Merge tag 'for-kvmgt' of git://git.kernel.org/pub/scm/virt/kvm/kvm into drm-intel-next-queued

Paulo Bonzini writes:

The three KVM patches that KVMGT needs.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>

Documentation/virtual/kvm/locking.txt

@@ -4,7 +4,17 @@ KVM Lock Overview
 1. Acquisition Orders
 ---------------------
 
-(to be written)
+The acquisition orders for mutexes are as follows:
+
+- kvm->lock is taken outside vcpu->mutex
+
+- kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock
+
+- kvm->slots_lock is taken outside kvm->irq_lock, though acquiring
+  them together is quite rare.
+
+For spinlocks, kvm_lock is taken outside kvm->mmu_lock.  Everything
+else is a leaf: no other lock is taken inside the critical sections.
 
 2: Exception
 ------------

arch/mips/include/asm/kvm_host.h

@@ -293,7 +293,10 @@ struct kvm_vcpu_arch {
 	/* Host KSEG0 address of the EI/DI offset */
 	void *kseg0_commpage;
 
-	u32 io_gpr;		/* GPR used as IO source/target */
+	/* Resume PC after MMIO completion */
+	unsigned long io_pc;
+	/* GPR used as IO source/target */
+	u32 io_gpr;
 
 	struct hrtimer comparecount_timer;
 	/* Count timer control KVM register */
@@ -315,8 +318,6 @@ struct kvm_vcpu_arch {
 	/* Bitmask of pending exceptions to be cleared */
 	unsigned long pending_exceptions_clr;
 
-	u32 pending_load_cause;
-
 	/* Save/Restore the entryhi register when are are preempted/scheduled back in */
 	unsigned long preempt_entryhi;
 

arch/mips/kvm/emulate.c

@@ -790,15 +790,15 @@ enum emulation_result kvm_mips_emul_eret(struct kvm_vcpu *vcpu)
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	enum emulation_result er = EMULATE_DONE;
 
-	if (kvm_read_c0_guest_status(cop0) & ST0_EXL) {
+	if (kvm_read_c0_guest_status(cop0) & ST0_ERL) {
+		kvm_clear_c0_guest_status(cop0, ST0_ERL);
+		vcpu->arch.pc = kvm_read_c0_guest_errorepc(cop0);
+	} else if (kvm_read_c0_guest_status(cop0) & ST0_EXL) {
 		kvm_debug("[%#lx] ERET to %#lx\n", vcpu->arch.pc,
 			  kvm_read_c0_guest_epc(cop0));
 		kvm_clear_c0_guest_status(cop0, ST0_EXL);
 		vcpu->arch.pc = kvm_read_c0_guest_epc(cop0);
 
-	} else if (kvm_read_c0_guest_status(cop0) & ST0_ERL) {
-		kvm_clear_c0_guest_status(cop0, ST0_ERL);
-		vcpu->arch.pc = kvm_read_c0_guest_errorepc(cop0);
 	} else {
 		kvm_err("[%#lx] ERET when MIPS_SR_EXL|MIPS_SR_ERL == 0\n",
 			vcpu->arch.pc);
@@ -1528,13 +1528,25 @@ enum emulation_result kvm_mips_emulate_load(union mips_instruction inst,
 					    struct kvm_vcpu *vcpu)
 {
 	enum emulation_result er = EMULATE_DO_MMIO;
+	unsigned long curr_pc;
 	u32 op, rt;
 	u32 bytes;
 
 	rt = inst.i_format.rt;
 	op = inst.i_format.opcode;
 
-	vcpu->arch.pending_load_cause = cause;
+	/*
+	 * Find the resume PC now while we have safe and easy access to the
+	 * prior branch instruction, and save it for
+	 * kvm_mips_complete_mmio_load() to restore later.
+	 */
+	curr_pc = vcpu->arch.pc;
+	er = update_pc(vcpu, cause);
+	if (er == EMULATE_FAIL)
+		return er;
+	vcpu->arch.io_pc = vcpu->arch.pc;
+	vcpu->arch.pc = curr_pc;
+
 	vcpu->arch.io_gpr = rt;
 
 	switch (op) {
@@ -2494,9 +2506,8 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
 		goto done;
 	}
 
-	er = update_pc(vcpu, vcpu->arch.pending_load_cause);
-	if (er == EMULATE_FAIL)
-		return er;
+	/* Restore saved resume PC */
+	vcpu->arch.pc = vcpu->arch.io_pc;
 
 	switch (run->mmio.len) {
 	case 4:
@@ -2518,11 +2529,6 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
 		break;
 	}
 
-	if (vcpu->arch.pending_load_cause & CAUSEF_BD)
-		kvm_debug("[%#lx] Completing %d byte BD Load to gpr %d (0x%08lx) type %d\n",
-			  vcpu->arch.pc, run->mmio.len, vcpu->arch.io_gpr, *gpr,
-			  vcpu->mmio_needed);
-
 done:
 	return er;
 }

arch/mips/kvm/mips.c

@@ -426,7 +426,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 static void kvm_mips_check_asids(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
-	int cpu = smp_processor_id();
+	int i, cpu = smp_processor_id();
 	unsigned int gasid;
 
 	/*
@@ -442,6 +442,9 @@ static void kvm_mips_check_asids(struct kvm_vcpu *vcpu)
 						vcpu);
 			vcpu->arch.guest_user_asid[cpu] =
 				vcpu->arch.guest_user_mm.context.asid[cpu];
+			for_each_possible_cpu(i)
+				if (i != cpu)
+					vcpu->arch.guest_user_asid[cpu] = 0;
 			vcpu->arch.last_user_gasid = gasid;
 		}
 	}

arch/mips/kvm/mmu.c

@@ -260,13 +260,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	if ((vcpu->arch.guest_user_asid[cpu] ^ asid_cache(cpu)) &
 						asid_version_mask(cpu)) {
-		u32 gasid = kvm_read_c0_guest_entryhi(vcpu->arch.cop0) &
-				KVM_ENTRYHI_ASID;
-
 		kvm_get_new_mmu_context(&vcpu->arch.guest_user_mm, cpu, vcpu);
 		vcpu->arch.guest_user_asid[cpu] =
 		    vcpu->arch.guest_user_mm.context.asid[cpu];
-		vcpu->arch.last_user_gasid = gasid;
 		newasid++;
 
 		kvm_debug("[%d]: cpu_context: %#lx\n", cpu,

arch/s390/kvm/sthyi.c

@@ -315,7 +315,7 @@ static void fill_diag(struct sthyi_sctns *sctns)
 	if (r < 0)
 		goto out;
 
-	diag224_buf = kmalloc(PAGE_SIZE, GFP_KERNEL | GFP_DMA);
+	diag224_buf = (void *)__get_free_page(GFP_KERNEL | GFP_DMA);
 	if (!diag224_buf || diag224(diag224_buf))
 		goto out;
 
@@ -378,7 +378,7 @@ static void fill_diag(struct sthyi_sctns *sctns)
 	sctns->par.infpval1 |= PAR_WGHT_VLD;
 
 out:
-	kfree(diag224_buf);
+	free_page((unsigned long)diag224_buf);
 	vfree(diag204_buf);
 }
 

arch/x86/include/asm/kvm_host.h

@@ -948,7 +948,6 @@ struct kvm_x86_ops {
 	int (*get_lpage_level)(void);
 	bool (*rdtscp_supported)(void);
 	bool (*invpcid_supported)(void);
-	void (*adjust_tsc_offset_guest)(struct kvm_vcpu *vcpu, s64 adjustment);
 
 	void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
 
@@ -958,8 +957,6 @@ struct kvm_x86_ops {
 
 	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
 
-	u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu, u64 host_tsc);
-
 	void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
 
 	int (*check_intercept)(struct kvm_vcpu *vcpu,

arch/x86/include/asm/kvm_page_track.h

@@ -29,9 +29,20 @@ struct kvm_page_track_notifier_node {
 	 * @gpa: the physical address written by guest.
 	 * @new: the data was written to the address.
 	 * @bytes: the written length.
+	 * @node: this node
 	 */
 	void (*track_write)(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
-			    int bytes);
+			    int bytes, struct kvm_page_track_notifier_node *node);
+	/*
+	 * It is called when memory slot is being moved or removed
+	 * users can drop write-protection for the pages in that memory slot
+	 *
+	 * @kvm: the kvm where memory slot being moved or removed
+	 * @slot: the memory slot being moved or removed
+	 * @node: this node
+	 */
+	void (*track_flush_slot)(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    struct kvm_page_track_notifier_node *node);
 };
 
 void kvm_page_track_init(struct kvm *kvm);
@@ -58,4 +69,5 @@ kvm_page_track_unregister_notifier(struct kvm *kvm,
 				   struct kvm_page_track_notifier_node *n);
 void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 			  int bytes);
+void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
 #endif

arch/x86/kvm/emulate.c

@@ -5045,7 +5045,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 	/* Decode and fetch the destination operand: register or memory. */
 	rc = decode_operand(ctxt, &ctxt->dst, (ctxt->d >> DstShift) & OpMask);
 
-	if (ctxt->rip_relative)
+	if (ctxt->rip_relative && likely(ctxt->memopp))
 		ctxt->memopp->addr.mem.ea = address_mask(ctxt,
 					ctxt->memopp->addr.mem.ea + ctxt->_eip);
 

arch/x86/kvm/mmu.c

@@ -4405,7 +4405,8 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte)
 }
 
 static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-			      const u8 *new, int bytes)
+			      const u8 *new, int bytes,
+			      struct kvm_page_track_notifier_node *node)
 {
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	struct kvm_mmu_page *sp;
@@ -4617,11 +4618,19 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu)
 	init_kvm_mmu(vcpu);
 }
 
+static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
+			struct kvm_memory_slot *slot,
+			struct kvm_page_track_notifier_node *node)
+{
+	kvm_mmu_invalidate_zap_all_pages(kvm);
+}
+
 void kvm_mmu_init_vm(struct kvm *kvm)
 {
 	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
 
 	node->track_write = kvm_mmu_pte_write;
+	node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot;
 	kvm_page_track_register_notifier(kvm, node);
 }
 

arch/x86/kvm/page_track.c

@@ -106,6 +106,7 @@ void kvm_slot_page_track_add_page(struct kvm *kvm,
 		if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn))
 			kvm_flush_remote_tlbs(kvm);
 }
+EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page);
 
 /*
  * remove the guest page from the tracking pool which stops the interception
@@ -135,6 +136,7 @@ void kvm_slot_page_track_remove_page(struct kvm *kvm,
 	 */
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
+EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page);
 
 /*
  * check if the corresponding access on the specified guest page is tracked.
@@ -181,6 +183,7 @@ kvm_page_track_register_notifier(struct kvm *kvm,
 	hlist_add_head_rcu(&n->node, &head->track_notifier_list);
 	spin_unlock(&kvm->mmu_lock);
 }
+EXPORT_SYMBOL_GPL(kvm_page_track_register_notifier);
 
 /*
  * stop receiving the event interception. It is the opposed operation of
@@ -199,6 +202,7 @@ kvm_page_track_unregister_notifier(struct kvm *kvm,
 	spin_unlock(&kvm->mmu_lock);
 	synchronize_srcu(&head->track_srcu);
 }
+EXPORT_SYMBOL_GPL(kvm_page_track_unregister_notifier);
 
 /*
  * Notify the node that write access is intercepted and write emulation is
@@ -222,6 +226,31 @@ void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 	idx = srcu_read_lock(&head->track_srcu);
 	hlist_for_each_entry_rcu(n, &head->track_notifier_list, node)
 		if (n->track_write)
-			n->track_write(vcpu, gpa, new, bytes);
+			n->track_write(vcpu, gpa, new, bytes, n);
+	srcu_read_unlock(&head->track_srcu, idx);
+}
+
+/*
+ * Notify the node that memory slot is being removed or moved so that it can
+ * drop write-protection for the pages in the memory slot.
+ *
+ * The node should figure out it has any write-protected pages in this slot
+ * by itself.
+ */
+void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+	struct kvm_page_track_notifier_head *head;
+	struct kvm_page_track_notifier_node *n;
+	int idx;
+
+	head = &kvm->arch.track_notifier_head;
+
+	if (hlist_empty(&head->track_notifier_list))
+		return;
+
+	idx = srcu_read_lock(&head->track_srcu);
+	hlist_for_each_entry_rcu(n, &head->track_notifier_list, node)
+		if (n->track_flush_slot)
+			n->track_flush_slot(kvm, slot, n);
 	srcu_read_unlock(&head->track_srcu, idx);
 }

arch/x86/kvm/svm.c

@@ -1138,21 +1138,6 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 }
 
-static void svm_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-
-	svm->vmcb->control.tsc_offset += adjustment;
-	if (is_guest_mode(vcpu))
-		svm->nested.hsave->control.tsc_offset += adjustment;
-	else
-		trace_kvm_write_tsc_offset(vcpu->vcpu_id,
-				     svm->vmcb->control.tsc_offset - adjustment,
-				     svm->vmcb->control.tsc_offset);
-
-	mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
-}
-
 static void avic_init_vmcb(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = svm->vmcb;
@@ -3449,12 +3434,6 @@ static int cr8_write_interception(struct vcpu_svm *svm)
 	return 0;
 }
 
-static u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
-{
-	struct vmcb *vmcb = get_host_vmcb(to_svm(vcpu));
-	return vmcb->control.tsc_offset + host_tsc;
-}
-
 static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -5422,8 +5401,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.has_wbinvd_exit = svm_has_wbinvd_exit,
 
 	.write_tsc_offset = svm_write_tsc_offset,
-	.adjust_tsc_offset_guest = svm_adjust_tsc_offset_guest,
-	.read_l1_tsc = svm_read_l1_tsc,
 
 	.set_tdp_cr3 = set_tdp_cr3,
 

arch/x86/kvm/vmx.c

@@ -187,6 +187,7 @@ struct vmcs {
  */
 struct loaded_vmcs {
 	struct vmcs *vmcs;
+	struct vmcs *shadow_vmcs;
 	int cpu;
 	int launched;
 	struct list_head loaded_vmcss_on_cpu_link;
@@ -411,7 +412,6 @@ struct nested_vmx {
 	 * memory during VMXOFF, VMCLEAR, VMPTRLD.
 	 */
 	struct vmcs12 *cached_vmcs12;
-	struct vmcs *current_shadow_vmcs;
 	/*
 	 * Indicates if the shadow vmcs must be updated with the
 	 * data hold by vmcs12
@@ -421,7 +421,6 @@ struct nested_vmx {
 	/* vmcs02_list cache of VMCSs recently used to run L2 guests */
 	struct list_head vmcs02_pool;
 	int vmcs02_num;
-	u64 vmcs01_tsc_offset;
 	bool change_vmcs01_virtual_x2apic_mode;
 	/* L2 must run next, and mustn't decide to exit to L1. */
 	bool nested_run_pending;
@@ -1419,6 +1418,8 @@ static void vmcs_clear(struct vmcs *vmcs)
 static inline void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs)
 {
 	vmcs_clear(loaded_vmcs->vmcs);
+	if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched)
+		vmcs_clear(loaded_vmcs->shadow_vmcs);
 	loaded_vmcs->cpu = -1;
 	loaded_vmcs->launched = 0;
 }
@@ -2604,20 +2605,6 @@ static u64 guest_read_tsc(struct kvm_vcpu *vcpu)
 	return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset;
 }
 
-/*
- * Like guest_read_tsc, but always returns L1's notion of the timestamp
- * counter, even if a nested guest (L2) is currently running.
- */
-static u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
-{
-	u64 tsc_offset;
-
-	tsc_offset = is_guest_mode(vcpu) ?
-		to_vmx(vcpu)->nested.vmcs01_tsc_offset :
-		vmcs_read64(TSC_OFFSET);
-	return host_tsc + tsc_offset;
-}
-
 /*
  * writes 'offset' into guest's timestamp counter offset register
  */
@@ -2631,7 +2618,6 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 		 * to the newly set TSC to get L2's TSC.
 		 */
 		struct vmcs12 *vmcs12;
-		to_vmx(vcpu)->nested.vmcs01_tsc_offset = offset;
 		/* recalculate vmcs02.TSC_OFFSET: */
 		vmcs12 = get_vmcs12(vcpu);
 		vmcs_write64(TSC_OFFSET, offset +
@@ -2644,19 +2630,6 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	}
 }
 
-static void vmx_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment)
-{
-	u64 offset = vmcs_read64(TSC_OFFSET);
-
-	vmcs_write64(TSC_OFFSET, offset + adjustment);
-	if (is_guest_mode(vcpu)) {
-		/* Even when running L2, the adjustment needs to apply to L1 */
-		to_vmx(vcpu)->nested.vmcs01_tsc_offset += adjustment;
-	} else
-		trace_kvm_write_tsc_offset(vcpu->vcpu_id, offset,
-					   offset + adjustment);
-}
-
 static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best = kvm_find_cpuid_entry(vcpu, 1, 0);
@@ -3562,6 +3535,7 @@ static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
 	loaded_vmcs_clear(loaded_vmcs);
 	free_vmcs(loaded_vmcs->vmcs);
 	loaded_vmcs->vmcs = NULL;
+	WARN_ON(loaded_vmcs->shadow_vmcs != NULL);
 }
 
 static void free_kvm_area(void)
@@ -6696,6 +6670,7 @@ static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx)
 	if (!item)
 		return NULL;
 	item->vmcs02.vmcs = alloc_vmcs();
+	item->vmcs02.shadow_vmcs = NULL;
 	if (!item->vmcs02.vmcs) {
 		kfree(item);
 		return NULL;
@@ -7072,7 +7047,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		shadow_vmcs->revision_id |= (1u << 31);
 		/* init shadow vmcs */
 		vmcs_clear(shadow_vmcs);
-		vmx->nested.current_shadow_vmcs = shadow_vmcs;
+		vmx->vmcs01.shadow_vmcs = shadow_vmcs;
 	}
 
 	INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool));
@@ -7174,8 +7149,11 @@ static void free_nested(struct vcpu_vmx *vmx)
 		free_page((unsigned long)vmx->nested.msr_bitmap);
 		vmx->nested.msr_bitmap = NULL;
 	}
-	if (enable_shadow_vmcs)
-		free_vmcs(vmx->nested.current_shadow_vmcs);
+	if (enable_shadow_vmcs) {
+		vmcs_clear(vmx->vmcs01.shadow_vmcs);
+		free_vmcs(vmx->vmcs01.shadow_vmcs);
+		vmx->vmcs01.shadow_vmcs = NULL;
+	}
 	kfree(vmx->nested.cached_vmcs12);
 	/* Unpin physical memory we referred to in current vmcs02 */
 	if (vmx->nested.apic_access_page) {
@@ -7352,7 +7330,7 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
 	int i;
 	unsigned long field;
 	u64 field_value;
-	struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs;
+	struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
 	const unsigned long *fields = shadow_read_write_fields;
 	const int num_fields = max_shadow_read_write_fields;
 
@@ -7401,7 +7379,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
 	int i, q;
 	unsigned long field;
 	u64 field_value = 0;
-	struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs;
+	struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
 
 	vmcs_load(shadow_vmcs);
 
@@ -7591,7 +7569,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 			vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
 				      SECONDARY_EXEC_SHADOW_VMCS);
 			vmcs_write64(VMCS_LINK_POINTER,
-				     __pa(vmx->nested.current_shadow_vmcs));
+				     __pa(vmx->vmcs01.shadow_vmcs));
 			vmx->nested.sync_shadow_vmcs = true;
 		}
 	}
@@ -7659,7 +7637,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 
 	types = (vmx->nested.nested_vmx_ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
 
-	if (!(types & (1UL << type))) {
+	if (type >= 32 || !(types & (1 << type))) {
 		nested_vmx_failValid(vcpu,
 				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 		skip_emulated_instruction(vcpu);
@@ -7722,7 +7700,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 
 	types = (vmx->nested.nested_vmx_vpid_caps >> 8) & 0x7;
 
-	if (!(types & (1UL << type))) {
+	if (type >= 32 || !(types & (1 << type))) {
 		nested_vmx_failValid(vcpu,
 			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 		skip_emulated_instruction(vcpu);
@@ -9156,6 +9134,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	vmx->loaded_vmcs = &vmx->vmcs01;
 	vmx->loaded_vmcs->vmcs = alloc_vmcs();
+	vmx->loaded_vmcs->shadow_vmcs = NULL;
 	if (!vmx->loaded_vmcs->vmcs)
 		goto free_msrs;
 	if (!vmm_exclusive)
@@ -10061,9 +10040,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
 		vmcs_write64(TSC_OFFSET,
-			vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset);
+			vcpu->arch.tsc_offset + vmcs12->tsc_offset);
 	else
-		vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
+		vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
 	if (kvm_has_tsc_control)
 		decache_tsc_multiplier(vmx);
 
@@ -10293,8 +10272,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 
 	enter_guest_mode(vcpu);
 
-	vmx->nested.vmcs01_tsc_offset = vmcs_read64(TSC_OFFSET);
-
 	if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
 		vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
 
@@ -10818,7 +10795,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	load_vmcs12_host_state(vcpu, vmcs12);
 
 	/* Update any VMCS fields that might have changed while L2 ran */
-	vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
+	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
 	if (vmx->hv_deadline_tsc == -1)
 		vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
 				PIN_BASED_VMX_PREEMPTION_TIMER);
@@ -11339,8 +11316,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
 
 	.write_tsc_offset = vmx_write_tsc_offset,
-	.adjust_tsc_offset_guest = vmx_adjust_tsc_offset_guest,
-	.read_l1_tsc = vmx_read_l1_tsc,
 
 	.set_tdp_cr3 = vmx_set_cr3,
 

arch/x86/kvm/x86.c

@@ -1409,7 +1409,7 @@ static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 
 u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
 {
-	return kvm_x86_ops->read_l1_tsc(vcpu, kvm_scale_tsc(vcpu, host_tsc));
+	return vcpu->arch.tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
 }
 EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
 
@@ -1547,7 +1547,7 @@ EXPORT_SYMBOL_GPL(kvm_write_tsc);
 static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
 					   s64 adjustment)
 {
-	kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment);
+	kvm_vcpu_write_tsc_offset(vcpu, vcpu->arch.tsc_offset + adjustment);
 }
 
 static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)
@@ -1555,7 +1555,7 @@ static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)
 	if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio)
 		WARN_ON(adjustment < 0);
 	adjustment = kvm_scale_tsc(vcpu, (u64) adjustment);
-	kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment);
+	adjust_tsc_offset_guest(vcpu, adjustment);
 }
 
 #ifdef CONFIG_X86_64
@@ -2262,7 +2262,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		/* Drop writes to this legacy MSR -- see rdmsr
 		 * counterpart for further detail.
 		 */
-		vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data);
+		vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", msr, data);
 		break;
 	case MSR_AMD64_OSVW_ID_LENGTH:
 		if (!guest_cpuid_has_osvw(vcpu))
@@ -2280,11 +2280,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (kvm_pmu_is_valid_msr(vcpu, msr))
 			return kvm_pmu_set_msr(vcpu, msr_info);
 		if (!ignore_msrs) {
-			vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n",
+			vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data 0x%llx\n",
 				    msr, data);
 			return 1;
 		} else {
-			vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n",
+			vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n",
 				    msr, data);
 			break;
 		}
@@ -7410,10 +7410,12 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
+	void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask;
+
 	kvmclock_reset(vcpu);
 
-	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
 	kvm_x86_ops->vcpu_free(vcpu);
+	free_cpumask_var(wbinvd_dirty_mask);
 }
 
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
@@ -8153,7 +8155,7 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
-	kvm_mmu_invalidate_zap_all_pages(kvm);
+	kvm_page_track_flush_slot(kvm, slot);
 }
 
 static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)

virt/kvm/eventfd.c

@@ -42,6 +42,7 @@
 
 #ifdef CONFIG_HAVE_KVM_IRQFD
 
+static struct workqueue_struct *irqfd_cleanup_wq;
 
 static void
 irqfd_inject(struct work_struct *work)
@@ -167,7 +168,7 @@ irqfd_deactivate(struct kvm_kernel_irqfd *irqfd)
 
 	list_del_init(&irqfd->list);
 
-	schedule_work(&irqfd->shutdown);
+	queue_work(irqfd_cleanup_wq, &irqfd->shutdown);
 }
 
 int __attribute__((weak)) kvm_arch_set_irq_inatomic(
@@ -554,7 +555,7 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args)
 	 * so that we guarantee there will not be any more interrupts on this
 	 * gsi once this deassign function returns.
 	 */
-	flush_work(&irqfd->shutdown);
+	flush_workqueue(irqfd_cleanup_wq);
 
 	return 0;
 }
@@ -591,7 +592,7 @@ kvm_irqfd_release(struct kvm *kvm)
 	 * Block until we know all outstanding shutdown jobs have completed
 	 * since we do not take a kvm* reference.
 	 */
-	flush_work(&irqfd->shutdown);
+	flush_workqueue(irqfd_cleanup_wq);
 
 }
 
@@ -621,8 +622,23 @@ void kvm_irq_routing_update(struct kvm *kvm)
 	spin_unlock_irq(&kvm->irqfds.lock);
 }
 
+/*
+ * create a host-wide workqueue for issuing deferred shutdown requests
+ * aggregated from all vm* instances. We need our own isolated
+ * queue to ease flushing work items when a VM exits.
+ */
+int kvm_irqfd_init(void)
+{
+	irqfd_cleanup_wq = alloc_workqueue("kvm-irqfd-cleanup", 0, 0);
+	if (!irqfd_cleanup_wq)
+		return -ENOMEM;
+
+	return 0;
+}
+
 void kvm_irqfd_exit(void)
 {
+	destroy_workqueue(irqfd_cleanup_wq);
 }
 #endif
 

virt/kvm/kvm_main.c

@@ -3846,7 +3846,12 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	 * kvm_arch_init makes sure there's at most one caller
 	 * for architectures that support multiple implementations,
 	 * like intel and amd on x86.
+	 * kvm_arch_init must be called before kvm_irqfd_init to avoid creating
+	 * conflicts in case kvm is already setup for another implementation.
 	 */
+	r = kvm_irqfd_init();
+	if (r)
+		goto out_irqfd;
 
 	if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) {
 		r = -ENOMEM;
@@ -3928,6 +3933,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	free_cpumask_var(cpus_hardware_enabled);
 out_free_0:
 	kvm_irqfd_exit();
+out_irqfd:
 	kvm_arch_exit();
 out_fail:
 	return r;