(ctxt->d &
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index f98370a39936..f00830e5202f 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1172,6 +1172,7 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm)
 {
 	struct kvm_hv *hv = to_kvm_hv(kvm);
 	u64 gfn;
+	int idx;
 
 	if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN ||
 	    hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET ||
@@ -1190,9 +1191,16 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm)
 	gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
 
 	hv->tsc_ref.tsc_sequence = 0;
+
+	/*
+	 * Take the srcu lock as memslots will be accessed to check the gfn
+	 * cache generation against the memslots generation.
+	 */
+	idx = srcu_read_lock(&kvm->srcu);
 	if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
 			    &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
 		hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN;
+	srcu_read_unlock(&kvm->srcu, idx);
 
 out_unlock:
 	mutex_unlock(&hv->hv_lock);
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index f016838faedd..3e870bf9ca4d 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -314,7 +314,6 @@ struct x86_emulate_ctxt {
 	int interruptibility;
 
 	bool perm_ok; /* do not check permissions if true */
-	bool ud;	/* inject an #UD if host doesn't support insn */
 	bool tf;	/* TF value before instruction (after for syscall/sysret) */
 
 	bool have_exception;
@@ -491,7 +490,7 @@ enum x86_intercept {
 #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64
 #endif
 
-int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len);
+int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int emulation_type);
 bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt);
 #define EMULATION_FAILED -1
 #define EMULATION_OK 0
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c0ebef560bd1..8120e8614b92 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1598,11 +1598,19 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
 	guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
 	apic->lapic_timer.advance_expire_delta = guest_tsc - tsc_deadline;
 
+	if (lapic_timer_advance_dynamic) {
+		adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta);
+		/*
+		 * If the timer fired early, reread the TSC to account for the
+		 * overhead of the above adjustment to avoid waiting longer
+		 * than is necessary.
+		 */
+		if (guest_tsc < tsc_deadline)
+			guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
+	}
+
 	if (guest_tsc < tsc_deadline)
 		__wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);
-
-	if (lapic_timer_advance_dynamic)
-		adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta);
 }
 
 void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
@@ -1661,7 +1669,7 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn)
 	}
 
 	atomic_inc(&apic->lapic_timer.pending);
-	kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+	kvm_make_request(KVM_REQ_UNBLOCK, vcpu);
 	if (from_timer_fn)
 		kvm_vcpu_kick(vcpu);
 }
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 95eeb5ac6a8a..237317b1eddd 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1192,9 +1192,9 @@ bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 }
 
 /*
- * Remove write access from all the SPTEs mapping GFNs [start, end). If
- * skip_4k is set, SPTEs that map 4k pages, will not be write-protected.
- * Returns true if an SPTE has been changed and the TLBs need to be flushed.
+ * Remove write access from all SPTEs at or above min_level that map GFNs
+ * [start, end). Returns true if an SPTE has been changed and the TLBs need to
+ * be flushed.
  */
 static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 			     gfn_t start, gfn_t end, int min_level)
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 712b4e0de481..0e62e6a2438c 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -28,10 +28,8 @@
 #include "svm.h"
 
 /* enable / disable AVIC */
-int avic;
-#ifdef CONFIG_X86_LOCAL_APIC
-module_param(avic, int, S_IRUGO);
-#endif
+bool avic;
+module_param(avic, bool, S_IRUGO);
 
 #define SVM_AVIC_DOORBELL	0xc001011b
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 05eca131eaf2..e088086f3de6 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1010,9 +1010,7 @@ static __init int svm_hardware_setup(void)
 	}
 
 	if (avic) {
-		if (!npt_enabled ||
-		    !boot_cpu_has(X86_FEATURE_AVIC) ||
-		    !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) {
+		if (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC)) {
 			avic = false;
 		} else {
 			pr_info("AVIC enabled\n");
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 2c9ece618b29..2908c6ab5bb4 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -480,7 +480,7 @@ extern struct kvm_x86_nested_ops svm_nested_ops;
 
 #define VMCB_AVIC_APIC_BAR_MASK		0xFFFFFFFFFF000ULL
 
-extern int avic;
+extern bool avic;
 
 static inline void avic_update_vapic_bar(struct vcpu_svm *svm, u64 data)
 {
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 8dee8a5fbc17..aa0e7872fcc9 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -90,8 +90,7 @@ static inline bool cpu_has_vmx_preemption_timer(void)
 
 static inline bool cpu_has_vmx_posted_intr(void)
 {
-	return IS_ENABLED(CONFIG_X86_LOCAL_APIC) &&
-		vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR;
+	return vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR;
 }
 
 static inline bool cpu_has_load_ia32_efer(void)
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 459748680daf..5f81ef092bd4 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -238,6 +238,20 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)
 
 
 /*
+ * Bail out of the block loop if the VM has an assigned
+ * device, but the blocking vCPU didn't reconfigure the
+ * PI.NV to the wakeup vector, i.e. the assigned device
+ * came along after the initial check in pi_pre_block().
+ */
+void vmx_pi_start_assignment(struct kvm *kvm)
+{
+	if (!irq_remapping_cap(IRQ_POSTING_CAP))
+		return;
+
+	kvm_make_all_cpus_request(kvm, KVM_REQ_UNBLOCK);
+}
+
+/*
  * pi_update_irte - set IRTE for Posted-Interrupts
  *
  * @kvm: kvm
diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
index 0bdc41391c5b..7f7b2326caf5 100644
--- a/arch/x86/kvm/vmx/posted_intr.h
+++ b/arch/x86/kvm/vmx/posted_intr.h
@@ -95,5 +95,6 @@ void __init pi_init_cpu(int cpu);
 bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu);
 int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq,
 		   bool set);
+void vmx_pi_start_assignment(struct kvm *kvm);
 
 #endif /* __KVM_X86_VMX_POSTED_INTR_H */
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4bceb5ca3a89..50b42d7a8a11 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4843,7 +4843,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct kvm_run *kvm_run = vcpu->run;
 	u32 intr_info, ex_no, error_code;
-	unsigned long cr2, rip, dr6;
+	unsigned long cr2, dr6;
 	u32 vect_info;
 
 	vect_info = vmx->idt_vectoring_info;
@@ -4933,8 +4933,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 		vmx->vcpu.arch.event_exit_inst_len =
 			vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
 		kvm_run->exit_reason = KVM_EXIT_DEBUG;
-		rip = kvm_rip_read(vcpu);
-		kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip;
+		kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu);
 		kvm_run->debug.arch.exception = ex_no;
 		break;
 	case AC_VECTOR:
@@ -7721,6 +7720,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.nested_ops = &vmx_nested_ops,
 
 	.update_pi_irte = pi_update_irte,
+	.start_assignment = vmx_pi_start_assignment,
 
 #ifdef CONFIG_X86_64
 	.set_hv_timer = vmx_set_hv_timer,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bbc4e04e67ad..b594275d49b5 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3105,6 +3105,8 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 				       st->preempted & KVM_VCPU_FLUSH_TLB);
 		if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB)
 			kvm_vcpu_flush_tlb_guest(vcpu);
+	} else {
+		st->preempted = 0;
 	}
 
 	vcpu->arch.st.preempted = 0;
@@ -7226,6 +7228,11 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
 	BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK);
 	BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK);
 
+	ctxt->interruptibility = 0;
+	ctxt->have_exception = false;
+	ctxt->exception.vector = -1;
+	ctxt->perm_ok = false;
+
 	init_decode_cache(ctxt);
 	vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
 }
@@ -7561,14 +7568,7 @@ int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type,
 	    kvm_vcpu_check_breakpoint(vcpu, &r))
 		return r;
 
-	ctxt->interruptibility = 0;
-	ctxt->have_exception = false;
-	ctxt->exception.vector = -1;
-	ctxt->perm_ok = false;
-
-	ctxt->ud = emulation_type & EMULTYPE_TRAP_UD;
-
-	r = x86_decode_insn(ctxt, insn, insn_len);
+	r = x86_decode_insn(ctxt, insn, insn_len, emulation_type);
 
 	trace_kvm_emulate_insn_start(vcpu);
 	++vcpu->stat.insn_emulation;
@@ -8360,6 +8360,9 @@ static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id)
 
 	vcpu->stat.directed_yield_attempted++;
 
+	if (single_task_running())
+		goto no_yield;
+
 	rcu_read_lock();
 	map = rcu_dereference(vcpu->kvm->arch.apic_map);
 
@@ -9496,7 +9499,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 		if (r <= 0)
 			break;
 
-		kvm_clear_request(KVM_REQ_PENDING_TIMER, vcpu);
+		kvm_clear_request(KVM_REQ_UNBLOCK, vcpu);
 		if (kvm_cpu_has_pending_timer(vcpu))
 			kvm_inject_pending_timer_irqs(vcpu);
 
@@ -10115,8 +10118,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	kvm_update_dr7(vcpu);
 
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
-		vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) +
-			get_segment_base(vcpu, VCPU_SREG_CS);
+		vcpu->arch.singlestep_rip = kvm_get_linear_rip(vcpu);
 
 	/*
 	 * Trigger an rflags update that will inject or remove the trace
@@ -11499,7 +11501,8 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu)
 
 void kvm_arch_start_assignment(struct kvm *kvm)
 {
-	atomic_inc(&kvm->arch.assigned_device_count);
+	if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1)
+		static_call_cond(kvm_x86_start_assignment)(kvm);
 }
 EXPORT_SYMBOL_GPL(kvm_arch_start_assignment);