Merge tag 'kvmarm-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for Linux 6.6

- Add support for TLB range invalidation of Stage-2 page tables,
  avoiding unnecessary invalidations. Systems that do not implement
  range invalidation still rely on a full invalidation when dealing
  with large ranges.

- Add infrastructure for forwarding traps taken from a L2 guest to
  the L1 guest, with L0 acting as the dispatcher, another baby step
  towards the full nested support.

- Simplify the way we deal with the (long deprecated) 'CPU target',
  resulting in a much needed cleanup.

- Fix another set of PMU bugs, both on the guest and host sides,
  as we seem to never have any shortage of those...

- Relax the alignment requirements of EL2 VA allocations for
  non-stack allocations, as we were otherwise wasting a lot of that
  precious VA space.

- The usual set of non-functional cleanups, although I note the lack
  of spelling fixes...

Author: bonzini

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__ */