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

Pull KVM updates from Paolo Bonzini:
 "Small release, the most interesting stuff is x86 nested virt
  improvements.

  x86:
   - userspace can now hide nested VMX features from guests
   - nested VMX can now run Hyper-V in a guest
   - support for AVX512_4VNNIW and AVX512_FMAPS in KVM
   - infrastructure support for virtual Intel GPUs.

  PPC:
   - support for KVM guests on POWER9
   - improved support for interrupt polling
   - optimizations and cleanups.

  s390:
   - two small optimizations, more stuff is in flight and will be in
     4.11.

  ARM:
   - support for the GICv3 ITS on 32bit platforms"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (94 commits)
  arm64: KVM: pmu: Reset PMSELR_EL0.SEL to a sane value before entering the guest
  KVM: arm/arm64: timer: Check for properly initialized timer on init
  KVM: arm/arm64: vgic-v2: Limit ITARGETSR bits to number of VCPUs
  KVM: x86: Handle the kthread worker using the new API
  KVM: nVMX: invvpid handling improvements
  KVM: nVMX: check host CR3 on vmentry and vmexit
  KVM: nVMX: introduce nested_vmx_load_cr3 and call it on vmentry
  KVM: nVMX: propagate errors from prepare_vmcs02
  KVM: nVMX: fix CR3 load if L2 uses PAE paging and EPT
  KVM: nVMX: load GUEST_EFER after GUEST_CR0 during emulated VM-entry
  KVM: nVMX: generate MSR_IA32_CR{0,4}_FIXED1 from guest CPUID
  KVM: nVMX: fix checks on CR{0,4} during virtual VMX operation
  KVM: nVMX: support restore of VMX capability MSRs
  KVM: nVMX: generate non-true VMX MSRs based on true versions
  KVM: x86: Do not clear RFLAGS.TF when a singlestep trap occurs.
  KVM: x86: Add kvm_skip_emulated_instruction and use it.
  KVM: VMX: Move skip_emulated_instruction out of nested_vmx_check_vmcs12
  KVM: VMX: Reorder some skip_emulated_instruction calls
  KVM: x86: Add a return value to kvm_emulate_cpuid
  KVM: PPC: Book3S: Move prototypes for KVM functions into kvm_ppc.h
  ...

Documentation/virtual/kvm/00-INDEX

@@ -6,6 +6,8 @@ cpuid.txt
 	- KVM-specific cpuid leaves (x86).
 devices/
 	- KVM_CAP_DEVICE_CTRL userspace API.
+halt-polling.txt
+	- notes on halt-polling
 hypercalls.txt
 	- KVM hypercalls.
 locking.txt

Documentation/virtual/kvm/api.txt

@@ -2034,6 +2034,8 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_WORT              | 64
   PPC	| KVM_REG_PPC_SPRG9             | 64
   PPC	| KVM_REG_PPC_DBSR              | 32
+  PPC   | KVM_REG_PPC_TIDR              | 64
+  PPC   | KVM_REG_PPC_PSSCR             | 64
   PPC   | KVM_REG_PPC_TM_GPR0           | 64
           ...
   PPC   | KVM_REG_PPC_TM_GPR31          | 64
@@ -2050,6 +2052,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_TM_VSCR           | 32
   PPC   | KVM_REG_PPC_TM_DSCR           | 64
   PPC   | KVM_REG_PPC_TM_TAR            | 64
+  PPC   | KVM_REG_PPC_TM_XER            | 64
         |                               |
   MIPS  | KVM_REG_MIPS_R0               | 64
           ...
@@ -2209,7 +2212,7 @@ after pausing the vcpu, but before it is resumed.
 4.71 KVM_SIGNAL_MSI
 
 Capability: KVM_CAP_SIGNAL_MSI
-Architectures: x86 arm64
+Architectures: x86 arm arm64
 Type: vm ioctl
 Parameters: struct kvm_msi (in)
 Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error

Documentation/virtual/kvm/halt-polling.txt

@@ -0,0 +1,127 @@
+The KVM halt polling system
+===========================
+
+The KVM halt polling system provides a feature within KVM whereby the latency
+of a guest can, under some circumstances, be reduced by polling in the host
+for some time period after the guest has elected to no longer run by cedeing.
+That is, when a guest vcpu has ceded, or in the case of powerpc when all of the
+vcpus of a single vcore have ceded, the host kernel polls for wakeup conditions
+before giving up the cpu to the scheduler in order to let something else run.
+
+Polling provides a latency advantage in cases where the guest can be run again
+very quickly by at least saving us a trip through the scheduler, normally on
+the order of a few micro-seconds, although performance benefits are workload
+dependant. In the event that no wakeup source arrives during the polling
+interval or some other task on the runqueue is runnable the scheduler is
+invoked. Thus halt polling is especially useful on workloads with very short
+wakeup periods where the time spent halt polling is minimised and the time
+savings of not invoking the scheduler are distinguishable.
+
+The generic halt polling code is implemented in:
+
+	virt/kvm/kvm_main.c: kvm_vcpu_block()
+
+The powerpc kvm-hv specific case is implemented in:
+
+	arch/powerpc/kvm/book3s_hv.c: kvmppc_vcore_blocked()
+
+Halt Polling Interval
+=====================
+
+The maximum time for which to poll before invoking the scheduler, referred to
+as the halt polling interval, is increased and decreased based on the perceived
+effectiveness of the polling in an attempt to limit pointless polling.
+This value is stored in either the vcpu struct:
+
+	kvm_vcpu->halt_poll_ns
+
+or in the case of powerpc kvm-hv, in the vcore struct:
+
+	kvmppc_vcore->halt_poll_ns
+
+Thus this is a per vcpu (or vcore) value.
+
+During polling if a wakeup source is received within the halt polling interval,
+the interval is left unchanged. In the event that a wakeup source isn't
+received during the polling interval (and thus schedule is invoked) there are
+two options, either the polling interval and total block time[0] were less than
+the global max polling interval (see module params below), or the total block
+time was greater than the global max polling interval.
+
+In the event that both the polling interval and total block time were less than
+the global max polling interval then the polling interval can be increased in
+the hope that next time during the longer polling interval the wake up source
+will be received while the host is polling and the latency benefits will be
+received. The polling interval is grown in the function grow_halt_poll_ns() and
+is multiplied by the module parameter halt_poll_ns_grow.
+
+In the event that the total block time was greater than the global max polling
+interval then the host will never poll for long enough (limited by the global
+max) to wakeup during the polling interval so it may as well be shrunk in order
+to avoid pointless polling. The polling interval is shrunk in the function
+shrink_halt_poll_ns() and is divided by the module parameter
+halt_poll_ns_shrink, or set to 0 iff halt_poll_ns_shrink == 0.
+
+It is worth noting that this adjustment process attempts to hone in on some
+steady state polling interval but will only really do a good job for wakeups
+which come at an approximately constant rate, otherwise there will be constant
+adjustment of the polling interval.
+
+[0] total block time: the time between when the halt polling function is
+		      invoked and a wakeup source received (irrespective of
+		      whether the scheduler is invoked within that function).
+
+Module Parameters
+=================
+
+The kvm module has 3 tuneable module parameters to adjust the global max
+polling interval as well as the rate at which the polling interval is grown and
+shrunk. These variables are defined in include/linux/kvm_host.h and as module
+parameters in virt/kvm/kvm_main.c, or arch/powerpc/kvm/book3s_hv.c in the
+powerpc kvm-hv case.
+
+Module Parameter    |	     Description	      |	     Default Value
+--------------------------------------------------------------------------------
+halt_poll_ns	    | The global max polling interval | KVM_HALT_POLL_NS_DEFAULT
+		    | which defines the ceiling value |
+		    | of the polling interval for     | (per arch value)
+		    | each vcpu. 		      |
+--------------------------------------------------------------------------------
+halt_poll_ns_grow   | The value by which the halt     |	2
+		    | polling interval is multiplied  |
+		    | in the grow_halt_poll_ns()      |
+		    | function.			      |
+--------------------------------------------------------------------------------
+halt_poll_ns_shrink | The value by which the halt     |	0
+		    | polling interval is divided in  |
+		    | the shrink_halt_poll_ns()	      |
+		    | function.			      |
+--------------------------------------------------------------------------------
+
+These module parameters can be set from the debugfs files in:
+
+	/sys/module/kvm/parameters/
+
+Note: that these module parameters are system wide values and are not able to
+      be tuned on a per vm basis.
+
+Further Notes
+=============
+
+- Care should be taken when setting the halt_poll_ns module parameter as a
+large value has the potential to drive the cpu usage to 100% on a machine which
+would be almost entirely idle otherwise. This is because even if a guest has
+wakeups during which very little work is done and which are quite far apart, if
+the period is shorter than the global max polling interval (halt_poll_ns) then
+the host will always poll for the entire block time and thus cpu utilisation
+will go to 100%.
+
+- Halt polling essentially presents a trade off between power usage and latency
+and the module parameters should be used to tune the affinity for this. Idle
+cpu time is essentially converted to host kernel time with the aim of decreasing
+latency when entering the guest.
+
+- Halt polling will only be conducted by the host when no other tasks are
+runnable on that cpu, otherwise the polling will cease immediately and
+schedule will be invoked to allow that other task to run. Thus this doesn't
+allow a guest to denial of service the cpu.

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

@@ -87,9 +87,11 @@ struct kvm_regs {
 /* Supported VGICv3 address types  */
 #define KVM_VGIC_V3_ADDR_TYPE_DIST	2
 #define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
+#define KVM_VGIC_ITS_ADDR_TYPE		4
 
 #define KVM_VGIC_V3_DIST_SIZE		SZ_64K
 #define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
+#define KVM_VGIC_V3_ITS_SIZE		(2 * SZ_64K)
 
 #define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
 #define KVM_ARM_VCPU_PSCI_0_2		1 /* CPU uses PSCI v0.2 */

arch/arm/kvm/Kconfig

@@ -34,6 +34,7 @@ config KVM
 	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_IRQ_ROUTING
+	select HAVE_KVM_MSI
 	depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER
 	---help---
 	  Support hosting virtualized guest machines.

arch/arm/kvm/Makefile

@@ -32,5 +32,6 @@ obj-y += $(KVM)/arm/vgic/vgic-mmio.o
 obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o
 obj-y += $(KVM)/arm/vgic/vgic-mmio-v3.o
 obj-y += $(KVM)/arm/vgic/vgic-kvm-device.o
+obj-y += $(KVM)/arm/vgic/vgic-its.o
 obj-y += $(KVM)/irqchip.o
 obj-y += $(KVM)/arm/arch_timer.o

arch/arm/kvm/arm.c

@@ -221,6 +221,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
 		break;
+	case KVM_CAP_MSI_DEVID:
+		if (!kvm)
+			r = -EINVAL;
+		else
+			r = kvm->arch.vgic.msis_require_devid;
+		break;
 	default:
 		r = kvm_arch_dev_ioctl_check_extension(kvm, ext);
 		break;

arch/arm64/kvm/Kconfig

@@ -16,9 +16,6 @@ menuconfig VIRTUALIZATION
 
 if VIRTUALIZATION
 
-config KVM_ARM_VGIC_V3_ITS
-	bool
-
 config KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
 	depends on OF
@@ -34,7 +31,6 @@ config KVM
 	select KVM_VFIO
 	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQFD
-	select KVM_ARM_VGIC_V3_ITS
 	select KVM_ARM_PMU if HW_PERF_EVENTS
 	select HAVE_KVM_MSI
 	select HAVE_KVM_IRQCHIP

arch/arm64/kvm/hyp/switch.c

@@ -85,7 +85,13 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 	write_sysreg(val, hcr_el2);
 	/* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */
 	write_sysreg(1 << 15, hstr_el2);
-	/* Make sure we trap PMU access from EL0 to EL2 */
+	/*
+	 * Make sure we trap PMU access from EL0 to EL2. Also sanitize
+	 * PMSELR_EL0 to make sure it never contains the cycle
+	 * counter, which could make a PMXEVCNTR_EL0 access UNDEF at
+	 * EL1 instead of being trapped to EL2.
+	 */
+	write_sysreg(0, pmselr_el0);
 	write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 	__activate_traps_arch()();

arch/arm64/kvm/reset.c

@@ -86,12 +86,6 @@ int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_VCPU_ATTRIBUTES:
 		r = 1;
 		break;
-	case KVM_CAP_MSI_DEVID:
-		if (!kvm)
-			r = -EINVAL;
-		else
-			r = kvm->arch.vgic.msis_require_devid;
-		break;
 	default:
 		r = 0;
 	}

arch/powerpc/include/asm/book3s/64/mmu-hash.h

@@ -70,7 +70,9 @@
 
 #define HPTE_V_SSIZE_SHIFT	62
 #define HPTE_V_AVPN_SHIFT	7
+#define HPTE_V_COMMON_BITS	ASM_CONST(0x000fffffffffffff)
 #define HPTE_V_AVPN		ASM_CONST(0x3fffffffffffff80)
+#define HPTE_V_AVPN_3_0		ASM_CONST(0x000fffffffffff80)
 #define HPTE_V_AVPN_VAL(x)	(((x) & HPTE_V_AVPN) >> HPTE_V_AVPN_SHIFT)
 #define HPTE_V_COMPARE(x,y)	(!(((x) ^ (y)) & 0xffffffffffffff80UL))
 #define HPTE_V_BOLTED		ASM_CONST(0x0000000000000010)
@@ -80,14 +82,16 @@
 #define HPTE_V_VALID		ASM_CONST(0x0000000000000001)
 
 /*
- * ISA 3.0 have a different HPTE format.
+ * ISA 3.0 has a different HPTE format.
  */
 #define HPTE_R_3_0_SSIZE_SHIFT	58
+#define HPTE_R_3_0_SSIZE_MASK	(3ull << HPTE_R_3_0_SSIZE_SHIFT)
 #define HPTE_R_PP0		ASM_CONST(0x8000000000000000)
 #define HPTE_R_TS		ASM_CONST(0x4000000000000000)
 #define HPTE_R_KEY_HI		ASM_CONST(0x3000000000000000)
 #define HPTE_R_RPN_SHIFT	12
 #define HPTE_R_RPN		ASM_CONST(0x0ffffffffffff000)
+#define HPTE_R_RPN_3_0		ASM_CONST(0x01fffffffffff000)
 #define HPTE_R_PP		ASM_CONST(0x0000000000000003)
 #define HPTE_R_PPP		ASM_CONST(0x8000000000000003)
 #define HPTE_R_N		ASM_CONST(0x0000000000000004)
@@ -316,11 +320,42 @@ static inline unsigned long hpte_encode_avpn(unsigned long vpn, int psize,
 	 */
 	v = (vpn >> (23 - VPN_SHIFT)) & ~(mmu_psize_defs[psize].avpnm);
 	v <<= HPTE_V_AVPN_SHIFT;
-	if (!cpu_has_feature(CPU_FTR_ARCH_300))
-		v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
+	v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
 	return v;
 }
 
+/*
+ * ISA v3.0 defines a new HPTE format, which differs from the old
+ * format in having smaller AVPN and ARPN fields, and the B field
+ * in the second dword instead of the first.
+ */
+static inline unsigned long hpte_old_to_new_v(unsigned long v)
+{
+	/* trim AVPN, drop B */
+	return v & HPTE_V_COMMON_BITS;
+}
+
+static inline unsigned long hpte_old_to_new_r(unsigned long v, unsigned long r)
+{
+	/* move B field from 1st to 2nd dword, trim ARPN */
+	return (r & ~HPTE_R_3_0_SSIZE_MASK) |
+		(((v) >> HPTE_V_SSIZE_SHIFT) << HPTE_R_3_0_SSIZE_SHIFT);
+}
+
+static inline unsigned long hpte_new_to_old_v(unsigned long v, unsigned long r)
+{
+	/* insert B field */
+	return (v & HPTE_V_COMMON_BITS) |
+		((r & HPTE_R_3_0_SSIZE_MASK) <<
+		 (HPTE_V_SSIZE_SHIFT - HPTE_R_3_0_SSIZE_SHIFT));
+}
+
+static inline unsigned long hpte_new_to_old_r(unsigned long r)
+{
+	/* clear out B field */
+	return r & ~HPTE_R_3_0_SSIZE_MASK;
+}
+
 /*
  * This function sets the AVPN and L fields of the HPTE  appropriately
  * using the base page size and actual page size.
@@ -341,12 +376,8 @@ static inline unsigned long hpte_encode_v(unsigned long vpn, int base_psize,
  * aligned for the requested page size
  */
 static inline unsigned long hpte_encode_r(unsigned long pa, int base_psize,
-					  int actual_psize, int ssize)
+					  int actual_psize)
 {
-
-	if (cpu_has_feature(CPU_FTR_ARCH_300))
-		pa |= ((unsigned long) ssize) << HPTE_R_3_0_SSIZE_SHIFT;
-
 	/* A 4K page needs no special encoding */
 	if (actual_psize == MMU_PAGE_4K)
 		return pa & HPTE_R_RPN;

arch/powerpc/include/asm/kvm_asm.h

@@ -99,6 +99,7 @@
 #define BOOK3S_INTERRUPT_H_EMUL_ASSIST	0xe40
 #define BOOK3S_INTERRUPT_HMI		0xe60
 #define BOOK3S_INTERRUPT_H_DOORBELL	0xe80
+#define BOOK3S_INTERRUPT_H_VIRT		0xea0
 #define BOOK3S_INTERRUPT_PERFMON	0xf00
 #define BOOK3S_INTERRUPT_ALTIVEC	0xf20
 #define BOOK3S_INTERRUPT_VSX		0xf40

arch/powerpc/include/asm/kvm_host.h

@@ -48,7 +48,7 @@
 #ifdef CONFIG_KVM_MMIO
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #endif
-#define KVM_HALT_POLL_NS_DEFAULT 500000
+#define KVM_HALT_POLL_NS_DEFAULT 10000	/* 10 us */
 
 /* These values are internal and can be increased later */
 #define KVM_NR_IRQCHIPS          1
@@ -244,8 +244,10 @@ struct kvm_arch_memory_slot {
 struct kvm_arch {
 	unsigned int lpid;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	unsigned int tlb_sets;
 	unsigned long hpt_virt;
 	struct revmap_entry *revmap;
+	atomic64_t mmio_update;
 	unsigned int host_lpid;
 	unsigned long host_lpcr;
 	unsigned long sdr1;
@@ -408,6 +410,24 @@ struct kvmppc_passthru_irqmap {
 #define KVMPPC_IRQ_MPIC		1
 #define KVMPPC_IRQ_XICS		2
 
+#define MMIO_HPTE_CACHE_SIZE	4
+
+struct mmio_hpte_cache_entry {
+	unsigned long hpte_v;
+	unsigned long hpte_r;
+	unsigned long rpte;
+	unsigned long pte_index;
+	unsigned long eaddr;
+	unsigned long slb_v;
+	long mmio_update;
+	unsigned int slb_base_pshift;
+};
+
+struct mmio_hpte_cache {
+	struct mmio_hpte_cache_entry entry[MMIO_HPTE_CACHE_SIZE];
+	unsigned int index;
+};
+
 struct openpic;
 
 struct kvm_vcpu_arch {
@@ -498,6 +518,8 @@ struct kvm_vcpu_arch {
 	ulong tcscr;
 	ulong acop;
 	ulong wort;
+	ulong tid;
+	ulong psscr;
 	ulong shadow_srr1;
 #endif
 	u32 vrsave; /* also USPRG0 */
@@ -546,6 +568,7 @@ struct kvm_vcpu_arch {
 	u64 tfiar;
 
 	u32 cr_tm;
+	u64 xer_tm;
 	u64 lr_tm;
 	u64 ctr_tm;
 	u64 amr_tm;
@@ -655,9 +678,11 @@ struct kvm_vcpu_arch {
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	struct kvm_vcpu_arch_shared shregs;
 
+	struct mmio_hpte_cache mmio_cache;
 	unsigned long pgfault_addr;
 	long pgfault_index;
 	unsigned long pgfault_hpte[2];
+	struct mmio_hpte_cache_entry *pgfault_cache;
 
 	struct task_struct *run_task;
 	struct kvm_run *kvm_run;

arch/powerpc/include/asm/kvm_ppc.h

@@ -483,9 +483,10 @@ extern void kvmppc_xics_set_mapped(struct kvm *kvm, unsigned long guest_irq,
 				   unsigned long host_irq);
 extern void kvmppc_xics_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
 				   unsigned long host_irq);
-extern long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu, u32 xirr,
-				 struct kvmppc_irq_map *irq_map,
-				 struct kvmppc_passthru_irqmap *pimap);
+extern long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu, __be32 xirr,
+					struct kvmppc_irq_map *irq_map,
+					struct kvmppc_passthru_irqmap *pimap,
+					bool *again);
 extern int h_ipi_redirect;
 #else
 static inline struct kvmppc_passthru_irqmap *kvmppc_get_passthru_irqmap(
@@ -509,6 +510,48 @@ static inline int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd)
 	{ return 0; }
 #endif
 
+/*
+ * Prototypes for functions called only from assembler code.
+ * Having prototypes reduces sparse errors.
+ */
+long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
+			 unsigned long ioba, unsigned long tce);
+long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+				  unsigned long liobn, unsigned long ioba,
+				  unsigned long tce_list, unsigned long npages);
+long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
+			   unsigned long liobn, unsigned long ioba,
+			   unsigned long tce_value, unsigned long npages);
+long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target,
+                            unsigned int yield_count);
+long kvmppc_h_random(struct kvm_vcpu *vcpu);
+void kvmhv_commence_exit(int trap);
+long kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu);
+void kvmppc_subcore_enter_guest(void);
+void kvmppc_subcore_exit_guest(void);
+long kvmppc_realmode_hmi_handler(void);
+long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
+                    long pte_index, unsigned long pteh, unsigned long ptel);
+long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
+                     unsigned long pte_index, unsigned long avpn);
+long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu);
+long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
+                      unsigned long pte_index, unsigned long avpn,
+                      unsigned long va);
+long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
+                   unsigned long pte_index);
+long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags,
+                        unsigned long pte_index);
+long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
+                        unsigned long pte_index);
+long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
+                          unsigned long slb_v, unsigned int status, bool data);
+unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu);
+int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
+                    unsigned long mfrr);
+int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
+int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr);
+
 /*
  * Host-side operations we want to set up while running in real
  * mode in the guest operating on the xics.

arch/powerpc/include/asm/mmu.h

@@ -214,6 +214,11 @@ extern u64 ppc64_rma_size;
 /* Cleanup function used by kexec */
 extern void mmu_cleanup_all(void);
 extern void radix__mmu_cleanup_all(void);
+
+/* Functions for creating and updating partition table on POWER9 */
+extern void mmu_partition_table_init(void);
+extern void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
+					  unsigned long dw1);
 #endif /* CONFIG_PPC64 */
 
 struct mm_struct;

arch/powerpc/include/asm/opal.h

@@ -220,9 +220,12 @@ int64_t opal_pci_set_power_state(uint64_t async_token, uint64_t id,
 int64_t opal_pci_poll2(uint64_t id, uint64_t data);
 
 int64_t opal_int_get_xirr(uint32_t *out_xirr, bool just_poll);
+int64_t opal_rm_int_get_xirr(__be32 *out_xirr, bool just_poll);
 int64_t opal_int_set_cppr(uint8_t cppr);
 int64_t opal_int_eoi(uint32_t xirr);
+int64_t opal_rm_int_eoi(uint32_t xirr);
 int64_t opal_int_set_mfrr(uint32_t cpu, uint8_t mfrr);
+int64_t opal_rm_int_set_mfrr(uint32_t cpu, uint8_t mfrr);
 int64_t opal_pci_tce_kill(uint64_t phb_id, uint32_t kill_type,
 			  uint32_t pe_num, uint32_t tce_size,
 			  uint64_t dma_addr, uint32_t npages);

arch/powerpc/include/asm/reg.h

@@ -153,6 +153,8 @@
 #define PSSCR_EC		0x00100000 /* Exit Criterion */
 #define PSSCR_ESL		0x00200000 /* Enable State Loss */
 #define PSSCR_SD		0x00400000 /* Status Disable */
+#define PSSCR_PLS	0xf000000000000000 /* Power-saving Level Status */
+#define PSSCR_GUEST_VIS	0xf0000000000003ff /* Guest-visible PSSCR fields */
 
 /* Floating Point Status and Control Register (FPSCR) Fields */
 #define FPSCR_FX	0x80000000	/* FPU exception summary */
@@ -236,6 +238,7 @@
 #define SPRN_TEXASRU	0x83	/* ''	   ''	   ''	 Upper 32  */
 #define   TEXASR_FS	__MASK(63-36) /* TEXASR Failure Summary */
 #define SPRN_TFHAR	0x80	/* Transaction Failure Handler Addr */
+#define SPRN_TIDR	144	/* Thread ID register */
 #define SPRN_CTRLF	0x088
 #define SPRN_CTRLT	0x098
 #define   CTRL_CT	0xc0000000	/* current thread */
@@ -294,6 +297,7 @@
 #define SPRN_HSRR1	0x13B	/* Hypervisor Save/Restore 1 */
 #define SPRN_LMRR	0x32D	/* Load Monitor Region Register */
 #define SPRN_LMSER	0x32E	/* Load Monitor Section Enable Register */
+#define SPRN_ASDR	0x330	/* Access segment descriptor register */
 #define SPRN_IC		0x350	/* Virtual Instruction Count */
 #define SPRN_VTB	0x351	/* Virtual Time Base */
 #define SPRN_LDBAR	0x352	/* LD Base Address Register */
@@ -305,6 +309,7 @@
 
 /* HFSCR and FSCR bit numbers are the same */
 #define FSCR_LM_LG	11	/* Enable Load Monitor Registers */
+#define FSCR_MSGP_LG	10	/* Enable MSGP */
 #define FSCR_TAR_LG	8	/* Enable Target Address Register */
 #define FSCR_EBB_LG	7	/* Enable Event Based Branching */
 #define FSCR_TM_LG	5	/* Enable Transactional Memory */
@@ -320,6 +325,7 @@
 #define   FSCR_DSCR	__MASK(FSCR_DSCR_LG)
 #define SPRN_HFSCR	0xbe	/* HV=1 Facility Status & Control Register */
 #define   HFSCR_LM	__MASK(FSCR_LM_LG)
+#define   HFSCR_MSGP	__MASK(FSCR_MSGP_LG)
 #define   HFSCR_TAR	__MASK(FSCR_TAR_LG)
 #define   HFSCR_EBB	__MASK(FSCR_EBB_LG)
 #define   HFSCR_TM	__MASK(FSCR_TM_LG)
@@ -358,6 +364,7 @@
 #define     LPCR_PECE_HVEE	ASM_CONST(0x0000400000000000)	/* P9 Wakeup on HV interrupts */
 #define   LPCR_MER		ASM_CONST(0x0000000000000800)	/* Mediated External Exception */
 #define   LPCR_MER_SH		11
+#define	  LPCR_GTSE		ASM_CONST(0x0000000000000400)  	/* Guest Translation Shootdown Enable */
 #define   LPCR_TC		ASM_CONST(0x0000000000000200)	/* Translation control */
 #define   LPCR_LPES		0x0000000c
 #define   LPCR_LPES0		ASM_CONST(0x0000000000000008)      /* LPAR Env selector 0 */
@@ -378,6 +385,12 @@
 #define   PCR_VEC_DIS	(1ul << (63-0))	/* Vec. disable (bit NA since POWER8) */
 #define   PCR_VSX_DIS	(1ul << (63-1))	/* VSX disable (bit NA since POWER8) */
 #define   PCR_TM_DIS	(1ul << (63-2))	/* Trans. memory disable (POWER8) */
+/*
+ * These bits are used in the function kvmppc_set_arch_compat() to specify and
+ * determine both the compatibility level which we want to emulate and the
+ * compatibility level which the host is capable of emulating.
+ */
+#define   PCR_ARCH_207	0x8		/* Architecture 2.07 */
 #define   PCR_ARCH_206	0x4		/* Architecture 2.06 */
 #define   PCR_ARCH_205	0x2		/* Architecture 2.05 */
 #define	SPRN_HEIR	0x153	/* Hypervisor Emulated Instruction Register */
@@ -1219,6 +1232,7 @@
 #define PVR_ARCH_206	0x0f000003
 #define PVR_ARCH_206p	0x0f100003
 #define PVR_ARCH_207	0x0f000004
+#define PVR_ARCH_300	0x0f000005
 
 /* Macros for setting and retrieving special purpose registers */
 #ifndef __ASSEMBLY__

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

@@ -573,6 +573,10 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_SPRG9	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xba)
 #define KVM_REG_PPC_DBSR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbb)
 
+/* POWER9 registers */
+#define KVM_REG_PPC_TIDR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc)
+#define KVM_REG_PPC_PSSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
+
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
  */
@@ -596,6 +600,7 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_TM_VSCR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67)
 #define KVM_REG_PPC_TM_DSCR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68)
 #define KVM_REG_PPC_TM_TAR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69)
+#define KVM_REG_PPC_TM_XER	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x6a)
 
 /* PPC64 eXternal Interrupt Controller Specification */
 #define KVM_DEV_XICS_GRP_SOURCES	1	/* 64-bit source attributes */

arch/powerpc/kernel/asm-offsets.c

@@ -487,6 +487,7 @@ int main(void)
 
 	/* book3s */
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	DEFINE(KVM_TLB_SETS, offsetof(struct kvm, arch.tlb_sets));
 	DEFINE(KVM_SDR1, offsetof(struct kvm, arch.sdr1));
 	DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid));
 	DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr));
@@ -548,6 +549,8 @@ int main(void)
 	DEFINE(VCPU_TCSCR, offsetof(struct kvm_vcpu, arch.tcscr));
 	DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop));
 	DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
+	DEFINE(VCPU_TID, offsetof(struct kvm_vcpu, arch.tid));
+	DEFINE(VCPU_PSSCR, offsetof(struct kvm_vcpu, arch.psscr));
 	DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_map));
 	DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
 	DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
@@ -569,6 +572,7 @@ int main(void)
 	DEFINE(VCPU_VRS_TM, offsetof(struct kvm_vcpu, arch.vr_tm.vr));
 	DEFINE(VCPU_VRSAVE_TM, offsetof(struct kvm_vcpu, arch.vrsave_tm));
 	DEFINE(VCPU_CR_TM, offsetof(struct kvm_vcpu, arch.cr_tm));
+	DEFINE(VCPU_XER_TM, offsetof(struct kvm_vcpu, arch.xer_tm));
 	DEFINE(VCPU_LR_TM, offsetof(struct kvm_vcpu, arch.lr_tm));
 	DEFINE(VCPU_CTR_TM, offsetof(struct kvm_vcpu, arch.ctr_tm));
 	DEFINE(VCPU_AMR_TM, offsetof(struct kvm_vcpu, arch.amr_tm));

arch/powerpc/kernel/cpu_setup_power.S

@@ -174,7 +174,7 @@ __init_FSCR:
 __init_HFSCR:
 	mfspr	r3,SPRN_HFSCR
 	ori	r3,r3,HFSCR_TAR|HFSCR_TM|HFSCR_BHRB|HFSCR_PM|\
-		      HFSCR_DSCR|HFSCR_VECVSX|HFSCR_FP|HFSCR_EBB
+		      HFSCR_DSCR|HFSCR_VECVSX|HFSCR_FP|HFSCR_EBB|HFSCR_MSGP
 	mtspr	SPRN_HFSCR,r3
 	blr
 

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -88,6 +88,8 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 	/* 128 (2**7) bytes in each HPTEG */
 	kvm->arch.hpt_mask = (1ul << (order - 7)) - 1;
 
+	atomic64_set(&kvm->arch.mmio_update, 0);
+
 	/* Allocate reverse map array */
 	rev = vmalloc(sizeof(struct revmap_entry) * kvm->arch.hpt_npte);
 	if (!rev) {
@@ -255,7 +257,7 @@ static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
 	kvmppc_set_msr(vcpu, msr);
 }
 
-long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags,
+static long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags,
 				long pte_index, unsigned long pteh,
 				unsigned long ptel, unsigned long *pte_idx_ret)
 {
@@ -312,7 +314,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	struct kvmppc_slb *slbe;
 	unsigned long slb_v;
 	unsigned long pp, key;
-	unsigned long v, gr;
+	unsigned long v, orig_v, gr;
 	__be64 *hptep;
 	int index;
 	int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR);
@@ -337,10 +339,12 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		return -ENOENT;
 	}
 	hptep = (__be64 *)(kvm->arch.hpt_virt + (index << 4));
-	v = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK;
+	v = orig_v = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK;
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		v = hpte_new_to_old_v(v, be64_to_cpu(hptep[1]));
 	gr = kvm->arch.revmap[index].guest_rpte;
 
-	unlock_hpte(hptep, v);
+	unlock_hpte(hptep, orig_v);
 	preempt_enable();
 
 	gpte->eaddr = eaddr;
@@ -438,6 +442,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 {
 	struct kvm *kvm = vcpu->kvm;
 	unsigned long hpte[3], r;
+	unsigned long hnow_v, hnow_r;
 	__be64 *hptep;
 	unsigned long mmu_seq, psize, pte_size;
 	unsigned long gpa_base, gfn_base;
@@ -451,6 +456,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	unsigned int writing, write_ok;
 	struct vm_area_struct *vma;
 	unsigned long rcbits;
+	long mmio_update;
 
 	/*
 	 * Real-mode code has already searched the HPT and found the
@@ -460,6 +466,19 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 */
 	if (ea != vcpu->arch.pgfault_addr)
 		return RESUME_GUEST;
+
+	if (vcpu->arch.pgfault_cache) {
+		mmio_update = atomic64_read(&kvm->arch.mmio_update);
+		if (mmio_update == vcpu->arch.pgfault_cache->mmio_update) {
+			r = vcpu->arch.pgfault_cache->rpte;
+			psize = hpte_page_size(vcpu->arch.pgfault_hpte[0], r);
+			gpa_base = r & HPTE_R_RPN & ~(psize - 1);
+			gfn_base = gpa_base >> PAGE_SHIFT;
+			gpa = gpa_base | (ea & (psize - 1));
+			return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea,
+						dsisr & DSISR_ISSTORE);
+		}
+	}
 	index = vcpu->arch.pgfault_index;
 	hptep = (__be64 *)(kvm->arch.hpt_virt + (index << 4));
 	rev = &kvm->arch.revmap[index];
@@ -472,6 +491,10 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	unlock_hpte(hptep, hpte[0]);
 	preempt_enable();
 
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		hpte[0] = hpte_new_to_old_v(hpte[0], hpte[1]);
+		hpte[1] = hpte_new_to_old_r(hpte[1]);
+	}
 	if (hpte[0] != vcpu->arch.pgfault_hpte[0] ||
 	    hpte[1] != vcpu->arch.pgfault_hpte[1])
 		return RESUME_GUEST;
@@ -575,16 +598,22 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 */
 	if (psize < PAGE_SIZE)
 		psize = PAGE_SIZE;
-	r = (r & ~(HPTE_R_PP0 - psize)) | ((pfn << PAGE_SHIFT) & ~(psize - 1));
+	r = (r & HPTE_R_KEY_HI) | (r & ~(HPTE_R_PP0 - psize)) |
+					((pfn << PAGE_SHIFT) & ~(psize - 1));
 	if (hpte_is_writable(r) && !write_ok)
 		r = hpte_make_readonly(r);
 	ret = RESUME_GUEST;
 	preempt_disable();
 	while (!try_lock_hpte(hptep, HPTE_V_HVLOCK))
 		cpu_relax();
-	if ((be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK) != hpte[0] ||
-		be64_to_cpu(hptep[1]) != hpte[1] ||
-		rev->guest_rpte != hpte[2])
+	hnow_v = be64_to_cpu(hptep[0]);
+	hnow_r = be64_to_cpu(hptep[1]);
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		hnow_v = hpte_new_to_old_v(hnow_v, hnow_r);
+		hnow_r = hpte_new_to_old_r(hnow_r);
+	}
+	if ((hnow_v & ~HPTE_V_HVLOCK) != hpte[0] || hnow_r != hpte[1] ||
+	    rev->guest_rpte != hpte[2])
 		/* HPTE has been changed under us; let the guest retry */
 		goto out_unlock;
 	hpte[0] = (hpte[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;
@@ -615,6 +644,10 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		kvmppc_add_revmap_chain(kvm, rev, rmap, index, 0);
 	}
 
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		r = hpte_old_to_new_r(hpte[0], r);
+		hpte[0] = hpte_old_to_new_v(hpte[0]);
+	}
 	hptep[1] = cpu_to_be64(r);
 	eieio();
 	__unlock_hpte(hptep, hpte[0]);
@@ -758,6 +791,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 		    hpte_rpn(ptel, psize) == gfn) {
 			hptep[0] |= cpu_to_be64(HPTE_V_ABSENT);
 			kvmppc_invalidate_hpte(kvm, hptep, i);
+			hptep[1] &= ~cpu_to_be64(HPTE_R_KEY_HI | HPTE_R_KEY_LO);
 			/* Harvest R and C */
 			rcbits = be64_to_cpu(hptep[1]) & (HPTE_R_R | HPTE_R_C);
 			*rmapp |= rcbits << KVMPPC_RMAP_RC_SHIFT;
@@ -1165,7 +1199,7 @@ static long record_hpte(unsigned long flags, __be64 *hptp,
 			unsigned long *hpte, struct revmap_entry *revp,
 			int want_valid, int first_pass)
 {
-	unsigned long v, r;
+	unsigned long v, r, hr;
 	unsigned long rcbits_unset;
 	int ok = 1;
 	int valid, dirty;
@@ -1192,6 +1226,11 @@ static long record_hpte(unsigned long flags, __be64 *hptp,
 		while (!try_lock_hpte(hptp, HPTE_V_HVLOCK))
 			cpu_relax();
 		v = be64_to_cpu(hptp[0]);
+		hr = be64_to_cpu(hptp[1]);
+		if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+			v = hpte_new_to_old_v(v, hr);
+			hr = hpte_new_to_old_r(hr);
+		}
 
 		/* re-evaluate valid and dirty from synchronized HPTE value */
 		valid = !!(v & HPTE_V_VALID);
@@ -1199,8 +1238,8 @@ static long record_hpte(unsigned long flags, __be64 *hptp,
 
 		/* Harvest R and C into guest view if necessary */
 		rcbits_unset = ~revp->guest_rpte & (HPTE_R_R | HPTE_R_C);
-		if (valid && (rcbits_unset & be64_to_cpu(hptp[1]))) {
-			revp->guest_rpte |= (be64_to_cpu(hptp[1]) &
+		if (valid && (rcbits_unset & hr)) {
+			revp->guest_rpte |= (hr &
 				(HPTE_R_R | HPTE_R_C)) | HPTE_GR_MODIFIED;
 			dirty = 1;
 		}
@@ -1608,7 +1647,7 @@ static ssize_t debugfs_htab_read(struct file *file, char __user *buf,
 	return ret;
 }
 
-ssize_t debugfs_htab_write(struct file *file, const char __user *buf,
+static ssize_t debugfs_htab_write(struct file *file, const char __user *buf,
 			   size_t len, loff_t *ppos)
 {
 	return -EACCES;

arch/powerpc/kvm/book3s_64_vio_hv.c

@@ -39,7 +39,6 @@
 #include <asm/udbg.h>
 #include <asm/iommu.h>
 #include <asm/tce.h>
-#include <asm/iommu.h>
 
 #define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
 

arch/powerpc/kvm/book3s_hv.c

@@ -54,6 +54,9 @@
 #include <asm/dbell.h>
 #include <asm/hmi.h>
 #include <asm/pnv-pci.h>
+#include <asm/mmu.h>
+#include <asm/opal.h>
+#include <asm/xics.h>
 #include <linux/gfp.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
@@ -62,6 +65,7 @@
 #include <linux/irqbypass.h>
 #include <linux/module.h>
 #include <linux/compiler.h>
+#include <linux/of.h>
 
 #include "book3s.h"
 
@@ -104,23 +108,6 @@ module_param_cb(h_ipi_redirect, &module_param_ops, &h_ipi_redirect,
 MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core");
 #endif
 
-/* Maximum halt poll interval defaults to KVM_HALT_POLL_NS_DEFAULT */
-static unsigned int halt_poll_max_ns = KVM_HALT_POLL_NS_DEFAULT;
-module_param(halt_poll_max_ns, uint, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(halt_poll_max_ns, "Maximum halt poll time in ns");
-
-/* Factor by which the vcore halt poll interval is grown, default is to double
- */
-static unsigned int halt_poll_ns_grow = 2;
-module_param(halt_poll_ns_grow, int, S_IRUGO);
-MODULE_PARM_DESC(halt_poll_ns_grow, "Factor halt poll time is grown by");
-
-/* Factor by which the vcore halt poll interval is shrunk, default is to reset
- */
-static unsigned int halt_poll_ns_shrink;
-module_param(halt_poll_ns_shrink, int, S_IRUGO);
-MODULE_PARM_DESC(halt_poll_ns_shrink, "Factor halt poll time is shrunk by");
-
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
@@ -146,12 +133,21 @@ static inline struct kvm_vcpu *next_runnable_thread(struct kvmppc_vcore *vc,
 
 static bool kvmppc_ipi_thread(int cpu)
 {
+	unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+
+	/* On POWER9 we can use msgsnd to IPI any cpu */
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		msg |= get_hard_smp_processor_id(cpu);
+		smp_mb();
+		__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+		return true;
+	}
+
 	/* On POWER8 for IPIs to threads in the same core, use msgsnd */
 	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
 		preempt_disable();
 		if (cpu_first_thread_sibling(cpu) ==
 		    cpu_first_thread_sibling(smp_processor_id())) {
-			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 			msg |= cpu_thread_in_core(cpu);
 			smp_mb();
 			__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
@@ -162,8 +158,12 @@ static bool kvmppc_ipi_thread(int cpu)
 	}
 
 #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
-	if (cpu >= 0 && cpu < nr_cpu_ids && paca[cpu].kvm_hstate.xics_phys) {
-		xics_wake_cpu(cpu);
+	if (cpu >= 0 && cpu < nr_cpu_ids) {
+		if (paca[cpu].kvm_hstate.xics_phys) {
+			xics_wake_cpu(cpu);
+			return true;
+		}
+		opal_int_set_mfrr(get_hard_smp_processor_id(cpu), IPI_PRIORITY);
 		return true;
 	}
 #endif
@@ -299,41 +299,54 @@ static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
 	vcpu->arch.pvr = pvr;
 }
 
+/* Dummy value used in computing PCR value below */
+#define PCR_ARCH_300	(PCR_ARCH_207 << 1)
+
 static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 {
-	unsigned long pcr = 0;
+	unsigned long host_pcr_bit = 0, guest_pcr_bit = 0;
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
+	/* We can (emulate) our own architecture version and anything older */
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		host_pcr_bit = PCR_ARCH_300;
+	else if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		host_pcr_bit = PCR_ARCH_207;
+	else if (cpu_has_feature(CPU_FTR_ARCH_206))
+		host_pcr_bit = PCR_ARCH_206;
+	else
+		host_pcr_bit = PCR_ARCH_205;
+
+	/* Determine lowest PCR bit needed to run guest in given PVR level */
+	guest_pcr_bit = host_pcr_bit;
 	if (arch_compat) {
 		switch (arch_compat) {
 		case PVR_ARCH_205:
-			/*
-			 * If an arch bit is set in PCR, all the defined
-			 * higher-order arch bits also have to be set.
-			 */
-			pcr = PCR_ARCH_206 | PCR_ARCH_205;
+			guest_pcr_bit = PCR_ARCH_205;
 			break;
 		case PVR_ARCH_206:
 		case PVR_ARCH_206p:
-			pcr = PCR_ARCH_206;
+			guest_pcr_bit = PCR_ARCH_206;
 			break;
 		case PVR_ARCH_207:
+			guest_pcr_bit = PCR_ARCH_207;
+			break;
+		case PVR_ARCH_300:
+			guest_pcr_bit = PCR_ARCH_300;
 			break;
 		default:
 			return -EINVAL;
 		}
-
-		if (!cpu_has_feature(CPU_FTR_ARCH_207S)) {
-			/* POWER7 can't emulate POWER8 */
-			if (!(pcr & PCR_ARCH_206))
-				return -EINVAL;
-			pcr &= ~PCR_ARCH_206;
-		}
 	}
 
+	/* Check requested PCR bits don't exceed our capabilities */
+	if (guest_pcr_bit > host_pcr_bit)
+		return -EINVAL;
+
 	spin_lock(&vc->lock);
 	vc->arch_compat = arch_compat;
-	vc->pcr = pcr;
+	/* Set all PCR bits for which guest_pcr_bit <= bit < host_pcr_bit */
+	vc->pcr = host_pcr_bit - guest_pcr_bit;
 	spin_unlock(&vc->lock);
 
 	return 0;
@@ -945,6 +958,7 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		break;
 	case BOOK3S_INTERRUPT_EXTERNAL:
 	case BOOK3S_INTERRUPT_H_DOORBELL:
+	case BOOK3S_INTERRUPT_H_VIRT:
 		vcpu->stat.ext_intr_exits++;
 		r = RESUME_GUEST;
 		break;
@@ -1229,6 +1243,12 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_WORT:
 		*val = get_reg_val(id, vcpu->arch.wort);
 		break;
+	case KVM_REG_PPC_TIDR:
+		*val = get_reg_val(id, vcpu->arch.tid);
+		break;
+	case KVM_REG_PPC_PSSCR:
+		*val = get_reg_val(id, vcpu->arch.psscr);
+		break;
 	case KVM_REG_PPC_VPA_ADDR:
 		spin_lock(&vcpu->arch.vpa_update_lock);
 		*val = get_reg_val(id, vcpu->arch.vpa.next_gpa);
@@ -1288,6 +1308,9 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_TM_CR:
 		*val = get_reg_val(id, vcpu->arch.cr_tm);
 		break;
+	case KVM_REG_PPC_TM_XER:
+		*val = get_reg_val(id, vcpu->arch.xer_tm);
+		break;
 	case KVM_REG_PPC_TM_LR:
 		*val = get_reg_val(id, vcpu->arch.lr_tm);
 		break;
@@ -1427,6 +1450,12 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_WORT:
 		vcpu->arch.wort = set_reg_val(id, *val);
 		break;
+	case KVM_REG_PPC_TIDR:
+		vcpu->arch.tid = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_PSSCR:
+		vcpu->arch.psscr = set_reg_val(id, *val) & PSSCR_GUEST_VIS;
+		break;
 	case KVM_REG_PPC_VPA_ADDR:
 		addr = set_reg_val(id, *val);
 		r = -EINVAL;
@@ -1498,6 +1527,9 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_TM_CR:
 		vcpu->arch.cr_tm = set_reg_val(id, *val);
 		break;
+	case KVM_REG_PPC_TM_XER:
+		vcpu->arch.xer_tm = set_reg_val(id, *val);
+		break;
 	case KVM_REG_PPC_TM_LR:
 		vcpu->arch.lr_tm = set_reg_val(id, *val);
 		break;
@@ -1540,6 +1572,20 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	return r;
 }
 
+/*
+ * On POWER9, threads are independent and can be in different partitions.
+ * Therefore we consider each thread to be a subcore.
+ * There is a restriction that all threads have to be in the same
+ * MMU mode (radix or HPT), unfortunately, but since we only support
+ * HPT guests on a HPT host so far, that isn't an impediment yet.
+ */
+static int threads_per_vcore(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		return 1;
+	return threads_per_subcore;
+}
+
 static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
 {
 	struct kvmppc_vcore *vcore;
@@ -1554,7 +1600,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
 	init_swait_queue_head(&vcore->wq);
 	vcore->preempt_tb = TB_NIL;
 	vcore->lpcr = kvm->arch.lpcr;
-	vcore->first_vcpuid = core * threads_per_subcore;
+	vcore->first_vcpuid = core * threads_per_vcore();
 	vcore->kvm = kvm;
 	INIT_LIST_HEAD(&vcore->preempt_list);
 
@@ -1717,7 +1763,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 	int core;
 	struct kvmppc_vcore *vcore;
 
-	core = id / threads_per_subcore;
+	core = id / threads_per_vcore();
 	if (core >= KVM_MAX_VCORES)
 		goto out;
 
@@ -1935,7 +1981,10 @@ static void kvmppc_wait_for_nap(void)
 {
 	int cpu = smp_processor_id();
 	int i, loops;
+	int n_threads = threads_per_vcore();
 
+	if (n_threads <= 1)
+		return;
 	for (loops = 0; loops < 1000000; ++loops) {
 		/*
 		 * Check if all threads are finished.
@@ -1943,17 +1992,17 @@ static void kvmppc_wait_for_nap(void)
 		 * and the thread clears it when finished, so we look
 		 * for any threads that still have a non-NULL vcore ptr.
 		 */
-		for (i = 1; i < threads_per_subcore; ++i)
+		for (i = 1; i < n_threads; ++i)
 			if (paca[cpu + i].kvm_hstate.kvm_vcore)
 				break;
-		if (i == threads_per_subcore) {
+		if (i == n_threads) {
 			HMT_medium();
 			return;
 		}
 		HMT_low();
 	}
 	HMT_medium();
-	for (i = 1; i < threads_per_subcore; ++i)
+	for (i = 1; i < n_threads; ++i)
 		if (paca[cpu + i].kvm_hstate.kvm_vcore)
 			pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
 }
@@ -2019,7 +2068,7 @@ static void kvmppc_vcore_preempt(struct kvmppc_vcore *vc)
 
 	vc->vcore_state = VCORE_PREEMPT;
 	vc->pcpu = smp_processor_id();
-	if (vc->num_threads < threads_per_subcore) {
+	if (vc->num_threads < threads_per_vcore()) {
 		spin_lock(&lp->lock);
 		list_add_tail(&vc->preempt_list, &lp->list);
 		spin_unlock(&lp->lock);
@@ -2123,8 +2172,7 @@ static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip)
 	cip->subcore_threads[sub] = vc->num_threads;
 	cip->subcore_vm[sub] = vc->kvm;
 	init_master_vcore(vc);
-	list_del(&vc->preempt_list);
-	list_add_tail(&vc->preempt_list, &cip->vcs[sub]);
+	list_move_tail(&vc->preempt_list, &cip->vcs[sub]);
 
 	return true;
 }
@@ -2309,6 +2357,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	unsigned long cmd_bit, stat_bit;
 	int pcpu, thr;
 	int target_threads;
+	int controlled_threads;
 
 	/*
 	 * Remove from the list any threads that have a signal pending
@@ -2326,12 +2375,19 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	init_master_vcore(vc);
 	vc->preempt_tb = TB_NIL;
 
+	/*
+	 * Number of threads that we will be controlling: the same as
+	 * the number of threads per subcore, except on POWER9,
+	 * where it's 1 because the threads are (mostly) independent.
+	 */
+	controlled_threads = threads_per_vcore();
+
 	/*
 	 * Make sure we are running on primary threads, and that secondary
 	 * threads are offline.  Also check if the number of threads in this
 	 * guest are greater than the current system threads per guest.
 	 */
-	if ((threads_per_core > 1) &&
+	if ((controlled_threads > 1) &&
 	    ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
 		for_each_runnable_thread(i, vcpu, vc) {
 			vcpu->arch.ret = -EBUSY;
@@ -2347,7 +2403,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	 */
 	init_core_info(&core_info, vc);
 	pcpu = smp_processor_id();
-	target_threads = threads_per_subcore;
+	target_threads = controlled_threads;
 	if (target_smt_mode && target_smt_mode < target_threads)
 		target_threads = target_smt_mode;
 	if (vc->num_threads < target_threads)
@@ -2383,7 +2439,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 		smp_wmb();
 	}
 	pcpu = smp_processor_id();
-	for (thr = 0; thr < threads_per_subcore; ++thr)
+	for (thr = 0; thr < controlled_threads; ++thr)
 		paca[pcpu + thr].kvm_hstate.kvm_split_mode = sip;
 
 	/* Initiate micro-threading (split-core) if required */
@@ -2493,7 +2549,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	}
 
 	/* Let secondaries go back to the offline loop */
-	for (i = 0; i < threads_per_subcore; ++i) {
+	for (i = 0; i < controlled_threads; ++i) {
 		kvmppc_release_hwthread(pcpu + i);
 		if (sip && sip->napped[i])
 			kvmppc_ipi_thread(pcpu + i);
@@ -2545,9 +2601,6 @@ static void grow_halt_poll_ns(struct kvmppc_vcore *vc)
 		vc->halt_poll_ns = 10000;
 	else
 		vc->halt_poll_ns *= halt_poll_ns_grow;
-
-	if (vc->halt_poll_ns > halt_poll_max_ns)
-		vc->halt_poll_ns = halt_poll_max_ns;
 }
 
 static void shrink_halt_poll_ns(struct kvmppc_vcore *vc)
@@ -2558,7 +2611,8 @@ static void shrink_halt_poll_ns(struct kvmppc_vcore *vc)
 		vc->halt_poll_ns /= halt_poll_ns_shrink;
 }
 
-/* Check to see if any of the runnable vcpus on the vcore have pending
+/*
+ * Check to see if any of the runnable vcpus on the vcore have pending
  * exceptions or are no longer ceded
  */
 static int kvmppc_vcore_check_block(struct kvmppc_vcore *vc)
@@ -2657,16 +2711,18 @@ out:
 	}
 
 	/* Adjust poll time */
-	if (halt_poll_max_ns) {
+	if (halt_poll_ns) {
 		if (block_ns <= vc->halt_poll_ns)
 			;
 		/* We slept and blocked for longer than the max halt time */
-		else if (vc->halt_poll_ns && block_ns > halt_poll_max_ns)
+		else if (vc->halt_poll_ns && block_ns > halt_poll_ns)
 			shrink_halt_poll_ns(vc);
 		/* We slept and our poll time is too small */
-		else if (vc->halt_poll_ns < halt_poll_max_ns &&
-				block_ns < halt_poll_max_ns)
+		else if (vc->halt_poll_ns < halt_poll_ns &&
+				block_ns < halt_poll_ns)
 			grow_halt_poll_ns(vc);
+		if (vc->halt_poll_ns > halt_poll_ns)
+			vc->halt_poll_ns = halt_poll_ns;
 	} else
 		vc->halt_poll_ns = 0;
 
@@ -2973,6 +3029,15 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 
+	/*
+	 * If we are making a new memslot, it might make
+	 * some address that was previously cached as emulated
+	 * MMIO be no longer emulated MMIO, so invalidate
+	 * all the caches of emulated MMIO translations.
+	 */
+	if (npages)
+		atomic64_inc(&kvm->arch.mmio_update);
+
 	if (npages && old->npages) {
 		/*
 		 * If modifying a memslot, reset all the rmap dirty bits.
@@ -3017,6 +3082,22 @@ static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu)
 	return;
 }
 
+static void kvmppc_setup_partition_table(struct kvm *kvm)
+{
+	unsigned long dw0, dw1;
+
+	/* PS field - page size for VRMA */
+	dw0 = ((kvm->arch.vrma_slb_v & SLB_VSID_L) >> 1) |
+		((kvm->arch.vrma_slb_v & SLB_VSID_LP) << 1);
+	/* HTABSIZE and HTABORG fields */
+	dw0 |= kvm->arch.sdr1;
+
+	/* Second dword has GR=0; other fields are unused since UPRT=0 */
+	dw1 = 0;
+
+	mmu_partition_table_set_entry(kvm->arch.lpid, dw0, dw1);
+}
+
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 {
 	int err = 0;
@@ -3068,17 +3149,20 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	      psize == 0x1000000))
 		goto out_srcu;
 
-	/* Update VRMASD field in the LPCR */
 	senc = slb_pgsize_encoding(psize);
 	kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
 		(VRMA_VSID << SLB_VSID_SHIFT_1T);
-	/* the -4 is to account for senc values starting at 0x10 */
-	lpcr = senc << (LPCR_VRMASD_SH - 4);
-
 	/* Create HPTEs in the hash page table for the VRMA */
 	kvmppc_map_vrma(vcpu, memslot, porder);
 
-	kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
+	/* Update VRMASD field in the LPCR */
+	if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+		/* the -4 is to account for senc values starting at 0x10 */
+		lpcr = senc << (LPCR_VRMASD_SH - 4);
+		kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
+	} else {
+		kvmppc_setup_partition_table(kvm);
+	}
 
 	/* Order updates to kvm->arch.lpcr etc. vs. hpte_setup_done */
 	smp_wmb();
@@ -3193,14 +3277,18 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 	 * Since we don't flush the TLB when tearing down a VM,
 	 * and this lpid might have previously been used,
 	 * make sure we flush on each core before running the new VM.
+	 * On POWER9, the tlbie in mmu_partition_table_set_entry()
+	 * does this flush for us.
 	 */
-	cpumask_setall(&kvm->arch.need_tlb_flush);
+	if (!cpu_has_feature(CPU_FTR_ARCH_300))
+		cpumask_setall(&kvm->arch.need_tlb_flush);
 
 	/* Start out with the default set of hcalls enabled */
 	memcpy(kvm->arch.enabled_hcalls, default_enabled_hcalls,
 	       sizeof(kvm->arch.enabled_hcalls));
 
-	kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
+	if (!cpu_has_feature(CPU_FTR_ARCH_300))
+		kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
 
 	/* Init LPCR for virtual RMA mode */
 	kvm->arch.host_lpid = mfspr(SPRN_LPID);
@@ -3213,8 +3301,28 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 	/* On POWER8 turn on online bit to enable PURR/SPURR */
 	if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		lpcr |= LPCR_ONL;
+	/*
+	 * On POWER9, VPM0 bit is reserved (VPM0=1 behaviour is assumed)
+	 * Set HVICE bit to enable hypervisor virtualization interrupts.
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		lpcr &= ~LPCR_VPM0;
+		lpcr |= LPCR_HVICE;
+	}
+
 	kvm->arch.lpcr = lpcr;
 
+	/*
+	 * Work out how many sets the TLB has, for the use of
+	 * the TLB invalidation loop in book3s_hv_rmhandlers.S.
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		kvm->arch.tlb_sets = POWER9_TLB_SETS_HASH;	/* 256 */
+	else if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		kvm->arch.tlb_sets = POWER8_TLB_SETS;		/* 512 */
+	else
+		kvm->arch.tlb_sets = POWER7_TLB_SETS;		/* 128 */
+
 	/*
 	 * Track that we now have a HV mode VM active. This blocks secondary
 	 * CPU threads from coming online.
@@ -3279,9 +3387,9 @@ static int kvmppc_core_check_processor_compat_hv(void)
 	    !cpu_has_feature(CPU_FTR_ARCH_206))
 		return -EIO;
 	/*
-	 * Disable KVM for Power9, untill the required bits merged.
+	 * Disable KVM for Power9 in radix mode.
 	 */
-	if (cpu_has_feature(CPU_FTR_ARCH_300))
+	if (cpu_has_feature(CPU_FTR_ARCH_300) && radix_enabled())
 		return -EIO;
 
 	return 0;
@@ -3635,6 +3743,23 @@ static int kvmppc_book3s_init_hv(void)
 	if (r)
 		return r;
 
+	/*
+	 * We need a way of accessing the XICS interrupt controller,
+	 * either directly, via paca[cpu].kvm_hstate.xics_phys, or
+	 * indirectly, via OPAL.
+	 */
+#ifdef CONFIG_SMP
+	if (!get_paca()->kvm_hstate.xics_phys) {
+		struct device_node *np;
+
+		np = of_find_compatible_node(NULL, NULL, "ibm,opal-intc");
+		if (!np) {
+			pr_err("KVM-HV: Cannot determine method for accessing XICS\n");
+			return -ENODEV;
+		}
+	}
+#endif
+
 	kvm_ops_hv.owner = THIS_MODULE;
 	kvmppc_hv_ops = &kvm_ops_hv;
 
@@ -3657,3 +3782,4 @@ module_exit(kvmppc_book3s_exit_hv);
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_MISCDEV(KVM_MINOR);
 MODULE_ALIAS("devname:kvm");
+

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -26,6 +26,8 @@
 #include <asm/dbell.h>
 #include <asm/cputhreads.h>
 #include <asm/io.h>
+#include <asm/opal.h>
+#include <asm/smp.h>
 
 #define KVM_CMA_CHUNK_ORDER	18
 
@@ -205,12 +207,18 @@ static inline void rm_writeb(unsigned long paddr, u8 val)
 void kvmhv_rm_send_ipi(int cpu)
 {
 	unsigned long xics_phys;
+	unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 
-	/* On POWER8 for IPIs to threads in the same core, use msgsnd */
+	/* On POWER9 we can use msgsnd for any destination cpu. */
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		msg |= get_hard_smp_processor_id(cpu);
+		__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+		return;
+	}
+	/* On POWER8 for IPIs to threads in the same core, use msgsnd. */
 	if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
 	    cpu_first_thread_sibling(cpu) ==
 	    cpu_first_thread_sibling(raw_smp_processor_id())) {
-		unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 		msg |= cpu_thread_in_core(cpu);
 		__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
 		return;
@@ -218,7 +226,11 @@ void kvmhv_rm_send_ipi(int cpu)
 
 	/* Else poke the target with an IPI */
 	xics_phys = paca[cpu].kvm_hstate.xics_phys;
-	rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
+	if (xics_phys)
+		rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
+	else
+		opal_rm_int_set_mfrr(get_hard_smp_processor_id(cpu),
+				     IPI_PRIORITY);
 }
 
 /*
@@ -329,7 +341,7 @@ static struct kvmppc_irq_map *get_irqmap(struct kvmppc_passthru_irqmap *pimap,
  * saved a copy of the XIRR in the PACA, it will be picked up by
  * the host ICP driver.
  */
-static int kvmppc_check_passthru(u32 xisr, __be32 xirr)
+static int kvmppc_check_passthru(u32 xisr, __be32 xirr, bool *again)
 {
 	struct kvmppc_passthru_irqmap *pimap;
 	struct kvmppc_irq_map *irq_map;
@@ -348,11 +360,11 @@ static int kvmppc_check_passthru(u32 xisr, __be32 xirr)
 	/* We're handling this interrupt, generic code doesn't need to */
 	local_paca->kvm_hstate.saved_xirr = 0;
 
-	return kvmppc_deliver_irq_passthru(vcpu, xirr, irq_map, pimap);
+	return kvmppc_deliver_irq_passthru(vcpu, xirr, irq_map, pimap, again);
 }
 
 #else
-static inline int kvmppc_check_passthru(u32 xisr, __be32 xirr)
+static inline int kvmppc_check_passthru(u32 xisr, __be32 xirr, bool *again)
 {
 	return 1;
 }
@@ -367,14 +379,31 @@ static inline int kvmppc_check_passthru(u32 xisr, __be32 xirr)
  *	-1 if there was a guest wakeup IPI (which has now been cleared)
  *	-2 if there is PCI passthrough external interrupt that was handled
  */
+static long kvmppc_read_one_intr(bool *again);
 
 long kvmppc_read_intr(void)
+{
+	long ret = 0;
+	long rc;
+	bool again;
+
+	do {
+		again = false;
+		rc = kvmppc_read_one_intr(&again);
+		if (rc && (ret == 0 || rc > ret))
+			ret = rc;
+	} while (again);
+	return ret;
+}
+
+static long kvmppc_read_one_intr(bool *again)
 {
 	unsigned long xics_phys;
 	u32 h_xirr;
 	__be32 xirr;
 	u32 xisr;
 	u8 host_ipi;
+	int64_t rc;
 
 	/* see if a host IPI is pending */
 	host_ipi = local_paca->kvm_hstate.host_ipi;
@@ -383,8 +412,14 @@ long kvmppc_read_intr(void)
 
 	/* Now read the interrupt from the ICP */
 	xics_phys = local_paca->kvm_hstate.xics_phys;
-	if (unlikely(!xics_phys))
-		return 1;
+	if (!xics_phys) {
+		/* Use OPAL to read the XIRR */
+		rc = opal_rm_int_get_xirr(&xirr, false);
+		if (rc < 0)
+			return 1;
+	} else {
+		xirr = _lwzcix(xics_phys + XICS_XIRR);
+	}
 
 	/*
 	 * Save XIRR for later. Since we get control in reverse endian
@@ -392,7 +427,6 @@ long kvmppc_read_intr(void)
 	 * host endian. Note that xirr is the value read from the
 	 * XIRR register, while h_xirr is the host endian version.
 	 */
-	xirr = _lwzcix(xics_phys + XICS_XIRR);
 	h_xirr = be32_to_cpu(xirr);
 	local_paca->kvm_hstate.saved_xirr = h_xirr;
 	xisr = h_xirr & 0xffffff;
@@ -411,8 +445,16 @@ long kvmppc_read_intr(void)
 	 * If it is an IPI, clear the MFRR and EOI it.
 	 */
 	if (xisr == XICS_IPI) {
-		_stbcix(xics_phys + XICS_MFRR, 0xff);
-		_stwcix(xics_phys + XICS_XIRR, xirr);
+		if (xics_phys) {
+			_stbcix(xics_phys + XICS_MFRR, 0xff);
+			_stwcix(xics_phys + XICS_XIRR, xirr);
+		} else {
+			opal_rm_int_set_mfrr(hard_smp_processor_id(), 0xff);
+			rc = opal_rm_int_eoi(h_xirr);
+			/* If rc > 0, there is another interrupt pending */
+			*again = rc > 0;
+		}
+
 		/*
 		 * Need to ensure side effects of above stores
 		 * complete before proceeding.
@@ -429,7 +471,11 @@ long kvmppc_read_intr(void)
 			/* We raced with the host,
 			 * we need to resend that IPI, bummer
 			 */
-			_stbcix(xics_phys + XICS_MFRR, IPI_PRIORITY);
+			if (xics_phys)
+				_stbcix(xics_phys + XICS_MFRR, IPI_PRIORITY);
+			else
+				opal_rm_int_set_mfrr(hard_smp_processor_id(),
+						     IPI_PRIORITY);
 			/* Let side effects complete */
 			smp_mb();
 			return 1;
@@ -440,5 +486,5 @@ long kvmppc_read_intr(void)
 		return -1;
 	}
 
-	return kvmppc_check_passthru(xisr, xirr);
+	return kvmppc_check_passthru(xisr, xirr, again);
 }

arch/powerpc/kvm/book3s_hv_ras.c

@@ -16,6 +16,7 @@
 #include <asm/machdep.h>
 #include <asm/cputhreads.h>
 #include <asm/hmi.h>
+#include <asm/kvm_ppc.h>
 
 /* SRR1 bits for machine check on POWER7 */
 #define SRR1_MC_LDSTERR		(1ul << (63-42))

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -264,8 +264,10 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 
 	if (pa)
 		pteh |= HPTE_V_VALID;
-	else
+	else {
 		pteh |= HPTE_V_ABSENT;
+		ptel &= ~(HPTE_R_KEY_HI | HPTE_R_KEY_LO);
+	}
 
 	/*If we had host pte mapping then  Check WIMG */
 	if (ptep && !hpte_cache_flags_ok(ptel, is_ci)) {
@@ -351,6 +353,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 			/* inval in progress, write a non-present HPTE */
 			pteh |= HPTE_V_ABSENT;
 			pteh &= ~HPTE_V_VALID;
+			ptel &= ~(HPTE_R_KEY_HI | HPTE_R_KEY_LO);
 			unlock_rmap(rmap);
 		} else {
 			kvmppc_add_revmap_chain(kvm, rev, rmap, pte_index,
@@ -361,6 +364,11 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		}
 	}
 
+	/* Convert to new format on P9 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		ptel = hpte_old_to_new_r(pteh, ptel);
+		pteh = hpte_old_to_new_v(pteh);
+	}
 	hpte[1] = cpu_to_be64(ptel);
 
 	/* Write the first HPTE dword, unlocking the HPTE and making it valid */
@@ -386,6 +394,13 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 #define LOCK_TOKEN	(*(u32 *)(&get_paca()->paca_index))
 #endif
 
+static inline int is_mmio_hpte(unsigned long v, unsigned long r)
+{
+	return ((v & HPTE_V_ABSENT) &&
+		(r & (HPTE_R_KEY_HI | HPTE_R_KEY_LO)) ==
+		(HPTE_R_KEY_HI | HPTE_R_KEY_LO));
+}
+
 static inline int try_lock_tlbie(unsigned int *lock)
 {
 	unsigned int tmp, old;
@@ -409,13 +424,18 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
 {
 	long i;
 
+	/*
+	 * We use the POWER9 5-operand versions of tlbie and tlbiel here.
+	 * Since we are using RIC=0 PRS=0 R=0, and P7/P8 tlbiel ignores
+	 * the RS field, this is backwards-compatible with P7 and P8.
+	 */
 	if (global) {
 		while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
 			cpu_relax();
 		if (need_sync)
 			asm volatile("ptesync" : : : "memory");
 		for (i = 0; i < npages; ++i)
-			asm volatile(PPC_TLBIE(%1,%0) : :
+			asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
 				     "r" (rbvalues[i]), "r" (kvm->arch.lpid));
 		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 		kvm->arch.tlbie_lock = 0;
@@ -423,7 +443,8 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
 		if (need_sync)
 			asm volatile("ptesync" : : : "memory");
 		for (i = 0; i < npages; ++i)
-			asm volatile("tlbiel %0" : : "r" (rbvalues[i]));
+			asm volatile(PPC_TLBIEL(%0,%1,0,0,0) : :
+				     "r" (rbvalues[i]), "r" (0));
 		asm volatile("ptesync" : : : "memory");
 	}
 }
@@ -435,18 +456,23 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 	__be64 *hpte;
 	unsigned long v, r, rb;
 	struct revmap_entry *rev;
-	u64 pte;
+	u64 pte, orig_pte, pte_r;
 
 	if (pte_index >= kvm->arch.hpt_npte)
 		return H_PARAMETER;
 	hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4));
 	while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
 		cpu_relax();
-	pte = be64_to_cpu(hpte[0]);
+	pte = orig_pte = be64_to_cpu(hpte[0]);
+	pte_r = be64_to_cpu(hpte[1]);
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		pte = hpte_new_to_old_v(pte, pte_r);
+		pte_r = hpte_new_to_old_r(pte_r);
+	}
 	if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
 	    ((flags & H_AVPN) && (pte & ~0x7fUL) != avpn) ||
 	    ((flags & H_ANDCOND) && (pte & avpn) != 0)) {
-		__unlock_hpte(hpte, pte);
+		__unlock_hpte(hpte, orig_pte);
 		return H_NOT_FOUND;
 	}
 
@@ -454,7 +480,7 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 	v = pte & ~HPTE_V_HVLOCK;
 	if (v & HPTE_V_VALID) {
 		hpte[0] &= ~cpu_to_be64(HPTE_V_VALID);
-		rb = compute_tlbie_rb(v, be64_to_cpu(hpte[1]), pte_index);
+		rb = compute_tlbie_rb(v, pte_r, pte_index);
 		do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true);
 		/*
 		 * The reference (R) and change (C) bits in a HPT
@@ -472,6 +498,9 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 	note_hpte_modification(kvm, rev);
 	unlock_hpte(hpte, 0);
 
+	if (is_mmio_hpte(v, pte_r))
+		atomic64_inc(&kvm->arch.mmio_update);
+
 	if (v & HPTE_V_ABSENT)
 		v = (v & ~HPTE_V_ABSENT) | HPTE_V_VALID;
 	hpret[0] = v;
@@ -498,7 +527,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 	int global;
 	long int ret = H_SUCCESS;
 	struct revmap_entry *rev, *revs[4];
-	u64 hp0;
+	u64 hp0, hp1;
 
 	global = global_invalidates(kvm, 0);
 	for (i = 0; i < 4 && ret == H_SUCCESS; ) {
@@ -531,6 +560,11 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 			}
 			found = 0;
 			hp0 = be64_to_cpu(hp[0]);
+			hp1 = be64_to_cpu(hp[1]);
+			if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+				hp0 = hpte_new_to_old_v(hp0, hp1);
+				hp1 = hpte_new_to_old_r(hp1);
+			}
 			if (hp0 & (HPTE_V_ABSENT | HPTE_V_VALID)) {
 				switch (flags & 3) {
 				case 0:		/* absolute */
@@ -561,13 +595,14 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 				rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C);
 				args[j] |= rcbits << (56 - 5);
 				hp[0] = 0;
+				if (is_mmio_hpte(hp0, hp1))
+					atomic64_inc(&kvm->arch.mmio_update);
 				continue;
 			}
 
 			/* leave it locked */
 			hp[0] &= ~cpu_to_be64(HPTE_V_VALID);
-			tlbrb[n] = compute_tlbie_rb(be64_to_cpu(hp[0]),
-				be64_to_cpu(hp[1]), pte_index);
+			tlbrb[n] = compute_tlbie_rb(hp0, hp1, pte_index);
 			indexes[n] = j;
 			hptes[n] = hp;
 			revs[n] = rev;
@@ -605,7 +640,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 	__be64 *hpte;
 	struct revmap_entry *rev;
 	unsigned long v, r, rb, mask, bits;
-	u64 pte;
+	u64 pte_v, pte_r;
 
 	if (pte_index >= kvm->arch.hpt_npte)
 		return H_PARAMETER;
@@ -613,14 +648,16 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 	hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4));
 	while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
 		cpu_relax();
-	pte = be64_to_cpu(hpte[0]);
-	if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
-	    ((flags & H_AVPN) && (pte & ~0x7fUL) != avpn)) {
-		__unlock_hpte(hpte, pte);
+	v = pte_v = be64_to_cpu(hpte[0]);
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		v = hpte_new_to_old_v(v, be64_to_cpu(hpte[1]));
+	if ((v & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
+	    ((flags & H_AVPN) && (v & ~0x7fUL) != avpn)) {
+		__unlock_hpte(hpte, pte_v);
 		return H_NOT_FOUND;
 	}
 
-	v = pte;
+	pte_r = be64_to_cpu(hpte[1]);
 	bits = (flags << 55) & HPTE_R_PP0;
 	bits |= (flags << 48) & HPTE_R_KEY_HI;
 	bits |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO);
@@ -642,22 +679,26 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 		 * readonly to writable.  If it should be writable, we'll
 		 * take a trap and let the page fault code sort it out.
 		 */
-		pte = be64_to_cpu(hpte[1]);
-		r = (pte & ~mask) | bits;
-		if (hpte_is_writable(r) && !hpte_is_writable(pte))
+		r = (pte_r & ~mask) | bits;
+		if (hpte_is_writable(r) && !hpte_is_writable(pte_r))
 			r = hpte_make_readonly(r);
 		/* If the PTE is changing, invalidate it first */
-		if (r != pte) {
+		if (r != pte_r) {
 			rb = compute_tlbie_rb(v, r, pte_index);
-			hpte[0] = cpu_to_be64((v & ~HPTE_V_VALID) |
+			hpte[0] = cpu_to_be64((pte_v & ~HPTE_V_VALID) |
 					      HPTE_V_ABSENT);
 			do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags),
 				  true);
+			/* Don't lose R/C bit updates done by hardware */
+			r |= be64_to_cpu(hpte[1]) & (HPTE_R_R | HPTE_R_C);
 			hpte[1] = cpu_to_be64(r);
 		}
 	}
-	unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
+	unlock_hpte(hpte, pte_v & ~HPTE_V_HVLOCK);
 	asm volatile("ptesync" : : : "memory");
+	if (is_mmio_hpte(v, pte_r))
+		atomic64_inc(&kvm->arch.mmio_update);
+
 	return H_SUCCESS;
 }
 
@@ -681,6 +722,10 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
 		hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4));
 		v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK;
 		r = be64_to_cpu(hpte[1]);
+		if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+			v = hpte_new_to_old_v(v, r);
+			r = hpte_new_to_old_r(r);
+		}
 		if (v & HPTE_V_ABSENT) {
 			v &= ~HPTE_V_ABSENT;
 			v |= HPTE_V_VALID;
@@ -798,10 +843,16 @@ void kvmppc_invalidate_hpte(struct kvm *kvm, __be64 *hptep,
 			unsigned long pte_index)
 {
 	unsigned long rb;
+	u64 hp0, hp1;
 
 	hptep[0] &= ~cpu_to_be64(HPTE_V_VALID);
-	rb = compute_tlbie_rb(be64_to_cpu(hptep[0]), be64_to_cpu(hptep[1]),
-			      pte_index);
+	hp0 = be64_to_cpu(hptep[0]);
+	hp1 = be64_to_cpu(hptep[1]);
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		hp0 = hpte_new_to_old_v(hp0, hp1);
+		hp1 = hpte_new_to_old_r(hp1);
+	}
+	rb = compute_tlbie_rb(hp0, hp1, pte_index);
 	do_tlbies(kvm, &rb, 1, 1, true);
 }
 EXPORT_SYMBOL_GPL(kvmppc_invalidate_hpte);
@@ -811,9 +862,15 @@ void kvmppc_clear_ref_hpte(struct kvm *kvm, __be64 *hptep,
 {
 	unsigned long rb;
 	unsigned char rbyte;
+	u64 hp0, hp1;
 
-	rb = compute_tlbie_rb(be64_to_cpu(hptep[0]), be64_to_cpu(hptep[1]),
-			      pte_index);
+	hp0 = be64_to_cpu(hptep[0]);
+	hp1 = be64_to_cpu(hptep[1]);
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		hp0 = hpte_new_to_old_v(hp0, hp1);
+		hp1 = hpte_new_to_old_r(hp1);
+	}
+	rb = compute_tlbie_rb(hp0, hp1, pte_index);
 	rbyte = (be64_to_cpu(hptep[1]) & ~HPTE_R_R) >> 8;
 	/* modify only the second-last byte, which contains the ref bit */
 	*((char *)hptep + 14) = rbyte;
@@ -828,6 +885,37 @@ static int slb_base_page_shift[4] = {
 	20,	/* 1M, unsupported */
 };
 
+static struct mmio_hpte_cache_entry *mmio_cache_search(struct kvm_vcpu *vcpu,
+		unsigned long eaddr, unsigned long slb_v, long mmio_update)
+{
+	struct mmio_hpte_cache_entry *entry = NULL;
+	unsigned int pshift;
+	unsigned int i;
+
+	for (i = 0; i < MMIO_HPTE_CACHE_SIZE; i++) {
+		entry = &vcpu->arch.mmio_cache.entry[i];
+		if (entry->mmio_update == mmio_update) {
+			pshift = entry->slb_base_pshift;
+			if ((entry->eaddr >> pshift) == (eaddr >> pshift) &&
+			    entry->slb_v == slb_v)
+				return entry;
+		}
+	}
+	return NULL;
+}
+
+static struct mmio_hpte_cache_entry *
+			next_mmio_cache_entry(struct kvm_vcpu *vcpu)
+{
+	unsigned int index = vcpu->arch.mmio_cache.index;
+
+	vcpu->arch.mmio_cache.index++;
+	if (vcpu->arch.mmio_cache.index == MMIO_HPTE_CACHE_SIZE)
+		vcpu->arch.mmio_cache.index = 0;
+
+	return &vcpu->arch.mmio_cache.entry[index];
+}
+
 /* When called from virtmode, this func should be protected by
  * preempt_disable(), otherwise, the holding of HPTE_V_HVLOCK
  * can trigger deadlock issue.
@@ -842,7 +930,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 	unsigned long avpn;
 	__be64 *hpte;
 	unsigned long mask, val;
-	unsigned long v, r;
+	unsigned long v, r, orig_v;
 
 	/* Get page shift, work out hash and AVPN etc. */
 	mask = SLB_VSID_B | HPTE_V_AVPN | HPTE_V_SECONDARY;
@@ -877,6 +965,8 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 		for (i = 0; i < 16; i += 2) {
 			/* Read the PTE racily */
 			v = be64_to_cpu(hpte[i]) & ~HPTE_V_HVLOCK;
+			if (cpu_has_feature(CPU_FTR_ARCH_300))
+				v = hpte_new_to_old_v(v, be64_to_cpu(hpte[i+1]));
 
 			/* Check valid/absent, hash, segment size and AVPN */
 			if (!(v & valid) || (v & mask) != val)
@@ -885,8 +975,12 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 			/* Lock the PTE and read it under the lock */
 			while (!try_lock_hpte(&hpte[i], HPTE_V_HVLOCK))
 				cpu_relax();
-			v = be64_to_cpu(hpte[i]) & ~HPTE_V_HVLOCK;
+			v = orig_v = be64_to_cpu(hpte[i]) & ~HPTE_V_HVLOCK;
 			r = be64_to_cpu(hpte[i+1]);
+			if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+				v = hpte_new_to_old_v(v, r);
+				r = hpte_new_to_old_r(r);
+			}
 
 			/*
 			 * Check the HPTE again, including base page size
@@ -896,7 +990,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 				/* Return with the HPTE still locked */
 				return (hash << 3) + (i >> 1);
 
-			__unlock_hpte(&hpte[i], v);
+			__unlock_hpte(&hpte[i], orig_v);
 		}
 
 		if (val & HPTE_V_SECONDARY)
@@ -924,30 +1018,45 @@ long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
 {
 	struct kvm *kvm = vcpu->kvm;
 	long int index;
-	unsigned long v, r, gr;
+	unsigned long v, r, gr, orig_v;
 	__be64 *hpte;
 	unsigned long valid;
 	struct revmap_entry *rev;
 	unsigned long pp, key;
+	struct mmio_hpte_cache_entry *cache_entry = NULL;
+	long mmio_update = 0;
 
 	/* For protection fault, expect to find a valid HPTE */
 	valid = HPTE_V_VALID;
-	if (status & DSISR_NOHPTE)
+	if (status & DSISR_NOHPTE) {
 		valid |= HPTE_V_ABSENT;
-
-	index = kvmppc_hv_find_lock_hpte(kvm, addr, slb_v, valid);
-	if (index < 0) {
-		if (status & DSISR_NOHPTE)
-			return status;	/* there really was no HPTE */
-		return 0;		/* for prot fault, HPTE disappeared */
+		mmio_update = atomic64_read(&kvm->arch.mmio_update);
+		cache_entry = mmio_cache_search(vcpu, addr, slb_v, mmio_update);
 	}
-	hpte = (__be64 *)(kvm->arch.hpt_virt + (index << 4));
-	v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK;
-	r = be64_to_cpu(hpte[1]);
-	rev = real_vmalloc_addr(&kvm->arch.revmap[index]);
-	gr = rev->guest_rpte;
+	if (cache_entry) {
+		index = cache_entry->pte_index;
+		v = cache_entry->hpte_v;
+		r = cache_entry->hpte_r;
+		gr = cache_entry->rpte;
+	} else {
+		index = kvmppc_hv_find_lock_hpte(kvm, addr, slb_v, valid);
+		if (index < 0) {
+			if (status & DSISR_NOHPTE)
+				return status;	/* there really was no HPTE */
+			return 0;	/* for prot fault, HPTE disappeared */
+		}
+		hpte = (__be64 *)(kvm->arch.hpt_virt + (index << 4));
+		v = orig_v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK;
+		r = be64_to_cpu(hpte[1]);
+		if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+			v = hpte_new_to_old_v(v, r);
+			r = hpte_new_to_old_r(r);
+		}
+		rev = real_vmalloc_addr(&kvm->arch.revmap[index]);
+		gr = rev->guest_rpte;
 
-	unlock_hpte(hpte, v);
+		unlock_hpte(hpte, orig_v);
+	}
 
 	/* For not found, if the HPTE is valid by now, retry the instruction */
 	if ((status & DSISR_NOHPTE) && (v & HPTE_V_VALID))
@@ -985,12 +1094,32 @@ long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
 	vcpu->arch.pgfault_index = index;
 	vcpu->arch.pgfault_hpte[0] = v;
 	vcpu->arch.pgfault_hpte[1] = r;
+	vcpu->arch.pgfault_cache = cache_entry;
 
 	/* Check the storage key to see if it is possibly emulated MMIO */
-	if (data && (vcpu->arch.shregs.msr & MSR_IR) &&
-	    (r & (HPTE_R_KEY_HI | HPTE_R_KEY_LO)) ==
-	    (HPTE_R_KEY_HI | HPTE_R_KEY_LO))
-		return -2;	/* MMIO emulation - load instr word */
+	if ((r & (HPTE_R_KEY_HI | HPTE_R_KEY_LO)) ==
+	    (HPTE_R_KEY_HI | HPTE_R_KEY_LO)) {
+		if (!cache_entry) {
+			unsigned int pshift = 12;
+			unsigned int pshift_index;
+
+			if (slb_v & SLB_VSID_L) {
+				pshift_index = ((slb_v & SLB_VSID_LP) >> 4);
+				pshift = slb_base_page_shift[pshift_index];
+			}
+			cache_entry = next_mmio_cache_entry(vcpu);
+			cache_entry->eaddr = addr;
+			cache_entry->slb_base_pshift = pshift;
+			cache_entry->pte_index = index;
+			cache_entry->hpte_v = v;
+			cache_entry->hpte_r = r;
+			cache_entry->rpte = gr;
+			cache_entry->slb_v = slb_v;
+			cache_entry->mmio_update = mmio_update;
+		}
+		if (data && (vcpu->arch.shregs.msr & MSR_IR))
+			return -2;	/* MMIO emulation - load instr word */
+	}
 
 	return -1;		/* send fault up to host kernel mode */
 }

arch/powerpc/kvm/book3s_hv_rm_xics.c

@@ -70,7 +70,11 @@ static inline void icp_send_hcore_msg(int hcore, struct kvm_vcpu *vcpu)
 	hcpu = hcore << threads_shift;
 	kvmppc_host_rm_ops_hv->rm_core[hcore].rm_data = vcpu;
 	smp_muxed_ipi_set_message(hcpu, PPC_MSG_RM_HOST_ACTION);
-	icp_native_cause_ipi_rm(hcpu);
+	if (paca[hcpu].kvm_hstate.xics_phys)
+		icp_native_cause_ipi_rm(hcpu);
+	else
+		opal_rm_int_set_mfrr(get_hard_smp_processor_id(hcpu),
+				     IPI_PRIORITY);
 }
 #else
 static inline void icp_send_hcore_msg(int hcore, struct kvm_vcpu *vcpu) { }
@@ -737,7 +741,7 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
 
 unsigned long eoi_rc;
 
-static void icp_eoi(struct irq_chip *c, u32 hwirq, u32 xirr)
+static void icp_eoi(struct irq_chip *c, u32 hwirq, __be32 xirr, bool *again)
 {
 	unsigned long xics_phys;
 	int64_t rc;
@@ -751,7 +755,12 @@ static void icp_eoi(struct irq_chip *c, u32 hwirq, u32 xirr)
 
 	/* EOI it */
 	xics_phys = local_paca->kvm_hstate.xics_phys;
-	_stwcix(xics_phys + XICS_XIRR, xirr);
+	if (xics_phys) {
+		_stwcix(xics_phys + XICS_XIRR, xirr);
+	} else {
+		rc = opal_rm_int_eoi(be32_to_cpu(xirr));
+		*again = rc > 0;
+	}
 }
 
 static int xics_opal_rm_set_server(unsigned int hw_irq, int server_cpu)
@@ -809,9 +818,10 @@ static void kvmppc_rm_handle_irq_desc(struct irq_desc *desc)
 }
 
 long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu,
-				 u32 xirr,
+				 __be32 xirr,
 				 struct kvmppc_irq_map *irq_map,
-				 struct kvmppc_passthru_irqmap *pimap)
+				 struct kvmppc_passthru_irqmap *pimap,
+				 bool *again)
 {
 	struct kvmppc_xics *xics;
 	struct kvmppc_icp *icp;
@@ -825,7 +835,8 @@ long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu,
 	icp_rm_deliver_irq(xics, icp, irq);
 
 	/* EOI the interrupt */
-	icp_eoi(irq_desc_get_chip(irq_map->desc), irq_map->r_hwirq, xirr);
+	icp_eoi(irq_desc_get_chip(irq_map->desc), irq_map->r_hwirq, xirr,
+		again);
 
 	if (check_too_hard(xics, icp) == H_TOO_HARD)
 		return 2;

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -501,17 +501,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	cmpwi	r0, 0
 	beq	57f
 	li	r3, (LPCR_PECEDH | LPCR_PECE0) >> 4
-	mfspr	r4, SPRN_LPCR
-	rlwimi	r4, r3, 4, (LPCR_PECEDP | LPCR_PECEDH | LPCR_PECE0 | LPCR_PECE1)
-	mtspr	SPRN_LPCR, r4
-	isync
-	std	r0, HSTATE_SCRATCH0(r13)
-	ptesync
-	ld	r0, HSTATE_SCRATCH0(r13)
-1:	cmpd	r0, r0
-	bne	1b
-	nap
-	b	.
+	mfspr	r5, SPRN_LPCR
+	rlwimi	r5, r3, 4, (LPCR_PECEDP | LPCR_PECEDH | LPCR_PECE0 | LPCR_PECE1)
+	b	kvm_nap_sequence
 
 57:	li	r0, 0
 	stbx	r0, r3, r4
@@ -523,6 +515,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
  *                                                                            *
  *****************************************************************************/
 
+/* Stack frame offsets */
+#define STACK_SLOT_TID		(112-16)
+#define STACK_SLOT_PSSCR	(112-24)
+
 .global kvmppc_hv_entry
 kvmppc_hv_entry:
 
@@ -581,12 +577,14 @@ kvmppc_hv_entry:
 	ld	r9,VCORE_KVM(r5)	/* pointer to struct kvm */
 	cmpwi	r6,0
 	bne	10f
-	ld	r6,KVM_SDR1(r9)
 	lwz	r7,KVM_LPID(r9)
+BEGIN_FTR_SECTION
+	ld	r6,KVM_SDR1(r9)
 	li	r0,LPID_RSVD		/* switch to reserved LPID */
 	mtspr	SPRN_LPID,r0
 	ptesync
 	mtspr	SPRN_SDR1,r6		/* switch to partition page table */
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPID,r7
 	isync
 
@@ -607,12 +605,8 @@ kvmppc_hv_entry:
 	stdcx.	r7,0,r6
 	bne	23b
 	/* Flush the TLB of any entries for this LPID */
-	/* use arch 2.07S as a proxy for POWER8 */
-BEGIN_FTR_SECTION
-	li	r6,512			/* POWER8 has 512 sets */
-FTR_SECTION_ELSE
-	li	r6,128			/* POWER7 has 128 sets */
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_207S)
+	lwz	r6,KVM_TLB_SETS(r9)
+	li	r0,0			/* RS for P9 version of tlbiel */
 	mtctr	r6
 	li	r7,0x800		/* IS field = 0b10 */
 	ptesync
@@ -698,6 +692,14 @@ kvmppc_got_guest:
 	mtspr	SPRN_PURR,r7
 	mtspr	SPRN_SPURR,r8
 
+	/* Save host values of some registers */
+BEGIN_FTR_SECTION
+	mfspr	r5, SPRN_TIDR
+	mfspr	r6, SPRN_PSSCR
+	std	r5, STACK_SLOT_TID(r1)
+	std	r6, STACK_SLOT_PSSCR(r1)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
 BEGIN_FTR_SECTION
 	/* Set partition DABR */
 	/* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
@@ -750,14 +752,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
 BEGIN_FTR_SECTION
 	ld	r5, VCPU_MMCR + 24(r4)
 	ld	r6, VCPU_SIER(r4)
+	mtspr	SPRN_MMCR2, r5
+	mtspr	SPRN_SIER, r6
+BEGIN_FTR_SECTION_NESTED(96)
 	lwz	r7, VCPU_PMC + 24(r4)
 	lwz	r8, VCPU_PMC + 28(r4)
 	ld	r9, VCPU_MMCR + 32(r4)
-	mtspr	SPRN_MMCR2, r5
-	mtspr	SPRN_SIER, r6
 	mtspr	SPRN_SPMC1, r7
 	mtspr	SPRN_SPMC2, r8
 	mtspr	SPRN_MMCRS, r9
+END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_MMCR0, r3
 	isync
@@ -813,20 +817,30 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_EBBHR, r8
 	ld	r5, VCPU_EBBRR(r4)
 	ld	r6, VCPU_BESCR(r4)
-	ld	r7, VCPU_CSIGR(r4)
-	ld	r8, VCPU_TACR(r4)
+	lwz	r7, VCPU_GUEST_PID(r4)
+	ld	r8, VCPU_WORT(r4)
 	mtspr	SPRN_EBBRR, r5
 	mtspr	SPRN_BESCR, r6
-	mtspr	SPRN_CSIGR, r7
-	mtspr	SPRN_TACR, r8
+	mtspr	SPRN_PID, r7
+	mtspr	SPRN_WORT, r8
+BEGIN_FTR_SECTION
+	/* POWER8-only registers */
 	ld	r5, VCPU_TCSCR(r4)
 	ld	r6, VCPU_ACOP(r4)
-	lwz	r7, VCPU_GUEST_PID(r4)
-	ld	r8, VCPU_WORT(r4)
+	ld	r7, VCPU_CSIGR(r4)
+	ld	r8, VCPU_TACR(r4)
 	mtspr	SPRN_TCSCR, r5
 	mtspr	SPRN_ACOP, r6
-	mtspr	SPRN_PID, r7
-	mtspr	SPRN_WORT, r8
+	mtspr	SPRN_CSIGR, r7
+	mtspr	SPRN_TACR, r8
+FTR_SECTION_ELSE
+	/* POWER9-only registers */
+	ld	r5, VCPU_TID(r4)
+	ld	r6, VCPU_PSSCR(r4)
+	oris	r6, r6, PSSCR_EC@h	/* This makes stop trap to HV */
+	mtspr	SPRN_TIDR, r5
+	mtspr	SPRN_PSSCR, r6
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 8:
 
 	/*
@@ -1341,20 +1355,29 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	std	r8, VCPU_EBBHR(r9)
 	mfspr	r5, SPRN_EBBRR
 	mfspr	r6, SPRN_BESCR
-	mfspr	r7, SPRN_CSIGR
-	mfspr	r8, SPRN_TACR
+	mfspr	r7, SPRN_PID
+	mfspr	r8, SPRN_WORT
 	std	r5, VCPU_EBBRR(r9)
 	std	r6, VCPU_BESCR(r9)
-	std	r7, VCPU_CSIGR(r9)
-	std	r8, VCPU_TACR(r9)
+	stw	r7, VCPU_GUEST_PID(r9)
+	std	r8, VCPU_WORT(r9)
+BEGIN_FTR_SECTION
 	mfspr	r5, SPRN_TCSCR
 	mfspr	r6, SPRN_ACOP
-	mfspr	r7, SPRN_PID
-	mfspr	r8, SPRN_WORT
+	mfspr	r7, SPRN_CSIGR
+	mfspr	r8, SPRN_TACR
 	std	r5, VCPU_TCSCR(r9)
 	std	r6, VCPU_ACOP(r9)
-	stw	r7, VCPU_GUEST_PID(r9)
-	std	r8, VCPU_WORT(r9)
+	std	r7, VCPU_CSIGR(r9)
+	std	r8, VCPU_TACR(r9)
+FTR_SECTION_ELSE
+	mfspr	r5, SPRN_TIDR
+	mfspr	r6, SPRN_PSSCR
+	std	r5, VCPU_TID(r9)
+	rldicl	r6, r6, 4, 50		/* r6 &= PSSCR_GUEST_VIS */
+	rotldi	r6, r6, 60
+	std	r6, VCPU_PSSCR(r9)
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	/*
 	 * Restore various registers to 0, where non-zero values
 	 * set by the guest could disrupt the host.
@@ -1363,12 +1386,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_IAMR, r0
 	mtspr	SPRN_CIABR, r0
 	mtspr	SPRN_DAWRX, r0
-	mtspr	SPRN_TCSCR, r0
 	mtspr	SPRN_WORT, r0
+BEGIN_FTR_SECTION
+	mtspr	SPRN_TCSCR, r0
 	/* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
 	li	r0, 1
 	sldi	r0, r0, 31
 	mtspr	SPRN_MMCRS, r0
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 8:
 
 	/* Save and reset AMR and UAMOR before turning on the MMU */
@@ -1502,15 +1527,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	stw	r8, VCPU_PMC + 20(r9)
 BEGIN_FTR_SECTION
 	mfspr	r5, SPRN_SIER
+	std	r5, VCPU_SIER(r9)
+BEGIN_FTR_SECTION_NESTED(96)
 	mfspr	r6, SPRN_SPMC1
 	mfspr	r7, SPRN_SPMC2
 	mfspr	r8, SPRN_MMCRS
-	std	r5, VCPU_SIER(r9)
 	stw	r6, VCPU_PMC + 24(r9)
 	stw	r7, VCPU_PMC + 28(r9)
 	std	r8, VCPU_MMCR + 32(r9)
 	lis	r4, 0x8000
 	mtspr	SPRN_MMCRS, r4
+END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 22:
 	/* Clear out SLB */
@@ -1519,6 +1546,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	slbia
 	ptesync
 
+	/* Restore host values of some registers */
+BEGIN_FTR_SECTION
+	ld	r5, STACK_SLOT_TID(r1)
+	ld	r6, STACK_SLOT_PSSCR(r1)
+	mtspr	SPRN_TIDR, r5
+	mtspr	SPRN_PSSCR, r6
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
 	/*
 	 * POWER7/POWER8 guest -> host partition switch code.
 	 * We don't have to lock against tlbies but we do
@@ -1552,12 +1587,14 @@ kvmhv_switch_to_host:
 	beq	19f
 
 	/* Primary thread switches back to host partition */
-	ld	r6,KVM_HOST_SDR1(r4)
 	lwz	r7,KVM_HOST_LPID(r4)
+BEGIN_FTR_SECTION
+	ld	r6,KVM_HOST_SDR1(r4)
 	li	r8,LPID_RSVD		/* switch to reserved LPID */
 	mtspr	SPRN_LPID,r8
 	ptesync
-	mtspr	SPRN_SDR1,r6		/* switch to partition page table */
+	mtspr	SPRN_SDR1,r6		/* switch to host page table */
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPID,r7
 	isync
 
@@ -2211,6 +2248,21 @@ BEGIN_FTR_SECTION
 	ori	r5, r5, LPCR_PECEDH
 	rlwimi	r5, r3, 0, LPCR_PECEDP
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
+kvm_nap_sequence:		/* desired LPCR value in r5 */
+BEGIN_FTR_SECTION
+	/*
+	 * PSSCR bits:	exit criterion = 1 (wakeup based on LPCR at sreset)
+	 *		enable state loss = 1 (allow SMT mode switch)
+	 *		requested level = 0 (just stop dispatching)
+	 */
+	lis	r3, (PSSCR_EC | PSSCR_ESL)@h
+	mtspr	SPRN_PSSCR, r3
+	/* Set LPCR_PECE_HVEE bit to enable wakeup by HV interrupts */
+	li	r4, LPCR_PECE_HVEE@higher
+	sldi	r4, r4, 32
+	or	r5, r5, r4
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPCR,r5
 	isync
 	li	r0, 0
@@ -2219,7 +2271,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	ld	r0, HSTATE_SCRATCH0(r13)
 1:	cmpd	r0, r0
 	bne	1b
+BEGIN_FTR_SECTION
 	nap
+FTR_SECTION_ELSE
+	PPC_STOP
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	b	.
 
 33:	mr	r4, r3
@@ -2600,11 +2656,13 @@ kvmppc_save_tm:
 	mfctr	r7
 	mfspr	r8, SPRN_AMR
 	mfspr	r10, SPRN_TAR
+	mfxer	r11
 	std	r5, VCPU_LR_TM(r9)
 	stw	r6, VCPU_CR_TM(r9)
 	std	r7, VCPU_CTR_TM(r9)
 	std	r8, VCPU_AMR_TM(r9)
 	std	r10, VCPU_TAR_TM(r9)
+	std	r11, VCPU_XER_TM(r9)
 
 	/* Restore r12 as trap number. */
 	lwz	r12, VCPU_TRAP(r9)
@@ -2697,11 +2755,13 @@ kvmppc_restore_tm:
 	ld	r7, VCPU_CTR_TM(r4)
 	ld	r8, VCPU_AMR_TM(r4)
 	ld	r9, VCPU_TAR_TM(r4)
+	ld	r10, VCPU_XER_TM(r4)
 	mtlr	r5
 	mtcr	r6
 	mtctr	r7
 	mtspr	SPRN_AMR, r8
 	mtspr	SPRN_TAR, r9
+	mtxer	r10
 
 	/*
 	 * Load up PPR and DSCR values but don't put them in the actual SPRs

arch/powerpc/kvm/powerpc.c

@@ -536,7 +536,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
 	case KVM_CAP_SPAPR_TCE_64:
-	case KVM_CAP_PPC_ALLOC_HTAB:
 	case KVM_CAP_PPC_RTAS:
 	case KVM_CAP_PPC_FIXUP_HCALL:
 	case KVM_CAP_PPC_ENABLE_HCALL:
@@ -545,13 +544,20 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #endif
 		r = 1;
 		break;
+
+	case KVM_CAP_PPC_ALLOC_HTAB:
+		r = hv_enabled;
+		break;
 #endif /* CONFIG_PPC_BOOK3S_64 */
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_SMT:
-		if (hv_enabled)
-			r = threads_per_subcore;
-		else
-			r = 0;
+		r = 0;
+		if (hv_enabled) {
+			if (cpu_has_feature(CPU_FTR_ARCH_300))
+				r = 1;
+			else
+				r = threads_per_subcore;
+		}
 		break;
 	case KVM_CAP_PPC_RMA:
 		r = 0;

arch/powerpc/kvm/trace_hv.h

@@ -449,7 +449,7 @@ TRACE_EVENT(kvmppc_vcore_wakeup,
 		__entry->tgid   = current->tgid;
 	),
 
-	TP_printk("%s time %lld ns, tgid=%d",
+	TP_printk("%s time %llu ns, tgid=%d",
 		__entry->waited ? "wait" : "poll",
 		__entry->ns, __entry->tgid)
 );

arch/powerpc/mm/hash_native_64.c

@@ -221,13 +221,18 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 		return -1;
 
 	hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
-	hpte_r = hpte_encode_r(pa, psize, apsize, ssize) | rflags;
+	hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
 
 	if (!(vflags & HPTE_V_BOLTED)) {
 		DBG_LOW(" i=%x hpte_v=%016lx, hpte_r=%016lx\n",
 			i, hpte_v, hpte_r);
 	}
 
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		hpte_r = hpte_old_to_new_r(hpte_v, hpte_r);
+		hpte_v = hpte_old_to_new_v(hpte_v);
+	}
+
 	hptep->r = cpu_to_be64(hpte_r);
 	/* Guarantee the second dword is visible before the valid bit */
 	eieio();
@@ -295,6 +300,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 		vpn, want_v & HPTE_V_AVPN, slot, newpp);
 
 	hpte_v = be64_to_cpu(hptep->v);
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));
 	/*
 	 * We need to invalidate the TLB always because hpte_remove doesn't do
 	 * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
@@ -309,6 +316,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 		native_lock_hpte(hptep);
 		/* recheck with locks held */
 		hpte_v = be64_to_cpu(hptep->v);
+		if (cpu_has_feature(CPU_FTR_ARCH_300))
+			hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));
 		if (unlikely(!HPTE_V_COMPARE(hpte_v, want_v) ||
 			     !(hpte_v & HPTE_V_VALID))) {
 			ret = -1;
@@ -350,6 +359,8 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize)
 	for (i = 0; i < HPTES_PER_GROUP; i++) {
 		hptep = htab_address + slot;
 		hpte_v = be64_to_cpu(hptep->v);
+		if (cpu_has_feature(CPU_FTR_ARCH_300))
+			hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));
 
 		if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID))
 			/* HPTE matches */
@@ -409,6 +420,8 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	want_v = hpte_encode_avpn(vpn, bpsize, ssize);
 	native_lock_hpte(hptep);
 	hpte_v = be64_to_cpu(hptep->v);
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));
 
 	/*
 	 * We need to invalidate the TLB always because hpte_remove doesn't do
@@ -467,6 +480,8 @@ static void native_hugepage_invalidate(unsigned long vsid,
 		want_v = hpte_encode_avpn(vpn, psize, ssize);
 		native_lock_hpte(hptep);
 		hpte_v = be64_to_cpu(hptep->v);
+		if (cpu_has_feature(CPU_FTR_ARCH_300))
+			hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));
 
 		/* Even if we miss, we need to invalidate the TLB */
 		if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
@@ -504,6 +519,10 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 	/* Look at the 8 bit LP value */
 	unsigned int lp = (hpte_r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
 
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		hpte_v = hpte_new_to_old_v(hpte_v, hpte_r);
+		hpte_r = hpte_new_to_old_r(hpte_r);
+	}
 	if (!(hpte_v & HPTE_V_LARGE)) {
 		size   = MMU_PAGE_4K;
 		a_size = MMU_PAGE_4K;
@@ -512,11 +531,7 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 		a_size = hpte_page_sizes[lp] >> 4;
 	}
 	/* This works for all page sizes, and for 256M and 1T segments */
-	if (cpu_has_feature(CPU_FTR_ARCH_300))
-		*ssize = hpte_r >> HPTE_R_3_0_SSIZE_SHIFT;
-	else
-		*ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
-
+	*ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
 	shift = mmu_psize_defs[size].shift;
 
 	avpn = (HPTE_V_AVPN_VAL(hpte_v) & ~mmu_psize_defs[size].avpnm);
@@ -639,6 +654,9 @@ static void native_flush_hash_range(unsigned long number, int local)
 			want_v = hpte_encode_avpn(vpn, psize, ssize);
 			native_lock_hpte(hptep);
 			hpte_v = be64_to_cpu(hptep->v);
+			if (cpu_has_feature(CPU_FTR_ARCH_300))
+				hpte_v = hpte_new_to_old_v(hpte_v,
+						be64_to_cpu(hptep->r));
 			if (!HPTE_V_COMPARE(hpte_v, want_v) ||
 			    !(hpte_v & HPTE_V_VALID))
 				native_unlock_hpte(hptep);

arch/powerpc/mm/hash_utils_64.c

@@ -796,37 +796,17 @@ static void update_hid_for_hash(void)
 static void __init hash_init_partition_table(phys_addr_t hash_table,
 					     unsigned long htab_size)
 {
-	unsigned long ps_field;
-	unsigned long patb_size = 1UL << PATB_SIZE_SHIFT;
+	mmu_partition_table_init();
 
 	/*
-	 * slb llp encoding for the page size used in VPM real mode.
-	 * We can ignore that for lpid 0
+	 * PS field (VRMA page size) is not used for LPID 0, hence set to 0.
+	 * For now, UPRT is 0 and we have no segment table.
 	 */
-	ps_field = 0;
 	htab_size =  __ilog2(htab_size) - 18;
-
-	BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 24), "Partition table size too large.");
-	partition_tb = __va(memblock_alloc_base(patb_size, patb_size,
-						MEMBLOCK_ALLOC_ANYWHERE));
-
-	/* Initialize the Partition Table with no entries */
-	memset((void *)partition_tb, 0, patb_size);
-	partition_tb->patb0 = cpu_to_be64(ps_field | hash_table | htab_size);
-	/*
-	 * FIXME!! This should be done via update_partition table
-	 * For now UPRT is 0 for us.
-	 */
-	partition_tb->patb1 = 0;
+	mmu_partition_table_set_entry(0, hash_table | htab_size, 0);
 	pr_info("Partition table %p\n", partition_tb);
 	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
 		update_hid_for_hash();
-	/*
-	 * update partition table control register,
-	 * 64 K size.
-	 */
-	mtspr(SPRN_PTCR, __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
-
 }
 
 static void __init htab_initialize(void)

arch/powerpc/mm/pgtable-radix.c

@@ -177,23 +177,15 @@ redo:
 
 static void __init radix_init_partition_table(void)
 {
-	unsigned long rts_field;
+	unsigned long rts_field, dw0;
 
+	mmu_partition_table_init();
 	rts_field = radix__get_tree_size();
+	dw0 = rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE | PATB_HR;
+	mmu_partition_table_set_entry(0, dw0, 0);
 
-	BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 24), "Partition table size too large.");
-	partition_tb = early_alloc_pgtable(1UL << PATB_SIZE_SHIFT);
-	partition_tb->patb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) |
-					  RADIX_PGD_INDEX_SIZE | PATB_HR);
 	pr_info("Initializing Radix MMU\n");
 	pr_info("Partition table %p\n", partition_tb);
-
-	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
-	/*
-	 * update partition table control register,
-	 * 64 K size.
-	 */
-	mtspr(SPRN_PTCR, __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
 }
 
 void __init radix_init_native(void)
@@ -378,6 +370,8 @@ void __init radix__early_init_mmu(void)
 		radix_init_partition_table();
 	}
 
+	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
+
 	radix_init_pgtable();
 }
 

arch/powerpc/mm/pgtable_64.c

@@ -431,3 +431,37 @@ void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
 	}
 }
 #endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+void __init mmu_partition_table_init(void)
+{
+	unsigned long patb_size = 1UL << PATB_SIZE_SHIFT;
+
+	BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 36), "Partition table size too large.");
+	partition_tb = __va(memblock_alloc_base(patb_size, patb_size,
+						MEMBLOCK_ALLOC_ANYWHERE));
+
+	/* Initialize the Partition Table with no entries */
+	memset((void *)partition_tb, 0, patb_size);
+
+	/*
+	 * update partition table control register,
+	 * 64 K size.
+	 */
+	mtspr(SPRN_PTCR, __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
+}
+
+void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
+				   unsigned long dw1)
+{
+	partition_tb[lpid].patb0 = cpu_to_be64(dw0);
+	partition_tb[lpid].patb1 = cpu_to_be64(dw1);
+
+	/* Global flush of TLBs and partition table caches for this lpid */
+	asm volatile("ptesync" : : : "memory");
+	asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : :
+		     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
+	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+}
+EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry);
+#endif /* CONFIG_PPC_BOOK3S_64 */

arch/powerpc/platforms/powernv/opal-wrappers.S

@@ -304,8 +304,11 @@ OPAL_CALL(opal_pci_get_presence_state,		OPAL_PCI_GET_PRESENCE_STATE);
 OPAL_CALL(opal_pci_get_power_state,		OPAL_PCI_GET_POWER_STATE);
 OPAL_CALL(opal_pci_set_power_state,		OPAL_PCI_SET_POWER_STATE);
 OPAL_CALL(opal_int_get_xirr,			OPAL_INT_GET_XIRR);
+OPAL_CALL_REAL(opal_rm_int_get_xirr,		OPAL_INT_GET_XIRR);
 OPAL_CALL(opal_int_set_cppr,			OPAL_INT_SET_CPPR);
 OPAL_CALL(opal_int_eoi,				OPAL_INT_EOI);
+OPAL_CALL_REAL(opal_rm_int_eoi,			OPAL_INT_EOI);
 OPAL_CALL(opal_int_set_mfrr,			OPAL_INT_SET_MFRR);
+OPAL_CALL_REAL(opal_rm_int_set_mfrr,		OPAL_INT_SET_MFRR);
 OPAL_CALL(opal_pci_tce_kill,			OPAL_PCI_TCE_KILL);
 OPAL_CALL_REAL(opal_rm_pci_tce_kill,		OPAL_PCI_TCE_KILL);

arch/powerpc/platforms/powernv/opal.c

@@ -896,3 +896,5 @@ EXPORT_SYMBOL_GPL(opal_leds_get_ind);
 EXPORT_SYMBOL_GPL(opal_leds_set_ind);
 /* Export this symbol for PowerNV Operator Panel class driver */
 EXPORT_SYMBOL_GPL(opal_write_oppanel_async);
+/* Export this for KVM */
+EXPORT_SYMBOL_GPL(opal_int_set_mfrr);

arch/powerpc/platforms/ps3/htab.c

@@ -63,7 +63,7 @@ static long ps3_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 	vflags &= ~HPTE_V_SECONDARY;
 
 	hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
-	hpte_r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize, apsize, ssize) | rflags;
+	hpte_r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize, apsize) | rflags;
 
 	spin_lock_irqsave(&ps3_htab_lock, flags);
 

arch/powerpc/platforms/pseries/lpar.c

@@ -145,7 +145,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 			 hpte_group, vpn,  pa, rflags, vflags, psize);
 
 	hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
-	hpte_r = hpte_encode_r(pa, psize, apsize, ssize) | rflags;
+	hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
 
 	if (!(vflags & HPTE_V_BOLTED))
 		pr_devel(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r);

arch/s390/kvm/interrupt.c

@@ -415,7 +415,7 @@ static int __write_machine_check(struct kvm_vcpu *vcpu,
 	int rc;
 
 	mci.val = mchk->mcic;
-	/* take care of lazy register loading via vcpu load/put */
+	/* take care of lazy register loading */
 	save_fpu_regs();
 	save_access_regs(vcpu->run->s.regs.acrs);
 

arch/s390/kvm/kvm-s390.c

@@ -1812,22 +1812,7 @@ __u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	/* Save host register state */
-	save_fpu_regs();
-	vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
-	vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
-
-	if (MACHINE_HAS_VX)
-		current->thread.fpu.regs = vcpu->run->s.regs.vrs;
-	else
-		current->thread.fpu.regs = vcpu->run->s.regs.fprs;
-	current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
-	if (test_fp_ctl(current->thread.fpu.fpc))
-		/* User space provided an invalid FPC, let's clear it */
-		current->thread.fpu.fpc = 0;
 
-	save_access_regs(vcpu->arch.host_acrs);
-	restore_access_regs(vcpu->run->s.regs.acrs);
 	gmap_enable(vcpu->arch.enabled_gmap);
 	atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
@@ -1844,16 +1829,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	vcpu->arch.enabled_gmap = gmap_get_enabled();
 	gmap_disable(vcpu->arch.enabled_gmap);
 
-	/* Save guest register state */
-	save_fpu_regs();
-	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
-
-	/* Restore host register state */
-	current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
-	current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
-
-	save_access_regs(vcpu->run->s.regs.acrs);
-	restore_access_regs(vcpu->arch.host_acrs);
 }
 
 static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
@@ -2243,7 +2218,6 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 {
 	memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
 	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
-	restore_access_regs(vcpu->run->s.regs.acrs);
 	return 0;
 }
 
@@ -2257,11 +2231,9 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	/* make sure the new values will be lazily loaded */
-	save_fpu_regs();
 	if (test_fp_ctl(fpu->fpc))
 		return -EINVAL;
-	current->thread.fpu.fpc = fpu->fpc;
+	vcpu->run->s.regs.fpc = fpu->fpc;
 	if (MACHINE_HAS_VX)
 		convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs,
 				 (freg_t *) fpu->fprs);
@@ -2279,7 +2251,7 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 				 (__vector128 *) vcpu->run->s.regs.vrs);
 	else
 		memcpy(fpu->fprs, vcpu->run->s.regs.fprs, sizeof(fpu->fprs));
-	fpu->fpc = current->thread.fpu.fpc;
+	fpu->fpc = vcpu->run->s.regs.fpc;
 	return 0;
 }
 
@@ -2740,6 +2712,20 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		if (riccb->valid)
 			vcpu->arch.sie_block->ecb3 |= 0x01;
 	}
+	save_access_regs(vcpu->arch.host_acrs);
+	restore_access_regs(vcpu->run->s.regs.acrs);
+	/* save host (userspace) fprs/vrs */
+	save_fpu_regs();
+	vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
+	vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
+	if (MACHINE_HAS_VX)
+		current->thread.fpu.regs = vcpu->run->s.regs.vrs;
+	else
+		current->thread.fpu.regs = vcpu->run->s.regs.fprs;
+	current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
+	if (test_fp_ctl(current->thread.fpu.fpc))
+		/* User space provided an invalid FPC, let's clear it */
+		current->thread.fpu.fpc = 0;
 
 	kvm_run->kvm_dirty_regs = 0;
 }
@@ -2758,6 +2744,15 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	kvm_run->s.regs.pft = vcpu->arch.pfault_token;
 	kvm_run->s.regs.pfs = vcpu->arch.pfault_select;
 	kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
+	save_access_regs(vcpu->run->s.regs.acrs);
+	restore_access_regs(vcpu->arch.host_acrs);
+	/* Save guest register state */
+	save_fpu_regs();
+	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
+	/* Restore will be done lazily at return */
+	current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
+	current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
+
 }
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
@@ -2874,7 +2869,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 {
 	/*
 	 * The guest FPRS and ACRS are in the host FPRS/ACRS due to the lazy
-	 * copying in vcpu load/put. Lets update our copies before we save
+	 * switch in the run ioctl. Let's update our copies before we save
 	 * it into the save area
 	 */
 	save_fpu_regs();

arch/x86/include/asm/kvm_host.h

@@ -191,6 +191,8 @@ enum {
 #define PFERR_RSVD_BIT 3
 #define PFERR_FETCH_BIT 4
 #define PFERR_PK_BIT 5
+#define PFERR_GUEST_FINAL_BIT 32
+#define PFERR_GUEST_PAGE_BIT 33
 
 #define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT)
 #define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT)
@@ -198,6 +200,13 @@ enum {
 #define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT)
 #define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT)
 #define PFERR_PK_MASK (1U << PFERR_PK_BIT)
+#define PFERR_GUEST_FINAL_MASK (1ULL << PFERR_GUEST_FINAL_BIT)
+#define PFERR_GUEST_PAGE_MASK (1ULL << PFERR_GUEST_PAGE_BIT)
+
+#define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK |	\
+				 PFERR_USER_MASK |		\
+				 PFERR_WRITE_MASK |		\
+				 PFERR_PRESENT_MASK)
 
 /* apic attention bits */
 #define KVM_APIC_CHECK_VAPIC	0
@@ -1062,6 +1071,7 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
 
 int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
+bool pdptrs_changed(struct kvm_vcpu *vcpu);
 
 int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 			  const void *val, int bytes);
@@ -1124,7 +1134,8 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
 struct x86_emulate_ctxt;
 
 int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port);
-void kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
+int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port);
+int kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
 int kvm_emulate_halt(struct kvm_vcpu *vcpu);
 int kvm_vcpu_halt(struct kvm_vcpu *vcpu);
 int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);
@@ -1203,7 +1214,7 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu);
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code,
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code,
 		       void *insn, int insn_len);
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
 void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu);
@@ -1358,7 +1369,8 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
 bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu);
 extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 
-void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
+int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu);
+int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
 
 int kvm_is_in_guest(void);
 

arch/x86/include/asm/vmx.h

@@ -25,6 +25,7 @@
 #define VMX_H
 
 
+#include <linux/bitops.h>
 #include <linux/types.h>
 #include <uapi/asm/vmx.h>
 
@@ -60,6 +61,7 @@
  */
 #define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
 #define SECONDARY_EXEC_ENABLE_EPT               0x00000002
+#define SECONDARY_EXEC_DESC			0x00000004
 #define SECONDARY_EXEC_RDTSCP			0x00000008
 #define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE   0x00000010
 #define SECONDARY_EXEC_ENABLE_VPID              0x00000020
@@ -110,6 +112,36 @@
 #define VMX_MISC_SAVE_EFER_LMA			0x00000020
 #define VMX_MISC_ACTIVITY_HLT			0x00000040
 
+static inline u32 vmx_basic_vmcs_revision_id(u64 vmx_basic)
+{
+	return vmx_basic & GENMASK_ULL(30, 0);
+}
+
+static inline u32 vmx_basic_vmcs_size(u64 vmx_basic)
+{
+	return (vmx_basic & GENMASK_ULL(44, 32)) >> 32;
+}
+
+static inline int vmx_misc_preemption_timer_rate(u64 vmx_misc)
+{
+	return vmx_misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK;
+}
+
+static inline int vmx_misc_cr3_count(u64 vmx_misc)
+{
+	return (vmx_misc & GENMASK_ULL(24, 16)) >> 16;
+}
+
+static inline int vmx_misc_max_msr(u64 vmx_misc)
+{
+	return (vmx_misc & GENMASK_ULL(27, 25)) >> 25;
+}
+
+static inline int vmx_misc_mseg_revid(u64 vmx_misc)
+{
+	return (vmx_misc & GENMASK_ULL(63, 32)) >> 32;
+}
+
 /* VMCS Encodings */
 enum vmcs_field {
 	VIRTUAL_PROCESSOR_ID            = 0x00000000,
@@ -399,10 +431,11 @@ enum vmcs_field {
 #define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT	(KVM_USER_MEM_SLOTS + 2)
 
 #define VMX_NR_VPIDS				(1 << 16)
+#define VMX_VPID_EXTENT_INDIVIDUAL_ADDR		0
 #define VMX_VPID_EXTENT_SINGLE_CONTEXT		1
 #define VMX_VPID_EXTENT_ALL_CONTEXT		2
+#define VMX_VPID_EXTENT_SINGLE_NON_GLOBAL	3
 
-#define VMX_EPT_EXTENT_INDIVIDUAL_ADDR		0
 #define VMX_EPT_EXTENT_CONTEXT			1
 #define VMX_EPT_EXTENT_GLOBAL			2
 #define VMX_EPT_EXTENT_SHIFT			24
@@ -419,8 +452,10 @@ enum vmcs_field {
 #define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
 
 #define VMX_VPID_INVVPID_BIT                    (1ull << 0) /* (32 - 32) */
+#define VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT     (1ull << 8) /* (40 - 32) */
 #define VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT      (1ull << 9) /* (41 - 32) */
 #define VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT      (1ull << 10) /* (42 - 32) */
+#define VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT   (1ull << 11) /* (43 - 32) */
 
 #define VMX_EPT_DEFAULT_GAW			3
 #define VMX_EPT_MAX_GAW				0x4

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

@@ -65,6 +65,8 @@
 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43
 #define EXIT_REASON_APIC_ACCESS         44
 #define EXIT_REASON_EOI_INDUCED         45
+#define EXIT_REASON_GDTR_IDTR           46
+#define EXIT_REASON_LDTR_TR             47
 #define EXIT_REASON_EPT_VIOLATION       48
 #define EXIT_REASON_EPT_MISCONFIG       49
 #define EXIT_REASON_INVEPT              50
@@ -113,6 +115,8 @@
 	{ EXIT_REASON_MCE_DURING_VMENTRY,    "MCE_DURING_VMENTRY" }, \
 	{ EXIT_REASON_TPR_BELOW_THRESHOLD,   "TPR_BELOW_THRESHOLD" }, \
 	{ EXIT_REASON_APIC_ACCESS,           "APIC_ACCESS" }, \
+	{ EXIT_REASON_GDTR_IDTR,	     "GDTR_IDTR" }, \
+	{ EXIT_REASON_LDTR_TR,		     "LDTR_TR" }, \
 	{ EXIT_REASON_EPT_VIOLATION,         "EPT_VIOLATION" }, \
 	{ EXIT_REASON_EPT_MISCONFIG,         "EPT_MISCONFIG" }, \
 	{ EXIT_REASON_INVEPT,                "INVEPT" }, \
@@ -129,6 +133,7 @@
 	{ EXIT_REASON_XRSTORS,               "XRSTORS" }
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
+#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL       2
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
 
 #endif /* _UAPIVMX_H */

arch/x86/kvm/cpuid.c

@@ -16,6 +16,7 @@
 #include <linux/export.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
+#include <asm/processor.h>
 #include <asm/user.h>
 #include <asm/fpu/xstate.h>
 #include "cpuid.h"
@@ -64,6 +65,11 @@ u64 kvm_supported_xcr0(void)
 
 #define F(x) bit(X86_FEATURE_##x)
 
+/* These are scattered features in cpufeatures.h. */
+#define KVM_CPUID_BIT_AVX512_4VNNIW     2
+#define KVM_CPUID_BIT_AVX512_4FMAPS     3
+#define KF(x) bit(KVM_CPUID_BIT_##x)
+
 int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
@@ -80,6 +86,10 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 			best->ecx |= F(OSXSAVE);
 	}
 
+	best->edx &= ~F(APIC);
+	if (vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE)
+		best->edx |= F(APIC);
+
 	if (apic) {
 		if (best->ecx & F(TSC_DEADLINE_TIMER))
 			apic->lapic_timer.timer_mode_mask = 3 << 17;
@@ -374,6 +384,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	/* cpuid 7.0.ecx*/
 	const u32 kvm_cpuid_7_0_ecx_x86_features = F(PKU) | 0 /*OSPKE*/;
 
+	/* cpuid 7.0.edx*/
+	const u32 kvm_cpuid_7_0_edx_x86_features =
+		KF(AVX512_4VNNIW) | KF(AVX512_4FMAPS);
+
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
 
@@ -456,12 +470,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			/* PKU is not yet implemented for shadow paging. */
 			if (!tdp_enabled)
 				entry->ecx &= ~F(PKU);
+			entry->edx &= kvm_cpuid_7_0_edx_x86_features;
+			entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX);
 		} else {
 			entry->ebx = 0;
 			entry->ecx = 0;
+			entry->edx = 0;
 		}
 		entry->eax = 0;
-		entry->edx = 0;
 		break;
 	}
 	case 9:
@@ -861,17 +877,17 @@ void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
 }
 EXPORT_SYMBOL_GPL(kvm_cpuid);
 
-void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
+int kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
 {
-	u32 function, eax, ebx, ecx, edx;
+	u32 eax, ebx, ecx, edx;
 
-	function = eax = kvm_register_read(vcpu, VCPU_REGS_RAX);
+	eax = kvm_register_read(vcpu, VCPU_REGS_RAX);
 	ecx = kvm_register_read(vcpu, VCPU_REGS_RCX);
 	kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx);
 	kvm_register_write(vcpu, VCPU_REGS_RAX, eax);
 	kvm_register_write(vcpu, VCPU_REGS_RBX, ebx);
 	kvm_register_write(vcpu, VCPU_REGS_RCX, ecx);
 	kvm_register_write(vcpu, VCPU_REGS_RDX, edx);
-	kvm_x86_ops->skip_emulated_instruction(vcpu);
+	return kvm_skip_emulated_instruction(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);

arch/x86/kvm/emulate.c

@@ -158,9 +158,11 @@
 #define Src2GS      (OpGS << Src2Shift)
 #define Src2Mask    (OpMask << Src2Shift)
 #define Mmx         ((u64)1 << 40)  /* MMX Vector instruction */
+#define AlignMask   ((u64)7 << 41)
 #define Aligned     ((u64)1 << 41)  /* Explicitly aligned (e.g. MOVDQA) */
-#define Unaligned   ((u64)1 << 42)  /* Explicitly unaligned (e.g. MOVDQU) */
-#define Avx         ((u64)1 << 43)  /* Advanced Vector Extensions */
+#define Unaligned   ((u64)2 << 41)  /* Explicitly unaligned (e.g. MOVDQU) */
+#define Avx         ((u64)3 << 41)  /* Advanced Vector Extensions */
+#define Aligned16   ((u64)4 << 41)  /* Aligned to 16 byte boundary (e.g. FXSAVE) */
 #define Fastop      ((u64)1 << 44)  /* Use opcode::u.fastop */
 #define NoWrite     ((u64)1 << 45)  /* No writeback */
 #define SrcWrite    ((u64)1 << 46)  /* Write back src operand */
@@ -446,6 +448,26 @@ FOP_END;
 FOP_START(salc) "pushf; sbb %al, %al; popf \n\t" FOP_RET
 FOP_END;
 
+/*
+ * XXX: inoutclob user must know where the argument is being expanded.
+ *      Relying on CC_HAVE_ASM_GOTO would allow us to remove _fault.
+ */
+#define asm_safe(insn, inoutclob...) \
+({ \
+	int _fault = 0; \
+ \
+	asm volatile("1:" insn "\n" \
+	             "2:\n" \
+	             ".pushsection .fixup, \"ax\"\n" \
+	             "3: movl $1, %[_fault]\n" \
+	             "   jmp  2b\n" \
+	             ".popsection\n" \
+	             _ASM_EXTABLE(1b, 3b) \
+	             : [_fault] "+qm"(_fault) inoutclob ); \
+ \
+	_fault ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; \
+})
+
 static int emulator_check_intercept(struct x86_emulate_ctxt *ctxt,
 				    enum x86_intercept intercept,
 				    enum x86_intercept_stage stage)
@@ -632,21 +654,26 @@ static void set_segment_selector(struct x86_emulate_ctxt *ctxt, u16 selector,
  * depending on whether they're AVX encoded or not.
  *
  * Also included is CMPXCHG16B which is not a vector instruction, yet it is
- * subject to the same check.
+ * subject to the same check.  FXSAVE and FXRSTOR are checked here too as their
+ * 512 bytes of data must be aligned to a 16 byte boundary.
  */
-static bool insn_aligned(struct x86_emulate_ctxt *ctxt, unsigned size)
+static unsigned insn_alignment(struct x86_emulate_ctxt *ctxt, unsigned size)
 {
-	if (likely(size < 16))
-		return false;
+	u64 alignment = ctxt->d & AlignMask;
 
-	if (ctxt->d & Aligned)
-		return true;
-	else if (ctxt->d & Unaligned)
-		return false;
-	else if (ctxt->d & Avx)
-		return false;
-	else
-		return true;
+	if (likely(size < 16))
+		return 1;
+
+	switch (alignment) {
+	case Unaligned:
+	case Avx:
+		return 1;
+	case Aligned16:
+		return 16;
+	case Aligned:
+	default:
+		return size;
+	}
 }
 
 static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
@@ -704,7 +731,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 		}
 		break;
 	}
-	if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0))
+	if (la & (insn_alignment(ctxt, size) - 1))
 		return emulate_gp(ctxt, 0);
 	return X86EMUL_CONTINUE;
 bad:
@@ -3842,6 +3869,131 @@ static int em_movsxd(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
+static int check_fxsr(struct x86_emulate_ctxt *ctxt)
+{
+	u32 eax = 1, ebx, ecx = 0, edx;
+
+	ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+	if (!(edx & FFL(FXSR)))
+		return emulate_ud(ctxt);
+
+	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
+		return emulate_nm(ctxt);
+
+	/*
+	 * Don't emulate a case that should never be hit, instead of working
+	 * around a lack of fxsave64/fxrstor64 on old compilers.
+	 */
+	if (ctxt->mode >= X86EMUL_MODE_PROT64)
+		return X86EMUL_UNHANDLEABLE;
+
+	return X86EMUL_CONTINUE;
+}
+
+/*
+ * FXSAVE and FXRSTOR have 4 different formats depending on execution mode,
+ *  1) 16 bit mode
+ *  2) 32 bit mode
+ *     - like (1), but FIP and FDP (foo) are only 16 bit.  At least Intel CPUs
+ *       preserve whole 32 bit values, though, so (1) and (2) are the same wrt.
+ *       save and restore
+ *  3) 64-bit mode with REX.W prefix
+ *     - like (2), but XMM 8-15 are being saved and restored
+ *  4) 64-bit mode without REX.W prefix
+ *     - like (3), but FIP and FDP are 64 bit
+ *
+ * Emulation uses (3) for (1) and (2) and preserves XMM 8-15 to reach the
+ * desired result.  (4) is not emulated.
+ *
+ * Note: Guest and host CPUID.(EAX=07H,ECX=0H):EBX[bit 13] (deprecate FPU CS
+ * and FPU DS) should match.
+ */
+static int em_fxsave(struct x86_emulate_ctxt *ctxt)
+{
+	struct fxregs_state fx_state;
+	size_t size;
+	int rc;
+
+	rc = check_fxsr(ctxt);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	ctxt->ops->get_fpu(ctxt);
+
+	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
+
+	ctxt->ops->put_fpu(ctxt);
+
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR)
+		size = offsetof(struct fxregs_state, xmm_space[8 * 16/4]);
+	else
+		size = offsetof(struct fxregs_state, xmm_space[0]);
+
+	return segmented_write(ctxt, ctxt->memop.addr.mem, &fx_state, size);
+}
+
+static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt,
+		struct fxregs_state *new)
+{
+	int rc = X86EMUL_CONTINUE;
+	struct fxregs_state old;
+
+	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(old));
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	/*
+	 * 64 bit host will restore XMM 8-15, which is not correct on non-64
+	 * bit guests.  Load the current values in order to preserve 64 bit
+	 * XMMs after fxrstor.
+	 */
+#ifdef CONFIG_X86_64
+	/* XXX: accessing XMM 8-15 very awkwardly */
+	memcpy(&new->xmm_space[8 * 16/4], &old.xmm_space[8 * 16/4], 8 * 16);
+#endif
+
+	/*
+	 * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but
+	 * does save and restore MXCSR.
+	 */
+	if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))
+		memcpy(new->xmm_space, old.xmm_space, 8 * 16);
+
+	return rc;
+}
+
+static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
+{
+	struct fxregs_state fx_state;
+	int rc;
+
+	rc = check_fxsr(ctxt);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	rc = segmented_read(ctxt, ctxt->memop.addr.mem, &fx_state, 512);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	if (fx_state.mxcsr >> 16)
+		return emulate_gp(ctxt, 0);
+
+	ctxt->ops->get_fpu(ctxt);
+
+	if (ctxt->mode < X86EMUL_MODE_PROT64)
+		rc = fxrstor_fixup(ctxt, &fx_state);
+
+	if (rc == X86EMUL_CONTINUE)
+		rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state));
+
+	ctxt->ops->put_fpu(ctxt);
+
+	return rc;
+}
+
 static bool valid_cr(int nr)
 {
 	switch (nr) {
@@ -4194,7 +4346,9 @@ static const struct gprefix pfx_0f_ae_7 = {
 };
 
 static const struct group_dual group15 = { {
-	N, N, N, N, N, N, N, GP(0, &pfx_0f_ae_7),
+	I(ModRM | Aligned16, em_fxsave),
+	I(ModRM | Aligned16, em_fxrstor),
+	N, N, N, N, N, GP(0, &pfx_0f_ae_7),
 }, {
 	N, N, N, N, N, N, N, N,
 } };
@@ -5066,21 +5220,13 @@ static bool string_insn_completed(struct x86_emulate_ctxt *ctxt)
 
 static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
 {
-	bool fault = false;
+	int rc;
 
 	ctxt->ops->get_fpu(ctxt);
-	asm volatile("1: fwait \n\t"
-		     "2: \n\t"
-		     ".pushsection .fixup,\"ax\" \n\t"
-		     "3: \n\t"
-		     "movb $1, %[fault] \n\t"
-		     "jmp 2b \n\t"
-		     ".popsection \n\t"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [fault]"+qm"(fault));
+	rc = asm_safe("fwait");
 	ctxt->ops->put_fpu(ctxt);
 
-	if (unlikely(fault))
+	if (unlikely(rc != X86EMUL_CONTINUE))
 		return emulate_exception(ctxt, MF_VECTOR, 0, false);
 
 	return X86EMUL_CONTINUE;

arch/x86/kvm/hyperv.c

@@ -291,7 +291,7 @@ static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata)
 	return ret;
 }
 
-int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint)
+static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint)
 {
 	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
 	struct kvm_lapic_irq irq;

arch/x86/kvm/i8254.c

@@ -212,7 +212,7 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian)
 	 */
 	smp_mb();
 	if (atomic_dec_if_positive(&ps->pending) > 0)
-		kthread_queue_work(&pit->worker, &pit->expired);
+		kthread_queue_work(pit->worker, &pit->expired);
 }
 
 void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
@@ -272,7 +272,7 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 	if (atomic_read(&ps->reinject))
 		atomic_inc(&ps->pending);
 
-	kthread_queue_work(&pt->worker, &pt->expired);
+	kthread_queue_work(pt->worker, &pt->expired);
 
 	if (ps->is_periodic) {
 		hrtimer_add_expires_ns(&ps->timer, ps->period);
@@ -667,10 +667,8 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 	pid_nr = pid_vnr(pid);
 	put_pid(pid);
 
-	kthread_init_worker(&pit->worker);
-	pit->worker_task = kthread_run(kthread_worker_fn, &pit->worker,
-				       "kvm-pit/%d", pid_nr);
-	if (IS_ERR(pit->worker_task))
+	pit->worker = kthread_create_worker(0, "kvm-pit/%d", pid_nr);
+	if (IS_ERR(pit->worker))
 		goto fail_kthread;
 
 	kthread_init_work(&pit->expired, pit_do_work);
@@ -713,7 +711,7 @@ fail_register_speaker:
 fail_register_pit:
 	mutex_unlock(&kvm->slots_lock);
 	kvm_pit_set_reinject(pit, false);
-	kthread_stop(pit->worker_task);
+	kthread_destroy_worker(pit->worker);
 fail_kthread:
 	kvm_free_irq_source_id(kvm, pit->irq_source_id);
 fail_request:
@@ -730,8 +728,7 @@ void kvm_free_pit(struct kvm *kvm)
 		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->speaker_dev);
 		kvm_pit_set_reinject(pit, false);
 		hrtimer_cancel(&pit->pit_state.timer);
-		kthread_flush_work(&pit->expired);
-		kthread_stop(pit->worker_task);
+		kthread_destroy_worker(pit->worker);
 		kvm_free_irq_source_id(kvm, pit->irq_source_id);
 		kfree(pit);
 	}

arch/x86/kvm/i8254.h

@@ -44,8 +44,7 @@ struct kvm_pit {
 	struct kvm_kpit_state pit_state;
 	int irq_source_id;
 	struct kvm_irq_mask_notifier mask_notifier;
-	struct kthread_worker worker;
-	struct task_struct *worker_task;
+	struct kthread_worker *worker;
 	struct kthread_work expired;
 };
 

arch/x86/kvm/lapic.c

@@ -342,9 +342,11 @@ void __kvm_apic_update_irr(u32 *pir, void *regs)
 	u32 i, pir_val;
 
 	for (i = 0; i <= 7; i++) {
-		pir_val = xchg(&pir[i], 0);
-		if (pir_val)
+		pir_val = READ_ONCE(pir[i]);
+		if (pir_val) {
+			pir_val = xchg(&pir[i], 0);
 			*((u32 *)(regs + APIC_IRR + i * 0x10)) |= pir_val;
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(__kvm_apic_update_irr);
@@ -1090,7 +1092,7 @@ static void apic_send_ipi(struct kvm_lapic *apic)
 
 static u32 apic_get_tmcct(struct kvm_lapic *apic)
 {
-	ktime_t remaining;
+	ktime_t remaining, now;
 	s64 ns;
 	u32 tmcct;
 
@@ -1101,7 +1103,8 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic)
 		apic->lapic_timer.period == 0)
 		return 0;
 
-	remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
+	now = ktime_get();
+	remaining = ktime_sub(apic->lapic_timer.target_expiration, now);
 	if (ktime_to_ns(remaining) < 0)
 		remaining = ktime_set(0, 0);
 
@@ -1332,7 +1335,7 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic)
 
 	local_irq_save(flags);
 
-	now = apic->lapic_timer.timer.base->get_time();
+	now = ktime_get();
 	guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
 	if (likely(tscdeadline > guest_tsc)) {
 		ns = (tscdeadline - guest_tsc) * 1000000ULL;
@@ -1347,6 +1350,79 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic)
 	local_irq_restore(flags);
 }
 
+static void start_sw_period(struct kvm_lapic *apic)
+{
+	if (!apic->lapic_timer.period)
+		return;
+
+	if (apic_lvtt_oneshot(apic) &&
+	    ktime_after(ktime_get(),
+			apic->lapic_timer.target_expiration)) {
+		apic_timer_expired(apic);
+		return;
+	}
+
+	hrtimer_start(&apic->lapic_timer.timer,
+		apic->lapic_timer.target_expiration,
+		HRTIMER_MODE_ABS_PINNED);
+}
+
+static bool set_target_expiration(struct kvm_lapic *apic)
+{
+	ktime_t now;
+	u64 tscl = rdtsc();
+
+	now = ktime_get();
+	apic->lapic_timer.period = (u64)kvm_lapic_get_reg(apic, APIC_TMICT)
+		* APIC_BUS_CYCLE_NS * apic->divide_count;
+
+	if (!apic->lapic_timer.period)
+		return false;
+
+	/*
+	 * Do not allow the guest to program periodic timers with small
+	 * interval, since the hrtimers are not throttled by the host
+	 * scheduler.
+	 */
+	if (apic_lvtt_period(apic)) {
+		s64 min_period = min_timer_period_us * 1000LL;
+
+		if (apic->lapic_timer.period < min_period) {
+			pr_info_ratelimited(
+			    "kvm: vcpu %i: requested %lld ns "
+			    "lapic timer period limited to %lld ns\n",
+			    apic->vcpu->vcpu_id,
+			    apic->lapic_timer.period, min_period);
+			apic->lapic_timer.period = min_period;
+		}
+	}
+
+	apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016"
+		   PRIx64 ", "
+		   "timer initial count 0x%x, period %lldns, "
+		   "expire @ 0x%016" PRIx64 ".\n", __func__,
+		   APIC_BUS_CYCLE_NS, ktime_to_ns(now),
+		   kvm_lapic_get_reg(apic, APIC_TMICT),
+		   apic->lapic_timer.period,
+		   ktime_to_ns(ktime_add_ns(now,
+				apic->lapic_timer.period)));
+
+	apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) +
+		nsec_to_cycles(apic->vcpu, apic->lapic_timer.period);
+	apic->lapic_timer.target_expiration = ktime_add_ns(now, apic->lapic_timer.period);
+
+	return true;
+}
+
+static void advance_periodic_target_expiration(struct kvm_lapic *apic)
+{
+	apic->lapic_timer.tscdeadline +=
+		nsec_to_cycles(apic->vcpu, apic->lapic_timer.period);
+	apic->lapic_timer.target_expiration =
+		ktime_add_ns(apic->lapic_timer.target_expiration,
+				apic->lapic_timer.period);
+}
+
 bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu)
 {
 	if (!lapic_in_kernel(vcpu))
@@ -1356,52 +1432,59 @@ bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use);
 
-static void cancel_hv_tscdeadline(struct kvm_lapic *apic)
+static void cancel_hv_timer(struct kvm_lapic *apic)
 {
 	kvm_x86_ops->cancel_hv_timer(apic->vcpu);
 	apic->lapic_timer.hv_timer_in_use = false;
 }
 
-void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
-{
-	struct kvm_lapic *apic = vcpu->arch.apic;
-
-	WARN_ON(!apic->lapic_timer.hv_timer_in_use);
-	WARN_ON(swait_active(&vcpu->wq));
-	cancel_hv_tscdeadline(apic);
-	apic_timer_expired(apic);
-}
-EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer);
-
-static bool start_hv_tscdeadline(struct kvm_lapic *apic)
+static bool start_hv_timer(struct kvm_lapic *apic)
 {
 	u64 tscdeadline = apic->lapic_timer.tscdeadline;
 
-	if (atomic_read(&apic->lapic_timer.pending) ||
+	if ((atomic_read(&apic->lapic_timer.pending) &&
+		!apic_lvtt_period(apic)) ||
 		kvm_x86_ops->set_hv_timer(apic->vcpu, tscdeadline)) {
 		if (apic->lapic_timer.hv_timer_in_use)
-			cancel_hv_tscdeadline(apic);
+			cancel_hv_timer(apic);
 	} else {
 		apic->lapic_timer.hv_timer_in_use = true;
 		hrtimer_cancel(&apic->lapic_timer.timer);
 
 		/* In case the sw timer triggered in the window */
-		if (atomic_read(&apic->lapic_timer.pending))
-			cancel_hv_tscdeadline(apic);
+		if (atomic_read(&apic->lapic_timer.pending) &&
+			!apic_lvtt_period(apic))
+			cancel_hv_timer(apic);
 	}
 	trace_kvm_hv_timer_state(apic->vcpu->vcpu_id,
 			apic->lapic_timer.hv_timer_in_use);
 	return apic->lapic_timer.hv_timer_in_use;
 }
 
+void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	WARN_ON(!apic->lapic_timer.hv_timer_in_use);
+	WARN_ON(swait_active(&vcpu->wq));
+	cancel_hv_timer(apic);
+	apic_timer_expired(apic);
+
+	if (apic_lvtt_period(apic) && apic->lapic_timer.period) {
+		advance_periodic_target_expiration(apic);
+		if (!start_hv_timer(apic))
+			start_sw_period(apic);
+	}
+}
+EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer);
+
 void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	WARN_ON(apic->lapic_timer.hv_timer_in_use);
 
-	if (apic_lvtt_tscdeadline(apic))
-		start_hv_tscdeadline(apic);
+	start_hv_timer(apic);
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_hv_timer);
 
@@ -1413,62 +1496,28 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu)
 	if (!apic->lapic_timer.hv_timer_in_use)
 		return;
 
-	cancel_hv_tscdeadline(apic);
+	cancel_hv_timer(apic);
 
 	if (atomic_read(&apic->lapic_timer.pending))
 		return;
 
-	start_sw_tscdeadline(apic);
+	if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic))
+		start_sw_period(apic);
+	else if (apic_lvtt_tscdeadline(apic))
+		start_sw_tscdeadline(apic);
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer);
 
 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)) {
-		/* lapic timer in oneshot or periodic mode */
-		now = apic->lapic_timer.timer.base->get_time();
-		apic->lapic_timer.period = (u64)kvm_lapic_get_reg(apic, APIC_TMICT)
-			    * APIC_BUS_CYCLE_NS * apic->divide_count;
-
-		if (!apic->lapic_timer.period)
-			return;
-		/*
-		 * Do not allow the guest to program periodic timers with small
-		 * interval, since the hrtimers are not throttled by the host
-		 * scheduler.
-		 */
-		if (apic_lvtt_period(apic)) {
-			s64 min_period = min_timer_period_us * 1000LL;
-
-			if (apic->lapic_timer.period < min_period) {
-				pr_info_ratelimited(
-				    "kvm: vcpu %i: requested %lld ns "
-				    "lapic timer period limited to %lld ns\n",
-				    apic->vcpu->vcpu_id,
-				    apic->lapic_timer.period, min_period);
-				apic->lapic_timer.period = min_period;
-			}
-		}
-
-		hrtimer_start(&apic->lapic_timer.timer,
-			      ktime_add_ns(now, apic->lapic_timer.period),
-			      HRTIMER_MODE_ABS_PINNED);
-
-		apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016"
-			   PRIx64 ", "
-			   "timer initial count 0x%x, period %lldns, "
-			   "expire @ 0x%016" PRIx64 ".\n", __func__,
-			   APIC_BUS_CYCLE_NS, ktime_to_ns(now),
-			   kvm_lapic_get_reg(apic, APIC_TMICT),
-			   apic->lapic_timer.period,
-			   ktime_to_ns(ktime_add_ns(now,
-					apic->lapic_timer.period)));
+		if (set_target_expiration(apic) &&
+			!(kvm_x86_ops->set_hv_timer && start_hv_timer(apic)))
+			start_sw_period(apic);
 	} else if (apic_lvtt_tscdeadline(apic)) {
-		if (!(kvm_x86_ops->set_hv_timer && start_hv_tscdeadline(apic)))
+		if (!(kvm_x86_ops->set_hv_timer && start_hv_timer(apic)))
 			start_sw_tscdeadline(apic);
 	}
 }
@@ -1701,13 +1750,22 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu)
  * LAPIC interface
  *----------------------------------------------------------------------
  */
+u64 kvm_get_lapic_target_expiration_tsc(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	if (!lapic_in_kernel(vcpu))
+		return 0;
+
+	return apic->lapic_timer.tscdeadline;
+}
 
 u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) ||
-			apic_lvtt_period(apic))
+	if (!lapic_in_kernel(vcpu) ||
+		!apic_lvtt_tscdeadline(apic))
 		return 0;
 
 	return apic->lapic_timer.tscdeadline;
@@ -1748,14 +1806,17 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 	u64 old_value = vcpu->arch.apic_base;
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!apic) {
+	if (!apic)
 		value |= MSR_IA32_APICBASE_BSP;
-		vcpu->arch.apic_base = value;
-		return;
-	}
 
 	vcpu->arch.apic_base = value;
 
+	if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE)
+		kvm_update_cpuid(vcpu);
+
+	if (!apic)
+		return;
+
 	/* update jump label if enable bit changes */
 	if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) {
 		if (value & MSR_IA32_APICBASE_ENABLE) {
@@ -1909,6 +1970,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
 	apic_timer_expired(apic);
 
 	if (lapic_is_periodic(apic)) {
+		advance_periodic_target_expiration(apic);
 		hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
 		return HRTIMER_RESTART;
 	} else
@@ -1993,6 +2055,10 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
 		kvm_apic_local_deliver(apic, APIC_LVTT);
 		if (apic_lvtt_tscdeadline(apic))
 			apic->lapic_timer.tscdeadline = 0;
+		if (apic_lvtt_oneshot(apic)) {
+			apic->lapic_timer.tscdeadline = 0;
+			apic->lapic_timer.target_expiration = ktime_set(0, 0);
+		}
 		atomic_set(&apic->lapic_timer.pending, 0);
 	}
 }

arch/x86/kvm/lapic.h

@@ -15,6 +15,7 @@
 struct kvm_timer {
 	struct hrtimer timer;
 	s64 period; 				/* unit: ns */
+	ktime_t target_expiration;
 	u32 timer_mode;
 	u32 timer_mode_mask;
 	u64 tscdeadline;
@@ -85,6 +86,7 @@ int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
 int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
 
+u64 kvm_get_lapic_target_expiration_tsc(struct kvm_vcpu *vcpu);
 u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu);
 void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data);
 

arch/x86/kvm/mmu.c

@@ -1660,17 +1660,9 @@ int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 	 * This has some overhead, but not as much as the cost of swapping
 	 * out actively used pages or breaking up actively used hugepages.
 	 */
-	if (!shadow_accessed_mask) {
-		/*
-		 * We are holding the kvm->mmu_lock, and we are blowing up
-		 * shadow PTEs. MMU notifier consumers need to be kept at bay.
-		 * This is correct as long as we don't decouple the mmu_lock
-		 * protected regions (like invalidate_range_start|end does).
-		 */
-		kvm->mmu_notifier_seq++;
+	if (!shadow_accessed_mask)
 		return kvm_handle_hva_range(kvm, start, end, 0,
 					    kvm_unmap_rmapp);
-	}
 
 	return kvm_handle_hva_range(kvm, start, end, 0, kvm_age_rmapp);
 }
@@ -4509,7 +4501,7 @@ static void make_mmu_pages_available(struct kvm_vcpu *vcpu)
 	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
 }
 
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 		       void *insn, int insn_len)
 {
 	int r, emulation_type = EMULTYPE_RETRY;
@@ -4528,12 +4520,28 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
 			return r;
 	}
 
-	r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false);
+	r = vcpu->arch.mmu.page_fault(vcpu, cr2, lower_32_bits(error_code),
+				      false);
 	if (r < 0)
 		return r;
 	if (!r)
 		return 1;
 
+	/*
+	 * Before emulating the instruction, check if the error code
+	 * was due to a RO violation while translating the guest page.
+	 * This can occur when using nested virtualization with nested
+	 * paging in both guests. If true, we simply unprotect the page
+	 * and resume the guest.
+	 *
+	 * Note: AMD only (since it supports the PFERR_GUEST_PAGE_MASK used
+	 *       in PFERR_NEXT_GUEST_PAGE)
+	 */
+	if (error_code == PFERR_NESTED_GUEST_PAGE) {
+		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2));
+		return 1;
+	}
+
 	if (mmio_info_in_cache(vcpu, cr2, direct))
 		emulation_type = 0;
 emulate:
@@ -4967,7 +4975,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots)
 	 * zap all shadow pages.
 	 */
 	if (unlikely((slots->generation & MMIO_GEN_MASK) == 0)) {
-		printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n");
+		kvm_debug_ratelimited("kvm: zapping shadow pages for mmio generation wraparound\n");
 		kvm_mmu_invalidate_zap_all_pages(kvm);
 	}
 }

arch/x86/kvm/svm.c

@@ -2074,7 +2074,7 @@ static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value)
 static int pf_interception(struct vcpu_svm *svm)
 {
 	u64 fault_address = svm->vmcb->control.exit_info_2;
-	u32 error_code;
+	u64 error_code;
 	int r = 1;
 
 	switch (svm->apf_reason) {
@@ -2270,7 +2270,7 @@ static int io_interception(struct vcpu_svm *svm)
 	++svm->vcpu.stat.io_exits;
 	string = (io_info & SVM_IOIO_STR_MASK) != 0;
 	in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
-	if (string || in)
+	if (string)
 		return emulate_instruction(vcpu, 0) == EMULATE_DONE;
 
 	port = io_info >> 16;
@@ -2278,7 +2278,8 @@ static int io_interception(struct vcpu_svm *svm)
 	svm->next_rip = svm->vmcb->control.exit_info_2;
 	skip_emulated_instruction(&svm->vcpu);
 
-	return kvm_fast_pio_out(vcpu, size, port);
+	return in ? kvm_fast_pio_in(vcpu, size, port)
+		  : kvm_fast_pio_out(vcpu, size, port);
 }
 
 static int nmi_interception(struct vcpu_svm *svm)
@@ -3150,8 +3151,7 @@ static int skinit_interception(struct vcpu_svm *svm)
 
 static int wbinvd_interception(struct vcpu_svm *svm)
 {
-	kvm_emulate_wbinvd(&svm->vcpu);
-	return 1;
+	return kvm_emulate_wbinvd(&svm->vcpu);
 }
 
 static int xsetbv_interception(struct vcpu_svm *svm)
@@ -3238,8 +3238,7 @@ static int task_switch_interception(struct vcpu_svm *svm)
 static int cpuid_interception(struct vcpu_svm *svm)
 {
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
-	kvm_emulate_cpuid(&svm->vcpu);
-	return 1;
+	return kvm_emulate_cpuid(&svm->vcpu);
 }
 
 static int iret_interception(struct vcpu_svm *svm)
@@ -3275,9 +3274,7 @@ static int rdpmc_interception(struct vcpu_svm *svm)
 		return emulate_on_interception(svm);
 
 	err = kvm_rdpmc(&svm->vcpu);
-	kvm_complete_insn_gp(&svm->vcpu, err);
-
-	return 1;
+	return kvm_complete_insn_gp(&svm->vcpu, err);
 }
 
 static bool check_selective_cr0_intercepted(struct vcpu_svm *svm,
@@ -3374,9 +3371,7 @@ static int cr_interception(struct vcpu_svm *svm)
 		}
 		kvm_register_write(&svm->vcpu, reg, val);
 	}
-	kvm_complete_insn_gp(&svm->vcpu, err);
-
-	return 1;
+	return kvm_complete_insn_gp(&svm->vcpu, err);
 }
 
 static int dr_interception(struct vcpu_svm *svm)

arch/x86/kvm/vmx.c

@@ -132,6 +132,22 @@ module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
 
 #define VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE 5
 
+#define VMX_VPID_EXTENT_SUPPORTED_MASK		\
+	(VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT |	\
+	VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |	\
+	VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT |	\
+	VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT)
+
+/*
+ * Hyper-V requires all of these, so mark them as supported even though
+ * they are just treated the same as all-context.
+ */
+#define VMX_VPID_EXTENT_SUPPORTED_MASK		\
+	(VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT |	\
+	VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |	\
+	VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT |	\
+	VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT)
+
 /*
  * These 2 parameters are used to config the controls for Pause-Loop Exiting:
  * ple_gap:    upper bound on the amount of time between two successive
@@ -446,23 +462,31 @@ struct nested_vmx {
 	u16 vpid02;
 	u16 last_vpid;
 
+	/*
+	 * We only store the "true" versions of the VMX capability MSRs. We
+	 * generate the "non-true" versions by setting the must-be-1 bits
+	 * according to the SDM.
+	 */
 	u32 nested_vmx_procbased_ctls_low;
 	u32 nested_vmx_procbased_ctls_high;
-	u32 nested_vmx_true_procbased_ctls_low;
 	u32 nested_vmx_secondary_ctls_low;
 	u32 nested_vmx_secondary_ctls_high;
 	u32 nested_vmx_pinbased_ctls_low;
 	u32 nested_vmx_pinbased_ctls_high;
 	u32 nested_vmx_exit_ctls_low;
 	u32 nested_vmx_exit_ctls_high;
-	u32 nested_vmx_true_exit_ctls_low;
 	u32 nested_vmx_entry_ctls_low;
 	u32 nested_vmx_entry_ctls_high;
-	u32 nested_vmx_true_entry_ctls_low;
 	u32 nested_vmx_misc_low;
 	u32 nested_vmx_misc_high;
 	u32 nested_vmx_ept_caps;
 	u32 nested_vmx_vpid_caps;
+	u64 nested_vmx_basic;
+	u64 nested_vmx_cr0_fixed0;
+	u64 nested_vmx_cr0_fixed1;
+	u64 nested_vmx_cr4_fixed0;
+	u64 nested_vmx_cr4_fixed1;
+	u64 nested_vmx_vmcs_enum;
 };
 
 #define POSTED_INTR_ON  0
@@ -520,6 +544,12 @@ static inline void pi_set_sn(struct pi_desc *pi_desc)
 			(unsigned long *)&pi_desc->control);
 }
 
+static inline void pi_clear_on(struct pi_desc *pi_desc)
+{
+	clear_bit(POSTED_INTR_ON,
+  		  (unsigned long *)&pi_desc->control);
+}
+
 static inline int pi_test_on(struct pi_desc *pi_desc)
 {
 	return test_bit(POSTED_INTR_ON,
@@ -920,16 +950,32 @@ static DEFINE_PER_CPU(struct desc_ptr, host_gdt);
 static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
 static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock);
 
-static unsigned long *vmx_io_bitmap_a;
-static unsigned long *vmx_io_bitmap_b;
-static unsigned long *vmx_msr_bitmap_legacy;
-static unsigned long *vmx_msr_bitmap_longmode;
-static unsigned long *vmx_msr_bitmap_legacy_x2apic;
-static unsigned long *vmx_msr_bitmap_longmode_x2apic;
-static unsigned long *vmx_msr_bitmap_legacy_x2apic_apicv_inactive;
-static unsigned long *vmx_msr_bitmap_longmode_x2apic_apicv_inactive;
-static unsigned long *vmx_vmread_bitmap;
-static unsigned long *vmx_vmwrite_bitmap;
+enum {
+	VMX_IO_BITMAP_A,
+	VMX_IO_BITMAP_B,
+	VMX_MSR_BITMAP_LEGACY,
+	VMX_MSR_BITMAP_LONGMODE,
+	VMX_MSR_BITMAP_LEGACY_X2APIC_APICV,
+	VMX_MSR_BITMAP_LONGMODE_X2APIC_APICV,
+	VMX_MSR_BITMAP_LEGACY_X2APIC,
+	VMX_MSR_BITMAP_LONGMODE_X2APIC,
+	VMX_VMREAD_BITMAP,
+	VMX_VMWRITE_BITMAP,
+	VMX_BITMAP_NR
+};
+
+static unsigned long *vmx_bitmap[VMX_BITMAP_NR];
+
+#define vmx_io_bitmap_a                      (vmx_bitmap[VMX_IO_BITMAP_A])
+#define vmx_io_bitmap_b                      (vmx_bitmap[VMX_IO_BITMAP_B])
+#define vmx_msr_bitmap_legacy                (vmx_bitmap[VMX_MSR_BITMAP_LEGACY])
+#define vmx_msr_bitmap_longmode              (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE])
+#define vmx_msr_bitmap_legacy_x2apic_apicv   (vmx_bitmap[VMX_MSR_BITMAP_LEGACY_X2APIC_APICV])
+#define vmx_msr_bitmap_longmode_x2apic_apicv (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE_X2APIC_APICV])
+#define vmx_msr_bitmap_legacy_x2apic         (vmx_bitmap[VMX_MSR_BITMAP_LEGACY_X2APIC])
+#define vmx_msr_bitmap_longmode_x2apic       (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE_X2APIC])
+#define vmx_vmread_bitmap                    (vmx_bitmap[VMX_VMREAD_BITMAP])
+#define vmx_vmwrite_bitmap                   (vmx_bitmap[VMX_VMWRITE_BITMAP])
 
 static bool cpu_has_load_ia32_efer;
 static bool cpu_has_load_perf_global_ctrl;
@@ -2523,14 +2569,14 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
 		  SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
 		if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) {
 			if (is_long_mode(vcpu))
-				msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
+				msr_bitmap = vmx_msr_bitmap_longmode_x2apic_apicv;
 			else
-				msr_bitmap = vmx_msr_bitmap_legacy_x2apic;
+				msr_bitmap = vmx_msr_bitmap_legacy_x2apic_apicv;
 		} else {
 			if (is_long_mode(vcpu))
-				msr_bitmap = vmx_msr_bitmap_longmode_x2apic_apicv_inactive;
+				msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
 			else
-				msr_bitmap = vmx_msr_bitmap_legacy_x2apic_apicv_inactive;
+				msr_bitmap = vmx_msr_bitmap_legacy_x2apic;
 		}
 	} else {
 		if (is_long_mode(vcpu))
@@ -2706,9 +2752,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		vmx->nested.nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
 
 	/* We support free control of debug control saving. */
-	vmx->nested.nested_vmx_true_exit_ctls_low =
-		vmx->nested.nested_vmx_exit_ctls_low &
-		~VM_EXIT_SAVE_DEBUG_CONTROLS;
+	vmx->nested.nested_vmx_exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS;
 
 	/* entry controls */
 	rdmsr(MSR_IA32_VMX_ENTRY_CTLS,
@@ -2727,9 +2771,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		vmx->nested.nested_vmx_entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
 
 	/* We support free control of debug control loading. */
-	vmx->nested.nested_vmx_true_entry_ctls_low =
-		vmx->nested.nested_vmx_entry_ctls_low &
-		~VM_ENTRY_LOAD_DEBUG_CONTROLS;
+	vmx->nested.nested_vmx_entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS;
 
 	/* cpu-based controls */
 	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS,
@@ -2762,8 +2804,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		CPU_BASED_USE_MSR_BITMAPS;
 
 	/* We support free control of CR3 access interception. */
-	vmx->nested.nested_vmx_true_procbased_ctls_low =
-		vmx->nested.nested_vmx_procbased_ctls_low &
+	vmx->nested.nested_vmx_procbased_ctls_low &=
 		~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING);
 
 	/* secondary cpu-based controls */
@@ -2774,6 +2815,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	vmx->nested.nested_vmx_secondary_ctls_high &=
 		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
 		SECONDARY_EXEC_RDTSCP |
+		SECONDARY_EXEC_DESC |
 		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
 		SECONDARY_EXEC_ENABLE_VPID |
 		SECONDARY_EXEC_APIC_REGISTER_VIRT |
@@ -2805,8 +2847,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	 */
 	if (enable_vpid)
 		vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
-				VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |
-				VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
+			VMX_VPID_EXTENT_SUPPORTED_MASK;
 	else
 		vmx->nested.nested_vmx_vpid_caps = 0;
 
@@ -2823,14 +2864,52 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE |
 		VMX_MISC_ACTIVITY_HLT;
 	vmx->nested.nested_vmx_misc_high = 0;
+
+	/*
+	 * This MSR reports some information about VMX support. We
+	 * should return information about the VMX we emulate for the
+	 * guest, and the VMCS structure we give it - not about the
+	 * VMX support of the underlying hardware.
+	 */
+	vmx->nested.nested_vmx_basic =
+		VMCS12_REVISION |
+		VMX_BASIC_TRUE_CTLS |
+		((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) |
+		(VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT);
+
+	if (cpu_has_vmx_basic_inout())
+		vmx->nested.nested_vmx_basic |= VMX_BASIC_INOUT;
+
+	/*
+	 * These MSRs specify bits which the guest must keep fixed on
+	 * while L1 is in VMXON mode (in L1's root mode, or running an L2).
+	 * We picked the standard core2 setting.
+	 */
+#define VMXON_CR0_ALWAYSON     (X86_CR0_PE | X86_CR0_PG | X86_CR0_NE)
+#define VMXON_CR4_ALWAYSON     X86_CR4_VMXE
+	vmx->nested.nested_vmx_cr0_fixed0 = VMXON_CR0_ALWAYSON;
+	vmx->nested.nested_vmx_cr4_fixed0 = VMXON_CR4_ALWAYSON;
+
+	/* These MSRs specify bits which the guest must keep fixed off. */
+	rdmsrl(MSR_IA32_VMX_CR0_FIXED1, vmx->nested.nested_vmx_cr0_fixed1);
+	rdmsrl(MSR_IA32_VMX_CR4_FIXED1, vmx->nested.nested_vmx_cr4_fixed1);
+
+	/* highest index: VMX_PREEMPTION_TIMER_VALUE */
+	vmx->nested.nested_vmx_vmcs_enum = 0x2e;
+}
+
+/*
+ * if fixed0[i] == 1: val[i] must be 1
+ * if fixed1[i] == 0: val[i] must be 0
+ */
+static inline bool fixed_bits_valid(u64 val, u64 fixed0, u64 fixed1)
+{
+	return ((val & fixed1) | fixed0) == val;
 }
 
 static inline bool vmx_control_verify(u32 control, u32 low, u32 high)
 {
-	/*
-	 * Bits 0 in high must be 0, and bits 1 in low must be 1.
-	 */
-	return ((control & high) | low) == control;
+	return fixed_bits_valid(control, low, high);
 }
 
 static inline u64 vmx_control_msr(u32 low, u32 high)
@@ -2838,87 +2917,285 @@ static inline u64 vmx_control_msr(u32 low, u32 high)
 	return low | ((u64)high << 32);
 }
 
-/* Returns 0 on success, non-0 otherwise. */
-static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
+static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask)
+{
+	superset &= mask;
+	subset &= mask;
+
+	return (superset | subset) == superset;
+}
+
+static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data)
+{
+	const u64 feature_and_reserved =
+		/* feature (except bit 48; see below) */
+		BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55) |
+		/* reserved */
+		BIT_ULL(31) | GENMASK_ULL(47, 45) | GENMASK_ULL(63, 56);
+	u64 vmx_basic = vmx->nested.nested_vmx_basic;
+
+	if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved))
+		return -EINVAL;
+
+	/*
+	 * KVM does not emulate a version of VMX that constrains physical
+	 * addresses of VMX structures (e.g. VMCS) to 32-bits.
+	 */
+	if (data & BIT_ULL(48))
+		return -EINVAL;
+
+	if (vmx_basic_vmcs_revision_id(vmx_basic) !=
+	    vmx_basic_vmcs_revision_id(data))
+		return -EINVAL;
+
+	if (vmx_basic_vmcs_size(vmx_basic) > vmx_basic_vmcs_size(data))
+		return -EINVAL;
+
+	vmx->nested.nested_vmx_basic = data;
+	return 0;
+}
+
+static int
+vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
+{
+	u64 supported;
+	u32 *lowp, *highp;
+
+	switch (msr_index) {
+	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
+		lowp = &vmx->nested.nested_vmx_pinbased_ctls_low;
+		highp = &vmx->nested.nested_vmx_pinbased_ctls_high;
+		break;
+	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
+		lowp = &vmx->nested.nested_vmx_procbased_ctls_low;
+		highp = &vmx->nested.nested_vmx_procbased_ctls_high;
+		break;
+	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
+		lowp = &vmx->nested.nested_vmx_exit_ctls_low;
+		highp = &vmx->nested.nested_vmx_exit_ctls_high;
+		break;
+	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
+		lowp = &vmx->nested.nested_vmx_entry_ctls_low;
+		highp = &vmx->nested.nested_vmx_entry_ctls_high;
+		break;
+	case MSR_IA32_VMX_PROCBASED_CTLS2:
+		lowp = &vmx->nested.nested_vmx_secondary_ctls_low;
+		highp = &vmx->nested.nested_vmx_secondary_ctls_high;
+		break;
+	default:
+		BUG();
+	}
+
+	supported = vmx_control_msr(*lowp, *highp);
+
+	/* Check must-be-1 bits are still 1. */
+	if (!is_bitwise_subset(data, supported, GENMASK_ULL(31, 0)))
+		return -EINVAL;
+
+	/* Check must-be-0 bits are still 0. */
+	if (!is_bitwise_subset(supported, data, GENMASK_ULL(63, 32)))
+		return -EINVAL;
+
+	*lowp = data;
+	*highp = data >> 32;
+	return 0;
+}
+
+static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data)
+{
+	const u64 feature_and_reserved_bits =
+		/* feature */
+		BIT_ULL(5) | GENMASK_ULL(8, 6) | BIT_ULL(14) | BIT_ULL(15) |
+		BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30) |
+		/* reserved */
+		GENMASK_ULL(13, 9) | BIT_ULL(31);
+	u64 vmx_misc;
+
+	vmx_misc = vmx_control_msr(vmx->nested.nested_vmx_misc_low,
+				   vmx->nested.nested_vmx_misc_high);
+
+	if (!is_bitwise_subset(vmx_misc, data, feature_and_reserved_bits))
+		return -EINVAL;
+
+	if ((vmx->nested.nested_vmx_pinbased_ctls_high &
+	     PIN_BASED_VMX_PREEMPTION_TIMER) &&
+	    vmx_misc_preemption_timer_rate(data) !=
+	    vmx_misc_preemption_timer_rate(vmx_misc))
+		return -EINVAL;
+
+	if (vmx_misc_cr3_count(data) > vmx_misc_cr3_count(vmx_misc))
+		return -EINVAL;
+
+	if (vmx_misc_max_msr(data) > vmx_misc_max_msr(vmx_misc))
+		return -EINVAL;
+
+	if (vmx_misc_mseg_revid(data) != vmx_misc_mseg_revid(vmx_misc))
+		return -EINVAL;
+
+	vmx->nested.nested_vmx_misc_low = data;
+	vmx->nested.nested_vmx_misc_high = data >> 32;
+	return 0;
+}
+
+static int vmx_restore_vmx_ept_vpid_cap(struct vcpu_vmx *vmx, u64 data)
+{
+	u64 vmx_ept_vpid_cap;
+
+	vmx_ept_vpid_cap = vmx_control_msr(vmx->nested.nested_vmx_ept_caps,
+					   vmx->nested.nested_vmx_vpid_caps);
+
+	/* Every bit is either reserved or a feature bit. */
+	if (!is_bitwise_subset(vmx_ept_vpid_cap, data, -1ULL))
+		return -EINVAL;
+
+	vmx->nested.nested_vmx_ept_caps = data;
+	vmx->nested.nested_vmx_vpid_caps = data >> 32;
+	return 0;
+}
+
+static int vmx_restore_fixed0_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
+{
+	u64 *msr;
+
+	switch (msr_index) {
+	case MSR_IA32_VMX_CR0_FIXED0:
+		msr = &vmx->nested.nested_vmx_cr0_fixed0;
+		break;
+	case MSR_IA32_VMX_CR4_FIXED0:
+		msr = &vmx->nested.nested_vmx_cr4_fixed0;
+		break;
+	default:
+		BUG();
+	}
+
+	/*
+	 * 1 bits (which indicates bits which "must-be-1" during VMX operation)
+	 * must be 1 in the restored value.
+	 */
+	if (!is_bitwise_subset(data, *msr, -1ULL))
+		return -EINVAL;
+
+	*msr = data;
+	return 0;
+}
+
+/*
+ * Called when userspace is restoring VMX MSRs.
+ *
+ * Returns 0 on success, non-0 otherwise.
+ */
+static int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
 	switch (msr_index) {
 	case MSR_IA32_VMX_BASIC:
+		return vmx_restore_vmx_basic(vmx, data);
+	case MSR_IA32_VMX_PINBASED_CTLS:
+	case MSR_IA32_VMX_PROCBASED_CTLS:
+	case MSR_IA32_VMX_EXIT_CTLS:
+	case MSR_IA32_VMX_ENTRY_CTLS:
+		/*
+		 * The "non-true" VMX capability MSRs are generated from the
+		 * "true" MSRs, so we do not support restoring them directly.
+		 *
+		 * If userspace wants to emulate VMX_BASIC[55]=0, userspace
+		 * should restore the "true" MSRs with the must-be-1 bits
+		 * set according to the SDM Vol 3. A.2 "RESERVED CONTROLS AND
+		 * DEFAULT SETTINGS".
+		 */
+		return -EINVAL;
+	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
+	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
+	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
+	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
+	case MSR_IA32_VMX_PROCBASED_CTLS2:
+		return vmx_restore_control_msr(vmx, msr_index, data);
+	case MSR_IA32_VMX_MISC:
+		return vmx_restore_vmx_misc(vmx, data);
+	case MSR_IA32_VMX_CR0_FIXED0:
+	case MSR_IA32_VMX_CR4_FIXED0:
+		return vmx_restore_fixed0_msr(vmx, msr_index, data);
+	case MSR_IA32_VMX_CR0_FIXED1:
+	case MSR_IA32_VMX_CR4_FIXED1:
+		/*
+		 * These MSRs are generated based on the vCPU's CPUID, so we
+		 * do not support restoring them directly.
+		 */
+		return -EINVAL;
+	case MSR_IA32_VMX_EPT_VPID_CAP:
+		return vmx_restore_vmx_ept_vpid_cap(vmx, data);
+	case MSR_IA32_VMX_VMCS_ENUM:
+		vmx->nested.nested_vmx_vmcs_enum = data;
+		return 0;
+	default:
 		/*
-		 * This MSR reports some information about VMX support. We
-		 * should return information about the VMX we emulate for the
-		 * guest, and the VMCS structure we give it - not about the
-		 * VMX support of the underlying hardware.
+		 * The rest of the VMX capability MSRs do not support restore.
 		 */
-		*pdata = VMCS12_REVISION | VMX_BASIC_TRUE_CTLS |
-			   ((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) |
-			   (VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT);
-		if (cpu_has_vmx_basic_inout())
-			*pdata |= VMX_BASIC_INOUT;
+		return -EINVAL;
+	}
+}
+
+/* Returns 0 on success, non-0 otherwise. */
+static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	switch (msr_index) {
+	case MSR_IA32_VMX_BASIC:
+		*pdata = vmx->nested.nested_vmx_basic;
 		break;
 	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
 	case MSR_IA32_VMX_PINBASED_CTLS:
 		*pdata = vmx_control_msr(
 			vmx->nested.nested_vmx_pinbased_ctls_low,
 			vmx->nested.nested_vmx_pinbased_ctls_high);
+		if (msr_index == MSR_IA32_VMX_PINBASED_CTLS)
+			*pdata |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
 		break;
 	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
-		*pdata = vmx_control_msr(
-			vmx->nested.nested_vmx_true_procbased_ctls_low,
-			vmx->nested.nested_vmx_procbased_ctls_high);
-		break;
 	case MSR_IA32_VMX_PROCBASED_CTLS:
 		*pdata = vmx_control_msr(
 			vmx->nested.nested_vmx_procbased_ctls_low,
 			vmx->nested.nested_vmx_procbased_ctls_high);
+		if (msr_index == MSR_IA32_VMX_PROCBASED_CTLS)
+			*pdata |= CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
 		break;
 	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
-		*pdata = vmx_control_msr(
-			vmx->nested.nested_vmx_true_exit_ctls_low,
-			vmx->nested.nested_vmx_exit_ctls_high);
-		break;
 	case MSR_IA32_VMX_EXIT_CTLS:
 		*pdata = vmx_control_msr(
 			vmx->nested.nested_vmx_exit_ctls_low,
 			vmx->nested.nested_vmx_exit_ctls_high);
+		if (msr_index == MSR_IA32_VMX_EXIT_CTLS)
+			*pdata |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
 		break;
 	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
-		*pdata = vmx_control_msr(
-			vmx->nested.nested_vmx_true_entry_ctls_low,
-			vmx->nested.nested_vmx_entry_ctls_high);
-		break;
 	case MSR_IA32_VMX_ENTRY_CTLS:
 		*pdata = vmx_control_msr(
 			vmx->nested.nested_vmx_entry_ctls_low,
 			vmx->nested.nested_vmx_entry_ctls_high);
+		if (msr_index == MSR_IA32_VMX_ENTRY_CTLS)
+			*pdata |= VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
 		break;
 	case MSR_IA32_VMX_MISC:
 		*pdata = vmx_control_msr(
 			vmx->nested.nested_vmx_misc_low,
 			vmx->nested.nested_vmx_misc_high);
 		break;
-	/*
-	 * These MSRs specify bits which the guest must keep fixed (on or off)
-	 * while L1 is in VMXON mode (in L1's root mode, or running an L2).
-	 * We picked the standard core2 setting.
-	 */
-#define VMXON_CR0_ALWAYSON	(X86_CR0_PE | X86_CR0_PG | X86_CR0_NE)
-#define VMXON_CR4_ALWAYSON	X86_CR4_VMXE
 	case MSR_IA32_VMX_CR0_FIXED0:
-		*pdata = VMXON_CR0_ALWAYSON;
+		*pdata = vmx->nested.nested_vmx_cr0_fixed0;
 		break;
 	case MSR_IA32_VMX_CR0_FIXED1:
-		*pdata = -1ULL;
+		*pdata = vmx->nested.nested_vmx_cr0_fixed1;
 		break;
 	case MSR_IA32_VMX_CR4_FIXED0:
-		*pdata = VMXON_CR4_ALWAYSON;
+		*pdata = vmx->nested.nested_vmx_cr4_fixed0;
 		break;
 	case MSR_IA32_VMX_CR4_FIXED1:
-		*pdata = -1ULL;
+		*pdata = vmx->nested.nested_vmx_cr4_fixed1;
 		break;
 	case MSR_IA32_VMX_VMCS_ENUM:
-		*pdata = 0x2e; /* highest index: VMX_PREEMPTION_TIMER_VALUE */
+		*pdata = vmx->nested.nested_vmx_vmcs_enum;
 		break;
 	case MSR_IA32_VMX_PROCBASED_CTLS2:
 		*pdata = vmx_control_msr(
@@ -3101,7 +3378,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			vmx_leave_nested(vcpu);
 		break;
 	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
-		return 1; /* they are read-only */
+		if (!msr_info->host_initiated)
+			return 1; /* they are read-only */
+		if (!nested_vmx_allowed(vcpu))
+			return 1;
+		return vmx_set_vmx_msr(vcpu, msr_index, data);
 	case MSR_IA32_XSS:
 		if (!vmx_xsaves_supported())
 			return 1;
@@ -3863,6 +4144,40 @@ static void ept_save_pdptrs(struct kvm_vcpu *vcpu)
 		  (unsigned long *)&vcpu->arch.regs_dirty);
 }
 
+static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	u64 fixed0 = to_vmx(vcpu)->nested.nested_vmx_cr0_fixed0;
+	u64 fixed1 = to_vmx(vcpu)->nested.nested_vmx_cr0_fixed1;
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	if (to_vmx(vcpu)->nested.nested_vmx_secondary_ctls_high &
+		SECONDARY_EXEC_UNRESTRICTED_GUEST &&
+	    nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST))
+		fixed0 &= ~(X86_CR0_PE | X86_CR0_PG);
+
+	return fixed_bits_valid(val, fixed0, fixed1);
+}
+
+static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	u64 fixed0 = to_vmx(vcpu)->nested.nested_vmx_cr0_fixed0;
+	u64 fixed1 = to_vmx(vcpu)->nested.nested_vmx_cr0_fixed1;
+
+	return fixed_bits_valid(val, fixed0, fixed1);
+}
+
+static bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	u64 fixed0 = to_vmx(vcpu)->nested.nested_vmx_cr4_fixed0;
+	u64 fixed1 = to_vmx(vcpu)->nested.nested_vmx_cr4_fixed1;
+
+	return fixed_bits_valid(val, fixed0, fixed1);
+}
+
+/* No difference in the restrictions on guest and host CR4 in VMX operation. */
+#define nested_guest_cr4_valid	nested_cr4_valid
+#define nested_host_cr4_valid	nested_cr4_valid
+
 static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
 
 static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
@@ -3991,8 +4306,8 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 		if (!nested_vmx_allowed(vcpu))
 			return 1;
 	}
-	if (to_vmx(vcpu)->nested.vmxon &&
-	    ((cr4 & VMXON_CR4_ALWAYSON) != VMXON_CR4_ALWAYSON))
+
+	if (to_vmx(vcpu)->nested.vmxon && !nested_cr4_valid(vcpu, cr4))
 		return 1;
 
 	vcpu->arch.cr4 = cr4;
@@ -4569,41 +4884,6 @@ static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
 	}
 }
 
-static void __vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
-						u32 msr, int type)
-{
-	int f = sizeof(unsigned long);
-
-	if (!cpu_has_vmx_msr_bitmap())
-		return;
-
-	/*
-	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
-	 * have the write-low and read-high bitmap offsets the wrong way round.
-	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
-	 */
-	if (msr <= 0x1fff) {
-		if (type & MSR_TYPE_R)
-			/* read-low */
-			__set_bit(msr, msr_bitmap + 0x000 / f);
-
-		if (type & MSR_TYPE_W)
-			/* write-low */
-			__set_bit(msr, msr_bitmap + 0x800 / f);
-
-	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
-		msr &= 0x1fff;
-		if (type & MSR_TYPE_R)
-			/* read-high */
-			__set_bit(msr, msr_bitmap + 0x400 / f);
-
-		if (type & MSR_TYPE_W)
-			/* write-high */
-			__set_bit(msr, msr_bitmap + 0xc00 / f);
-
-	}
-}
-
 /*
  * If a msr is allowed by L0, we should check whether it is allowed by L1.
  * The corresponding bit will be cleared unless both of L0 and L1 allow it.
@@ -4659,48 +4939,18 @@ static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only)
 						msr, MSR_TYPE_R | MSR_TYPE_W);
 }
 
-static void vmx_enable_intercept_msr_read_x2apic(u32 msr, bool apicv_active)
-{
-	if (apicv_active) {
-		__vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
-				msr, MSR_TYPE_R);
-		__vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
-				msr, MSR_TYPE_R);
-	} else {
-		__vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive,
-				msr, MSR_TYPE_R);
-		__vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive,
-				msr, MSR_TYPE_R);
-	}
-}
-
-static void vmx_disable_intercept_msr_read_x2apic(u32 msr, bool apicv_active)
+static void vmx_disable_intercept_msr_x2apic(u32 msr, int type, bool apicv_active)
 {
 	if (apicv_active) {
-		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
-				msr, MSR_TYPE_R);
-		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
-				msr, MSR_TYPE_R);
+		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv,
+				msr, type);
+		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv,
+				msr, type);
 	} else {
-		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive,
-				msr, MSR_TYPE_R);
-		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive,
-				msr, MSR_TYPE_R);
-	}
-}
-
-static void vmx_disable_intercept_msr_write_x2apic(u32 msr, bool apicv_active)
-{
-	if (apicv_active) {
 		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
-				msr, MSR_TYPE_W);
+				msr, type);
 		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
-				msr, MSR_TYPE_W);
-	} else {
-		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive,
-				msr, MSR_TYPE_W);
-		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive,
-				msr, MSR_TYPE_W);
+				msr, type);
 	}
 }
 
@@ -4822,9 +5072,15 @@ static void vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (!pi_test_and_clear_on(&vmx->pi_desc))
+	if (!pi_test_on(&vmx->pi_desc))
 		return;
 
+	pi_clear_on(&vmx->pi_desc);
+	/*
+	 * IOMMU can write to PIR.ON, so the barrier matters even on UP.
+	 * But on x86 this is just a compiler barrier anyway.
+	 */
+	smp_mb__after_atomic();
 	kvm_apic_update_irr(vcpu, vmx->pi_desc.pir);
 }
 
@@ -5583,7 +5839,7 @@ static int handle_triple_fault(struct kvm_vcpu *vcpu)
 static int handle_io(struct kvm_vcpu *vcpu)
 {
 	unsigned long exit_qualification;
-	int size, in, string;
+	int size, in, string, ret;
 	unsigned port;
 
 	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
@@ -5597,9 +5853,14 @@ static int handle_io(struct kvm_vcpu *vcpu)
 
 	port = exit_qualification >> 16;
 	size = (exit_qualification & 7) + 1;
-	skip_emulated_instruction(vcpu);
 
-	return kvm_fast_pio_out(vcpu, size, port);
+	ret = kvm_skip_emulated_instruction(vcpu);
+
+	/*
+	 * TODO: we might be squashing a KVM_GUESTDBG_SINGLESTEP-triggered
+	 * KVM_EXIT_DEBUG here.
+	 */
+	return kvm_fast_pio_out(vcpu, size, port) && ret;
 }
 
 static void
@@ -5613,18 +5874,6 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
 	hypercall[2] = 0xc1;
 }
 
-static bool nested_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
-{
-	unsigned long always_on = VMXON_CR0_ALWAYSON;
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-
-	if (to_vmx(vcpu)->nested.nested_vmx_secondary_ctls_high &
-		SECONDARY_EXEC_UNRESTRICTED_GUEST &&
-	    nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST))
-		always_on &= ~(X86_CR0_PE | X86_CR0_PG);
-	return (val & always_on) == always_on;
-}
-
 /* called to set cr0 as appropriate for a mov-to-cr0 exit. */
 static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
 {
@@ -5643,7 +5892,7 @@ static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
 		val = (val & ~vmcs12->cr0_guest_host_mask) |
 			(vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask);
 
-		if (!nested_cr0_valid(vcpu, val))
+		if (!nested_guest_cr0_valid(vcpu, val))
 			return 1;
 
 		if (kvm_set_cr0(vcpu, val))
@@ -5652,8 +5901,9 @@ static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
 		return 0;
 	} else {
 		if (to_vmx(vcpu)->nested.vmxon &&
-		    ((val & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON))
+		    !nested_host_cr0_valid(vcpu, val))
 			return 1;
+
 		return kvm_set_cr0(vcpu, val);
 	}
 }
@@ -5697,6 +5947,7 @@ static int handle_cr(struct kvm_vcpu *vcpu)
 	int cr;
 	int reg;
 	int err;
+	int ret;
 
 	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 	cr = exit_qualification & 15;
@@ -5708,25 +5959,27 @@ static int handle_cr(struct kvm_vcpu *vcpu)
 		switch (cr) {
 		case 0:
 			err = handle_set_cr0(vcpu, val);
-			kvm_complete_insn_gp(vcpu, err);
-			return 1;
+			return kvm_complete_insn_gp(vcpu, err);
 		case 3:
 			err = kvm_set_cr3(vcpu, val);
-			kvm_complete_insn_gp(vcpu, err);
-			return 1;
+			return kvm_complete_insn_gp(vcpu, err);
 		case 4:
 			err = handle_set_cr4(vcpu, val);
-			kvm_complete_insn_gp(vcpu, err);
-			return 1;
+			return kvm_complete_insn_gp(vcpu, err);
 		case 8: {
 				u8 cr8_prev = kvm_get_cr8(vcpu);
 				u8 cr8 = (u8)val;
 				err = kvm_set_cr8(vcpu, cr8);
-				kvm_complete_insn_gp(vcpu, err);
+				ret = kvm_complete_insn_gp(vcpu, err);
 				if (lapic_in_kernel(vcpu))
-					return 1;
+					return ret;
 				if (cr8_prev <= cr8)
-					return 1;
+					return ret;
+				/*
+				 * TODO: we might be squashing a
+				 * KVM_GUESTDBG_SINGLESTEP-triggered
+				 * KVM_EXIT_DEBUG here.
+				 */
 				vcpu->run->exit_reason = KVM_EXIT_SET_TPR;
 				return 0;
 			}
@@ -5735,23 +5988,20 @@ static int handle_cr(struct kvm_vcpu *vcpu)
 	case 2: /* clts */
 		handle_clts(vcpu);
 		trace_kvm_cr_write(0, kvm_read_cr0(vcpu));
-		skip_emulated_instruction(vcpu);
 		vmx_fpu_activate(vcpu);
-		return 1;
+		return kvm_skip_emulated_instruction(vcpu);
 	case 1: /*mov from cr*/
 		switch (cr) {
 		case 3:
 			val = kvm_read_cr3(vcpu);
 			kvm_register_write(vcpu, reg, val);
 			trace_kvm_cr_read(cr, val);
-			skip_emulated_instruction(vcpu);
-			return 1;
+			return kvm_skip_emulated_instruction(vcpu);
 		case 8:
 			val = kvm_get_cr8(vcpu);
 			kvm_register_write(vcpu, reg, val);
 			trace_kvm_cr_read(cr, val);
-			skip_emulated_instruction(vcpu);
-			return 1;
+			return kvm_skip_emulated_instruction(vcpu);
 		}
 		break;
 	case 3: /* lmsw */
@@ -5759,8 +6009,7 @@ static int handle_cr(struct kvm_vcpu *vcpu)
 		trace_kvm_cr_write(0, (kvm_read_cr0(vcpu) & ~0xful) | val);
 		kvm_lmsw(vcpu, val);
 
-		skip_emulated_instruction(vcpu);
-		return 1;
+		return kvm_skip_emulated_instruction(vcpu);
 	default:
 		break;
 	}
@@ -5831,8 +6080,7 @@ static int handle_dr(struct kvm_vcpu *vcpu)
 		if (kvm_set_dr(vcpu, dr, kvm_register_readl(vcpu, reg)))
 			return 1;
 
-	skip_emulated_instruction(vcpu);
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 static u64 vmx_get_dr6(struct kvm_vcpu *vcpu)
@@ -5864,8 +6112,7 @@ static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
 
 static int handle_cpuid(struct kvm_vcpu *vcpu)
 {
-	kvm_emulate_cpuid(vcpu);
-	return 1;
+	return kvm_emulate_cpuid(vcpu);
 }
 
 static int handle_rdmsr(struct kvm_vcpu *vcpu)
@@ -5886,8 +6133,7 @@ static int handle_rdmsr(struct kvm_vcpu *vcpu)
 	/* FIXME: handling of bits 32:63 of rax, rdx */
 	vcpu->arch.regs[VCPU_REGS_RAX] = msr_info.data & -1u;
 	vcpu->arch.regs[VCPU_REGS_RDX] = (msr_info.data >> 32) & -1u;
-	skip_emulated_instruction(vcpu);
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 static int handle_wrmsr(struct kvm_vcpu *vcpu)
@@ -5907,8 +6153,7 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu)
 	}
 
 	trace_kvm_msr_write(ecx, data);
-	skip_emulated_instruction(vcpu);
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu)
@@ -5952,8 +6197,7 @@ static int handle_invlpg(struct kvm_vcpu *vcpu)
 	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 
 	kvm_mmu_invlpg(vcpu, exit_qualification);
-	skip_emulated_instruction(vcpu);
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 static int handle_rdpmc(struct kvm_vcpu *vcpu)
@@ -5961,15 +6205,12 @@ static int handle_rdpmc(struct kvm_vcpu *vcpu)
 	int err;
 
 	err = kvm_rdpmc(vcpu);
-	kvm_complete_insn_gp(vcpu, err);
-
-	return 1;
+	return kvm_complete_insn_gp(vcpu, err);
 }
 
 static int handle_wbinvd(struct kvm_vcpu *vcpu)
 {
-	kvm_emulate_wbinvd(vcpu);
-	return 1;
+	return kvm_emulate_wbinvd(vcpu);
 }
 
 static int handle_xsetbv(struct kvm_vcpu *vcpu)
@@ -5978,20 +6219,20 @@ static int handle_xsetbv(struct kvm_vcpu *vcpu)
 	u32 index = kvm_register_read(vcpu, VCPU_REGS_RCX);
 
 	if (kvm_set_xcr(vcpu, index, new_bv) == 0)
-		skip_emulated_instruction(vcpu);
+		return kvm_skip_emulated_instruction(vcpu);
 	return 1;
 }
 
 static int handle_xsaves(struct kvm_vcpu *vcpu)
 {
-	skip_emulated_instruction(vcpu);
+	kvm_skip_emulated_instruction(vcpu);
 	WARN(1, "this should never happen\n");
 	return 1;
 }
 
 static int handle_xrstors(struct kvm_vcpu *vcpu)
 {
-	skip_emulated_instruction(vcpu);
+	kvm_skip_emulated_instruction(vcpu);
 	WARN(1, "this should never happen\n");
 	return 1;
 }
@@ -6012,8 +6253,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu)
 		if ((access_type == TYPE_LINEAR_APIC_INST_WRITE) &&
 		    (offset == APIC_EOI)) {
 			kvm_lapic_set_eoi(vcpu);
-			skip_emulated_instruction(vcpu);
-			return 1;
+			return kvm_skip_emulated_instruction(vcpu);
 		}
 	}
 	return emulate_instruction(vcpu, 0) == EMULATE_DONE;
@@ -6161,9 +6401,8 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
 	if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
-		skip_emulated_instruction(vcpu);
 		trace_kvm_fast_mmio(gpa);
-		return 1;
+		return kvm_skip_emulated_instruction(vcpu);
 	}
 
 	ret = handle_mmio_page_fault(vcpu, gpa, true);
@@ -6348,50 +6587,13 @@ static __init int hardware_setup(void)
 	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i)
 		kvm_define_shared_msr(i, vmx_msr_index[i]);
 
-	vmx_io_bitmap_a = (unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_io_bitmap_a)
-		return r;
+	for (i = 0; i < VMX_BITMAP_NR; i++) {
+		vmx_bitmap[i] = (unsigned long *)__get_free_page(GFP_KERNEL);
+		if (!vmx_bitmap[i])
+			goto out;
+	}
 
 	vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_io_bitmap_b)
-		goto out;
-
-	vmx_msr_bitmap_legacy = (unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_msr_bitmap_legacy)
-		goto out1;
-
-	vmx_msr_bitmap_legacy_x2apic =
-				(unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_msr_bitmap_legacy_x2apic)
-		goto out2;
-
-	vmx_msr_bitmap_legacy_x2apic_apicv_inactive =
-				(unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_msr_bitmap_legacy_x2apic_apicv_inactive)
-		goto out3;
-
-	vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_msr_bitmap_longmode)
-		goto out4;
-
-	vmx_msr_bitmap_longmode_x2apic =
-				(unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_msr_bitmap_longmode_x2apic)
-		goto out5;
-
-	vmx_msr_bitmap_longmode_x2apic_apicv_inactive =
-				(unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_msr_bitmap_longmode_x2apic_apicv_inactive)
-		goto out6;
-
-	vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_vmread_bitmap)
-		goto out7;
-
-	vmx_vmwrite_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_vmwrite_bitmap)
-		goto out8;
-
 	memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
 	memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
 
@@ -6409,7 +6611,7 @@ static __init int hardware_setup(void)
 
 	if (setup_vmcs_config(&vmcs_config) < 0) {
 		r = -EIO;
-		goto out9;
+		goto out;
 	}
 
 	if (boot_cpu_has(X86_FEATURE_NX))
@@ -6472,39 +6674,34 @@ static __init int hardware_setup(void)
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
 	vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true);
 
-	memcpy(vmx_msr_bitmap_legacy_x2apic,
+	memcpy(vmx_msr_bitmap_legacy_x2apic_apicv,
 			vmx_msr_bitmap_legacy, PAGE_SIZE);
-	memcpy(vmx_msr_bitmap_longmode_x2apic,
+	memcpy(vmx_msr_bitmap_longmode_x2apic_apicv,
 			vmx_msr_bitmap_longmode, PAGE_SIZE);
-	memcpy(vmx_msr_bitmap_legacy_x2apic_apicv_inactive,
+	memcpy(vmx_msr_bitmap_legacy_x2apic,
 			vmx_msr_bitmap_legacy, PAGE_SIZE);
-	memcpy(vmx_msr_bitmap_longmode_x2apic_apicv_inactive,
+	memcpy(vmx_msr_bitmap_longmode_x2apic,
 			vmx_msr_bitmap_longmode, PAGE_SIZE);
 
 	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
 
+	for (msr = 0x800; msr <= 0x8ff; msr++) {
+		if (msr == 0x839 /* TMCCT */)
+			continue;
+		vmx_disable_intercept_msr_x2apic(msr, MSR_TYPE_R, true);
+	}
+
 	/*
-	 * enable_apicv && kvm_vcpu_apicv_active()
+	 * TPR reads and writes can be virtualized even if virtual interrupt
+	 * delivery is not in use.
 	 */
-	for (msr = 0x800; msr <= 0x8ff; msr++)
-		vmx_disable_intercept_msr_read_x2apic(msr, true);
+	vmx_disable_intercept_msr_x2apic(0x808, MSR_TYPE_W, true);
+	vmx_disable_intercept_msr_x2apic(0x808, MSR_TYPE_R | MSR_TYPE_W, false);
 
-	/* TMCCT */
-	vmx_enable_intercept_msr_read_x2apic(0x839, true);
-	/* TPR */
-	vmx_disable_intercept_msr_write_x2apic(0x808, true);
 	/* EOI */
-	vmx_disable_intercept_msr_write_x2apic(0x80b, true);
+	vmx_disable_intercept_msr_x2apic(0x80b, MSR_TYPE_W, true);
 	/* SELF-IPI */
-	vmx_disable_intercept_msr_write_x2apic(0x83f, true);
-
-	/*
-	 * (enable_apicv && !kvm_vcpu_apicv_active()) ||
-	 * 	!enable_apicv
-	 */
-	/* TPR */
-	vmx_disable_intercept_msr_read_x2apic(0x808, false);
-	vmx_disable_intercept_msr_write_x2apic(0x808, false);
+	vmx_disable_intercept_msr_x2apic(0x83f, MSR_TYPE_W, true);
 
 	if (enable_ept) {
 		kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK,
@@ -6551,42 +6748,19 @@ static __init int hardware_setup(void)
 
 	return alloc_kvm_area();
 
-out9:
-	free_page((unsigned long)vmx_vmwrite_bitmap);
-out8:
-	free_page((unsigned long)vmx_vmread_bitmap);
-out7:
-	free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic_apicv_inactive);
-out6:
-	free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
-out5:
-	free_page((unsigned long)vmx_msr_bitmap_longmode);
-out4:
-	free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic_apicv_inactive);
-out3:
-	free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
-out2:
-	free_page((unsigned long)vmx_msr_bitmap_legacy);
-out1:
-	free_page((unsigned long)vmx_io_bitmap_b);
 out:
-	free_page((unsigned long)vmx_io_bitmap_a);
+	for (i = 0; i < VMX_BITMAP_NR; i++)
+		free_page((unsigned long)vmx_bitmap[i]);
 
     return r;
 }
 
 static __exit void hardware_unsetup(void)
 {
-	free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
-	free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic_apicv_inactive);
-	free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
-	free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic_apicv_inactive);
-	free_page((unsigned long)vmx_msr_bitmap_legacy);
-	free_page((unsigned long)vmx_msr_bitmap_longmode);
-	free_page((unsigned long)vmx_io_bitmap_b);
-	free_page((unsigned long)vmx_io_bitmap_a);
-	free_page((unsigned long)vmx_vmwrite_bitmap);
-	free_page((unsigned long)vmx_vmread_bitmap);
+	int i;
+
+	for (i = 0; i < VMX_BITMAP_NR; i++)
+		free_page((unsigned long)vmx_bitmap[i]);
 
 	free_kvm_area();
 }
@@ -6600,16 +6774,13 @@ static int handle_pause(struct kvm_vcpu *vcpu)
 	if (ple_gap)
 		grow_ple_window(vcpu);
 
-	skip_emulated_instruction(vcpu);
 	kvm_vcpu_on_spin(vcpu);
-
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 static int handle_nop(struct kvm_vcpu *vcpu)
 {
-	skip_emulated_instruction(vcpu);
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 static int handle_mwait(struct kvm_vcpu *vcpu)
@@ -6916,8 +7087,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
 		 */
 		if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
 			nested_vmx_failInvalid(vcpu);
-			skip_emulated_instruction(vcpu);
-			return 1;
+			return kvm_skip_emulated_instruction(vcpu);
 		}
 
 		page = nested_get_page(vcpu, vmptr);
@@ -6925,8 +7095,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
 		    *(u32 *)kmap(page) != VMCS12_REVISION) {
 			nested_vmx_failInvalid(vcpu);
 			kunmap(page);
-			skip_emulated_instruction(vcpu);
-			return 1;
+			return kvm_skip_emulated_instruction(vcpu);
 		}
 		kunmap(page);
 		vmx->nested.vmxon_ptr = vmptr;
@@ -6935,30 +7104,26 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
 		if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
 			nested_vmx_failValid(vcpu,
 					     VMXERR_VMCLEAR_INVALID_ADDRESS);
-			skip_emulated_instruction(vcpu);
-			return 1;
+			return kvm_skip_emulated_instruction(vcpu);
 		}
 
 		if (vmptr == vmx->nested.vmxon_ptr) {
 			nested_vmx_failValid(vcpu,
 					     VMXERR_VMCLEAR_VMXON_POINTER);
-			skip_emulated_instruction(vcpu);
-			return 1;
+			return kvm_skip_emulated_instruction(vcpu);
 		}
 		break;
 	case EXIT_REASON_VMPTRLD:
 		if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
 			nested_vmx_failValid(vcpu,
 					     VMXERR_VMPTRLD_INVALID_ADDRESS);
-			skip_emulated_instruction(vcpu);
-			return 1;
+			return kvm_skip_emulated_instruction(vcpu);
 		}
 
 		if (vmptr == vmx->nested.vmxon_ptr) {
 			nested_vmx_failValid(vcpu,
 					     VMXERR_VMCLEAR_VMXON_POINTER);
-			skip_emulated_instruction(vcpu);
-			return 1;
+			return kvm_skip_emulated_instruction(vcpu);
 		}
 		break;
 	default:
@@ -7014,8 +7179,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 
 	if (vmx->nested.vmxon) {
 		nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
-		skip_emulated_instruction(vcpu);
-		return 1;
+		return kvm_skip_emulated_instruction(vcpu);
 	}
 
 	if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
@@ -7055,9 +7219,8 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 
 	vmx->nested.vmxon = true;
 
-	skip_emulated_instruction(vcpu);
 	nested_vmx_succeed(vcpu);
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 
 out_shadow_vmcs:
 	kfree(vmx->nested.cached_vmcs12);
@@ -7176,9 +7339,8 @@ static int handle_vmoff(struct kvm_vcpu *vcpu)
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 	free_nested(to_vmx(vcpu));
-	skip_emulated_instruction(vcpu);
 	nested_vmx_succeed(vcpu);
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 /* Emulate the VMCLEAR instruction */
@@ -7217,9 +7379,8 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
 
 	nested_free_vmcs02(vmx, vmptr);
 
-	skip_emulated_instruction(vcpu);
 	nested_vmx_succeed(vcpu);
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch);
@@ -7417,7 +7578,6 @@ static int nested_vmx_check_vmcs12(struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	if (vmx->nested.current_vmptr == -1ull) {
 		nested_vmx_failInvalid(vcpu);
-		skip_emulated_instruction(vcpu);
 		return 0;
 	}
 	return 1;
@@ -7431,17 +7591,18 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
 	gva_t gva = 0;
 
-	if (!nested_vmx_check_permission(vcpu) ||
-	    !nested_vmx_check_vmcs12(vcpu))
+	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
+	if (!nested_vmx_check_vmcs12(vcpu))
+		return kvm_skip_emulated_instruction(vcpu);
+
 	/* Decode instruction info and find the field to read */
 	field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
 	/* Read the field, zero-extended to a u64 field_value */
 	if (vmcs12_read_any(vcpu, field, &field_value) < 0) {
 		nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
-		skip_emulated_instruction(vcpu);
-		return 1;
+		return kvm_skip_emulated_instruction(vcpu);
 	}
 	/*
 	 * Now copy part of this value to register or memory, as requested.
@@ -7461,8 +7622,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 	}
 
 	nested_vmx_succeed(vcpu);
-	skip_emulated_instruction(vcpu);
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 
@@ -7481,10 +7641,12 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 	u64 field_value = 0;
 	struct x86_exception e;
 
-	if (!nested_vmx_check_permission(vcpu) ||
-	    !nested_vmx_check_vmcs12(vcpu))
+	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
+	if (!nested_vmx_check_vmcs12(vcpu))
+		return kvm_skip_emulated_instruction(vcpu);
+
 	if (vmx_instruction_info & (1u << 10))
 		field_value = kvm_register_readl(vcpu,
 			(((vmx_instruction_info) >> 3) & 0xf));
@@ -7504,19 +7666,16 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 	if (vmcs_field_readonly(field)) {
 		nested_vmx_failValid(vcpu,
 			VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT);
-		skip_emulated_instruction(vcpu);
-		return 1;
+		return kvm_skip_emulated_instruction(vcpu);
 	}
 
 	if (vmcs12_write_any(vcpu, field, field_value) < 0) {
 		nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
-		skip_emulated_instruction(vcpu);
-		return 1;
+		return kvm_skip_emulated_instruction(vcpu);
 	}
 
 	nested_vmx_succeed(vcpu);
-	skip_emulated_instruction(vcpu);
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 /* Emulate the VMPTRLD instruction */
@@ -7537,8 +7696,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		page = nested_get_page(vcpu, vmptr);
 		if (page == NULL) {
 			nested_vmx_failInvalid(vcpu);
-			skip_emulated_instruction(vcpu);
-			return 1;
+			return kvm_skip_emulated_instruction(vcpu);
 		}
 		new_vmcs12 = kmap(page);
 		if (new_vmcs12->revision_id != VMCS12_REVISION) {
@@ -7546,8 +7704,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 			nested_release_page_clean(page);
 			nested_vmx_failValid(vcpu,
 				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
-			skip_emulated_instruction(vcpu);
-			return 1;
+			return kvm_skip_emulated_instruction(vcpu);
 		}
 
 		nested_release_vmcs12(vmx);
@@ -7571,8 +7728,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 	}
 
 	nested_vmx_succeed(vcpu);
-	skip_emulated_instruction(vcpu);
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 /* Emulate the VMPTRST instruction */
@@ -7597,8 +7753,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
 		return 1;
 	}
 	nested_vmx_succeed(vcpu);
-	skip_emulated_instruction(vcpu);
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 /* Emulate the INVEPT instruction */
@@ -7636,8 +7791,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	if (type >= 32 || !(types & (1 << type))) {
 		nested_vmx_failValid(vcpu,
 				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
-		skip_emulated_instruction(vcpu);
-		return 1;
+		return kvm_skip_emulated_instruction(vcpu);
 	}
 
 	/* According to the Intel VMX instruction reference, the memory
@@ -7668,8 +7822,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 		break;
 	}
 
-	skip_emulated_instruction(vcpu);
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 static int handle_invvpid(struct kvm_vcpu *vcpu)
@@ -7694,13 +7847,13 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
 	type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf);
 
-	types = (vmx->nested.nested_vmx_vpid_caps >> 8) & 0x7;
+	types = (vmx->nested.nested_vmx_vpid_caps &
+			VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8;
 
 	if (type >= 32 || !(types & (1 << type))) {
 		nested_vmx_failValid(vcpu,
 			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
-		skip_emulated_instruction(vcpu);
-		return 1;
+		return kvm_skip_emulated_instruction(vcpu);
 	}
 
 	/* according to the intel vmx instruction reference, the memory
@@ -7716,23 +7869,26 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 	}
 
 	switch (type) {
+	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
 	case VMX_VPID_EXTENT_SINGLE_CONTEXT:
-		/*
-		 * Old versions of KVM use the single-context version so we
-		 * have to support it; just treat it the same as all-context.
-		 */
+	case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL:
+		if (!vpid) {
+			nested_vmx_failValid(vcpu,
+				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+			return kvm_skip_emulated_instruction(vcpu);
+		}
+		break;
 	case VMX_VPID_EXTENT_ALL_CONTEXT:
-		__vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
-		nested_vmx_succeed(vcpu);
 		break;
 	default:
-		/* Trap individual address invalidation invvpid calls */
-		BUG_ON(1);
-		break;
+		WARN_ON_ONCE(1);
+		return kvm_skip_emulated_instruction(vcpu);
 	}
 
-	skip_emulated_instruction(vcpu);
-	return 1;
+	__vmx_flush_tlb(vcpu, vmx->nested.vpid02);
+	nested_vmx_succeed(vcpu);
+
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 static int handle_pml_full(struct kvm_vcpu *vcpu)
@@ -8071,6 +8227,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		return nested_cpu_has(vmcs12, CPU_BASED_MOV_DR_EXITING);
 	case EXIT_REASON_IO_INSTRUCTION:
 		return nested_vmx_exit_handled_io(vcpu, vmcs12);
+	case EXIT_REASON_GDTR_IDTR: case EXIT_REASON_LDTR_TR:
+		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC);
 	case EXIT_REASON_MSR_READ:
 	case EXIT_REASON_MSR_WRITE:
 		return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason);
@@ -8620,11 +8778,6 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 	u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
 	register void *__sp asm(_ASM_SP);
 
-	/*
-	 * If external interrupt exists, IF bit is set in rflags/eflags on the
-	 * interrupt stack frame, and interrupt will be enabled on a return
-	 * from interrupt handler.
-	 */
 	if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK))
 			== (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) {
 		unsigned int vector;
@@ -8809,7 +8962,7 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 					msrs[i].host);
 }
 
-void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
+static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u64 tscl;
@@ -9279,6 +9432,50 @@ static void vmcs_set_secondary_exec_control(u32 new_ctl)
 		     (new_ctl & ~mask) | (cur_ctl & mask));
 }
 
+/*
+ * Generate MSR_IA32_VMX_CR{0,4}_FIXED1 according to CPUID. Only set bits
+ * (indicating "allowed-1") if they are supported in the guest's CPUID.
+ */
+static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct kvm_cpuid_entry2 *entry;
+
+	vmx->nested.nested_vmx_cr0_fixed1 = 0xffffffff;
+	vmx->nested.nested_vmx_cr4_fixed1 = X86_CR4_PCE;
+
+#define cr4_fixed1_update(_cr4_mask, _reg, _cpuid_mask) do {		\
+	if (entry && (entry->_reg & (_cpuid_mask)))			\
+		vmx->nested.nested_vmx_cr4_fixed1 |= (_cr4_mask);	\
+} while (0)
+
+	entry = kvm_find_cpuid_entry(vcpu, 0x1, 0);
+	cr4_fixed1_update(X86_CR4_VME,        edx, bit(X86_FEATURE_VME));
+	cr4_fixed1_update(X86_CR4_PVI,        edx, bit(X86_FEATURE_VME));
+	cr4_fixed1_update(X86_CR4_TSD,        edx, bit(X86_FEATURE_TSC));
+	cr4_fixed1_update(X86_CR4_DE,         edx, bit(X86_FEATURE_DE));
+	cr4_fixed1_update(X86_CR4_PSE,        edx, bit(X86_FEATURE_PSE));
+	cr4_fixed1_update(X86_CR4_PAE,        edx, bit(X86_FEATURE_PAE));
+	cr4_fixed1_update(X86_CR4_MCE,        edx, bit(X86_FEATURE_MCE));
+	cr4_fixed1_update(X86_CR4_PGE,        edx, bit(X86_FEATURE_PGE));
+	cr4_fixed1_update(X86_CR4_OSFXSR,     edx, bit(X86_FEATURE_FXSR));
+	cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, bit(X86_FEATURE_XMM));
+	cr4_fixed1_update(X86_CR4_VMXE,       ecx, bit(X86_FEATURE_VMX));
+	cr4_fixed1_update(X86_CR4_SMXE,       ecx, bit(X86_FEATURE_SMX));
+	cr4_fixed1_update(X86_CR4_PCIDE,      ecx, bit(X86_FEATURE_PCID));
+	cr4_fixed1_update(X86_CR4_OSXSAVE,    ecx, bit(X86_FEATURE_XSAVE));
+
+	entry = kvm_find_cpuid_entry(vcpu, 0x7, 0);
+	cr4_fixed1_update(X86_CR4_FSGSBASE,   ebx, bit(X86_FEATURE_FSGSBASE));
+	cr4_fixed1_update(X86_CR4_SMEP,       ebx, bit(X86_FEATURE_SMEP));
+	cr4_fixed1_update(X86_CR4_SMAP,       ebx, bit(X86_FEATURE_SMAP));
+	cr4_fixed1_update(X86_CR4_PKE,        ecx, bit(X86_FEATURE_PKU));
+	/* TODO: Use X86_CR4_UMIP and X86_FEATURE_UMIP macros */
+	cr4_fixed1_update(bit(11),            ecx, bit(2));
+
+#undef cr4_fixed1_update
+}
+
 static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
@@ -9320,6 +9517,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 	else
 		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
 			~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+
+	if (nested_vmx_allowed(vcpu))
+		nested_vmx_cr_fixed1_bits_update(vcpu);
 }
 
 static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
@@ -9774,6 +9974,49 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 	return 0;
 }
 
+static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	unsigned long invalid_mask;
+
+	invalid_mask = (~0ULL) << cpuid_maxphyaddr(vcpu);
+	return (val & invalid_mask) == 0;
+}
+
+/*
+ * Load guest's/host's cr3 at nested entry/exit. nested_ept is true if we are
+ * emulating VM entry into a guest with EPT enabled.
+ * Returns 0 on success, 1 on failure. Invalid state exit qualification code
+ * is assigned to entry_failure_code on failure.
+ */
+static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept,
+			       unsigned long *entry_failure_code)
+{
+	if (cr3 != kvm_read_cr3(vcpu) || (!nested_ept && pdptrs_changed(vcpu))) {
+		if (!nested_cr3_valid(vcpu, cr3)) {
+			*entry_failure_code = ENTRY_FAIL_DEFAULT;
+			return 1;
+		}
+
+		/*
+		 * If PAE paging and EPT are both on, CR3 is not used by the CPU and
+		 * must not be dereferenced.
+		 */
+		if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu) &&
+		    !nested_ept) {
+			if (!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) {
+				*entry_failure_code = ENTRY_FAIL_PDPTE;
+				return 1;
+			}
+		}
+
+		vcpu->arch.cr3 = cr3;
+		__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	}
+
+	kvm_mmu_reset_context(vcpu);
+	return 0;
+}
+
 /*
  * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
  * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
@@ -9782,11 +10025,15 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
  * needs. In addition to modifying the active vmcs (which is vmcs02), this
  * function also has additional necessary side-effects, like setting various
  * vcpu->arch fields.
+ * Returns 0 on success, 1 on failure. Invalid state exit qualification code
+ * is assigned to entry_failure_code on failure.
  */
-static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
+static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
+			  unsigned long *entry_failure_code)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 exec_control;
+	bool nested_ept_enabled = false;
 
 	vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
 	vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
@@ -9951,6 +10198,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 				vmcs12->guest_intr_status);
 		}
 
+		nested_ept_enabled = (exec_control & SECONDARY_EXEC_ENABLE_EPT) != 0;
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
 	}
 
@@ -9963,6 +10211,15 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	 */
 	vmx_set_constant_host_state(vmx);
 
+	/*
+	 * Set the MSR load/store lists to match L0's settings.
+	 */
+	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
+	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
+	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
+
 	/*
 	 * HOST_RSP is normally set correctly in vmx_vcpu_run() just before
 	 * entry, but only if the current (host) sp changed from the value
@@ -10069,15 +10326,6 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		nested_ept_init_mmu_context(vcpu);
 	}
 
-	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)
-		vcpu->arch.efer = vmcs12->guest_ia32_efer;
-	else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
-		vcpu->arch.efer |= (EFER_LMA | EFER_LME);
-	else
-		vcpu->arch.efer &= ~(EFER_LMA | EFER_LME);
-	/* Note: modifies VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */
-	vmx_set_efer(vcpu, vcpu->arch.efer);
-
 	/*
 	 * This sets GUEST_CR0 to vmcs12->guest_cr0, with possibly a modified
 	 * TS bit (for lazy fpu) and bits which we consider mandatory enabled.
@@ -10092,8 +10340,20 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	vmx_set_cr4(vcpu, vmcs12->guest_cr4);
 	vmcs_writel(CR4_READ_SHADOW, nested_read_cr4(vmcs12));
 
-	/* shadow page tables on either EPT or shadow page tables */
-	kvm_set_cr3(vcpu, vmcs12->guest_cr3);
+	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)
+		vcpu->arch.efer = vmcs12->guest_ia32_efer;
+	else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
+		vcpu->arch.efer |= (EFER_LMA | EFER_LME);
+	else
+		vcpu->arch.efer &= ~(EFER_LMA | EFER_LME);
+	/* Note: modifies VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */
+	vmx_set_efer(vcpu, vcpu->arch.efer);
+
+	/* Shadow page tables on either EPT or shadow page tables. */
+	if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_ept_enabled,
+				entry_failure_code))
+		return 1;
+
 	kvm_mmu_reset_context(vcpu);
 
 	if (!enable_ept)
@@ -10111,6 +10371,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 	kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);
 	kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->guest_rip);
+	return 0;
 }
 
 /*
@@ -10125,12 +10386,14 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	struct loaded_vmcs *vmcs02;
 	bool ia32e;
 	u32 msr_entry_idx;
+	unsigned long exit_qualification;
 
-	if (!nested_vmx_check_permission(vcpu) ||
-	    !nested_vmx_check_vmcs12(vcpu))
+	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	skip_emulated_instruction(vcpu);
+	if (!nested_vmx_check_vmcs12(vcpu))
+		goto out;
+
 	vmcs12 = get_vmcs12(vcpu);
 
 	if (enable_shadow_vmcs)
@@ -10150,37 +10413,37 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		nested_vmx_failValid(vcpu,
 			launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS
 			       : VMXERR_VMRESUME_NONLAUNCHED_VMCS);
-		return 1;
+		goto out;
 	}
 
 	if (vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE &&
 	    vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) {
 		nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
-		return 1;
+		goto out;
 	}
 
 	if (!nested_get_vmcs12_pages(vcpu, vmcs12)) {
 		nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
-		return 1;
+		goto out;
 	}
 
 	if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12)) {
 		nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
-		return 1;
+		goto out;
 	}
 
 	if (nested_vmx_check_apicv_controls(vcpu, vmcs12)) {
 		nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
-		return 1;
+		goto out;
 	}
 
 	if (nested_vmx_check_msr_switch_controls(vcpu, vmcs12)) {
 		nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
-		return 1;
+		goto out;
 	}
 
 	if (!vmx_control_verify(vmcs12->cpu_based_vm_exec_control,
-				vmx->nested.nested_vmx_true_procbased_ctls_low,
+				vmx->nested.nested_vmx_procbased_ctls_low,
 				vmx->nested.nested_vmx_procbased_ctls_high) ||
 	    !vmx_control_verify(vmcs12->secondary_vm_exec_control,
 				vmx->nested.nested_vmx_secondary_ctls_low,
@@ -10189,33 +10452,34 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 				vmx->nested.nested_vmx_pinbased_ctls_low,
 				vmx->nested.nested_vmx_pinbased_ctls_high) ||
 	    !vmx_control_verify(vmcs12->vm_exit_controls,
-				vmx->nested.nested_vmx_true_exit_ctls_low,
+				vmx->nested.nested_vmx_exit_ctls_low,
 				vmx->nested.nested_vmx_exit_ctls_high) ||
 	    !vmx_control_verify(vmcs12->vm_entry_controls,
-				vmx->nested.nested_vmx_true_entry_ctls_low,
+				vmx->nested.nested_vmx_entry_ctls_low,
 				vmx->nested.nested_vmx_entry_ctls_high))
 	{
 		nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
-		return 1;
+		goto out;
 	}
 
-	if (((vmcs12->host_cr0 & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON) ||
-	    ((vmcs12->host_cr4 & VMXON_CR4_ALWAYSON) != VMXON_CR4_ALWAYSON)) {
+	if (!nested_host_cr0_valid(vcpu, vmcs12->host_cr0) ||
+	    !nested_host_cr4_valid(vcpu, vmcs12->host_cr4) ||
+	    !nested_cr3_valid(vcpu, vmcs12->host_cr3)) {
 		nested_vmx_failValid(vcpu,
 			VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);
-		return 1;
+		goto out;
 	}
 
-	if (!nested_cr0_valid(vcpu, vmcs12->guest_cr0) ||
-	    ((vmcs12->guest_cr4 & VMXON_CR4_ALWAYSON) != VMXON_CR4_ALWAYSON)) {
+	if (!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0) ||
+	    !nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)) {
 		nested_vmx_entry_failure(vcpu, vmcs12,
 			EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT);
-		return 1;
+		goto out;
 	}
 	if (vmcs12->vmcs_link_pointer != -1ull) {
 		nested_vmx_entry_failure(vcpu, vmcs12,
 			EXIT_REASON_INVALID_STATE, ENTRY_FAIL_VMCS_LINK_PTR);
-		return 1;
+		goto out;
 	}
 
 	/*
@@ -10235,7 +10499,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		     ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME))) {
 			nested_vmx_entry_failure(vcpu, vmcs12,
 				EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT);
-			return 1;
+			goto out;
 		}
 	}
 
@@ -10253,7 +10517,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		    ia32e != !!(vmcs12->host_ia32_efer & EFER_LME)) {
 			nested_vmx_entry_failure(vcpu, vmcs12,
 				EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT);
-			return 1;
+			goto out;
 		}
 	}
 
@@ -10266,6 +10530,12 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	if (!vmcs02)
 		return -ENOMEM;
 
+	/*
+	 * After this point, the trap flag no longer triggers a singlestep trap
+	 * on the vm entry instructions. Don't call
+	 * kvm_skip_emulated_instruction.
+	 */
+	skip_emulated_instruction(vcpu);
 	enter_guest_mode(vcpu);
 
 	if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
@@ -10280,7 +10550,13 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 
 	vmx_segment_cache_clear(vmx);
 
-	prepare_vmcs02(vcpu, vmcs12);
+	if (prepare_vmcs02(vcpu, vmcs12, &exit_qualification)) {
+		leave_guest_mode(vcpu);
+		vmx_load_vmcs01(vcpu);
+		nested_vmx_entry_failure(vcpu, vmcs12,
+				EXIT_REASON_INVALID_STATE, exit_qualification);
+		return 1;
+	}
 
 	msr_entry_idx = nested_vmx_load_msr(vcpu,
 					    vmcs12->vm_entry_msr_load_addr,
@@ -10307,6 +10583,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	 * the success flag) when L2 exits (see nested_vmx_vmexit()).
 	 */
 	return 1;
+
+out:
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 /*
@@ -10612,6 +10891,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 				   struct vmcs12 *vmcs12)
 {
 	struct kvm_segment seg;
+	unsigned long entry_failure_code;
 
 	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
 		vcpu->arch.efer = vmcs12->host_ia32_efer;
@@ -10649,8 +10929,12 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 
 	nested_ept_uninit_mmu_context(vcpu);
 
-	kvm_set_cr3(vcpu, vmcs12->host_cr3);
-	kvm_mmu_reset_context(vcpu);
+	/*
+	 * Only PDPTE load can fail as the value of cr3 was checked on entry and
+	 * couldn't have changed.
+	 */
+	if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
+		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
 
 	if (!enable_ept)
 		vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
@@ -10751,6 +11035,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	u32 vm_inst_error = 0;
 
 	/* trying to cancel vmlaunch/vmresume is a bug */
 	WARN_ON_ONCE(vmx->nested.nested_run_pending);
@@ -10763,6 +11048,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 				 vmcs12->vm_exit_msr_store_count))
 		nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL);
 
+	if (unlikely(vmx->fail))
+		vm_inst_error = vmcs_read32(VM_INSTRUCTION_ERROR);
+
 	vmx_load_vmcs01(vcpu);
 
 	if ((exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT)
@@ -10791,6 +11079,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	load_vmcs12_host_state(vcpu, vmcs12);
 
 	/* Update any VMCS fields that might have changed while L2 ran */
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
 	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
 	if (vmx->hv_deadline_tsc == -1)
 		vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
@@ -10839,7 +11129,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	 */
 	if (unlikely(vmx->fail)) {
 		vmx->fail = 0;
-		nested_vmx_failValid(vcpu, vmcs_read32(VM_INSTRUCTION_ERROR));
+		nested_vmx_failValid(vcpu, vm_inst_error);
 	} else
 		nested_vmx_succeed(vcpu);
 	if (enable_shadow_vmcs)

arch/x86/kvm/x86.c

@@ -434,12 +434,14 @@ void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
 }
 EXPORT_SYMBOL_GPL(kvm_requeue_exception);
 
-void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
+int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
 {
 	if (err)
 		kvm_inject_gp(vcpu, 0);
 	else
-		kvm_x86_ops->skip_emulated_instruction(vcpu);
+		return kvm_skip_emulated_instruction(vcpu);
+
+	return 1;
 }
 EXPORT_SYMBOL_GPL(kvm_complete_insn_gp);
 
@@ -573,7 +575,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(load_pdptrs);
 
-static bool pdptrs_changed(struct kvm_vcpu *vcpu)
+bool pdptrs_changed(struct kvm_vcpu *vcpu)
 {
 	u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)];
 	bool changed = true;
@@ -599,6 +601,7 @@ out:
 
 	return changed;
 }
+EXPORT_SYMBOL_GPL(pdptrs_changed);
 
 int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 {
@@ -2178,7 +2181,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_KVM_SYSTEM_TIME_NEW:
 	case MSR_KVM_SYSTEM_TIME: {
-		u64 gpa_offset;
 		struct kvm_arch *ka = &vcpu->kvm->arch;
 
 		kvmclock_reset(vcpu);
@@ -2200,8 +2202,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!(data & 1))
 			break;
 
-		gpa_offset = data & ~(PAGE_MASK | 1);
-
 		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
 		     &vcpu->arch.pv_time, data & ~1ULL,
 		     sizeof(struct pvclock_vcpu_time_info)))
@@ -2296,7 +2296,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (kvm_pmu_is_valid_msr(vcpu, msr))
 			return kvm_pmu_set_msr(vcpu, msr_info);
 		if (!ignore_msrs) {
-			vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data 0x%llx\n",
+			vcpu_debug_ratelimited(vcpu, "unhandled wrmsr: 0x%x data 0x%llx\n",
 				    msr, data);
 			return 1;
 		} else {
@@ -2508,7 +2508,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (kvm_pmu_is_valid_msr(vcpu, msr_info->index))
 			return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data);
 		if (!ignore_msrs) {
-			vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr_info->index);
+			vcpu_debug_ratelimited(vcpu, "unhandled rdmsr: 0x%x\n",
+					       msr_info->index);
 			return 1;
 		} else {
 			vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr_info->index);
@@ -2812,7 +2813,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		}
 		if (kvm_lapic_hv_timer_in_use(vcpu) &&
 				kvm_x86_ops->set_hv_timer(vcpu,
-					kvm_get_lapic_tscdeadline_msr(vcpu)))
+					kvm_get_lapic_target_expiration_tsc(vcpu)))
 			kvm_lapic_switch_to_sw_timer(vcpu);
 		/*
 		 * On a host with synchronized TSC, there is no need to update
@@ -4832,7 +4833,7 @@ static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address)
 	kvm_mmu_invlpg(emul_to_vcpu(ctxt), address);
 }
 
-int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu)
+static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu)
 {
 	if (!need_emulate_wbinvd(vcpu))
 		return X86EMUL_CONTINUE;
@@ -4852,8 +4853,8 @@ int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu)
 
 int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu)
 {
-	kvm_x86_ops->skip_emulated_instruction(vcpu);
-	return kvm_emulate_wbinvd_noskip(vcpu);
+	kvm_emulate_wbinvd_noskip(vcpu);
+	return kvm_skip_emulated_instruction(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd);
 
@@ -5451,7 +5452,6 @@ static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflag
 			kvm_run->exit_reason = KVM_EXIT_DEBUG;
 			*r = EMULATE_USER_EXIT;
 		} else {
-			vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF;
 			/*
 			 * "Certain debug exceptions may clear bit 0-3.  The
 			 * remaining contents of the DR6 register are never
@@ -5464,6 +5464,17 @@ static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflag
 	}
 }
 
+int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu)
+{
+	unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
+	int r = EMULATE_DONE;
+
+	kvm_x86_ops->skip_emulated_instruction(vcpu);
+	kvm_vcpu_check_singlestep(vcpu, rflags, &r);
+	return r == EMULATE_DONE;
+}
+EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction);
+
 static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r)
 {
 	if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) &&
@@ -5649,6 +5660,49 @@ int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port)
 }
 EXPORT_SYMBOL_GPL(kvm_fast_pio_out);
 
+static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
+{
+	unsigned long val;
+
+	/* We should only ever be called with arch.pio.count equal to 1 */
+	BUG_ON(vcpu->arch.pio.count != 1);
+
+	/* For size less than 4 we merge, else we zero extend */
+	val = (vcpu->arch.pio.size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX)
+					: 0;
+
+	/*
+	 * Since vcpu->arch.pio.count == 1 let emulator_pio_in_emulated perform
+	 * the copy and tracing
+	 */
+	emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, vcpu->arch.pio.size,
+				 vcpu->arch.pio.port, &val, 1);
+	kvm_register_write(vcpu, VCPU_REGS_RAX, val);
+
+	return 1;
+}
+
+int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port)
+{
+	unsigned long val;
+	int ret;
+
+	/* For size less than 4 we merge, else we zero extend */
+	val = (size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX) : 0;
+
+	ret = emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, size, port,
+				       &val, 1);
+	if (ret) {
+		kvm_register_write(vcpu, VCPU_REGS_RAX, val);
+		return ret;
+	}
+
+	vcpu->arch.complete_userspace_io = complete_fast_pio_in;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_fast_pio_in);
+
 static int kvmclock_cpu_down_prep(unsigned int cpu)
 {
 	__this_cpu_write(cpu_tsc_khz, 0);
@@ -5998,8 +6052,12 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_halt);
 
 int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 {
-	kvm_x86_ops->skip_emulated_instruction(vcpu);
-	return kvm_vcpu_halt(vcpu);
+	int ret = kvm_skip_emulated_instruction(vcpu);
+	/*
+	 * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered
+	 * KVM_EXIT_DEBUG here.
+	 */
+	return kvm_vcpu_halt(vcpu) && ret;
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_halt);
 
@@ -6030,9 +6088,9 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu)
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
-	int op_64_bit, r = 1;
+	int op_64_bit, r;
 
-	kvm_x86_ops->skip_emulated_instruction(vcpu);
+	r = kvm_skip_emulated_instruction(vcpu);
 
 	if (kvm_hv_hypercall_enabled(vcpu->kvm))
 		return kvm_hv_hypercall(vcpu);

include/linux/irqchip/arm-gic-v3.h

@@ -295,10 +295,10 @@
 #define GITS_BASER_InnerShareable					\
 	GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)
 #define GITS_BASER_PAGE_SIZE_SHIFT	(8)
-#define GITS_BASER_PAGE_SIZE_4K		(0UL << GITS_BASER_PAGE_SIZE_SHIFT)
-#define GITS_BASER_PAGE_SIZE_16K	(1UL << GITS_BASER_PAGE_SIZE_SHIFT)
-#define GITS_BASER_PAGE_SIZE_64K	(2UL << GITS_BASER_PAGE_SIZE_SHIFT)
-#define GITS_BASER_PAGE_SIZE_MASK	(3UL << GITS_BASER_PAGE_SIZE_SHIFT)
+#define GITS_BASER_PAGE_SIZE_4K		(0ULL << GITS_BASER_PAGE_SIZE_SHIFT)
+#define GITS_BASER_PAGE_SIZE_16K	(1ULL << GITS_BASER_PAGE_SIZE_SHIFT)
+#define GITS_BASER_PAGE_SIZE_64K	(2ULL << GITS_BASER_PAGE_SIZE_SHIFT)
+#define GITS_BASER_PAGE_SIZE_MASK	(3ULL << GITS_BASER_PAGE_SIZE_SHIFT)
 #define GITS_BASER_PAGES_MAX		256
 #define GITS_BASER_PAGES_SHIFT		(0)
 #define GITS_BASER_NR_PAGES(r)		(((r) & 0xff) + 1)

include/linux/kvm_host.h

@@ -438,6 +438,9 @@ struct kvm {
 	pr_info("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__)
 #define kvm_debug(fmt, ...) \
 	pr_debug("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__)
+#define kvm_debug_ratelimited(fmt, ...) \
+	pr_debug_ratelimited("kvm [%i]: " fmt, task_pid_nr(current), \
+			     ## __VA_ARGS__)
 #define kvm_pr_unimpl(fmt, ...) \
 	pr_err_ratelimited("kvm [%i]: " fmt, \
 			   task_tgid_nr(current), ## __VA_ARGS__)
@@ -449,6 +452,9 @@ struct kvm {
 
 #define vcpu_debug(vcpu, fmt, ...)					\
 	kvm_debug("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
+#define vcpu_debug_ratelimited(vcpu, fmt, ...)				\
+	kvm_debug_ratelimited("vcpu%i " fmt, (vcpu)->vcpu_id,           \
+			      ## __VA_ARGS__)
 #define vcpu_err(vcpu, fmt, ...)					\
 	kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
 
@@ -1108,6 +1114,10 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
 
 extern bool kvm_rebooting;
 
+extern unsigned int halt_poll_ns;
+extern unsigned int halt_poll_ns_grow;
+extern unsigned int halt_poll_ns_shrink;
+
 struct kvm_device {
 	struct kvm_device_ops *ops;
 	struct kvm *kvm;

include/uapi/linux/kvm.h

@@ -651,6 +651,9 @@ struct kvm_enable_cap {
 };
 
 /* for KVM_PPC_GET_PVINFO */
+
+#define KVM_PPC_PVINFO_FLAGS_EV_IDLE   (1<<0)
+
 struct kvm_ppc_pvinfo {
 	/* out */
 	__u32 flags;
@@ -682,8 +685,6 @@ struct kvm_ppc_smmu_info {
 	struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
 };
 
-#define KVM_PPC_PVINFO_FLAGS_EV_IDLE   (1<<0)
-
 #define KVMIO 0xAE
 
 /* machine type bits, to be used as argument to KVM_CREATE_VM */

virt/kvm/arm/arch_timer.c

@@ -425,6 +425,11 @@ int kvm_timer_hyp_init(void)
 	info = arch_timer_get_kvm_info();
 	timecounter = &info->timecounter;
 
+	if (!timecounter->cc) {
+		kvm_err("kvm_arch_timer: uninitialized timecounter\n");
+		return -ENODEV;
+	}
+
 	if (info->virtual_irq <= 0) {
 		kvm_err("kvm_arch_timer: invalid virtual timer IRQ: %d\n",
 			info->virtual_irq);
@@ -498,17 +503,7 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
 	if (ret)
 		return ret;
 
-
-	/*
-	 * There is a potential race here between VCPUs starting for the first
-	 * time, which may be enabling the timer multiple times.  That doesn't
-	 * hurt though, because we're just setting a variable to the same
-	 * variable that it already was.  The important thing is that all
-	 * VCPUs have the enabled variable set, before entering the guest, if
-	 * the arch timers are enabled.
-	 */
-	if (timecounter)
-		timer->enabled = 1;
+	timer->enabled = 1;
 
 	return 0;
 }

virt/kvm/arm/vgic/vgic-its.c

@@ -632,21 +632,22 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, int id)
 	int index;
 	u64 indirect_ptr;
 	gfn_t gfn;
+	int esz = GITS_BASER_ENTRY_SIZE(baser);
 
 	if (!(baser & GITS_BASER_INDIRECT)) {
 		phys_addr_t addr;
 
-		if (id >= (l1_tbl_size / GITS_BASER_ENTRY_SIZE(baser)))
+		if (id >= (l1_tbl_size / esz))
 			return false;
 
-		addr = BASER_ADDRESS(baser) + id * GITS_BASER_ENTRY_SIZE(baser);
+		addr = BASER_ADDRESS(baser) + id * esz;
 		gfn = addr >> PAGE_SHIFT;
 
 		return kvm_is_visible_gfn(its->dev->kvm, gfn);
 	}
 
 	/* calculate and check the index into the 1st level */
-	index = id / (SZ_64K / GITS_BASER_ENTRY_SIZE(baser));
+	index = id / (SZ_64K / esz);
 	if (index >= (l1_tbl_size / sizeof(u64)))
 		return false;
 
@@ -670,8 +671,8 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, int id)
 	indirect_ptr &= GENMASK_ULL(51, 16);
 
 	/* Find the address of the actual entry */
-	index = id % (SZ_64K / GITS_BASER_ENTRY_SIZE(baser));
-	indirect_ptr += index * GITS_BASER_ENTRY_SIZE(baser);
+	index = id % (SZ_64K / esz);
+	indirect_ptr += index * esz;
 	gfn = indirect_ptr >> PAGE_SHIFT;
 
 	return kvm_is_visible_gfn(its->dev->kvm, gfn);

virt/kvm/arm/vgic/vgic-kvm-device.c

@@ -221,11 +221,9 @@ int kvm_register_vgic_device(unsigned long type)
 		ret = kvm_register_device_ops(&kvm_arm_vgic_v3_ops,
 					      KVM_DEV_TYPE_ARM_VGIC_V3);
 
-#ifdef CONFIG_KVM_ARM_VGIC_V3_ITS
 		if (ret)
 			break;
 		ret = kvm_vgic_register_its_device();
-#endif
 		break;
 	}
 

virt/kvm/arm/vgic/vgic-mmio-v2.c

@@ -129,6 +129,7 @@ static void vgic_mmio_write_target(struct kvm_vcpu *vcpu,
 				   unsigned long val)
 {
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 8);
+	u8 cpu_mask = GENMASK(atomic_read(&vcpu->kvm->online_vcpus) - 1, 0);
 	int i;
 
 	/* GICD_ITARGETSR[0-7] are read-only */
@@ -141,7 +142,7 @@ static void vgic_mmio_write_target(struct kvm_vcpu *vcpu,
 
 		spin_lock(&irq->irq_lock);
 
-		irq->targets = (val >> (i * 8)) & 0xff;
+		irq->targets = (val >> (i * 8)) & cpu_mask;
 		target = irq->targets ? __ffs(irq->targets) : 0;
 		irq->target_vcpu = kvm_get_vcpu(vcpu->kvm, target);
 

virt/kvm/arm/vgic/vgic-mmio-v3.c

@@ -42,7 +42,6 @@ u64 update_64bit_reg(u64 reg, unsigned int offset, unsigned int len,
 	return reg | ((u64)val << lower);
 }
 
-#ifdef CONFIG_KVM_ARM_VGIC_V3_ITS
 bool vgic_has_its(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
@@ -52,7 +51,6 @@ bool vgic_has_its(struct kvm *kvm)
 
 	return dist->has_its;
 }
-#endif
 
 static unsigned long vgic_mmio_read_v3_misc(struct kvm_vcpu *vcpu,
 					    gpa_t addr, unsigned int len)

virt/kvm/arm/vgic/vgic.h

@@ -84,37 +84,11 @@ int vgic_v3_probe(const struct gic_kvm_info *info);
 int vgic_v3_map_resources(struct kvm *kvm);
 int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t dist_base_address);
 
-#ifdef CONFIG_KVM_ARM_VGIC_V3_ITS
 int vgic_register_its_iodevs(struct kvm *kvm);
 bool vgic_has_its(struct kvm *kvm);
 int kvm_vgic_register_its_device(void);
 void vgic_enable_lpis(struct kvm_vcpu *vcpu);
 int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi);
-#else
-static inline int vgic_register_its_iodevs(struct kvm *kvm)
-{
-	return -ENODEV;
-}
-
-static inline bool vgic_has_its(struct kvm *kvm)
-{
-	return false;
-}
-
-static inline int kvm_vgic_register_its_device(void)
-{
-	return -ENODEV;
-}
-
-static inline void vgic_enable_lpis(struct kvm_vcpu *vcpu)
-{
-}
-
-static inline int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi)
-{
-	return -ENODEV;
-}
-#endif
 
 int kvm_register_vgic_device(unsigned long type);
 int vgic_lazy_init(struct kvm *kvm);

virt/kvm/kvm_main.c

@@ -70,16 +70,19 @@ MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
 /* Architectures should define their poll value according to the halt latency */
-static unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT;
+unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT;
 module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR);
+EXPORT_SYMBOL_GPL(halt_poll_ns);
 
 /* Default doubles per-vcpu halt_poll_ns. */
-static unsigned int halt_poll_ns_grow = 2;
+unsigned int halt_poll_ns_grow = 2;
 module_param(halt_poll_ns_grow, uint, S_IRUGO | S_IWUSR);
+EXPORT_SYMBOL_GPL(halt_poll_ns_grow);
 
 /* Default resets per-vcpu halt_poll_ns . */
-static unsigned int halt_poll_ns_shrink;
+unsigned int halt_poll_ns_shrink;
 module_param(halt_poll_ns_shrink, uint, S_IRUGO | S_IWUSR);
+EXPORT_SYMBOL_GPL(halt_poll_ns_shrink);
 
 /*
  * Ordering of locks:
@@ -595,7 +598,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 		stat_data->kvm = kvm;
 		stat_data->offset = p->offset;
 		kvm->debugfs_stat_data[p - debugfs_entries] = stat_data;
-		if (!debugfs_create_file(p->name, 0444,
+		if (!debugfs_create_file(p->name, 0644,
 					 kvm->debugfs_dentry,
 					 stat_data,
 					 stat_fops_per_vm[p->kind]))
@@ -3669,11 +3672,23 @@ static int vm_stat_get_per_vm(void *data, u64 *val)
 	return 0;
 }
 
+static int vm_stat_clear_per_vm(void *data, u64 val)
+{
+	struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
+
+	if (val)
+		return -EINVAL;
+
+	*(ulong *)((void *)stat_data->kvm + stat_data->offset) = 0;
+
+	return 0;
+}
+
 static int vm_stat_get_per_vm_open(struct inode *inode, struct file *file)
 {
 	__simple_attr_check_format("%llu\n", 0ull);
 	return kvm_debugfs_open(inode, file, vm_stat_get_per_vm,
-				NULL, "%llu\n");
+				vm_stat_clear_per_vm, "%llu\n");
 }
 
 static const struct file_operations vm_stat_get_per_vm_fops = {
@@ -3699,11 +3714,26 @@ static int vcpu_stat_get_per_vm(void *data, u64 *val)
 	return 0;
 }
 
+static int vcpu_stat_clear_per_vm(void *data, u64 val)
+{
+	int i;
+	struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
+	struct kvm_vcpu *vcpu;
+
+	if (val)
+		return -EINVAL;
+
+	kvm_for_each_vcpu(i, vcpu, stat_data->kvm)
+		*(u64 *)((void *)vcpu + stat_data->offset) = 0;
+
+	return 0;
+}
+
 static int vcpu_stat_get_per_vm_open(struct inode *inode, struct file *file)
 {
 	__simple_attr_check_format("%llu\n", 0ull);
 	return kvm_debugfs_open(inode, file, vcpu_stat_get_per_vm,
-				 NULL, "%llu\n");
+				 vcpu_stat_clear_per_vm, "%llu\n");
 }
 
 static const struct file_operations vcpu_stat_get_per_vm_fops = {
@@ -3738,7 +3768,26 @@ static int vm_stat_get(void *_offset, u64 *val)
 	return 0;
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, NULL, "%llu\n");
+static int vm_stat_clear(void *_offset, u64 val)
+{
+	unsigned offset = (long)_offset;
+	struct kvm *kvm;
+	struct kvm_stat_data stat_tmp = {.offset = offset};
+
+	if (val)
+		return -EINVAL;
+
+	spin_lock(&kvm_lock);
+	list_for_each_entry(kvm, &vm_list, vm_list) {
+		stat_tmp.kvm = kvm;
+		vm_stat_clear_per_vm((void *)&stat_tmp, 0);
+	}
+	spin_unlock(&kvm_lock);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, vm_stat_clear, "%llu\n");
 
 static int vcpu_stat_get(void *_offset, u64 *val)
 {
@@ -3758,7 +3807,27 @@ static int vcpu_stat_get(void *_offset, u64 *val)
 	return 0;
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, NULL, "%llu\n");
+static int vcpu_stat_clear(void *_offset, u64 val)
+{
+	unsigned offset = (long)_offset;
+	struct kvm *kvm;
+	struct kvm_stat_data stat_tmp = {.offset = offset};
+
+	if (val)
+		return -EINVAL;
+
+	spin_lock(&kvm_lock);
+	list_for_each_entry(kvm, &vm_list, vm_list) {
+		stat_tmp.kvm = kvm;
+		vcpu_stat_clear_per_vm((void *)&stat_tmp, 0);
+	}
+	spin_unlock(&kvm_lock);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, vcpu_stat_clear,
+			"%llu\n");
 
 static const struct file_operations *stat_fops[] = {
 	[KVM_STAT_VCPU] = &vcpu_stat_fops,
@@ -3776,7 +3845,7 @@ static int kvm_init_debug(void)
 
 	kvm_debugfs_num_entries = 0;
 	for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) {
-		if (!debugfs_create_file(p->name, 0444, kvm_debugfs_dir,
+		if (!debugfs_create_file(p->name, 0644, kvm_debugfs_dir,
 					 (void *)(long)p->offset,
 					 stat_fops[p->kind]))
 			goto out_dir;