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

Pull kvm updates from Paolo Bonzini:
 "ARM:

   - Clean up vCPU targets, always returning generic v8 as the preferred
     target

   - Trap forwarding infrastructure for nested virtualization (used for
     traps that are taken from an L2 guest and are needed by the L1
     hypervisor)

   - FEAT_TLBIRANGE support to only invalidate specific ranges of
     addresses when collapsing a table PTE to a block PTE. This avoids
     that the guest refills the TLBs again for addresses that aren't
     covered by the table PTE.

   - Fix vPMU issues related to handling of PMUver.

   - Don't unnecessary align non-stack allocations in the EL2 VA space

   - Drop HCR_VIRT_EXCP_MASK, which was never used...

   - Don't use smp_processor_id() in kvm_arch_vcpu_load(), but the cpu
     parameter instead

   - Drop redundant call to kvm_set_pfn_accessed() in user_mem_abort()

   - Remove prototypes without implementations

  RISC-V:

   - Zba, Zbs, Zicntr, Zicsr, Zifencei, and Zihpm support for guest

   - Added ONE_REG interface for SATP mode

   - Added ONE_REG interface to enable/disable multiple ISA extensions

   - Improved error codes returned by ONE_REG interfaces

   - Added KVM_GET_REG_LIST ioctl() implementation for KVM RISC-V

   - Added get-reg-list selftest for KVM RISC-V

  s390:

   - PV crypto passthrough enablement (Tony, Steffen, Viktor, Janosch)

     Allows a PV guest to use crypto cards. Card access is governed by
     the firmware and once a crypto queue is "bound" to a PV VM every
     other entity (PV or not) looses access until it is not bound
     anymore. Enablement is done via flags when creating the PV VM.

   - Guest debug fixes (Ilya)

  x86:

   - Clean up KVM's handling of Intel architectural events

   - Intel bugfixes

   - Add support for SEV-ES DebugSwap, allowing SEV-ES guests to use
     debug registers and generate/handle #DBs

   - Clean up LBR virtualization code

   - Fix a bug where KVM fails to set the target pCPU during an IRTE
     update

   - Fix fatal bugs in SEV-ES intrahost migration

   - Fix a bug where the recent (architecturally correct) change to
     reinject #BP and skip INT3 broke SEV guests (can't decode INT3 to
     skip it)

   - Retry APIC map recalculation if a vCPU is added/enabled

   - Overhaul emergency reboot code to bring SVM up to par with VMX, tie
     the "emergency disabling" behavior to KVM actually being loaded,
     and move all of the logic within KVM

   - Fix user triggerable WARNs in SVM where KVM incorrectly assumes the
     TSC ratio MSR cannot diverge from the default when TSC scaling is
     disabled up related code

   - Add a framework to allow "caching" feature flags so that KVM can
     check if the guest can use a feature without needing to search
     guest CPUID

   - Rip out the ancient MMU_DEBUG crud and replace the useful bits with
     CONFIG_KVM_PROVE_MMU

   - Fix KVM's handling of !visible guest roots to avoid premature
     triple fault injection

   - Overhaul KVM's page-track APIs, and KVMGT's usage, to reduce the
     API surface that is needed by external users (currently only
     KVMGT), and fix a variety of issues in the process

  Generic:

   - Wrap kvm_{gfn,hva}_range.pte in a union to allow mmu_notifier
     events to pass action specific data without needing to constantly
     update the main handlers.

   - Drop unused function declarations

  Selftests:

   - Add testcases to x86's sync_regs_test for detecting KVM TOCTOU bugs

   - Add support for printf() in guest code and covert all guest asserts
     to use printf-based reporting

   - Clean up the PMU event filter test and add new testcases

   - Include x86 selftests in the KVM x86 MAINTAINERS entry"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (279 commits)
  KVM: x86/mmu: Include mmu.h in spte.h
  KVM: x86/mmu: Use dummy root, backed by zero page, for !visible guest roots
  KVM: x86/mmu: Disallow guest from using !visible slots for page tables
  KVM: x86/mmu: Harden TDP MMU iteration against root w/o shadow page
  KVM: x86/mmu: Harden new PGD against roots without shadow pages
  KVM: x86/mmu: Add helper to convert root hpa to shadow page
  drm/i915/gvt: Drop final dependencies on KVM internal details
  KVM: x86/mmu: Handle KVM bookkeeping in page-track APIs, not callers
  KVM: x86/mmu: Drop @slot param from exported/external page-track APIs
  KVM: x86/mmu: Bug the VM if write-tracking is used but not enabled
  KVM: x86/mmu: Assert that correct locks are held for page write-tracking
  KVM: x86/mmu: Rename page-track APIs to reflect the new reality
  KVM: x86/mmu: Drop infrastructure for multiple page-track modes
  KVM: x86/mmu: Use page-track notifiers iff there are external users
  KVM: x86/mmu: Move KVM-only page-track declarations to internal header
  KVM: x86: Remove the unused page-track hook track_flush_slot()
  drm/i915/gvt: switch from ->track_flush_slot() to ->track_remove_region()
  KVM: x86: Add a new page-track hook to handle memslot deletion
  drm/i915/gvt: Don't bother removing write-protection on to-be-deleted slot
  KVM: x86: Reject memslot MOVE operations if KVMGT is attached
  ...

Documentation/virt/kvm/api.rst

@@ -2259,6 +2259,8 @@ Errors:
   EINVAL   invalid register ID, or no such register or used with VMs in
            protected virtualization mode on s390
   EPERM    (arm64) register access not allowed before vcpu finalization
+  EBUSY    (riscv) changing register value not allowed after the vcpu
+           has run at least once
   ======   ============================================================
 
 (These error codes are indicative only: do not rely on a specific error
@@ -3499,7 +3501,7 @@ VCPU matching underlying host.
 ---------------------
 
 :Capability: basic
-:Architectures: arm64, mips
+:Architectures: arm64, mips, riscv
 :Type: vcpu ioctl
 :Parameters: struct kvm_reg_list (in/out)
 :Returns: 0 on success; -1 on error

MAINTAINERS

@@ -11589,6 +11589,8 @@ F:	arch/x86/include/uapi/asm/svm.h
 F:	arch/x86/include/uapi/asm/vmx.h
 F:	arch/x86/kvm/
 F:	arch/x86/kvm/*/
+F:	tools/testing/selftests/kvm/*/x86_64/
+F:	tools/testing/selftests/kvm/x86_64/
 KERNFS
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>

arch/arm/include/asm/arm_pmuv3.h

@@ -227,6 +227,8 @@ static inline bool kvm_set_pmuserenr(u64 val)
 	return false;
 }
 
+static inline void kvm_vcpu_pmu_resync_el0(void) {}
+
 /* PMU Version in DFR Register */
 #define ARMV8_PMU_DFR_VER_NI        0
 #define ARMV8_PMU_DFR_VER_V3P4      0x5

arch/arm64/include/asm/kvm_arm.h

@@ -18,10 +18,19 @@
 #define HCR_DCT		(UL(1) << 57)
 #define HCR_ATA_SHIFT	56
 #define HCR_ATA		(UL(1) << HCR_ATA_SHIFT)
+#define HCR_TTLBOS	(UL(1) << 55)
+#define HCR_TTLBIS	(UL(1) << 54)
+#define HCR_ENSCXT	(UL(1) << 53)
+#define HCR_TOCU	(UL(1) << 52)
 #define HCR_AMVOFFEN	(UL(1) << 51)
+#define HCR_TICAB	(UL(1) << 50)
 #define HCR_TID4	(UL(1) << 49)
 #define HCR_FIEN	(UL(1) << 47)
 #define HCR_FWB		(UL(1) << 46)
+#define HCR_NV2		(UL(1) << 45)
+#define HCR_AT		(UL(1) << 44)
+#define HCR_NV1		(UL(1) << 43)
+#define HCR_NV		(UL(1) << 42)
 #define HCR_API		(UL(1) << 41)
 #define HCR_APK		(UL(1) << 40)
 #define HCR_TEA		(UL(1) << 37)
@@ -89,7 +98,6 @@
 			 HCR_BSU_IS | HCR_FB | HCR_TACR | \
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
 			 HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3)
-#define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
 #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA)
 #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
@@ -324,6 +332,47 @@
 				 BIT(18) |		\
 				 GENMASK(16, 15))
 
+/*
+ * FGT register definitions
+ *
+ * RES0 and polarity masks as of DDI0487J.a, to be updated as needed.
+ * We're not using the generated masks as they are usually ahead of
+ * the published ARM ARM, which we use as a reference.
+ *
+ * Once we get to a point where the two describe the same thing, we'll
+ * merge the definitions. One day.
+ */
+#define __HFGRTR_EL2_RES0	(GENMASK(63, 56) | GENMASK(53, 51))
+#define __HFGRTR_EL2_MASK	GENMASK(49, 0)
+#define __HFGRTR_EL2_nMASK	(GENMASK(55, 54) | BIT(50))
+
+#define __HFGWTR_EL2_RES0	(GENMASK(63, 56) | GENMASK(53, 51) |	\
+				 BIT(46) | BIT(42) | BIT(40) | BIT(28) | \
+				 GENMASK(26, 25) | BIT(21) | BIT(18) |	\
+				 GENMASK(15, 14) | GENMASK(10, 9) | BIT(2))
+#define __HFGWTR_EL2_MASK	GENMASK(49, 0)
+#define __HFGWTR_EL2_nMASK	(GENMASK(55, 54) | BIT(50))
+
+#define __HFGITR_EL2_RES0	GENMASK(63, 57)
+#define __HFGITR_EL2_MASK	GENMASK(54, 0)
+#define __HFGITR_EL2_nMASK	GENMASK(56, 55)
+
+#define __HDFGRTR_EL2_RES0	(BIT(49) | BIT(42) | GENMASK(39, 38) |	\
+				 GENMASK(21, 20) | BIT(8))
+#define __HDFGRTR_EL2_MASK	~__HDFGRTR_EL2_nMASK
+#define __HDFGRTR_EL2_nMASK	GENMASK(62, 59)
+
+#define __HDFGWTR_EL2_RES0	(BIT(63) | GENMASK(59, 58) | BIT(51) | BIT(47) | \
+				 BIT(43) | GENMASK(40, 38) | BIT(34) | BIT(30) | \
+				 BIT(22) | BIT(9) | BIT(6))
+#define __HDFGWTR_EL2_MASK	~__HDFGWTR_EL2_nMASK
+#define __HDFGWTR_EL2_nMASK	GENMASK(62, 60)
+
+/* Similar definitions for HCRX_EL2 */
+#define __HCRX_EL2_RES0		(GENMASK(63, 16) | GENMASK(13, 12))
+#define __HCRX_EL2_MASK		(0)
+#define __HCRX_EL2_nMASK	(GENMASK(15, 14) | GENMASK(4, 0))
+
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
 #define HPFAR_MASK	(~UL(0xf))
 /*

arch/arm64/include/asm/kvm_asm.h

@@ -70,6 +70,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa,
 	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa_nsh,
 	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid,
+	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_range,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context,
 	__KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff,
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr,
@@ -229,6 +230,8 @@ extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
 extern void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
 					 phys_addr_t ipa,
 					 int level);
+extern void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
+					phys_addr_t start, unsigned long pages);
 extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);

arch/arm64/include/asm/kvm_host.h

@@ -49,6 +49,7 @@
 #define KVM_REQ_RELOAD_GICv4	KVM_ARCH_REQ(4)
 #define KVM_REQ_RELOAD_PMU	KVM_ARCH_REQ(5)
 #define KVM_REQ_SUSPEND		KVM_ARCH_REQ(6)
+#define KVM_REQ_RESYNC_PMU_EL0	KVM_ARCH_REQ(7)
 
 #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
 				     KVM_DIRTY_LOG_INITIALLY_SET)
@@ -380,6 +381,7 @@ enum vcpu_sysreg {
 	CPTR_EL2,	/* Architectural Feature Trap Register (EL2) */
 	HSTR_EL2,	/* Hypervisor System Trap Register */
 	HACR_EL2,	/* Hypervisor Auxiliary Control Register */
+	HCRX_EL2,	/* Extended Hypervisor Configuration Register */
 	TTBR0_EL2,	/* Translation Table Base Register 0 (EL2) */
 	TTBR1_EL2,	/* Translation Table Base Register 1 (EL2) */
 	TCR_EL2,	/* Translation Control Register (EL2) */
@@ -400,6 +402,11 @@ enum vcpu_sysreg {
 	TPIDR_EL2,	/* EL2 Software Thread ID Register */
 	CNTHCTL_EL2,	/* Counter-timer Hypervisor Control register */
 	SP_EL2,		/* EL2 Stack Pointer */
+	HFGRTR_EL2,
+	HFGWTR_EL2,
+	HFGITR_EL2,
+	HDFGRTR_EL2,
+	HDFGWTR_EL2,
 	CNTHP_CTL_EL2,
 	CNTHP_CVAL_EL2,
 	CNTHV_CTL_EL2,
@@ -567,8 +574,7 @@ struct kvm_vcpu_arch {
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
-	/* Target CPU and feature flags */
-	int target;
+	/* feature flags */
 	DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);
 
 	/* Virtual SError ESR to restore when HCR_EL2.VSE is set */
@@ -669,6 +675,8 @@ struct kvm_vcpu_arch {
 #define VCPU_SVE_FINALIZED	__vcpu_single_flag(cflags, BIT(1))
 /* PTRAUTH exposed to guest */
 #define GUEST_HAS_PTRAUTH	__vcpu_single_flag(cflags, BIT(2))
+/* KVM_ARM_VCPU_INIT completed */
+#define VCPU_INITIALIZED	__vcpu_single_flag(cflags, BIT(3))
 
 /* Exception pending */
 #define PENDING_EXCEPTION	__vcpu_single_flag(iflags, BIT(0))
@@ -899,7 +907,6 @@ struct kvm_vcpu_stat {
 	u64 exits;
 };
 
-void kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
 int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
@@ -967,8 +974,6 @@ void kvm_arm_resume_guest(struct kvm *kvm);
 #define kvm_call_hyp_nvhe(f, ...) f(__VA_ARGS__)
 #endif /* __KVM_NVHE_HYPERVISOR__ */
 
-void force_vm_exit(const cpumask_t *mask);
-
 int handle_exit(struct kvm_vcpu *vcpu, int exception_index);
 void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index);
 
@@ -983,6 +988,7 @@ int kvm_handle_cp10_id(struct kvm_vcpu *vcpu);
 void kvm_reset_sys_regs(struct kvm_vcpu *vcpu);
 
 int __init kvm_sys_reg_table_init(void);
+int __init populate_nv_trap_config(void);
 
 bool lock_all_vcpus(struct kvm *kvm);
 void unlock_all_vcpus(struct kvm *kvm);
@@ -1049,8 +1055,6 @@ static inline bool kvm_system_needs_idmapped_vectors(void)
 	return cpus_have_const_cap(ARM64_SPECTRE_V3A);
 }
 
-void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu);
-
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 
@@ -1113,13 +1117,15 @@ int __init kvm_set_ipa_limit(void);
 #define __KVM_HAVE_ARCH_VM_ALLOC
 struct kvm *kvm_arch_alloc_vm(void);
 
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
+
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+
 static inline bool kvm_vm_is_protected(struct kvm *kvm)
 {
 	return false;
 }
 
-void kvm_init_protected_traps(struct kvm_vcpu *vcpu);
-
 int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature);
 bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
 

arch/arm64/include/asm/kvm_mmu.h

@@ -168,6 +168,7 @@ int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
 			   void __iomem **haddr);
 int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 			     void **haddr);
+int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr);
 void __init free_hyp_pgds(void);
 
 void stage2_unmap_vm(struct kvm *kvm);

arch/arm64/include/asm/kvm_nested.h

@@ -11,6 +11,8 @@ static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
 		test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features));
 }
 
+extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu);
+
 struct sys_reg_params;
 struct sys_reg_desc;
 

arch/arm64/include/asm/kvm_pgtable.h

@@ -746,4 +746,14 @@ enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte);
  *	   kvm_pgtable_prot format.
  */
 enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte);
+
+/**
+ * kvm_tlb_flush_vmid_range() - Invalidate/flush a range of TLB entries
+ *
+ * @mmu:	Stage-2 KVM MMU struct
+ * @addr:	The base Intermediate physical address from which to invalidate
+ * @size:	Size of the range from the base to invalidate
+ */
+void kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
+				phys_addr_t addr, size_t size);
 #endif	/* __ARM64_KVM_PGTABLE_H__ */

arch/arm64/include/asm/sysreg.h

@@ -124,6 +124,37 @@
 #define SYS_DC_CIGSW			sys_insn(1, 0, 7, 14, 4)
 #define SYS_DC_CIGDSW			sys_insn(1, 0, 7, 14, 6)
 
+#define SYS_IC_IALLUIS			sys_insn(1, 0, 7, 1, 0)
+#define SYS_IC_IALLU			sys_insn(1, 0, 7, 5, 0)
+#define SYS_IC_IVAU			sys_insn(1, 3, 7, 5, 1)
+
+#define SYS_DC_IVAC			sys_insn(1, 0, 7, 6, 1)
+#define SYS_DC_IGVAC			sys_insn(1, 0, 7, 6, 3)
+#define SYS_DC_IGDVAC			sys_insn(1, 0, 7, 6, 5)
+
+#define SYS_DC_CVAC			sys_insn(1, 3, 7, 10, 1)
+#define SYS_DC_CGVAC			sys_insn(1, 3, 7, 10, 3)
+#define SYS_DC_CGDVAC			sys_insn(1, 3, 7, 10, 5)
+
+#define SYS_DC_CVAU			sys_insn(1, 3, 7, 11, 1)
+
+#define SYS_DC_CVAP			sys_insn(1, 3, 7, 12, 1)
+#define SYS_DC_CGVAP			sys_insn(1, 3, 7, 12, 3)
+#define SYS_DC_CGDVAP			sys_insn(1, 3, 7, 12, 5)
+
+#define SYS_DC_CVADP			sys_insn(1, 3, 7, 13, 1)
+#define SYS_DC_CGVADP			sys_insn(1, 3, 7, 13, 3)
+#define SYS_DC_CGDVADP			sys_insn(1, 3, 7, 13, 5)
+
+#define SYS_DC_CIVAC			sys_insn(1, 3, 7, 14, 1)
+#define SYS_DC_CIGVAC			sys_insn(1, 3, 7, 14, 3)
+#define SYS_DC_CIGDVAC			sys_insn(1, 3, 7, 14, 5)
+
+/* Data cache zero operations */
+#define SYS_DC_ZVA			sys_insn(1, 3, 7, 4, 1)
+#define SYS_DC_GVA			sys_insn(1, 3, 7, 4, 3)
+#define SYS_DC_GZVA			sys_insn(1, 3, 7, 4, 4)
+
 /*
  * Automatically generated definitions for system registers, the
  * manual encodings below are in the process of being converted to
@@ -163,6 +194,82 @@
 #define SYS_DBGDTRTX_EL0		sys_reg(2, 3, 0, 5, 0)
 #define SYS_DBGVCR32_EL2		sys_reg(2, 4, 0, 7, 0)
 
+#define SYS_BRBINF_EL1(n)		sys_reg(2, 1, 8, (n & 15), (((n & 16) >> 2) | 0))
+#define SYS_BRBINFINJ_EL1		sys_reg(2, 1, 9, 1, 0)
+#define SYS_BRBSRC_EL1(n)		sys_reg(2, 1, 8, (n & 15), (((n & 16) >> 2) | 1))
+#define SYS_BRBSRCINJ_EL1		sys_reg(2, 1, 9, 1, 1)
+#define SYS_BRBTGT_EL1(n)		sys_reg(2, 1, 8, (n & 15), (((n & 16) >> 2) | 2))
+#define SYS_BRBTGTINJ_EL1		sys_reg(2, 1, 9, 1, 2)
+#define SYS_BRBTS_EL1			sys_reg(2, 1, 9, 0, 2)
+
+#define SYS_BRBCR_EL1			sys_reg(2, 1, 9, 0, 0)
+#define SYS_BRBFCR_EL1			sys_reg(2, 1, 9, 0, 1)
+#define SYS_BRBIDR0_EL1			sys_reg(2, 1, 9, 2, 0)
+
+#define SYS_TRCITECR_EL1		sys_reg(3, 0, 1, 2, 3)
+#define SYS_TRCACATR(m)			sys_reg(2, 1, 2, ((m & 7) << 1), (2 | (m >> 3)))
+#define SYS_TRCACVR(m)			sys_reg(2, 1, 2, ((m & 7) << 1), (0 | (m >> 3)))
+#define SYS_TRCAUTHSTATUS		sys_reg(2, 1, 7, 14, 6)
+#define SYS_TRCAUXCTLR			sys_reg(2, 1, 0, 6, 0)
+#define SYS_TRCBBCTLR			sys_reg(2, 1, 0, 15, 0)
+#define SYS_TRCCCCTLR			sys_reg(2, 1, 0, 14, 0)
+#define SYS_TRCCIDCCTLR0		sys_reg(2, 1, 3, 0, 2)
+#define SYS_TRCCIDCCTLR1		sys_reg(2, 1, 3, 1, 2)
+#define SYS_TRCCIDCVR(m)		sys_reg(2, 1, 3, ((m & 7) << 1), 0)
+#define SYS_TRCCLAIMCLR			sys_reg(2, 1, 7, 9, 6)
+#define SYS_TRCCLAIMSET			sys_reg(2, 1, 7, 8, 6)
+#define SYS_TRCCNTCTLR(m)		sys_reg(2, 1, 0, (4 | (m & 3)), 5)
+#define SYS_TRCCNTRLDVR(m)		sys_reg(2, 1, 0, (0 | (m & 3)), 5)
+#define SYS_TRCCNTVR(m)			sys_reg(2, 1, 0, (8 | (m & 3)), 5)
+#define SYS_TRCCONFIGR			sys_reg(2, 1, 0, 4, 0)
+#define SYS_TRCDEVARCH			sys_reg(2, 1, 7, 15, 6)
+#define SYS_TRCDEVID			sys_reg(2, 1, 7, 2, 7)
+#define SYS_TRCEVENTCTL0R		sys_reg(2, 1, 0, 8, 0)
+#define SYS_TRCEVENTCTL1R		sys_reg(2, 1, 0, 9, 0)
+#define SYS_TRCEXTINSELR(m)		sys_reg(2, 1, 0, (8 | (m & 3)), 4)
+#define SYS_TRCIDR0			sys_reg(2, 1, 0, 8, 7)
+#define SYS_TRCIDR10			sys_reg(2, 1, 0, 2, 6)
+#define SYS_TRCIDR11			sys_reg(2, 1, 0, 3, 6)
+#define SYS_TRCIDR12			sys_reg(2, 1, 0, 4, 6)
+#define SYS_TRCIDR13			sys_reg(2, 1, 0, 5, 6)
+#define SYS_TRCIDR1			sys_reg(2, 1, 0, 9, 7)
+#define SYS_TRCIDR2			sys_reg(2, 1, 0, 10, 7)
+#define SYS_TRCIDR3			sys_reg(2, 1, 0, 11, 7)
+#define SYS_TRCIDR4			sys_reg(2, 1, 0, 12, 7)
+#define SYS_TRCIDR5			sys_reg(2, 1, 0, 13, 7)
+#define SYS_TRCIDR6			sys_reg(2, 1, 0, 14, 7)
+#define SYS_TRCIDR7			sys_reg(2, 1, 0, 15, 7)
+#define SYS_TRCIDR8			sys_reg(2, 1, 0, 0, 6)
+#define SYS_TRCIDR9			sys_reg(2, 1, 0, 1, 6)
+#define SYS_TRCIMSPEC(m)		sys_reg(2, 1, 0, (m & 7), 7)
+#define SYS_TRCITEEDCR			sys_reg(2, 1, 0, 2, 1)
+#define SYS_TRCOSLSR			sys_reg(2, 1, 1, 1, 4)
+#define SYS_TRCPRGCTLR			sys_reg(2, 1, 0, 1, 0)
+#define SYS_TRCQCTLR			sys_reg(2, 1, 0, 1, 1)
+#define SYS_TRCRSCTLR(m)		sys_reg(2, 1, 1, (m & 15), (0 | (m >> 4)))
+#define SYS_TRCRSR			sys_reg(2, 1, 0, 10, 0)
+#define SYS_TRCSEQEVR(m)		sys_reg(2, 1, 0, (m & 3), 4)
+#define SYS_TRCSEQRSTEVR		sys_reg(2, 1, 0, 6, 4)
+#define SYS_TRCSEQSTR			sys_reg(2, 1, 0, 7, 4)
+#define SYS_TRCSSCCR(m)			sys_reg(2, 1, 1, (m & 7), 2)
+#define SYS_TRCSSCSR(m)			sys_reg(2, 1, 1, (8 | (m & 7)), 2)
+#define SYS_TRCSSPCICR(m)		sys_reg(2, 1, 1, (m & 7), 3)
+#define SYS_TRCSTALLCTLR		sys_reg(2, 1, 0, 11, 0)
+#define SYS_TRCSTATR			sys_reg(2, 1, 0, 3, 0)
+#define SYS_TRCSYNCPR			sys_reg(2, 1, 0, 13, 0)
+#define SYS_TRCTRACEIDR			sys_reg(2, 1, 0, 0, 1)
+#define SYS_TRCTSCTLR			sys_reg(2, 1, 0, 12, 0)
+#define SYS_TRCVICTLR			sys_reg(2, 1, 0, 0, 2)
+#define SYS_TRCVIIECTLR			sys_reg(2, 1, 0, 1, 2)
+#define SYS_TRCVIPCSSCTLR		sys_reg(2, 1, 0, 3, 2)
+#define SYS_TRCVISSCTLR			sys_reg(2, 1, 0, 2, 2)
+#define SYS_TRCVMIDCCTLR0		sys_reg(2, 1, 3, 2, 2)
+#define SYS_TRCVMIDCCTLR1		sys_reg(2, 1, 3, 3, 2)
+#define SYS_TRCVMIDCVR(m)		sys_reg(2, 1, 3, ((m & 7) << 1), 1)
+
+/* ETM */
+#define SYS_TRCOSLAR			sys_reg(2, 1, 1, 0, 4)
+
 #define SYS_MIDR_EL1			sys_reg(3, 0, 0, 0, 0)
 #define SYS_MPIDR_EL1			sys_reg(3, 0, 0, 0, 5)
 #define SYS_REVIDR_EL1			sys_reg(3, 0, 0, 0, 6)
@@ -203,8 +310,13 @@
 #define SYS_ERXCTLR_EL1			sys_reg(3, 0, 5, 4, 1)
 #define SYS_ERXSTATUS_EL1		sys_reg(3, 0, 5, 4, 2)
 #define SYS_ERXADDR_EL1			sys_reg(3, 0, 5, 4, 3)
+#define SYS_ERXPFGF_EL1			sys_reg(3, 0, 5, 4, 4)
+#define SYS_ERXPFGCTL_EL1		sys_reg(3, 0, 5, 4, 5)
+#define SYS_ERXPFGCDN_EL1		sys_reg(3, 0, 5, 4, 6)
 #define SYS_ERXMISC0_EL1		sys_reg(3, 0, 5, 5, 0)
 #define SYS_ERXMISC1_EL1		sys_reg(3, 0, 5, 5, 1)
+#define SYS_ERXMISC2_EL1		sys_reg(3, 0, 5, 5, 2)
+#define SYS_ERXMISC3_EL1		sys_reg(3, 0, 5, 5, 3)
 #define SYS_TFSR_EL1			sys_reg(3, 0, 5, 6, 0)
 #define SYS_TFSRE0_EL1			sys_reg(3, 0, 5, 6, 1)
 
@@ -275,6 +387,8 @@
 #define SYS_ICC_IGRPEN0_EL1		sys_reg(3, 0, 12, 12, 6)
 #define SYS_ICC_IGRPEN1_EL1		sys_reg(3, 0, 12, 12, 7)
 
+#define SYS_ACCDATA_EL1			sys_reg(3, 0, 13, 0, 5)
+
 #define SYS_CNTKCTL_EL1			sys_reg(3, 0, 14, 1, 0)
 
 #define SYS_AIDR_EL1			sys_reg(3, 1, 0, 0, 7)
@@ -383,8 +497,6 @@
 #define SYS_VTCR_EL2			sys_reg(3, 4, 2, 1, 2)
 
 #define SYS_TRFCR_EL2			sys_reg(3, 4, 1, 2, 1)
-#define SYS_HDFGRTR_EL2			sys_reg(3, 4, 3, 1, 4)
-#define SYS_HDFGWTR_EL2			sys_reg(3, 4, 3, 1, 5)
 #define SYS_HAFGRTR_EL2			sys_reg(3, 4, 3, 1, 6)
 #define SYS_SPSR_EL2			sys_reg(3, 4, 4, 0, 0)
 #define SYS_ELR_EL2			sys_reg(3, 4, 4, 0, 1)
@@ -478,6 +590,158 @@
 
 #define SYS_SP_EL2			sys_reg(3, 6,  4, 1, 0)
 
+/* AT instructions */
+#define AT_Op0 1
+#define AT_CRn 7
+
+#define OP_AT_S1E1R	sys_insn(AT_Op0, 0, AT_CRn, 8, 0)
+#define OP_AT_S1E1W	sys_insn(AT_Op0, 0, AT_CRn, 8, 1)
+#define OP_AT_S1E0R	sys_insn(AT_Op0, 0, AT_CRn, 8, 2)
+#define OP_AT_S1E0W	sys_insn(AT_Op0, 0, AT_CRn, 8, 3)
+#define OP_AT_S1E1RP	sys_insn(AT_Op0, 0, AT_CRn, 9, 0)
+#define OP_AT_S1E1WP	sys_insn(AT_Op0, 0, AT_CRn, 9, 1)
+#define OP_AT_S1E2R	sys_insn(AT_Op0, 4, AT_CRn, 8, 0)
+#define OP_AT_S1E2W	sys_insn(AT_Op0, 4, AT_CRn, 8, 1)
+#define OP_AT_S12E1R	sys_insn(AT_Op0, 4, AT_CRn, 8, 4)
+#define OP_AT_S12E1W	sys_insn(AT_Op0, 4, AT_CRn, 8, 5)
+#define OP_AT_S12E0R	sys_insn(AT_Op0, 4, AT_CRn, 8, 6)
+#define OP_AT_S12E0W	sys_insn(AT_Op0, 4, AT_CRn, 8, 7)
+
+/* TLBI instructions */
+#define OP_TLBI_VMALLE1OS		sys_insn(1, 0, 8, 1, 0)
+#define OP_TLBI_VAE1OS			sys_insn(1, 0, 8, 1, 1)
+#define OP_TLBI_ASIDE1OS		sys_insn(1, 0, 8, 1, 2)
+#define OP_TLBI_VAAE1OS			sys_insn(1, 0, 8, 1, 3)
+#define OP_TLBI_VALE1OS			sys_insn(1, 0, 8, 1, 5)
+#define OP_TLBI_VAALE1OS		sys_insn(1, 0, 8, 1, 7)
+#define OP_TLBI_RVAE1IS			sys_insn(1, 0, 8, 2, 1)
+#define OP_TLBI_RVAAE1IS		sys_insn(1, 0, 8, 2, 3)
+#define OP_TLBI_RVALE1IS		sys_insn(1, 0, 8, 2, 5)
+#define OP_TLBI_RVAALE1IS		sys_insn(1, 0, 8, 2, 7)
+#define OP_TLBI_VMALLE1IS		sys_insn(1, 0, 8, 3, 0)
+#define OP_TLBI_VAE1IS			sys_insn(1, 0, 8, 3, 1)
+#define OP_TLBI_ASIDE1IS		sys_insn(1, 0, 8, 3, 2)
+#define OP_TLBI_VAAE1IS			sys_insn(1, 0, 8, 3, 3)
+#define OP_TLBI_VALE1IS			sys_insn(1, 0, 8, 3, 5)
+#define OP_TLBI_VAALE1IS		sys_insn(1, 0, 8, 3, 7)
+#define OP_TLBI_RVAE1OS			sys_insn(1, 0, 8, 5, 1)
+#define OP_TLBI_RVAAE1OS		sys_insn(1, 0, 8, 5, 3)
+#define OP_TLBI_RVALE1OS		sys_insn(1, 0, 8, 5, 5)
+#define OP_TLBI_RVAALE1OS		sys_insn(1, 0, 8, 5, 7)
+#define OP_TLBI_RVAE1			sys_insn(1, 0, 8, 6, 1)
+#define OP_TLBI_RVAAE1			sys_insn(1, 0, 8, 6, 3)
+#define OP_TLBI_RVALE1			sys_insn(1, 0, 8, 6, 5)
+#define OP_TLBI_RVAALE1			sys_insn(1, 0, 8, 6, 7)
+#define OP_TLBI_VMALLE1			sys_insn(1, 0, 8, 7, 0)
+#define OP_TLBI_VAE1			sys_insn(1, 0, 8, 7, 1)
+#define OP_TLBI_ASIDE1			sys_insn(1, 0, 8, 7, 2)
+#define OP_TLBI_VAAE1			sys_insn(1, 0, 8, 7, 3)
+#define OP_TLBI_VALE1			sys_insn(1, 0, 8, 7, 5)
+#define OP_TLBI_VAALE1			sys_insn(1, 0, 8, 7, 7)
+#define OP_TLBI_VMALLE1OSNXS		sys_insn(1, 0, 9, 1, 0)
+#define OP_TLBI_VAE1OSNXS		sys_insn(1, 0, 9, 1, 1)
+#define OP_TLBI_ASIDE1OSNXS		sys_insn(1, 0, 9, 1, 2)
+#define OP_TLBI_VAAE1OSNXS		sys_insn(1, 0, 9, 1, 3)
+#define OP_TLBI_VALE1OSNXS		sys_insn(1, 0, 9, 1, 5)
+#define OP_TLBI_VAALE1OSNXS		sys_insn(1, 0, 9, 1, 7)
+#define OP_TLBI_RVAE1ISNXS		sys_insn(1, 0, 9, 2, 1)
+#define OP_TLBI_RVAAE1ISNXS		sys_insn(1, 0, 9, 2, 3)
+#define OP_TLBI_RVALE1ISNXS		sys_insn(1, 0, 9, 2, 5)
+#define OP_TLBI_RVAALE1ISNXS		sys_insn(1, 0, 9, 2, 7)
+#define OP_TLBI_VMALLE1ISNXS		sys_insn(1, 0, 9, 3, 0)
+#define OP_TLBI_VAE1ISNXS		sys_insn(1, 0, 9, 3, 1)
+#define OP_TLBI_ASIDE1ISNXS		sys_insn(1, 0, 9, 3, 2)
+#define OP_TLBI_VAAE1ISNXS		sys_insn(1, 0, 9, 3, 3)
+#define OP_TLBI_VALE1ISNXS		sys_insn(1, 0, 9, 3, 5)
+#define OP_TLBI_VAALE1ISNXS		sys_insn(1, 0, 9, 3, 7)
+#define OP_TLBI_RVAE1OSNXS		sys_insn(1, 0, 9, 5, 1)
+#define OP_TLBI_RVAAE1OSNXS		sys_insn(1, 0, 9, 5, 3)
+#define OP_TLBI_RVALE1OSNXS		sys_insn(1, 0, 9, 5, 5)
+#define OP_TLBI_RVAALE1OSNXS		sys_insn(1, 0, 9, 5, 7)
+#define OP_TLBI_RVAE1NXS		sys_insn(1, 0, 9, 6, 1)
+#define OP_TLBI_RVAAE1NXS		sys_insn(1, 0, 9, 6, 3)
+#define OP_TLBI_RVALE1NXS		sys_insn(1, 0, 9, 6, 5)
+#define OP_TLBI_RVAALE1NXS		sys_insn(1, 0, 9, 6, 7)
+#define OP_TLBI_VMALLE1NXS		sys_insn(1, 0, 9, 7, 0)
+#define OP_TLBI_VAE1NXS			sys_insn(1, 0, 9, 7, 1)
+#define OP_TLBI_ASIDE1NXS		sys_insn(1, 0, 9, 7, 2)
+#define OP_TLBI_VAAE1NXS		sys_insn(1, 0, 9, 7, 3)
+#define OP_TLBI_VALE1NXS		sys_insn(1, 0, 9, 7, 5)
+#define OP_TLBI_VAALE1NXS		sys_insn(1, 0, 9, 7, 7)
+#define OP_TLBI_IPAS2E1IS		sys_insn(1, 4, 8, 0, 1)
+#define OP_TLBI_RIPAS2E1IS		sys_insn(1, 4, 8, 0, 2)
+#define OP_TLBI_IPAS2LE1IS		sys_insn(1, 4, 8, 0, 5)
+#define OP_TLBI_RIPAS2LE1IS		sys_insn(1, 4, 8, 0, 6)
+#define OP_TLBI_ALLE2OS			sys_insn(1, 4, 8, 1, 0)
+#define OP_TLBI_VAE2OS			sys_insn(1, 4, 8, 1, 1)
+#define OP_TLBI_ALLE1OS			sys_insn(1, 4, 8, 1, 4)
+#define OP_TLBI_VALE2OS			sys_insn(1, 4, 8, 1, 5)
+#define OP_TLBI_VMALLS12E1OS		sys_insn(1, 4, 8, 1, 6)
+#define OP_TLBI_RVAE2IS			sys_insn(1, 4, 8, 2, 1)
+#define OP_TLBI_RVALE2IS		sys_insn(1, 4, 8, 2, 5)
+#define OP_TLBI_ALLE2IS			sys_insn(1, 4, 8, 3, 0)
+#define OP_TLBI_VAE2IS			sys_insn(1, 4, 8, 3, 1)
+#define OP_TLBI_ALLE1IS			sys_insn(1, 4, 8, 3, 4)
+#define OP_TLBI_VALE2IS			sys_insn(1, 4, 8, 3, 5)
+#define OP_TLBI_VMALLS12E1IS		sys_insn(1, 4, 8, 3, 6)
+#define OP_TLBI_IPAS2E1OS		sys_insn(1, 4, 8, 4, 0)
+#define OP_TLBI_IPAS2E1			sys_insn(1, 4, 8, 4, 1)
+#define OP_TLBI_RIPAS2E1		sys_insn(1, 4, 8, 4, 2)
+#define OP_TLBI_RIPAS2E1OS		sys_insn(1, 4, 8, 4, 3)
+#define OP_TLBI_IPAS2LE1OS		sys_insn(1, 4, 8, 4, 4)
+#define OP_TLBI_IPAS2LE1		sys_insn(1, 4, 8, 4, 5)
+#define OP_TLBI_RIPAS2LE1		sys_insn(1, 4, 8, 4, 6)
+#define OP_TLBI_RIPAS2LE1OS		sys_insn(1, 4, 8, 4, 7)
+#define OP_TLBI_RVAE2OS			sys_insn(1, 4, 8, 5, 1)
+#define OP_TLBI_RVALE2OS		sys_insn(1, 4, 8, 5, 5)
+#define OP_TLBI_RVAE2			sys_insn(1, 4, 8, 6, 1)
+#define OP_TLBI_RVALE2			sys_insn(1, 4, 8, 6, 5)
+#define OP_TLBI_ALLE2			sys_insn(1, 4, 8, 7, 0)
+#define OP_TLBI_VAE2			sys_insn(1, 4, 8, 7, 1)
+#define OP_TLBI_ALLE1			sys_insn(1, 4, 8, 7, 4)
+#define OP_TLBI_VALE2			sys_insn(1, 4, 8, 7, 5)
+#define OP_TLBI_VMALLS12E1		sys_insn(1, 4, 8, 7, 6)
+#define OP_TLBI_IPAS2E1ISNXS		sys_insn(1, 4, 9, 0, 1)
+#define OP_TLBI_RIPAS2E1ISNXS		sys_insn(1, 4, 9, 0, 2)
+#define OP_TLBI_IPAS2LE1ISNXS		sys_insn(1, 4, 9, 0, 5)
+#define OP_TLBI_RIPAS2LE1ISNXS		sys_insn(1, 4, 9, 0, 6)
+#define OP_TLBI_ALLE2OSNXS		sys_insn(1, 4, 9, 1, 0)
+#define OP_TLBI_VAE2OSNXS		sys_insn(1, 4, 9, 1, 1)
+#define OP_TLBI_ALLE1OSNXS		sys_insn(1, 4, 9, 1, 4)
+#define OP_TLBI_VALE2OSNXS		sys_insn(1, 4, 9, 1, 5)
+#define OP_TLBI_VMALLS12E1OSNXS		sys_insn(1, 4, 9, 1, 6)
+#define OP_TLBI_RVAE2ISNXS		sys_insn(1, 4, 9, 2, 1)
+#define OP_TLBI_RVALE2ISNXS		sys_insn(1, 4, 9, 2, 5)
+#define OP_TLBI_ALLE2ISNXS		sys_insn(1, 4, 9, 3, 0)
+#define OP_TLBI_VAE2ISNXS		sys_insn(1, 4, 9, 3, 1)
+#define OP_TLBI_ALLE1ISNXS		sys_insn(1, 4, 9, 3, 4)
+#define OP_TLBI_VALE2ISNXS		sys_insn(1, 4, 9, 3, 5)
+#define OP_TLBI_VMALLS12E1ISNXS		sys_insn(1, 4, 9, 3, 6)
+#define OP_TLBI_IPAS2E1OSNXS		sys_insn(1, 4, 9, 4, 0)
+#define OP_TLBI_IPAS2E1NXS		sys_insn(1, 4, 9, 4, 1)
+#define OP_TLBI_RIPAS2E1NXS		sys_insn(1, 4, 9, 4, 2)
+#define OP_TLBI_RIPAS2E1OSNXS		sys_insn(1, 4, 9, 4, 3)
+#define OP_TLBI_IPAS2LE1OSNXS		sys_insn(1, 4, 9, 4, 4)
+#define OP_TLBI_IPAS2LE1NXS		sys_insn(1, 4, 9, 4, 5)
+#define OP_TLBI_RIPAS2LE1NXS		sys_insn(1, 4, 9, 4, 6)
+#define OP_TLBI_RIPAS2LE1OSNXS		sys_insn(1, 4, 9, 4, 7)
+#define OP_TLBI_RVAE2OSNXS		sys_insn(1, 4, 9, 5, 1)
+#define OP_TLBI_RVALE2OSNXS		sys_insn(1, 4, 9, 5, 5)
+#define OP_TLBI_RVAE2NXS		sys_insn(1, 4, 9, 6, 1)
+#define OP_TLBI_RVALE2NXS		sys_insn(1, 4, 9, 6, 5)
+#define OP_TLBI_ALLE2NXS		sys_insn(1, 4, 9, 7, 0)
+#define OP_TLBI_VAE2NXS			sys_insn(1, 4, 9, 7, 1)
+#define OP_TLBI_ALLE1NXS		sys_insn(1, 4, 9, 7, 4)
+#define OP_TLBI_VALE2NXS		sys_insn(1, 4, 9, 7, 5)
+#define OP_TLBI_VMALLS12E1NXS		sys_insn(1, 4, 9, 7, 6)
+
+/* Misc instructions */
+#define OP_BRB_IALL			sys_insn(1, 1, 7, 2, 4)
+#define OP_BRB_INJ			sys_insn(1, 1, 7, 2, 5)
+#define OP_CFP_RCTX			sys_insn(1, 3, 7, 3, 4)
+#define OP_DVP_RCTX			sys_insn(1, 3, 7, 3, 5)
+#define OP_CPP_RCTX			sys_insn(1, 3, 7, 3, 7)
+
 /* Common SCTLR_ELx flags. */
 #define SCTLR_ELx_ENTP2	(BIT(60))
 #define SCTLR_ELx_DSSBS	(BIT(44))

arch/arm64/include/asm/tlbflush.h

@@ -335,14 +335,77 @@ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
  */
 #define MAX_TLBI_OPS	PTRS_PER_PTE
 
+/*
+ * __flush_tlb_range_op - Perform TLBI operation upon a range
+ *
+ * @op:	TLBI instruction that operates on a range (has 'r' prefix)
+ * @start:	The start address of the range
+ * @pages:	Range as the number of pages from 'start'
+ * @stride:	Flush granularity
+ * @asid:	The ASID of the task (0 for IPA instructions)
+ * @tlb_level:	Translation Table level hint, if known
+ * @tlbi_user:	If 'true', call an additional __tlbi_user()
+ *              (typically for user ASIDs). 'flase' for IPA instructions
+ *
+ * When the CPU does not support TLB range operations, flush the TLB
+ * entries one by one at the granularity of 'stride'. If the TLB
+ * range ops are supported, then:
+ *
+ * 1. If 'pages' is odd, flush the first page through non-range
+ *    operations;
+ *
+ * 2. For remaining pages: the minimum range granularity is decided
+ *    by 'scale', so multiple range TLBI operations may be required.
+ *    Start from scale = 0, flush the corresponding number of pages
+ *    ((num+1)*2^(5*scale+1) starting from 'addr'), then increase it
+ *    until no pages left.
+ *
+ * Note that certain ranges can be represented by either num = 31 and
+ * scale or num = 0 and scale + 1. The loop below favours the latter
+ * since num is limited to 30 by the __TLBI_RANGE_NUM() macro.
+ */
+#define __flush_tlb_range_op(op, start, pages, stride,			\
+				asid, tlb_level, tlbi_user)		\
+do {									\
+	int num = 0;							\
+	int scale = 0;							\
+	unsigned long addr;						\
+									\
+	while (pages > 0) {						\
+		if (!system_supports_tlb_range() ||			\
+		    pages % 2 == 1) {					\
+			addr = __TLBI_VADDR(start, asid);		\
+			__tlbi_level(op, addr, tlb_level);		\
+			if (tlbi_user)					\
+				__tlbi_user_level(op, addr, tlb_level);	\
+			start += stride;				\
+			pages -= stride >> PAGE_SHIFT;			\
+			continue;					\
+		}							\
+									\
+		num = __TLBI_RANGE_NUM(pages, scale);			\
+		if (num >= 0) {						\
+			addr = __TLBI_VADDR_RANGE(start, asid, scale,	\
+						  num, tlb_level);	\
+			__tlbi(r##op, addr);				\
+			if (tlbi_user)					\
+				__tlbi_user(r##op, addr);		\
+			start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \
+			pages -= __TLBI_RANGE_PAGES(num, scale);	\
+		}							\
+		scale++;						\
+	}								\
+} while (0)
+
+#define __flush_s2_tlb_range_op(op, start, pages, stride, tlb_level) \
+	__flush_tlb_range_op(op, start, pages, stride, 0, tlb_level, false)
+
 static inline void __flush_tlb_range(struct vm_area_struct *vma,
 				     unsigned long start, unsigned long end,
 				     unsigned long stride, bool last_level,
 				     int tlb_level)
 {
-	int num = 0;
-	int scale = 0;
-	unsigned long asid, addr, pages;
+	unsigned long asid, pages;
 
 	start = round_down(start, stride);
 	end = round_up(end, stride);
@@ -364,56 +427,11 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 	dsb(ishst);
 	asid = ASID(vma->vm_mm);
 
-	/*
-	 * When the CPU does not support TLB range operations, flush the TLB
-	 * entries one by one at the granularity of 'stride'. If the TLB
-	 * range ops are supported, then:
-	 *
-	 * 1. If 'pages' is odd, flush the first page through non-range
-	 *    operations;
-	 *
-	 * 2. For remaining pages: the minimum range granularity is decided
-	 *    by 'scale', so multiple range TLBI operations may be required.
-	 *    Start from scale = 0, flush the corresponding number of pages
-	 *    ((num+1)*2^(5*scale+1) starting from 'addr'), then increase it
-	 *    until no pages left.
-	 *
-	 * Note that certain ranges can be represented by either num = 31 and
-	 * scale or num = 0 and scale + 1. The loop below favours the latter
-	 * since num is limited to 30 by the __TLBI_RANGE_NUM() macro.
-	 */
-	while (pages > 0) {
-		if (!system_supports_tlb_range() ||
-		    pages % 2 == 1) {
-			addr = __TLBI_VADDR(start, asid);
-			if (last_level) {
-				__tlbi_level(vale1is, addr, tlb_level);
-				__tlbi_user_level(vale1is, addr, tlb_level);
-			} else {
-				__tlbi_level(vae1is, addr, tlb_level);
-				__tlbi_user_level(vae1is, addr, tlb_level);
-			}
-			start += stride;
-			pages -= stride >> PAGE_SHIFT;
-			continue;
-		}
-
-		num = __TLBI_RANGE_NUM(pages, scale);
-		if (num >= 0) {
-			addr = __TLBI_VADDR_RANGE(start, asid, scale,
-						  num, tlb_level);
-			if (last_level) {
-				__tlbi(rvale1is, addr);
-				__tlbi_user(rvale1is, addr);
-			} else {
-				__tlbi(rvae1is, addr);
-				__tlbi_user(rvae1is, addr);
-			}
-			start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT;
-			pages -= __TLBI_RANGE_PAGES(num, scale);
-		}
-		scale++;
-	}
+	if (last_level)
+		__flush_tlb_range_op(vale1is, start, pages, stride, asid, tlb_level, true);
+	else
+		__flush_tlb_range_op(vae1is, start, pages, stride, asid, tlb_level, true);
+
 	dsb(ish);
 	mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end);
 }

arch/arm64/kernel/cpufeature.c

@@ -2627,6 +2627,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, LRCPC, IMP)
 	},
+	{
+		.desc = "Fine Grained Traps",
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.capability = ARM64_HAS_FGT,
+		.matches = has_cpuid_feature,
+		ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, FGT, IMP)
+	},
 #ifdef CONFIG_ARM64_SME
 	{
 		.desc = "Scalable Matrix Extension",

arch/arm64/kvm/Kconfig

@@ -25,7 +25,6 @@ menuconfig KVM
 	select MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
-	select HAVE_KVM_ARCH_TLB_FLUSH_ALL
 	select KVM_MMIO
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_XFER_TO_GUEST_WORK
@@ -43,6 +42,7 @@ menuconfig KVM
 	select SCHED_INFO
 	select GUEST_PERF_EVENTS if PERF_EVENTS
 	select INTERVAL_TREE
+	select XARRAY_MULTI
 	help
 	  Support hosting virtualized guest machines.
 

arch/arm64/kvm/arm.c

@@ -36,6 +36,7 @@
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmu.h>
+#include <asm/kvm_nested.h>
 #include <asm/kvm_pkvm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/sections.h>
@@ -365,7 +366,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 #endif
 
 	/* Force users to call KVM_ARM_VCPU_INIT */
-	vcpu->arch.target = -1;
+	vcpu_clear_flag(vcpu, VCPU_INITIALIZED);
 	bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
 
 	vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO;
@@ -462,7 +463,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		vcpu_ptrauth_disable(vcpu);
 	kvm_arch_vcpu_load_debug_state_flags(vcpu);
 
-	if (!cpumask_test_cpu(smp_processor_id(), vcpu->kvm->arch.supported_cpus))
+	if (!cpumask_test_cpu(cpu, vcpu->kvm->arch.supported_cpus))
 		vcpu_set_on_unsupported_cpu(vcpu);
 }
 
@@ -574,7 +575,7 @@ unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
 
 static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.target >= 0;
+	return vcpu_get_flag(vcpu, VCPU_INITIALIZED);
 }
 
 /*
@@ -803,6 +804,9 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 			kvm_pmu_handle_pmcr(vcpu,
 					    __vcpu_sys_reg(vcpu, PMCR_EL0));
 
+		if (kvm_check_request(KVM_REQ_RESYNC_PMU_EL0, vcpu))
+			kvm_vcpu_pmu_restore_guest(vcpu);
+
 		if (kvm_check_request(KVM_REQ_SUSPEND, vcpu))
 			return kvm_vcpu_suspend(vcpu);
 
@@ -818,6 +822,9 @@ static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu)
 	if (likely(!vcpu_mode_is_32bit(vcpu)))
 		return false;
 
+	if (vcpu_has_nv(vcpu))
+		return true;
+
 	return !kvm_supports_32bit_el0();
 }
 
@@ -1058,7 +1065,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			 * invalid. The VMM can try and fix it by issuing  a
 			 * KVM_ARM_VCPU_INIT if it really wants to.
 			 */
-			vcpu->arch.target = -1;
+			vcpu_clear_flag(vcpu, VCPU_INITIALIZED);
 			ret = ARM_EXCEPTION_IL;
 		}
 
@@ -1219,8 +1226,7 @@ static bool kvm_vcpu_init_changed(struct kvm_vcpu *vcpu,
 {
 	unsigned long features = init->features[0];
 
-	return !bitmap_equal(vcpu->arch.features, &features, KVM_VCPU_MAX_FEATURES) ||
-			vcpu->arch.target != init->target;
+	return !bitmap_equal(vcpu->arch.features, &features, KVM_VCPU_MAX_FEATURES);
 }
 
 static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
@@ -1236,20 +1242,18 @@ static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 	    !bitmap_equal(kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES))
 		goto out_unlock;
 
-	vcpu->arch.target = init->target;
 	bitmap_copy(vcpu->arch.features, &features, KVM_VCPU_MAX_FEATURES);
 
 	/* Now we know what it is, we can reset it. */
 	ret = kvm_reset_vcpu(vcpu);
 	if (ret) {
-		vcpu->arch.target = -1;
 		bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
 		goto out_unlock;
 	}
 
 	bitmap_copy(kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES);
 	set_bit(KVM_ARCH_FLAG_VCPU_FEATURES_CONFIGURED, &kvm->arch.flags);
-
+	vcpu_set_flag(vcpu, VCPU_INITIALIZED);
 out_unlock:
 	mutex_unlock(&kvm->arch.config_lock);
 	return ret;
@@ -1260,14 +1264,15 @@ static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 {
 	int ret;
 
-	if (init->target != kvm_target_cpu())
+	if (init->target != KVM_ARM_TARGET_GENERIC_V8 &&
+	    init->target != kvm_target_cpu())
 		return -EINVAL;
 
 	ret = kvm_vcpu_init_check_features(vcpu, init);
 	if (ret)
 		return ret;
 
-	if (vcpu->arch.target == -1)
+	if (!kvm_vcpu_initialized(vcpu))
 		return __kvm_vcpu_set_target(vcpu, init);
 
 	if (kvm_vcpu_init_changed(vcpu, init))
@@ -1532,12 +1537,6 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 
 }
 
-void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
-					const struct kvm_memory_slot *memslot)
-{
-	kvm_flush_remote_tlbs(kvm);
-}
-
 static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm,
 					struct kvm_arm_device_addr *dev_addr)
 {
@@ -1595,9 +1594,9 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 		return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr);
 	}
 	case KVM_ARM_PREFERRED_TARGET: {
-		struct kvm_vcpu_init init;
-
-		kvm_vcpu_preferred_target(&init);
+		struct kvm_vcpu_init init = {
+			.target = KVM_ARM_TARGET_GENERIC_V8,
+		};
 
 		if (copy_to_user(argp, &init, sizeof(init)))
 			return -EFAULT;
@@ -2276,30 +2275,8 @@ static int __init init_hyp_mode(void)
 	for_each_possible_cpu(cpu) {
 		struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
 		char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu);
-		unsigned long hyp_addr;
 
-		/*
-		 * Allocate a contiguous HYP private VA range for the stack
-		 * and guard page. The allocation is also aligned based on
-		 * the order of its size.
-		 */
-		err = hyp_alloc_private_va_range(PAGE_SIZE * 2, &hyp_addr);
-		if (err) {
-			kvm_err("Cannot allocate hyp stack guard page\n");
-			goto out_err;
-		}
-
-		/*
-		 * Since the stack grows downwards, map the stack to the page
-		 * at the higher address and leave the lower guard page
-		 * unbacked.
-		 *
-		 * Any valid stack address now has the PAGE_SHIFT bit as 1
-		 * and addresses corresponding to the guard page have the
-		 * PAGE_SHIFT bit as 0 - this is used for overflow detection.
-		 */
-		err = __create_hyp_mappings(hyp_addr + PAGE_SIZE, PAGE_SIZE,
-					    __pa(stack_page), PAGE_HYP);
+		err = create_hyp_stack(__pa(stack_page), &params->stack_hyp_va);
 		if (err) {
 			kvm_err("Cannot map hyp stack\n");
 			goto out_err;
@@ -2312,8 +2289,6 @@ static int __init init_hyp_mode(void)
 		 * has been mapped in the flexible private VA space.
 		 */
 		params->stack_pa = __pa(stack_page);
-
-		params->stack_hyp_va = hyp_addr + (2 * PAGE_SIZE);
 	}
 
 	for_each_possible_cpu(cpu) {

arch/arm64/kvm/guest.c

@@ -884,21 +884,6 @@ u32 __attribute_const__ kvm_target_cpu(void)
 	return KVM_ARM_TARGET_GENERIC_V8;
 }
 
-void kvm_vcpu_preferred_target(struct kvm_vcpu_init *init)
-{
-	u32 target = kvm_target_cpu();
-
-	memset(init, 0, sizeof(*init));
-
-	/*
-	 * For now, we don't return any features.
-	 * In future, we might use features to return target
-	 * specific features available for the preferred
-	 * target type.
-	 */
-	init->target = (__u32)target;
-}
-
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	return -EINVAL;

arch/arm64/kvm/handle_exit.c

@@ -222,7 +222,33 @@ static int kvm_handle_eret(struct kvm_vcpu *vcpu)
 	if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_ERET_ISS_ERET)
 		return kvm_handle_ptrauth(vcpu);
 
-	kvm_emulate_nested_eret(vcpu);
+	/*
+	 * If we got here, two possibilities:
+	 *
+	 * - the guest is in EL2, and we need to fully emulate ERET
+	 *
+	 * - the guest is in EL1, and we need to reinject the
+         *   exception into the L1 hypervisor.
+	 *
+	 * If KVM ever traps ERET for its own use, we'll have to
+	 * revisit this.
+	 */
+	if (is_hyp_ctxt(vcpu))
+		kvm_emulate_nested_eret(vcpu);
+	else
+		kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+
+	return 1;
+}
+
+static int handle_svc(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * So far, SVC traps only for NV via HFGITR_EL2. A SVC from a
+	 * 32bit guest would be caught by vpcu_mode_is_bad_32bit(), so
+	 * we should only have to deal with a 64 bit exception.
+	 */
+	kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
 	return 1;
 }
 
@@ -239,6 +265,7 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[ESR_ELx_EC_SMC32]	= handle_smc,
 	[ESR_ELx_EC_HVC64]	= handle_hvc,
 	[ESR_ELx_EC_SMC64]	= handle_smc,
+	[ESR_ELx_EC_SVC64]	= handle_svc,
 	[ESR_ELx_EC_SYS64]	= kvm_handle_sys_reg,
 	[ESR_ELx_EC_SVE]	= handle_sve,
 	[ESR_ELx_EC_ERET]	= kvm_handle_eret,

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -70,20 +70,26 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 	}
 }
 
-static inline bool __hfgxtr_traps_required(void)
-{
-	if (cpus_have_final_cap(ARM64_SME))
-		return true;
-
-	if (cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38))
-		return true;
+#define compute_clr_set(vcpu, reg, clr, set)				\
+	do {								\
+		u64 hfg;						\
+		hfg = __vcpu_sys_reg(vcpu, reg) & ~__ ## reg ## _RES0;	\
+		set |= hfg & __ ## reg ## _MASK; 			\
+		clr |= ~hfg & __ ## reg ## _nMASK; 			\
+	} while(0)
 
-	return false;
-}
 
-static inline void __activate_traps_hfgxtr(void)
+static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 {
+	struct kvm_cpu_context *hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
 	u64 r_clr = 0, w_clr = 0, r_set = 0, w_set = 0, tmp;
+	u64 r_val, w_val;
+
+	if (!cpus_have_final_cap(ARM64_HAS_FGT))
+		return;
+
+	ctxt_sys_reg(hctxt, HFGRTR_EL2) = read_sysreg_s(SYS_HFGRTR_EL2);
+	ctxt_sys_reg(hctxt, HFGWTR_EL2) = read_sysreg_s(SYS_HFGWTR_EL2);
 
 	if (cpus_have_final_cap(ARM64_SME)) {
 		tmp = HFGxTR_EL2_nSMPRI_EL1_MASK | HFGxTR_EL2_nTPIDR2_EL0_MASK;
@@ -98,26 +104,72 @@ static inline void __activate_traps_hfgxtr(void)
 	if (cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38))
 		w_set |= HFGxTR_EL2_TCR_EL1_MASK;
 
-	sysreg_clear_set_s(SYS_HFGRTR_EL2, r_clr, r_set);
-	sysreg_clear_set_s(SYS_HFGWTR_EL2, w_clr, w_set);
+	if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) {
+		compute_clr_set(vcpu, HFGRTR_EL2, r_clr, r_set);
+		compute_clr_set(vcpu, HFGWTR_EL2, w_clr, w_set);
+	}
+
+	/* The default is not to trap anything but ACCDATA_EL1 */
+	r_val = __HFGRTR_EL2_nMASK & ~HFGxTR_EL2_nACCDATA_EL1;
+	r_val |= r_set;
+	r_val &= ~r_clr;
+
+	w_val = __HFGWTR_EL2_nMASK & ~HFGxTR_EL2_nACCDATA_EL1;
+	w_val |= w_set;
+	w_val &= ~w_clr;
+
+	write_sysreg_s(r_val, SYS_HFGRTR_EL2);
+	write_sysreg_s(w_val, SYS_HFGWTR_EL2);
+
+	if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
+		return;
+
+	ctxt_sys_reg(hctxt, HFGITR_EL2) = read_sysreg_s(SYS_HFGITR_EL2);
+
+	r_set = r_clr = 0;
+	compute_clr_set(vcpu, HFGITR_EL2, r_clr, r_set);
+	r_val = __HFGITR_EL2_nMASK;
+	r_val |= r_set;
+	r_val &= ~r_clr;
+
+	write_sysreg_s(r_val, SYS_HFGITR_EL2);
+
+	ctxt_sys_reg(hctxt, HDFGRTR_EL2) = read_sysreg_s(SYS_HDFGRTR_EL2);
+	ctxt_sys_reg(hctxt, HDFGWTR_EL2) = read_sysreg_s(SYS_HDFGWTR_EL2);
+
+	r_clr = r_set = w_clr = w_set = 0;
+
+	compute_clr_set(vcpu, HDFGRTR_EL2, r_clr, r_set);
+	compute_clr_set(vcpu, HDFGWTR_EL2, w_clr, w_set);
+
+	r_val = __HDFGRTR_EL2_nMASK;
+	r_val |= r_set;
+	r_val &= ~r_clr;
+
+	w_val = __HDFGWTR_EL2_nMASK;
+	w_val |= w_set;
+	w_val &= ~w_clr;
+
+	write_sysreg_s(r_val, SYS_HDFGRTR_EL2);
+	write_sysreg_s(w_val, SYS_HDFGWTR_EL2);
 }
 
-static inline void __deactivate_traps_hfgxtr(void)
+static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 {
-	u64 r_clr = 0, w_clr = 0, r_set = 0, w_set = 0, tmp;
+	struct kvm_cpu_context *hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
 
-	if (cpus_have_final_cap(ARM64_SME)) {
-		tmp = HFGxTR_EL2_nSMPRI_EL1_MASK | HFGxTR_EL2_nTPIDR2_EL0_MASK;
+	if (!cpus_have_final_cap(ARM64_HAS_FGT))
+		return;
 
-		r_set |= tmp;
-		w_set |= tmp;
-	}
+	write_sysreg_s(ctxt_sys_reg(hctxt, HFGRTR_EL2), SYS_HFGRTR_EL2);
+	write_sysreg_s(ctxt_sys_reg(hctxt, HFGWTR_EL2), SYS_HFGWTR_EL2);
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38))
-		w_clr |= HFGxTR_EL2_TCR_EL1_MASK;
+	if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
+		return;
 
-	sysreg_clear_set_s(SYS_HFGRTR_EL2, r_clr, r_set);
-	sysreg_clear_set_s(SYS_HFGWTR_EL2, w_clr, w_set);
+	write_sysreg_s(ctxt_sys_reg(hctxt, HFGITR_EL2), SYS_HFGITR_EL2);
+	write_sysreg_s(ctxt_sys_reg(hctxt, HDFGRTR_EL2), SYS_HDFGRTR_EL2);
+	write_sysreg_s(ctxt_sys_reg(hctxt, HDFGWTR_EL2), SYS_HDFGWTR_EL2);
 }
 
 static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
@@ -145,8 +197,21 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 	vcpu->arch.mdcr_el2_host = read_sysreg(mdcr_el2);
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 
-	if (__hfgxtr_traps_required())
-		__activate_traps_hfgxtr();
+	if (cpus_have_final_cap(ARM64_HAS_HCX)) {
+		u64 hcrx = HCRX_GUEST_FLAGS;
+		if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) {
+			u64 clr = 0, set = 0;
+
+			compute_clr_set(vcpu, HCRX_EL2, clr, set);
+
+			hcrx |= set;
+			hcrx &= ~clr;
+		}
+
+		write_sysreg_s(hcrx, SYS_HCRX_EL2);
+	}
+
+	__activate_traps_hfgxtr(vcpu);
 }
 
 static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
@@ -162,8 +227,10 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
 		vcpu_clear_flag(vcpu, PMUSERENR_ON_CPU);
 	}
 
-	if (__hfgxtr_traps_required())
-		__deactivate_traps_hfgxtr();
+	if (cpus_have_final_cap(ARM64_HAS_HCX))
+		write_sysreg_s(HCRX_HOST_FLAGS, SYS_HCRX_EL2);
+
+	__deactivate_traps_hfgxtr(vcpu);
 }
 
 static inline void ___activate_traps(struct kvm_vcpu *vcpu)
@@ -177,9 +244,6 @@ static inline void ___activate_traps(struct kvm_vcpu *vcpu)
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
 		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
-
-	if (cpus_have_final_cap(ARM64_HAS_HCX))
-		write_sysreg_s(HCRX_GUEST_FLAGS, SYS_HCRX_EL2);
 }
 
 static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
@@ -194,9 +258,6 @@ static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
 		vcpu->arch.hcr_el2 &= ~HCR_VSE;
 		vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
 	}
-
-	if (cpus_have_final_cap(ARM64_HAS_HCX))
-		write_sysreg_s(HCRX_HOST_FLAGS, SYS_HCRX_EL2);
 }
 
 static inline bool __populate_fault_info(struct kvm_vcpu *vcpu)

arch/arm64/kvm/hyp/include/nvhe/mm.h

@@ -26,6 +26,7 @@ int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot
 int __pkvm_create_private_mapping(phys_addr_t phys, size_t size,
 				  enum kvm_pgtable_prot prot,
 				  unsigned long *haddr);
+int pkvm_create_stack(phys_addr_t phys, unsigned long *haddr);
 int pkvm_alloc_private_va_range(size_t size, unsigned long *haddr);
 
 #endif /* __KVM_HYP_MM_H */

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -135,6 +135,16 @@ static void handle___kvm_tlb_flush_vmid_ipa_nsh(struct kvm_cpu_context *host_ctx
 	__kvm_tlb_flush_vmid_ipa_nsh(kern_hyp_va(mmu), ipa, level);
 }
 
+static void
+handle___kvm_tlb_flush_vmid_range(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
+	DECLARE_REG(phys_addr_t, start, host_ctxt, 2);
+	DECLARE_REG(unsigned long, pages, host_ctxt, 3);
+
+	__kvm_tlb_flush_vmid_range(kern_hyp_va(mmu), start, pages);
+}
+
 static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
@@ -327,6 +337,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa_nsh),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid),
+	HANDLE_FUNC(__kvm_tlb_flush_vmid_range),
 	HANDLE_FUNC(__kvm_flush_cpu_context),
 	HANDLE_FUNC(__kvm_timer_set_cntvoff),
 	HANDLE_FUNC(__vgic_v3_read_vmcr),