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

Pull KVM update from Paolo Bonzini:
 "Fairly small update, but there are some interesting new features.

  Common:
     Optional support for adding a small amount of polling on each HLT
     instruction executed in the guest (or equivalent for other
     architectures).  This can improve latency up to 50% on some
     scenarios (e.g. O_DSYNC writes or TCP_RR netperf tests).  This
     also has to be enabled manually for now, but the plan is to
     auto-tune this in the future.

  ARM/ARM64:
     The highlights are support for GICv3 emulation and dirty page
     tracking

  s390:
     Several optimizations and bugfixes.  Also a first: a feature
     exposed by KVM (UUID and long guest name in /proc/sysinfo) before
     it is available in IBM's hypervisor! :)

  MIPS:
     Bugfixes.

  x86:
     Support for PML (page modification logging, a new feature in
     Broadwell Xeons that speeds up dirty page tracking), nested
     virtualization improvements (nested APICv---a nice optimization),
     usual round of emulation fixes.

     There is also a new option to reduce latency of the TSC deadline
     timer in the guest; this needs to be tuned manually.

     Some commits are common between this pull and Catalin's; I see you
     have already included his tree.

  Powerpc:
     Nothing yet.

     The KVM/PPC changes will come in through the PPC maintainers,
     because I haven't received them yet and I might end up being
     offline for some part of next week"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (130 commits)
  KVM: ia64: drop kvm.h from installed user headers
  KVM: x86: fix build with !CONFIG_SMP
  KVM: x86: emulate: correct page fault error code for NoWrite instructions
  KVM: Disable compat ioctl for s390
  KVM: s390: add cpu model support
  KVM: s390: use facilities and cpu_id per KVM
  KVM: s390/CPACF: Choose crypto control block format
  s390/kernel: Update /proc/sysinfo file with Extended Name and UUID
  KVM: s390: reenable LPP facility
  KVM: s390: floating irqs: fix user triggerable endless loop
  kvm: add halt_poll_ns module parameter
  kvm: remove KVM_MMIO_SIZE
  KVM: MIPS: Don't leak FPU/DSP to guest
  KVM: MIPS: Disable HTW while in guest
  KVM: nVMX: Enable nested posted interrupt processing
  KVM: nVMX: Enable nested virtual interrupt delivery
  KVM: nVMX: Enable nested apic register virtualization
  KVM: nVMX: Make nested control MSRs per-cpu
  KVM: nVMX: Enable nested virtualize x2apic mode
  KVM: nVMX: Prepare for using hardware MSR bitmap
  ...

Documentation/virtual/kvm/api.txt

@@ -612,11 +612,14 @@ Type: vm ioctl
 Parameters: none
 Returns: 0 on success, -1 on error
 
-Creates an interrupt controller model in the kernel.  On x86, creates a virtual
-ioapic, a virtual PIC (two PICs, nested), and sets up future vcpus to have a
-local APIC.  IRQ routing for GSIs 0-15 is set to both PIC and IOAPIC; GSI 16-23
-only go to the IOAPIC.  On ARM/arm64, a GIC is
-created. On s390, a dummy irq routing table is created.
+Creates an interrupt controller model in the kernel.
+On x86, creates a virtual ioapic, a virtual PIC (two PICs, nested), and sets up
+future vcpus to have a local APIC.  IRQ routing for GSIs 0-15 is set to both
+PIC and IOAPIC; GSI 16-23 only go to the IOAPIC.
+On ARM/arm64, a GICv2 is created. Any other GIC versions require the usage of
+KVM_CREATE_DEVICE, which also supports creating a GICv2.  Using
+KVM_CREATE_DEVICE is preferred over KVM_CREATE_IRQCHIP for GICv2.
+On s390, a dummy irq routing table is created.
 
 Note that on s390 the KVM_CAP_S390_IRQCHIP vm capability needs to be enabled
 before KVM_CREATE_IRQCHIP can be used.
@@ -2312,7 +2315,7 @@ struct kvm_s390_interrupt {
 
 type can be one of the following:
 
-KVM_S390_SIGP_STOP (vcpu) - sigp restart
+KVM_S390_SIGP_STOP (vcpu) - sigp stop; optional flags in parm
 KVM_S390_PROGRAM_INT (vcpu) - program check; code in parm
 KVM_S390_SIGP_SET_PREFIX (vcpu) - sigp set prefix; prefix address in parm
 KVM_S390_RESTART (vcpu) - restart
@@ -3225,3 +3228,23 @@ userspace from doing that.
 If the hcall number specified is not one that has an in-kernel
 implementation, the KVM_ENABLE_CAP ioctl will fail with an EINVAL
 error.
+
+7.2 KVM_CAP_S390_USER_SIGP
+
+Architectures: s390
+Parameters: none
+
+This capability controls which SIGP orders will be handled completely in user
+space. With this capability enabled, all fast orders will be handled completely
+in the kernel:
+- SENSE
+- SENSE RUNNING
+- EXTERNAL CALL
+- EMERGENCY SIGNAL
+- CONDITIONAL EMERGENCY SIGNAL
+
+All other orders will be handled completely in user space.
+
+Only privileged operation exceptions will be checked for in the kernel (or even
+in the hardware prior to interception). If this capability is not enabled, the
+old way of handling SIGP orders is used (partially in kernel and user space).

Documentation/virtual/kvm/devices/arm-vgic.txt

@@ -3,22 +3,42 @@ ARM Virtual Generic Interrupt Controller (VGIC)
 
 Device types supported:
   KVM_DEV_TYPE_ARM_VGIC_V2     ARM Generic Interrupt Controller v2.0
+  KVM_DEV_TYPE_ARM_VGIC_V3     ARM Generic Interrupt Controller v3.0
 
 Only one VGIC instance may be instantiated through either this API or the
 legacy KVM_CREATE_IRQCHIP api.  The created VGIC will act as the VM interrupt
 controller, requiring emulated user-space devices to inject interrupts to the
 VGIC instead of directly to CPUs.
 
+Creating a guest GICv3 device requires a host GICv3 as well.
+GICv3 implementations with hardware compatibility support allow a guest GICv2
+as well.
+
 Groups:
   KVM_DEV_ARM_VGIC_GRP_ADDR
   Attributes:
     KVM_VGIC_V2_ADDR_TYPE_DIST (rw, 64-bit)
       Base address in the guest physical address space of the GIC distributor
-      register mappings.
+      register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V2.
+      This address needs to be 4K aligned and the region covers 4 KByte.
 
     KVM_VGIC_V2_ADDR_TYPE_CPU (rw, 64-bit)
       Base address in the guest physical address space of the GIC virtual cpu
-      interface register mappings.
+      interface register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V2.
+      This address needs to be 4K aligned and the region covers 4 KByte.
+
+    KVM_VGIC_V3_ADDR_TYPE_DIST (rw, 64-bit)
+      Base address in the guest physical address space of the GICv3 distributor
+      register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V3.
+      This address needs to be 64K aligned and the region covers 64 KByte.
+
+    KVM_VGIC_V3_ADDR_TYPE_REDIST (rw, 64-bit)
+      Base address in the guest physical address space of the GICv3
+      redistributor register mappings. There are two 64K pages for each
+      VCPU and all of the redistributor pages are contiguous.
+      Only valid for KVM_DEV_TYPE_ARM_VGIC_V3.
+      This address needs to be 64K aligned.
+
 
   KVM_DEV_ARM_VGIC_GRP_DIST_REGS
   Attributes:
@@ -36,6 +56,7 @@ Groups:
     the register.
   Limitations:
     - Priorities are not implemented, and registers are RAZ/WI
+    - Currently only implemented for KVM_DEV_TYPE_ARM_VGIC_V2.
   Errors:
     -ENODEV: Getting or setting this register is not yet supported
     -EBUSY: One or more VCPUs are running
@@ -68,6 +89,7 @@ Groups:
 
   Limitations:
     - Priorities are not implemented, and registers are RAZ/WI
+    - Currently only implemented for KVM_DEV_TYPE_ARM_VGIC_V2.
   Errors:
     -ENODEV: Getting or setting this register is not yet supported
     -EBUSY: One or more VCPUs are running
@@ -81,3 +103,14 @@ Groups:
     -EINVAL: Value set is out of the expected range
     -EBUSY: Value has already be set, or GIC has already been initialized
             with default values.
+
+  KVM_DEV_ARM_VGIC_GRP_CTRL
+  Attributes:
+    KVM_DEV_ARM_VGIC_CTRL_INIT
+      request the initialization of the VGIC, no additional parameter in
+      kvm_device_attr.addr.
+  Errors:
+    -ENXIO: VGIC not properly configured as required prior to calling
+     this attribute
+    -ENODEV: no online VCPU
+    -ENOMEM: memory shortage when allocating vgic internal data

Documentation/virtual/kvm/devices/vm.txt

@@ -24,3 +24,62 @@ Returns: 0
 
 Clear the CMMA status for all guest pages, so any pages the guest marked
 as unused are again used any may not be reclaimed by the host.
+
+1.3. ATTRIBUTE KVM_S390_VM_MEM_LIMIT_SIZE
+Parameters: in attr->addr the address for the new limit of guest memory
+Returns: -EFAULT if the given address is not accessible
+         -EINVAL if the virtual machine is of type UCONTROL
+         -E2BIG if the given guest memory is to big for that machine
+         -EBUSY if a vcpu is already defined
+         -ENOMEM if not enough memory is available for a new shadow guest mapping
+          0 otherwise
+
+Allows userspace to query the actual limit and set a new limit for
+the maximum guest memory size. The limit will be rounded up to
+2048 MB, 4096 GB, 8192 TB respectively, as this limit is governed by
+the number of page table levels.
+
+2. GROUP: KVM_S390_VM_CPU_MODEL
+Architectures: s390
+
+2.1. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE (r/o)
+
+Allows user space to retrieve machine and kvm specific cpu related information:
+
+struct kvm_s390_vm_cpu_machine {
+       __u64 cpuid;           # CPUID of host
+       __u32 ibc;             # IBC level range offered by host
+       __u8  pad[4];
+       __u64 fac_mask[256];   # set of cpu facilities enabled by KVM
+       __u64 fac_list[256];   # set of cpu facilities offered by host
+}
+
+Parameters: address of buffer to store the machine related cpu data
+            of type struct kvm_s390_vm_cpu_machine*
+Returns:    -EFAULT if the given address is not accessible from kernel space
+	    -ENOMEM if not enough memory is available to process the ioctl
+	    0 in case of success
+
+2.2. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR (r/w)
+
+Allows user space to retrieve or request to change cpu related information for a vcpu:
+
+struct kvm_s390_vm_cpu_processor {
+       __u64 cpuid;           # CPUID currently (to be) used by this vcpu
+       __u16 ibc;             # IBC level currently (to be) used by this vcpu
+       __u8  pad[6];
+       __u64 fac_list[256];   # set of cpu facilities currently (to be) used
+                              # by this vcpu
+}
+
+KVM does not enforce or limit the cpu model data in any form. Take the information
+retrieved by means of KVM_S390_VM_CPU_MACHINE as hint for reasonable configuration
+setups. Instruction interceptions triggered by additionally set facilitiy bits that
+are not handled by KVM need to by imlemented in the VM driver code.
+
+Parameters: address of buffer to store/set the processor related cpu
+	    data of type struct kvm_s390_vm_cpu_processor*.
+Returns:    -EBUSY in case 1 or more vcpus are already activated (only in write case)
+	    -EFAULT if the given address is not accessible from kernel space
+	    -ENOMEM if not enough memory is available to process the ioctl
+	    0 in case of success

arch/arm/include/asm/kvm_asm.h

@@ -96,6 +96,7 @@ extern char __kvm_hyp_code_end[];
 
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
+extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 #endif

arch/arm/include/asm/kvm_emulate.h

@@ -23,6 +23,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
 #include <asm/kvm_arm.h>
+#include <asm/cputype.h>
 
 unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
 unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu);
@@ -177,9 +178,9 @@ static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK;
 }
 
-static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu)
+static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.cp15[c0_MPIDR];
+	return vcpu->arch.cp15[c0_MPIDR] & MPIDR_HWID_BITMASK;
 }
 
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)

arch/arm/include/asm/kvm_host.h

@@ -68,6 +68,7 @@ struct kvm_arch {
 
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
+	int max_vcpus;
 };
 
 #define KVM_NR_MEM_OBJS     40
@@ -144,6 +145,7 @@ struct kvm_vm_stat {
 };
 
 struct kvm_vcpu_stat {
+	u32 halt_successful_poll;
 	u32 halt_wakeup;
 };
 
@@ -231,6 +233,10 @@ static inline void vgic_arch_setup(const struct vgic_params *vgic)
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
+void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
+
+struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
+
 static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}

arch/arm/include/asm/kvm_mmio.h

@@ -37,6 +37,7 @@ struct kvm_exit_mmio {
 	u8		data[8];
 	u32		len;
 	bool		is_write;
+	void		*private;
 };
 
 static inline void kvm_prepare_mmio(struct kvm_run *run,

arch/arm/include/asm/kvm_mmu.h

@@ -115,6 +115,27 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 	pmd_val(*pmd) |= L_PMD_S2_RDWR;
 }
 
+static inline void kvm_set_s2pte_readonly(pte_t *pte)
+{
+	pte_val(*pte) = (pte_val(*pte) & ~L_PTE_S2_RDWR) | L_PTE_S2_RDONLY;
+}
+
+static inline bool kvm_s2pte_readonly(pte_t *pte)
+{
+	return (pte_val(*pte) & L_PTE_S2_RDWR) == L_PTE_S2_RDONLY;
+}
+
+static inline void kvm_set_s2pmd_readonly(pmd_t *pmd)
+{
+	pmd_val(*pmd) = (pmd_val(*pmd) & ~L_PMD_S2_RDWR) | L_PMD_S2_RDONLY;
+}
+
+static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
+{
+	return (pmd_val(*pmd) & L_PMD_S2_RDWR) == L_PMD_S2_RDONLY;
+}
+
+
 /* Open coded p*d_addr_end that can deal with 64bit addresses */
 #define kvm_pgd_addr_end(addr, end)					\
 ({	u64 __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK;		\

arch/arm/include/asm/pgtable-3level.h

@@ -129,6 +129,7 @@
 #define L_PTE_S2_RDONLY			(_AT(pteval_t, 1) << 6)   /* HAP[1]   */
 #define L_PTE_S2_RDWR			(_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
 
+#define L_PMD_S2_RDONLY			(_AT(pmdval_t, 1) << 6)   /* HAP[1]   */
 #define L_PMD_S2_RDWR			(_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
 
 /*

arch/arm/include/uapi/asm/kvm.h

@@ -175,6 +175,8 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
 #define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
 #define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
+#define KVM_DEV_ARM_VGIC_GRP_CTRL       4
+#define   KVM_DEV_ARM_VGIC_CTRL_INIT    0
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24

arch/arm/kvm/Kconfig

@@ -21,8 +21,10 @@ config KVM
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
+	select HAVE_KVM_ARCH_TLB_FLUSH_ALL
 	select KVM_MMIO
 	select KVM_ARM_HOST
+	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select SRCU
 	depends on ARM_VIRT_EXT && ARM_LPAE
 	---help---

arch/arm/kvm/Makefile

@@ -22,4 +22,5 @@ obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
 obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o
 obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o
 obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o
+obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2-emul.o
 obj-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o

arch/arm/kvm/arm.c

@@ -132,6 +132,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	/* Mark the initial VMID generation invalid */
 	kvm->arch.vmid_gen = 0;
 
+	/* The maximum number of VCPUs is limited by the host's GIC model */
+	kvm->arch.max_vcpus = kvm_vgic_get_max_vcpus();
+
 	return ret;
 out_free_stage2_pgd:
 	kvm_free_stage2_pgd(kvm);
@@ -218,6 +221,11 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 		goto out;
 	}
 
+	if (id >= kvm->arch.max_vcpus) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
 	if (!vcpu) {
 		err = -ENOMEM;
@@ -241,9 +249,8 @@ out:
 	return ERR_PTR(err);
 }
 
-int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
+void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
-	return 0;
 }
 
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
@@ -777,9 +784,39 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	}
 }
 
+/**
+ * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot
+ * @kvm: kvm instance
+ * @log: slot id and address to which we copy the log
+ *
+ * Steps 1-4 below provide general overview of dirty page logging. See
+ * kvm_get_dirty_log_protect() function description for additional details.
+ *
+ * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we
+ * always flush the TLB (step 4) even if previous step failed  and the dirty
+ * bitmap may be corrupt. Regardless of previous outcome the KVM logging API
+ * does not preclude user space subsequent dirty log read. Flushing TLB ensures
+ * writes will be marked dirty for next log read.
+ *
+ *   1. Take a snapshot of the bit and clear it if needed.
+ *   2. Write protect the corresponding page.
+ *   3. Copy the snapshot to the userspace.
+ *   4. Flush TLB's if needed.
+ */
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 {
-	return -EINVAL;
+	bool is_dirty = false;
+	int r;
+
+	mutex_lock(&kvm->slots_lock);
+
+	r = kvm_get_dirty_log_protect(kvm, log, &is_dirty);
+
+	if (is_dirty)
+		kvm_flush_remote_tlbs(kvm);
+
+	mutex_unlock(&kvm->slots_lock);
+	return r;
 }
 
 static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm,
@@ -811,7 +848,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	switch (ioctl) {
 	case KVM_CREATE_IRQCHIP: {
 		if (vgic_present)
-			return kvm_vgic_create(kvm);
+			return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
 		else
 			return -ENXIO;
 	}
@@ -1035,6 +1072,19 @@ static void check_kvm_target_cpu(void *ret)
 	*(int *)ret = kvm_target_cpu();
 }
 
+struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr)
+{
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	mpidr &= MPIDR_HWID_BITMASK;
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (mpidr == kvm_vcpu_get_mpidr_aff(vcpu))
+			return vcpu;
+	}
+	return NULL;
+}
+
 /**
  * Initialize Hyp-mode and memory mappings on all CPUs.
  */

arch/arm/kvm/handle_exit.c

@@ -87,11 +87,13 @@ static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
  */
 static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	trace_kvm_wfi(*vcpu_pc(vcpu));
-	if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE)
+	if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE) {
+		trace_kvm_wfx(*vcpu_pc(vcpu), true);
 		kvm_vcpu_on_spin(vcpu);
-	else
+	} else {
+		trace_kvm_wfx(*vcpu_pc(vcpu), false);
 		kvm_vcpu_block(vcpu);
+	}
 
 	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
 

arch/arm/kvm/interrupts.S

@@ -66,6 +66,17 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 	bx	lr
 ENDPROC(__kvm_tlb_flush_vmid_ipa)
 
+/**
+ * void __kvm_tlb_flush_vmid(struct kvm *kvm) - Flush per-VMID TLBs
+ *
+ * Reuses __kvm_tlb_flush_vmid_ipa() for ARMv7, without passing address
+ * parameter
+ */
+
+ENTRY(__kvm_tlb_flush_vmid)
+	b	__kvm_tlb_flush_vmid_ipa
+ENDPROC(__kvm_tlb_flush_vmid)
+
 /********************************************************************
  * Flush TLBs and instruction caches of all CPUs inside the inner-shareable
  * domain, for all VMIDs

arch/arm/kvm/mmu.c

@@ -45,6 +45,26 @@ static phys_addr_t hyp_idmap_vector;
 #define hyp_pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
 
 #define kvm_pmd_huge(_x)	(pmd_huge(_x) || pmd_trans_huge(_x))
+#define kvm_pud_huge(_x)	pud_huge(_x)
+
+#define KVM_S2PTE_FLAG_IS_IOMAP		(1UL << 0)
+#define KVM_S2_FLAG_LOGGING_ACTIVE	(1UL << 1)
+
+static bool memslot_is_logging(struct kvm_memory_slot *memslot)
+{
+	return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY);
+}
+
+/**
+ * kvm_flush_remote_tlbs() - flush all VM TLB entries for v7/8
+ * @kvm:	pointer to kvm structure.
+ *
+ * Interface to HYP function to flush all VM TLB entries
+ */
+void kvm_flush_remote_tlbs(struct kvm *kvm)
+{
+	kvm_call_hyp(__kvm_tlb_flush_vmid, kvm);
+}
 
 static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
@@ -78,6 +98,25 @@ static void kvm_flush_dcache_pud(pud_t pud)
 	__kvm_flush_dcache_pud(pud);
 }
 
+/**
+ * stage2_dissolve_pmd() - clear and flush huge PMD entry
+ * @kvm:	pointer to kvm structure.
+ * @addr:	IPA
+ * @pmd:	pmd pointer for IPA
+ *
+ * Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs. Marks all
+ * pages in the range dirty.
+ */
+static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd)
+{
+	if (!kvm_pmd_huge(*pmd))
+		return;
+
+	pmd_clear(pmd);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	put_page(virt_to_page(pmd));
+}
+
 static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
 				  int min, int max)
 {
@@ -819,10 +858,15 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
 }
 
 static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
-			  phys_addr_t addr, const pte_t *new_pte, bool iomap)
+			  phys_addr_t addr, const pte_t *new_pte,
+			  unsigned long flags)
 {
 	pmd_t *pmd;
 	pte_t *pte, old_pte;
+	bool iomap = flags & KVM_S2PTE_FLAG_IS_IOMAP;
+	bool logging_active = flags & KVM_S2_FLAG_LOGGING_ACTIVE;
+
+	VM_BUG_ON(logging_active && !cache);
 
 	/* Create stage-2 page table mapping - Levels 0 and 1 */
 	pmd = stage2_get_pmd(kvm, cache, addr);
@@ -834,6 +878,13 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 		return 0;
 	}
 
+	/*
+	 * While dirty page logging - dissolve huge PMD, then continue on to
+	 * allocate page.
+	 */
+	if (logging_active)
+		stage2_dissolve_pmd(kvm, addr, pmd);
+
 	/* Create stage-2 page mappings - Level 2 */
 	if (pmd_none(*pmd)) {
 		if (!cache)
@@ -890,7 +941,8 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 		if (ret)
 			goto out;
 		spin_lock(&kvm->mmu_lock);
-		ret = stage2_set_pte(kvm, &cache, addr, &pte, true);
+		ret = stage2_set_pte(kvm, &cache, addr, &pte,
+						KVM_S2PTE_FLAG_IS_IOMAP);
 		spin_unlock(&kvm->mmu_lock);
 		if (ret)
 			goto out;
@@ -957,6 +1009,165 @@ static bool kvm_is_device_pfn(unsigned long pfn)
 	return !pfn_valid(pfn);
 }
 
+/**
+ * stage2_wp_ptes - write protect PMD range
+ * @pmd:	pointer to pmd entry
+ * @addr:	range start address
+ * @end:	range end address
+ */
+static void stage2_wp_ptes(pmd_t *pmd, phys_addr_t addr, phys_addr_t end)
+{
+	pte_t *pte;
+
+	pte = pte_offset_kernel(pmd, addr);
+	do {
+		if (!pte_none(*pte)) {
+			if (!kvm_s2pte_readonly(pte))
+				kvm_set_s2pte_readonly(pte);
+		}
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+}
+
+/**
+ * stage2_wp_pmds - write protect PUD range
+ * @pud:	pointer to pud entry
+ * @addr:	range start address
+ * @end:	range end address
+ */
+static void stage2_wp_pmds(pud_t *pud, phys_addr_t addr, phys_addr_t end)
+{
+	pmd_t *pmd;
+	phys_addr_t next;
+
+	pmd = pmd_offset(pud, addr);
+
+	do {
+		next = kvm_pmd_addr_end(addr, end);
+		if (!pmd_none(*pmd)) {
+			if (kvm_pmd_huge(*pmd)) {
+				if (!kvm_s2pmd_readonly(pmd))
+					kvm_set_s2pmd_readonly(pmd);
+			} else {
+				stage2_wp_ptes(pmd, addr, next);
+			}
+		}
+	} while (pmd++, addr = next, addr != end);
+}
+
+/**
+  * stage2_wp_puds - write protect PGD range
+  * @pgd:	pointer to pgd entry
+  * @addr:	range start address
+  * @end:	range end address
+  *
+  * Process PUD entries, for a huge PUD we cause a panic.
+  */
+static void  stage2_wp_puds(pgd_t *pgd, phys_addr_t addr, phys_addr_t end)
+{
+	pud_t *pud;
+	phys_addr_t next;
+
+	pud = pud_offset(pgd, addr);
+	do {
+		next = kvm_pud_addr_end(addr, end);
+		if (!pud_none(*pud)) {
+			/* TODO:PUD not supported, revisit later if supported */
+			BUG_ON(kvm_pud_huge(*pud));
+			stage2_wp_pmds(pud, addr, next);
+		}
+	} while (pud++, addr = next, addr != end);
+}
+
+/**
+ * stage2_wp_range() - write protect stage2 memory region range
+ * @kvm:	The KVM pointer
+ * @addr:	Start address of range
+ * @end:	End address of range
+ */
+static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
+{
+	pgd_t *pgd;
+	phys_addr_t next;
+
+	pgd = kvm->arch.pgd + pgd_index(addr);
+	do {
+		/*
+		 * Release kvm_mmu_lock periodically if the memory region is
+		 * large. Otherwise, we may see kernel panics with
+		 * CONFIG_DETECT_HUNG_TASK, CONFIG_LOCKUP_DETECTOR,
+		 * CONFIG_LOCKDEP. Additionally, holding the lock too long
+		 * will also starve other vCPUs.
+		 */
+		if (need_resched() || spin_needbreak(&kvm->mmu_lock))
+			cond_resched_lock(&kvm->mmu_lock);
+
+		next = kvm_pgd_addr_end(addr, end);
+		if (pgd_present(*pgd))
+			stage2_wp_puds(pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
+}
+
+/**
+ * kvm_mmu_wp_memory_region() - write protect stage 2 entries for memory slot
+ * @kvm:	The KVM pointer
+ * @slot:	The memory slot to write protect
+ *
+ * Called to start logging dirty pages after memory region
+ * KVM_MEM_LOG_DIRTY_PAGES operation is called. After this function returns
+ * all present PMD and PTEs are write protected in the memory region.
+ * Afterwards read of dirty page log can be called.
+ *
+ * Acquires kvm_mmu_lock. Called with kvm->slots_lock mutex acquired,
+ * serializing operations for VM memory regions.
+ */
+void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
+{
+	struct kvm_memory_slot *memslot = id_to_memslot(kvm->memslots, slot);
+	phys_addr_t start = memslot->base_gfn << PAGE_SHIFT;
+	phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
+
+	spin_lock(&kvm->mmu_lock);
+	stage2_wp_range(kvm, start, end);
+	spin_unlock(&kvm->mmu_lock);
+	kvm_flush_remote_tlbs(kvm);
+}
+
+/**
+ * kvm_mmu_write_protect_pt_masked() - write protect dirty pages
+ * @kvm:	The KVM pointer
+ * @slot:	The memory slot associated with mask
+ * @gfn_offset:	The gfn offset in memory slot
+ * @mask:	The mask of dirty pages at offset 'gfn_offset' in this memory
+ *		slot to be write protected
+ *
+ * Walks bits set in mask write protects the associated pte's. Caller must
+ * acquire kvm_mmu_lock.
+ */
+static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
+		struct kvm_memory_slot *slot,
+		gfn_t gfn_offset, unsigned long mask)
+{
+	phys_addr_t base_gfn = slot->base_gfn + gfn_offset;
+	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
+	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
+
+	stage2_wp_range(kvm, start, end);
+}
+
+/*
+ * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected
+ * dirty pages.
+ *
+ * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to
+ * enable dirty logging for them.
+ */
+void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
+		struct kvm_memory_slot *slot,
+		gfn_t gfn_offset, unsigned long mask)
+{
+	kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
+}
+
 static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
 				      unsigned long size, bool uncached)
 {
@@ -977,6 +1188,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	pfn_t pfn;
 	pgprot_t mem_type = PAGE_S2;
 	bool fault_ipa_uncached;
+	bool logging_active = memslot_is_logging(memslot);
+	unsigned long flags = 0;
 
 	write_fault = kvm_is_write_fault(vcpu);
 	if (fault_status == FSC_PERM && !write_fault) {
@@ -993,7 +1206,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		return -EFAULT;
 	}
 
-	if (is_vm_hugetlb_page(vma)) {
+	if (is_vm_hugetlb_page(vma) && !logging_active) {
 		hugetlb = true;
 		gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT;
 	} else {
@@ -1034,12 +1247,30 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (is_error_pfn(pfn))
 		return -EFAULT;
 
-	if (kvm_is_device_pfn(pfn))
+	if (kvm_is_device_pfn(pfn)) {
 		mem_type = PAGE_S2_DEVICE;
+		flags |= KVM_S2PTE_FLAG_IS_IOMAP;
+	} else if (logging_active) {
+		/*
+		 * Faults on pages in a memslot with logging enabled
+		 * should not be mapped with huge pages (it introduces churn
+		 * and performance degradation), so force a pte mapping.
+		 */
+		force_pte = true;
+		flags |= KVM_S2_FLAG_LOGGING_ACTIVE;
+
+		/*
+		 * Only actually map the page as writable if this was a write
+		 * fault.
+		 */
+		if (!write_fault)
+			writable = false;
+	}
 
 	spin_lock(&kvm->mmu_lock);
 	if (mmu_notifier_retry(kvm, mmu_seq))
 		goto out_unlock;
+
 	if (!hugetlb && !force_pte)
 		hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa);
 
@@ -1056,16 +1287,16 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
 	} else {
 		pte_t new_pte = pfn_pte(pfn, mem_type);
+
 		if (writable) {
 			kvm_set_s2pte_writable(&new_pte);
 			kvm_set_pfn_dirty(pfn);
+			mark_page_dirty(kvm, gfn);
 		}
 		coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE, fault_ipa_uncached);
-		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte,
-			pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE));
+		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags);
 	}
 
-
 out_unlock:
 	spin_unlock(&kvm->mmu_lock);
 	kvm_release_pfn_clean(pfn);
@@ -1215,7 +1446,14 @@ static void kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data)
 {
 	pte_t *pte = (pte_t *)data;
 
-	stage2_set_pte(kvm, NULL, gpa, pte, false);
+	/*
+	 * We can always call stage2_set_pte with KVM_S2PTE_FLAG_LOGGING_ACTIVE
+	 * flag clear because MMU notifiers will have unmapped a huge PMD before
+	 * calling ->change_pte() (which in turn calls kvm_set_spte_hva()) and
+	 * therefore stage2_set_pte() never needs to clear out a huge PMD
+	 * through this calling path.
+	 */
+	stage2_set_pte(kvm, NULL, gpa, pte, 0);
 }
 
 
@@ -1348,6 +1586,13 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				   const struct kvm_memory_slot *old,
 				   enum kvm_mr_change change)
 {
+	/*
+	 * At this point memslot has been committed and there is an
+	 * allocated dirty_bitmap[], dirty pages will be be tracked while the
+	 * memory slot is write protected.
+	 */
+	if (change != KVM_MR_DELETE && mem->flags & KVM_MEM_LOG_DIRTY_PAGES)
+		kvm_mmu_wp_memory_region(kvm, mem->slot);
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -1360,7 +1605,8 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	bool writable = !(mem->flags & KVM_MEM_READONLY);
 	int ret = 0;
 
-	if (change != KVM_MR_CREATE && change != KVM_MR_MOVE)
+	if (change != KVM_MR_CREATE && change != KVM_MR_MOVE &&
+			change != KVM_MR_FLAGS_ONLY)
 		return 0;
 
 	/*
@@ -1411,6 +1657,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 			phys_addr_t pa = (vma->vm_pgoff << PAGE_SHIFT) +
 					 vm_start - vma->vm_start;
 
+			/* IO region dirty page logging not allowed */
+			if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES)
+				return -EINVAL;
+
 			ret = kvm_phys_addr_ioremap(kvm, gpa, pa,
 						    vm_end - vm_start,
 						    writable);
@@ -1420,6 +1670,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		hva = vm_end;
 	} while (hva < reg_end);
 
+	if (change == KVM_MR_FLAGS_ONLY)
+		return ret;
+
 	spin_lock(&kvm->mmu_lock);
 	if (ret)
 		unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size);

arch/arm/kvm/psci.c

@@ -22,6 +22,7 @@
 #include <asm/cputype.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_psci.h>
+#include <asm/kvm_host.h>
 
 /*
  * This is an implementation of the Power State Coordination Interface
@@ -66,25 +67,17 @@ static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
 static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 {
 	struct kvm *kvm = source_vcpu->kvm;
-	struct kvm_vcpu *vcpu = NULL, *tmp;
+	struct kvm_vcpu *vcpu = NULL;
 	wait_queue_head_t *wq;
 	unsigned long cpu_id;
 	unsigned long context_id;
-	unsigned long mpidr;
 	phys_addr_t target_pc;
-	int i;
 
-	cpu_id = *vcpu_reg(source_vcpu, 1);
+	cpu_id = *vcpu_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
 	if (vcpu_mode_is_32bit(source_vcpu))
 		cpu_id &= ~((u32) 0);
 
-	kvm_for_each_vcpu(i, tmp, kvm) {
-		mpidr = kvm_vcpu_get_mpidr(tmp);
-		if ((mpidr & MPIDR_HWID_BITMASK) == (cpu_id & MPIDR_HWID_BITMASK)) {
-			vcpu = tmp;
-			break;
-		}
-	}
+	vcpu = kvm_mpidr_to_vcpu(kvm, cpu_id);
 
 	/*
 	 * Make sure the caller requested a valid CPU and that the CPU is
@@ -155,7 +148,7 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
 	 * then ON else OFF
 	 */
 	kvm_for_each_vcpu(i, tmp, kvm) {
-		mpidr = kvm_vcpu_get_mpidr(tmp);
+		mpidr = kvm_vcpu_get_mpidr_aff(tmp);
 		if (((mpidr & target_affinity_mask) == target_affinity) &&
 		    !tmp->arch.pause) {
 			return PSCI_0_2_AFFINITY_LEVEL_ON;

arch/arm/kvm/trace.h

@@ -140,19 +140,22 @@ TRACE_EVENT(kvm_emulate_cp15_imp,
 			__entry->CRm, __entry->Op2)
 );
 
-TRACE_EVENT(kvm_wfi,
-	TP_PROTO(unsigned long vcpu_pc),
-	TP_ARGS(vcpu_pc),
+TRACE_EVENT(kvm_wfx,
+	TP_PROTO(unsigned long vcpu_pc, bool is_wfe),
+	TP_ARGS(vcpu_pc, is_wfe),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	vcpu_pc		)
+		__field(		 bool,	is_wfe		)
 	),
 
 	TP_fast_assign(
 		__entry->vcpu_pc		= vcpu_pc;
+		__entry->is_wfe			= is_wfe;
 	),
 
-	TP_printk("guest executed wfi at: 0x%08lx", __entry->vcpu_pc)
+	TP_printk("guest executed wf%c at: 0x%08lx",
+		__entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc)
 );
 
 TRACE_EVENT(kvm_unmap_hva,

arch/arm64/include/asm/esr.h

@@ -96,6 +96,7 @@
 #define ESR_ELx_COND_SHIFT	(20)
 #define ESR_ELx_COND_MASK	(UL(0xF) << ESR_ELx_COND_SHIFT)
 #define ESR_ELx_WFx_ISS_WFE	(UL(1) << 0)
+#define ESR_ELx_xVC_IMM_MASK	((1UL << 16) - 1)
 
 #ifndef __ASSEMBLY__
 #include <asm/types.h>

arch/arm64/include/asm/kvm_asm.h

@@ -126,6 +126,7 @@ extern char __kvm_hyp_vector[];
 
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
+extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);