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 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	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/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);
 

arch/arm64/include/asm/kvm_emulate.h

@@ -29,6 +29,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
 #include <asm/ptrace.h>
+#include <asm/cputype.h>
 
 unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num);
 unsigned long *vcpu_spsr32(const struct kvm_vcpu *vcpu);
@@ -140,6 +141,11 @@ static inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu)
 	return ((phys_addr_t)vcpu->arch.fault.hpfar_el2 & HPFAR_MASK) << 8;
 }
 
+static inline u32 kvm_vcpu_hvc_get_imm(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_xVC_IMM_MASK;
+}
+
 static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV);
@@ -201,9 +207,9 @@ static inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC_TYPE;
 }
 
-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_sys_reg(vcpu, MPIDR_EL1);
+	return vcpu_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
 }
 
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)

arch/arm64/include/asm/kvm_host.h

@@ -59,6 +59,9 @@ struct kvm_arch {
 	/* VTTBR value associated with above pgd and vmid */
 	u64    vttbr;
 
+	/* The maximum number of vCPUs depends on the used GIC model */
+	int max_vcpus;
+
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
 
@@ -159,6 +162,7 @@ struct kvm_vm_stat {
 };
 
 struct kvm_vcpu_stat {
+	u32 halt_successful_poll;
 	u32 halt_wakeup;
 };
 
@@ -196,6 +200,7 @@ struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
 
 u64 kvm_call_hyp(void *hypfn, ...);
 void force_vm_exit(const cpumask_t *mask);
+void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
 
 int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		int exception_index);
@@ -203,6 +208,8 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
+struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
+
 static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
 				       phys_addr_t pgd_ptr,
 				       unsigned long hyp_stack_ptr,

arch/arm64/include/asm/kvm_mmio.h

@@ -40,6 +40,7 @@ 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/arm64/include/asm/kvm_mmu.h

@@ -118,6 +118,27 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 	pmd_val(*pmd) |= PMD_S2_RDWR;
 }
 
+static inline void kvm_set_s2pte_readonly(pte_t *pte)
+{
+	pte_val(*pte) = (pte_val(*pte) & ~PTE_S2_RDWR) | PTE_S2_RDONLY;
+}
+
+static inline bool kvm_s2pte_readonly(pte_t *pte)
+{
+	return (pte_val(*pte) & PTE_S2_RDWR) == PTE_S2_RDONLY;
+}
+
+static inline void kvm_set_s2pmd_readonly(pmd_t *pmd)
+{
+	pmd_val(*pmd) = (pmd_val(*pmd) & ~PMD_S2_RDWR) | PMD_S2_RDONLY;
+}
+
+static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
+{
+	return (pmd_val(*pmd) & PMD_S2_RDWR) == PMD_S2_RDONLY;
+}
+
+
 #define kvm_pgd_addr_end(addr, end)	pgd_addr_end(addr, end)
 #define kvm_pud_addr_end(addr, end)	pud_addr_end(addr, end)
 #define kvm_pmd_addr_end(addr, end)	pmd_addr_end(addr, end)

arch/arm64/include/asm/pgtable-hwdef.h

@@ -119,6 +119,7 @@
 #define PTE_S2_RDONLY		(_AT(pteval_t, 1) << 6)   /* HAP[2:1] */
 #define PTE_S2_RDWR		(_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
 
+#define PMD_S2_RDONLY		(_AT(pmdval_t, 1) << 6)   /* HAP[2:1] */
 #define PMD_S2_RDWR		(_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
 
 /*

arch/arm64/include/uapi/asm/kvm.h

@@ -78,6 +78,13 @@ struct kvm_regs {
 #define KVM_VGIC_V2_DIST_SIZE		0x1000
 #define KVM_VGIC_V2_CPU_SIZE		0x2000
 
+/* Supported VGICv3 address types  */
+#define KVM_VGIC_V3_ADDR_TYPE_DIST	2
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
+
+#define KVM_VGIC_V3_DIST_SIZE		SZ_64K
+#define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
+
 #define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
 #define KVM_ARM_VCPU_EL1_32BIT		1 /* CPU running a 32bit VM */
 #define KVM_ARM_VCPU_PSCI_0_2		2 /* CPU uses PSCI v0.2 */
@@ -161,6 +168,8 @@ 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/arm64/kernel/asm-offsets.c

@@ -140,6 +140,7 @@ int main(void)
   DEFINE(VGIC_V2_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr));
   DEFINE(VGIC_V2_CPU_APR,	offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
   DEFINE(VGIC_V2_CPU_LR,	offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
+  DEFINE(VGIC_V3_CPU_SRE,	offsetof(struct vgic_cpu, vgic_v3.vgic_sre));
   DEFINE(VGIC_V3_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v3.vgic_hcr));
   DEFINE(VGIC_V3_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v3.vgic_vmcr));
   DEFINE(VGIC_V3_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v3.vgic_misr));

arch/arm64/kvm/Kconfig

@@ -22,10 +22,12 @@ 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_ARM_VGIC
 	select KVM_ARM_TIMER
+	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select SRCU
 	---help---
 	  Support hosting virtualized guest machines.

arch/arm64/kvm/Makefile

@@ -21,7 +21,9 @@ kvm-$(CONFIG_KVM_ARM_HOST) += guest.o reset.o sys_regs.o sys_regs_generic_v8.o
 
 kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o
 kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2-emul.o
 kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v2-switch.o
 kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v3.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v3-emul.o
 kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v3-switch.o
 kvm-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o

arch/arm64/kvm/handle_exit.c

@@ -28,12 +28,18 @@
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_psci.h>
 
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
 typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
 
 static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	int ret;
 
+	trace_kvm_hvc_arm64(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
+			    kvm_vcpu_hvc_get_imm(vcpu));
+
 	ret = kvm_psci_call(vcpu);
 	if (ret < 0) {
 		kvm_inject_undefined(vcpu);
@@ -63,10 +69,13 @@ static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
  */
 static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE)
+	if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
+		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
 		kvm_vcpu_on_spin(vcpu);
-	else
+	} else {
+		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false);
 		kvm_vcpu_block(vcpu);
+	}
 
 	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
 

arch/arm64/kvm/hyp.S

@@ -1032,6 +1032,28 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 	ret
 ENDPROC(__kvm_tlb_flush_vmid_ipa)
 
+/**
+ * void __kvm_tlb_flush_vmid(struct kvm *kvm) - Flush per-VMID TLBs
+ * @struct kvm *kvm - pointer to kvm structure
+ *
+ * Invalidates all Stage 1 and 2 TLB entries for current VMID.
+ */
+ENTRY(__kvm_tlb_flush_vmid)
+	dsb     ishst
+
+	kern_hyp_va     x0
+	ldr     x2, [x0, #KVM_VTTBR]
+	msr     vttbr_el2, x2
+	isb
+
+	tlbi    vmalls12e1is
+	dsb     ish
+	isb
+
+	msr     vttbr_el2, xzr
+	ret
+ENDPROC(__kvm_tlb_flush_vmid)
+
 ENTRY(__kvm_flush_vm_context)
 	dsb	ishst
 	tlbi	alle1is

arch/arm64/kvm/sys_regs.c

@@ -113,6 +113,27 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+/*
+ * Trap handler for the GICv3 SGI generation system register.
+ * Forward the request to the VGIC emulation.
+ * The cp15_64 code makes sure this automatically works
+ * for both AArch64 and AArch32 accesses.
+ */
+static bool access_gic_sgi(struct kvm_vcpu *vcpu,
+			   const struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	u64 val;
+
+	if (!p->is_write)
+		return read_from_write_only(vcpu, p);
+
+	val = *vcpu_reg(vcpu, p->Rt);
+	vgic_v3_dispatch_sgi(vcpu, val);
+
+	return true;
+}
+
 static bool trap_raz_wi(struct kvm_vcpu *vcpu,
 			const struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
@@ -200,10 +221,19 @@ static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 
 static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
+	u64 mpidr;
+
 	/*
-	 * Simply map the vcpu_id into the Aff0 field of the MPIDR.
+	 * Map the vcpu_id into the first three affinity level fields of
+	 * the MPIDR. We limit the number of VCPUs in level 0 due to a
+	 * limitation to 16 CPUs in that level in the ICC_SGIxR registers
+	 * of the GICv3 to be able to address each CPU directly when
+	 * sending IPIs.
 	 */
-	vcpu_sys_reg(vcpu, MPIDR_EL1) = (1UL << 31) | (vcpu->vcpu_id & 0xff);
+	mpidr = (vcpu->vcpu_id & 0x0f) << MPIDR_LEVEL_SHIFT(0);
+	mpidr |= ((vcpu->vcpu_id >> 4) & 0xff) << MPIDR_LEVEL_SHIFT(1);
+	mpidr |= ((vcpu->vcpu_id >> 12) & 0xff) << MPIDR_LEVEL_SHIFT(2);
+	vcpu_sys_reg(vcpu, MPIDR_EL1) = (1ULL << 31) | mpidr;
 }
 
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
@@ -373,6 +403,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b0000), Op2(0b000),
 	  NULL, reset_val, VBAR_EL1, 0 },
 
+	/* ICC_SGI1R_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1011), Op2(0b101),
+	  access_gic_sgi },
 	/* ICC_SRE_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1100), Op2(0b101),
 	  trap_raz_wi },
@@ -605,6 +638,8 @@ static const struct sys_reg_desc cp14_64_regs[] = {
  * register).
  */
 static const struct sys_reg_desc cp15_regs[] = {
+	{ Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi },
+
 	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, c1_SCTLR },
 	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
 	{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
@@ -652,6 +687,7 @@ static const struct sys_reg_desc cp15_regs[] = {
 
 static const struct sys_reg_desc cp15_64_regs[] = {
 	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+	{ Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi },
 	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
 };
 

arch/arm64/kvm/trace.h

+#if !defined(_TRACE_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_ARM64_KVM_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+
+TRACE_EVENT(kvm_wfx_arm64,
+	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 wf%c at: 0x%08lx",
+		  __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc)
+);
+
+TRACE_EVENT(kvm_hvc_arm64,
+	TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm),
+	TP_ARGS(vcpu_pc, r0, imm),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, vcpu_pc)
+		__field(unsigned long, r0)
+		__field(unsigned long, imm)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc = vcpu_pc;
+		__entry->r0 = r0;
+		__entry->imm = imm;
+	),
+
+	TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx)",
+		  __entry->vcpu_pc, __entry->r0, __entry->imm)
+);
+
+#endif /* _TRACE_ARM64_KVM_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

arch/arm64/kvm/vgic-v3-switch.S

@@ -148,17 +148,18 @@
  * x0: Register pointing to VCPU struct
  */
 .macro	restore_vgic_v3_state
-	// Disable SRE_EL1 access. Necessary, otherwise
-	// ICH_VMCR_EL2.VFIQEn becomes one, and FIQ happens...
-	msr_s	ICC_SRE_EL1, xzr
-	isb
-
 	// Compute the address of struct vgic_cpu
 	add	x3, x0, #VCPU_VGIC_CPU
 
 	// Restore all interesting registers
 	ldr	w4, [x3, #VGIC_V3_CPU_HCR]
 	ldr	w5, [x3, #VGIC_V3_CPU_VMCR]
+	ldr	w25, [x3, #VGIC_V3_CPU_SRE]
+
+	msr_s	ICC_SRE_EL1, x25
+
+	// make sure SRE is valid before writing the other registers
+	isb
 
 	msr_s	ICH_HCR_EL2, x4
 	msr_s	ICH_VMCR_EL2, x5
@@ -244,9 +245,12 @@
 	dsb	sy
 
 	// Prevent the guest from touching the GIC system registers
+	// if SRE isn't enabled for GICv3 emulation
+	cbnz	x25, 1f
 	mrs_s	x5, ICC_SRE_EL2
 	and	x5, x5, #~ICC_SRE_EL2_ENABLE
 	msr_s	ICC_SRE_EL2, x5
+1:
 .endm
 
 ENTRY(__save_vgic_v3_state)

arch/ia64/include/uapi/asm/Kbuild

@@ -18,7 +18,6 @@ header-y += intrinsics.h
 header-y += ioctl.h
 header-y += ioctls.h
 header-y += ipcbuf.h
-header-y += kvm.h
 header-y += kvm_para.h
 header-y += mman.h
 header-y += msgbuf.h

arch/mips/include/asm/kvm_host.h

@@ -120,6 +120,7 @@ struct kvm_vcpu_stat {
 	u32 resvd_inst_exits;
 	u32 break_inst_exits;
 	u32 flush_dcache_exits;
+	u32 halt_successful_poll;
 	u32 halt_wakeup;
 };
 

arch/mips/kvm/locore.S

@@ -434,7 +434,7 @@ __kvm_mips_return_to_guest:
 	/* Setup status register for running guest in UM */
 	.set	at
 	or	v1, v1, (ST0_EXL | KSU_USER | ST0_IE)
-	and	v1, v1, ~ST0_CU0
+	and	v1, v1, ~(ST0_CU0 | ST0_MX)
 	.set	noat
 	mtc0	v1, CP0_STATUS
 	ehb

arch/mips/kvm/mips.c

@@ -15,9 +15,11 @@
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
 #include <linux/bootmem.h>
+#include <asm/fpu.h>
 #include <asm/page.h>
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
+#include <asm/pgtable.h>
 
 #include <linux/kvm_host.h>
 
@@ -47,6 +49,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "resvd_inst",	  VCPU_STAT(resvd_inst_exits),	 KVM_STAT_VCPU },
 	{ "break_inst",	  VCPU_STAT(break_inst_exits),	 KVM_STAT_VCPU },
 	{ "flush_dcache", VCPU_STAT(flush_dcache_exits), KVM_STAT_VCPU },
+	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll), KVM_STAT_VCPU },
 	{ "halt_wakeup",  VCPU_STAT(halt_wakeup),	 KVM_STAT_VCPU },
 	{NULL}
 };
@@ -378,6 +381,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		vcpu->mmio_needed = 0;
 	}
 
+	lose_fpu(1);
+
 	local_irq_disable();
 	/* Check if we have any exceptions/interrupts pending */
 	kvm_mips_deliver_interrupts(vcpu,
@@ -385,8 +390,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	kvm_guest_enter();
 
+	/* Disable hardware page table walking while in guest */
+	htw_stop();
+
 	r = __kvm_mips_vcpu_run(run, vcpu);
 
+	/* Re-enable HTW before enabling interrupts */
+	htw_start();
+
 	kvm_guest_exit();
 	local_irq_enable();
 
@@ -832,9 +843,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return -ENOIOCTLCMD;
 }
 
-int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
+void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
-	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
@@ -980,9 +990,6 @@ static void kvm_mips_set_c0_status(void)
 {
 	uint32_t status = read_c0_status();
 
-	if (cpu_has_fpu)
-		status |= (ST0_CU1);
-
 	if (cpu_has_dsp)
 		status |= (ST0_MX);
 
@@ -1002,6 +1009,9 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
+	/* re-enable HTW before enabling interrupts */
+	htw_start();
+
 	/* Set a default exit reason */
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	run->ready_for_interrupt_injection = 1;
@@ -1136,6 +1146,9 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		}
 	}
 
+	/* Disable HTW before returning to guest or host */
+	htw_stop();
+
 	return ret;
 }
 

arch/powerpc/include/asm/kvm_host.h

@@ -107,6 +107,7 @@ struct kvm_vcpu_stat {
 	u32 emulated_inst_exits;
 	u32 dec_exits;
 	u32 ext_intr_exits;
+	u32 halt_successful_poll;
 	u32 halt_wakeup;
 	u32 dbell_exits;
 	u32 gdbell_exits;

arch/powerpc/kvm/book3s.c

@@ -52,6 +52,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "dec",         VCPU_STAT(dec_exits) },
 	{ "ext_intr",    VCPU_STAT(ext_intr_exits) },
 	{ "queue_intr",  VCPU_STAT(queue_intr) },
+	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll), },
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
 	{ "pf_storage",  VCPU_STAT(pf_storage) },
 	{ "sp_storage",  VCPU_STAT(sp_storage) },

arch/powerpc/kvm/booke.c

@@ -62,6 +62,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "inst_emu",   VCPU_STAT(emulated_inst_exits) },
 	{ "dec",        VCPU_STAT(dec_exits) },
 	{ "ext_intr",   VCPU_STAT(ext_intr_exits) },
+	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
 	{ "doorbell", VCPU_STAT(dbell_exits) },
 	{ "guest doorbell", VCPU_STAT(gdbell_exits) },

arch/powerpc/kvm/powerpc.c

@@ -623,9 +623,8 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	return vcpu;
 }
 
-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)

arch/s390/include/asm/kvm_host.h

@@ -35,11 +35,13 @@
 #define KVM_NR_IRQCHIPS 1
 #define KVM_IRQCHIP_NUM_PINS 4096
 
-#define SIGP_CTRL_C	0x00800000
+#define SIGP_CTRL_C		0x80
+#define SIGP_CTRL_SCN_MASK	0x3f
 
 struct sca_entry {
-	atomic_t ctrl;
-	__u32	reserved;
+	__u8	reserved0;
+	__u8	sigp_ctrl;
+	__u16	reserved[3];
 	__u64	sda;
 	__u64	reserved2[2];
 } __attribute__((packed));
@@ -87,7 +89,8 @@ struct kvm_s390_sie_block {
 	atomic_t cpuflags;		/* 0x0000 */
 	__u32 : 1;			/* 0x0004 */
 	__u32 prefix : 18;
-	__u32 : 13;
+	__u32 : 1;
+	__u32 ibc : 12;
 	__u8	reserved08[4];		/* 0x0008 */
 #define PROG_IN_SIE (1<<0)
 	__u32	prog0c;			/* 0x000c */
@@ -132,7 +135,9 @@ struct kvm_s390_sie_block {
 	__u8	reserved60;		/* 0x0060 */
 	__u8	ecb;			/* 0x0061 */
 	__u8    ecb2;                   /* 0x0062 */
-	__u8    reserved63[1];          /* 0x0063 */
+#define ECB3_AES 0x04
+#define ECB3_DEA 0x08
+	__u8    ecb3;			/* 0x0063 */
 	__u32	scaol;			/* 0x0064 */
 	__u8	reserved68[4];		/* 0x0068 */
 	__u32	todpr;			/* 0x006c */
@@ -159,6 +164,7 @@ struct kvm_s390_sie_block {
 	__u64	tecmc;			/* 0x00e8 */
 	__u8	reservedf0[12];		/* 0x00f0 */
 #define CRYCB_FORMAT1 0x00000001
+#define CRYCB_FORMAT2 0x00000003
 	__u32	crycbd;			/* 0x00fc */
 	__u64	gcr[16];		/* 0x0100 */
 	__u64	gbea;			/* 0x0180 */
@@ -192,6 +198,7 @@ struct kvm_vcpu_stat {
 	u32 exit_stop_request;
 	u32 exit_validity;
 	u32 exit_instruction;
+	u32 halt_successful_poll;
 	u32 halt_wakeup;
 	u32 instruction_lctl;
 	u32 instruction_lctlg;
@@ -378,14 +385,11 @@ struct kvm_s390_interrupt_info {
 		struct kvm_s390_emerg_info emerg;
 		struct kvm_s390_extcall_info extcall;
 		struct kvm_s390_prefix_info prefix;
+		struct kvm_s390_stop_info stop;
 		struct kvm_s390_mchk_info mchk;
 	};
 };
 
-/* for local_interrupt.action_flags */
-#define ACTION_STORE_ON_STOP		(1<<0)
-#define ACTION_STOP_ON_STOP		(1<<1)
-
 struct kvm_s390_irq_payload {
 	struct kvm_s390_io_info io;
 	struct kvm_s390_ext_info ext;
@@ -393,6 +397,7 @@ struct kvm_s390_irq_payload {
 	struct kvm_s390_emerg_info emerg;
 	struct kvm_s390_extcall_info extcall;
 	struct kvm_s390_prefix_info prefix;
+	struct kvm_s390_stop_info stop;
 	struct kvm_s390_mchk_info mchk;
 };
 
@@ -401,7 +406,6 @@ struct kvm_s390_local_interrupt {
 	struct kvm_s390_float_interrupt *float_int;
 	wait_queue_head_t *wq;
 	atomic_t *cpuflags;
-	unsigned int action_bits;
 	DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS);
 	struct kvm_s390_irq_payload irq;
 	unsigned long pending_irqs;
@@ -470,7 +474,6 @@ struct kvm_vcpu_arch {
 	};
 	struct gmap *gmap;
 	struct kvm_guestdbg_info_arch guestdbg;
-#define KVM_S390_PFAULT_TOKEN_INVALID	(-1UL)
 	unsigned long pfault_token;
 	unsigned long pfault_select;
 	unsigned long pfault_compare;
@@ -504,13 +507,39 @@ struct s390_io_adapter {
 #define MAX_S390_IO_ADAPTERS ((MAX_ISC + 1) * 8)
 #define MAX_S390_ADAPTER_MAPS 256
 
+/* maximum size of facilities and facility mask is 2k bytes */
+#define S390_ARCH_FAC_LIST_SIZE_BYTE (1<<11)
+#define S390_ARCH_FAC_LIST_SIZE_U64 \
+	(S390_ARCH_FAC_LIST_SIZE_BYTE / sizeof(u64))
+#define S390_ARCH_FAC_MASK_SIZE_BYTE S390_ARCH_FAC_LIST_SIZE_BYTE
+#define S390_ARCH_FAC_MASK_SIZE_U64 \
+	(S390_ARCH_FAC_MASK_SIZE_BYTE / sizeof(u64))
+
+struct s390_model_fac {
+	/* facilities used in SIE context */
+	__u64 sie[S390_ARCH_FAC_LIST_SIZE_U64];
+	/* subset enabled by kvm */
+	__u64 kvm[S390_ARCH_FAC_LIST_SIZE_U64];
+};
+
+struct kvm_s390_cpu_model {
+	struct s390_model_fac *fac;
+	struct cpuid cpu_id;
+	unsigned short ibc;
+};
+
 struct kvm_s390_crypto {
 	struct kvm_s390_crypto_cb *crycb;
 	__u32 crycbd;
+	__u8 aes_kw;
+	__u8 dea_kw;
 };
 
 struct kvm_s390_crypto_cb {
-	__u8    reserved00[128];                /* 0x0000 */
+	__u8    reserved00[72];                 /* 0x0000 */
+	__u8    dea_wrapping_key_mask[24];      /* 0x0048 */
+	__u8    aes_wrapping_key_mask[32];      /* 0x0060 */
+	__u8    reserved80[128];                /* 0x0080 */
 };
 
 struct kvm_arch{
@@ -523,12 +552,15 @@ struct kvm_arch{
 	int use_irqchip;
 	int use_cmma;
 	int user_cpu_state_ctrl;
+	int user_sigp;
 	struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
 	wait_queue_head_t ipte_wq;
 	int ipte_lock_count;
 	struct mutex ipte_mutex;
 	spinlock_t start_stop_lock;
+	struct kvm_s390_cpu_model model;
 	struct kvm_s390_crypto crypto;
+	u64 epoch;
 };
 
 #define KVM_HVA_ERR_BAD		(-1UL)

arch/s390/include/asm/sclp.h

@@ -31,7 +31,8 @@ struct sclp_cpu_entry {
 	u8 reserved0[2];
 	u8 : 3;
 	u8 siif : 1;
-	u8 : 4;
+	u8 sigpif : 1;
+	u8 : 3;
 	u8 reserved2[10];
 	u8 type;
 	u8 reserved1;
@@ -69,6 +70,7 @@ int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode);
 unsigned long sclp_get_hsa_size(void);
 void sclp_early_detect(void);
 int sclp_has_siif(void);
+int sclp_has_sigpif(void);
 unsigned int sclp_get_ibc(void);
 
 long _sclp_print_early(const char *);

arch/s390/include/asm/sysinfo.h

@@ -15,6 +15,7 @@
 #define __ASM_S390_SYSINFO_H
 
 #include <asm/bitsperlong.h>
+#include <linux/uuid.h>
 
 struct sysinfo_1_1_1 {
 	unsigned char p:1;
@@ -116,10 +117,13 @@ struct sysinfo_3_2_2 {
 		char name[8];
 		unsigned int caf;
 		char cpi[16];
-		char reserved_1[24];
-
+		char reserved_1[3];
+		char ext_name_encoding;
+		unsigned int reserved_2;
+		uuid_be uuid;
 	} vm[8];
-	char reserved_544[3552];
+	char reserved_3[1504];
+	char ext_names[8][256];
 };
 
 extern int topology_max_mnest;

arch/s390/include/uapi/asm/kvm.h

@@ -57,10 +57,44 @@ struct kvm_s390_io_adapter_req {
 
 /* kvm attr_group  on vm fd */
 #define KVM_S390_VM_MEM_CTRL		0
+#define KVM_S390_VM_TOD			1
+#define KVM_S390_VM_CRYPTO		2
+#define KVM_S390_VM_CPU_MODEL		3
 
 /* kvm attributes for mem_ctrl */
 #define KVM_S390_VM_MEM_ENABLE_CMMA	0
 #define KVM_S390_VM_MEM_CLR_CMMA	1
+#define KVM_S390_VM_MEM_LIMIT_SIZE	2
+
+/* kvm attributes for KVM_S390_VM_TOD */
+#define KVM_S390_VM_TOD_LOW		0
+#define KVM_S390_VM_TOD_HIGH		1
+
+/* kvm attributes for KVM_S390_VM_CPU_MODEL */
+/* processor related attributes are r/w */
+#define KVM_S390_VM_CPU_PROCESSOR	0
+struct kvm_s390_vm_cpu_processor {
+	__u64 cpuid;
+	__u16 ibc;
+	__u8  pad[6];
+	__u64 fac_list[256];
+};
+
+/* machine related attributes are r/o */
+#define KVM_S390_VM_CPU_MACHINE		1
+struct kvm_s390_vm_cpu_machine {
+	__u64 cpuid;
+	__u32 ibc;
+	__u8  pad[4];
+	__u64 fac_mask[256];
+	__u64 fac_list[256];
+};
+
+/* kvm attributes for crypto */
+#define KVM_S390_VM_CRYPTO_ENABLE_AES_KW	0
+#define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW	1
+#define KVM_S390_VM_CRYPTO_DISABLE_AES_KW	2
+#define KVM_S390_VM_CRYPTO_DISABLE_DEA_KW	3
 
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
@@ -107,6 +141,9 @@ struct kvm_guest_debug_arch {
 	struct kvm_hw_breakpoint __user *hw_bp;
 };
 
+/* for KVM_SYNC_PFAULT and KVM_REG_S390_PFTOKEN */
+#define KVM_S390_PFAULT_TOKEN_INVALID	0xffffffffffffffffULL
+
 #define KVM_SYNC_PREFIX (1UL << 0)
 #define KVM_SYNC_GPRS   (1UL << 1)
 #define KVM_SYNC_ACRS   (1UL << 2)

arch/s390/kernel/sysinfo.c

@@ -204,6 +204,33 @@ static void stsi_2_2_2(struct seq_file *m, struct sysinfo_2_2_2 *info)
 	}
 }
 
+static void print_ext_name(struct seq_file *m, int lvl,
+			   struct sysinfo_3_2_2 *info)
+{
+	if (info->vm[lvl].ext_name_encoding == 0)
+		return;
+	if (info->ext_names[lvl][0] == 0)
+		return;
+	switch (info->vm[lvl].ext_name_encoding) {
+	case 1: /* EBCDIC */
+		EBCASC(info->ext_names[lvl], sizeof(info->ext_names[lvl]));
+		break;
+	case 2:	/* UTF-8 */
+		break;
+	default:
+		return;
+	}
+	seq_printf(m, "VM%02d Extended Name:   %-.256s\n", lvl,
+		   info->ext_names[lvl]);
+}
+
+static void print_uuid(struct seq_file *m, int i, struct sysinfo_3_2_2 *info)
+{
+	if (!memcmp(&info->vm[i].uuid, &NULL_UUID_BE, sizeof(uuid_be)))
+		return;
+	seq_printf(m, "VM%02d UUID:            %pUb\n", i, &info->vm[i].uuid);
+}
+
 static void stsi_3_2_2(struct seq_file *m, struct sysinfo_3_2_2 *info)
 {
 	int i;
@@ -221,6 +248,8 @@ static void stsi_3_2_2(struct seq_file *m, struct sysinfo_3_2_2 *info)
 		seq_printf(m, "VM%02d CPUs Configured: %d\n", i, info->vm[i].cpus_configured);
 		seq_printf(m, "VM%02d CPUs Standby:    %d\n", i, info->vm[i].cpus_standby);
 		seq_printf(m, "VM%02d CPUs Reserved:   %d\n", i, info->vm[i].cpus_reserved);
+		print_ext_name(m, i, info);
+		print_uuid(m, i, info);
 	}
 }
 

arch/s390/kvm/gaccess.c

@@ -357,8 +357,8 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
 	union asce asce;
 
 	ctlreg0.val = vcpu->arch.sie_block->gcr[0];
-	edat1 = ctlreg0.edat && test_vfacility(8);
-	edat2 = edat1 && test_vfacility(78);
+	edat1 = ctlreg0.edat && test_kvm_facility(vcpu->kvm, 8);
+	edat2 = edat1 && test_kvm_facility(vcpu->kvm, 78);
 	asce.val = get_vcpu_asce(vcpu);
 	if (asce.r)
 		goto real_address;

arch/s390/kvm/intercept.c

@@ -68,18 +68,27 @@ static int handle_noop(struct kvm_vcpu *vcpu)
 
 static int handle_stop(struct kvm_vcpu *vcpu)
 {
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	int rc = 0;
-	unsigned int action_bits;
+	uint8_t flags, stop_pending;
 
 	vcpu->stat.exit_stop_request++;
-	trace_kvm_s390_stop_request(vcpu->arch.local_int.action_bits);
 
-	action_bits = vcpu->arch.local_int.action_bits;
+	/* delay the stop if any non-stop irq is pending */
+	if (kvm_s390_vcpu_has_irq(vcpu, 1))
+		return 0;
+
+	/* avoid races with the injection/SIGP STOP code */
+	spin_lock(&li->lock);
+	flags = li->irq.stop.flags;
+	stop_pending = kvm_s390_is_stop_irq_pending(vcpu);
+	spin_unlock(&li->lock);
 
-	if (!(action_bits & ACTION_STOP_ON_STOP))
+	trace_kvm_s390_stop_request(stop_pending, flags);
+	if (!stop_pending)
 		return 0;
 
-	if (action_bits & ACTION_STORE_ON_STOP) {
+	if (flags & KVM_S390_STOP_FLAG_STORE_STATUS) {
 		rc = kvm_s390_vcpu_store_status(vcpu,
 						KVM_S390_STORE_STATUS_NOADDR);
 		if (rc)
@@ -279,11 +288,13 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu)
 		irq.type = KVM_S390_INT_CPU_TIMER;
 		break;
 	case EXT_IRQ_EXTERNAL_CALL:
-		if (kvm_s390_si_ext_call_pending(vcpu))
-			return 0;
 		irq.type = KVM_S390_INT_EXTERNAL_CALL;
 		irq.u.extcall.code = vcpu->arch.sie_block->extcpuaddr;
-		break;
+		rc = kvm_s390_inject_vcpu(vcpu, &irq);
+		/* ignore if another external call is already pending */
+		if (rc == -EBUSY)
+			return 0;
+		return rc;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -307,17 +318,19 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
 
 	/* Make sure that the source is paged-in */
-	srcaddr = kvm_s390_real_to_abs(vcpu, vcpu->run->s.regs.gprs[reg2]);
-	if (kvm_is_error_gpa(vcpu->kvm, srcaddr))
-		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg2],
+				     &srcaddr, 0);
+	if (rc)
+		return kvm_s390_inject_prog_cond(vcpu, rc);
 	rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0);
 	if (rc != 0)
 		return rc;
 
 	/* Make sure that the destination is paged-in */
-	dstaddr = kvm_s390_real_to_abs(vcpu, vcpu->run->s.regs.gprs[reg1]);
-	if (kvm_is_error_gpa(vcpu->kvm, dstaddr))
-		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg1],
+				     &dstaddr, 1);
+	if (rc)
+		return kvm_s390_inject_prog_cond(vcpu, rc);
 	rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1);
 	if (rc != 0)
 		return rc;

arch/s390/kvm/kvm-s390.h

@@ -18,12 +18,10 @@
 #include <linux/hrtimer.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
+#include <asm/facility.h>
 
 typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
 
-/* declare vfacilities extern */
-extern unsigned long *vfacilities;
-
 /* Transactional Memory Execution related macros */
 #define IS_TE_ENABLED(vcpu)	((vcpu->arch.sie_block->ecb & 0x10))
 #define TDB_FORMAT1		1
@@ -127,6 +125,12 @@ static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc)
 	vcpu->arch.sie_block->gpsw.mask |= cc << 44;
 }
 
+/* test availability of facility in a kvm intance */
+static inline int test_kvm_facility(struct kvm *kvm, unsigned long nr)
+{
+	return __test_facility(nr, kvm->arch.model.fac->kvm);
+}
+
 /* are cpu states controlled by user space */
 static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm)
 {
@@ -183,7 +187,8 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
 /* is cmma enabled */
 bool kvm_s390_cmma_enabled(struct kvm *kvm);
-int test_vfacility(unsigned long nr);
+unsigned long kvm_s390_fac_list_mask_size(void);
+extern unsigned long kvm_s390_fac_list_mask[];
 
 /* implemented in diag.c */
 int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
@@ -228,11 +233,13 @@ int s390int_to_s390irq(struct kvm_s390_interrupt *s390int,
 			struct kvm_s390_irq *s390irq);
 
 /* implemented in interrupt.c */
-int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
+int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop);
 int psw_extint_disabled(struct kvm_vcpu *vcpu);
 void kvm_s390_destroy_adapters(struct kvm *kvm);
-int kvm_s390_si_ext_call_pending(struct kvm_vcpu *vcpu);
+int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu);
 extern struct kvm_device_ops kvm_flic_ops;
+int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu);
+void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu);
 
 /* implemented in guestdbg.c */
 void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu);

arch/s390/kvm/priv.c

@@ -337,19 +337,24 @@ static int handle_io_inst(struct kvm_vcpu *vcpu)
 static int handle_stfl(struct kvm_vcpu *vcpu)
 {
 	int rc;
+	unsigned int fac;
 
 	vcpu->stat.instruction_stfl++;
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
+	/*
+	 * We need to shift the lower 32 facility bits (bit 0-31) from a u64
+	 * into a u32 memory representation. They will remain bits 0-31.
+	 */
+	fac = *vcpu->kvm->arch.model.fac->sie >> 32;
 	rc = write_guest_lc(vcpu, offsetof(struct _lowcore, stfl_fac_list),
-			    vfacilities, 4);
+			    &fac, sizeof(fac));
 	if (rc)
 		return rc;
-	VCPU_EVENT(vcpu, 5, "store facility list value %x",
-		   *(unsigned int *) vfacilities);
-	trace_kvm_s390_handle_stfl(vcpu, *(unsigned int *) vfacilities);
+	VCPU_EVENT(vcpu, 5, "store facility list value %x", fac);
+	trace_kvm_s390_handle_stfl(vcpu, fac);
 	return 0;
 }
 

arch/s390/kvm/sigp.c

@@ -26,15 +26,17 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu,
 	struct kvm_s390_local_interrupt *li;
 	int cpuflags;
 	int rc;
+	int ext_call_pending;
 
 	li = &dst_vcpu->arch.local_int;
 
 	cpuflags = atomic_read(li->cpuflags);
-	if (!(cpuflags & (CPUSTAT_ECALL_PEND | CPUSTAT_STOPPED)))
+	ext_call_pending = kvm_s390_ext_call_pending(dst_vcpu);
+	if (!(cpuflags & CPUSTAT_STOPPED) && !ext_call_pending)
 		rc = SIGP_CC_ORDER_CODE_ACCEPTED;
 	else {
 		*reg &= 0xffffffff00000000UL;
-		if (cpuflags & CPUSTAT_ECALL_PEND)
+		if (ext_call_pending)
 			*reg |= SIGP_STATUS_EXT_CALL_PENDING;
 		if (cpuflags & CPUSTAT_STOPPED)
 			*reg |= SIGP_STATUS_STOPPED;
@@ -96,7 +98,7 @@ static int __sigp_conditional_emergency(struct kvm_vcpu *vcpu,
 }
 
 static int __sigp_external_call(struct kvm_vcpu *vcpu,
-				struct kvm_vcpu *dst_vcpu)
+				struct kvm_vcpu *dst_vcpu, u64 *reg)
 {
 	struct kvm_s390_irq irq = {
 		.type = KVM_S390_INT_EXTERNAL_CALL,
@@ -105,45 +107,31 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu,
 	int rc;
 
 	rc = kvm_s390_inject_vcpu(dst_vcpu, &irq);
-	if (!rc)
+	if (rc == -EBUSY) {
+		*reg &= 0xffffffff00000000UL;
+		*reg |= SIGP_STATUS_EXT_CALL_PENDING;
+		return SIGP_CC_STATUS_STORED;
+	} else if (rc == 0) {
 		VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x",
 			   dst_vcpu->vcpu_id);
-
-	return rc ? rc : SIGP_CC_ORDER_CODE_ACCEPTED;
-}
-
-static int __inject_sigp_stop(struct kvm_vcpu *dst_vcpu, int action)
-{
-	struct kvm_s390_local_interrupt *li = &dst_vcpu->arch.local_int;
-	int rc = SIGP_CC_ORDER_CODE_ACCEPTED;
-
-	spin_lock(&li->lock);
-	if (li->action_bits & ACTION_STOP_ON_STOP) {
-		/* another SIGP STOP is pending */
-		rc = SIGP_CC_BUSY;
-		goto out;
-	}
-	if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
-		if ((action & ACTION_STORE_ON_STOP) != 0)
-			rc = -ESHUTDOWN;
-		goto out;
 	}
-	set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs);
-	li->action_bits |= action;
-	atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
-	kvm_s390_vcpu_wakeup(dst_vcpu);
-out:
-	spin_unlock(&li->lock);
 
-	return rc;
+	return rc ? rc : SIGP_CC_ORDER_CODE_ACCEPTED;
 }
 
 static int __sigp_stop(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu)
 {
+	struct kvm_s390_irq irq = {
+		.type = KVM_S390_SIGP_STOP,
+	};
 	int rc;
 
-	rc = __inject_sigp_stop(dst_vcpu, ACTION_STOP_ON_STOP);
-	VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", dst_vcpu->vcpu_id);
+	rc = kvm_s390_inject_vcpu(dst_vcpu, &irq);
+	if (rc == -EBUSY)
+		rc = SIGP_CC_BUSY;
+	else if (rc == 0)
+		VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x",
+			   dst_vcpu->vcpu_id);
 
 	return rc;
 }
@@ -151,21 +139,19 @@ static int __sigp_stop(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu)
 static int __sigp_stop_and_store_status(struct kvm_vcpu *vcpu,
 					struct kvm_vcpu *dst_vcpu, u64 *reg)
 {
+	struct kvm_s390_irq irq = {
+		.type = KVM_S390_SIGP_STOP,
+		.u.stop.flags = KVM_S390_STOP_FLAG_STORE_STATUS,
+	};
 	int rc;
 
-	rc = __inject_sigp_stop(dst_vcpu, ACTION_STOP_ON_STOP |
-					      ACTION_STORE_ON_STOP);
+	rc = kvm_s390_inject_vcpu(dst_vcpu, &irq);
+	if (rc == -EBUSY)
+		rc = SIGP_CC_BUSY;
+	else if (rc == 0)
 		VCPU_EVENT(vcpu, 4, "sent sigp stop and store status to cpu %x",
 			   dst_vcpu->vcpu_id);
 
-	if (rc == -ESHUTDOWN) {
-		/* If the CPU has already been stopped, we still have
-		 * to save the status when doing stop-and-store. This
-		 * has to be done after unlocking all spinlocks. */
-		rc = kvm_s390_store_status_unloaded(dst_vcpu,
-						KVM_S390_STORE_STATUS_NOADDR);
-	}
-
 	return rc;
 }
 
@@ -197,41 +183,33 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
 static int __sigp_set_prefix(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu,
 			     u32 address, u64 *reg)
 {
-	struct kvm_s390_local_interrupt *li;
+	struct kvm_s390_irq irq = {
+		.type = KVM_S390_SIGP_SET_PREFIX,
+		.u.prefix.address = address & 0x7fffe000u,
+	};
 	int rc;
 
-	li = &dst_vcpu->arch.local_int;
-
 	/*
 	 * Make sure the new value is valid memory. We only need to check the
 	 * first page, since address is 8k aligned and memory pieces are always
 	 * at least 1MB aligned and have at least a size of 1MB.
 	 */
-	address &= 0x7fffe000u;
-	if (kvm_is_error_gpa(vcpu->kvm, address)) {
+	if (kvm_is_error_gpa(vcpu->kvm, irq.u.prefix.address)) {
 		*reg &= 0xffffffff00000000UL;
 		*reg |= SIGP_STATUS_INVALID_PARAMETER;
 		return SIGP_CC_STATUS_STORED;
 	}
 
-	spin_lock(&li->lock);
-	/* cpu must be in stopped state */
-	if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
+	rc = kvm_s390_inject_vcpu(dst_vcpu, &irq);
+	if (rc == -EBUSY) {
 		*reg &= 0xffffffff00000000UL;
 		*reg |= SIGP_STATUS_INCORRECT_STATE;
-		rc = SIGP_CC_STATUS_STORED;
-		goto out_li;
+		return SIGP_CC_STATUS_STORED;
+	} else if (rc == 0) {
+		VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x",
+			   dst_vcpu->vcpu_id, irq.u.prefix.address);
 	}
 
-	li->irq.prefix.address = address;
-	set_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs);
-	kvm_s390_vcpu_wakeup(dst_vcpu);
-	rc = SIGP_CC_ORDER_CODE_ACCEPTED;
-
-	VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", dst_vcpu->vcpu_id,
-		   address);
-out_li:
-	spin_unlock(&li->lock);
 	return rc;
 }
 
@@ -242,9 +220,7 @@ static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu,
 	int flags;
 	int rc;
 
-	spin_lock(&dst_vcpu->arch.local_int.lock);
 	flags = atomic_read(dst_vcpu->arch.local_int.cpuflags);
-	spin_unlock(&dst_vcpu->arch.local_int.lock);
 	if (!(flags & CPUSTAT_STOPPED)) {
 		*reg &= 0xffffffff00000000UL;
 		*reg |= SIGP_STATUS_INCORRECT_STATE;
@@ -291,8 +267,9 @@ static int __prepare_sigp_re_start(struct kvm_vcpu *vcpu,
 	/* handle (RE)START in user space */
 	int rc = -EOPNOTSUPP;
 
+	/* make sure we don't race with STOP irq injection */
 	spin_lock(&li->lock);
-	if (li->action_bits & ACTION_STOP_ON_STOP)
+	if (kvm_s390_is_stop_irq_pending(dst_vcpu))
 		rc = SIGP_CC_BUSY;
 	spin_unlock(&li->lock);
 
@@ -333,7 +310,7 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code,
 		break;
 	case SIGP_EXTERNAL_CALL:
 		vcpu->stat.instruction_sigp_external_call++;
-		rc = __sigp_external_call(vcpu, dst_vcpu);
+		rc = __sigp_external_call(vcpu, dst_vcpu, status_reg);
 		break;
 	case SIGP_EMERGENCY_SIGNAL:
 		vcpu->stat.instruction_sigp_emergency++;
@@ -394,6 +371,53 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code,
 	return rc;
 }
 
+static int handle_sigp_order_in_user_space(struct kvm_vcpu *vcpu, u8 order_code)
+{
+	if (!vcpu->kvm->arch.user_sigp)
+		return 0;
+
+	switch (order_code) {
+	case SIGP_SENSE:
+	case SIGP_EXTERNAL_CALL:
+	case SIGP_EMERGENCY_SIGNAL:
+	case SIGP_COND_EMERGENCY_SIGNAL:
+	case SIGP_SENSE_RUNNING:
+		return 0;
+	/* update counters as we're directly dropping to user space */
+	case SIGP_STOP:
+		vcpu->stat.instruction_sigp_stop++;
+		break;
+	case SIGP_STOP_AND_STORE_STATUS:
+		vcpu->stat.instruction_sigp_stop_store_status++;
+		break;
+	case SIGP_STORE_STATUS_AT_ADDRESS:
+		vcpu->stat.instruction_sigp_store_status++;
+		break;
+	case SIGP_SET_PREFIX:
+		vcpu->stat.instruction_sigp_prefix++;
+		break;
+	case SIGP_START:
+		vcpu->stat.instruction_sigp_start++;
+		break;
+	case SIGP_RESTART:
+		vcpu->stat.instruction_sigp_restart++;
+		break;
+	case SIGP_INITIAL_CPU_RESET:
+		vcpu->stat.instruction_sigp_init_cpu_reset++;
+		break;
+	case SIGP_CPU_RESET:
+		vcpu->stat.instruction_sigp_cpu_reset++;
+		break;
+	default:
+		vcpu->stat.instruction_sigp_unknown++;
+	}
+
+	VCPU_EVENT(vcpu, 4, "sigp order %u: completely handled in user space",
+		   order_code);
+
+	return 1;
+}
+
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 {
 	int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
@@ -408,6 +432,8 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
 	order_code = kvm_s390_get_base_disp_rs(vcpu);
+	if (handle_sigp_order_in_user_space(vcpu, order_code))
+		return -EOPNOTSUPP;
 
 	if (r1 % 2)
 		parameter = vcpu->run->s.regs.gprs[r1];

arch/s390/kvm/trace-s390.h

@@ -209,19 +209,21 @@ TRACE_EVENT(kvm_s390_request_resets,
  * Trace point for a vcpu's stop requests.
  */
 TRACE_EVENT(kvm_s390_stop_request,
-	    TP_PROTO(unsigned int action_bits),
-	    TP_ARGS(action_bits),
+	    TP_PROTO(unsigned char stop_irq, unsigned char flags),
+	    TP_ARGS(stop_irq, flags),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int, action_bits)
+		    __field(unsigned char, stop_irq)
+		    __field(unsigned char, flags)
 		    ),
 
 	    TP_fast_assign(
-		    __entry->action_bits = action_bits;
+		    __entry->stop_irq = stop_irq;
+		    __entry->flags = flags;
 		    ),
 
-	    TP_printk("stop request, action_bits = %08x",
-		      __entry->action_bits)
+	    TP_printk("stop request, stop irq = %u, flags = %08x",
+		      __entry->stop_irq, __entry->flags)
 	);
 
 

arch/x86/include/asm/kvm_emulate.h

@@ -208,6 +208,7 @@ struct x86_emulate_ops {
 
 	void (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
 			  u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
+	void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
 };
 
 typedef u32 __attribute__((vector_size(16))) sse128_t;

arch/x86/include/asm/kvm_host.h

@@ -38,8 +38,6 @@
 #define KVM_PRIVATE_MEM_SLOTS 3
 #define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)
 
-#define KVM_MMIO_SIZE 16
-
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
 
@@ -51,7 +49,7 @@
 			  | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
 
 #define CR3_L_MODE_RESERVED_BITS 0xFFFFFF0000000000ULL
-#define CR3_PCID_INVD		 (1UL << 63)
+#define CR3_PCID_INVD		 BIT_64(63)
 #define CR4_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
 			  | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE     \
@@ -160,6 +158,18 @@ enum {
 #define DR7_FIXED_1	0x00000400
 #define DR7_VOLATILE	0xffff2bff
 
+#define PFERR_PRESENT_BIT 0
+#define PFERR_WRITE_BIT 1
+#define PFERR_USER_BIT 2
+#define PFERR_RSVD_BIT 3
+#define PFERR_FETCH_BIT 4
+
+#define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT)
+#define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT)
+#define PFERR_USER_MASK (1U << PFERR_USER_BIT)
+#define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT)
+#define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT)
+
 /* apic attention bits */
 #define KVM_APIC_CHECK_VAPIC	0
 /*
@@ -615,6 +625,8 @@ struct kvm_arch {
 	#ifdef CONFIG_KVM_MMU_AUDIT
 	int audit_point;
 	#endif
+
+	bool boot_vcpu_runs_old_kvmclock;
 };
 
 struct kvm_vm_stat {
@@ -643,6 +655,7 @@ struct kvm_vcpu_stat {
 	u32 irq_window_exits;
 	u32 nmi_window_exits;
 	u32 halt_exits;
+	u32 halt_successful_poll;
 	u32 halt_wakeup;
 	u32 request_irq_exits;
 	u32 irq_exits;
@@ -787,6 +800,31 @@ struct kvm_x86_ops {
 	int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
 
 	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.
+	 */
+	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);
 };
 
 struct kvm_arch_async_pf {
@@ -819,8 +857,15 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 		u64 dirty_mask, u64 nx_mask, u64 x_mask);
 
 void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
-void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
-void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
+void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
+				      struct kvm_memory_slot *memslot);
+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);

arch/x86/include/asm/vmx.h

@@ -69,6 +69,7 @@
 #define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
 #define SECONDARY_EXEC_ENABLE_INVPCID		0x00001000
 #define SECONDARY_EXEC_SHADOW_VMCS              0x00004000
+#define SECONDARY_EXEC_ENABLE_PML               0x00020000
 #define SECONDARY_EXEC_XSAVES			0x00100000
 
 
@@ -121,6 +122,7 @@ enum vmcs_field {
 	GUEST_LDTR_SELECTOR             = 0x0000080c,
 	GUEST_TR_SELECTOR               = 0x0000080e,
 	GUEST_INTR_STATUS               = 0x00000810,
+	GUEST_PML_INDEX			= 0x00000812,
 	HOST_ES_SELECTOR                = 0x00000c00,
 	HOST_CS_SELECTOR                = 0x00000c02,
 	HOST_SS_SELECTOR                = 0x00000c04,
@@ -140,6 +142,8 @@ enum vmcs_field {
 	VM_EXIT_MSR_LOAD_ADDR_HIGH      = 0x00002009,
 	VM_ENTRY_MSR_LOAD_ADDR          = 0x0000200a,
 	VM_ENTRY_MSR_LOAD_ADDR_HIGH     = 0x0000200b,
+	PML_ADDRESS			= 0x0000200e,
+	PML_ADDRESS_HIGH		= 0x0000200f,
 	TSC_OFFSET                      = 0x00002010,
 	TSC_OFFSET_HIGH                 = 0x00002011,
 	VIRTUAL_APIC_PAGE_ADDR          = 0x00002012,

arch/x86/include/uapi/asm/msr-index.h

@@ -364,6 +364,9 @@
 #define MSR_IA32_UCODE_WRITE		0x00000079
 #define MSR_IA32_UCODE_REV		0x0000008b
 
+#define MSR_IA32_SMM_MONITOR_CTL	0x0000009b
+#define MSR_IA32_SMBASE			0x0000009e
+
 #define MSR_IA32_PERF_STATUS		0x00000198
 #define MSR_IA32_PERF_CTL		0x00000199
 #define INTEL_PERF_CTL_MASK		0xffff

arch/x86/include/uapi/asm/vmx.h

@@ -56,6 +56,7 @@
 #define EXIT_REASON_MSR_READ            31
 #define EXIT_REASON_MSR_WRITE           32
 #define EXIT_REASON_INVALID_STATE       33
+#define EXIT_REASON_MSR_LOAD_FAIL       34
 #define EXIT_REASON_MWAIT_INSTRUCTION   36
 #define EXIT_REASON_MONITOR_INSTRUCTION 39
 #define EXIT_REASON_PAUSE_INSTRUCTION   40
@@ -72,6 +73,7 @@
 #define EXIT_REASON_XSETBV              55
 #define EXIT_REASON_APIC_WRITE          56
 #define EXIT_REASON_INVPCID             58
+#define EXIT_REASON_PML_FULL            62
 #define EXIT_REASON_XSAVES              63
 #define EXIT_REASON_XRSTORS             64
 
@@ -116,10 +118,14 @@
 	{ EXIT_REASON_APIC_WRITE,            "APIC_WRITE" }, \
 	{ EXIT_REASON_EOI_INDUCED,           "EOI_INDUCED" }, \
 	{ EXIT_REASON_INVALID_STATE,         "INVALID_STATE" }, \
+	{ EXIT_REASON_MSR_LOAD_FAIL,         "MSR_LOAD_FAIL" }, \
 	{ EXIT_REASON_INVD,                  "INVD" }, \
 	{ EXIT_REASON_INVVPID,               "INVVPID" }, \
 	{ EXIT_REASON_INVPCID,               "INVPCID" }, \
 	{ EXIT_REASON_XSAVES,                "XSAVES" }, \
 	{ EXIT_REASON_XRSTORS,               "XRSTORS" }
 
+#define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
+#define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
+
 #endif /* _UAPIVMX_H */

arch/x86/kvm/Kconfig

@@ -39,6 +39,7 @@ config KVM
 	select PERF_EVENTS
 	select HAVE_KVM_MSI
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
+	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_VFIO
 	select SRCU
 	---help---

arch/x86/kvm/ioapic.h

@@ -98,7 +98,7 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm)
 }
 
 void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu);
-int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
+bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 		int short_hand, unsigned int dest, int dest_mode);
 int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
 void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector,

arch/x86/kvm/iommu.c

@@ -138,7 +138,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 
 		gfn += page_size >> PAGE_SHIFT;
 
-
+		cond_resched();
 	}
 
 	return 0;
@@ -306,6 +306,8 @@ static void kvm_iommu_put_pages(struct kvm *kvm,
 		kvm_unpin_pages(kvm, pfn, unmap_pages);
 
 		gfn += unmap_pages;
+
+		cond_resched();
 	}
 }
 

arch/x86/kvm/lapic.c

@@ -33,6 +33,7 @@
 #include <asm/page.h>
 #include <asm/current.h>
 #include <asm/apicdef.h>
+#include <asm/delay.h>
 #include <linux/atomic.h>
 #include <linux/jump_label.h>
 #include "kvm_cache_regs.h"
@@ -327,17 +328,24 @@ static u8 count_vectors(void *bitmap)
 	return count;
 }
 
-void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir)
+void __kvm_apic_update_irr(u32 *pir, void *regs)
 {
 	u32 i, pir_val;
-	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	for (i = 0; i <= 7; i++) {
 		pir_val = xchg(&pir[i], 0);
 		if (pir_val)
-			*((u32 *)(apic->regs + APIC_IRR + i * 0x10)) |= pir_val;
+			*((u32 *)(regs + APIC_IRR + i * 0x10)) |= pir_val;
 	}
 }
+EXPORT_SYMBOL_GPL(__kvm_apic_update_irr);
+
+void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	__kvm_apic_update_irr(pir, apic->regs);
+}
 EXPORT_SYMBOL_GPL(kvm_apic_update_irr);
 
 static inline void apic_set_irr(int vec, struct kvm_lapic *apic)
@@ -405,7 +413,7 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
 	 * because the processor can modify ISR under the hood.  Instead
 	 * just set SVI.
 	 */
-	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+	if (unlikely(kvm_x86_ops->hwapic_isr_update))
 		kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec);
 	else {
 		++apic->isr_count;
@@ -453,7 +461,7 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
 	 * on the other hand isr_count and highest_isr_cache are unused
 	 * and must be left alone.
 	 */
-	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+	if (unlikely(kvm_x86_ops->hwapic_isr_update))
 		kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
 					       apic_find_highest_isr(apic));
 	else {
@@ -580,55 +588,48 @@ static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr)
 	apic_update_ppr(apic);
 }
 
-static int kvm_apic_broadcast(struct kvm_lapic *apic, u32 dest)
+static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 dest)
 {
 	return dest == (apic_x2apic_mode(apic) ?
 			X2APIC_BROADCAST : APIC_BROADCAST);
 }
 
-int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 dest)
+static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 dest)
 {
 	return kvm_apic_id(apic) == dest || kvm_apic_broadcast(apic, dest);
 }
 
-int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda)
+static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda)
 {
-	int result = 0;
 	u32 logical_id;
 
 	if (kvm_apic_broadcast(apic, mda))
-		return 1;
+		return true;
 
-	if (apic_x2apic_mode(apic)) {
 	logical_id = kvm_apic_get_reg(apic, APIC_LDR);
-		return logical_id & mda;
-	}
 
-	logical_id = GET_APIC_LOGICAL_ID(kvm_apic_get_reg(apic, APIC_LDR));
+	if (apic_x2apic_mode(apic))
+		return ((logical_id >> 16) == (mda >> 16))
+		       && (logical_id & mda & 0xffff) != 0;
+
+	logical_id = GET_APIC_LOGICAL_ID(logical_id);
 
 	switch (kvm_apic_get_reg(apic, APIC_DFR)) {
 	case APIC_DFR_FLAT:
-		if (logical_id & mda)
-			result = 1;
-		break;
+		return (logical_id & mda) != 0;
 	case APIC_DFR_CLUSTER:
-		if (((logical_id >> 4) == (mda >> 0x4))
-		    && (logical_id & mda & 0xf))
-			result = 1;
-		break;
+		return ((logical_id >> 4) == (mda >> 4))
+		       && (logical_id & mda & 0xf) != 0;
 	default:
 		apic_debug("Bad DFR vcpu %d: %08x\n",
 			   apic->vcpu->vcpu_id, kvm_apic_get_reg(apic, APIC_DFR));
-		break;
+		return false;
 	}
-
-	return result;
 }
 
-int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
+bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 			   int short_hand, unsigned int dest, int dest_mode)
 {
-	int result = 0;
 	struct kvm_lapic *target = vcpu->arch.apic;
 
 	apic_debug("target %p, source %p, dest 0x%x, "
@@ -638,29 +639,21 @@ int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 	ASSERT(target);
 	switch (short_hand) {
 	case APIC_DEST_NOSHORT:
-		if (dest_mode == 0)
-			/* Physical mode. */
-			result = kvm_apic_match_physical_addr(target, dest);
+		if (dest_mode == APIC_DEST_PHYSICAL)
+			return kvm_apic_match_physical_addr(target, dest);
 		else
-			/* Logical mode. */
-			result = kvm_apic_match_logical_addr(target, dest);
-		break;
+			return kvm_apic_match_logical_addr(target, dest);
 	case APIC_DEST_SELF:
-		result = (target == source);
-		break;
+		return target == source;
 	case APIC_DEST_ALLINC:
-		result = 1;
-		break;
+		return true;
 	case APIC_DEST_ALLBUT:
-		result = (target != source);
-		break;
+		return target != source;
 	default:
 		apic_debug("kvm: apic: Bad dest shorthand value %x\n",
 			   short_hand);
-		break;
+		return false;
 	}
-
-	return result;
 }
 
 bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
@@ -693,7 +686,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 
 	ret = true;
 
-	if (irq->dest_mode == 0) { /* physical mode */
+	if (irq->dest_mode == APIC_DEST_PHYSICAL) {
 		if (irq->dest_id >= ARRAY_SIZE(map->phys_map))
 			goto out;
 
@@ -1076,25 +1069,72 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 {
 	struct kvm_vcpu *vcpu = apic->vcpu;
 	wait_queue_head_t *q = &vcpu->wq;
+	struct kvm_timer *ktimer = &apic->lapic_timer;
 
-	/*
-	 * Note: KVM_REQ_PENDING_TIMER is implicitly checked in
-	 * vcpu_enter_guest.
-	 */
 	if (atomic_read(&apic->lapic_timer.pending))
 		return;
 
 	atomic_inc(&apic->lapic_timer.pending);
-	/* FIXME: this code should not know anything about vcpus */
-	kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+	kvm_set_pending_timer(vcpu);
 
 	if (waitqueue_active(q))
 		wake_up_interruptible(q);
+
+	if (apic_lvtt_tscdeadline(apic))
+		ktimer->expired_tscdeadline = ktimer->tscdeadline;
+}
+
+/*
+ * On APICv, this test will cause a busy wait
+ * during a higher-priority task.
+ */
+
+static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+	u32 reg = kvm_apic_get_reg(apic, APIC_LVTT);
+
+	if (kvm_apic_hw_enabled(apic)) {
+		int vec = reg & APIC_VECTOR_MASK;
+		void *bitmap = apic->regs + APIC_ISR;
+
+		if (kvm_x86_ops->deliver_posted_interrupt)
+			bitmap = apic->regs + APIC_IRR;
+
+		if (apic_test_vector(vec, bitmap))
+			return true;
+	}
+	return false;
+}
+
+void wait_lapic_expire(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+	u64 guest_tsc, tsc_deadline;
+
+	if (!kvm_vcpu_has_lapic(vcpu))
+		return;
+
+	if (apic->lapic_timer.expired_tscdeadline == 0)
+		return;
+
+	if (!lapic_timer_int_injected(vcpu))
+		return;
+
+	tsc_deadline = apic->lapic_timer.expired_tscdeadline;
+	apic->lapic_timer.expired_tscdeadline = 0;
+	guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc());
+	trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline);
+
+	/* __delay is delay_tsc whenever the hardware has TSC, thus always.  */
+	if (guest_tsc < tsc_deadline)
+		__delay(tsc_deadline - guest_tsc);
 }
 
 static void start_apic_timer(struct kvm_lapic *apic)
 {
 	ktime_t now;
+
 	atomic_set(&apic->lapic_timer.pending, 0);
 
 	if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) {
@@ -1140,6 +1180,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 		/* lapic timer in tsc deadline mode */
 		u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline;
 		u64 ns = 0;
+		ktime_t expire;
 		struct kvm_vcpu *vcpu = apic->vcpu;
 		unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz;
 		unsigned long flags;
@@ -1154,8 +1195,10 @@ static void start_apic_timer(struct kvm_lapic *apic)
 		if (likely(tscdeadline > guest_tsc)) {
 			ns = (tscdeadline - guest_tsc) * 1000000ULL;
 			do_div(ns, this_tsc_khz);
+			expire = ktime_add_ns(now, ns);
+			expire = ktime_sub_ns(expire, lapic_timer_advance_ns);
 			hrtimer_start(&apic->lapic_timer.timer,
-				ktime_add_ns(now, ns), HRTIMER_MODE_ABS);
+				      expire, HRTIMER_MODE_ABS);
 		} else
 			apic_timer_expired(apic);
 
@@ -1745,7 +1788,9 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
 	if (kvm_x86_ops->hwapic_irr_update)
 		kvm_x86_ops->hwapic_irr_update(vcpu,
 				apic_find_highest_irr(apic));
-	kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic));
+	if (unlikely(kvm_x86_ops->hwapic_isr_update))
+		kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
+				apic_find_highest_isr(apic));
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 	kvm_rtc_eoi_tracking_restore_one(vcpu);
 }

arch/x86/kvm/lapic.h

@@ -14,6 +14,7 @@ struct kvm_timer {
 	u32 timer_mode;
 	u32 timer_mode_mask;
 	u64 tscdeadline;
+	u64 expired_tscdeadline;
 	atomic_t pending;			/* accumulated triggered timers */
 };
 
@@ -56,9 +57,8 @@ u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu);
 void kvm_apic_set_version(struct kvm_vcpu *vcpu);
 
 void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr);
+void __kvm_apic_update_irr(u32 *pir, void *regs);
 void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir);
-int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 dest);
-int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda);
 int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
 		unsigned long *dest_map);
 int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type);
@@ -170,4 +170,6 @@ static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu)
 
 bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
 
+void wait_lapic_expire(struct kvm_vcpu *vcpu);
+
 #endif

arch/x86/kvm/mmu.h

@@ -44,18 +44,6 @@
 #define PT_DIRECTORY_LEVEL 2
 #define PT_PAGE_TABLE_LEVEL 1
 
-#define PFERR_PRESENT_BIT 0
-#define PFERR_WRITE_BIT 1
-#define PFERR_USER_BIT 2
-#define PFERR_RSVD_BIT 3
-#define PFERR_FETCH_BIT 4
-
-#define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT)
-#define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT)
-#define PFERR_USER_MASK (1U << PFERR_USER_BIT)
-#define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT)
-#define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT)
-
 static inline u64 rsvd_bits(int s, int e)
 {
 	return ((1ULL << (e - s + 1)) - 1) << s;
@@ -81,9 +69,8 @@ enum {
 };
 
 int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
-void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
-void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
-		bool execonly);
+void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
+void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly);
 void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 		bool ept);
 

arch/x86/kvm/svm.c

@@ -2003,8 +2003,8 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
 
 static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
 {
-	kvm_init_shadow_mmu(vcpu, &vcpu->arch.mmu);
-
+	WARN_ON(mmu_is_nested(vcpu));
+	kvm_init_shadow_mmu(vcpu);
 	vcpu->arch.mmu.set_cr3           = nested_svm_set_tdp_cr3;
 	vcpu->arch.mmu.get_cr3           = nested_svm_get_tdp_cr3;
 	vcpu->arch.mmu.get_pdptr         = nested_svm_get_tdp_pdptr;

arch/x86/kvm/trace.h

@@ -848,6 +848,24 @@ TRACE_EVENT(kvm_track_tsc,
 
 #endif /* CONFIG_X86_64 */
 
+/*
+ * Tracepoint for PML full VMEXIT.
+ */
+TRACE_EVENT(kvm_pml_full,
+	TP_PROTO(unsigned int vcpu_id),
+	TP_ARGS(vcpu_id),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	vcpu_id			)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id		= vcpu_id;
+	),
+
+	TP_printk("vcpu %d: PML full", __entry->vcpu_id)
+);
+
 TRACE_EVENT(kvm_ple_window,
 	TP_PROTO(bool grow, unsigned int vcpu_id, int new, int old),
 	TP_ARGS(grow, vcpu_id, new, old),
@@ -914,6 +932,26 @@ TRACE_EVENT(kvm_pvclock_update,
 		  __entry->flags)
 );
 
+TRACE_EVENT(kvm_wait_lapic_expire,
+	TP_PROTO(unsigned int vcpu_id, s64 delta),
+	TP_ARGS(vcpu_id, delta),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	vcpu_id		)
+		__field(	s64,		delta		)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id	   = vcpu_id;
+		__entry->delta             = delta;
+	),
+
+	TP_printk("vcpu %u: delta %lld (%s)",
+		  __entry->vcpu_id,
+		  __entry->delta,
+		  __entry->delta < 0 ? "early" : "late")
+);
+
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH