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

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

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

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

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

  MIPS:
     Bugfixes.

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

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

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

  Powerpc:
     Nothing yet.

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

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

16 files changed, 189 insertions, 11 deletions

diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 62167090937d..92bbae381598 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -96,6 +96,7 @@
 #define ESR_ELx_COND_SHIFT	(20)
 #define ESR_ELx_COND_MASK	(UL(0xF) << ESR_ELx_COND_SHIFT)
 #define ESR_ELx_WFx_ISS_WFE	(UL(1) << 0)
+#define ESR_ELx_xVC_IMM_MASK	((1UL << 16) - 1)
 
 #ifndef __ASSEMBLY__
 #include <asm/types.h>
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 483842180f8f..4f7310fa77f0 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -126,6 +126,7 @@ extern char __kvm_hyp_vector[];
 
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
+extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 0163b5775ca5..17e92f05b1fe 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -29,6 +29,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
 #include <asm/ptrace.h>
+#include <asm/cputype.h>
 
 unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num);
 unsigned long *vcpu_spsr32(const struct kvm_vcpu *vcpu);
@@ -140,6 +141,11 @@ static inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu)
 	return ((phys_addr_t)vcpu->arch.fault.hpfar_el2 & HPFAR_MASK) << 8;
 }
 
+static inline u32 kvm_vcpu_hvc_get_imm(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_xVC_IMM_MASK;
+}
+
 static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV);
@@ -201,9 +207,9 @@ static inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC_TYPE;
 }
 
-static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu)
+static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
 {
-	return vcpu_sys_reg(vcpu, MPIDR_EL1);
+	return vcpu_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
 }
 
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index acd101a9014d..8ac3c70fe3c6 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -59,6 +59,9 @@ struct kvm_arch {
 	/* VTTBR value associated with above pgd and vmid */
 	u64    vttbr;
 
+	/* The maximum number of vCPUs depends on the used GIC model */
+	int max_vcpus;
+
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
 
@@ -159,6 +162,7 @@ struct kvm_vm_stat {
 };
 
 struct kvm_vcpu_stat {
+	u32 halt_successful_poll;
 	u32 halt_wakeup;
 };
 
@@ -196,6 +200,7 @@ struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
 
 u64 kvm_call_hyp(void *hypfn, ...);
 void force_vm_exit(const cpumask_t *mask);
+void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
 
 int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		int exception_index);
@@ -203,6 +208,8 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
+struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
+
 static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
 				       phys_addr_t pgd_ptr,
 				       unsigned long hyp_stack_ptr,
diff --git a/arch/arm64/include/asm/kvm_mmio.h b/arch/arm64/include/asm/kvm_mmio.h
index fc2f689c0694..9f52beb7cb13 100644
--- a/arch/arm64/include/asm/kvm_mmio.h
+++ b/arch/arm64/include/asm/kvm_mmio.h
@@ -40,6 +40,7 @@ struct kvm_exit_mmio {
 	u8		data[8];
 	u32		len;
 	bool		is_write;
+	void		*private;
 };
 
 static inline void kvm_prepare_mmio(struct kvm_run *run,
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index adcf49547301..6458b5373142 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -118,6 +118,27 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 	pmd_val(*pmd) |= PMD_S2_RDWR;
 }
 
+static inline void kvm_set_s2pte_readonly(pte_t *pte)
+{
+	pte_val(*pte) = (pte_val(*pte) & ~PTE_S2_RDWR) | PTE_S2_RDONLY;
+}
+
+static inline bool kvm_s2pte_readonly(pte_t *pte)
+{
+	return (pte_val(*pte) & PTE_S2_RDWR) == PTE_S2_RDONLY;
+}
+
+static inline void kvm_set_s2pmd_readonly(pmd_t *pmd)
+{
+	pmd_val(*pmd) = (pmd_val(*pmd) & ~PMD_S2_RDWR) | PMD_S2_RDONLY;
+}
+
+static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
+{
+	return (pmd_val(*pmd) & PMD_S2_RDWR) == PMD_S2_RDONLY;
+}
+
+
 #define kvm_pgd_addr_end(addr, end)	pgd_addr_end(addr, end)
 #define kvm_pud_addr_end(addr, end)	pud_addr_end(addr, end)
 #define kvm_pmd_addr_end(addr, end)	pmd_addr_end(addr, end)
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 88174e0bfafe..5f930cc9ea83 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -119,6 +119,7 @@
 #define PTE_S2_RDONLY		(_AT(pteval_t, 1) << 6)   /* HAP[2:1] */
 #define PTE_S2_RDWR		(_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
 
+#define PMD_S2_RDONLY		(_AT(pmdval_t, 1) << 6)   /* HAP[2:1] */
 #define PMD_S2_RDWR		(_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
 
 /*
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 8e38878c87c6..3ef77a466018 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -78,6 +78,13 @@ struct kvm_regs {
 #define KVM_VGIC_V2_DIST_SIZE		0x1000
 #define KVM_VGIC_V2_CPU_SIZE		0x2000
 
+/* Supported VGICv3 address types  */
+#define KVM_VGIC_V3_ADDR_TYPE_DIST	2
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
+
+#define KVM_VGIC_V3_DIST_SIZE		SZ_64K
+#define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
+
 #define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
 #define KVM_ARM_VCPU_EL1_32BIT		1 /* CPU running a 32bit VM */
 #define KVM_ARM_VCPU_PSCI_0_2		2 /* CPU uses PSCI v0.2 */
@@ -161,6 +168,8 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
 #define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
 #define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
+#define KVM_DEV_ARM_VGIC_GRP_CTRL	4
+#define   KVM_DEV_ARM_VGIC_CTRL_INIT	0
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index a2ae19403abb..f7fa65d4c352 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -140,6 +140,7 @@ int main(void)
   DEFINE(VGIC_V2_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr));
   DEFINE(VGIC_V2_CPU_APR,	offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
   DEFINE(VGIC_V2_CPU_LR,	offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
+  DEFINE(VGIC_V3_CPU_SRE,	offsetof(struct vgic_cpu, vgic_v3.vgic_sre));
   DEFINE(VGIC_V3_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v3.vgic_hcr));
   DEFINE(VGIC_V3_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v3.vgic_vmcr));
   DEFINE(VGIC_V3_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v3.vgic_misr));
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index b334084d3675..f5590c81d95f 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -22,10 +22,12 @@ config KVM
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
+	select HAVE_KVM_ARCH_TLB_FLUSH_ALL
 	select KVM_MMIO
 	select KVM_ARM_HOST
 	select KVM_ARM_VGIC
 	select KVM_ARM_TIMER
+	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select SRCU
 	---help---
 	  Support hosting virtualized guest machines.
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 32a096174b94..4e6e09ee4033 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -21,7 +21,9 @@ kvm-$(CONFIG_KVM_ARM_HOST) += guest.o reset.o sys_regs.o sys_regs_generic_v8.o
 
 kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o
 kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2-emul.o
 kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v2-switch.o
 kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v3.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v3-emul.o
 kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v3-switch.o
 kvm-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 29b184a8f3f8..524fa25671fc 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -28,12 +28,18 @@
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_psci.h>
 
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
 typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
 
 static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	int ret;
 
+	trace_kvm_hvc_arm64(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
+			    kvm_vcpu_hvc_get_imm(vcpu));
+
 	ret = kvm_psci_call(vcpu);
 	if (ret < 0) {
 		kvm_inject_undefined(vcpu);
@@ -63,10 +69,13 @@ static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
  */
 static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE)
+	if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
+		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
 		kvm_vcpu_on_spin(vcpu);
-	else
+	} else {
+		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false);
 		kvm_vcpu_block(vcpu);
+	}
 
 	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
 
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 9bff671cc561..5befd010e232 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -1032,6 +1032,28 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 	ret
 ENDPROC(__kvm_tlb_flush_vmid_ipa)
 
+/**
+ * void __kvm_tlb_flush_vmid(struct kvm *kvm) - Flush per-VMID TLBs
+ * @struct kvm *kvm - pointer to kvm structure
+ *
+ * Invalidates all Stage 1 and 2 TLB entries for current VMID.
+ */
+ENTRY(__kvm_tlb_flush_vmid)
+	dsb     ishst
+
+	kern_hyp_va     x0
+	ldr     x2, [x0, #KVM_VTTBR]
+	msr     vttbr_el2, x2
+	isb
+
+	tlbi    vmalls12e1is
+	dsb     ish
+	isb
+
+	msr     vttbr_el2, xzr
+	ret
+ENDPROC(__kvm_tlb_flush_vmid)
+
 ENTRY(__kvm_flush_vm_context)
 	dsb	ishst
 	tlbi	alle1is
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index b96afdf6cee4..c370b4014799 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -113,6 +113,27 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+/*
+ * Trap handler for the GICv3 SGI generation system register.
+ * Forward the request to the VGIC emulation.
+ * The cp15_64 code makes sure this automatically works
+ * for both AArch64 and AArch32 accesses.
+ */
+static bool access_gic_sgi(struct kvm_vcpu *vcpu,
+			   const struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	u64 val;
+
+	if (!p->is_write)
+		return read_from_write_only(vcpu, p);
+
+	val = *vcpu_reg(vcpu, p->Rt);
+	vgic_v3_dispatch_sgi(vcpu, val);
+
+	return true;
+}
+
 static bool trap_raz_wi(struct kvm_vcpu *vcpu,
 			const struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
@@ -200,10 +221,19 @@ static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 
 static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
+	u64 mpidr;
+
 	/*
-	 * Simply map the vcpu_id into the Aff0 field of the MPIDR.
+	 * Map the vcpu_id into the first three affinity level fields of
+	 * the MPIDR. We limit the number of VCPUs in level 0 due to a
+	 * limitation to 16 CPUs in that level in the ICC_SGIxR registers
+	 * of the GICv3 to be able to address each CPU directly when
+	 * sending IPIs.
 	 */
-	vcpu_sys_reg(vcpu, MPIDR_EL1) = (1UL << 31) | (vcpu->vcpu_id & 0xff);
+	mpidr = (vcpu->vcpu_id & 0x0f) << MPIDR_LEVEL_SHIFT(0);
+	mpidr |= ((vcpu->vcpu_id >> 4) & 0xff) << MPIDR_LEVEL_SHIFT(1);
+	mpidr |= ((vcpu->vcpu_id >> 12) & 0xff) << MPIDR_LEVEL_SHIFT(2);
+	vcpu_sys_reg(vcpu, MPIDR_EL1) = (1ULL << 31) | mpidr;
 }
 
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
@@ -373,6 +403,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b0000), Op2(0b000),
 	  NULL, reset_val, VBAR_EL1, 0 },
 
+	/* ICC_SGI1R_EL1 */
+	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1011), Op2(0b101),
+	  access_gic_sgi },
 	/* ICC_SRE_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1100), Op2(0b101),
 	  trap_raz_wi },
@@ -605,6 +638,8 @@ static const struct sys_reg_desc cp14_64_regs[] = {
  * register).
  */
 static const struct sys_reg_desc cp15_regs[] = {
+	{ Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi },
+
 	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, c1_SCTLR },
 	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
 	{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
@@ -652,6 +687,7 @@ static const struct sys_reg_desc cp15_regs[] = {
 
 static const struct sys_reg_desc cp15_64_regs[] = {
 	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+	{ Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi },
 	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
 };
 
diff --git a/arch/arm64/kvm/trace.h b/arch/arm64/kvm/trace.h
new file mode 100644
index 000000000000..157416e963f2
--- /dev/null
+++ b/arch/arm64/kvm/trace.h
@@ -0,0 +1,55 @@
+#if !defined(_TRACE_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_ARM64_KVM_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+
+TRACE_EVENT(kvm_wfx_arm64,
+	TP_PROTO(unsigned long vcpu_pc, bool is_wfe),
+	TP_ARGS(vcpu_pc, is_wfe),
+
+	TP_STRUCT__entry(
+		__field(unsigned long,	vcpu_pc)
+		__field(bool,		is_wfe)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc = vcpu_pc;
+		__entry->is_wfe  = is_wfe;
+	),
+
+	TP_printk("guest executed wf%c at: 0x%08lx",
+		  __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc)
+);
+
+TRACE_EVENT(kvm_hvc_arm64,
+	TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm),
+	TP_ARGS(vcpu_pc, r0, imm),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, vcpu_pc)
+		__field(unsigned long, r0)
+		__field(unsigned long, imm)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc = vcpu_pc;
+		__entry->r0 = r0;
+		__entry->imm = imm;
+	),
+
+	TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx)",
+		  __entry->vcpu_pc, __entry->r0, __entry->imm)
+);
+
+#endif /* _TRACE_ARM64_KVM_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/arch/arm64/kvm/vgic-v3-switch.S b/arch/arm64/kvm/vgic-v3-switch.S
index d16046999e06..617a012a0107 100644
--- a/arch/arm64/kvm/vgic-v3-switch.S
+++ b/arch/arm64/kvm/vgic-v3-switch.S
@@ -148,17 +148,18 @@
  * x0: Register pointing to VCPU struct
  */
 .macro	restore_vgic_v3_state
-	// Disable SRE_EL1 access. Necessary, otherwise
-	// ICH_VMCR_EL2.VFIQEn becomes one, and FIQ happens...
-	msr_s	ICC_SRE_EL1, xzr
-	isb
-
 	// Compute the address of struct vgic_cpu
 	add	x3, x0, #VCPU_VGIC_CPU
 
 	// Restore all interesting registers
 	ldr	w4, [x3, #VGIC_V3_CPU_HCR]
 	ldr	w5, [x3, #VGIC_V3_CPU_VMCR]
+	ldr	w25, [x3, #VGIC_V3_CPU_SRE]
+
+	msr_s	ICC_SRE_EL1, x25
+
+	// make sure SRE is valid before writing the other registers
+	isb
 
 	msr_s	ICH_HCR_EL2, x4
 	msr_s	ICH_VMCR_EL2, x5
@@ -244,9 +245,12 @@
 	dsb	sy
 
 	// Prevent the guest from touching the GIC system registers
+	// if SRE isn't enabled for GICv3 emulation
+	cbnz	x25, 1f
 	mrs_s	x5, ICC_SRE_EL2
 	and	x5, x5, #~ICC_SRE_EL2_ENABLE
 	msr_s	ICC_SRE_EL2, x5
+1:
 .endm
 
 ENTRY(__save_vgic_v3_state)