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

Pull more KVM updates from Paolo Bonzini:
 "x86:

   - take into account HVA before retrying on MMU notifier race

   - fixes for nested AMD guests without NPT

   - allow INVPCID in guest without PCID

   - disable PML in hardware when not in use

   - MMU code cleanups:

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (28 commits)
  KVM: SVM: Fix nested VM-Exit on #GP interception handling
  KVM: vmx/pmu: Fix dummy check if lbr_desc->event is created
  KVM: x86/mmu: Consider the hva in mmu_notifier retry
  KVM: x86/mmu: Skip mmu_notifier check when handling MMIO page fault
  KVM: Documentation: rectify rst markup in KVM_GET_SUPPORTED_HV_CPUID
  KVM: nSVM: prepare guest save area while is_guest_mode is true
  KVM: x86/mmu: Remove a variety of unnecessary exports
  KVM: x86: Fold "write-protect large" use case into generic write-protect
  KVM: x86/mmu: Don't set dirty bits when disabling dirty logging w/ PML
  KVM: VMX: Dynamically enable/disable PML based on memslot dirty logging
  KVM: x86: Further clarify the logic and comments for toggling log dirty
  KVM: x86: Move MMU's PML logic to common code
  KVM: x86/mmu: Make dirty log size hook (PML) a value, not a function
  KVM: x86/mmu: Expand on the comment in kvm_vcpu_ad_need_write_protect()
  KVM: nVMX: Disable PML in hardware when running L2
  KVM: x86/mmu: Consult max mapping level when zapping collapsible SPTEs
  KVM: x86/mmu: Pass the memslot to the rmap callbacks
  KVM: x86/mmu: Split out max mapping level calculation to helper
  KVM: x86/mmu: Expand collapsible SPTE zap for TDP MMU to ZONE_DEVICE and HugeTLB pages
  KVM: nVMX: no need to undo inject_page_fault change on nested vmexit
  ...

Documentation/virt/kvm/api.rst

@@ -4519,6 +4519,7 @@ KVM_GET_SUPPORTED_CPUID ioctl because some of them intersect with KVM feature
 leaves (0x40000000, 0x40000001).
 
 Currently, the following list of CPUID leaves are returned:
+
  - HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS
  - HYPERV_CPUID_INTERFACE
  - HYPERV_CPUID_VERSION
@@ -4543,6 +4544,7 @@ userspace should not expect to get any particular value there.
 Note, vcpu version of KVM_GET_SUPPORTED_HV_CPUID is currently deprecated. Unlike
 system ioctl which exposes all supported feature bits unconditionally, vcpu
 version has the following quirks:
+
 - HYPERV_CPUID_NESTED_FEATURES leaf and HV_X64_ENLIGHTENED_VMCS_RECOMMENDED
   feature bit are only exposed when Enlightened VMCS was previously enabled
   on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS).

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -591,7 +591,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu,
 	} else {
 		/* Call KVM generic code to do the slow-path check */
 		pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
-					   writing, &write_ok);
+					   writing, &write_ok, NULL);
 		if (is_error_noslot_pfn(pfn))
 			return -EFAULT;
 		page = NULL;

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -822,7 +822,7 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
 
 		/* Call KVM generic code to do the slow-path check */
 		pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
-					   writing, upgrade_p);
+					   writing, upgrade_p, NULL);
 		if (is_error_noslot_pfn(pfn))
 			return -EFAULT;
 		page = NULL;

arch/x86/include/asm/kvm-x86-ops.h

@@ -93,11 +93,7 @@ KVM_X86_OP(check_intercept)
 KVM_X86_OP(handle_exit_irqoff)
 KVM_X86_OP_NULL(request_immediate_exit)
 KVM_X86_OP(sched_in)
-KVM_X86_OP_NULL(slot_enable_log_dirty)
-KVM_X86_OP_NULL(slot_disable_log_dirty)
-KVM_X86_OP_NULL(flush_log_dirty)
-KVM_X86_OP_NULL(enable_log_dirty_pt_masked)
-KVM_X86_OP_NULL(cpu_dirty_log_size)
+KVM_X86_OP_NULL(update_cpu_dirty_logging)
 KVM_X86_OP_NULL(pre_block)
 KVM_X86_OP_NULL(post_block)
 KVM_X86_OP_NULL(vcpu_blocking)

arch/x86/include/asm/kvm_host.h

@@ -89,6 +89,8 @@
 	KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_APF_READY		KVM_ARCH_REQ(28)
 #define KVM_REQ_MSR_FILTER_CHANGED	KVM_ARCH_REQ(29)
+#define KVM_REQ_UPDATE_CPU_DIRTY_LOGGING \
+	KVM_ARCH_REQ_FLAGS(30, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 
 #define CR0_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
@@ -1007,6 +1009,7 @@ struct kvm_arch {
 	u32 bsp_vcpu_id;
 
 	u64 disabled_quirks;
+	int cpu_dirty_logging_count;
 
 	enum kvm_irqchip_mode irqchip_mode;
 	u8 nr_reserved_ioapic_pins;
@@ -1271,30 +1274,11 @@ struct kvm_x86_ops {
 	void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
 
 	/*
-	 * Arch-specific dirty logging hooks. These hooks are only supposed to
-	 * be valid if the specific arch has hardware-accelerated dirty logging
-	 * mechanism. Currently only for PML on VMX.
-	 *
-	 *  - slot_enable_log_dirty:
-	 *	called when enabling log dirty mode for the slot.
-	 *  - slot_disable_log_dirty:
-	 *	called when disabling log dirty mode for the slot.
-	 *	also called when slot is created with log dirty disabled.
-	 *  - flush_log_dirty:
-	 *	called before reporting dirty_bitmap to userspace.
-	 *  - enable_log_dirty_pt_masked:
-	 *	called when reenabling log dirty for the GFNs in the mask after
-	 *	corresponding bits are cleared in slot->dirty_bitmap.
+	 * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer.  A zero
+	 * value indicates CPU dirty logging is unsupported or disabled.
 	 */
-	void (*slot_enable_log_dirty)(struct kvm *kvm,
-				      struct kvm_memory_slot *slot);
-	void (*slot_disable_log_dirty)(struct kvm *kvm,
-				       struct kvm_memory_slot *slot);
-	void (*flush_log_dirty)(struct kvm *kvm);
-	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
-					   struct kvm_memory_slot *slot,
-					   gfn_t offset, unsigned long mask);
-	int (*cpu_dirty_log_size)(void);
+	int cpu_dirty_log_size;
+	void (*update_cpu_dirty_logging)(struct kvm_vcpu *vcpu);
 
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;
@@ -1437,11 +1421,6 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot);
 void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
 					struct kvm_memory_slot *memslot);
-void kvm_mmu_slot_set_dirty(struct kvm *kvm,
-			    struct kvm_memory_slot *memslot);
-void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
-				   struct kvm_memory_slot *slot,
-				   gfn_t gfn_offset, unsigned long mask);
 void kvm_mmu_zap_all(struct kvm *kvm);
 void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen);
 unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm);
@@ -1613,7 +1592,6 @@ void kvm_inject_nmi(struct kvm_vcpu *vcpu);
 void kvm_update_dr7(struct kvm_vcpu *vcpu);
 
 int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
-int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
 void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);
 void kvm_mmu_unload(struct kvm_vcpu *vcpu);

arch/x86/kvm/cpuid.c

@@ -408,7 +408,7 @@ void kvm_set_cpu_caps(void)
 
 	kvm_cpu_cap_mask(CPUID_7_0_EBX,
 		F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
-		F(BMI2) | F(ERMS) | 0 /*INVPCID*/ | F(RTM) | 0 /*MPX*/ | F(RDSEED) |
+		F(BMI2) | F(ERMS) | F(INVPCID) | F(RTM) | 0 /*MPX*/ | F(RDSEED) |
 		F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) |
 		F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) |
 		F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | 0 /*INTEL_PT*/