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

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - VHE optimizations

   - EL2 address space randomization

   - speculative execution mitigations ("variant 3a", aka execution past
     invalid privilege register access)

   - bugfixes and cleanups

  PPC:
   - improvements for the radix page fault handler for HV KVM on POWER9

  s390:
   - more kvm stat counters

   - virtio gpu plumbing

   - documentation

   - facilities improvements

  x86:
   - support for VMware magic I/O port and pseudo-PMCs

   - AMD pause loop exiting

   - support for AMD core performance extensions

   - support for synchronous register access

   - expose nVMX capabilities to userspace

   - support for Hyper-V signaling via eventfd

   - use Enlightened VMCS when running on Hyper-V

   - allow userspace to disable MWAIT/HLT/PAUSE vmexits

   - usual roundup of optimizations and nested virtualization bugfixes

  Generic:
   - API selftest infrastructure (though the only tests are for x86 as
     of now)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (174 commits)
  kvm: x86: fix a prototype warning
  kvm: selftests: add sync_regs_test
  kvm: selftests: add API testing infrastructure
  kvm: x86: fix a compile warning
  KVM: X86: Add Force Emulation Prefix for "emulate the next instruction"
  KVM: X86: Introduce handle_ud()
  KVM: vmx: unify adjacent #ifdefs
  x86: kvm: hide the unused 'cpu' variable
  KVM: VMX: remove bogus WARN_ON in handle_ept_misconfig
  Revert "KVM: X86: Fix SMRAM accessing even if VM is shutdown"
  kvm: Add emulation for movups/movupd
  KVM: VMX: raise internal error for exception during invalid protected mode state
  KVM: nVMX: Optimization: Dont set KVM_REQ_EVENT when VMExit with nested_run_pending
  KVM: nVMX: Require immediate-exit when event reinjected to L2 and L1 event pending
  KVM: x86: Fix misleading comments on handling pending exceptions
  KVM: x86: Rename interrupt.pending to interrupt.injected
  KVM: VMX: No need to clear pending NMI/interrupt on inject realmode interrupt
  x86/kvm: use Enlightened VMCS when running on Hyper-V
  x86/hyper-v: detect nested features
  x86/hyper-v: define struct hv_enlightened_vmcs and clean field bits
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -1907,6 +1907,9 @@
 	kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs.
 			Default is 0 (don't ignore, but inject #GP)
 
+	kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface.
+				   Default is false (don't support).
+
 	kvm.mmu_audit=	[KVM] This is a R/W parameter which allows audit
 			KVM MMU at runtime.
 			Default is 0 (off)

Documentation/arm64/memory.txt

@@ -86,9 +86,12 @@ Translation table lookup with 64KB pages:
  +-------------------------------------------------> [63] TTBR0/1
 
 
-When using KVM without the Virtualization Host Extensions, the hypervisor
-maps kernel pages in EL2 at a fixed offset from the kernel VA. See the
-kern_hyp_va macro for more details.
+When using KVM without the Virtualization Host Extensions, the
+hypervisor maps kernel pages in EL2 at a fixed (and potentially
+random) offset from the linear mapping. See the kern_hyp_va macro and
+kvm_update_va_mask function for more details. MMIO devices such as
+GICv2 gets mapped next to the HYP idmap page, as do vectors when
+ARM64_HARDEN_EL2_VECTORS is selected for particular CPUs.
 
 When using KVM with the Virtualization Host Extensions, no additional
 mappings are created, since the host kernel runs directly in EL2.

Documentation/virtual/kvm/00-INDEX

@@ -1,7 +1,12 @@
 00-INDEX
 	- this file.
+amd-memory-encryption.rst
+	- notes on AMD Secure Encrypted Virtualization feature and SEV firmware
+	  command description
 api.txt
 	- KVM userspace API.
+arm
+	- internal ABI between the kernel and HYP (for arm/arm64)
 cpuid.txt
 	- KVM-specific cpuid leaves (x86).
 devices/
@@ -26,6 +31,5 @@ s390-diag.txt
 	- Diagnose hypercall description (for IBM S/390)
 timekeeping.txt
 	- timekeeping virtualization for x86-based architectures.
-amd-memory-encryption.txt
-	- notes on AMD Secure Encrypted Virtualization feature and SEV firmware
-	  command description
+vcpu-requests.rst
+	- internal VCPU request API

Documentation/virtual/kvm/api.txt

@@ -3480,7 +3480,7 @@ encrypted VMs.
 
 Currently, this ioctl is used for issuing Secure Encrypted Virtualization
 (SEV) commands on AMD Processors. The SEV commands are defined in
-Documentation/virtual/kvm/amd-memory-encryption.txt.
+Documentation/virtual/kvm/amd-memory-encryption.rst.
 
 4.111 KVM_MEMORY_ENCRYPT_REG_REGION
 
@@ -3516,6 +3516,38 @@ Returns: 0 on success; -1 on error
 This ioctl can be used to unregister the guest memory region registered
 with KVM_MEMORY_ENCRYPT_REG_REGION ioctl above.
 
+4.113 KVM_HYPERV_EVENTFD
+
+Capability: KVM_CAP_HYPERV_EVENTFD
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_hyperv_eventfd (in)
+
+This ioctl (un)registers an eventfd to receive notifications from the guest on
+the specified Hyper-V connection id through the SIGNAL_EVENT hypercall, without
+causing a user exit.  SIGNAL_EVENT hypercall with non-zero event flag number
+(bits 24-31) still triggers a KVM_EXIT_HYPERV_HCALL user exit.
+
+struct kvm_hyperv_eventfd {
+	__u32 conn_id;
+	__s32 fd;
+	__u32 flags;
+	__u32 padding[3];
+};
+
+The conn_id field should fit within 24 bits:
+
+#define KVM_HYPERV_CONN_ID_MASK		0x00ffffff
+
+The acceptable values for the flags field are:
+
+#define KVM_HYPERV_EVENTFD_DEASSIGN	(1 << 0)
+
+Returns: 0 on success,
+	-EINVAL if conn_id or flags is outside the allowed range
+	-ENOENT on deassign if the conn_id isn't registered
+	-EEXIST on assign if the conn_id is already registered
+
 
 5. The kvm_run structure
 ------------------------
@@ -3873,7 +3905,7 @@ in userspace.
 	__u64 kvm_dirty_regs;
 	union {
 		struct kvm_sync_regs regs;
-		char padding[1024];
+		char padding[SYNC_REGS_SIZE_BYTES];
 	} s;
 
 If KVM_CAP_SYNC_REGS is defined, these fields allow userspace to access
@@ -4078,6 +4110,46 @@ Once this is done the KVM_REG_MIPS_VEC_* and KVM_REG_MIPS_MSA_* registers can be
 accessed, and the Config5.MSAEn bit is accessible via the KVM API and also from
 the guest.
 
+6.74 KVM_CAP_SYNC_REGS
+Architectures: s390, x86
+Target: s390: always enabled, x86: vcpu
+Parameters: none
+Returns: x86: KVM_CHECK_EXTENSION returns a bit-array indicating which register
+sets are supported (bitfields defined in arch/x86/include/uapi/asm/kvm.h).
+
+As described above in the kvm_sync_regs struct info in section 5 (kvm_run):
+KVM_CAP_SYNC_REGS "allow[s] userspace to access certain guest registers
+without having to call SET/GET_*REGS". This reduces overhead by eliminating
+repeated ioctl calls for setting and/or getting register values. This is
+particularly important when userspace is making synchronous guest state
+modifications, e.g. when emulating and/or intercepting instructions in
+userspace.
+
+For s390 specifics, please refer to the source code.
+
+For x86:
+- the register sets to be copied out to kvm_run are selectable
+  by userspace (rather that all sets being copied out for every exit).
+- vcpu_events are available in addition to regs and sregs.
+
+For x86, the 'kvm_valid_regs' field of struct kvm_run is overloaded to
+function as an input bit-array field set by userspace to indicate the
+specific register sets to be copied out on the next exit.
+
+To indicate when userspace has modified values that should be copied into
+the vCPU, the all architecture bitarray field, 'kvm_dirty_regs' must be set.
+This is done using the same bitflags as for the 'kvm_valid_regs' field.
+If the dirty bit is not set, then the register set values will not be copied
+into the vCPU even if they've been modified.
+
+Unused bitfields in the bitarrays must be set to zero.
+
+struct kvm_sync_regs {
+        struct kvm_regs regs;
+        struct kvm_sregs sregs;
+        struct kvm_vcpu_events events;
+};
+
 7. Capabilities that can be enabled on VMs
 ------------------------------------------
 
@@ -4286,6 +4358,26 @@ enables QEMU to build error log and branch to guest kernel registered
 machine check handling routine. Without this capability KVM will
 branch to guests' 0x200 interrupt vector.
 
+7.13 KVM_CAP_X86_DISABLE_EXITS
+
+Architectures: x86
+Parameters: args[0] defines which exits are disabled
+Returns: 0 on success, -EINVAL when args[0] contains invalid exits
+
+Valid bits in args[0] are
+
+#define KVM_X86_DISABLE_EXITS_MWAIT            (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HLT              (1 << 1)
+
+Enabling this capability on a VM provides userspace with a way to no
+longer intercept some instructions for improved latency in some
+workloads, and is suggested when vCPUs are associated to dedicated
+physical CPUs.  More bits can be added in the future; userspace can
+just pass the KVM_CHECK_EXTENSION result to KVM_ENABLE_CAP to disable
+all such vmexits.
+
+Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits.
+
 8. Other capabilities.
 ----------------------
 
@@ -4398,15 +4490,6 @@ reserved.
     Both registers and addresses are 64-bits wide.
     It will be possible to run 64-bit or 32-bit guest code.
 
-8.8 KVM_CAP_X86_GUEST_MWAIT
-
-Architectures: x86
-
-This capability indicates that guest using memory monotoring instructions
-(MWAIT/MWAITX) to stop the virtual CPU will not cause a VM exit.  As such time
-spent while virtual CPU is halted in this way will then be accounted for as
-guest running time on the host (as opposed to e.g. HLT).
-
 8.9 KVM_CAP_ARM_USER_IRQ
 
 Architectures: arm, arm64
@@ -4483,3 +4566,33 @@ Parameters: none
 This capability indicates if the flic device will be able to get/set the
 AIS states for migration via the KVM_DEV_FLIC_AISM_ALL attribute and allows
 to discover this without having to create a flic device.
+
+8.14 KVM_CAP_S390_PSW
+
+Architectures: s390
+
+This capability indicates that the PSW is exposed via the kvm_run structure.
+
+8.15 KVM_CAP_S390_GMAP
+
+Architectures: s390
+
+This capability indicates that the user space memory used as guest mapping can
+be anywhere in the user memory address space, as long as the memory slots are
+aligned and sized to a segment (1MB) boundary.
+
+8.16 KVM_CAP_S390_COW
+
+Architectures: s390
+
+This capability indicates that the user space memory used as guest mapping can
+use copy-on-write semantics as well as dirty pages tracking via read-only page
+tables.
+
+8.17 KVM_CAP_S390_BPB
+
+Architectures: s390
+
+This capability indicates that kvm will implement the interfaces to handle
+reset, migration and nested KVM for branch prediction blocking. The stfle
+facility 82 should not be provided to the guest without this capability.

Documentation/virtual/kvm/cpuid.txt

@@ -23,8 +23,8 @@ This function queries the presence of KVM cpuid leafs.
 
 
 function: define KVM_CPUID_FEATURES (0x40000001)
-returns : ebx, ecx, edx = 0
-          eax = and OR'ed group of (1 << flag), where each flags is:
+returns : ebx, ecx
+          eax = an OR'ed group of (1 << flag), where each flags is:
 
 
 flag                               || value || meaning
@@ -66,3 +66,14 @@ KVM_FEATURE_CLOCKSOURCE_STABLE_BIT ||    24 || host will warn if no guest-side
                                    ||       || per-cpu warps are expected in
                                    ||       || kvmclock.
 ------------------------------------------------------------------------------
+
+          edx = an OR'ed group of (1 << flag), where each flags is:
+
+
+flag                               || value || meaning
+==================================================================================
+KVM_HINTS_DEDICATED                ||     0 || guest checks this feature bit to
+                                   ||       || determine if there is vCPU pinning
+                                   ||       || and there is no vCPU over-commitment,
+                                   ||       || allowing optimizations
+----------------------------------------------------------------------------------

MAINTAINERS

@@ -6516,7 +6516,7 @@ S:	Maintained
 F:	Documentation/networking/netvsc.txt
 F:	arch/x86/include/asm/mshyperv.h
 F:	arch/x86/include/asm/trace/hyperv.h
-F:	arch/x86/include/uapi/asm/hyperv.h
+F:	arch/x86/include/asm/hyperv-tlfs.h
 F:	arch/x86/kernel/cpu/mshyperv.c
 F:	arch/x86/hyperv
 F:	drivers/hid/hid-hyperv.c

arch/arm/include/asm/kvm_asm.h

@@ -70,7 +70,10 @@ extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
 
 extern void __kvm_timer_set_cntvoff(u32 cntvoff_low, u32 cntvoff_high);
 
-extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+/* no VHE on 32-bit :( */
+static inline int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) { BUG(); return 0; }
+
+extern int __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu);
 
 extern void __init_stage2_translation(void);
 

arch/arm/include/asm/kvm_emulate.h

@@ -41,7 +41,17 @@ static inline unsigned long *vcpu_reg32(struct kvm_vcpu *vcpu, u8 reg_num)
 	return vcpu_reg(vcpu, reg_num);
 }
 
-unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu);
+unsigned long *__vcpu_spsr(struct kvm_vcpu *vcpu);
+
+static inline unsigned long vpcu_read_spsr(struct kvm_vcpu *vcpu)
+{
+	return *__vcpu_spsr(vcpu);
+}
+
+static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
+{
+	*__vcpu_spsr(vcpu) = v;
+}
 
 static inline unsigned long vcpu_get_reg(struct kvm_vcpu *vcpu,
 					 u8 reg_num)
@@ -92,14 +102,9 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 	vcpu->arch.hcr = HCR_GUEST_MASK;
 }
 
-static inline unsigned long vcpu_get_hcr(const struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.hcr;
-}
-
-static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr)
+static inline unsigned long *vcpu_hcr(const struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.hcr = hcr;
+	return (unsigned long *)&vcpu->arch.hcr;
 }
 
 static inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu)

arch/arm/include/asm/kvm_host.h

@@ -155,9 +155,6 @@ struct kvm_vcpu_arch {
 	/* HYP trapping configuration */
 	u32 hcr;
 
-	/* Interrupt related fields */
-	u32 irq_lines;		/* IRQ and FIQ levels */
-
 	/* Exception Information */
 	struct kvm_vcpu_fault_info fault;
 
@@ -315,4 +312,7 @@ static inline bool kvm_arm_harden_branch_predictor(void)
 	return false;
 }
 
+static inline void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu) {}
+static inline void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu) {}
+
 #endif /* __ARM_KVM_HOST_H__ */

arch/arm/include/asm/kvm_hyp.h

@@ -110,6 +110,10 @@ void __sysreg_restore_state(struct kvm_cpu_context *ctxt);
 
 void __vgic_v3_save_state(struct kvm_vcpu *vcpu);
 void __vgic_v3_restore_state(struct kvm_vcpu *vcpu);
+void __vgic_v3_activate_traps(struct kvm_vcpu *vcpu);
+void __vgic_v3_deactivate_traps(struct kvm_vcpu *vcpu);
+void __vgic_v3_save_aprs(struct kvm_vcpu *vcpu);
+void __vgic_v3_restore_aprs(struct kvm_vcpu *vcpu);
 
 asmlinkage void __vfp_save_state(struct vfp_hard_struct *vfp);
 asmlinkage void __vfp_restore_state(struct vfp_hard_struct *vfp);

arch/arm/include/asm/kvm_mmu.h

@@ -28,6 +28,13 @@
  */
 #define kern_hyp_va(kva)	(kva)
 
+/* Contrary to arm64, there is no need to generate a PC-relative address */
+#define hyp_symbol_addr(s)						\
+	({								\
+		typeof(s) *addr = &(s);					\
+		addr;							\
+	})
+
 /*
  * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation levels.
  */
@@ -42,8 +49,15 @@
 #include <asm/pgalloc.h>
 #include <asm/stage2_pgtable.h>
 
+/* Ensure compatibility with arm64 */
+#define VA_BITS			32
+
 int create_hyp_mappings(void *from, void *to, pgprot_t prot);
-int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
+int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
+			   void __iomem **kaddr,
+			   void __iomem **haddr);
+int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
+			     void **haddr);
 void free_hyp_pgds(void);
 
 void stage2_unmap_vm(struct kvm *kvm);

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

@@ -135,6 +135,15 @@ struct kvm_arch_memory_slot {
 #define KVM_REG_ARM_CRM_SHIFT		7
 #define KVM_REG_ARM_32_CRN_MASK		0x0000000000007800
 #define KVM_REG_ARM_32_CRN_SHIFT	11
+/*
+ * For KVM currently all guest registers are nonsecure, but we reserve a bit
+ * in the encoding to distinguish secure from nonsecure for AArch32 system
+ * registers that are banked by security. This is 1 for the secure banked
+ * register, and 0 for the nonsecure banked register or if the register is
+ * not banked by security.
+ */
+#define KVM_REG_ARM_SECURE_MASK	0x0000000010000000
+#define KVM_REG_ARM_SECURE_SHIFT	28
 
 #define ARM_CP15_REG_SHIFT_MASK(x,n) \
 	(((x) << KVM_REG_ARM_ ## n ## _SHIFT) & KVM_REG_ARM_ ## n ## _MASK)

arch/arm/kvm/coproc.c

@@ -270,6 +270,60 @@ static bool access_gic_sre(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static bool access_cntp_tval(struct kvm_vcpu *vcpu,
+			     const struct coproc_params *p,
+			     const struct coproc_reg *r)
+{
+	u64 now = kvm_phys_timer_read();
+	u64 val;
+
+	if (p->is_write) {
+		val = *vcpu_reg(vcpu, p->Rt1);
+		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL, val + now);
+	} else {
+		val = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL);
+		*vcpu_reg(vcpu, p->Rt1) = val - now;
+	}
+
+	return true;
+}
+
+static bool access_cntp_ctl(struct kvm_vcpu *vcpu,
+			    const struct coproc_params *p,
+			    const struct coproc_reg *r)
+{
+	u32 val;
+
+	if (p->is_write) {
+		val = *vcpu_reg(vcpu, p->Rt1);
+		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CTL, val);
+	} else {
+		val = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CTL);
+		*vcpu_reg(vcpu, p->Rt1) = val;
+	}
+
+	return true;
+}
+
+static bool access_cntp_cval(struct kvm_vcpu *vcpu,
+			     const struct coproc_params *p,
+			     const struct coproc_reg *r)
+{
+	u64 val;
+
+	if (p->is_write) {
+		val = (u64)*vcpu_reg(vcpu, p->Rt2) << 32;
+		val |= *vcpu_reg(vcpu, p->Rt1);
+		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL, val);
+	} else {
+		val = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL);
+		*vcpu_reg(vcpu, p->Rt1) = val;
+		*vcpu_reg(vcpu, p->Rt2) = val >> 32;
+	}
+
+	return true;
+}
+
 /*
  * We could trap ID_DFR0 and tell the guest we don't support performance
  * monitoring.  Unfortunately the patch to make the kernel check ID_DFR0 was
@@ -423,10 +477,17 @@ static const struct coproc_reg cp15_regs[] = {
 	{ CRn(13), CRm( 0), Op1( 0), Op2( 4), is32,
 			NULL, reset_unknown, c13_TID_PRIV },
 
+	/* CNTP */
+	{ CRm64(14), Op1( 2), is64, access_cntp_cval},
+
 	/* CNTKCTL: swapped by interrupt.S. */
 	{ CRn(14), CRm( 1), Op1( 0), Op2( 0), is32,
 			NULL, reset_val, c14_CNTKCTL, 0x00000000 },
 
+	/* CNTP */
+	{ CRn(14), CRm( 2), Op1( 0), Op2( 0), is32, access_cntp_tval },
+	{ CRn(14), CRm( 2), Op1( 0), Op2( 1), is32, access_cntp_ctl },
+
 	/* The Configuration Base Address Register. */
 	{ CRn(15), CRm( 0), Op1( 4), Op2( 0), is32, access_cbar},
 };

arch/arm/kvm/emulate.c

@@ -142,7 +142,7 @@ unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num)
 /*
  * Return the SPSR for the current mode of the virtual CPU.
  */
-unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu)
+unsigned long *__vcpu_spsr(struct kvm_vcpu *vcpu)
 {
 	unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK;
 	switch (mode) {
@@ -174,5 +174,5 @@ unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu)
  */
 void kvm_inject_vabt(struct kvm_vcpu *vcpu)
 {
-	vcpu_set_hcr(vcpu, vcpu_get_hcr(vcpu) | HCR_VA);
+	*vcpu_hcr(vcpu) |= HCR_VA;
 }

arch/arm/kvm/hyp/Makefile

@@ -9,7 +9,6 @@ KVM=../../../../virt/kvm
 
 CFLAGS_ARMV7VE		   :=$(call cc-option, -march=armv7ve)
 
-obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o
 

arch/arm/kvm/hyp/switch.c

@@ -44,7 +44,7 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu, u32 *fpexc_host)
 		isb();
 	}
 
-	write_sysreg(vcpu->arch.hcr | vcpu->arch.irq_lines, HCR);
+	write_sysreg(vcpu->arch.hcr, HCR);
 	/* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */
 	write_sysreg(HSTR_T(15), HSTR);
 	write_sysreg(HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11), HCPTR);
@@ -90,18 +90,18 @@ static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
 
 static void __hyp_text __vgic_save_state(struct kvm_vcpu *vcpu)
 {
-	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
+	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
 		__vgic_v3_save_state(vcpu);
-	else
-		__vgic_v2_save_state(vcpu);
+		__vgic_v3_deactivate_traps(vcpu);
+	}
 }
 
 static void __hyp_text __vgic_restore_state(struct kvm_vcpu *vcpu)
 {
-	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
+	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
+		__vgic_v3_activate_traps(vcpu);
 		__vgic_v3_restore_state(vcpu);
-	else
-		__vgic_v2_restore_state(vcpu);
+	}
 }
 
 static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
@@ -154,7 +154,7 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
+int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;

arch/arm64/Kconfig

@@ -922,6 +922,22 @@ config HARDEN_BRANCH_PREDICTOR
 
 	  If unsure, say Y.
 
+config HARDEN_EL2_VECTORS
+	bool "Harden EL2 vector mapping against system register leak" if EXPERT
+	default y
+	help
+	  Speculation attacks against some high-performance processors can
+	  be used to leak privileged information such as the vector base
+	  register, resulting in a potential defeat of the EL2 layout
+	  randomization.
+
+	  This config option will map the vectors to a fixed location,
+	  independent of the EL2 code mapping, so that revealing VBAR_EL2
+	  to an attacker does not give away any extra information. This
+	  only gets enabled on affected CPUs.
+
+	  If unsure, say Y.
+
 menuconfig ARMV8_DEPRECATED
 	bool "Emulate deprecated/obsolete ARMv8 instructions"
 	depends on COMPAT

arch/arm64/include/asm/alternative.h

@@ -5,6 +5,8 @@
 #include <asm/cpucaps.h>
 #include <asm/insn.h>
 
+#define ARM64_CB_PATCH ARM64_NCAPS
+
 #ifndef __ASSEMBLY__
 
 #include <linux/init.h>
@@ -22,12 +24,19 @@ struct alt_instr {
 	u8  alt_len;		/* size of new instruction(s), <= orig_len */
 };
 
+typedef void (*alternative_cb_t)(struct alt_instr *alt,
+				 __le32 *origptr, __le32 *updptr, int nr_inst);
+
 void __init apply_alternatives_all(void);
 void apply_alternatives(void *start, size_t length);
 
-#define ALTINSTR_ENTRY(feature)						      \
+#define ALTINSTR_ENTRY(feature,cb)					      \
 	" .word 661b - .\n"				/* label           */ \
+	" .if " __stringify(cb) " == 0\n"				      \
 	" .word 663f - .\n"				/* new instruction */ \
+	" .else\n"							      \
+	" .word " __stringify(cb) "- .\n"		/* callback */	      \
+	" .endif\n"							      \
 	" .hword " __stringify(feature) "\n"		/* feature bit     */ \
 	" .byte 662b-661b\n"				/* source len      */ \
 	" .byte 664f-663f\n"				/* replacement len */
@@ -45,15 +54,18 @@ void apply_alternatives(void *start, size_t length);
  * but most assemblers die if insn1 or insn2 have a .inst. This should
  * be fixed in a binutils release posterior to 2.25.51.0.2 (anything
  * containing commit 4e4d08cf7399b606 or c1baaddf8861).
+ *
+ * Alternatives with callbacks do not generate replacement instructions.
  */
-#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled)	\
+#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled, cb)	\
 	".if "__stringify(cfg_enabled)" == 1\n"				\
 	"661:\n\t"							\
 	oldinstr "\n"							\
 	"662:\n"							\
 	".pushsection .altinstructions,\"a\"\n"				\
-	ALTINSTR_ENTRY(feature)						\
+	ALTINSTR_ENTRY(feature,cb)					\
 	".popsection\n"							\
+	" .if " __stringify(cb) " == 0\n"				\
 	".pushsection .altinstr_replacement, \"a\"\n"			\
 	"663:\n\t"							\
 	newinstr "\n"							\
@@ -61,11 +73,17 @@ void apply_alternatives(void *start, size_t length);
 	".popsection\n\t"						\
 	".org	. - (664b-663b) + (662b-661b)\n\t"			\
 	".org	. - (662b-661b) + (664b-663b)\n"			\
+	".else\n\t"							\
+	"663:\n\t"							\
+	"664:\n\t"							\
+	".endif\n"							\
 	".endif\n"
 
 #define _ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg, ...)	\
-	__ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg))
+	__ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg), 0)
 
+#define ALTERNATIVE_CB(oldinstr, cb) \
+	__ALTERNATIVE_CFG(oldinstr, "NOT_AN_INSTRUCTION", ARM64_CB_PATCH, 1, cb)
 #else
 
 #include <asm/assembler.h>
@@ -132,6 +150,14 @@ void apply_alternatives(void *start, size_t length);
 661:
 .endm
 
+.macro alternative_cb cb
+	.set .Lasm_alt_mode, 0
+	.pushsection .altinstructions, "a"
+	altinstruction_entry 661f, \cb, ARM64_CB_PATCH, 662f-661f, 0
+	.popsection
+661:
+.endm
+
 /*
  * Provide the other half of the alternative code sequence.
  */
@@ -157,6 +183,13 @@ void apply_alternatives(void *start, size_t length);
 	.org	. - (662b-661b) + (664b-663b)
 .endm
 
+/*
+ * Callback-based alternative epilogue
+ */
+.macro alternative_cb_end
+662:
+.endm
+
 /*
  * Provides a trivial alternative or default sequence consisting solely
  * of NOPs. The number of NOPs is chosen automatically to match the

arch/arm64/include/asm/cpucaps.h

@@ -32,7 +32,7 @@
 #define ARM64_HAS_VIRT_HOST_EXTN		11
 #define ARM64_WORKAROUND_CAVIUM_27456		12
 #define ARM64_HAS_32BIT_EL0			13
-#define ARM64_HYP_OFFSET_LOW			14
+#define ARM64_HARDEN_EL2_VECTORS		14
 #define ARM64_MISMATCHED_CACHE_LINE_SIZE	15
 #define ARM64_HAS_NO_FPSIMD			16
 #define ARM64_WORKAROUND_REPEAT_TLBI		17

arch/arm64/include/asm/insn.h

@@ -70,6 +70,7 @@ enum aarch64_insn_imm_type {
 	AARCH64_INSN_IMM_6,
 	AARCH64_INSN_IMM_S,
 	AARCH64_INSN_IMM_R,
+	AARCH64_INSN_IMM_N,
 	AARCH64_INSN_IMM_MAX
 };
 
@@ -314,6 +315,11 @@ __AARCH64_INSN_FUNCS(eor,	0x7F200000, 0x4A000000)
 __AARCH64_INSN_FUNCS(eon,	0x7F200000, 0x4A200000)
 __AARCH64_INSN_FUNCS(ands,	0x7F200000, 0x6A000000)
 __AARCH64_INSN_FUNCS(bics,	0x7F200000, 0x6A200000)
+__AARCH64_INSN_FUNCS(and_imm,	0x7F800000, 0x12000000)
+__AARCH64_INSN_FUNCS(orr_imm,	0x7F800000, 0x32000000)
+__AARCH64_INSN_FUNCS(eor_imm,	0x7F800000, 0x52000000)
+__AARCH64_INSN_FUNCS(ands_imm,	0x7F800000, 0x72000000)
+__AARCH64_INSN_FUNCS(extr,	0x7FA00000, 0x13800000)
 __AARCH64_INSN_FUNCS(b,		0xFC000000, 0x14000000)
 __AARCH64_INSN_FUNCS(bl,	0xFC000000, 0x94000000)
 __AARCH64_INSN_FUNCS(cbz,	0x7F000000, 0x34000000)
@@ -423,6 +429,16 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
 					 int shift,
 					 enum aarch64_insn_variant variant,
 					 enum aarch64_insn_logic_type type);
+u32 aarch64_insn_gen_logical_immediate(enum aarch64_insn_logic_type type,
+				       enum aarch64_insn_variant variant,
+				       enum aarch64_insn_register Rn,
+				       enum aarch64_insn_register Rd,
+				       u64 imm);
+u32 aarch64_insn_gen_extr(enum aarch64_insn_variant variant,
+			  enum aarch64_insn_register Rm,
+			  enum aarch64_insn_register Rn,
+			  enum aarch64_insn_register Rd,
+			  u8 lsb);
 u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base,
 			      enum aarch64_insn_prfm_type type,
 			      enum aarch64_insn_prfm_target target,

arch/arm64/include/asm/kvm_arm.h

@@ -25,6 +25,7 @@
 /* Hyp Configuration Register (HCR) bits */
 #define HCR_TEA		(UL(1) << 37)
 #define HCR_TERR	(UL(1) << 36)
+#define HCR_TLOR	(UL(1) << 35)
 #define HCR_E2H		(UL(1) << 34)
 #define HCR_ID		(UL(1) << 33)
 #define HCR_CD		(UL(1) << 32)
@@ -64,6 +65,7 @@
 
 /*
  * The bits we set in HCR:
+ * TLOR:	Trap LORegion register accesses
  * RW:		64bit by default, can be overridden for 32bit VMs
  * TAC:		Trap ACTLR
  * TSC:		Trap SMC
@@ -81,9 +83,9 @@
  */
 #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
 			 HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \
-			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW)
+			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
+			 HCR_FMO | HCR_IMO)
 #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
-#define HCR_INT_OVERRIDE   (HCR_FMO | HCR_IMO)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
 /* TCR_EL2 Registers bits */

arch/arm64/include/asm/kvm_asm.h

@@ -33,6 +33,7 @@
 #define KVM_ARM64_DEBUG_DIRTY_SHIFT	0
 #define KVM_ARM64_DEBUG_DIRTY		(1 << KVM_ARM64_DEBUG_DIRTY_SHIFT)
 
+/* Translate a kernel address of @sym into its equivalent linear mapping */
 #define kvm_ksym_ref(sym)						\
 	({								\
 		void *val = &sym;					\
@@ -57,7 +58,9 @@ extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
 
 extern void __kvm_timer_set_cntvoff(u32 cntvoff_low, u32 cntvoff_high);
 
-extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+extern int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu);
+
+extern int __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu);
 
 extern u64 __vgic_v3_get_ich_vtr_el2(void);
 extern u64 __vgic_v3_read_vmcr(void);
@@ -70,6 +73,20 @@ extern u32 __init_stage2_translation(void);
 
 extern void __qcom_hyp_sanitize_btac_predictors(void);
 
+#else /* __ASSEMBLY__ */
+
+.macro get_host_ctxt reg, tmp
+	adr_l	\reg, kvm_host_cpu_state
+	mrs	\tmp, tpidr_el2
+	add	\reg, \reg, \tmp
+.endm
+
+.macro get_vcpu_ptr vcpu, ctxt
+	get_host_ctxt \ctxt, \vcpu
+	ldr	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]
+	kern_hyp_va	\vcpu
+.endm
+
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */

arch/arm64/include/asm/kvm_emulate.h

@@ -26,13 +26,15 @@
 
 #include <asm/esr.h>
 #include <asm/kvm_arm.h>
+#include <asm/kvm_hyp.h>
 #include <asm/kvm_mmio.h>
 #include <asm/ptrace.h>
 #include <asm/cputype.h>
 #include <asm/virt.h>
 
 unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num);
-unsigned long *vcpu_spsr32(const struct kvm_vcpu *vcpu);
+unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu);
+void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v);
 
 bool kvm_condition_valid32(const struct kvm_vcpu *vcpu);
 void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr);
@@ -45,6 +47,11 @@ void kvm_inject_undef32(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_inject_pabt32(struct kvm_vcpu *vcpu, unsigned long addr);
 
+static inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
+{
+	return !(vcpu->arch.hcr_el2 & HCR_RW);
+}
+
 static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
@@ -59,16 +66,19 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 
 	if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
 		vcpu->arch.hcr_el2 &= ~HCR_RW;
-}
 
-static inline unsigned long vcpu_get_hcr(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.hcr_el2;
+	/*
+	 * TID3: trap feature register accesses that we virtualise.
+	 * For now this is conditional, since no AArch32 feature regs
+	 * are currently virtualised.
+	 */
+	if (!vcpu_el1_is_32bit(vcpu))
+		vcpu->arch.hcr_el2 |= HCR_TID3;
 }
 
-static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr)
+static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.hcr_el2 = hcr;
+	return (unsigned long *)&vcpu->arch.hcr_el2;
 }
 
 static inline void vcpu_set_vsesr(struct kvm_vcpu *vcpu, u64 vsesr)
@@ -81,11 +91,27 @@ static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
 	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc;
 }
 
-static inline unsigned long *vcpu_elr_el1(const struct kvm_vcpu *vcpu)
+static inline unsigned long *__vcpu_elr_el1(const struct kvm_vcpu *vcpu)
 {
 	return (unsigned long *)&vcpu_gp_regs(vcpu)->elr_el1;
 }
 
+static inline unsigned long vcpu_read_elr_el1(const struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.sysregs_loaded_on_cpu)
+		return read_sysreg_el1(elr);
+	else
+		return *__vcpu_elr_el1(vcpu);
+}
+
+static inline void vcpu_write_elr_el1(const struct kvm_vcpu *vcpu, unsigned long v)
+{
+	if (vcpu->arch.sysregs_loaded_on_cpu)
+		write_sysreg_el1(v, elr);
+	else
+		*__vcpu_elr_el1(vcpu) = v;
+}
+
 static inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu)
 {
 	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pstate;
@@ -135,13 +161,28 @@ static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
 		vcpu_gp_regs(vcpu)->regs.regs[reg_num] = val;
 }
 
-/* Get vcpu SPSR for current mode */
-static inline unsigned long *vcpu_spsr(const struct kvm_vcpu *vcpu)
+static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu)
 {
 	if (vcpu_mode_is_32bit(vcpu))
-		return vcpu_spsr32(vcpu);
+		return vcpu_read_spsr32(vcpu);
 
-	return (unsigned long *)&vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1];
+	if (vcpu->arch.sysregs_loaded_on_cpu)
+		return read_sysreg_el1(spsr);
+	else
+		return vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1];
+}
+
+static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
+{
+	if (vcpu_mode_is_32bit(vcpu)) {
+		vcpu_write_spsr32(vcpu, v);
+		return;
+	}
+
+	if (vcpu->arch.sysregs_loaded_on_cpu)
+		write_sysreg_el1(v, spsr);
+	else
+		vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1] = v;
 }
 
 static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
@@ -282,15 +323,18 @@ static inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
 
 static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
 {
-	return vcpu_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
+	return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
 }
 
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
 {
-	if (vcpu_mode_is_32bit(vcpu))
+	if (vcpu_mode_is_32bit(vcpu)) {
 		*vcpu_cpsr(vcpu) |= COMPAT_PSR_E_BIT;
-	else
-		vcpu_sys_reg(vcpu, SCTLR_EL1) |= (1 << 25);
+	} else {
+		u64 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
+		sctlr |= (1 << 25);
+		vcpu_write_sys_reg(vcpu, SCTLR_EL1, sctlr);
+	}
 }
 
 static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu)
@@ -298,7 +342,7 @@ static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu)
 	if (vcpu_mode_is_32bit(vcpu))
 		return !!(*vcpu_cpsr(vcpu) & COMPAT_PSR_E_BIT);
 
-	return !!(vcpu_sys_reg(vcpu, SCTLR_EL1) & (1 << 25));
+	return !!(vcpu_read_sys_reg(vcpu, SCTLR_EL1) & (1 << 25));
 }
 
 static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,

arch/arm64/include/asm/kvm_host.h

@@ -272,9 +272,6 @@ struct kvm_vcpu_arch {
 	/* IO related fields */
 	struct kvm_decode mmio_decode;
 
-	/* Interrupt related fields */
-	u64 irq_lines;		/* IRQ and FIQ levels */
-
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
@@ -287,10 +284,25 @@ struct kvm_vcpu_arch {
 
 	/* Virtual SError ESR to restore when HCR_EL2.VSE is set */
 	u64 vsesr_el2;
+
+	/* True when deferrable sysregs are loaded on the physical CPU,
+	 * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */
+	bool sysregs_loaded_on_cpu;
 };
 
 #define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)
-#define vcpu_sys_reg(v,r)	((v)->arch.ctxt.sys_regs[(r)])
+
+/*
+ * Only use __vcpu_sys_reg if you know you want the memory backed version of a
+ * register, and not the one most recently accessed by a running VCPU.  For
+ * example, for userspace access or for system registers that are never context
+ * switched, but only emulated.
+ */
+#define __vcpu_sys_reg(v,r)	((v)->arch.ctxt.sys_regs[(r)])
+
+u64 vcpu_read_sys_reg(struct kvm_vcpu *vcpu, int reg);
+void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
+
 /*
  * CP14 and CP15 live in the same array, as they are backed by the
  * same system registers.
@@ -298,14 +310,6 @@ struct kvm_vcpu_arch {
 #define vcpu_cp14(v,r)		((v)->arch.ctxt.copro[(r)])
 #define vcpu_cp15(v,r)		((v)->arch.ctxt.copro[(r)])
 
-#ifdef CONFIG_CPU_BIG_ENDIAN
-#define vcpu_cp15_64_high(v,r)	vcpu_cp15((v),(r))
-#define vcpu_cp15_64_low(v,r)	vcpu_cp15((v),(r) + 1)
-#else
-#define vcpu_cp15_64_high(v,r)	vcpu_cp15((v),(r) + 1)
-#define vcpu_cp15_64_low(v,r)	vcpu_cp15((v),(r))
-#endif
-
 struct kvm_vm_stat {
 	ulong remote_tlb_flush;
 };
@@ -358,10 +362,15 @@ int kvm_perf_teardown(void);
 
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
 
+void __kvm_set_tpidr_el2(u64 tpidr_el2);
+DECLARE_PER_CPU(kvm_cpu_context_t, kvm_host_cpu_state);
+
 static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 				       unsigned long hyp_stack_ptr,
 				       unsigned long vector_ptr)
 {
+	u64 tpidr_el2;
+
 	/*
 	 * Call initialization code, and switch to the full blown HYP code.
 	 * If the cpucaps haven't been finalized yet, something has gone very
@@ -370,6 +379,16 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 	 */
 	BUG_ON(!static_branch_likely(&arm64_const_caps_ready));
 	__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr);
+
+	/*
+	 * Calculate the raw per-cpu offset without a translation from the
+	 * kernel's mapping to the linear mapping, and store it in tpidr_el2
+	 * so that we can use adr_l to access per-cpu variables in EL2.
+	 */
+	tpidr_el2 = (u64)this_cpu_ptr(&kvm_host_cpu_state)
+		- (u64)kvm_ksym_ref(kvm_host_cpu_state);
+
+	kvm_call_hyp(__kvm_set_tpidr_el2, tpidr_el2);
 }
 
 static inline void kvm_arch_hardware_unsetup(void) {}
@@ -416,6 +435,13 @@ static inline void kvm_arm_vhe_guest_enter(void)
 static inline void kvm_arm_vhe_guest_exit(void)
 {
 	local_daif_restore(DAIF_PROCCTX_NOIRQ);
+
+	/*
+	 * When we exit from the guest we change a number of CPU configuration
+	 * parameters, such as traps.  Make sure these changes take effect
+	 * before running the host or additional guests.
+	 */
+	isb();
 }
 
 static inline bool kvm_arm_harden_branch_predictor(void)
@@ -423,4 +449,7 @@ static inline bool kvm_arm_harden_branch_predictor(void)
 	return cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR);
 }
 
+void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu);
+void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu);
+
 #endif /* __ARM64_KVM_HOST_H__ */

arch/arm64/include/asm/kvm_hyp.h

@@ -120,37 +120,38 @@ typeof(orig) * __hyp_text fname(void)					\
 	return val;							\
 }
 
-void __vgic_v2_save_state(struct kvm_vcpu *vcpu);
-void __vgic_v2_restore_state(struct kvm_vcpu *vcpu);
 int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu);
 
 void __vgic_v3_save_state(struct kvm_vcpu *vcpu);
 void __vgic_v3_restore_state(struct kvm_vcpu *vcpu);
+void __vgic_v3_activate_traps(struct kvm_vcpu *vcpu);
+void __vgic_v3_deactivate_traps(struct kvm_vcpu *vcpu);
+void __vgic_v3_save_aprs(struct kvm_vcpu *vcpu);
+void __vgic_v3_restore_aprs(struct kvm_vcpu *vcpu);
 int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu);
 
 void __timer_enable_traps(struct kvm_vcpu *vcpu);
 void __timer_disable_traps(struct kvm_vcpu *vcpu);
 
-void __sysreg_save_host_state(struct kvm_cpu_context *ctxt);
-void __sysreg_restore_host_state(struct kvm_cpu_context *ctxt);
-void __sysreg_save_guest_state(struct kvm_cpu_context *ctxt);
-void __sysreg_restore_guest_state(struct kvm_cpu_context *ctxt);
+void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt);
+void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt);
+void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt);
+void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt);
+void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt);
+void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt);
 void __sysreg32_save_state(struct kvm_vcpu *vcpu);
 void __sysreg32_restore_state(struct kvm_vcpu *vcpu);
 
-void __debug_save_state(struct kvm_vcpu *vcpu,
-			struct kvm_guest_debug_arch *dbg,
-			struct kvm_cpu_context *ctxt);
-void __debug_restore_state(struct kvm_vcpu *vcpu,
-			   struct kvm_guest_debug_arch *dbg,
-			   struct kvm_cpu_context *ctxt);
-void __debug_cond_save_host_state(struct kvm_vcpu *vcpu);
-void __debug_cond_restore_host_state(struct kvm_vcpu *vcpu);
+void __debug_switch_to_guest(struct kvm_vcpu *vcpu);
+void __debug_switch_to_host(struct kvm_vcpu *vcpu);
 
 void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
 void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
 bool __fpsimd_enabled(void);
 
+void activate_traps_vhe_load(struct kvm_vcpu *vcpu);
+void deactivate_traps_vhe_put(void);
+
 u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt);
 void __noreturn __hyp_do_panic(unsigned long, ...);
 

arch/arm64/include/asm/kvm_mmu.h

@@ -69,9 +69,6 @@
  * mappings, and none of this applies in that case.
  */
 
-#define HYP_PAGE_OFFSET_HIGH_MASK	((UL(1) << VA_BITS) - 1)
-#define HYP_PAGE_OFFSET_LOW_MASK	((UL(1) << (VA_BITS - 1)) - 1)
-
 #ifdef __ASSEMBLY__
 
 #include <asm/alternative.h>
@@ -81,28 +78,19 @@
  * Convert a kernel VA into a HYP VA.
  * reg: VA to be converted.
  *
- * This generates the following sequences:
- * - High mask:
- *		and x0, x0, #HYP_PAGE_OFFSET_HIGH_MASK
- *		nop
- * - Low mask:
- *		and x0, x0, #HYP_PAGE_OFFSET_HIGH_MASK
- *		and x0, x0, #HYP_PAGE_OFFSET_LOW_MASK
- * - VHE:
- *		nop
- *		nop
- *
- * The "low mask" version works because the mask is a strict subset of
- * the "high mask", hence performing the first mask for nothing.
- * Should be completely invisible on any viable CPU.
+ * The actual code generation takes place in kvm_update_va_mask, and
+ * the instructions below are only there to reserve the space and
+ * perform the register allocation (kvm_update_va_mask uses the
+ * specific registers encoded in the instructions).
  */
 .macro kern_hyp_va	reg
-alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
-	and     \reg, \reg, #HYP_PAGE_OFFSET_HIGH_MASK
-alternative_else_nop_endif
-alternative_if ARM64_HYP_OFFSET_LOW
-	and     \reg, \reg, #HYP_PAGE_OFFSET_LOW_MASK
-alternative_else_nop_endif
+alternative_cb kvm_update_va_mask
+	and     \reg, \reg, #1		/* mask with va_mask */
+	ror	\reg, \reg, #1		/* rotate to the first tag bit */
+	add	\reg, \reg, #0		/* insert the low 12 bits of the tag */
+	add	\reg, \reg, #0, lsl 12	/* insert the top 12 bits of the tag */
+	ror	\reg, \reg, #63		/* rotate back */
+alternative_cb_end
 .endm
 
 #else
@@ -113,23 +101,43 @@ alternative_else_nop_endif
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 
+void kvm_update_va_mask(struct alt_instr *alt,
+			__le32 *origptr, __le32 *updptr, int nr_inst);
+
 static inline unsigned long __kern_hyp_va(unsigned long v)
 {
-	asm volatile(ALTERNATIVE("and %0, %0, %1",
-				 "nop",
-				 ARM64_HAS_VIRT_HOST_EXTN)
-		     : "+r" (v)
-		     : "i" (HYP_PAGE_OFFSET_HIGH_MASK));
-	asm volatile(ALTERNATIVE("nop",
-				 "and %0, %0, %1",
-				 ARM64_HYP_OFFSET_LOW)
-		     : "+r" (v)
-		     : "i" (HYP_PAGE_OFFSET_LOW_MASK));
+	asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n"
+				    "ror %0, %0, #1\n"
+				    "add %0, %0, #0\n"
+				    "add %0, %0, #0, lsl 12\n"
+				    "ror %0, %0, #63\n",
+				    kvm_update_va_mask)
+		     : "+r" (v));
 	return v;
 }
 
 #define kern_hyp_va(v) 	((typeof(v))(__kern_hyp_va((unsigned long)(v))))
 
+/*
+ * Obtain the PC-relative address of a kernel symbol
+ * s: symbol
+ *
+ * The goal of this macro is to return a symbol's address based on a
+ * PC-relative computation, as opposed to a loading the VA from a
+ * constant pool or something similar. This works well for HYP, as an
+ * absolute VA is guaranteed to be wrong. Only use this if trying to
+ * obtain the address of a symbol (i.e. not something you obtained by
+ * following a pointer).
+ */
+#define hyp_symbol_addr(s)						\
+	({								\
+		typeof(s) *addr;					\
+		asm("adrp	%0, %1\n"				\
+		    "add	%0, %0, :lo12:%1\n"			\
+		    : "=r" (addr) : "S" (&s));				\
+		addr;							\
+	})
+
 /*
  * We currently only support a 40bit IPA.
  */
@@ -140,7 +148,11 @@ static inline unsigned long __kern_hyp_va(unsigned long v)
 #include <asm/stage2_pgtable.h>
 
 int create_hyp_mappings(void *from, void *to, pgprot_t prot);
-int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
+int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
+			   void __iomem **kaddr,
+			   void __iomem **haddr);
+int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
+			     void **haddr);
 void free_hyp_pgds(void);
 
 void stage2_unmap_vm(struct kvm *kvm);
@@ -249,7 +261,7 @@ struct kvm;
 
 static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 {
-	return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
+	return (vcpu_read_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
 }
 
 static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
@@ -348,36 +360,95 @@ static inline unsigned int kvm_get_vmid_bits(void)
 	return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
 }
 
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+#ifdef CONFIG_KVM_INDIRECT_VECTORS
+/*
+ * EL2 vectors can be mapped and rerouted in a number of ways,
+ * depending on the kernel configuration and CPU present:
+ *
+ * - If the CPU has the ARM64_HARDEN_BRANCH_PREDICTOR cap, the
+ *   hardening sequence is placed in one of the vector slots, which is
+ *   executed before jumping to the real vectors.
+ *
+ * - If the CPU has both the ARM64_HARDEN_EL2_VECTORS cap and the
+ *   ARM64_HARDEN_BRANCH_PREDICTOR cap, the slot containing the
+ *   hardening sequence is mapped next to the idmap page, and executed
+ *   before jumping to the real vectors.
+ *
+ * - If the CPU only has the ARM64_HARDEN_EL2_VECTORS cap, then an
+ *   empty slot is selected, mapped next to the idmap page, and
+ *   executed before jumping to the real vectors.
+ *
+ * Note that ARM64_HARDEN_EL2_VECTORS is somewhat incompatible with
+ * VHE, as we don't have hypervisor-specific mappings. If the system
+ * is VHE and yet selects this capability, it will be ignored.
+ */
 #include <asm/mmu.h>
 
+extern void *__kvm_bp_vect_base;
+extern int __kvm_harden_el2_vector_slot;
+
 static inline void *kvm_get_hyp_vector(void)
 {
 	struct bp_hardening_data *data = arm64_get_bp_hardening_data();
-	void *vect = kvm_ksym_ref(__kvm_hyp_vector);
+	void *vect = kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector));
+	int slot = -1;
 
-	if (data->fn) {
-		vect = __bp_harden_hyp_vecs_start +
-		       data->hyp_vectors_slot * SZ_2K;
+	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR) && data->fn) {
+		vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs_start));
+		slot = data->hyp_vectors_slot;
+	}
 
-		if (!has_vhe())
-			vect = lm_alias(vect);
+	if (this_cpu_has_cap(ARM64_HARDEN_EL2_VECTORS) && !has_vhe()) {
+		vect = __kvm_bp_vect_base;
+		if (slot == -1)
+			slot = __kvm_harden_el2_vector_slot;
 	}
 
+	if (slot != -1)
+		vect += slot * SZ_2K;
+
 	return vect;
 }
 
+/*  This is only called on a !VHE system */
 static inline int kvm_map_vectors(void)
 {
-	return create_hyp_mappings(kvm_ksym_ref(__bp_harden_hyp_vecs_start),
-				   kvm_ksym_ref(__bp_harden_hyp_vecs_end),
-				   PAGE_HYP_EXEC);
-}
+	/*
+	 * HBP  = ARM64_HARDEN_BRANCH_PREDICTOR
+	 * HEL2 = ARM64_HARDEN_EL2_VECTORS
+	 *
+	 * !HBP + !HEL2 -> use direct vectors
+	 *  HBP + !HEL2 -> use hardened vectors in place
+	 * !HBP +  HEL2 -> allocate one vector slot and use exec mapping
+	 *  HBP +  HEL2 -> use hardened vertors and use exec mapping
+	 */
+	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR)) {
+		__kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs_start);
+		__kvm_bp_vect_base = kern_hyp_va(__kvm_bp_vect_base);
+	}
+
+	if (cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)) {
+		phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs_start);
+		unsigned long size = (__bp_harden_hyp_vecs_end -
+				      __bp_harden_hyp_vecs_start);
+
+		/*
+		 * Always allocate a spare vector slot, as we don't
+		 * know yet which CPUs have a BP hardening slot that
+		 * we can reuse.
+		 */
+		__kvm_harden_el2_vector_slot = atomic_inc_return(&arm64_el2_vector_last_slot);
+		BUG_ON(__kvm_harden_el2_vector_slot >= BP_HARDEN_EL2_SLOTS);
+		return create_hyp_exec_mappings(vect_pa, size,
+						&__kvm_bp_vect_base);
+	}
 
+	return 0;
+}
 #else
 static inline void *kvm_get_hyp_vector(void)
 {
-	return kvm_ksym_ref(__kvm_hyp_vector);
+	return kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector));
 }
 
 static inline int kvm_map_vectors(void)

arch/arm64/include/asm/mmu.h

@@ -21,6 +21,8 @@
 #define USER_ASID_FLAG	(UL(1) << USER_ASID_BIT)
 #define TTBR_ASID_MASK	(UL(0xffff) << 48)
 
+#define BP_HARDEN_EL2_SLOTS 4
+
 #ifndef __ASSEMBLY__
 
 typedef struct {
@@ -49,9 +51,13 @@ struct bp_hardening_data {
 	bp_hardening_cb_t	fn;
 };
 
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+#if (defined(CONFIG_HARDEN_BRANCH_PREDICTOR) ||	\
+     defined(CONFIG_HARDEN_EL2_VECTORS))
 extern char __bp_harden_hyp_vecs_start[], __bp_harden_hyp_vecs_end[];
+extern atomic_t arm64_el2_vector_last_slot;
+#endif  /* CONFIG_HARDEN_BRANCH_PREDICTOR || CONFIG_HARDEN_EL2_VECTORS */
 
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
 
 static inline struct bp_hardening_data *arm64_get_bp_hardening_data(void)

arch/arm64/include/asm/sysreg.h

@@ -288,6 +288,12 @@
 #define SYS_MAIR_EL1			sys_reg(3, 0, 10, 2, 0)
 #define SYS_AMAIR_EL1			sys_reg(3, 0, 10, 3, 0)
 
+#define SYS_LORSA_EL1			sys_reg(3, 0, 10, 4, 0)
+#define SYS_LOREA_EL1			sys_reg(3, 0, 10, 4, 1)
+#define SYS_LORN_EL1			sys_reg(3, 0, 10, 4, 2)
+#define SYS_LORC_EL1			sys_reg(3, 0, 10, 4, 3)
+#define SYS_LORID_EL1			sys_reg(3, 0, 10, 4, 7)
+
 #define SYS_VBAR_EL1			sys_reg(3, 0, 12, 0, 0)
 #define SYS_DISR_EL1			sys_reg(3, 0, 12, 1, 1)
 

arch/arm64/kernel/Makefile

@@ -55,9 +55,7 @@ arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o
 arm64-obj-$(CONFIG_CRASH_DUMP)		+= crash_dump.o
 arm64-obj-$(CONFIG_ARM_SDE_INTERFACE)	+= sdei.o
 
-ifeq ($(CONFIG_KVM),y)
-arm64-obj-$(CONFIG_HARDEN_BRANCH_PREDICTOR)	+= bpi.o
-endif
+arm64-obj-$(CONFIG_KVM_INDIRECT_VECTORS)+= bpi.o
 
 obj-y					+= $(arm64-obj-y) vdso/ probes/
 obj-m					+= $(arm64-obj-m)

arch/arm64/kernel/alternative.c

@@ -107,32 +107,53 @@ static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnp
 	return insn;
 }
 
+static void patch_alternative(struct alt_instr *alt,
+			      __le32 *origptr, __le32 *updptr, int nr_inst)
+{
+	__le32 *replptr;
+	int i;
+
+	replptr = ALT_REPL_PTR(alt);
+	for (i = 0; i < nr_inst; i++) {
+		u32 insn;
+
+		insn = get_alt_insn(alt, origptr + i, replptr + i);
+		updptr[i] = cpu_to_le32(insn);
+	}
+}
+
 static void __apply_alternatives(void *alt_region, bool use_linear_alias)
 {
 	struct alt_instr *alt;
 	struct alt_region *region = alt_region;
-	__le32 *origptr, *replptr, *updptr;
+	__le32 *origptr, *updptr;
+	alternative_cb_t alt_cb;
 
 	for (alt = region->begin; alt < region->end; alt++) {
-		u32 insn;
-		int i, nr_inst;
+		int nr_inst;
 
-		if (!cpus_have_cap(alt->cpufeature))
+		/* Use ARM64_CB_PATCH as an unconditional patch */
+		if (alt->cpufeature < ARM64_CB_PATCH &&
+		    !cpus_have_cap(alt->cpufeature))
 			continue;
 
-		BUG_ON(alt->alt_len != alt->orig_len);
+		if (alt->cpufeature == ARM64_CB_PATCH)
+			BUG_ON(alt->alt_len != 0);
+		else
+			BUG_ON(alt->alt_len != alt->orig_len);
 
 		pr_info_once("patching kernel code\n");
 
 		origptr = ALT_ORIG_PTR(alt);
-		replptr = ALT_REPL_PTR(alt);
 		updptr = use_linear_alias ? lm_alias(origptr) : origptr;
-		nr_inst = alt->alt_len / sizeof(insn);
+		nr_inst = alt->orig_len / AARCH64_INSN_SIZE;
 
-		for (i = 0; i < nr_inst; i++) {
-			insn = get_alt_insn(alt, origptr + i, replptr + i);
-			updptr[i] = cpu_to_le32(insn);
-		}
+		if (alt->cpufeature < ARM64_CB_PATCH)
+			alt_cb = patch_alternative;
+		else
+			alt_cb  = ALT_REPL_PTR(alt);
+
+		alt_cb(alt, origptr, updptr, nr_inst);
 
 		flush_icache_range((uintptr_t)origptr,
 				   (uintptr_t)(origptr + nr_inst));

arch/arm64/kernel/asm-offsets.c

@@ -138,6 +138,7 @@ int main(void)
   DEFINE(CPU_FP_REGS,		offsetof(struct kvm_regs, fp_regs));
   DEFINE(VCPU_FPEXC32_EL2,	offsetof(struct kvm_vcpu, arch.ctxt.sys_regs[FPEXC32_EL2]));
   DEFINE(VCPU_HOST_CONTEXT,	offsetof(struct kvm_vcpu, arch.host_cpu_context));
+  DEFINE(HOST_CONTEXT_VCPU,	offsetof(struct kvm_cpu_context, __hyp_running_vcpu));
 #endif
 #ifdef CONFIG_CPU_PM
   DEFINE(CPU_SUSPEND_SZ,	sizeof(struct cpu_suspend_ctx));

arch/arm64/kernel/bpi.S

@@ -19,42 +19,61 @@
 #include <linux/linkage.h>
 #include <linux/arm-smccc.h>
 
-.macro ventry target
-	.rept 31
+#include <asm/alternative.h>
+#include <asm/mmu.h>
+
+.macro hyp_ventry
+	.align 7
+1:	.rept 27
 	nop
 	.endr
-	b	\target
+/*
+ * The default sequence is to directly branch to the KVM vectors,
+ * using the computed offset. This applies for VHE as well as
+ * !ARM64_HARDEN_EL2_VECTORS.
+ *
+ * For ARM64_HARDEN_EL2_VECTORS configurations, this gets replaced
+ * with:
+ *
+ * stp	x0, x1, [sp, #-16]!
+ * movz	x0, #(addr & 0xffff)
+ * movk	x0, #((addr >> 16) & 0xffff), lsl #16
+ * movk	x0, #((addr >> 32) & 0xffff), lsl #32
+ * br	x0
+ *
+ * Where addr = kern_hyp_va(__kvm_hyp_vector) + vector-offset + 4.
+ * See kvm_patch_vector_branch for details.
+ */
+alternative_cb	kvm_patch_vector_branch
+	b	__kvm_hyp_vector + (1b - 0b)
+	nop
+	nop
+	nop
+	nop
+alternative_cb_end
 .endm
 
-.macro vectors target
-	ventry \target + 0x000
-	ventry \target + 0x080
-	ventry \target + 0x100
-	ventry \target + 0x180
-
-	ventry \target + 0x200
-	ventry \target + 0x280
-	ventry \target + 0x300
-	ventry \target + 0x380
+.macro generate_vectors
+0:
+	.rept 16
+	hyp_ventry
+	.endr
+	.org 0b + SZ_2K		// Safety measure
+.endm
 
-	ventry \target + 0x400
-	ventry \target + 0x480
-	ventry \target + 0x500
-	ventry \target + 0x580
 
-	ventry \target + 0x600
-	ventry \target + 0x680
-	ventry \target + 0x700
-	ventry \target + 0x780
-.endm
+	.text
+	.pushsection	.hyp.text, "ax"
 
 	.align	11
 ENTRY(__bp_harden_hyp_vecs_start)
-	.rept 4
-	vectors __kvm_hyp_vector
+	.rept BP_HARDEN_EL2_SLOTS
+	generate_vectors
 	.endr
 ENTRY(__bp_harden_hyp_vecs_end)
 
+	.popsection
+
 ENTRY(__qcom_hyp_sanitize_link_stack_start)
 	stp     x29, x30, [sp, #-16]!
 	.rept	16

arch/arm64/kernel/cpu_errata.c

@@ -78,6 +78,8 @@ cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
 	config_sctlr_el1(SCTLR_EL1_UCT, 0);
 }
 
+atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
+
 #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
@@ -108,7 +110,6 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 				      const char *hyp_vecs_start,
 				      const char *hyp_vecs_end)
 {
-	static int last_slot = -1;
 	static DEFINE_SPINLOCK(bp_lock);
 	int cpu, slot = -1;
 
@@ -121,10 +122,8 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 	}
 
 	if (slot == -1) {
-		last_slot++;
-		BUG_ON(((__bp_harden_hyp_vecs_end - __bp_harden_hyp_vecs_start)
-			/ SZ_2K) <= last_slot);
-		slot = last_slot;
+		slot = atomic_inc_return(&arm64_el2_vector_last_slot);
+		BUG_ON(slot >= BP_HARDEN_EL2_SLOTS);
 		__copy_hyp_vect_bpi(slot, hyp_vecs_start, hyp_vecs_end);
 	}
 
@@ -348,6 +347,10 @@ static const struct arm64_cpu_capabilities arm64_bp_harden_list[] = {
 
 #endif
 
+#ifndef ERRATA_MIDR_ALL_VERSIONS
+#define	ERRATA_MIDR_ALL_VERSIONS(x)	MIDR_ALL_VERSIONS(x)
+#endif
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #if	defined(CONFIG_ARM64_ERRATUM_826319) || \
 	defined(CONFIG_ARM64_ERRATUM_827319) || \
@@ -500,6 +503,18 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.capability = ARM64_HARDEN_BP_POST_GUEST_EXIT,
 		ERRATA_MIDR_RANGE_LIST(qcom_bp_harden_cpus),
 	},
+#endif
+#ifdef CONFIG_HARDEN_EL2_VECTORS
+	{
+		.desc = "Cortex-A57 EL2 vector hardening",
+		.capability = ARM64_HARDEN_EL2_VECTORS,
+		ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
+	},
+	{
+		.desc = "Cortex-A72 EL2 vector hardening",
+		.capability = ARM64_HARDEN_EL2_VECTORS,
+		ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
+	},
 #endif
 	{
 	}

arch/arm64/kernel/cpufeature.c

@@ -838,19 +838,6 @@ static bool has_no_hw_prefetch(const struct arm64_cpu_capabilities *entry, int _
 		MIDR_CPU_VAR_REV(1, MIDR_REVISION_MASK));
 }
 
-static bool hyp_offset_low(const struct arm64_cpu_capabilities *entry,
-			   int __unused)
-{
-	phys_addr_t idmap_addr = __pa_symbol(__hyp_idmap_text_start);
-
-	/*
-	 * Activate the lower HYP offset only if:
-	 * - the idmap doesn't clash with it,
-	 * - the kernel is not running at EL2.
-	 */
-	return idmap_addr > GENMASK(VA_BITS - 2, 0) && !is_kernel_in_hyp_mode();
-}
-
 static bool has_no_fpsimd(const struct arm64_cpu_capabilities *entry, int __unused)
 {
 	u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
@@ -1121,12 +1108,6 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.field_pos = ID_AA64PFR0_EL0_SHIFT,
 		.min_field_value = ID_AA64PFR0_EL0_32BIT_64BIT,
 	},
-	{
-		.desc = "Reduced HYP mapping offset",
-		.capability = ARM64_HYP_OFFSET_LOW,
-		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
-		.matches = hyp_offset_low,
-	},
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	{
 		.desc = "Kernel page table isolation (KPTI)",

arch/arm64/kernel/head.S

@@ -577,6 +577,13 @@ set_hcr:
 7:
 	msr	mdcr_el2, x3			// Configure debug traps
 
+	/* LORegions */
+	mrs	x1, id_aa64mmfr1_el1
+	ubfx	x0, x1, #ID_AA64MMFR1_LOR_SHIFT, 4
+	cbz	x0, 1f
+	msr_s	SYS_LORC_EL1, xzr
+1:
+
 	/* Stage-2 translation */
 	msr	vttbr_el2, xzr
 

arch/arm64/kernel/insn.c

@@ -35,6 +35,7 @@
 
 #define AARCH64_INSN_SF_BIT	BIT(31)
 #define AARCH64_INSN_N_BIT	BIT(22)
+#define AARCH64_INSN_LSL_12	BIT(22)
 
 static int aarch64_insn_encoding_class[] = {
 	AARCH64_INSN_CLS_UNKNOWN,
@@ -343,6 +344,10 @@ static int __kprobes aarch64_get_imm_shift_mask(enum aarch64_insn_imm_type type,
 		mask = BIT(6) - 1;
 		shift = 16;
 		break;
+	case AARCH64_INSN_IMM_N:
+		mask = 1;
+		shift = 22;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -899,9 +904,18 @@ u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst,
 		return AARCH64_BREAK_FAULT;
 	}
 
+	/* We can't encode more than a 24bit value (12bit + 12bit shift) */
+	if (imm & ~(BIT(24) - 1))
+		goto out;
+
+	/* If we have something in the top 12 bits... */
 	if (imm & ~(SZ_4K - 1)) {
-		pr_err("%s: invalid immediate encoding %d\n", __func__, imm);
-		return AARCH64_BREAK_FAULT;
+		/* ... and in the low 12 bits -> error */
+		if (imm & (SZ_4K - 1))
+			goto out;
+
+		imm >>= 12;
+		insn |= AARCH64_INSN_LSL_12;
 	}
 
 	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
@@ -909,6 +923,10 @@ u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst,
 	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src);
 
 	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_12, insn, imm);
+
+out:
+	pr_err("%s: invalid immediate encoding %d\n", __func__, imm);
+	return AARCH64_BREAK_FAULT;
 }
 
 u32 aarch64_insn_gen_bitfield(enum aarch64_insn_register dst,
@@ -1481,3 +1499,171 @@ pstate_check_t * const aarch32_opcode_cond_checks[16] = {
 	__check_hi, __check_ls, __check_ge, __check_lt,
 	__check_gt, __check_le, __check_al, __check_al
 };
+
+static bool range_of_ones(u64 val)
+{
+	/* Doesn't handle full ones or full zeroes */
+	u64 sval = val >> __ffs64(val);
+
+	/* One of Sean Eron Anderson's bithack tricks */
+	return ((sval + 1) & (sval)) == 0;
+}
+
+static u32 aarch64_encode_immediate(u64 imm,
+				    enum aarch64_insn_variant variant,
+				    u32 insn)
+{
+	unsigned int immr, imms, n, ones, ror, esz, tmp;
+	u64 mask = ~0UL;
+
+	/* Can't encode full zeroes or full ones */
+	if (!imm || !~imm)
+		return AARCH64_BREAK_FAULT;
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		if (upper_32_bits(imm))
+			return AARCH64_BREAK_FAULT;
+		esz = 32;
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		esz = 64;
+		break;
+	default:
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	/*
+	 * Inverse of Replicate(). Try to spot a repeating pattern
+	 * with a pow2 stride.
+	 */
+	for (tmp = esz / 2; tmp >= 2; tmp /= 2) {
+		u64 emask = BIT(tmp) - 1;
+
+		if ((imm & emask) != ((imm >> tmp) & emask))
+			break;
+
+		esz = tmp;
+		mask = emask;
+	}
+
+	/* N is only set if we're encoding a 64bit value */
+	n = esz == 64;
+
+	/* Trim imm to the element size */
+	imm &= mask;
+
+	/* That's how many ones we need to encode */
+	ones = hweight64(imm);
+
+	/*
+	 * imms is set to (ones - 1), prefixed with a string of ones
+	 * and a zero if they fit. Cap it to 6 bits.
+	 */
+	imms  = ones - 1;
+	imms |= 0xf << ffs(esz);
+	imms &= BIT(6) - 1;
+
+	/* Compute the rotation */
+	if (range_of_ones(imm)) {
+		/*
+		 * Pattern: 0..01..10..0
+		 *
+		 * Compute how many rotate we need to align it right
+		 */
+		ror = __ffs64(imm);
+	} else {
+		/*
+		 * Pattern: 0..01..10..01..1
+		 *
+		 * Fill the unused top bits with ones, and check if
+		 * the result is a valid immediate (all ones with a
+		 * contiguous ranges of zeroes).
+		 */
+		imm |= ~mask;
+		if (!range_of_ones(~imm))
+			return AARCH64_BREAK_FAULT;
+
+		/*
+		 * Compute the rotation to get a continuous set of
+		 * ones, with the first bit set at position 0
+		 */
+		ror = fls(~imm);
+	}
+
+	/*
+	 * immr is the number of bits we need to rotate back to the
+	 * original set of ones. Note that this is relative to the
+	 * element size...
+	 */
+	immr = (esz - ror) % esz;
+
+	insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_N, insn, n);
+	insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_R, insn, immr);
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_S, insn, imms);
+}
+
+u32 aarch64_insn_gen_logical_immediate(enum aarch64_insn_logic_type type,
+				       enum aarch64_insn_variant variant,
+				       enum aarch64_insn_register Rn,
+				       enum aarch64_insn_register Rd,
+				       u64 imm)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_LOGIC_AND:
+		insn = aarch64_insn_get_and_imm_value();
+		break;
+	case AARCH64_INSN_LOGIC_ORR:
+		insn = aarch64_insn_get_orr_imm_value();
+		break;
+	case AARCH64_INSN_LOGIC_EOR:
+		insn = aarch64_insn_get_eor_imm_value();
+		break;
+	case AARCH64_INSN_LOGIC_AND_SETFLAGS:
+		insn = aarch64_insn_get_ands_imm_value();
+		break;
+	default:
+		pr_err("%s: unknown logical encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, Rd);
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, Rn);
+	return aarch64_encode_immediate(imm, variant, insn);
+}
+
+u32 aarch64_insn_gen_extr(enum aarch64_insn_variant variant,
+			  enum aarch64_insn_register Rm,
+			  enum aarch64_insn_register Rn,
+			  enum aarch64_insn_register Rd,
+			  u8 lsb)
+{
+	u32 insn;
+
+	insn = aarch64_insn_get_extr_value();
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		if (lsb > 31)
+			return AARCH64_BREAK_FAULT;
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		if (lsb > 63)
+			return AARCH64_BREAK_FAULT;
+		insn |= AARCH64_INSN_SF_BIT;
+		insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_N, insn, 1);
+		break;
+	default:
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_S, insn, lsb);
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, Rd);
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, Rn);
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, Rm);
+}

arch/arm64/kvm/Kconfig

@@ -57,6 +57,9 @@ config KVM_ARM_PMU
 	  Adds support for a virtual Performance Monitoring Unit (PMU) in
 	  virtual machines.
 
+config KVM_INDIRECT_VECTORS
+       def_bool KVM && (HARDEN_BRANCH_PREDICTOR || HARDEN_EL2_VECTORS)
+
 source drivers/vhost/Kconfig
 
 endif # VIRTUALIZATION

arch/arm64/kvm/Makefile

@@ -16,7 +16,7 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/e
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/psci.o $(KVM)/arm/perf.o
 
-kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o
+kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o va_layout.o
 kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
 kvm-$(CONFIG_KVM_ARM_HOST) += guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o
 kvm-$(CONFIG_KVM_ARM_HOST) += vgic-sys-reg-v3.o

arch/arm64/kvm/debug.c

@@ -46,7 +46,9 @@ static DEFINE_PER_CPU(u32, mdcr_el2);
  */
 static void save_guest_debug_regs(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.guest_debug_preserved.mdscr_el1 = vcpu_sys_reg(vcpu, MDSCR_EL1);
+	u64 val = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
+
+	vcpu->arch.guest_debug_preserved.mdscr_el1 = val;
 
 	trace_kvm_arm_set_dreg32("Saved MDSCR_EL1",
 				vcpu->arch.guest_debug_preserved.mdscr_el1);
@@ -54,10 +56,12 @@ static void save_guest_debug_regs(struct kvm_vcpu *vcpu)
 
 static void restore_guest_debug_regs(struct kvm_vcpu *vcpu)
 {
-	vcpu_sys_reg(vcpu, MDSCR_EL1) = vcpu->arch.guest_debug_preserved.mdscr_el1;
+	u64 val = vcpu->arch.guest_debug_preserved.mdscr_el1;
+
+	vcpu_write_sys_reg(vcpu, val, MDSCR_EL1);
 
 	trace_kvm_arm_set_dreg32("Restored MDSCR_EL1",
-				vcpu_sys_reg(vcpu, MDSCR_EL1));
+				vcpu_read_sys_reg(vcpu, MDSCR_EL1));
 }
 
 /**
@@ -108,6 +112,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu)
 void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 {
 	bool trap_debug = !(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY);
+	unsigned long mdscr;
 
 	trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug);
 
@@ -152,9 +157,13 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 		 */
 		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
 			*vcpu_cpsr(vcpu) |=  DBG_SPSR_SS;
-			vcpu_sys_reg(vcpu, MDSCR_EL1) |= DBG_MDSCR_SS;
+			mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
+			mdscr |= DBG_MDSCR_SS;
+			vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1);
 		} else {
-			vcpu_sys_reg(vcpu, MDSCR_EL1) &= ~DBG_MDSCR_SS;
+			mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
+			mdscr &= ~DBG_MDSCR_SS;
+			vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1);
 		}
 
 		trace_kvm_arm_set_dreg32("SPSR_EL2", *vcpu_cpsr(vcpu));
@@ -170,7 +179,9 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 		 */
 		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) {
 			/* Enable breakpoints/watchpoints */
-			vcpu_sys_reg(vcpu, MDSCR_EL1) |= DBG_MDSCR_MDE;
+			mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
+			mdscr |= DBG_MDSCR_MDE;
+			vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1);
 
 			vcpu->arch.debug_ptr = &vcpu->arch.external_debug_state;
 			vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
@@ -193,8 +204,12 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 	if (trap_debug)
 		vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA;
 
+	/* If KDE or MDE are set, perform a full save/restore cycle. */
+	if (vcpu_read_sys_reg(vcpu, MDSCR_EL1) & (DBG_MDSCR_KDE | DBG_MDSCR_MDE))
+		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+
 	trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2);
-	trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_sys_reg(vcpu, MDSCR_EL1));
+	trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1));
 }
 
 void kvm_arm_clear_debug(struct kvm_vcpu *vcpu)

arch/arm64/kvm/hyp-init.S

@@ -117,7 +117,6 @@ CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
 	/* Set the stack and new vectors */
 	kern_hyp_va	x1
 	mov	sp, x1
-	kern_hyp_va	x2
 	msr	vbar_el2, x2
 
 	/* copy tpidr_el1 into tpidr_el2 for use by HYP */

arch/arm64/kvm/hyp/Makefile

@@ -7,10 +7,10 @@ ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING
 
 KVM=../../../../virt/kvm
 
-obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o
 
+obj-$(CONFIG_KVM_ARM_HOST) += vgic-v2-cpuif-proxy.o
 obj-$(CONFIG_KVM_ARM_HOST) += sysreg-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += debug-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += entry.o

arch/arm64/kvm/hyp/debug-sr.c

@@ -66,11 +66,6 @@
 	default:	write_debug(ptr[0], reg, 0);			\
 	}
 
-static void __hyp_text __debug_save_spe_vhe(u64 *pmscr_el1)
-{
-	/* The vcpu can run. but it can't hide. */
-}
-
 static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1)
 {
 	u64 reg;
@@ -103,11 +98,7 @@ static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1)
 	dsb(nsh);
 }
 
-static hyp_alternate_select(__debug_save_spe,
-			    __debug_save_spe_nvhe, __debug_save_spe_vhe,
-			    ARM64_HAS_VIRT_HOST_EXTN);
-
-static void __hyp_text __debug_restore_spe(u64 pmscr_el1)
+static void __hyp_text __debug_restore_spe_nvhe(u64 pmscr_el1)
 {
 	if (!pmscr_el1)
 		return;
@@ -119,16 +110,13 @@ static void __hyp_text __debug_restore_spe(u64 pmscr_el1)
 	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
 }
 
-void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
-				   struct kvm_guest_debug_arch *dbg,
-				   struct kvm_cpu_context *ctxt)
+static void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
+					  struct kvm_guest_debug_arch *dbg,
+					  struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
 
-	if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY))
-		return;
-
 	aa64dfr0 = read_sysreg(id_aa64dfr0_el1);
 	brps = (aa64dfr0 >> 12) & 0xf;
 	wrps = (aa64dfr0 >> 20) & 0xf;
@@ -141,16 +129,13 @@ void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
 	ctxt->sys_regs[MDCCINT_EL1] = read_sysreg(mdccint_el1);
 }
 
-void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
-				      struct kvm_guest_debug_arch *dbg,
-				      struct kvm_cpu_context *ctxt)
+static void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
+					     struct kvm_guest_debug_arch *dbg,
+					     struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
 
-	if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY))
-		return;
-
 	aa64dfr0 = read_sysreg(id_aa64dfr0_el1);
 
 	brps = (aa64dfr0 >> 12) & 0xf;
@@ -164,27 +149,54 @@ void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
 	write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1);
 }
 
-void __hyp_text __debug_cond_save_host_state(struct kvm_vcpu *vcpu)
+void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu)
 {
-	/* If any of KDE, MDE or KVM_ARM64_DEBUG_DIRTY is set, perform
-	 * a full save/restore cycle. */
-	if ((vcpu->arch.ctxt.sys_regs[MDSCR_EL1] & DBG_MDSCR_KDE) ||
-	    (vcpu->arch.ctxt.sys_regs[MDSCR_EL1] & DBG_MDSCR_MDE))
-		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
-
-	__debug_save_state(vcpu, &vcpu->arch.host_debug_state.regs,
-			   kern_hyp_va(vcpu->arch.host_cpu_context));
-	__debug_save_spe()(&vcpu->arch.host_debug_state.pmscr_el1);
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *guest_ctxt;
+	struct kvm_guest_debug_arch *host_dbg;
+	struct kvm_guest_debug_arch *guest_dbg;
+
+	/*
+	 * Non-VHE: Disable and flush SPE data generation
+	 * VHE: The vcpu can run, but it can't hide.
+	 */
+	if (!has_vhe())
+		__debug_save_spe_nvhe(&vcpu->arch.host_debug_state.pmscr_el1);
+
+	if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY))
+		return;
+
+	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+	guest_ctxt = &vcpu->arch.ctxt;
+	host_dbg = &vcpu->arch.host_debug_state.regs;
+	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
+
+	__debug_save_state(vcpu, host_dbg, host_ctxt);
+	__debug_restore_state(vcpu, guest_dbg, guest_ctxt);
 }
 
-void __hyp_text __debug_cond_restore_host_state(struct kvm_vcpu *vcpu)
+void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
 {
-	__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
-	__debug_restore_state(vcpu, &vcpu->arch.host_debug_state.regs,
-			      kern_hyp_va(vcpu->arch.host_cpu_context));
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *guest_ctxt;
+	struct kvm_guest_debug_arch *host_dbg;
+	struct kvm_guest_debug_arch *guest_dbg;
+
+	if (!has_vhe())
+		__debug_restore_spe_nvhe(vcpu->arch.host_debug_state.pmscr_el1);
+
+	if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY))
+		return;
+
+	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+	guest_ctxt = &vcpu->arch.ctxt;
+	host_dbg = &vcpu->arch.host_debug_state.regs;
+	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
+
+	__debug_save_state(vcpu, guest_dbg, guest_ctxt);
+	__debug_restore_state(vcpu, host_dbg, host_ctxt);
 
-	if (vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY)
-		vcpu->arch.debug_flags &= ~KVM_ARM64_DEBUG_DIRTY;
+	vcpu->arch.debug_flags &= ~KVM_ARM64_DEBUG_DIRTY;
 }
 
 u32 __hyp_text __kvm_get_mdcr_el2(void)

arch/arm64/kvm/hyp/entry.S

@@ -62,9 +62,6 @@ ENTRY(__guest_enter)
 	// Store the host regs
 	save_callee_saved_regs x1
 
-	// Store host_ctxt and vcpu for use at exit time
-	stp	x1, x0, [sp, #-16]!
-
 	add	x18, x0, #VCPU_CONTEXT
 
 	// Restore guest regs x0-x17
@@ -118,8 +115,7 @@ ENTRY(__guest_exit)
 	// Store the guest regs x19-x29, lr
 	save_callee_saved_regs x1
 
-	// Restore the host_ctxt from the stack
-	ldr	x2, [sp], #16
+	get_host_ctxt	x2, x3
 
 	// Now restore the host regs
 	restore_callee_saved_regs x2

arch/arm64/kvm/hyp/hyp-entry.S

@@ -55,15 +55,9 @@ ENTRY(__vhe_hyp_call)
 ENDPROC(__vhe_hyp_call)
 
 el1_sync:				// Guest trapped into EL2
-	stp	x0, x1, [sp, #-16]!
-
-alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
-	mrs	x1, esr_el2
-alternative_else
-	mrs	x1, esr_el1
-alternative_endif
-	lsr	x0, x1, #ESR_ELx_EC_SHIFT
 
+	mrs	x0, esr_el2
+	lsr	x0, x0, #ESR_ELx_EC_SHIFT
 	cmp	x0, #ESR_ELx_EC_HVC64
 	ccmp	x0, #ESR_ELx_EC_HVC32, #4, ne
 	b.ne	el1_trap
@@ -117,10 +111,14 @@ el1_hvc_guest:
 	eret
 
 el1_trap:
+	get_vcpu_ptr	x1, x0
+
+	mrs		x0, esr_el2
+	lsr		x0, x0, #ESR_ELx_EC_SHIFT
 	/*
 	 * x0: ESR_EC
+	 * x1: vcpu pointer
 	 */
-	ldr	x1, [sp, #16 + 8]	// vcpu stored by __guest_enter
 
 	/*
 	 * We trap the first access to the FP/SIMD to save the host context
@@ -137,18 +135,18 @@ alternative_else_nop_endif
 	b	__guest_exit
 
 el1_irq:
-	stp     x0, x1, [sp, #-16]!
-	ldr	x1, [sp, #16 + 8]
+	get_vcpu_ptr	x1, x0
 	mov	x0, #ARM_EXCEPTION_IRQ
 	b	__guest_exit
 
 el1_error:
-	stp     x0, x1, [sp, #-16]!
-	ldr	x1, [sp, #16 + 8]
+	get_vcpu_ptr	x1, x0
 	mov	x0, #ARM_EXCEPTION_EL1_SERROR
 	b	__guest_exit
 
 el2_error:
+	ldp	x0, x1, [sp], #16
+
 	/*
 	 * Only two possibilities:
 	 * 1) Either we come from the exit path, having just unmasked
@@ -180,14 +178,7 @@ ENTRY(__hyp_do_panic)
 ENDPROC(__hyp_do_panic)
 
 ENTRY(__hyp_panic)
-	/*
-	 * '=kvm_host_cpu_state' is a host VA from the constant pool, it may
-	 * not be accessible by this address from EL2, hyp_panic() converts
-	 * it with kern_hyp_va() before use.
-	 */
-	ldr	x0, =kvm_host_cpu_state
-	mrs	x1, tpidr_el2
-	add	x0, x0, x1
+	get_host_ctxt x0, x1
 	b	hyp_panic
 ENDPROC(__hyp_panic)
 
@@ -206,32 +197,43 @@ ENDPROC(\label)
 	invalid_vector	el2h_sync_invalid
 	invalid_vector	el2h_irq_invalid
 	invalid_vector	el2h_fiq_invalid
-	invalid_vector	el1_sync_invalid
-	invalid_vector	el1_irq_invalid
 	invalid_vector	el1_fiq_invalid
 
 	.ltorg
 
 	.align 11
 
+.macro valid_vect target
+	.align 7
+	stp	x0, x1, [sp, #-16]!
+	b	\target
+.endm
+
+.macro invalid_vect target
+	.align 7
+	b	\target
+	ldp	x0, x1, [sp], #16
+	b	\target
+.endm
+
 ENTRY(__kvm_hyp_vector)
-	ventry	el2t_sync_invalid		// Synchronous EL2t
-	ventry	el2t_irq_invalid		// IRQ EL2t
-	ventry	el2t_fiq_invalid		// FIQ EL2t
-	ventry	el2t_error_invalid		// Error EL2t
-
-	ventry	el2h_sync_invalid		// Synchronous EL2h
-	ventry	el2h_irq_invalid		// IRQ EL2h
-	ventry	el2h_fiq_invalid		// FIQ EL2h
-	ventry	el2_error			// Error EL2h
-
-	ventry	el1_sync			// Synchronous 64-bit EL1
-	ventry	el1_irq				// IRQ 64-bit EL1
-	ventry	el1_fiq_invalid			// FIQ 64-bit EL1
-	ventry	el1_error			// Error 64-bit EL1
-
-	ventry	el1_sync			// Synchronous 32-bit EL1
-	ventry	el1_irq				// IRQ 32-bit EL1
-	ventry	el1_fiq_invalid			// FIQ 32-bit EL1
-	ventry	el1_error			// Error 32-bit EL1
+	invalid_vect	el2t_sync_invalid	// Synchronous EL2t
+	invalid_vect	el2t_irq_invalid	// IRQ EL2t
+	invalid_vect	el2t_fiq_invalid	// FIQ EL2t
+	invalid_vect	el2t_error_invalid	// Error EL2t
+
+	invalid_vect	el2h_sync_invalid	// Synchronous EL2h
+	invalid_vect	el2h_irq_invalid	// IRQ EL2h
+	invalid_vect	el2h_fiq_invalid	// FIQ EL2h
+	valid_vect	el2_error		// Error EL2h
+
+	valid_vect	el1_sync		// Synchronous 64-bit EL1
+	valid_vect	el1_irq			// IRQ 64-bit EL1
+	invalid_vect	el1_fiq_invalid		// FIQ 64-bit EL1
+	valid_vect	el1_error		// Error 64-bit EL1
+
+	valid_vect	el1_sync		// Synchronous 32-bit EL1
+	valid_vect	el1_irq			// IRQ 32-bit EL1
+	invalid_vect	el1_fiq_invalid		// FIQ 32-bit EL1
+	valid_vect	el1_error		// Error 32-bit EL1
 ENDPROC(__kvm_hyp_vector)

arch/arm64/kvm/hyp/switch.c

@@ -33,49 +33,22 @@ static bool __hyp_text __fpsimd_enabled_nvhe(void)
 	return !(read_sysreg(cptr_el2) & CPTR_EL2_TFP);
 }
 
-static bool __hyp_text __fpsimd_enabled_vhe(void)
+static bool fpsimd_enabled_vhe(void)
 {
 	return !!(read_sysreg(cpacr_el1) & CPACR_EL1_FPEN);
 }
 
-static hyp_alternate_select(__fpsimd_is_enabled,
-			    __fpsimd_enabled_nvhe, __fpsimd_enabled_vhe,
-			    ARM64_HAS_VIRT_HOST_EXTN);
-
-bool __hyp_text __fpsimd_enabled(void)
-{
-	return __fpsimd_is_enabled()();
-}
-
-static void __hyp_text __activate_traps_vhe(void)
-{
-	u64 val;
-
-	val = read_sysreg(cpacr_el1);
-	val |= CPACR_EL1_TTA;
-	val &= ~(CPACR_EL1_FPEN | CPACR_EL1_ZEN);
-	write_sysreg(val, cpacr_el1);
-
-	write_sysreg(kvm_get_hyp_vector(), vbar_el1);
-}
-
-static void __hyp_text __activate_traps_nvhe(void)
+/* Save the 32-bit only FPSIMD system register state */
+static void __hyp_text __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
 {
-	u64 val;
+	if (!vcpu_el1_is_32bit(vcpu))
+		return;
 
-	val = CPTR_EL2_DEFAULT;
-	val |= CPTR_EL2_TTA | CPTR_EL2_TFP | CPTR_EL2_TZ;
-	write_sysreg(val, cptr_el2);
+	vcpu->arch.ctxt.sys_regs[FPEXC32_EL2] = read_sysreg(fpexc32_el2);
 }
 
-static hyp_alternate_select(__activate_traps_arch,
-			    __activate_traps_nvhe, __activate_traps_vhe,
-			    ARM64_HAS_VIRT_HOST_EXTN);
-
-static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
+static void __hyp_text __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 {
-	u64 val;
-
 	/*
 	 * We are about to set CPTR_EL2.TFP to trap all floating point
 	 * register accesses to EL2, however, the ARM ARM clearly states that
@@ -85,23 +58,17 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 	 * If FP/ASIMD is not implemented, FPEXC is UNDEFINED and any access to
 	 * it will cause an exception.
 	 */
-	val = vcpu->arch.hcr_el2;
-
-	if (!(val & HCR_RW) && system_supports_fpsimd()) {
+	if (vcpu_el1_is_32bit(vcpu) && system_supports_fpsimd()) {
 		write_sysreg(1 << 30, fpexc32_el2);
 		isb();
 	}
+}
 
-	if (val & HCR_RW) /* for AArch64 only: */
-		val |= HCR_TID3; /* TID3: trap feature register accesses */
-
-	write_sysreg(val, hcr_el2);
-
-	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (val & HCR_VSE))
-		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
-
-	/* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */
+static void __hyp_text __activate_traps_common(struct kvm_vcpu *vcpu)
+{
+	/* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
 	write_sysreg(1 << 15, hstr_el2);
+
 	/*
 	 * Make sure we trap PMU access from EL0 to EL2. Also sanitize
 	 * PMSELR_EL0 to make sure it never contains the cycle
@@ -111,19 +78,56 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 	write_sysreg(0, pmselr_el0);
 	write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
-	__activate_traps_arch()();
 }
 
-static void __hyp_text __deactivate_traps_vhe(void)
+static void __hyp_text __deactivate_traps_common(void)
 {
-	extern char vectors[];	/* kernel exception vectors */
-	u64 mdcr_el2 = read_sysreg(mdcr_el2);
+	write_sysreg(0, hstr_el2);
+	write_sysreg(0, pmuserenr_el0);
+}
 
-	mdcr_el2 &= MDCR_EL2_HPMN_MASK |
-		    MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT |
-		    MDCR_EL2_TPMS;
+static void activate_traps_vhe(struct kvm_vcpu *vcpu)
+{
+	u64 val;
 
-	write_sysreg(mdcr_el2, mdcr_el2);
+	val = read_sysreg(cpacr_el1);
+	val |= CPACR_EL1_TTA;
+	val &= ~(CPACR_EL1_FPEN | CPACR_EL1_ZEN);
+	write_sysreg(val, cpacr_el1);
+
+	write_sysreg(kvm_get_hyp_vector(), vbar_el1);
+}
+
+static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	__activate_traps_common(vcpu);
+
+	val = CPTR_EL2_DEFAULT;
+	val |= CPTR_EL2_TTA | CPTR_EL2_TFP | CPTR_EL2_TZ;
+	write_sysreg(val, cptr_el2);
+}
+
+static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
+{
+	u64 hcr = vcpu->arch.hcr_el2;
+
+	write_sysreg(hcr, hcr_el2);
+
+	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
+		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
+
+	__activate_traps_fpsimd32(vcpu);
+	if (has_vhe())
+		activate_traps_vhe(vcpu);
+	else
+		__activate_traps_nvhe(vcpu);
+}
+
+static void deactivate_traps_vhe(void)
+{
+	extern char vectors[];	/* kernel exception vectors */
 	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
 	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
 	write_sysreg(vectors, vbar_el1);
@@ -133,6 +137,8 @@ static void __hyp_text __deactivate_traps_nvhe(void)
 {
 	u64 mdcr_el2 = read_sysreg(mdcr_el2);
 
+	__deactivate_traps_common();
+
 	mdcr_el2 &= MDCR_EL2_HPMN_MASK;
 	mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
 
@@ -141,10 +147,6 @@ static void __hyp_text __deactivate_traps_nvhe(void)
 	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
 }
 
-static hyp_alternate_select(__deactivate_traps_arch,
-			    __deactivate_traps_nvhe, __deactivate_traps_vhe,
-			    ARM64_HAS_VIRT_HOST_EXTN);
-
 static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
 {
 	/*
@@ -156,14 +158,32 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.hcr_el2 & HCR_VSE)
 		vcpu->arch.hcr_el2 = read_sysreg(hcr_el2);
 
-	__deactivate_traps_arch()();
-	write_sysreg(0, hstr_el2);
-	write_sysreg(0, pmuserenr_el0);
+	if (has_vhe())
+		deactivate_traps_vhe();
+	else
+		__deactivate_traps_nvhe();
+}
+
+void activate_traps_vhe_load(struct kvm_vcpu *vcpu)
+{
+	__activate_traps_common(vcpu);
+}
+
+void deactivate_traps_vhe_put(void)
+{
+	u64 mdcr_el2 = read_sysreg(mdcr_el2);
+
+	mdcr_el2 &= MDCR_EL2_HPMN_MASK |
+		    MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT |
+		    MDCR_EL2_TPMS;
+
+	write_sysreg(mdcr_el2, mdcr_el2);
+
+	__deactivate_traps_common();
 }
 
-static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu)
+static void __hyp_text __activate_vm(struct kvm *kvm)
 {
-	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
 	write_sysreg(kvm->arch.vttbr, vttbr_el2);
 }
 
@@ -172,29 +192,22 @@ static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
 	write_sysreg(0, vttbr_el2);
 }
 
-static void __hyp_text __vgic_save_state(struct kvm_vcpu *vcpu)
+/* Save VGICv3 state on non-VHE systems */
+static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
 {
-	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
+	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
 		__vgic_v3_save_state(vcpu);
-	else
-		__vgic_v2_save_state(vcpu);
-
-	write_sysreg(read_sysreg(hcr_el2) & ~HCR_INT_OVERRIDE, hcr_el2);
+		__vgic_v3_deactivate_traps(vcpu);
+	}
 }
 
-static void __hyp_text __vgic_restore_state(struct kvm_vcpu *vcpu)
+/* Restore VGICv3 state on non_VEH systems */
+static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
 {
-	u64 val;
-
-	val = read_sysreg(hcr_el2);
-	val |= 	HCR_INT_OVERRIDE;
-	val |= vcpu->arch.irq_lines;
-	write_sysreg(val, hcr_el2);
-
-	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
+	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
+		__vgic_v3_activate_traps(vcpu);
 		__vgic_v3_restore_state(vcpu);
-	else
-		__vgic_v2_restore_state(vcpu);
+	}
 }
 
 static bool __hyp_text __true_value(void)
@@ -305,54 +318,27 @@ static bool __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
 	}
 }
 
-int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
+/*
+ * Return true when we were able to fixup the guest exit and should return to
+ * the guest, false when we should restore the host state and return to the
+ * main run loop.
+ */
+static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
-	struct kvm_cpu_context *host_ctxt;
-	struct kvm_cpu_context *guest_ctxt;
-	bool fp_enabled;
-	u64 exit_code;
-
-	vcpu = kern_hyp_va(vcpu);
-
-	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
-	host_ctxt->__hyp_running_vcpu = vcpu;
-	guest_ctxt = &vcpu->arch.ctxt;
-
-	__sysreg_save_host_state(host_ctxt);
-	__debug_cond_save_host_state(vcpu);
-
-	__activate_traps(vcpu);
-	__activate_vm(vcpu);
-
-	__vgic_restore_state(vcpu);
-	__timer_enable_traps(vcpu);
-
-	/*
-	 * We must restore the 32-bit state before the sysregs, thanks
-	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
-	 */
-	__sysreg32_restore_state(vcpu);
-	__sysreg_restore_guest_state(guest_ctxt);
-	__debug_restore_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt);
-
-	/* Jump in the fire! */
-again:
-	exit_code = __guest_enter(vcpu, host_ctxt);
-	/* And we're baaack! */
-
-	if (ARM_EXCEPTION_CODE(exit_code) != ARM_EXCEPTION_IRQ)
+	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
 		vcpu->arch.fault.esr_el2 = read_sysreg_el2(esr);
+
 	/*
 	 * We're using the raw exception code in order to only process
 	 * the trap if no SError is pending. We will come back to the
 	 * same PC once the SError has been injected, and replay the
 	 * trapping instruction.
 	 */
-	if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu))
-		goto again;
+	if (*exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu))
+		return true;
 
 	if (static_branch_unlikely(&vgic_v2_cpuif_trap) &&
-	    exit_code == ARM_EXCEPTION_TRAP) {
+	    *exit_code == ARM_EXCEPTION_TRAP) {
 		bool valid;
 
 		valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
@@ -366,9 +352,9 @@ again:
 
 			if (ret == 1) {
 				if (__skip_instr(vcpu))
-					goto again;
+					return true;
 				else
-					exit_code = ARM_EXCEPTION_TRAP;
+					*exit_code = ARM_EXCEPTION_TRAP;
 			}
 
 			if (ret == -1) {
@@ -380,29 +366,112 @@ again:
 				 */
 				if (!__skip_instr(vcpu))
 					*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
-				exit_code = ARM_EXCEPTION_EL1_SERROR;
+				*exit_code = ARM_EXCEPTION_EL1_SERROR;
 			}
-
-			/* 0 falls through to be handler out of EL2 */
 		}
 	}
 
 	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
-	    exit_code == ARM_EXCEPTION_TRAP &&
+	    *exit_code == ARM_EXCEPTION_TRAP &&
 	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 ||
 	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
 		int ret = __vgic_v3_perform_cpuif_access(vcpu);
 
 		if (ret == 1) {
 			if (__skip_instr(vcpu))
-				goto again;
+				return true;
 			else
-				exit_code = ARM_EXCEPTION_TRAP;
+				*exit_code = ARM_EXCEPTION_TRAP;
 		}
+	}
 
-		/* 0 falls through to be handled out of EL2 */
+	/* Return to the host kernel and handle the exit */
+	return false;
+}
+
+/* Switch to the guest for VHE systems running in EL2 */
+int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *guest_ctxt;
+	bool fp_enabled;
+	u64 exit_code;
+
+	host_ctxt = vcpu->arch.host_cpu_context;
+	host_ctxt->__hyp_running_vcpu = vcpu;
+	guest_ctxt = &vcpu->arch.ctxt;
+
+	sysreg_save_host_state_vhe(host_ctxt);
+
+	__activate_traps(vcpu);
+	__activate_vm(vcpu->kvm);
+
+	sysreg_restore_guest_state_vhe(guest_ctxt);
+	__debug_switch_to_guest(vcpu);
+
+	do {
+		/* Jump in the fire! */
+		exit_code = __guest_enter(vcpu, host_ctxt);
+
+		/* And we're baaack! */
+	} while (fixup_guest_exit(vcpu, &exit_code));
+
+	fp_enabled = fpsimd_enabled_vhe();
+
+	sysreg_save_guest_state_vhe(guest_ctxt);
+
+	__deactivate_traps(vcpu);
+
+	sysreg_restore_host_state_vhe(host_ctxt);
+
+	if (fp_enabled) {
+		__fpsimd_save_state(&guest_ctxt->gp_regs.fp_regs);
+		__fpsimd_restore_state(&host_ctxt->gp_regs.fp_regs);
+		__fpsimd_save_fpexc32(vcpu);
 	}
 
+	__debug_switch_to_host(vcpu);
+
+	return exit_code;
+}
+
+/* Switch to the guest for legacy non-VHE systems */
+int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *guest_ctxt;
+	bool fp_enabled;
+	u64 exit_code;
+
+	vcpu = kern_hyp_va(vcpu);
+
+	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+	host_ctxt->__hyp_running_vcpu = vcpu;
+	guest_ctxt = &vcpu->arch.ctxt;
+
+	__sysreg_save_state_nvhe(host_ctxt);
+
+	__activate_traps(vcpu);
+	__activate_vm(kern_hyp_va(vcpu->kvm));
+
+	__hyp_vgic_restore_state(vcpu);
+	__timer_enable_traps(vcpu);
+
+	/*
+	 * We must restore the 32-bit state before the sysregs, thanks
+	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
+	 */
+	__sysreg32_restore_state(vcpu);
+	__sysreg_restore_state_nvhe(guest_ctxt);
+	__debug_switch_to_guest(vcpu);
+
+	do {
+		/* Jump in the fire! */
+		exit_code = __guest_enter(vcpu, host_ctxt);
+
+		/* And we're baaack! */
+	} while (fixup_guest_exit(vcpu, &exit_code));
+
 	if (cpus_have_const_cap(ARM64_HARDEN_BP_POST_GUEST_EXIT)) {
 		u32 midr = read_cpuid_id();
 
@@ -413,29 +482,29 @@ again:
 		}
 	}
 
-	fp_enabled = __fpsimd_enabled();
+	fp_enabled = __fpsimd_enabled_nvhe();
 
-	__sysreg_save_guest_state(guest_ctxt);
+	__sysreg_save_state_nvhe(guest_ctxt);
 	__sysreg32_save_state(vcpu);
 	__timer_disable_traps(vcpu);
-	__vgic_save_state(vcpu);
+	__hyp_vgic_save_state(vcpu);
 
 	__deactivate_traps(vcpu);
 	__deactivate_vm(vcpu);
 
-	__sysreg_restore_host_state(host_ctxt);
+	__sysreg_restore_state_nvhe(host_ctxt);
 
 	if (fp_enabled) {
 		__fpsimd_save_state(&guest_ctxt->gp_regs.fp_regs);
 		__fpsimd_restore_state(&host_ctxt->gp_regs.fp_regs);
+		__fpsimd_save_fpexc32(vcpu);
 	}
 
-	__debug_save_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt);
 	/*
 	 * This must come after restoring the host sysregs, since a non-VHE
 	 * system may enable SPE here and make use of the TTBRs.
 	 */
-	__debug_cond_restore_host_state(vcpu);
+	__debug_switch_to_host(vcpu);
 
 	return exit_code;
 }
@@ -443,10 +512,20 @@ again:
 static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
 
 static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par,
-					     struct kvm_vcpu *vcpu)
+					     struct kvm_cpu_context *__host_ctxt)
 {
+	struct kvm_vcpu *vcpu;
 	unsigned long str_va;
 
+	vcpu = __host_ctxt->__hyp_running_vcpu;
+
+	if (read_sysreg(vttbr_el2)) {
+		__timer_disable_traps(vcpu);
+		__deactivate_traps(vcpu);
+		__deactivate_vm(vcpu);
+		__sysreg_restore_state_nvhe(__host_ctxt);
+	}
+
 	/*
 	 * Force the panic string to be loaded from the literal pool,
 	 * making sure it is a kernel address and not a PC-relative
@@ -460,40 +539,31 @@ static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par,
 		       read_sysreg(hpfar_el2), par, vcpu);
 }
 
-static void __hyp_text __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par,
-					    struct kvm_vcpu *vcpu)
+static void __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par,
+				 struct kvm_cpu_context *host_ctxt)
 {
+	struct kvm_vcpu *vcpu;
+	vcpu = host_ctxt->__hyp_running_vcpu;
+
+	__deactivate_traps(vcpu);
+	sysreg_restore_host_state_vhe(host_ctxt);
+
 	panic(__hyp_panic_string,
 	      spsr,  elr,
 	      read_sysreg_el2(esr),   read_sysreg_el2(far),
 	      read_sysreg(hpfar_el2), par, vcpu);
 }
 
-static hyp_alternate_select(__hyp_call_panic,
-			    __hyp_call_panic_nvhe, __hyp_call_panic_vhe,
-			    ARM64_HAS_VIRT_HOST_EXTN);
-
-void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *__host_ctxt)
+void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
 {
-	struct kvm_vcpu *vcpu = NULL;
-
 	u64 spsr = read_sysreg_el2(spsr);
 	u64 elr = read_sysreg_el2(elr);
 	u64 par = read_sysreg(par_el1);
 
-	if (read_sysreg(vttbr_el2)) {
-		struct kvm_cpu_context *host_ctxt;
-
-		host_ctxt = kern_hyp_va(__host_ctxt);
-		vcpu = host_ctxt->__hyp_running_vcpu;
-		__timer_disable_traps(vcpu);
-		__deactivate_traps(vcpu);
-		__deactivate_vm(vcpu);
-		__sysreg_restore_host_state(host_ctxt);
-	}
-
-	/* Call panic for real */
-	__hyp_call_panic()(spsr, elr, par, vcpu);
+	if (!has_vhe())
+		__hyp_call_panic_nvhe(spsr, elr, par, host_ctxt);
+	else
+		__hyp_call_panic_vhe(spsr, elr, par, host_ctxt);
 
 	unreachable();
 }

arch/arm64/kvm/hyp/sysreg-sr.c

@@ -19,32 +19,43 @@
 #include <linux/kvm_host.h>
 
 #include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 
-/* Yes, this does nothing, on purpose */
-static void __hyp_text __sysreg_do_nothing(struct kvm_cpu_context *ctxt) { }
-
 /*
  * Non-VHE: Both host and guest must save everything.
  *
- * VHE: Host must save tpidr*_el0, actlr_el1, mdscr_el1, sp_el0,
- * and guest must save everything.
+ * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and pstate,
+ * which are handled as part of the el2 return state) on every switch.
+ * tpidr_el0 and tpidrro_el0 only need to be switched when going
+ * to host userspace or a different VCPU.  EL1 registers only need to be
+ * switched when potentially going to run a different VCPU.  The latter two
+ * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put.
  */
 
 static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt->sys_regs[ACTLR_EL1]	= read_sysreg(actlr_el1);
-	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
-	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
 	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
+
+	/*
+	 * The host arm64 Linux uses sp_el0 to point to 'current' and it must
+	 * therefore be saved/restored on every entry/exit to/from the guest.
+	 */
 	ctxt->gp_regs.regs.sp		= read_sysreg(sp_el0);
 }
 
-static void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
+static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
+	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
+}
+
+static void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->sys_regs[MPIDR_EL1]	= read_sysreg(vmpidr_el2);
 	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
 	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg_el1(sctlr);
+	ctxt->sys_regs[ACTLR_EL1]	= read_sysreg(actlr_el1);
 	ctxt->sys_regs[CPACR_EL1]	= read_sysreg_el1(cpacr);
 	ctxt->sys_regs[TTBR0_EL1]	= read_sysreg_el1(ttbr0);
 	ctxt->sys_regs[TTBR1_EL1]	= read_sysreg_el1(ttbr1);
@@ -64,6 +75,10 @@ static void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
 	ctxt->gp_regs.sp_el1		= read_sysreg(sp_el1);
 	ctxt->gp_regs.elr_el1		= read_sysreg_el1(elr);
 	ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(spsr);
+}
+
+static void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
+{
 	ctxt->gp_regs.regs.pc		= read_sysreg_el2(elr);
 	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(spsr);
 
@@ -71,36 +86,48 @@ static void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
 		ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2);
 }
 
-static hyp_alternate_select(__sysreg_call_save_host_state,
-			    __sysreg_save_state, __sysreg_do_nothing,
-			    ARM64_HAS_VIRT_HOST_EXTN);
+void __hyp_text __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_save_el1_state(ctxt);
+	__sysreg_save_common_state(ctxt);
+	__sysreg_save_user_state(ctxt);
+	__sysreg_save_el2_return_state(ctxt);
+}
 
-void __hyp_text __sysreg_save_host_state(struct kvm_cpu_context *ctxt)
+void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt)
 {
-	__sysreg_call_save_host_state()(ctxt);
 	__sysreg_save_common_state(ctxt);
 }
 
-void __hyp_text __sysreg_save_guest_state(struct kvm_cpu_context *ctxt)
+void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt)
 {
-	__sysreg_save_state(ctxt);
 	__sysreg_save_common_state(ctxt);
+	__sysreg_save_el2_return_state(ctxt);
 }
 
 static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
 {
-	write_sysreg(ctxt->sys_regs[ACTLR_EL1],	  actlr_el1);
-	write_sysreg(ctxt->sys_regs[TPIDR_EL0],	  tpidr_el0);
-	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0);
 	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
+
+	/*
+	 * The host arm64 Linux uses sp_el0 to point to 'current' and it must
+	 * therefore be saved/restored on every entry/exit to/from the guest.
+	 */
 	write_sysreg(ctxt->gp_regs.regs.sp,	  sp_el0);
 }
 
-static void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
+static void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
+{
+	write_sysreg(ctxt->sys_regs[TPIDR_EL0],	  	tpidr_el0);
+	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], 	tpidrro_el0);
+}
+
+static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
 	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
 	write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	sctlr);
+	write_sysreg(ctxt->sys_regs[ACTLR_EL1],	  	actlr_el1);
 	write_sysreg_el1(ctxt->sys_regs[CPACR_EL1],	cpacr);
 	write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1],	ttbr0);
 	write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1],	ttbr1);
@@ -120,6 +147,11 @@ static void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
 	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
 	write_sysreg_el1(ctxt->gp_regs.elr_el1,		elr);
 	write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],spsr);
+}
+
+static void __hyp_text
+__sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
+{
 	write_sysreg_el2(ctxt->gp_regs.regs.pc,		elr);
 	write_sysreg_el2(ctxt->gp_regs.regs.pstate,	spsr);
 
@@ -127,27 +159,30 @@ static void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
 		write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
 }
 
-static hyp_alternate_select(__sysreg_call_restore_host_state,
-			    __sysreg_restore_state, __sysreg_do_nothing,
-			    ARM64_HAS_VIRT_HOST_EXTN);
+void __hyp_text __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_restore_el1_state(ctxt);
+	__sysreg_restore_common_state(ctxt);
+	__sysreg_restore_user_state(ctxt);
+	__sysreg_restore_el2_return_state(ctxt);
+}
 
-void __hyp_text __sysreg_restore_host_state(struct kvm_cpu_context *ctxt)
+void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt)
 {
-	__sysreg_call_restore_host_state()(ctxt);
 	__sysreg_restore_common_state(ctxt);
 }
 
-void __hyp_text __sysreg_restore_guest_state(struct kvm_cpu_context *ctxt)
+void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt)
 {
-	__sysreg_restore_state(ctxt);
 	__sysreg_restore_common_state(ctxt);
+	__sysreg_restore_el2_return_state(ctxt);
 }
 
 void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
 {
 	u64 *spsr, *sysreg;
 
-	if (read_sysreg(hcr_el2) & HCR_RW)
+	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
 	spsr = vcpu->arch.ctxt.gp_regs.spsr;
@@ -161,10 +196,7 @@ void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
 	sysreg[DACR32_EL2] = read_sysreg(dacr32_el2);
 	sysreg[IFSR32_EL2] = read_sysreg(ifsr32_el2);
 
-	if (__fpsimd_enabled())
-		sysreg[FPEXC32_EL2] = read_sysreg(fpexc32_el2);
-
-	if (vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY)
+	if (has_vhe() || vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY)
 		sysreg[DBGVCR32_EL2] = read_sysreg(dbgvcr32_el2);
 }
 
@@ -172,7 +204,7 @@ void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu)
 {
 	u64 *spsr, *sysreg;
 
-	if (read_sysreg(hcr_el2) & HCR_RW)
+	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
 	spsr = vcpu->arch.ctxt.gp_regs.spsr;
@@ -186,6 +218,78 @@ void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu)
 	write_sysreg(sysreg[DACR32_EL2], dacr32_el2);
 	write_sysreg(sysreg[IFSR32_EL2], ifsr32_el2);
 
-	if (vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY)
+	if (has_vhe() || vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY)
 		write_sysreg(sysreg[DBGVCR32_EL2], dbgvcr32_el2);
 }
+
+/**
+ * kvm_vcpu_load_sysregs - Load guest system registers to the physical CPU
+ *
+ * @vcpu: The VCPU pointer
+ *
+ * Load system registers that do not affect the host's execution, for
+ * example EL1 system registers on a VHE system where the host kernel
+ * runs at EL2.  This function is called from KVM's vcpu_load() function
+ * and loading system register state early avoids having to load them on
+ * every entry to the VM.
+ */
+void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt = vcpu->arch.host_cpu_context;
+	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
+
+	if (!has_vhe())
+		return;
+
+	__sysreg_save_user_state(host_ctxt);
+
+	/*
+	 * Load guest EL1 and user state
+	 *
+	 * We must restore the 32-bit state before the sysregs, thanks
+	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
+	 */
+	__sysreg32_restore_state(vcpu);
+	__sysreg_restore_user_state(guest_ctxt);
+	__sysreg_restore_el1_state(guest_ctxt);
+
+	vcpu->arch.sysregs_loaded_on_cpu = true;
+
+	activate_traps_vhe_load(vcpu);
+}
+
+/**
+ * kvm_vcpu_put_sysregs - Restore host system registers to the physical CPU
+ *
+ * @vcpu: The VCPU pointer
+ *
+ * Save guest system registers that do not affect the host's execution, for
+ * example EL1 system registers on a VHE system where the host kernel
+ * runs at EL2.  This function is called from KVM's vcpu_put() function
+ * and deferring saving system register state until we're no longer running the
+ * VCPU avoids having to save them on every exit from the VM.
+ */
+void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt = vcpu->arch.host_cpu_context;
+	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
+
+	if (!has_vhe())
+		return;
+
+	deactivate_traps_vhe_put();
+
+	__sysreg_save_el1_state(guest_ctxt);
+	__sysreg_save_user_state(guest_ctxt);
+	__sysreg32_save_state(vcpu);
+
+	/* Restore host user state */
+	__sysreg_restore_user_state(host_ctxt);
+
+	vcpu->arch.sysregs_loaded_on_cpu = false;
+}
+
+void __hyp_text __kvm_set_tpidr_el2(u64 tpidr_el2)
+{
+	asm("msr tpidr_el2, %0": : "r" (tpidr_el2));
+}

arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c

@@ -0,0 +1,78 @@
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/compiler.h>
+#include <linux/irqchip/arm-gic.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+
+/*
+ * __vgic_v2_perform_cpuif_access -- perform a GICV access on behalf of the
+ *				     guest.
+ *
+ * @vcpu: the offending vcpu
+ *
+ * Returns:
+ *  1: GICV access successfully performed
+ *  0: Not a GICV access
+ * -1: Illegal GICV access
+ */
+int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	struct vgic_dist *vgic = &kvm->arch.vgic;
+	phys_addr_t fault_ipa;
+	void __iomem *addr;
+	int rd;
+
+	/* Build the full address */
+	fault_ipa  = kvm_vcpu_get_fault_ipa(vcpu);
+	fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0);
+
+	/* If not for GICV, move on */
+	if (fault_ipa <  vgic->vgic_cpu_base ||
+	    fault_ipa >= (vgic->vgic_cpu_base + KVM_VGIC_V2_CPU_SIZE))
+		return 0;
+
+	/* Reject anything but a 32bit access */
+	if (kvm_vcpu_dabt_get_as(vcpu) != sizeof(u32))
+		return -1;
+
+	/* Not aligned? Don't bother */
+	if (fault_ipa & 3)
+		return -1;
+
+	rd = kvm_vcpu_dabt_get_rd(vcpu);
+	addr  = hyp_symbol_addr(kvm_vgic_global_state)->vcpu_hyp_va;
+	addr += fault_ipa - vgic->vgic_cpu_base;
+
+	if (kvm_vcpu_dabt_iswrite(vcpu)) {
+		u32 data = vcpu_data_guest_to_host(vcpu,
+						   vcpu_get_reg(vcpu, rd),
+						   sizeof(u32));
+		writel_relaxed(data, addr);
+	} else {
+		u32 data = readl_relaxed(addr);
+		vcpu_set_reg(vcpu, rd, vcpu_data_host_to_guest(vcpu, data,
+							       sizeof(u32)));
+	}
+
+	return 1;
+}

arch/arm64/kvm/inject_fault.c

@@ -58,7 +58,7 @@ static u64 get_except_vector(struct kvm_vcpu *vcpu, enum exception_type type)
 		exc_offset = LOWER_EL_AArch32_VECTOR;
 	}
 
-	return vcpu_sys_reg(vcpu, VBAR_EL1) + exc_offset + type;
+	return vcpu_read_sys_reg(vcpu, VBAR_EL1) + exc_offset + type;
 }
 
 static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
@@ -67,13 +67,13 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
 	bool is_aarch32 = vcpu_mode_is_32bit(vcpu);
 	u32 esr = 0;
 
-	*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
+	vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
 	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
 
 	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
-	*vcpu_spsr(vcpu) = cpsr;
+	vcpu_write_spsr(vcpu, cpsr);
 
-	vcpu_sys_reg(vcpu, FAR_EL1) = addr;
+	vcpu_write_sys_reg(vcpu, addr, FAR_EL1);
 
 	/*
 	 * Build an {i,d}abort, depending on the level and the
@@ -94,7 +94,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
 	if (!is_iabt)
 		esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT;
 
-	vcpu_sys_reg(vcpu, ESR_EL1) = esr | ESR_ELx_FSC_EXTABT;
+	vcpu_write_sys_reg(vcpu, esr | ESR_ELx_FSC_EXTABT, ESR_EL1);
 }
 
 static void inject_undef64(struct kvm_vcpu *vcpu)
@@ -102,11 +102,11 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
 	u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
 
-	*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
+	vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
 	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
 
 	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
-	*vcpu_spsr(vcpu) = cpsr;
+	vcpu_write_spsr(vcpu, cpsr);
 
 	/*
 	 * Build an unknown exception, depending on the instruction
@@ -115,7 +115,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 	if (kvm_vcpu_trap_il_is32bit(vcpu))
 		esr |= ESR_ELx_IL;
 
-	vcpu_sys_reg(vcpu, ESR_EL1) = esr;
+	vcpu_write_sys_reg(vcpu, esr, ESR_EL1);
 }
 
 /**
@@ -128,7 +128,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
  */
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr)
 {
-	if (!(vcpu->arch.hcr_el2 & HCR_RW))
+	if (vcpu_el1_is_32bit(vcpu))
 		kvm_inject_dabt32(vcpu, addr);
 	else
 		inject_abt64(vcpu, false, addr);
@@ -144,7 +144,7 @@ void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr)
  */
 void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr)
 {
-	if (!(vcpu->arch.hcr_el2 & HCR_RW))
+	if (vcpu_el1_is_32bit(vcpu))
 		kvm_inject_pabt32(vcpu, addr);
 	else
 		inject_abt64(vcpu, true, addr);
@@ -158,7 +158,7 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr)
  */
 void kvm_inject_undefined(struct kvm_vcpu *vcpu)
 {
-	if (!(vcpu->arch.hcr_el2 & HCR_RW))
+	if (vcpu_el1_is_32bit(vcpu))
 		kvm_inject_undef32(vcpu);
 	else
 		inject_undef64(vcpu);
@@ -167,7 +167,7 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu)
 static void pend_guest_serror(struct kvm_vcpu *vcpu, u64 esr)
 {
 	vcpu_set_vsesr(vcpu, esr);
-	vcpu_set_hcr(vcpu, vcpu_get_hcr(vcpu) | HCR_VSE);
+	*vcpu_hcr(vcpu) |= HCR_VSE;
 }
 
 /**

arch/arm64/kvm/regmap.c

@@ -141,28 +141,61 @@ unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num)
 /*
  * Return the SPSR for the current mode of the virtual CPU.
  */
-unsigned long *vcpu_spsr32(const struct kvm_vcpu *vcpu)
+static int vcpu_spsr32_mode(const struct kvm_vcpu *vcpu)
 {
 	unsigned long mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK;
 	switch (mode) {
-	case COMPAT_PSR_MODE_SVC:
-		mode = KVM_SPSR_SVC;
-		break;
-	case COMPAT_PSR_MODE_ABT:
-		mode = KVM_SPSR_ABT;
-		break;
-	case COMPAT_PSR_MODE_UND:
-		mode = KVM_SPSR_UND;
-		break;
-	case COMPAT_PSR_MODE_IRQ:
-		mode = KVM_SPSR_IRQ;
-		break;
-	case COMPAT_PSR_MODE_FIQ:
-		mode = KVM_SPSR_FIQ;
-		break;
+	case COMPAT_PSR_MODE_SVC: return KVM_SPSR_SVC;
+	case COMPAT_PSR_MODE_ABT: return KVM_SPSR_ABT;
+	case COMPAT_PSR_MODE_UND: return KVM_SPSR_UND;
+	case COMPAT_PSR_MODE_IRQ: return KVM_SPSR_IRQ;
+	case COMPAT_PSR_MODE_FIQ: return KVM_SPSR_FIQ;
+	default: BUG();
+	}
+}
+
+unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu)
+{
+	int spsr_idx = vcpu_spsr32_mode(vcpu);
+
+	if (!vcpu->arch.sysregs_loaded_on_cpu)
+		return vcpu_gp_regs(vcpu)->spsr[spsr_idx];
+
+	switch (spsr_idx) {
+	case KVM_SPSR_SVC:
+		return read_sysreg_el1(spsr);
+	case KVM_SPSR_ABT:
+		return read_sysreg(spsr_abt);
+	case KVM_SPSR_UND:
+		return read_sysreg(spsr_und);
+	case KVM_SPSR_IRQ:
+		return read_sysreg(spsr_irq);
+	case KVM_SPSR_FIQ:
+		return read_sysreg(spsr_fiq);
 	default:
 		BUG();
 	}
+}
+
+void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v)
+{
+	int spsr_idx = vcpu_spsr32_mode(vcpu);
+
+	if (!vcpu->arch.sysregs_loaded_on_cpu) {
+		vcpu_gp_regs(vcpu)->spsr[spsr_idx] = v;
+		return;
+	}
 
-	return (unsigned long *)&vcpu_gp_regs(vcpu)->spsr[mode];
+	switch (spsr_idx) {
+	case KVM_SPSR_SVC:
+		write_sysreg_el1(v, spsr);
+	case KVM_SPSR_ABT:
+		write_sysreg(v, spsr_abt);
+	case KVM_SPSR_UND:
+		write_sysreg(v, spsr_und);
+	case KVM_SPSR_IRQ:
+		write_sysreg(v, spsr_irq);
+	case KVM_SPSR_FIQ:
+		write_sysreg(v, spsr_fiq);
+	}
 }

arch/arm64/kvm/sys_regs.c

@@ -35,6 +35,7 @@
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_host.h>
+#include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 #include <asm/perf_event.h>
 #include <asm/sysreg.h>
@@ -76,6 +77,93 @@ static bool write_to_read_only(struct kvm_vcpu *vcpu,
 	return false;
 }
 
+u64 vcpu_read_sys_reg(struct kvm_vcpu *vcpu, int reg)
+{
+	if (!vcpu->arch.sysregs_loaded_on_cpu)
+		goto immediate_read;
+
+	/*
+	 * System registers listed in the switch are not saved on every
+	 * exit from the guest but are only saved on vcpu_put.
+	 *
+	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
+	 * should never be listed below, because the guest cannot modify its
+	 * own MPIDR_EL1 and MPIDR_EL1 is accessed for VCPU A from VCPU B's
+	 * thread when emulating cross-VCPU communication.
+	 */
+	switch (reg) {
+	case CSSELR_EL1:	return read_sysreg_s(SYS_CSSELR_EL1);
+	case SCTLR_EL1:		return read_sysreg_s(sctlr_EL12);
+	case ACTLR_EL1:		return read_sysreg_s(SYS_ACTLR_EL1);
+	case CPACR_EL1:		return read_sysreg_s(cpacr_EL12);
+	case TTBR0_EL1:		return read_sysreg_s(ttbr0_EL12);
+	case TTBR1_EL1:		return read_sysreg_s(ttbr1_EL12);
+	case TCR_EL1:		return read_sysreg_s(tcr_EL12);
+	case ESR_EL1:		return read_sysreg_s(esr_EL12);
+	case AFSR0_EL1:		return read_sysreg_s(afsr0_EL12);
+	case AFSR1_EL1:		return read_sysreg_s(afsr1_EL12);
+	case FAR_EL1:		return read_sysreg_s(far_EL12);
+	case MAIR_EL1:		return read_sysreg_s(mair_EL12);
+	case VBAR_EL1:		return read_sysreg_s(vbar_EL12);
+	case CONTEXTIDR_EL1:	return read_sysreg_s(contextidr_EL12);
+	case TPIDR_EL0:		return read_sysreg_s(SYS_TPIDR_EL0);
+	case TPIDRRO_EL0:	return read_sysreg_s(SYS_TPIDRRO_EL0);
+	case TPIDR_EL1:		return read_sysreg_s(SYS_TPIDR_EL1);
+	case AMAIR_EL1:		return read_sysreg_s(amair_EL12);
+	case CNTKCTL_EL1:	return read_sysreg_s(cntkctl_EL12);
+	case PAR_EL1:		return read_sysreg_s(SYS_PAR_EL1);
+	case DACR32_EL2:	return read_sysreg_s(SYS_DACR32_EL2);
+	case IFSR32_EL2:	return read_sysreg_s(SYS_IFSR32_EL2);
+	case DBGVCR32_EL2:	return read_sysreg_s(SYS_DBGVCR32_EL2);
+	}
+
+immediate_read:
+	return __vcpu_sys_reg(vcpu, reg);
+}
+
+void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
+{
+	if (!vcpu->arch.sysregs_loaded_on_cpu)
+		goto immediate_write;
+
+	/*
+	 * System registers listed in the switch are not restored on every
+	 * entry to the guest but are only restored on vcpu_load.
+	 *
+	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
+	 * should never be listed below, because the the MPIDR should only be
+	 * set once, before running the VCPU, and never changed later.
+	 */
+	switch (reg) {
+	case CSSELR_EL1:	write_sysreg_s(val, SYS_CSSELR_EL1);	return;
+	case SCTLR_EL1:		write_sysreg_s(val, sctlr_EL12);	return;
+	case ACTLR_EL1:		write_sysreg_s(val, SYS_ACTLR_EL1);	return;
+	case CPACR_EL1:		write_sysreg_s(val, cpacr_EL12);	return;
+	case TTBR0_EL1:		write_sysreg_s(val, ttbr0_EL12);	return;
+	case TTBR1_EL1:		write_sysreg_s(val, ttbr1_EL12);	return;
+	case TCR_EL1:		write_sysreg_s(val, tcr_EL12);		return;
+	case ESR_EL1:		write_sysreg_s(val, esr_EL12);		return;
+	case AFSR0_EL1:		write_sysreg_s(val, afsr0_EL12);	return;
+	case AFSR1_EL1:		write_sysreg_s(val, afsr1_EL12);	return;
+	case FAR_EL1:		write_sysreg_s(val, far_EL12);		return;
+	case MAIR_EL1:		write_sysreg_s(val, mair_EL12);		return;
+	case VBAR_EL1:		write_sysreg_s(val, vbar_EL12);		return;
+	case CONTEXTIDR_EL1:	write_sysreg_s(val, contextidr_EL12);	return;
+	case TPIDR_EL0:		write_sysreg_s(val, SYS_TPIDR_EL0);	return;
+	case TPIDRRO_EL0:	write_sysreg_s(val, SYS_TPIDRRO_EL0);	return;
+	case TPIDR_EL1:		write_sysreg_s(val, SYS_TPIDR_EL1);	return;
+	case AMAIR_EL1:		write_sysreg_s(val, amair_EL12);	return;
+	case CNTKCTL_EL1:	write_sysreg_s(val, cntkctl_EL12);	return;
+	case PAR_EL1:		write_sysreg_s(val, SYS_PAR_EL1);	return;
+	case DACR32_EL2:	write_sysreg_s(val, SYS_DACR32_EL2);	return;
+	case IFSR32_EL2:	write_sysreg_s(val, SYS_IFSR32_EL2);	return;
+	case DBGVCR32_EL2:	write_sysreg_s(val, SYS_DBGVCR32_EL2);	return;
+	}
+
+immediate_write:
+	 __vcpu_sys_reg(vcpu, reg) = val;
+}
+
 /* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */
 static u32 cache_levels;
 
@@ -121,16 +209,26 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
 			  const struct sys_reg_desc *r)
 {
 	bool was_enabled = vcpu_has_cache_enabled(vcpu);
+	u64 val;
+	int reg = r->reg;
 
 	BUG_ON(!p->is_write);
 
-	if (!p->is_aarch32) {
-		vcpu_sys_reg(vcpu, r->reg) = p->regval;
+	/* See the 32bit mapping in kvm_host.h */
+	if (p->is_aarch32)
+		reg = r->reg / 2;
+
+	if (!p->is_aarch32 || !p->is_32bit) {
+		val = p->regval;
 	} else {
-		if (!p->is_32bit)
-			vcpu_cp15_64_high(vcpu, r->reg) = upper_32_bits(p->regval);
-		vcpu_cp15_64_low(vcpu, r->reg) = lower_32_bits(p->regval);
+		val = vcpu_read_sys_reg(vcpu, reg);
+		if (r->reg % 2)
+			val = (p->regval << 32) | (u64)lower_32_bits(val);
+		else
+			val = ((u64)upper_32_bits(val) << 32) |
+				lower_32_bits(p->regval);
 	}
+	vcpu_write_sys_reg(vcpu, val, reg);
 
 	kvm_toggle_cache(vcpu, was_enabled);
 	return true;
@@ -175,6 +273,14 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu,
 		return read_zero(vcpu, p);
 }
 
+static bool trap_undef(struct kvm_vcpu *vcpu,
+		       struct sys_reg_params *p,
+		       const struct sys_reg_desc *r)
+{
+	kvm_inject_undefined(vcpu);
+	return false;
+}
+
 static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
 			   struct sys_reg_params *p,
 			   const struct sys_reg_desc *r)
@@ -231,10 +337,10 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu,
 			    const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
-		vcpu_sys_reg(vcpu, r->reg) = p->regval;
+		vcpu_write_sys_reg(vcpu, p->regval, r->reg);
 		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
 	} else {
-		p->regval = vcpu_sys_reg(vcpu, r->reg);
+		p->regval = vcpu_read_sys_reg(vcpu, r->reg);
 	}
 
 	trace_trap_reg(__func__, r->reg, p->is_write, p->regval);
@@ -447,7 +553,8 @@ static void reset_wcr(struct kvm_vcpu *vcpu,
 
 static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
-	vcpu_sys_reg(vcpu, AMAIR_EL1) = read_sysreg(amair_el1);
+	u64 amair = read_sysreg(amair_el1);
+	vcpu_write_sys_reg(vcpu, amair, AMAIR_EL1);
 }
 
 static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
@@ -464,7 +571,7 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	mpidr = (vcpu->vcpu_id & 0x0f) << MPIDR_LEVEL_SHIFT(0);
 	mpidr |= ((vcpu->vcpu_id >> 4) & 0xff) << MPIDR_LEVEL_SHIFT(1);
 	mpidr |= ((vcpu->vcpu_id >> 12) & 0xff) << MPIDR_LEVEL_SHIFT(2);
-	vcpu_sys_reg(vcpu, MPIDR_EL1) = (1ULL << 31) | mpidr;
+	vcpu_write_sys_reg(vcpu, (1ULL << 31) | mpidr, MPIDR_EL1);
 }
 
 static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
@@ -478,12 +585,12 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	 */
 	val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
 	       | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E);
-	vcpu_sys_reg(vcpu, PMCR_EL0) = val;
+	__vcpu_sys_reg(vcpu, PMCR_EL0) = val;
 }
 
 static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags)
 {
-	u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
+	u64 reg = __vcpu_sys_reg(vcpu, PMUSERENR_EL0);
 	bool enabled = (reg & flags) || vcpu_mode_priv(vcpu);
 
 	if (!enabled)
@@ -525,14 +632,14 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 
 	if (p->is_write) {
 		/* Only update writeable bits of PMCR */
-		val = vcpu_sys_reg(vcpu, PMCR_EL0);
+		val = __vcpu_sys_reg(vcpu, PMCR_EL0);
 		val &= ~ARMV8_PMU_PMCR_MASK;
 		val |= p->regval & ARMV8_PMU_PMCR_MASK;
-		vcpu_sys_reg(vcpu, PMCR_EL0) = val;
+		__vcpu_sys_reg(vcpu, PMCR_EL0) = val;
 		kvm_pmu_handle_pmcr(vcpu, val);
 	} else {
 		/* PMCR.P & PMCR.C are RAZ */
-		val = vcpu_sys_reg(vcpu, PMCR_EL0)
+		val = __vcpu_sys_reg(vcpu, PMCR_EL0)
 		      & ~(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C);
 		p->regval = val;
 	}
@@ -550,10 +657,10 @@ static bool access_pmselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		return false;
 
 	if (p->is_write)
-		vcpu_sys_reg(vcpu, PMSELR_EL0) = p->regval;
+		__vcpu_sys_reg(vcpu, PMSELR_EL0) = p->regval;
 	else
 		/* return PMSELR.SEL field */
-		p->regval = vcpu_sys_reg(vcpu, PMSELR_EL0)
+		p->regval = __vcpu_sys_reg(vcpu, PMSELR_EL0)
 			    & ARMV8_PMU_COUNTER_MASK;
 
 	return true;
@@ -586,7 +693,7 @@ static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx)
 {
 	u64 pmcr, val;
 
-	pmcr = vcpu_sys_reg(vcpu, PMCR_EL0);
+	pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0);
 	val = (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
 	if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX) {
 		kvm_inject_undefined(vcpu);
@@ -611,7 +718,7 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
 			if (pmu_access_event_counter_el0_disabled(vcpu))
 				return false;
 
-			idx = vcpu_sys_reg(vcpu, PMSELR_EL0)
+			idx = __vcpu_sys_reg(vcpu, PMSELR_EL0)
 			      & ARMV8_PMU_COUNTER_MASK;
 		} else if (r->Op2 == 0) {
 			/* PMCCNTR_EL0 */
@@ -666,7 +773,7 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 
 	if (r->CRn == 9 && r->CRm == 13 && r->Op2 == 1) {
 		/* PMXEVTYPER_EL0 */
-		idx = vcpu_sys_reg(vcpu, PMSELR_EL0) & ARMV8_PMU_COUNTER_MASK;
+		idx = __vcpu_sys_reg(vcpu, PMSELR_EL0) & ARMV8_PMU_COUNTER_MASK;
 		reg = PMEVTYPER0_EL0 + idx;
 	} else if (r->CRn == 14 && (r->CRm & 12) == 12) {
 		idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);
@@ -684,9 +791,9 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 
 	if (p->is_write) {
 		kvm_pmu_set_counter_event_type(vcpu, p->regval, idx);
-		vcpu_sys_reg(vcpu, reg) = p->regval & ARMV8_PMU_EVTYPE_MASK;
+		__vcpu_sys_reg(vcpu, reg) = p->regval & ARMV8_PMU_EVTYPE_MASK;
 	} else {
-		p->regval = vcpu_sys_reg(vcpu, reg) & ARMV8_PMU_EVTYPE_MASK;
+		p->regval = __vcpu_sys_reg(vcpu, reg) & ARMV8_PMU_EVTYPE_MASK;
 	}
 
 	return true;
@@ -708,15 +815,15 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		val = p->regval & mask;
 		if (r->Op2 & 0x1) {
 			/* accessing PMCNTENSET_EL0 */
-			vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val;
+			__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val;
 			kvm_pmu_enable_counter(vcpu, val);
 		} else {
 			/* accessing PMCNTENCLR_EL0 */
-			vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val;
+			__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val;
 			kvm_pmu_disable_counter(vcpu, val);
 		}
 	} else {
-		p->regval = vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask;
+		p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask;
 	}
 
 	return true;
@@ -740,12 +847,12 @@ static bool access_pminten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 
 		if (r->Op2 & 0x1)
 			/* accessing PMINTENSET_EL1 */
-			vcpu_sys_reg(vcpu, PMINTENSET_EL1) |= val;
+			__vcpu_sys_reg(vcpu, PMINTENSET_EL1) |= val;
 		else
 			/* accessing PMINTENCLR_EL1 */
-			vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= ~val;
+			__vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= ~val;
 	} else {
-		p->regval = vcpu_sys_reg(vcpu, PMINTENSET_EL1) & mask;
+		p->regval = __vcpu_sys_reg(vcpu, PMINTENSET_EL1) & mask;
 	}
 
 	return true;
@@ -765,12 +872,12 @@ static bool access_pmovs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	if (p->is_write) {
 		if (r->CRm & 0x2)
 			/* accessing PMOVSSET_EL0 */
-			vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= (p->regval & mask);
+			__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= (p->regval & mask);
 		else
 			/* accessing PMOVSCLR_EL0 */
-			vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= ~(p->regval & mask);
+			__vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= ~(p->regval & mask);
 	} else {
-		p->regval = vcpu_sys_reg(vcpu, PMOVSSET_EL0) & mask;
+		p->regval = __vcpu_sys_reg(vcpu, PMOVSSET_EL0) & mask;
 	}
 
 	return true;
@@ -807,10 +914,10 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			return false;
 		}
 
-		vcpu_sys_reg(vcpu, PMUSERENR_EL0) = p->regval
-						    & ARMV8_PMU_USERENR_MASK;
+		__vcpu_sys_reg(vcpu, PMUSERENR_EL0) =
+			       p->regval & ARMV8_PMU_USERENR_MASK;
 	} else {
-		p->regval = vcpu_sys_reg(vcpu, PMUSERENR_EL0)
+		p->regval = __vcpu_sys_reg(vcpu, PMUSERENR_EL0)
 			    & ARMV8_PMU_USERENR_MASK;
 	}
 
@@ -893,6 +1000,12 @@ static u64 read_id_reg(struct sys_reg_desc const *r, bool raz)
 				    task_pid_nr(current));
 
 		val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
+	} else if (id == SYS_ID_AA64MMFR1_EL1) {
+		if (val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))
+			pr_err_once("kvm [%i]: LORegions unsupported for guests, suppressing\n",
+				    task_pid_nr(current));
+
+		val &= ~(0xfUL << ID_AA64MMFR1_LOR_SHIFT);
 	}
 
 	return val;
@@ -1178,6 +1291,12 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 },
 	{ SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
 
+	{ SYS_DESC(SYS_LORSA_EL1), trap_undef },
+	{ SYS_DESC(SYS_LOREA_EL1), trap_undef },
+	{ SYS_DESC(SYS_LORN_EL1), trap_undef },
+	{ SYS_DESC(SYS_LORC_EL1), trap_undef },
+	{ SYS_DESC(SYS_LORID_EL1), trap_undef },
+
 	{ SYS_DESC(SYS_VBAR_EL1), NULL, reset_val, VBAR_EL1, 0 },
 	{ SYS_DESC(SYS_DISR_EL1), NULL, reset_val, DISR_EL1, 0 },
 
@@ -1545,6 +1664,11 @@ static const struct sys_reg_desc cp15_regs[] = {
 
 	{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
 
+	/* CNTP_TVAL */
+	{ Op1( 0), CRn(14), CRm( 2), Op2( 0), access_cntp_tval },
+	/* CNTP_CTL */
+	{ Op1( 0), CRn(14), CRm( 2), Op2( 1), access_cntp_ctl },
+
 	/* PMEVCNTRn */
 	PMU_PMEVCNTR(0),
 	PMU_PMEVCNTR(1),
@@ -1618,6 +1742,7 @@ static const struct sys_reg_desc cp15_64_regs[] = {
 	{ Op1( 0), CRn( 0), CRm( 9), Op2( 0), access_pmu_evcntr },
 	{ Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi },
 	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
+	{ Op1( 2), CRn( 0), CRm(14), Op2( 0), access_cntp_cval },
 };
 
 /* Target specific emulation tables */
@@ -2194,7 +2319,7 @@ int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg
 	if (r->get_user)
 		return (r->get_user)(vcpu, r, reg, uaddr);
 
-	return reg_to_user(uaddr, &vcpu_sys_reg(vcpu, r->reg), reg->id);
+	return reg_to_user(uaddr, &__vcpu_sys_reg(vcpu, r->reg), reg->id);
 }
 
 int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
@@ -2215,7 +2340,7 @@ int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg
 	if (r->set_user)
 		return (r->set_user)(vcpu, r, reg, uaddr);
 
-	return reg_from_user(&vcpu_sys_reg(vcpu, r->reg), uaddr, reg->id);
+	return reg_from_user(&__vcpu_sys_reg(vcpu, r->reg), uaddr, reg->id);
 }
 
 static unsigned int num_demux_regs(void)
@@ -2421,6 +2546,6 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
 	reset_sys_reg_descs(vcpu, table, num);
 
 	for (num = 1; num < NR_SYS_REGS; num++)
-		if (vcpu_sys_reg(vcpu, num) == 0x4242424242424242)
-			panic("Didn't reset vcpu_sys_reg(%zi)", num);
+		if (__vcpu_sys_reg(vcpu, num) == 0x4242424242424242)
+			panic("Didn't reset __vcpu_sys_reg(%zi)", num);
 }

arch/arm64/kvm/sys_regs.h

@@ -89,14 +89,14 @@ static inline void reset_unknown(struct kvm_vcpu *vcpu,
 {
 	BUG_ON(!r->reg);
 	BUG_ON(r->reg >= NR_SYS_REGS);
-	vcpu_sys_reg(vcpu, r->reg) = 0x1de7ec7edbadc0deULL;
+	__vcpu_sys_reg(vcpu, r->reg) = 0x1de7ec7edbadc0deULL;
 }
 
 static inline void reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	BUG_ON(!r->reg);
 	BUG_ON(r->reg >= NR_SYS_REGS);
-	vcpu_sys_reg(vcpu, r->reg) = r->val;
+	__vcpu_sys_reg(vcpu, r->reg) = r->val;
 }
 
 static inline int cmp_sys_reg(const struct sys_reg_desc *i1,

arch/arm64/kvm/sys_regs_generic_v8.c

@@ -38,13 +38,13 @@ static bool access_actlr(struct kvm_vcpu *vcpu,
 	if (p->is_write)
 		return ignore_write(vcpu, p);
 
-	p->regval = vcpu_sys_reg(vcpu, ACTLR_EL1);
+	p->regval = vcpu_read_sys_reg(vcpu, ACTLR_EL1);
 	return true;
 }
 
 static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
-	vcpu_sys_reg(vcpu, ACTLR_EL1) = read_sysreg(actlr_el1);
+	__vcpu_sys_reg(vcpu, ACTLR_EL1) = read_sysreg(actlr_el1);
 }
 
 /*

arch/arm64/kvm/va_layout.c

@@ -0,0 +1,227 @@
+/*
+ * Copyright (C) 2017 ARM Ltd.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/random.h>
+#include <linux/memblock.h>
+#include <asm/alternative.h>
+#include <asm/debug-monitors.h>
+#include <asm/insn.h>
+#include <asm/kvm_mmu.h>
+
+/*
+ * The LSB of the random hyp VA tag or 0 if no randomization is used.
+ */
+static u8 tag_lsb;
+/*
+ * The random hyp VA tag value with the region bit if hyp randomization is used
+ */
+static u64 tag_val;
+static u64 va_mask;
+
+static void compute_layout(void)
+{
+	phys_addr_t idmap_addr = __pa_symbol(__hyp_idmap_text_start);
+	u64 hyp_va_msb;
+	int kva_msb;
+
+	/* Where is my RAM region? */
+	hyp_va_msb  = idmap_addr & BIT(VA_BITS - 1);
+	hyp_va_msb ^= BIT(VA_BITS - 1);
+
+	kva_msb = fls64((u64)phys_to_virt(memblock_start_of_DRAM()) ^
+			(u64)(high_memory - 1));
+
+	if (kva_msb == (VA_BITS - 1)) {
+		/*
+		 * No space in the address, let's compute the mask so
+		 * that it covers (VA_BITS - 1) bits, and the region
+		 * bit. The tag stays set to zero.
+		 */
+		va_mask  = BIT(VA_BITS - 1) - 1;
+		va_mask |= hyp_va_msb;
+	} else {
+		/*
+		 * We do have some free bits to insert a random tag.
+		 * Hyp VAs are now created from kernel linear map VAs
+		 * using the following formula (with V == VA_BITS):
+		 *
+		 *  63 ... V |     V-1    | V-2 .. tag_lsb | tag_lsb - 1 .. 0
+		 *  ---------------------------------------------------------
+		 * | 0000000 | hyp_va_msb |    random tag  |  kern linear VA |
+		 */
+		tag_lsb = kva_msb;
+		va_mask = GENMASK_ULL(tag_lsb - 1, 0);
+		tag_val = get_random_long() & GENMASK_ULL(VA_BITS - 2, tag_lsb);
+		tag_val |= hyp_va_msb;
+		tag_val >>= tag_lsb;
+	}
+}
+
+static u32 compute_instruction(int n, u32 rd, u32 rn)
+{
+	u32 insn = AARCH64_BREAK_FAULT;
+
+	switch (n) {
+	case 0:
+		insn = aarch64_insn_gen_logical_immediate(AARCH64_INSN_LOGIC_AND,
+							  AARCH64_INSN_VARIANT_64BIT,
+							  rn, rd, va_mask);
+		break;
+
+	case 1:
+		/* ROR is a variant of EXTR with Rm = Rn */
+		insn = aarch64_insn_gen_extr(AARCH64_INSN_VARIANT_64BIT,
+					     rn, rn, rd,
+					     tag_lsb);
+		break;
+
+	case 2:
+		insn = aarch64_insn_gen_add_sub_imm(rd, rn,
+						    tag_val & GENMASK(11, 0),
+						    AARCH64_INSN_VARIANT_64BIT,
+						    AARCH64_INSN_ADSB_ADD);
+		break;
+
+	case 3:
+		insn = aarch64_insn_gen_add_sub_imm(rd, rn,
+						    tag_val & GENMASK(23, 12),
+						    AARCH64_INSN_VARIANT_64BIT,
+						    AARCH64_INSN_ADSB_ADD);
+		break;
+
+	case 4:
+		/* ROR is a variant of EXTR with Rm = Rn */
+		insn = aarch64_insn_gen_extr(AARCH64_INSN_VARIANT_64BIT,
+					     rn, rn, rd, 64 - tag_lsb);
+		break;
+	}
+
+	return insn;
+}
+
+void __init kvm_update_va_mask(struct alt_instr *alt,
+			       __le32 *origptr, __le32 *updptr, int nr_inst)
+{
+	int i;
+
+	BUG_ON(nr_inst != 5);
+
+	if (!has_vhe() && !va_mask)
+		compute_layout();
+
+	for (i = 0; i < nr_inst; i++) {
+		u32 rd, rn, insn, oinsn;
+
+		/*
+		 * VHE doesn't need any address translation, let's NOP
+		 * everything.
+		 *
+		 * Alternatively, if we don't have any spare bits in
+		 * the address, NOP everything after masking that
+		 * kernel VA.
+		 */
+		if (has_vhe() || (!tag_lsb && i > 0)) {
+			updptr[i] = cpu_to_le32(aarch64_insn_gen_nop());
+			continue;
+		}
+
+		oinsn = le32_to_cpu(origptr[i]);
+		rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, oinsn);
+		rn = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RN, oinsn);
+
+		insn = compute_instruction(i, rd, rn);
+		BUG_ON(insn == AARCH64_BREAK_FAULT);
+
+		updptr[i] = cpu_to_le32(insn);
+	}
+}
+
+void *__kvm_bp_vect_base;
+int __kvm_harden_el2_vector_slot;
+
+void kvm_patch_vector_branch(struct alt_instr *alt,
+			     __le32 *origptr, __le32 *updptr, int nr_inst)
+{
+	u64 addr;
+	u32 insn;
+
+	BUG_ON(nr_inst != 5);
+
+	if (has_vhe() || !cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)) {
+		WARN_ON_ONCE(cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS));
+		return;
+	}
+
+	if (!va_mask)
+		compute_layout();
+
+	/*
+	 * Compute HYP VA by using the same computation as kern_hyp_va()
+	 */
+	addr = (uintptr_t)kvm_ksym_ref(__kvm_hyp_vector);
+	addr &= va_mask;
+	addr |= tag_val << tag_lsb;
+
+	/* Use PC[10:7] to branch to the same vector in KVM */
+	addr |= ((u64)origptr & GENMASK_ULL(10, 7));
+
+	/*
+	 * Branch to the second instruction in the vectors in order to
+	 * avoid the initial store on the stack (which we already
+	 * perform in the hardening vectors).
+	 */
+	addr += AARCH64_INSN_SIZE;
+
+	/* stp x0, x1, [sp, #-16]! */
+	insn = aarch64_insn_gen_load_store_pair(AARCH64_INSN_REG_0,
+						AARCH64_INSN_REG_1,
+						AARCH64_INSN_REG_SP,
+						-16,
+						AARCH64_INSN_VARIANT_64BIT,
+						AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX);
+	*updptr++ = cpu_to_le32(insn);
+
+	/* movz x0, #(addr & 0xffff) */
+	insn = aarch64_insn_gen_movewide(AARCH64_INSN_REG_0,
+					 (u16)addr,
+					 0,
+					 AARCH64_INSN_VARIANT_64BIT,
+					 AARCH64_INSN_MOVEWIDE_ZERO);
+	*updptr++ = cpu_to_le32(insn);
+
+	/* movk x0, #((addr >> 16) & 0xffff), lsl #16 */
+	insn = aarch64_insn_gen_movewide(AARCH64_INSN_REG_0,
+					 (u16)(addr >> 16),
+					 16,
+					 AARCH64_INSN_VARIANT_64BIT,
+					 AARCH64_INSN_MOVEWIDE_KEEP);
+	*updptr++ = cpu_to_le32(insn);
+
+	/* movk x0, #((addr >> 32) & 0xffff), lsl #32 */
+	insn = aarch64_insn_gen_movewide(AARCH64_INSN_REG_0,
+					 (u16)(addr >> 32),
+					 32,
+					 AARCH64_INSN_VARIANT_64BIT,
+					 AARCH64_INSN_MOVEWIDE_KEEP);
+	*updptr++ = cpu_to_le32(insn);
+
+	/* br x0 */
+	insn = aarch64_insn_gen_branch_reg(AARCH64_INSN_REG_0,
+					   AARCH64_INSN_BRANCH_NOLINK);
+	*updptr++ = cpu_to_le32(insn);
+}

arch/mips/include/asm/kvm_para.h

@@ -94,6 +94,11 @@ static inline unsigned int kvm_arch_para_features(void)
 	return 0;
 }
 
+static inline unsigned int kvm_arch_para_hints(void)
+{
+	return 0;
+}
+
 #ifdef CONFIG_MIPS_PARAVIRT
 static inline bool kvm_para_available(void)
 {

arch/powerpc/include/asm/kvm_host.h

@@ -60,7 +60,6 @@
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 
-extern int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 extern int kvm_unmap_hva_range(struct kvm *kvm,
 			       unsigned long start, unsigned long end);
 extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);

arch/powerpc/include/asm/kvm_para.h

@@ -61,6 +61,11 @@ static inline unsigned int kvm_arch_para_features(void)
 	return r;
 }
 
+static inline unsigned int kvm_arch_para_hints(void)
+{
+	return 0;
+}
+
 static inline bool kvm_check_and_clear_guest_paused(void)
 {
 	return false;

arch/powerpc/include/asm/kvm_ppc.h

@@ -295,7 +295,6 @@ struct kvmppc_ops {
 				     const struct kvm_userspace_memory_region *mem,
 				     const struct kvm_memory_slot *old,
 				     const struct kvm_memory_slot *new);
-	int (*unmap_hva)(struct kvm *kvm, unsigned long hva);
 	int (*unmap_hva_range)(struct kvm *kvm, unsigned long start,
 			   unsigned long end);
 	int (*age_hva)(struct kvm *kvm, unsigned long start, unsigned long end);

arch/powerpc/kvm/book3s.c

@@ -819,12 +819,6 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
 	kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new);
 }
 
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
-{
-	return kvm->arch.kvm_ops->unmap_hva(kvm, hva);
-}
-EXPORT_SYMBOL_GPL(kvm_unmap_hva);
-
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
 {
 	return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end);

arch/powerpc/kvm/book3s.h

@@ -14,7 +14,6 @@
 
 extern void kvmppc_core_flush_memslot_hv(struct kvm *kvm,
 					 struct kvm_memory_slot *memslot);
-extern int kvm_unmap_hva_hv(struct kvm *kvm, unsigned long hva);
 extern int kvm_unmap_hva_range_hv(struct kvm *kvm, unsigned long start,
 				  unsigned long end);
 extern int kvm_age_hva_hv(struct kvm *kvm, unsigned long start,

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -877,15 +877,6 @@ static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	return 0;
 }
 
-int kvm_unmap_hva_hv(struct kvm *kvm, unsigned long hva)
-{
-	hva_handler_fn handler;
-
-	handler = kvm_is_radix(kvm) ? kvm_unmap_radix : kvm_unmap_rmapp;
-	kvm_handle_hva(kvm, hva, handler);
-	return 0;
-}
-
 int kvm_unmap_hva_range_hv(struct kvm *kvm, unsigned long start, unsigned long end)
 {
 	hva_handler_fn handler;

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -150,7 +150,9 @@ static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
 {
 	int psize = MMU_BASE_PSIZE;
 
-	if (pshift >= PMD_SHIFT)
+	if (pshift >= PUD_SHIFT)
+		psize = MMU_PAGE_1G;
+	else if (pshift >= PMD_SHIFT)
 		psize = MMU_PAGE_2M;
 	addr &= ~0xfffUL;
 	addr |= mmu_psize_defs[psize].ap << 5;
@@ -163,6 +165,17 @@ static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
 	asm volatile("ptesync": : :"memory");
 }
 
+static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned long addr)
+{
+	unsigned long rb = 0x2 << PPC_BITLSHIFT(53); /* IS = 2 */
+
+	asm volatile("ptesync": : :"memory");
+	/* RIC=1 PRS=0 R=1 IS=2 */
+	asm volatile(PPC_TLBIE_5(%0, %1, 1, 0, 1)
+		     : : "r" (rb), "r" (kvm->arch.lpid) : "memory");
+	asm volatile("ptesync": : :"memory");
+}
+
 unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep,
 				      unsigned long clr, unsigned long set,
 				      unsigned long addr, unsigned int shift)
@@ -223,9 +236,9 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 		new_pud = pud_alloc_one(kvm->mm, gpa);
 
 	pmd = NULL;
-	if (pud && pud_present(*pud))
+	if (pud && pud_present(*pud) && !pud_huge(*pud))
 		pmd = pmd_offset(pud, gpa);
-	else
+	else if (level <= 1)
 		new_pmd = pmd_alloc_one(kvm->mm, gpa);
 
 	if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_is_leaf(*pmd)))
@@ -246,6 +259,50 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 		new_pud = NULL;
 	}
 	pud = pud_offset(pgd, gpa);
+	if (pud_huge(*pud)) {
+		unsigned long hgpa = gpa & PUD_MASK;
+
+		/*
+		 * If we raced with another CPU which has just put
+		 * a 1GB pte in after we saw a pmd page, try again.
+		 */
+		if (level <= 1 && !new_pmd) {
+			ret = -EAGAIN;
+			goto out_unlock;
+		}
+		/* Check if we raced and someone else has set the same thing */
+		if (level == 2 && pud_raw(*pud) == pte_raw(pte)) {
+			ret = 0;
+			goto out_unlock;
+		}
+		/* Valid 1GB page here already, remove it */
+		old = kvmppc_radix_update_pte(kvm, (pte_t *)pud,
+					      ~0UL, 0, hgpa, PUD_SHIFT);
+		kvmppc_radix_tlbie_page(kvm, hgpa, PUD_SHIFT);
+		if (old & _PAGE_DIRTY) {
+			unsigned long gfn = hgpa >> PAGE_SHIFT;
+			struct kvm_memory_slot *memslot;
+			memslot = gfn_to_memslot(kvm, gfn);
+			if (memslot && memslot->dirty_bitmap)
+				kvmppc_update_dirty_map(memslot,
+							gfn, PUD_SIZE);
+		}
+	}
+	if (level == 2) {
+		if (!pud_none(*pud)) {
+			/*
+			 * There's a page table page here, but we wanted to
+			 * install a large page, so remove and free the page
+			 * table page.  new_pmd will be NULL since level == 2.
+			 */
+			new_pmd = pmd_offset(pud, 0);
+			pud_clear(pud);
+			kvmppc_radix_flush_pwc(kvm, gpa);
+		}
+		kvmppc_radix_set_pte_at(kvm, gpa, (pte_t *)pud, pte);
+		ret = 0;
+		goto out_unlock;
+	}
 	if (pud_none(*pud)) {
 		if (!new_pmd)
 			goto out_unlock;
@@ -264,6 +321,11 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 			ret = -EAGAIN;
 			goto out_unlock;
 		}
+		/* Check if we raced and someone else has set the same thing */
+		if (level == 1 && pmd_raw(*pmd) == pte_raw(pte)) {
+			ret = 0;
+			goto out_unlock;
+		}
 		/* Valid 2MB page here already, remove it */
 		old = kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd),
 					      ~0UL, 0, lgpa, PMD_SHIFT);
@@ -276,35 +338,43 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 				kvmppc_update_dirty_map(memslot,
 							gfn, PMD_SIZE);
 		}
-	} else if (level == 1 && !pmd_none(*pmd)) {
-		/*
-		 * There's a page table page here, but we wanted
-		 * to install a large page.  Tell the caller and let
-		 * it try installing a normal page if it wants.
-		 */
-		ret = -EBUSY;
-		goto out_unlock;
 	}
-	if (level == 0) {
-		if (pmd_none(*pmd)) {
-			if (!new_ptep)
-				goto out_unlock;
-			pmd_populate(kvm->mm, pmd, new_ptep);
-			new_ptep = NULL;
-		}
-		ptep = pte_offset_kernel(pmd, gpa);
-		if (pte_present(*ptep)) {
-			/* PTE was previously valid, so invalidate it */
-			old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT,
-						      0, gpa, 0);
-			kvmppc_radix_tlbie_page(kvm, gpa, 0);
-			if (old & _PAGE_DIRTY)
-				mark_page_dirty(kvm, gpa >> PAGE_SHIFT);
+	if (level == 1) {
+		if (!pmd_none(*pmd)) {
+			/*
+			 * There's a page table page here, but we wanted to
+			 * install a large page, so remove and free the page
+			 * table page.  new_ptep will be NULL since level == 1.
+			 */
+			new_ptep = pte_offset_kernel(pmd, 0);
+			pmd_clear(pmd);
+			kvmppc_radix_flush_pwc(kvm, gpa);
 		}
-		kvmppc_radix_set_pte_at(kvm, gpa, ptep, pte);
-	} else {
 		kvmppc_radix_set_pte_at(kvm, gpa, pmdp_ptep(pmd), pte);
+		ret = 0;
+		goto out_unlock;
 	}
+	if (pmd_none(*pmd)) {
+		if (!new_ptep)
+			goto out_unlock;
+		pmd_populate(kvm->mm, pmd, new_ptep);
+		new_ptep = NULL;
+	}
+	ptep = pte_offset_kernel(pmd, gpa);
+	if (pte_present(*ptep)) {
+		/* Check if someone else set the same thing */
+		if (pte_raw(*ptep) == pte_raw(pte)) {
+			ret = 0;
+			goto out_unlock;
+		}
+		/* PTE was previously valid, so invalidate it */
+		old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT,
+					      0, gpa, 0);
+		kvmppc_radix_tlbie_page(kvm, gpa, 0);
+		if (old & _PAGE_DIRTY)
+			mark_page_dirty(kvm, gpa >> PAGE_SHIFT);
+	}
+	kvmppc_radix_set_pte_at(kvm, gpa, ptep, pte);
 	ret = 0;
 
  out_unlock:
@@ -325,11 +395,11 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	unsigned long mmu_seq, pte_size;
 	unsigned long gpa, gfn, hva, pfn;
 	struct kvm_memory_slot *memslot;
-	struct page *page = NULL, *pages[1];
-	long ret, npages, ok;
-	unsigned int writing;
-	struct vm_area_struct *vma;
-	unsigned long flags;
+	struct page *page = NULL;
+	long ret;
+	bool writing;
+	bool upgrade_write = false;
+	bool *upgrade_p = &upgrade_write;
 	pte_t pte, *ptep;
 	unsigned long pgflags;
 	unsigned int shift, level;
@@ -369,122 +439,131 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 					      dsisr & DSISR_ISSTORE);
 	}
 
-	/* used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
-	smp_rmb();
-
 	writing = (dsisr & DSISR_ISSTORE) != 0;
-	hva = gfn_to_hva_memslot(memslot, gfn);
+	if (memslot->flags & KVM_MEM_READONLY) {
+		if (writing) {
+			/* give the guest a DSI */
+			dsisr = DSISR_ISSTORE | DSISR_PROTFAULT;
+			kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
+			return RESUME_GUEST;
+		}
+		upgrade_p = NULL;
+	}
+
 	if (dsisr & DSISR_SET_RC) {
 		/*
 		 * Need to set an R or C bit in the 2nd-level tables;
-		 * if the relevant bits aren't already set in the linux
-		 * page tables, fall through to do the gup_fast to
-		 * set them in the linux page tables too.
+		 * since we are just helping out the hardware here,
+		 * it is sufficient to do what the hardware does.
 		 */
-		ok = 0;
 		pgflags = _PAGE_ACCESSED;
 		if (writing)
 			pgflags |= _PAGE_DIRTY;
-		local_irq_save(flags);
-		ptep = find_current_mm_pte(current->mm->pgd, hva, NULL, NULL);
-		if (ptep) {
-			pte = READ_ONCE(*ptep);
-			if (pte_present(pte) &&
-			    (pte_val(pte) & pgflags) == pgflags)
-				ok = 1;
-		}
-		local_irq_restore(flags);
-		if (ok) {
-			spin_lock(&kvm->mmu_lock);
-			if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) {
-				spin_unlock(&kvm->mmu_lock);
-				return RESUME_GUEST;
-			}
-			/*
-			 * We are walking the secondary page table here. We can do this
-			 * without disabling irq.
-			 */
-			ptep = __find_linux_pte(kvm->arch.pgtable,
-						gpa, NULL, &shift);
-			if (ptep && pte_present(*ptep)) {
-				kvmppc_radix_update_pte(kvm, ptep, 0, pgflags,
-							gpa, shift);
-				spin_unlock(&kvm->mmu_lock);
-				return RESUME_GUEST;
-			}
-			spin_unlock(&kvm->mmu_lock);
+		/*
+		 * We are walking the secondary page table here. We can do this
+		 * without disabling irq.
+		 */
+		spin_lock(&kvm->mmu_lock);
+		ptep = __find_linux_pte(kvm->arch.pgtable,
+					gpa, NULL, &shift);
+		if (ptep && pte_present(*ptep) &&
+		    (!writing || pte_write(*ptep))) {
+			kvmppc_radix_update_pte(kvm, ptep, 0, pgflags,
+						gpa, shift);
+			dsisr &= ~DSISR_SET_RC;
 		}
+		spin_unlock(&kvm->mmu_lock);
+		if (!(dsisr & (DSISR_BAD_FAULT_64S | DSISR_NOHPTE |
+			       DSISR_PROTFAULT | DSISR_SET_RC)))
+			return RESUME_GUEST;
 	}
 
-	ret = -EFAULT;
-	pfn = 0;
-	pte_size = PAGE_SIZE;
-	pgflags = _PAGE_READ | _PAGE_EXEC;
-	level = 0;
-	npages = get_user_pages_fast(hva, 1, writing, pages);
-	if (npages < 1) {
-		/* Check if it's an I/O mapping */
-		down_read(&current->mm->mmap_sem);
-		vma = find_vma(current->mm, hva);
-		if (vma && vma->vm_start <= hva && hva < vma->vm_end &&
-		    (vma->vm_flags & VM_PFNMAP)) {
-			pfn = vma->vm_pgoff +
-				((hva - vma->vm_start) >> PAGE_SHIFT);
-			pgflags = pgprot_val(vma->vm_page_prot);
-		}
-		up_read(&current->mm->mmap_sem);
-		if (!pfn)
-			return -EFAULT;
-	} else {
-		page = pages[0];
+	/* used to check for invalidations in progress */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
+
+	/*
+	 * Do a fast check first, since __gfn_to_pfn_memslot doesn't
+	 * do it with !atomic && !async, which is how we call it.
+	 * We always ask for write permission since the common case
+	 * is that the page is writable.
+	 */
+	hva = gfn_to_hva_memslot(memslot, gfn);
+	if (upgrade_p && __get_user_pages_fast(hva, 1, 1, &page) == 1) {
 		pfn = page_to_pfn(page);
-		if (PageCompound(page)) {
-			pte_size <<= compound_order(compound_head(page));
-			/* See if we can insert a 2MB large-page PTE here */
-			if (pte_size >= PMD_SIZE &&
-			    (gpa & (PMD_SIZE - PAGE_SIZE)) ==
-			    (hva & (PMD_SIZE - PAGE_SIZE))) {
-				level = 1;
-				pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1);
-			}
+		upgrade_write = true;
+	} else {
+		/* Call KVM generic code to do the slow-path check */
+		pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
+					   writing, upgrade_p);
+		if (is_error_noslot_pfn(pfn))
+			return -EFAULT;
+		page = NULL;
+		if (pfn_valid(pfn)) {
+			page = pfn_to_page(pfn);
+			if (PageReserved(page))
+				page = NULL;
 		}
-		/* See if we can provide write access */
-		if (writing) {
-			pgflags |= _PAGE_WRITE;
-		} else {
-			local_irq_save(flags);
-			ptep = find_current_mm_pte(current->mm->pgd,
-						   hva, NULL, NULL);
-			if (ptep && pte_write(*ptep))
-				pgflags |= _PAGE_WRITE;
-			local_irq_restore(flags);
+	}
+
+	/* See if we can insert a 1GB or 2MB large PTE here */
+	level = 0;
+	if (page && PageCompound(page)) {
+		pte_size = PAGE_SIZE << compound_order(compound_head(page));
+		if (pte_size >= PUD_SIZE &&
+		    (gpa & (PUD_SIZE - PAGE_SIZE)) ==
+		    (hva & (PUD_SIZE - PAGE_SIZE))) {
+			level = 2;
+			pfn &= ~((PUD_SIZE >> PAGE_SHIFT) - 1);
+		} else if (pte_size >= PMD_SIZE &&
+			   (gpa & (PMD_SIZE - PAGE_SIZE)) ==
+			   (hva & (PMD_SIZE - PAGE_SIZE))) {
+			level = 1;
+			pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1);
 		}
 	}
 
 	/*
 	 * Compute the PTE value that we need to insert.
 	 */
-	pgflags |= _PAGE_PRESENT | _PAGE_PTE | _PAGE_ACCESSED;
-	if (pgflags & _PAGE_WRITE)
-		pgflags |= _PAGE_DIRTY;
-	pte = pfn_pte(pfn, __pgprot(pgflags));
-
-	/* Allocate space in the tree and write the PTE */
-	ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
-	if (ret == -EBUSY) {
+	if (page) {
+		pgflags = _PAGE_READ | _PAGE_EXEC | _PAGE_PRESENT | _PAGE_PTE |
+			_PAGE_ACCESSED;
+		if (writing || upgrade_write)
+			pgflags |= _PAGE_WRITE | _PAGE_DIRTY;
+		pte = pfn_pte(pfn, __pgprot(pgflags));
+	} else {
 		/*
-		 * There's already a PMD where wanted to install a large page;
-		 * for now, fall back to installing a small page.
+		 * Read the PTE from the process' radix tree and use that
+		 * so we get the attribute bits.
 		 */
-		level = 0;
-		pfn |= gfn & ((PMD_SIZE >> PAGE_SHIFT) - 1);
-		pte = pfn_pte(pfn, __pgprot(pgflags));
-		ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
+		local_irq_disable();
+		ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+		pte = *ptep;
+		local_irq_enable();
+		if (shift == PUD_SHIFT &&
+		    (gpa & (PUD_SIZE - PAGE_SIZE)) ==
+		    (hva & (PUD_SIZE - PAGE_SIZE))) {
+			level = 2;
+		} else if (shift == PMD_SHIFT &&
+			   (gpa & (PMD_SIZE - PAGE_SIZE)) ==
+			   (hva & (PMD_SIZE - PAGE_SIZE))) {
+			level = 1;
+		} else if (shift && shift != PAGE_SHIFT) {
+			/* Adjust PFN */
+			unsigned long mask = (1ul << shift) - PAGE_SIZE;
+			pte = __pte(pte_val(pte) | (hva & mask));
+		}
+		if (!(writing || upgrade_write))
+			pte = __pte(pte_val(pte) & ~ _PAGE_WRITE);
+		pte = __pte(pte_val(pte) | _PAGE_EXEC);
 	}
 
+	/* Allocate space in the tree and write the PTE */
+	ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
+
 	if (page) {
-		if (!ret && (pgflags & _PAGE_WRITE))
+		if (!ret && (pte_val(pte) & _PAGE_WRITE))
 			set_page_dirty_lock(page);
 		put_page(page);
 	}
@@ -662,6 +741,10 @@ void kvmppc_free_radix(struct kvm *kvm)
 		for (iu = 0; iu < PTRS_PER_PUD; ++iu, ++pud) {
 			if (!pud_present(*pud))
 				continue;
+			if (pud_huge(*pud)) {
+				pud_clear(pud);
+				continue;
+			}
 			pmd = pmd_offset(pud, 0);
 			for (im = 0; im < PTRS_PER_PMD; ++im, ++pmd) {
 				if (pmd_is_leaf(*pmd)) {

arch/powerpc/kvm/book3s_64_vio_hv.c

@@ -450,7 +450,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 
 		/*
 		 * Synchronize with the MMU notifier callbacks in
-		 * book3s_64_mmu_hv.c (kvm_unmap_hva_hv etc.).
+		 * book3s_64_mmu_hv.c (kvm_unmap_hva_range_hv etc.).
 		 * While we have the rmap lock, code running on other CPUs
 		 * cannot finish unmapping the host real page that backs
 		 * this guest real page, so we are OK to access the host

arch/powerpc/kvm/book3s_hv.c

@@ -4375,7 +4375,6 @@ static struct kvmppc_ops kvm_ops_hv = {
 	.flush_memslot  = kvmppc_core_flush_memslot_hv,
 	.prepare_memory_region = kvmppc_core_prepare_memory_region_hv,
 	.commit_memory_region  = kvmppc_core_commit_memory_region_hv,
-	.unmap_hva = kvm_unmap_hva_hv,
 	.unmap_hva_range = kvm_unmap_hva_range_hv,
 	.age_hva  = kvm_age_hva_hv,
 	.test_age_hva = kvm_test_age_hva_hv,

arch/powerpc/kvm/book3s_pr.c

@@ -277,15 +277,6 @@ static void do_kvm_unmap_hva(struct kvm *kvm, unsigned long start,
 	}
 }
 
-static int kvm_unmap_hva_pr(struct kvm *kvm, unsigned long hva)
-{
-	trace_kvm_unmap_hva(hva);
-
-	do_kvm_unmap_hva(kvm, hva, hva + PAGE_SIZE);
-
-	return 0;
-}
-
 static int kvm_unmap_hva_range_pr(struct kvm *kvm, unsigned long start,
 				  unsigned long end)
 {
@@ -1773,7 +1764,6 @@ static struct kvmppc_ops kvm_ops_pr = {
 	.flush_memslot = kvmppc_core_flush_memslot_pr,
 	.prepare_memory_region = kvmppc_core_prepare_memory_region_pr,
 	.commit_memory_region = kvmppc_core_commit_memory_region_pr,
-	.unmap_hva = kvm_unmap_hva_pr,
 	.unmap_hva_range = kvm_unmap_hva_range_pr,
 	.age_hva  = kvm_age_hva_pr,
 	.test_age_hva = kvm_test_age_hva_pr,

arch/powerpc/kvm/e500_mmu_host.c

@@ -724,7 +724,7 @@ int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, enum instruction_type type,
 
 /************* MMU Notifiers *************/
 
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+static int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
 {
 	trace_kvm_unmap_hva(hva);
 

arch/powerpc/kvm/trace_pr.h

@@ -254,21 +254,6 @@ TRACE_EVENT(kvm_exit,
 		)
 );
 
-TRACE_EVENT(kvm_unmap_hva,
-	TP_PROTO(unsigned long hva),
-	TP_ARGS(hva),
-
-	TP_STRUCT__entry(
-		__field(	unsigned long,	hva		)
-	),
-
-	TP_fast_assign(
-		__entry->hva		= hva;
-	),
-
-	TP_printk("unmap hva 0x%lx\n", __entry->hva)
-);
-
 #endif /* _TRACE_KVM_H */
 
 /* This part must be outside protection */

arch/s390/include/asm/kvm_host.h

@@ -294,6 +294,7 @@ struct kvm_vcpu_stat {
 	u64 exit_userspace;
 	u64 exit_null;
 	u64 exit_external_request;
+	u64 exit_io_request;
 	u64 exit_external_interrupt;
 	u64 exit_stop_request;
 	u64 exit_validity;
@@ -310,16 +311,29 @@ struct kvm_vcpu_stat {
 	u64 exit_program_interruption;
 	u64 exit_instr_and_program;
 	u64 exit_operation_exception;
+	u64 deliver_ckc;
+	u64 deliver_cputm;
 	u64 deliver_external_call;
 	u64 deliver_emergency_signal;
 	u64 deliver_service_signal;
-	u64 deliver_virtio_interrupt;
+	u64 deliver_virtio;
 	u64 deliver_stop_signal;
 	u64 deliver_prefix_signal;
 	u64 deliver_restart_signal;
-	u64 deliver_program_int;
-	u64 deliver_io_int;
+	u64 deliver_program;
+	u64 deliver_io;
+	u64 deliver_machine_check;
 	u64 exit_wait_state;
+	u64 inject_ckc;
+	u64 inject_cputm;
+	u64 inject_external_call;
+	u64 inject_emergency_signal;
+	u64 inject_mchk;
+	u64 inject_pfault_init;
+	u64 inject_program;
+	u64 inject_restart;
+	u64 inject_set_prefix;
+	u64 inject_stop_signal;
 	u64 instruction_epsw;
 	u64 instruction_gs;
 	u64 instruction_io_other;
@@ -644,7 +658,12 @@ struct kvm_vcpu_arch {
 };
 
 struct kvm_vm_stat {
-	ulong remote_tlb_flush;
+	u64 inject_io;
+	u64 inject_float_mchk;
+	u64 inject_pfault_done;
+	u64 inject_service_signal;
+	u64 inject_virtio;
+	u64 remote_tlb_flush;
 };
 
 struct kvm_arch_memory_slot {
@@ -792,6 +811,7 @@ struct kvm_arch{
 	int css_support;
 	int use_irqchip;
 	int use_cmma;
+	int use_pfmfi;
 	int user_cpu_state_ctrl;
 	int user_sigp;
 	int user_stsi;

arch/s390/include/asm/kvm_para.h

@@ -193,6 +193,11 @@ static inline unsigned int kvm_arch_para_features(void)
 	return 0;
 }
 
+static inline unsigned int kvm_arch_para_hints(void)
+{
+	return 0;
+}
+
 static inline bool kvm_check_and_clear_guest_paused(void)
 {
 	return false;

arch/s390/include/asm/mmu.h

@@ -22,8 +22,8 @@ typedef struct {
 	unsigned int has_pgste:1;
 	/* The mmu context uses storage keys. */
 	unsigned int use_skey:1;
-	/* The mmu context uses CMMA. */
-	unsigned int use_cmma:1;
+	/* The mmu context uses CMM. */
+	unsigned int uses_cmm:1;
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						   \

arch/s390/include/asm/mmu_context.h

@@ -31,7 +31,7 @@ static inline int init_new_context(struct task_struct *tsk,
 		(current->mm && current->mm->context.alloc_pgste);
 	mm->context.has_pgste = 0;
 	mm->context.use_skey = 0;
-	mm->context.use_cmma = 0;
+	mm->context.uses_cmm = 0;
 #endif
 	switch (mm->context.asce_limit) {
 	case _REGION2_SIZE:

arch/s390/kvm/gaccess.c

@@ -1050,8 +1050,7 @@ shadow_r2t:
 		rc = gmap_shadow_r2t(sg, saddr, rfte.val, *fake);
 		if (rc)
 			return rc;
-		/* fallthrough */
-	}
+	} /* fallthrough */
 	case ASCE_TYPE_REGION2: {
 		union region2_table_entry rste;
 
@@ -1077,8 +1076,7 @@ shadow_r3t:
 		rc = gmap_shadow_r3t(sg, saddr, rste.val, *fake);
 		if (rc)
 			return rc;
-		/* fallthrough */
-	}
+	} /* fallthrough */
 	case ASCE_TYPE_REGION3: {
 		union region3_table_entry rtte;
 
@@ -1113,8 +1111,7 @@ shadow_sgt:
 		rc = gmap_shadow_sgt(sg, saddr, rtte.val, *fake);
 		if (rc)
 			return rc;
-		/* fallthrough */
-	}
+	} /* fallthrough */
 	case ASCE_TYPE_SEGMENT: {
 		union segment_table_entry ste;
 

arch/s390/kvm/intercept.c

@@ -50,18 +50,6 @@ u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu)
 	return ilen;
 }
 
-static int handle_noop(struct kvm_vcpu *vcpu)
-{
-	switch (vcpu->arch.sie_block->icptcode) {
-	case 0x10:
-		vcpu->stat.exit_external_request++;
-		break;
-	default:
-		break; /* nothing */
-	}
-	return 0;
-}
-
 static int handle_stop(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -465,8 +453,11 @@ int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
 
 	switch (vcpu->arch.sie_block->icptcode) {
 	case ICPT_EXTREQ:
+		vcpu->stat.exit_external_request++;
+		return 0;
 	case ICPT_IOREQ:
-		return handle_noop(vcpu);
+		vcpu->stat.exit_io_request++;
+		return 0;
 	case ICPT_INST:
 		rc = handle_instruction(vcpu);
 		break;

arch/s390/kvm/interrupt.c

@@ -391,6 +391,7 @@ static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	int rc;
 
+	vcpu->stat.deliver_cputm++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER,
 					 0, 0);
 
@@ -410,6 +411,7 @@ static int __must_check __deliver_ckc(struct kvm_vcpu *vcpu)
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	int rc;
 
+	vcpu->stat.deliver_ckc++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP,
 					 0, 0);
 
@@ -595,6 +597,7 @@ static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
 		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
 						 KVM_S390_MCHK,
 						 mchk.cr14, mchk.mcic);
+		vcpu->stat.deliver_machine_check++;
 		rc = __write_machine_check(vcpu, &mchk);
 	}
 	return rc;
@@ -710,7 +713,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
 	ilen = pgm_info.flags & KVM_S390_PGM_FLAGS_ILC_MASK;
 	VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilen:%d",
 		   pgm_info.code, ilen);
-	vcpu->stat.deliver_program_int++;
+	vcpu->stat.deliver_program++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
 					 pgm_info.code, 0);
 
@@ -899,7 +902,7 @@ static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu)
 		VCPU_EVENT(vcpu, 4,
 			   "deliver: virtio parm: 0x%x,parm64: 0x%llx",
 			   inti->ext.ext_params, inti->ext.ext_params2);
-		vcpu->stat.deliver_virtio_interrupt++;
+		vcpu->stat.deliver_virtio++;
 		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
 				inti->type,
 				inti->ext.ext_params,
@@ -975,7 +978,7 @@ static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
 			inti->io.subchannel_id >> 1 & 0x3,
 			inti->io.subchannel_nr);
 
-		vcpu->stat.deliver_io_int++;
+		vcpu->stat.deliver_io++;
 		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
 				inti->type,
 				((__u32)inti->io.subchannel_id << 16) |
@@ -1004,7 +1007,7 @@ static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
 		VCPU_EVENT(vcpu, 4, "%s isc %u", "deliver: I/O (AI/gisa)", isc);
 		memset(&io, 0, sizeof(io));
 		io.io_int_word = isc_to_int_word(isc);
-		vcpu->stat.deliver_io_int++;
+		vcpu->stat.deliver_io++;
 		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
 			KVM_S390_INT_IO(1, 0, 0, 0),
 			((__u32)io.subchannel_id << 16) |
@@ -1268,6 +1271,7 @@ static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
+	vcpu->stat.inject_program++;
 	VCPU_EVENT(vcpu, 3, "inject: program irq code 0x%x", irq->u.pgm.code);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
 				   irq->u.pgm.code, 0);
@@ -1309,6 +1313,7 @@ static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
+	vcpu->stat.inject_pfault_init++;
 	VCPU_EVENT(vcpu, 4, "inject: pfault init parameter block at 0x%llx",
 		   irq->u.ext.ext_params2);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_PFAULT_INIT,
@@ -1327,6 +1332,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	struct kvm_s390_extcall_info *extcall = &li->irq.extcall;
 	uint16_t src_id = irq->u.extcall.code;
 
+	vcpu->stat.inject_external_call++;
 	VCPU_EVENT(vcpu, 4, "inject: external call source-cpu:%u",
 		   src_id);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EXTERNAL_CALL,
@@ -1351,6 +1357,7 @@ static int __inject_set_prefix(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	struct kvm_s390_prefix_info *prefix = &li->irq.prefix;
 
+	vcpu->stat.inject_set_prefix++;
 	VCPU_EVENT(vcpu, 3, "inject: set prefix to %x",
 		   irq->u.prefix.address);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_SET_PREFIX,
@@ -1371,6 +1378,7 @@ static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	struct kvm_s390_stop_info *stop = &li->irq.stop;
 	int rc = 0;
 
+	vcpu->stat.inject_stop_signal++;
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0);
 
 	if (irq->u.stop.flags & ~KVM_S390_STOP_SUPP_FLAGS)
@@ -1395,6 +1403,7 @@ static int __inject_sigp_restart(struct kvm_vcpu *vcpu,
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
+	vcpu->stat.inject_restart++;
 	VCPU_EVENT(vcpu, 3, "%s", "inject: restart int");
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);
 
@@ -1407,6 +1416,7 @@ static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
+	vcpu->stat.inject_emergency_signal++;
 	VCPU_EVENT(vcpu, 4, "inject: emergency from cpu %u",
 		   irq->u.emerg.code);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
@@ -1427,6 +1437,7 @@ static int __inject_mchk(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	struct kvm_s390_mchk_info *mchk = &li->irq.mchk;
 
+	vcpu->stat.inject_mchk++;
 	VCPU_EVENT(vcpu, 3, "inject: machine check mcic 0x%llx",
 		   irq->u.mchk.mcic);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_MCHK, 0,
@@ -1457,6 +1468,7 @@ static int __inject_ckc(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
+	vcpu->stat.inject_ckc++;
 	VCPU_EVENT(vcpu, 3, "%s", "inject: clock comparator external");
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP,
 				   0, 0);
@@ -1470,6 +1482,7 @@ static int __inject_cpu_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 
+	vcpu->stat.inject_cputm++;
 	VCPU_EVENT(vcpu, 3, "%s", "inject: cpu timer external");
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER,
 				   0, 0);
@@ -1596,6 +1609,7 @@ static int __inject_service(struct kvm *kvm,
 {
 	struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
 
+	kvm->stat.inject_service_signal++;
 	spin_lock(&fi->lock);
 	fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_EVENT_PENDING;
 	/*
@@ -1621,6 +1635,7 @@ static int __inject_virtio(struct kvm *kvm,
 {
 	struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
 
+	kvm->stat.inject_virtio++;
 	spin_lock(&fi->lock);
 	if (fi->counters[FIRQ_CNTR_VIRTIO] >= KVM_S390_MAX_VIRTIO_IRQS) {
 		spin_unlock(&fi->lock);
@@ -1638,6 +1653,7 @@ static int __inject_pfault_done(struct kvm *kvm,
 {
 	struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
 
+	kvm->stat.inject_pfault_done++;
 	spin_lock(&fi->lock);
 	if (fi->counters[FIRQ_CNTR_PFAULT] >=
 		(ASYNC_PF_PER_VCPU * KVM_MAX_VCPUS)) {
@@ -1657,6 +1673,7 @@ static int __inject_float_mchk(struct kvm *kvm,
 {
 	struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
 
+	kvm->stat.inject_float_mchk++;
 	spin_lock(&fi->lock);
 	fi->mchk.cr14 |= inti->mchk.cr14 & (1UL << CR_PENDING_SUBCLASS);
 	fi->mchk.mcic |= inti->mchk.mcic;
@@ -1672,6 +1689,7 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 	struct list_head *list;
 	int isc;
 
+	kvm->stat.inject_io++;
 	isc = int_word_to_isc(inti->io.io_int_word);
 
 	if (kvm->arch.gisa && inti->type & KVM_S390_INT_IO_AI_MASK) {

arch/s390/kvm/kvm-s390.c

@@ -57,6 +57,7 @@
 			   (KVM_MAX_VCPUS + LOCAL_IRQS))
 
 #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "userspace_handled", VCPU_STAT(exit_userspace) },
@@ -64,6 +65,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "exit_validity", VCPU_STAT(exit_validity) },
 	{ "exit_stop_request", VCPU_STAT(exit_stop_request) },
 	{ "exit_external_request", VCPU_STAT(exit_external_request) },
+	{ "exit_io_request", VCPU_STAT(exit_io_request) },
 	{ "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) },
 	{ "exit_instruction", VCPU_STAT(exit_instruction) },
 	{ "exit_pei", VCPU_STAT(exit_pei) },
@@ -78,16 +80,34 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
 	{ "instruction_stctl", VCPU_STAT(instruction_stctl) },
 	{ "instruction_stctg", VCPU_STAT(instruction_stctg) },
+	{ "deliver_ckc", VCPU_STAT(deliver_ckc) },
+	{ "deliver_cputm", VCPU_STAT(deliver_cputm) },
 	{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
 	{ "deliver_external_call", VCPU_STAT(deliver_external_call) },
 	{ "deliver_service_signal", VCPU_STAT(deliver_service_signal) },
-	{ "deliver_virtio_interrupt", VCPU_STAT(deliver_virtio_interrupt) },
+	{ "deliver_virtio", VCPU_STAT(deliver_virtio) },
 	{ "deliver_stop_signal", VCPU_STAT(deliver_stop_signal) },
 	{ "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) },
 	{ "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) },
-	{ "deliver_program_interruption", VCPU_STAT(deliver_program_int) },
-	{ "deliver_io_interrupt", VCPU_STAT(deliver_io_int) },
+	{ "deliver_program", VCPU_STAT(deliver_program) },
+	{ "deliver_io", VCPU_STAT(deliver_io) },
+	{ "deliver_machine_check", VCPU_STAT(deliver_machine_check) },
 	{ "exit_wait_state", VCPU_STAT(exit_wait_state) },
+	{ "inject_ckc", VCPU_STAT(inject_ckc) },
+	{ "inject_cputm", VCPU_STAT(inject_cputm) },
+	{ "inject_external_call", VCPU_STAT(inject_external_call) },
+	{ "inject_float_mchk", VM_STAT(inject_float_mchk) },
+	{ "inject_emergency_signal", VCPU_STAT(inject_emergency_signal) },
+	{ "inject_io", VM_STAT(inject_io) },
+	{ "inject_mchk", VCPU_STAT(inject_mchk) },
+	{ "inject_pfault_done", VM_STAT(inject_pfault_done) },
+	{ "inject_program", VCPU_STAT(inject_program) },
+	{ "inject_restart", VCPU_STAT(inject_restart) },
+	{ "inject_service_signal", VM_STAT(inject_service_signal) },
+	{ "inject_set_prefix", VCPU_STAT(inject_set_prefix) },
+	{ "inject_stop_signal", VCPU_STAT(inject_stop_signal) },
+	{ "inject_pfault_init", VCPU_STAT(inject_pfault_init) },
+	{ "inject_virtio", VM_STAT(inject_virtio) },
 	{ "instruction_epsw", VCPU_STAT(instruction_epsw) },
 	{ "instruction_gs", VCPU_STAT(instruction_gs) },
 	{ "instruction_io_other", VCPU_STAT(instruction_io_other) },
@@ -152,13 +172,33 @@ static int nested;
 module_param(nested, int, S_IRUGO);
 MODULE_PARM_DESC(nested, "Nested virtualization support");
 
-/* upper facilities limit for kvm */
-unsigned long kvm_s390_fac_list_mask[16] = { FACILITIES_KVM };
 
-unsigned long kvm_s390_fac_list_mask_size(void)
+/*
+ * For now we handle at most 16 double words as this is what the s390 base
+ * kernel handles and stores in the prefix page. If we ever need to go beyond
+ * this, this requires changes to code, but the external uapi can stay.
+ */
+#define SIZE_INTERNAL 16
+
+/*
+ * Base feature mask that defines default mask for facilities. Consists of the
+ * defines in FACILITIES_KVM and the non-hypervisor managed bits.
+ */
+static unsigned long kvm_s390_fac_base[SIZE_INTERNAL] = { FACILITIES_KVM };
+/*
+ * Extended feature mask. Consists of the defines in FACILITIES_KVM_CPUMODEL
+ * and defines the facilities that can be enabled via a cpu model.
+ */
+static unsigned long kvm_s390_fac_ext[SIZE_INTERNAL] = { FACILITIES_KVM_CPUMODEL };
+
+static unsigned long kvm_s390_fac_size(void)
 {
-	BUILD_BUG_ON(ARRAY_SIZE(kvm_s390_fac_list_mask) > S390_ARCH_FAC_MASK_SIZE_U64);
-	return ARRAY_SIZE(kvm_s390_fac_list_mask);
+	BUILD_BUG_ON(SIZE_INTERNAL > S390_ARCH_FAC_MASK_SIZE_U64);
+	BUILD_BUG_ON(SIZE_INTERNAL > S390_ARCH_FAC_LIST_SIZE_U64);
+	BUILD_BUG_ON(SIZE_INTERNAL * sizeof(unsigned long) >
+		sizeof(S390_lowcore.stfle_fac_list));
+
+	return SIZE_INTERNAL;
 }
 
 /* available cpu features supported by kvm */
@@ -679,6 +719,8 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 		mutex_lock(&kvm->lock);
 		if (!kvm->created_vcpus) {
 			kvm->arch.use_cmma = 1;
+			/* Not compatible with cmma. */
+			kvm->arch.use_pfmfi = 0;
 			ret = 0;
 		}
 		mutex_unlock(&kvm->lock);
@@ -1583,7 +1625,7 @@ static int kvm_s390_get_cmma_bits(struct kvm *kvm,
 		return -EINVAL;
 	/* CMMA is disabled or was not used, or the buffer has length zero */
 	bufsize = min(args->count, KVM_S390_CMMA_SIZE_MAX);
-	if (!bufsize || !kvm->mm->context.use_cmma) {
+	if (!bufsize || !kvm->mm->context.uses_cmm) {
 		memset(args, 0, sizeof(*args));
 		return 0;
 	}
@@ -1660,7 +1702,7 @@ static int kvm_s390_get_cmma_bits(struct kvm *kvm,
 /*
  * This function sets the CMMA attributes for the given pages. If the input
  * buffer has zero length, no action is taken, otherwise the attributes are
- * set and the mm->context.use_cmma flag is set.
+ * set and the mm->context.uses_cmm flag is set.
  */
 static int kvm_s390_set_cmma_bits(struct kvm *kvm,
 				  const struct kvm_s390_cmma_log *args)
@@ -1710,9 +1752,9 @@ static int kvm_s390_set_cmma_bits(struct kvm *kvm,
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 	up_read(&kvm->mm->mmap_sem);
 
-	if (!kvm->mm->context.use_cmma) {
+	if (!kvm->mm->context.uses_cmm) {
 		down_write(&kvm->mm->mmap_sem);
-		kvm->mm->context.use_cmma = 1;
+		kvm->mm->context.uses_cmm = 1;
 		up_write(&kvm->mm->mmap_sem);
 	}
 out:
@@ -1967,20 +2009,15 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (!kvm->arch.sie_page2)
 		goto out_err;
 
-	/* Populate the facility mask initially. */
-	memcpy(kvm->arch.model.fac_mask, S390_lowcore.stfle_fac_list,
-	       sizeof(S390_lowcore.stfle_fac_list));
-	for (i = 0; i < S390_ARCH_FAC_LIST_SIZE_U64; i++) {
-		if (i < kvm_s390_fac_list_mask_size())
-			kvm->arch.model.fac_mask[i] &= kvm_s390_fac_list_mask[i];
-		else
-			kvm->arch.model.fac_mask[i] = 0UL;
-	}
-
-	/* Populate the facility list initially. */
 	kvm->arch.model.fac_list = kvm->arch.sie_page2->fac_list;
-	memcpy(kvm->arch.model.fac_list, kvm->arch.model.fac_mask,
-	       S390_ARCH_FAC_LIST_SIZE_BYTE);
+
+	for (i = 0; i < kvm_s390_fac_size(); i++) {
+		kvm->arch.model.fac_mask[i] = S390_lowcore.stfle_fac_list[i] &
+					      (kvm_s390_fac_base[i] |
+					       kvm_s390_fac_ext[i]);
+		kvm->arch.model.fac_list[i] = S390_lowcore.stfle_fac_list[i] &
+					      kvm_s390_fac_base[i];
+	}
 
 	/* we are always in czam mode - even on pre z14 machines */
 	set_kvm_facility(kvm->arch.model.fac_mask, 138);
@@ -2028,6 +2065,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	kvm->arch.css_support = 0;
 	kvm->arch.use_irqchip = 0;
+	kvm->arch.use_pfmfi = sclp.has_pfmfi;
 	kvm->arch.epoch = 0;
 
 	spin_lock_init(&kvm->arch.start_stop_lock);
@@ -2454,8 +2492,6 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu)
 	vcpu->arch.sie_block->cbrlo = get_zeroed_page(GFP_KERNEL);
 	if (!vcpu->arch.sie_block->cbrlo)
 		return -ENOMEM;
-
-	vcpu->arch.sie_block->ecb2 &= ~ECB2_PFMFI;
 	return 0;
 }
 
@@ -2491,7 +2527,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	if (test_kvm_facility(vcpu->kvm, 73))
 		vcpu->arch.sie_block->ecb |= ECB_TE;
 
-	if (test_kvm_facility(vcpu->kvm, 8) && sclp.has_pfmfi)
+	if (test_kvm_facility(vcpu->kvm, 8) && vcpu->kvm->arch.use_pfmfi)
 		vcpu->arch.sie_block->ecb2 |= ECB2_PFMFI;
 	if (test_kvm_facility(vcpu->kvm, 130))
 		vcpu->arch.sie_block->ecb2 |= ECB2_IEP;
@@ -3023,7 +3059,7 @@ retry:
 
 	if (kvm_check_request(KVM_REQ_START_MIGRATION, vcpu)) {
 		/*
-		 * Disable CMMA virtualization; we will emulate the ESSA
+		 * Disable CMM virtualization; we will emulate the ESSA
 		 * instruction manually, in order to provide additional
 		 * functionalities needed for live migration.
 		 */
@@ -3033,11 +3069,11 @@ retry:
 
 	if (kvm_check_request(KVM_REQ_STOP_MIGRATION, vcpu)) {
 		/*
-		 * Re-enable CMMA virtualization if CMMA is available and
-		 * was used.
+		 * Re-enable CMM virtualization if CMMA is available and
+		 * CMM has been used.
 		 */
 		if ((vcpu->kvm->arch.use_cmma) &&
-		    (vcpu->kvm->mm->context.use_cmma))
+		    (vcpu->kvm->mm->context.uses_cmm))
 			vcpu->arch.sie_block->ecb2 |= ECB2_CMMA;
 		goto retry;
 	}
@@ -4044,7 +4080,7 @@ static int __init kvm_s390_init(void)
 	}
 
 	for (i = 0; i < 16; i++)
-		kvm_s390_fac_list_mask[i] |=
+		kvm_s390_fac_base[i] |=
 			S390_lowcore.stfle_fac_list[i] & nonhyp_mask(i);
 
 	return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);

arch/s390/kvm/kvm-s390.h

@@ -294,8 +294,6 @@ void exit_sie(struct kvm_vcpu *vcpu);
 void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu);
 int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
-unsigned long kvm_s390_fac_list_mask_size(void);
-extern unsigned long kvm_s390_fac_list_mask[];
 void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm);
 __u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu);
 

arch/s390/kvm/priv.c

@@ -1078,9 +1078,9 @@ static int handle_essa(struct kvm_vcpu *vcpu)
 		 * value really needs to be written to; if the value is
 		 * already correct, we do nothing and avoid the lock.
 		 */
-		if (vcpu->kvm->mm->context.use_cmma == 0) {
+		if (vcpu->kvm->mm->context.uses_cmm == 0) {
 			down_write(&vcpu->kvm->mm->mmap_sem);
-			vcpu->kvm->mm->context.use_cmma = 1;
+			vcpu->kvm->mm->context.uses_cmm = 1;
 			up_write(&vcpu->kvm->mm->mmap_sem);
 		}
 		/*

arch/s390/tools/gen_facilities.c

@@ -62,6 +62,13 @@ static struct facility_def facility_defs[] = {
 		}
 	},
 	{
+		/*
+		 * FACILITIES_KVM contains the list of facilities that are part
+		 * of the default facility mask and list that are passed to the
+		 * initial CPU model. If no CPU model is used, this, together
+		 * with the non-hypervisor managed bits, is the maximum list of
+		 * guest facilities supported by KVM.
+		 */
 		.name = "FACILITIES_KVM",
 		.bits = (int[]){
 			0,  /* N3 instructions */
@@ -89,6 +96,19 @@ static struct facility_def facility_defs[] = {
 			-1  /* END */
 		}
 	},
+	{
+		/*
+		 * FACILITIES_KVM_CPUMODEL contains the list of facilities
+		 * that can be enabled by CPU model code if the host supports
+		 * it. These facilities are not passed to the guest without
+		 * CPU model support.
+		 */
+
+		.name = "FACILITIES_KVM_CPUMODEL",
+		.bits = (int[]){
+			-1  /* END */
+		}
+	},
 };
 
 static void print_facility_list(struct facility_def *def)

arch/x86/hyperv/hv_init.c

@@ -21,7 +21,7 @@
 #include <asm/apic.h>
 #include <asm/desc.h>
 #include <asm/hypervisor.h>
-#include <asm/hyperv.h>
+#include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
 #include <linux/version.h>
 #include <linux/vmalloc.h>
@@ -88,11 +88,15 @@ EXPORT_SYMBOL_GPL(hyperv_cs);
 u32 *hv_vp_index;
 EXPORT_SYMBOL_GPL(hv_vp_index);
 
+struct hv_vp_assist_page **hv_vp_assist_page;
+EXPORT_SYMBOL_GPL(hv_vp_assist_page);
+
 u32 hv_max_vp_index;
 
 static int hv_cpu_init(unsigned int cpu)
 {
 	u64 msr_vp_index;
+	struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()];
 
 	hv_get_vp_index(msr_vp_index);
 
@@ -101,6 +105,22 @@ static int hv_cpu_init(unsigned int cpu)
 	if (msr_vp_index > hv_max_vp_index)
 		hv_max_vp_index = msr_vp_index;
 
+	if (!hv_vp_assist_page)
+		return 0;
+
+	if (!*hvp)
+		*hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
+
+	if (*hvp) {
+		u64 val;
+
+		val = vmalloc_to_pfn(*hvp);
+		val = (val << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) |
+			HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
+
+		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, val);
+	}
+
 	return 0;
 }
 
@@ -198,6 +218,9 @@ static int hv_cpu_die(unsigned int cpu)
 	struct hv_reenlightenment_control re_ctrl;
 	unsigned int new_cpu;
 
+	if (hv_vp_assist_page && hv_vp_assist_page[cpu])
+		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, 0);
+
 	if (hv_reenlightenment_cb == NULL)
 		return 0;
 
@@ -224,6 +247,7 @@ void hyperv_init(void)
 {
 	u64 guest_id, required_msrs;
 	union hv_x64_msr_hypercall_contents hypercall_msr;
+	int cpuhp;
 
 	if (x86_hyper_type != X86_HYPER_MS_HYPERV)
 		return;
@@ -241,9 +265,17 @@ void hyperv_init(void)
 	if (!hv_vp_index)
 		return;
 
-	if (cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online",
-			      hv_cpu_init, hv_cpu_die) < 0)
+	hv_vp_assist_page = kcalloc(num_possible_cpus(),
+				    sizeof(*hv_vp_assist_page), GFP_KERNEL);
+	if (!hv_vp_assist_page) {
+		ms_hyperv.hints &= ~HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
 		goto free_vp_index;
+	}
+
+	cpuhp = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online",
+				  hv_cpu_init, hv_cpu_die);
+	if (cpuhp < 0)
+		goto free_vp_assist_page;
 
 	/*
 	 * Setup the hypercall page and enable hypercalls.
@@ -256,7 +288,7 @@ void hyperv_init(void)
 	hv_hypercall_pg  = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX);
 	if (hv_hypercall_pg == NULL) {
 		wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
-		goto free_vp_index;
+		goto remove_cpuhp_state;
 	}
 
 	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
@@ -304,6 +336,11 @@ register_msr_cs:
 
 	return;
 
+remove_cpuhp_state:
+	cpuhp_remove_state(cpuhp);
+free_vp_assist_page:
+	kfree(hv_vp_assist_page);
+	hv_vp_assist_page = NULL;
 free_vp_index:
 	kfree(hv_vp_index);
 	hv_vp_index = NULL;

arch/x86/include/uapi/asm/hyperv.h → arch/x86/include/asm/hyperv-tlfs.h

@@ -1,6 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_X86_HYPERV_H
-#define _ASM_X86_HYPERV_H
+
+/*
+ * This file contains definitions from Hyper-V Hypervisor Top-Level Functional
+ * Specification (TLFS):
+ * https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs
+ */
+
+#ifndef _ASM_X86_HYPERV_TLFS_H
+#define _ASM_X86_HYPERV_TLFS_H
 
 #include <linux/types.h>
 
@@ -14,6 +21,7 @@
 #define HYPERV_CPUID_FEATURES			0x40000003
 #define HYPERV_CPUID_ENLIGHTMENT_INFO		0x40000004
 #define HYPERV_CPUID_IMPLEMENT_LIMITS		0x40000005
+#define HYPERV_CPUID_NESTED_FEATURES		0x4000000A
 
 #define HYPERV_HYPERVISOR_PRESENT_BIT		0x80000000
 #define HYPERV_CPUID_MIN			0x40000005
@@ -159,6 +167,9 @@
 /* Recommend using the newer ExProcessorMasks interface */
 #define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED	(1 << 11)
 
+/* Recommend using enlightened VMCS */
+#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED    (1 << 14)
+
 /*
  * Crash notification flag.
  */
@@ -192,7 +203,7 @@
 #define HV_X64_MSR_EOI				0x40000070
 #define HV_X64_MSR_ICR				0x40000071
 #define HV_X64_MSR_TPR				0x40000072
-#define HV_X64_MSR_APIC_ASSIST_PAGE		0x40000073
+#define HV_X64_MSR_VP_ASSIST_PAGE		0x40000073
 
 /* Define synthetic interrupt controller model specific registers. */
 #define HV_X64_MSR_SCONTROL			0x40000080
@@ -240,6 +251,55 @@
 #define HV_X64_MSR_CRASH_PARAMS		\
 		(1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0))
 
+/*
+ * Declare the MSR used to setup pages used to communicate with the hypervisor.
+ */
+union hv_x64_msr_hypercall_contents {
+	u64 as_uint64;
+	struct {
+		u64 enable:1;
+		u64 reserved:11;
+		u64 guest_physical_address:52;
+	};
+};
+
+/*
+ * TSC page layout.
+ */
+struct ms_hyperv_tsc_page {
+	volatile u32 tsc_sequence;
+	u32 reserved1;
+	volatile u64 tsc_scale;
+	volatile s64 tsc_offset;
+	u64 reserved2[509];
+};
+
+/*
+ * The guest OS needs to register the guest ID with the hypervisor.
+ * The guest ID is a 64 bit entity and the structure of this ID is
+ * specified in the Hyper-V specification:
+ *
+ * msdn.microsoft.com/en-us/library/windows/hardware/ff542653%28v=vs.85%29.aspx
+ *
+ * While the current guideline does not specify how Linux guest ID(s)
+ * need to be generated, our plan is to publish the guidelines for
+ * Linux and other guest operating systems that currently are hosted
+ * on Hyper-V. The implementation here conforms to this yet
+ * unpublished guidelines.
+ *
+ *
+ * Bit(s)
+ * 63 - Indicates if the OS is Open Source or not; 1 is Open Source
+ * 62:56 - Os Type; Linux is 0x100
+ * 55:48 - Distro specific identification
+ * 47:16 - Linux kernel version number
+ * 15:0  - Distro specific identification
+ *
+ *
+ */
+
+#define HV_LINUX_VENDOR_ID              0x8100
+
 /* TSC emulation after migration */
 #define HV_X64_MSR_REENLIGHTENMENT_CONTROL	0x40000106
 
@@ -278,10 +338,13 @@ struct hv_tsc_emulation_status {
 #define HVCALL_POST_MESSAGE			0x005c
 #define HVCALL_SIGNAL_EVENT			0x005d
 
-#define HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE		0x00000001
-#define HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT	12
-#define HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_MASK	\
-		(~((1ull << HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
+#define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE	0x00000001
+#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT	12
+#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK	\
+		(~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
+
+/* Hyper-V Enlightened VMCS version mask in nested features CPUID */
+#define HV_X64_ENLIGHTENED_VMCS_VERSION		0xff
 
 #define HV_X64_MSR_TSC_REFERENCE_ENABLE		0x00000001
 #define HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT	12
@@ -301,12 +364,22 @@ enum HV_GENERIC_SET_FORMAT {
 	HV_GENERIC_SET_ALL,
 };
 
+#define HV_HYPERCALL_RESULT_MASK	GENMASK_ULL(15, 0)
+#define HV_HYPERCALL_FAST_BIT		BIT(16)
+#define HV_HYPERCALL_VARHEAD_OFFSET	17
+#define HV_HYPERCALL_REP_COMP_OFFSET	32
+#define HV_HYPERCALL_REP_COMP_MASK	GENMASK_ULL(43, 32)
+#define HV_HYPERCALL_REP_START_OFFSET	48
+#define HV_HYPERCALL_REP_START_MASK	GENMASK_ULL(59, 48)
+
 /* hypercall status code */
 #define HV_STATUS_SUCCESS			0
 #define HV_STATUS_INVALID_HYPERCALL_CODE	2
 #define HV_STATUS_INVALID_HYPERCALL_INPUT	3
 #define HV_STATUS_INVALID_ALIGNMENT		4
+#define HV_STATUS_INVALID_PARAMETER		5
 #define HV_STATUS_INSUFFICIENT_MEMORY		11
+#define HV_STATUS_INVALID_PORT_ID		17
 #define HV_STATUS_INVALID_CONNECTION_ID		18
 #define HV_STATUS_INSUFFICIENT_BUFFERS		19
 
@@ -321,6 +394,8 @@ typedef struct _HV_REFERENCE_TSC_PAGE {
 #define HV_SYNIC_SINT_COUNT		(16)
 /* Define the expected SynIC version. */
 #define HV_SYNIC_VERSION_1		(0x1)
+/* Valid SynIC vectors are 16-255. */
+#define HV_SYNIC_FIRST_VALID_VECTOR	(16)
 
 #define HV_SYNIC_CONTROL_ENABLE		(1ULL << 0)
 #define HV_SYNIC_SIMP_ENABLE		(1ULL << 0)
@@ -415,6 +490,216 @@ struct hv_timer_message_payload {
 	__u64 delivery_time;	/* When the message was delivered */
 };
 
+/* Define virtual processor assist page structure. */
+struct hv_vp_assist_page {
+	__u32 apic_assist;
+	__u32 reserved;
+	__u64 vtl_control[2];
+	__u64 nested_enlightenments_control[2];
+	__u32 enlighten_vmentry;
+	__u64 current_nested_vmcs;
+};
+
+struct hv_enlightened_vmcs {
+	u32 revision_id;
+	u32 abort;
+
+	u16 host_es_selector;
+	u16 host_cs_selector;
+	u16 host_ss_selector;
+	u16 host_ds_selector;
+	u16 host_fs_selector;
+	u16 host_gs_selector;
+	u16 host_tr_selector;
+
+	u64 host_ia32_pat;
+	u64 host_ia32_efer;
+
+	u64 host_cr0;
+	u64 host_cr3;
+	u64 host_cr4;
+
+	u64 host_ia32_sysenter_esp;
+	u64 host_ia32_sysenter_eip;
+	u64 host_rip;
+	u32 host_ia32_sysenter_cs;
+
+	u32 pin_based_vm_exec_control;
+	u32 vm_exit_controls;
+	u32 secondary_vm_exec_control;
+
+	u64 io_bitmap_a;
+	u64 io_bitmap_b;
+	u64 msr_bitmap;
+
+	u16 guest_es_selector;
+	u16 guest_cs_selector;
+	u16 guest_ss_selector;
+	u16 guest_ds_selector;
+	u16 guest_fs_selector;
+	u16 guest_gs_selector;
+	u16 guest_ldtr_selector;
+	u16 guest_tr_selector;
+
+	u32 guest_es_limit;
+	u32 guest_cs_limit;
+	u32 guest_ss_limit;
+	u32 guest_ds_limit;
+	u32 guest_fs_limit;
+	u32 guest_gs_limit;
+	u32 guest_ldtr_limit;
+	u32 guest_tr_limit;
+	u32 guest_gdtr_limit;
+	u32 guest_idtr_limit;
+
+	u32 guest_es_ar_bytes;
+	u32 guest_cs_ar_bytes;
+	u32 guest_ss_ar_bytes;
+	u32 guest_ds_ar_bytes;
+	u32 guest_fs_ar_bytes;
+	u32 guest_gs_ar_bytes;
+	u32 guest_ldtr_ar_bytes;
+	u32 guest_tr_ar_bytes;
+
+	u64 guest_es_base;
+	u64 guest_cs_base;
+	u64 guest_ss_base;
+	u64 guest_ds_base;
+	u64 guest_fs_base;
+	u64 guest_gs_base;
+	u64 guest_ldtr_base;
+	u64 guest_tr_base;
+	u64 guest_gdtr_base;
+	u64 guest_idtr_base;
+
+	u64 padding64_1[3];
+
+	u64 vm_exit_msr_store_addr;
+	u64 vm_exit_msr_load_addr;
+	u64 vm_entry_msr_load_addr;
+
+	u64 cr3_target_value0;
+	u64 cr3_target_value1;
+	u64 cr3_target_value2;
+	u64 cr3_target_value3;
+
+	u32 page_fault_error_code_mask;
+	u32 page_fault_error_code_match;
+
+	u32 cr3_target_count;
+	u32 vm_exit_msr_store_count;
+	u32 vm_exit_msr_load_count;
+	u32 vm_entry_msr_load_count;
+
+	u64 tsc_offset;
+	u64 virtual_apic_page_addr;
+	u64 vmcs_link_pointer;
+
+	u64 guest_ia32_debugctl;
+	u64 guest_ia32_pat;
+	u64 guest_ia32_efer;
+
+	u64 guest_pdptr0;
+	u64 guest_pdptr1;
+	u64 guest_pdptr2;
+	u64 guest_pdptr3;
+
+	u64 guest_pending_dbg_exceptions;
+	u64 guest_sysenter_esp;
+	u64 guest_sysenter_eip;
+
+	u32 guest_activity_state;
+	u32 guest_sysenter_cs;
+
+	u64 cr0_guest_host_mask;
+	u64 cr4_guest_host_mask;
+	u64 cr0_read_shadow;
+	u64 cr4_read_shadow;
+	u64 guest_cr0;
+	u64 guest_cr3;
+	u64 guest_cr4;
+	u64 guest_dr7;
+
+	u64 host_fs_base;
+	u64 host_gs_base;
+	u64 host_tr_base;
+	u64 host_gdtr_base;
+	u64 host_idtr_base;
+	u64 host_rsp;
+
+	u64 ept_pointer;
+
+	u16 virtual_processor_id;
+	u16 padding16[3];
+
+	u64 padding64_2[5];
+	u64 guest_physical_address;
+
+	u32 vm_instruction_error;
+	u32 vm_exit_reason;
+	u32 vm_exit_intr_info;
+	u32 vm_exit_intr_error_code;
+	u32 idt_vectoring_info_field;
+	u32 idt_vectoring_error_code;
+	u32 vm_exit_instruction_len;
+	u32 vmx_instruction_info;
+
+	u64 exit_qualification;
+	u64 exit_io_instruction_ecx;
+	u64 exit_io_instruction_esi;
+	u64 exit_io_instruction_edi;
+	u64 exit_io_instruction_eip;
+
+	u64 guest_linear_address;
+	u64 guest_rsp;
+	u64 guest_rflags;
+
+	u32 guest_interruptibility_info;
+	u32 cpu_based_vm_exec_control;
+	u32 exception_bitmap;
+	u32 vm_entry_controls;
+	u32 vm_entry_intr_info_field;
+	u32 vm_entry_exception_error_code;
+	u32 vm_entry_instruction_len;
+	u32 tpr_threshold;
+
+	u64 guest_rip;
+
+	u32 hv_clean_fields;
+	u32 hv_padding_32;
+	u32 hv_synthetic_controls;
+	u32 hv_enlightenments_control;
+	u32 hv_vp_id;
+
+	u64 hv_vm_id;
+	u64 partition_assist_page;
+	u64 padding64_4[4];
+	u64 guest_bndcfgs;
+	u64 padding64_5[7];
+	u64 xss_exit_bitmap;
+	u64 padding64_6[7];
+};
+
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE			0
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP		BIT(0)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP		BIT(1)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2		BIT(2)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1		BIT(3)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC		BIT(4)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT		BIT(5)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY		BIT(6)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN		BIT(7)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR			BIT(8)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT		BIT(9)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC		BIT(10)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1		BIT(11)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2		BIT(12)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER		BIT(13)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1		BIT(14)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL	BIT(15)
+
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL			0xFFFF
+
 #define HV_STIMER_ENABLE		(1ULL << 0)
 #define HV_STIMER_PERIODIC		(1ULL << 1)
 #define HV_STIMER_LAZY			(1ULL << 2)

arch/x86/include/asm/kvm_host.h

@@ -34,6 +34,7 @@
 #include <asm/msr-index.h>
 #include <asm/asm.h>
 #include <asm/kvm_page_track.h>
+#include <asm/hyperv-tlfs.h>
 
 #define KVM_MAX_VCPUS 288
 #define KVM_SOFT_MAX_VCPUS 240
@@ -73,6 +74,7 @@
 #define KVM_REQ_HV_RESET		KVM_ARCH_REQ(20)
 #define KVM_REQ_HV_EXIT			KVM_ARCH_REQ(21)
 #define KVM_REQ_HV_STIMER		KVM_ARCH_REQ(22)
+#define KVM_REQ_LOAD_EOI_EXITMAP	KVM_ARCH_REQ(23)
 
 #define CR0_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
@@ -498,6 +500,7 @@ struct kvm_vcpu_arch {
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
 	bool apicv_active;
+	bool load_eoi_exitmap_pending;
 	DECLARE_BITMAP(ioapic_handled_vectors, 256);
 	unsigned long apic_attention;
 	int32_t apic_arb_prio;
@@ -571,7 +574,7 @@ struct kvm_vcpu_arch {
 	} exception;
 
 	struct kvm_queued_interrupt {
-		bool pending;
+		bool injected;
 		bool soft;
 		u8 nr;
 	} interrupt;
@@ -754,6 +757,12 @@ struct kvm_hv {
 	u64 hv_crash_ctl;
 
 	HV_REFERENCE_TSC_PAGE tsc_ref;
+
+	struct idr conn_to_evt;
+
+	u64 hv_reenlightenment_control;
+	u64 hv_tsc_emulation_control;
+	u64 hv_tsc_emulation_status;
 };
 
 enum kvm_irqchip_mode {
@@ -762,15 +771,6 @@ enum kvm_irqchip_mode {
 	KVM_IRQCHIP_SPLIT,        /* created with KVM_CAP_SPLIT_IRQCHIP */
 };
 
-struct kvm_sev_info {
-	bool active;		/* SEV enabled guest */
-	unsigned int asid;	/* ASID used for this guest */
-	unsigned int handle;	/* SEV firmware handle */
-	int fd;			/* SEV device fd */
-	unsigned long pages_locked; /* Number of pages locked */
-	struct list_head regions_list;  /* List of registered regions */
-};
-
 struct kvm_arch {
 	unsigned int n_used_mmu_pages;
 	unsigned int n_requested_mmu_pages;
@@ -800,13 +800,13 @@ struct kvm_arch {
 	struct mutex apic_map_lock;
 	struct kvm_apic_map *apic_map;
 
-	unsigned int tss_addr;
 	bool apic_access_page_done;
 
 	gpa_t wall_clock;
 
-	bool ept_identity_pagetable_done;
-	gpa_t ept_identity_map_addr;
+	bool mwait_in_guest;
+	bool hlt_in_guest;
+	bool pause_in_guest;
 
 	unsigned long irq_sources_bitmap;
 	s64 kvmclock_offset;
@@ -849,17 +849,8 @@ struct kvm_arch {
 
 	bool disabled_lapic_found;
 
-	/* Struct members for AVIC */
-	u32 avic_vm_id;
-	u32 ldr_mode;
-	struct page *avic_logical_id_table_page;
-	struct page *avic_physical_id_table_page;
-	struct hlist_node hnode;
-
 	bool x2apic_format;
 	bool x2apic_broadcast_quirk_disabled;
-
-	struct kvm_sev_info sev_info;
 };
 
 struct kvm_vm_stat {
@@ -936,6 +927,8 @@ struct kvm_x86_ops {
 	bool (*cpu_has_high_real_mode_segbase)(void);
 	void (*cpuid_update)(struct kvm_vcpu *vcpu);
 
+	struct kvm *(*vm_alloc)(void);
+	void (*vm_free)(struct kvm *);
 	int (*vm_init)(struct kvm *kvm);
 	void (*vm_destroy)(struct kvm *kvm);
 
@@ -1007,6 +1000,7 @@ struct kvm_x86_ops {
 	void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
 	int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
+	int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr);
 	int (*get_tdp_level)(struct kvm_vcpu *vcpu);
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
 	int (*get_lpage_level)(void);
@@ -1109,6 +1103,17 @@ struct kvm_arch_async_pf {
 
 extern struct kvm_x86_ops *kvm_x86_ops;
 
+#define __KVM_HAVE_ARCH_VM_ALLOC
+static inline struct kvm *kvm_arch_alloc_vm(void)
+{
+	return kvm_x86_ops->vm_alloc();
+}
+
+static inline void kvm_arch_free_vm(struct kvm *kvm)
+{
+	return kvm_x86_ops->vm_free(kvm);
+}
+
 int kvm_mmu_module_init(void);
 void kvm_mmu_module_exit(void);
 
@@ -1187,6 +1192,8 @@ enum emulation_result {
 #define EMULTYPE_SKIP		    (1 << 2)
 #define EMULTYPE_RETRY		    (1 << 3)
 #define EMULTYPE_NO_REEXECUTE	    (1 << 4)
+#define EMULTYPE_NO_UD_ON_FAIL	    (1 << 5)
+#define EMULTYPE_VMWARE		    (1 << 6)
 int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
 			    int emulation_type, void *insn, int insn_len);
 
@@ -1204,8 +1211,7 @@ 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);
-int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port);
+int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in);
 int kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
 int kvm_emulate_halt(struct kvm_vcpu *vcpu);
 int kvm_vcpu_halt(struct kvm_vcpu *vcpu);

arch/x86/include/asm/kvm_para.h

@@ -88,6 +88,7 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 #ifdef CONFIG_KVM_GUEST
 bool kvm_para_available(void);
 unsigned int kvm_arch_para_features(void);
+unsigned int kvm_arch_para_hints(void);
 void kvm_async_pf_task_wait(u32 token, int interrupt_kernel);
 void kvm_async_pf_task_wake(u32 token);
 u32 kvm_read_and_reset_pf_reason(void);
@@ -115,6 +116,11 @@ static inline unsigned int kvm_arch_para_features(void)
 	return 0;
 }
 
+static inline unsigned int kvm_arch_para_hints(void)
+{
+	return 0;
+}
+
 static inline u32 kvm_read_and_reset_pf_reason(void)
 {
 	return 0;

arch/x86/include/asm/mshyperv.h

@@ -6,90 +6,23 @@
 #include <linux/atomic.h>
 #include <linux/nmi.h>
 #include <asm/io.h>
-#include <asm/hyperv.h>
+#include <asm/hyperv-tlfs.h>
 #include <asm/nospec-branch.h>
 
-/*
- * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
- * is set by CPUID(HVCPUID_VERSION_FEATURES).
- */
-enum hv_cpuid_function {
-	HVCPUID_VERSION_FEATURES		= 0x00000001,
-	HVCPUID_VENDOR_MAXFUNCTION		= 0x40000000,
-	HVCPUID_INTERFACE			= 0x40000001,
-
-	/*
-	 * The remaining functions depend on the value of
-	 * HVCPUID_INTERFACE
-	 */
-	HVCPUID_VERSION				= 0x40000002,
-	HVCPUID_FEATURES			= 0x40000003,
-	HVCPUID_ENLIGHTENMENT_INFO		= 0x40000004,
-	HVCPUID_IMPLEMENTATION_LIMITS		= 0x40000005,
-};
-
 struct ms_hyperv_info {
 	u32 features;
 	u32 misc_features;
 	u32 hints;
+	u32 nested_features;
 	u32 max_vp_index;
 	u32 max_lp_index;
 };
 
 extern struct ms_hyperv_info ms_hyperv;
 
-/*
- * Declare the MSR used to setup pages used to communicate with the hypervisor.
- */
-union hv_x64_msr_hypercall_contents {
-	u64 as_uint64;
-	struct {
-		u64 enable:1;
-		u64 reserved:11;
-		u64 guest_physical_address:52;
-	};
-};
 
 /*
- * TSC page layout.
- */
-
-struct ms_hyperv_tsc_page {
-	volatile u32 tsc_sequence;
-	u32 reserved1;
-	volatile u64 tsc_scale;
-	volatile s64 tsc_offset;
-	u64 reserved2[509];
-};
-
-/*
- * The guest OS needs to register the guest ID with the hypervisor.
- * The guest ID is a 64 bit entity and the structure of this ID is
- * specified in the Hyper-V specification:
- *
- * msdn.microsoft.com/en-us/library/windows/hardware/ff542653%28v=vs.85%29.aspx
- *
- * While the current guideline does not specify how Linux guest ID(s)
- * need to be generated, our plan is to publish the guidelines for
- * Linux and other guest operating systems that currently are hosted
- * on Hyper-V. The implementation here conforms to this yet
- * unpublished guidelines.
- *
- *
- * Bit(s)
- * 63 - Indicates if the OS is Open Source or not; 1 is Open Source
- * 62:56 - Os Type; Linux is 0x100
- * 55:48 - Distro specific identification
- * 47:16 - Linux kernel version number
- * 15:0  - Distro specific identification
- *
- *
- */
-
-#define HV_LINUX_VENDOR_ID              0x8100
-
-/*
- * Generate the guest ID based on the guideline described above.
+ * Generate the guest ID.
  */
 
 static inline  __u64 generate_guest_id(__u64 d_info1, __u64 kernel_version,
@@ -228,14 +161,6 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 	return hv_status;
 }
 
-#define HV_HYPERCALL_RESULT_MASK	GENMASK_ULL(15, 0)
-#define HV_HYPERCALL_FAST_BIT		BIT(16)
-#define HV_HYPERCALL_VARHEAD_OFFSET	17
-#define HV_HYPERCALL_REP_COMP_OFFSET	32
-#define HV_HYPERCALL_REP_COMP_MASK	GENMASK_ULL(43, 32)
-#define HV_HYPERCALL_REP_START_OFFSET	48
-#define HV_HYPERCALL_REP_START_MASK	GENMASK_ULL(59, 48)
-
 /* Fast hypercall with 8 bytes of input and no output */
 static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 {
@@ -307,6 +232,15 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
  */
 extern u32 *hv_vp_index;
 extern u32 hv_max_vp_index;
+extern struct hv_vp_assist_page **hv_vp_assist_page;
+
+static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
+{
+	if (!hv_vp_assist_page)
+		return NULL;
+
+	return hv_vp_assist_page[cpu];
+}
 
 /**
  * hv_cpu_number_to_vp_number() - Map CPU to VP.
@@ -343,6 +277,10 @@ static inline void hyperv_setup_mmu_ops(void) {}
 static inline void set_hv_tscchange_cb(void (*cb)(void)) {}
 static inline void clear_hv_tscchange_cb(void) {}
 static inline void hyperv_stop_tsc_emulation(void) {};
+static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
+{
+	return NULL;
+}
 #endif /* CONFIG_HYPERV */
 
 #ifdef CONFIG_HYPERV_TSCPAGE

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

@@ -353,7 +353,21 @@
 
 /* Fam 15h MSRs */
 #define MSR_F15H_PERF_CTL		0xc0010200
+#define MSR_F15H_PERF_CTL0		MSR_F15H_PERF_CTL
+#define MSR_F15H_PERF_CTL1		(MSR_F15H_PERF_CTL + 2)
+#define MSR_F15H_PERF_CTL2		(MSR_F15H_PERF_CTL + 4)
+#define MSR_F15H_PERF_CTL3		(MSR_F15H_PERF_CTL + 6)
+#define MSR_F15H_PERF_CTL4		(MSR_F15H_PERF_CTL + 8)
+#define MSR_F15H_PERF_CTL5		(MSR_F15H_PERF_CTL + 10)
+
 #define MSR_F15H_PERF_CTR		0xc0010201
+#define MSR_F15H_PERF_CTR0		MSR_F15H_PERF_CTR
+#define MSR_F15H_PERF_CTR1		(MSR_F15H_PERF_CTR + 2)
+#define MSR_F15H_PERF_CTR2		(MSR_F15H_PERF_CTR + 4)
+#define MSR_F15H_PERF_CTR3		(MSR_F15H_PERF_CTR + 6)
+#define MSR_F15H_PERF_CTR4		(MSR_F15H_PERF_CTR + 8)
+#define MSR_F15H_PERF_CTR5		(MSR_F15H_PERF_CTR + 10)
+
 #define MSR_F15H_NB_PERF_CTL		0xc0010240
 #define MSR_F15H_NB_PERF_CTR		0xc0010241
 #define MSR_F15H_PTSC			0xc0010280

arch/x86/include/asm/processor.h

@@ -407,9 +407,19 @@ union irq_stack_union {
 DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible;
 DECLARE_INIT_PER_CPU(irq_stack_union);
 
+static inline unsigned long cpu_kernelmode_gs_base(int cpu)
+{
+	return (unsigned long)per_cpu(irq_stack_union.gs_base, cpu);
+}
+
 DECLARE_PER_CPU(char *, irq_stack_ptr);
 DECLARE_PER_CPU(unsigned int, irq_count);
 extern asmlinkage void ignore_sysret(void);
+
+#if IS_ENABLED(CONFIG_KVM)
+/* Save actual FS/GS selectors and bases to current->thread */
+void save_fsgs_for_kvm(void);
+#endif
 #else	/* X86_64 */
 #ifdef CONFIG_CC_STACKPROTECTOR
 /*

arch/x86/include/asm/svm.h

@@ -60,7 +60,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 	u32 intercept_dr;
 	u32 intercept_exceptions;
 	u64 intercept;
-	u8 reserved_1[42];
+	u8 reserved_1[40];
+	u16 pause_filter_thresh;
 	u16 pause_filter_count;
 	u64 iopm_base_pa;
 	u64 msrpm_base_pa;

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

@@ -354,8 +354,25 @@ struct kvm_xcrs {
 	__u64 padding[16];
 };
 
-/* definition of registers in kvm_run */
+#define KVM_SYNC_X86_REGS      (1UL << 0)
+#define KVM_SYNC_X86_SREGS     (1UL << 1)
+#define KVM_SYNC_X86_EVENTS    (1UL << 2)
+
+#define KVM_SYNC_X86_VALID_FIELDS \
+	(KVM_SYNC_X86_REGS| \
+	 KVM_SYNC_X86_SREGS| \
+	 KVM_SYNC_X86_EVENTS)
+
+/* kvm_sync_regs struct included by kvm_run struct */
 struct kvm_sync_regs {
+	/* Members of this structure are potentially malicious.
+	 * Care must be taken by code reading, esp. interpreting,
+	 * data fields from them inside KVM to prevent TOCTOU and
+	 * double-fetch types of vulnerabilities.
+	 */
+	struct kvm_regs regs;
+	struct kvm_sregs sregs;
+	struct kvm_vcpu_events events;
 };
 
 #define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)

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

@@ -3,15 +3,16 @@
 #define _UAPI_ASM_X86_KVM_PARA_H
 
 #include <linux/types.h>
-#include <asm/hyperv.h>
 
 /* This CPUID returns the signature 'KVMKVMKVM' in ebx, ecx, and edx.  It
  * should be used to determine that a VM is running under KVM.
  */
 #define KVM_CPUID_SIGNATURE	0x40000000
 
-/* This CPUID returns a feature bitmap in eax.  Before enabling a particular
- * paravirtualization, the appropriate feature bit should be checked.
+/* This CPUID returns two feature bitmaps in eax, edx. Before enabling
+ * a particular paravirtualization, the appropriate feature bit should
+ * be checked in eax. The performance hint feature bit should be checked
+ * in edx.
  */
 #define KVM_CPUID_FEATURES	0x40000001
 #define KVM_FEATURE_CLOCKSOURCE		0
@@ -28,6 +29,8 @@
 #define KVM_FEATURE_PV_TLB_FLUSH	9
 #define KVM_FEATURE_ASYNC_PF_VMEXIT	10
 
+#define KVM_HINTS_DEDICATED      0
+
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
  */

arch/x86/kernel/cpu/common.c

@@ -487,7 +487,7 @@ void load_percpu_segment(int cpu)
 	loadsegment(fs, __KERNEL_PERCPU);
 #else
 	__loadsegment_simple(gs, 0);
-	wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu));
+	wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
 #endif
 	load_stack_canary_segment();
 }
@@ -1398,6 +1398,7 @@ __setup("clearcpuid=", setup_clearcpuid);
 #ifdef CONFIG_X86_64
 DEFINE_PER_CPU_FIRST(union irq_stack_union,
 		     irq_stack_union) __aligned(PAGE_SIZE) __visible;
+EXPORT_PER_CPU_SYMBOL_GPL(irq_stack_union);
 
 /*
  * The following percpu variables are hot.  Align current_task to

arch/x86/kernel/cpu/mshyperv.c

@@ -22,7 +22,7 @@
 #include <linux/kexec.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
-#include <asm/hyperv.h>
+#include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
 #include <asm/desc.h>
 #include <asm/irq_regs.h>
@@ -216,8 +216,8 @@ static void __init ms_hyperv_init_platform(void)
 	pr_info("Hyper-V: features 0x%x, hints 0x%x\n",
 		ms_hyperv.features, ms_hyperv.hints);
 
-	ms_hyperv.max_vp_index = cpuid_eax(HVCPUID_IMPLEMENTATION_LIMITS);
-	ms_hyperv.max_lp_index = cpuid_ebx(HVCPUID_IMPLEMENTATION_LIMITS);
+	ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS);
+	ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS);
 
 	pr_debug("Hyper-V: max %u virtual processors, %u logical processors\n",
 		 ms_hyperv.max_vp_index, ms_hyperv.max_lp_index);
@@ -225,11 +225,12 @@ static void __init ms_hyperv_init_platform(void)
 	/*
 	 * Extract host information.
 	 */
-	if (cpuid_eax(HVCPUID_VENDOR_MAXFUNCTION) >= HVCPUID_VERSION) {
-		hv_host_info_eax = cpuid_eax(HVCPUID_VERSION);
-		hv_host_info_ebx = cpuid_ebx(HVCPUID_VERSION);
-		hv_host_info_ecx = cpuid_ecx(HVCPUID_VERSION);
-		hv_host_info_edx = cpuid_edx(HVCPUID_VERSION);
+	if (cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS) >=
+	    HYPERV_CPUID_VERSION) {
+		hv_host_info_eax = cpuid_eax(HYPERV_CPUID_VERSION);
+		hv_host_info_ebx = cpuid_ebx(HYPERV_CPUID_VERSION);
+		hv_host_info_ecx = cpuid_ecx(HYPERV_CPUID_VERSION);
+		hv_host_info_edx = cpuid_edx(HYPERV_CPUID_VERSION);
 
 		pr_info("Hyper-V Host Build:%d-%d.%d-%d-%d.%d\n",
 			hv_host_info_eax, hv_host_info_ebx >> 16,
@@ -243,6 +244,11 @@ static void __init ms_hyperv_init_platform(void)
 		x86_platform.calibrate_cpu = hv_get_tsc_khz;
 	}
 
+	if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED) {
+		ms_hyperv.nested_features =
+			cpuid_eax(HYPERV_CPUID_NESTED_FEATURES);
+	}
+
 #ifdef CONFIG_X86_LOCAL_APIC
 	if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
 	    ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {

arch/x86/kernel/kvm.c

@@ -454,6 +454,13 @@ static void __init sev_map_percpu_data(void)
 }
 
 #ifdef CONFIG_SMP
+static void __init kvm_smp_prepare_cpus(unsigned int max_cpus)
+{
+	native_smp_prepare_cpus(max_cpus);
+	if (kvm_para_has_hint(KVM_HINTS_DEDICATED))
+		static_branch_disable(&virt_spin_lock_key);
+}
+
 static void __init kvm_smp_prepare_boot_cpu(void)
 {
 	/*
@@ -546,6 +553,7 @@ static void __init kvm_guest_init(void)
 	}
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
+	    !kvm_para_has_hint(KVM_HINTS_DEDICATED) &&
 	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
 		pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
 
@@ -556,6 +564,7 @@ static void __init kvm_guest_init(void)
 		kvm_setup_vsyscall_timeinfo();
 
 #ifdef CONFIG_SMP
+	smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus;
 	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
 	if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online",
 				      kvm_cpu_online, kvm_cpu_down_prepare) < 0)
@@ -605,6 +614,11 @@ unsigned int kvm_arch_para_features(void)
 	return cpuid_eax(kvm_cpuid_base() | KVM_CPUID_FEATURES);
 }
 
+unsigned int kvm_arch_para_hints(void)
+{
+	return cpuid_edx(kvm_cpuid_base() | KVM_CPUID_FEATURES);
+}
+
 static uint32_t __init kvm_detect(void)
 {
 	return kvm_cpuid_base();
@@ -635,6 +649,7 @@ static __init int kvm_setup_pv_tlb_flush(void)
 	int cpu;
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
+	    !kvm_para_has_hint(KVM_HINTS_DEDICATED) &&
 	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		for_each_possible_cpu(cpu) {
 			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
@@ -730,6 +745,9 @@ void __init kvm_spinlock_init(void)
 	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
 		return;
 
+	if (kvm_para_has_hint(KVM_HINTS_DEDICATED))
+		return;
+
 	__pv_init_lock_hash();
 	pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
 	pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);

arch/x86/kernel/process_64.c

@@ -205,6 +205,20 @@ static __always_inline void save_fsgs(struct task_struct *task)
 	save_base_legacy(task, task->thread.gsindex, GS);
 }
 
+#if IS_ENABLED(CONFIG_KVM)
+/*
+ * While a process is running,current->thread.fsbase and current->thread.gsbase
+ * may not match the corresponding CPU registers (see save_base_legacy()). KVM
+ * wants an efficient way to save and restore FSBASE and GSBASE.
+ * When FSGSBASE extensions are enabled, this will have to use RD{FS,GS}BASE.
+ */
+void save_fsgs_for_kvm(void)
+{
+	save_fsgs(current);
+}
+EXPORT_SYMBOL_GPL(save_fsgs_for_kvm);
+#endif
+
 static __always_inline void loadseg(enum which_selector which,
 				    unsigned short sel)
 {

arch/x86/kvm/cpuid.c

@@ -135,6 +135,11 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 			return -EINVAL;
 	}
 
+	best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0);
+	if (kvm_hlt_in_guest(vcpu->kvm) && best &&
+		(best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
+		best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
+
 	/* Update physical-address width */
 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
 	kvm_mmu_reset_context(vcpu);
@@ -370,7 +375,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
 		F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) |
 		0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) |
-		F(TOPOEXT);
+		F(TOPOEXT) | F(PERFCTR_CORE);
 
 	/* cpuid 0x80000008.ebx */
 	const u32 kvm_cpuid_8000_0008_ebx_x86_features =

arch/x86/kvm/emulate.c

@@ -30,6 +30,7 @@
 #include "x86.h"
 #include "tss.h"
 #include "mmu.h"
+#include "pmu.h"
 
 /*
  * Operand types
@@ -2887,6 +2888,9 @@ static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt)
 	return ctxt->ops->cpl(ctxt) > iopl;
 }
 
+#define VMWARE_PORT_VMPORT	(0x5658)
+#define VMWARE_PORT_VMRPC	(0x5659)
+
 static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt,
 					    u16 port, u16 len)
 {
@@ -2898,6 +2902,14 @@ static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt,
 	unsigned mask = (1 << len) - 1;
 	unsigned long base;
 
+	/*
+	 * VMware allows access to these ports even if denied
+	 * by TSS I/O permission bitmap. Mimic behavior.
+	 */
+	if (enable_vmware_backdoor &&
+	    ((port == VMWARE_PORT_VMPORT) || (port == VMWARE_PORT_VMRPC)))
+		return true;
+
 	ops->get_segment(ctxt, &tr, &tr_seg, &base3, VCPU_SREG_TR);
 	if (!tr_seg.p)
 		return false;
@@ -4282,6 +4294,13 @@ static int check_rdpmc(struct x86_emulate_ctxt *ctxt)
 	u64 cr4 = ctxt->ops->get_cr(ctxt, 4);
 	u64 rcx = reg_read(ctxt, VCPU_REGS_RCX);
 
+	/*
+	 * VMware allows access to these Pseduo-PMCs even when read via RDPMC
+	 * in Ring3 when CR4.PCE=0.
+	 */
+	if (enable_vmware_backdoor && is_vmware_backdoor_pmc(rcx))
+		return X86EMUL_CONTINUE;
+
 	if ((!(cr4 & X86_CR4_PCE) && ctxt->ops->cpl(ctxt)) ||
 	    ctxt->ops->check_pmc(ctxt, rcx))
 		return emulate_gp(ctxt, 0);
@@ -4498,6 +4517,10 @@ static const struct gprefix pfx_0f_2b = {
 	ID(0, &instr_dual_0f_2b), ID(0, &instr_dual_0f_2b), N, N,
 };
 
+static const struct gprefix pfx_0f_10_0f_11 = {
+	I(Unaligned, em_mov), I(Unaligned, em_mov), N, N,
+};
+
 static const struct gprefix pfx_0f_28_0f_29 = {
 	I(Aligned, em_mov), I(Aligned, em_mov), N, N,
 };
@@ -4709,7 +4732,9 @@ static const struct opcode twobyte_table[256] = {
 	DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N,
 	N, D(ImplicitOps | ModRM | SrcMem | NoAccess), N, N,
 	/* 0x10 - 0x1F */
-	N, N, N, N, N, N, N, N,
+	GP(ModRM | DstReg | SrcMem | Mov | Sse, &pfx_0f_10_0f_11),
+	GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_10_0f_11),
+	N, N, N, N, N, N,
 	D(ImplicitOps | ModRM | SrcMem | NoAccess),
 	N, N, N, N, N, N, D(ImplicitOps | ModRM | SrcMem | NoAccess),
 	/* 0x20 - 0x2F */

arch/x86/kvm/hyperv.c

@@ -29,6 +29,7 @@
 #include <linux/kvm_host.h>
 #include <linux/highmem.h>
 #include <linux/sched/cputime.h>
+#include <linux/eventfd.h>
 
 #include <asm/apicdef.h>
 #include <trace/events/kvm.h>
@@ -74,13 +75,38 @@ static bool synic_has_vector_auto_eoi(struct kvm_vcpu_hv_synic *synic,
 	return false;
 }
 
+static void synic_update_vector(struct kvm_vcpu_hv_synic *synic,
+				int vector)
+{
+	if (vector < HV_SYNIC_FIRST_VALID_VECTOR)
+		return;
+
+	if (synic_has_vector_connected(synic, vector))
+		__set_bit(vector, synic->vec_bitmap);
+	else
+		__clear_bit(vector, synic->vec_bitmap);
+
+	if (synic_has_vector_auto_eoi(synic, vector))
+		__set_bit(vector, synic->auto_eoi_bitmap);
+	else
+		__clear_bit(vector, synic->auto_eoi_bitmap);
+}
+
 static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint,
 			  u64 data, bool host)
 {
-	int vector;
+	int vector, old_vector;
+	bool masked;
 
 	vector = data & HV_SYNIC_SINT_VECTOR_MASK;
-	if (vector < 16 && !host)
+	masked = data & HV_SYNIC_SINT_MASKED;
+
+	/*
+	 * Valid vectors are 16-255, however, nested Hyper-V attempts to write
+	 * default '0x10000' value on boot and this should not #GP. We need to
+	 * allow zero-initing the register from host as well.
+	 */
+	if (vector < HV_SYNIC_FIRST_VALID_VECTOR && !host && !masked)
 		return 1;
 	/*
 	 * Guest may configure multiple SINTs to use the same vector, so
@@ -88,18 +114,13 @@ static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint,
 	 * bitmap of vectors with auto-eoi behavior.  The bitmaps are
 	 * updated here, and atomically queried on fast paths.
 	 */
+	old_vector = synic_read_sint(synic, sint) & HV_SYNIC_SINT_VECTOR_MASK;
 
 	atomic64_set(&synic->sint[sint], data);
 
-	if (synic_has_vector_connected(synic, vector))
-		__set_bit(vector, synic->vec_bitmap);
-	else
-		__clear_bit(vector, synic->vec_bitmap);
+	synic_update_vector(synic, old_vector);
 
-	if (synic_has_vector_auto_eoi(synic, vector))
-		__set_bit(vector, synic->auto_eoi_bitmap);
-	else
-		__clear_bit(vector, synic->auto_eoi_bitmap);
+	synic_update_vector(synic, vector);
 
 	/* Load SynIC vectors into EOI exit bitmap */
 	kvm_make_request(KVM_REQ_SCAN_IOAPIC, synic_to_vcpu(synic));
@@ -736,6 +757,9 @@ static bool kvm_hv_msr_partition_wide(u32 msr)
 	case HV_X64_MSR_CRASH_CTL:
 	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
 	case HV_X64_MSR_RESET:
+	case HV_X64_MSR_REENLIGHTENMENT_CONTROL:
+	case HV_X64_MSR_TSC_EMULATION_CONTROL:
+	case HV_X64_MSR_TSC_EMULATION_STATUS:
 		r = true;
 		break;
 	}
@@ -981,6 +1005,15 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
 			kvm_make_request(KVM_REQ_HV_RESET, vcpu);
 		}
 		break;
+	case HV_X64_MSR_REENLIGHTENMENT_CONTROL:
+		hv->hv_reenlightenment_control = data;
+		break;
+	case HV_X64_MSR_TSC_EMULATION_CONTROL:
+		hv->hv_tsc_emulation_control = data;
+		break;
+	case HV_X64_MSR_TSC_EMULATION_STATUS:
+		hv->hv_tsc_emulation_status = data;
+		break;
 	default:
 		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
 			    msr, data);
@@ -1009,17 +1042,17 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 			return 1;
 		hv->vp_index = (u32)data;
 		break;
-	case HV_X64_MSR_APIC_ASSIST_PAGE: {
+	case HV_X64_MSR_VP_ASSIST_PAGE: {
 		u64 gfn;
 		unsigned long addr;
 
-		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
+		if (!(data & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE)) {
 			hv->hv_vapic = data;
 			if (kvm_lapic_enable_pv_eoi(vcpu, 0))
 				return 1;
 			break;
 		}
-		gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
+		gfn = data >> HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT;
 		addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
 		if (kvm_is_error_hva(addr))
 			return 1;
@@ -1105,6 +1138,15 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case HV_X64_MSR_RESET:
 		data = 0;
 		break;
+	case HV_X64_MSR_REENLIGHTENMENT_CONTROL:
+		data = hv->hv_reenlightenment_control;
+		break;
+	case HV_X64_MSR_TSC_EMULATION_CONTROL:
+		data = hv->hv_tsc_emulation_control;
+		break;
+	case HV_X64_MSR_TSC_EMULATION_STATUS:
+		data = hv->hv_tsc_emulation_status;
+		break;
 	default:
 		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
 		return 1;
@@ -1129,7 +1171,7 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 		return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
 	case HV_X64_MSR_TPR:
 		return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
-	case HV_X64_MSR_APIC_ASSIST_PAGE:
+	case HV_X64_MSR_VP_ASSIST_PAGE:
 		data = hv->hv_vapic;
 		break;
 	case HV_X64_MSR_VP_RUNTIME:
@@ -1226,10 +1268,47 @@ static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param)
+{
+	struct eventfd_ctx *eventfd;
+
+	if (unlikely(!fast)) {
+		int ret;
+		gpa_t gpa = param;
+
+		if ((gpa & (__alignof__(param) - 1)) ||
+		    offset_in_page(gpa) + sizeof(param) > PAGE_SIZE)
+			return HV_STATUS_INVALID_ALIGNMENT;
+
+		ret = kvm_vcpu_read_guest(vcpu, gpa, &param, sizeof(param));
+		if (ret < 0)
+			return HV_STATUS_INVALID_ALIGNMENT;
+	}
+
+	/*
+	 * Per spec, bits 32-47 contain the extra "flag number".  However, we
+	 * have no use for it, and in all known usecases it is zero, so just
+	 * report lookup failure if it isn't.
+	 */
+	if (param & 0xffff00000000ULL)
+		return HV_STATUS_INVALID_PORT_ID;
+	/* remaining bits are reserved-zero */
+	if (param & ~KVM_HYPERV_CONN_ID_MASK)
+		return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
+	/* conn_to_evt is protected by vcpu->kvm->srcu */
+	eventfd = idr_find(&vcpu->kvm->arch.hyperv.conn_to_evt, param);
+	if (!eventfd)
+		return HV_STATUS_INVALID_PORT_ID;
+
+	eventfd_signal(eventfd, 1);
+	return HV_STATUS_SUCCESS;
+}
+
 int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 {
-	u64 param, ingpa, outgpa, ret;
-	uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
+	u64 param, ingpa, outgpa, ret = HV_STATUS_SUCCESS;
+	uint16_t code, rep_idx, rep_cnt;
 	bool fast, longmode;
 
 	/*
@@ -1268,7 +1347,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 
 	/* Hypercall continuation is not supported yet */
 	if (rep_cnt || rep_idx) {
-		res = HV_STATUS_INVALID_HYPERCALL_CODE;
+		ret = HV_STATUS_INVALID_HYPERCALL_CODE;
 		goto set_result;
 	}
 
@@ -1276,11 +1355,15 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	case HVCALL_NOTIFY_LONG_SPIN_WAIT:
 		kvm_vcpu_on_spin(vcpu, true);
 		break;
-	case HVCALL_POST_MESSAGE:
 	case HVCALL_SIGNAL_EVENT:
+		ret = kvm_hvcall_signal_event(vcpu, fast, ingpa);
+		if (ret != HV_STATUS_INVALID_PORT_ID)
+			break;
+		/* maybe userspace knows this conn_id: fall through */
+	case HVCALL_POST_MESSAGE:
 		/* don't bother userspace if it has no way to handle it */
 		if (!vcpu_to_synic(vcpu)->active) {
-			res = HV_STATUS_INVALID_HYPERCALL_CODE;
+			ret = HV_STATUS_INVALID_HYPERCALL_CODE;
 			break;
 		}
 		vcpu->run->exit_reason = KVM_EXIT_HYPERV;
@@ -1292,12 +1375,79 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 				kvm_hv_hypercall_complete_userspace;
 		return 0;
 	default:
-		res = HV_STATUS_INVALID_HYPERCALL_CODE;
+		ret = HV_STATUS_INVALID_HYPERCALL_CODE;
 		break;
 	}
 
 set_result:
-	ret = res | (((u64)rep_done & 0xfff) << 32);
 	kvm_hv_hypercall_set_result(vcpu, ret);
 	return 1;
 }
+
+void kvm_hv_init_vm(struct kvm *kvm)
+{
+	mutex_init(&kvm->arch.hyperv.hv_lock);
+	idr_init(&kvm->arch.hyperv.conn_to_evt);
+}
+
+void kvm_hv_destroy_vm(struct kvm *kvm)
+{
+	struct eventfd_ctx *eventfd;
+	int i;
+
+	idr_for_each_entry(&kvm->arch.hyperv.conn_to_evt, eventfd, i)
+		eventfd_ctx_put(eventfd);
+	idr_destroy(&kvm->arch.hyperv.conn_to_evt);
+}
+
+static int kvm_hv_eventfd_assign(struct kvm *kvm, u32 conn_id, int fd)
+{
+	struct kvm_hv *hv = &kvm->arch.hyperv;
+	struct eventfd_ctx *eventfd;
+	int ret;
+
+	eventfd = eventfd_ctx_fdget(fd);
+	if (IS_ERR(eventfd))
+		return PTR_ERR(eventfd);
+
+	mutex_lock(&hv->hv_lock);
+	ret = idr_alloc(&hv->conn_to_evt, eventfd, conn_id, conn_id + 1,
+			GFP_KERNEL);
+	mutex_unlock(&hv->hv_lock);
+
+	if (ret >= 0)
+		return 0;
+
+	if (ret == -ENOSPC)
+		ret = -EEXIST;
+	eventfd_ctx_put(eventfd);
+	return ret;
+}
+
+static int kvm_hv_eventfd_deassign(struct kvm *kvm, u32 conn_id)
+{
+	struct kvm_hv *hv = &kvm->arch.hyperv;
+	struct eventfd_ctx *eventfd;
+
+	mutex_lock(&hv->hv_lock);
+	eventfd = idr_remove(&hv->conn_to_evt, conn_id);
+	mutex_unlock(&hv->hv_lock);
+
+	if (!eventfd)
+		return -ENOENT;
+
+	synchronize_srcu(&kvm->srcu);
+	eventfd_ctx_put(eventfd);
+	return 0;
+}
+
+int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args)
+{
+	if ((args->flags & ~KVM_HYPERV_EVENTFD_DEASSIGN) ||
+	    (args->conn_id & ~KVM_HYPERV_CONN_ID_MASK))
+		return -EINVAL;
+
+	if (args->flags == KVM_HYPERV_EVENTFD_DEASSIGN)
+		return kvm_hv_eventfd_deassign(kvm, args->conn_id);
+	return kvm_hv_eventfd_assign(kvm, args->conn_id, args->fd);
+}

arch/x86/kvm/hyperv.h

@@ -88,4 +88,8 @@ void kvm_hv_process_stimers(struct kvm_vcpu *vcpu);
 void kvm_hv_setup_tsc_page(struct kvm *kvm,
 			   struct pvclock_vcpu_time_info *hv_clock);
 
+void kvm_hv_init_vm(struct kvm *kvm);
+void kvm_hv_destroy_vm(struct kvm *kvm);
+int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args);
+
 #endif

arch/x86/kvm/irq.c

@@ -73,8 +73,19 @@ static int kvm_cpu_has_extint(struct kvm_vcpu *v)
  */
 int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
 {
+	/*
+	 * FIXME: interrupt.injected represents an interrupt that it's
+	 * side-effects have already been applied (e.g. bit from IRR
+	 * already moved to ISR). Therefore, it is incorrect to rely
+	 * on interrupt.injected to know if there is a pending
+	 * interrupt in the user-mode LAPIC.
+	 * This leads to nVMX/nSVM not be able to distinguish
+	 * if it should exit from L2 to L1 on EXTERNAL_INTERRUPT on
+	 * pending interrupt or should re-inject an injected
+	 * interrupt.
+	 */
 	if (!lapic_in_kernel(v))
-		return v->arch.interrupt.pending;
+		return v->arch.interrupt.injected;
 
 	if (kvm_cpu_has_extint(v))
 		return 1;
@@ -91,8 +102,19 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
  */
 int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
 {
+	/*
+	 * FIXME: interrupt.injected represents an interrupt that it's
+	 * side-effects have already been applied (e.g. bit from IRR
+	 * already moved to ISR). Therefore, it is incorrect to rely
+	 * on interrupt.injected to know if there is a pending
+	 * interrupt in the user-mode LAPIC.
+	 * This leads to nVMX/nSVM not be able to distinguish
+	 * if it should exit from L2 to L1 on EXTERNAL_INTERRUPT on
+	 * pending interrupt or should re-inject an injected
+	 * interrupt.
+	 */
 	if (!lapic_in_kernel(v))
-		return v->arch.interrupt.pending;
+		return v->arch.interrupt.injected;
 
 	if (kvm_cpu_has_extint(v))
 		return 1;

arch/x86/kvm/kvm_cache_regs.h

@@ -41,7 +41,7 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index)
 
 	if (!test_bit(VCPU_EXREG_PDPTR,
 		      (unsigned long *)&vcpu->arch.regs_avail))
-		kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_PDPTR);
+		kvm_x86_ops->cache_reg(vcpu, (enum kvm_reg)VCPU_EXREG_PDPTR);
 
 	return vcpu->arch.walk_mmu->pdptrs[index];
 }
@@ -93,6 +93,11 @@ static inline void enter_guest_mode(struct kvm_vcpu *vcpu)
 static inline void leave_guest_mode(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hflags &= ~HF_GUEST_MASK;
+
+	if (vcpu->arch.load_eoi_exitmap_pending) {
+		vcpu->arch.load_eoi_exitmap_pending = false;
+		kvm_make_request(KVM_REQ_LOAD_EOI_EXITMAP, vcpu);
+	}
 }
 
 static inline bool is_guest_mode(struct kvm_vcpu *vcpu)

arch/x86/kvm/lapic.c

@@ -321,8 +321,16 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu)
 	if (!lapic_in_kernel(vcpu))
 		return;
 
+	/*
+	 * KVM emulates 82093AA datasheet (with in-kernel IOAPIC implementation)
+	 * which doesn't have EOI register; Some buggy OSes (e.g. Windows with
+	 * Hyper-V role) disable EOI broadcast in lapic not checking for IOAPIC
+	 * version first and level-triggered interrupts never get EOIed in
+	 * IOAPIC.
+	 */
 	feat = kvm_find_cpuid_entry(apic->vcpu, 0x1, 0);
-	if (feat && (feat->ecx & (1 << (X86_FEATURE_X2APIC & 31))))
+	if (feat && (feat->ecx & (1 << (X86_FEATURE_X2APIC & 31))) &&
+	    !ioapic_in_kernel(vcpu->kvm))
 		v |= APIC_LVR_DIRECTED_EOI;
 	kvm_lapic_set_reg(apic, APIC_LVR, v);
 }

arch/x86/kvm/lapic.h

@@ -109,7 +109,7 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 
 static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE;
+	return vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
 }
 
 int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);

arch/x86/kvm/mmu.c

@@ -3031,7 +3031,7 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
 		return RET_PF_RETRY;
 	}
 
-	return RET_PF_EMULATE;
+	return -EFAULT;
 }
 
 static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,