KVM: arm64: nv: Shadow stage-2 page table handling

index 9e8a496fb284..f54f4842f116 100644
@@ -188,8 +188,40 @@ struct kvm_s2_mmu {
 	uint64_t split_page_chunk_size;
 
 	struct kvm_arch *arch;
+
+	/*
+	 * For a shadow stage-2 MMU, the virtual vttbr used by the
+	 * host to parse the guest S2.
+	 * This either contains:
+	 * - the virtual VTTBR programmed by the guest hypervisor with
+         *   CnP cleared
+	 * - The value 1 (VMID=0, BADDR=0, CnP=1) if invalid
+	 *
+	 * We also cache the full VTCR which gets used for TLB invalidation,
+	 * taking the ARM ARM's "Any of the bits in VTCR_EL2 are permitted
+	 * to be cached in a TLB" to the letter.
+	 */
+	u64	tlb_vttbr;
+	u64	tlb_vtcr;
+
+	/*
+	 * true when this represents a nested context where virtual
+	 * HCR_EL2.VM == 1
+	 */
+	bool	nested_stage2_enabled;
+
+	/*
+	 *  0: Nobody is currently using this, check vttbr for validity
+	 * >0: Somebody is actively using this.
+	 */
+	atomic_t refcnt;
 };
 
+static inline bool kvm_s2_mmu_valid(struct kvm_s2_mmu *mmu)
+{
+	return !(mmu->tlb_vttbr & 1);
+}
+
 struct kvm_arch_memory_slot {
 };
 

@@ -264,6 +296,14 @@ struct kvm_arch {
 	 */
 	u64 fgu[__NR_FGT_GROUP_IDS__];
 
+	/*
+	 * Stage 2 paging state for VMs with nested S2 using a virtual
+	 * VMID.
+	 */
+	struct kvm_s2_mmu *nested_mmus;
+	size_t nested_mmus_size;
+	int nested_mmus_next;
+
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
 

@@ -1239,6 +1279,7 @@ void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu);
 void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu);
 
 int __init kvm_set_ipa_limit(void);
+u32 kvm_get_pa_bits(struct kvm *kvm);
 
 #define __KVM_HAVE_ARCH_VM_ALLOC
 struct kvm *kvm_arch_alloc_vm(void);

index d5e48d870461..b48c9e12e7ff 100644
@@ -98,6 +98,7 @@ alternative_cb_end
 #include <asm/mmu_context.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_host.h>
+#include <asm/kvm_nested.h>
 
 void kvm_update_va_mask(struct alt_instr *alt,
 			__le32 *origptr, __le32 *updptr, int nr_inst);

@@ -165,6 +166,7 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr);
 void __init free_hyp_pgds(void);
 
+void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
 void stage2_unmap_vm(struct kvm *kvm);
 int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type);
 void kvm_uninit_stage2_mmu(struct kvm *kvm);

@@ -326,5 +328,12 @@ static inline struct kvm *kvm_s2_mmu_to_kvm(struct kvm_s2_mmu *mmu)
 {
 	return container_of(mmu->arch, struct kvm, arch);
 }
+
+static inline u64 get_vmid(u64 vttbr)
+{
+	return (vttbr & VTTBR_VMID_MASK(kvm_get_vmid_bits())) >>
+		VTTBR_VMID_SHIFT;
+}
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ARM64_KVM_MMU_H__ */

index c77d795556e1..1a4004e7573d 100644
@@ -60,6 +60,12 @@ static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0)
 	return ttbr0 & ~GENMASK_ULL(63, 48);
 }
 
+extern void kvm_init_nested(struct kvm *kvm);
+extern int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu);
+extern void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu);
+extern struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu);
+extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
+extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);
 
 int kvm_init_nv_sysregs(struct kvm *kvm);
 

index c4a0a35e02c7..bb19c53b6539 100644
@@ -147,6 +147,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	mutex_unlock(&kvm->lock);
 #endif
 
+	kvm_init_nested(kvm);
+
 	ret = kvm_share_hyp(kvm, kvm + 1);
 	if (ret)
 		return ret;

@@ -433,6 +435,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	struct kvm_s2_mmu *mmu;
 	int *last_ran;
 
+	if (vcpu_has_nv(vcpu))
+		kvm_vcpu_load_hw_mmu(vcpu);
+
 	mmu = vcpu->arch.hw_mmu;
 	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 

@@ -483,6 +488,8 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	kvm_timer_vcpu_put(vcpu);
 	kvm_vgic_put(vcpu);
 	kvm_vcpu_pmu_restore_host(vcpu);
+	if (vcpu_has_nv(vcpu))
+		kvm_vcpu_put_hw_mmu(vcpu);
 	kvm_arm_vmid_clear_active();
 
 	vcpu_clear_on_unsupported_cpu(vcpu);

@@ -1346,6 +1353,10 @@ static int kvm_setup_vcpu(struct kvm_vcpu *vcpu)
 	if (kvm_vcpu_has_pmu(vcpu) && !kvm->arch.arm_pmu)
 		ret = kvm_arm_set_default_pmu(kvm);
 
+	/* Prepare for nested if required */
+	if (!ret)
+		ret = kvm_vcpu_init_nested(vcpu);
+
 	return ret;
 }
 

125 lines not on this page · raw message

218 lines not on this page · raw message

index 68d1d05672bd..9151f7335ddf 100644
@@ -266,6 +266,12 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	preempt_enable();
 }
 
+u32 kvm_get_pa_bits(struct kvm *kvm)
+{
+	/* Fixed limit until we can configure ID_AA64MMFR0.PARange */
+	return kvm_ipa_limit;
+}
+
 u32 get_kvm_ipa_limit(void)
 {
 	return kvm_ipa_limit;

index 81606bf7d5ac..bf6e7de485f8 100644
@@ -152,6 +152,7 @@
 #define ESR_ELx_Xs_MASK		(GENMASK_ULL(4, 0))
 
 /* ISS field definitions for exceptions taken in to Hyp */
+#define ESR_ELx_FSC_ADDRSZ	(0x00)
 #define ESR_ELx_CV		(UL(1) << 24)
 #define ESR_ELx_COND_SHIFT	(20)
 #define ESR_ELx_COND_MASK	(UL(0xF) << ESR_ELx_COND_SHIFT)

index 1a4004e7573d..d7a1c402dc2d 100644
@@ -67,6 +67,19 @@ extern struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu);
 extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
 extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);
 
+struct kvm_s2_trans {
+	phys_addr_t output;
+	unsigned long block_size;
+	bool writable;
+	bool readable;
+	int level;
+	u32 esr;
+	u64 upper_attr;
+};
+
+extern int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
+			      struct kvm_s2_trans *result);
+
 int kvm_init_nv_sysregs(struct kvm *kvm);
 
 #endif /* __ARM64_KVM_NESTED_H */

271 lines not on this page · raw message

index 975af30af31f..675b93b0a4cd 100644
@@ -611,4 +611,5 @@ static __always_inline void kvm_reset_cptr_el2(struct kvm_vcpu *vcpu)
 
 	kvm_write_cptr_el2(val);
 }
+
 #endif /* __ARM64_KVM_EMULATE_H__ */

index d7a1c402dc2d..35044a5dce3f 100644
@@ -77,8 +77,41 @@ struct kvm_s2_trans {
 	u64 upper_attr;
 };
 
+static inline phys_addr_t kvm_s2_trans_output(struct kvm_s2_trans *trans)
+{
+	return trans->output;
+}
+
+static inline unsigned long kvm_s2_trans_size(struct kvm_s2_trans *trans)
+{
+	return trans->block_size;
+}
+
+static inline u32 kvm_s2_trans_esr(struct kvm_s2_trans *trans)
+{
+	return trans->esr;
+}
+
+static inline bool kvm_s2_trans_readable(struct kvm_s2_trans *trans)
+{
+	return trans->readable;
+}
+
+static inline bool kvm_s2_trans_writable(struct kvm_s2_trans *trans)
+{
+	return trans->writable;
+}
+
+static inline bool kvm_s2_trans_executable(struct kvm_s2_trans *trans)
+{
+	return !(trans->upper_attr & BIT(54));
+}
+
 extern int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
 			      struct kvm_s2_trans *result);
+extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu,
+				    struct kvm_s2_trans *trans);
+extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2);
 
 int kvm_init_nv_sysregs(struct kvm *kvm);
 

165 lines not on this page · raw message

57 lines not on this page · raw message

index b48c9e12e7ff..6975e47f9d4c 100644
@@ -164,6 +164,8 @@ int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
 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 kvm_stage2_flush_range(struct kvm_s2_mmu *mmu,
+			    phys_addr_t addr, phys_addr_t end);
 void __init free_hyp_pgds(void);
 
 void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);

@@ -173,6 +175,7 @@ void kvm_uninit_stage2_mmu(struct kvm *kvm);
 void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			  phys_addr_t pa, unsigned long size, bool writable);
+void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
 
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
 

index 35044a5dce3f..afb3d0689e17 100644
@@ -112,6 +112,9 @@ extern int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
 extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu,
 				    struct kvm_s2_trans *trans);
 extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2);
+extern void kvm_nested_s2_wp(struct kvm *kvm);
+extern void kvm_nested_s2_unmap(struct kvm *kvm);
+extern void kvm_nested_s2_flush(struct kvm *kvm);
 
 int kvm_init_nv_sysregs(struct kvm *kvm);
 

index fe2b403e9a14..cf31da306622 100644
@@ -333,13 +333,19 @@ void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
 	__unmap_stage2_range(mmu, start, size, true);
 }
 
+void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu,
+			    phys_addr_t addr, phys_addr_t end)
+{
+	stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_flush);
+}
+
 static void stage2_flush_memslot(struct kvm *kvm,
 				 struct kvm_memory_slot *memslot)
 {
 	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
 	phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
 
-	stage2_apply_range_resched(&kvm->arch.mmu, addr, end, kvm_pgtable_stage2_flush);
+	kvm_stage2_flush_range(&kvm->arch.mmu, addr, end);
 }
 
 /**

@@ -362,6 +368,8 @@ static void stage2_flush_vm(struct kvm *kvm)
 	kvm_for_each_memslot(memslot, bkt, slots)
 		stage2_flush_memslot(kvm, memslot);
 
+	kvm_nested_s2_flush(kvm);
+
 	write_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, idx);
 }

@@ -1042,6 +1050,8 @@ void stage2_unmap_vm(struct kvm *kvm)
 	kvm_for_each_memslot(memslot, bkt, slots)
 		stage2_unmap_memslot(kvm, memslot);
 
+	kvm_nested_s2_unmap(kvm);
+
 	write_unlock(&kvm->mmu_lock);
 	mmap_read_unlock(current->mm);
 	srcu_read_unlock(&kvm->srcu, idx);

@@ -1141,12 +1151,12 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 }
 
 /**
- * stage2_wp_range() - write protect stage2 memory region range
+ * kvm_stage2_wp_range() - write protect stage2 memory region range
  * @mmu:        The KVM stage-2 MMU pointer
  * @addr:	Start address of range
  * @end:	End address of range
  */
-static void stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
+void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
 {
 	stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_wrprotect);
 }

@@ -1177,7 +1187,8 @@ static void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
 	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
 
 	write_lock(&kvm->mmu_lock);
-	stage2_wp_range(&kvm->arch.mmu, start, end);
+	kvm_stage2_wp_range(&kvm->arch.mmu, start, end);
+	kvm_nested_s2_wp(kvm);
 	write_unlock(&kvm->mmu_lock);
 	kvm_flush_remote_tlbs_memslot(kvm, memslot);
 }

@@ -1231,7 +1242,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
-	stage2_wp_range(&kvm->arch.mmu, start, end);
+	kvm_stage2_wp_range(&kvm->arch.mmu, start, end);
 
 	/*
 	 * Eager-splitting is done when manual-protect is set.  We

@@ -1243,6 +1254,8 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 	 */
 	if (kvm_dirty_log_manual_protect_and_init_set(kvm))
 		kvm_mmu_split_huge_pages(kvm, start, end);
+
+	kvm_nested_s2_wp(kvm);
 }
 
 static void kvm_send_hwpoison_signal(unsigned long address, short lsb)

@@ -1883,6 +1896,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 			     (range->end - range->start) << PAGE_SHIFT,
 			     range->may_block);
 
+	kvm_nested_s2_unmap(kvm);
 	return false;
 }
 

@@ -1917,6 +1931,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 			       PAGE_SIZE, __pfn_to_phys(pfn),
 			       KVM_PGTABLE_PROT_R, NULL, 0);
 
+	kvm_nested_s2_unmap(kvm);
 	return false;
 }
 

@@ -1930,6 +1945,10 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
 						   range->start << PAGE_SHIFT,
 						   size, true);
+	/*
+	 * TODO: Handle nested_mmu structures here using the reverse mapping in
+	 * a later version of patch series.
+	 */
 }
 
 bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)

@@ -2180,6 +2199,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 
 	write_lock(&kvm->mmu_lock);
 	kvm_unmap_stage2_range(&kvm->arch.mmu, gpa, size);
+	kvm_nested_s2_unmap(kvm);
 	write_unlock(&kvm->mmu_lock);
 }
 

48 lines not on this page · raw message

index 24b5e6b23417..38644fa648fa 100644
@@ -234,6 +234,8 @@ 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 int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding);
+
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);

68 lines not on this page · raw message

index afb3d0689e17..136c878b742e 100644
@@ -116,6 +116,61 @@ extern void kvm_nested_s2_wp(struct kvm *kvm);
 extern void kvm_nested_s2_unmap(struct kvm *kvm);
 extern void kvm_nested_s2_flush(struct kvm *kvm);
 
+static inline bool kvm_supported_tlbi_s1e1_op(struct kvm_vcpu *vpcu, u32 instr)
+{
+	struct kvm *kvm = vpcu->kvm;
+	u8 CRm = sys_reg_CRm(instr);
+
+	if (!(sys_reg_Op0(instr) == TLBI_Op0 &&
+	      sys_reg_Op1(instr) == TLBI_Op1_EL1))
+		return false;
+
+	if (!(sys_reg_CRn(instr) == TLBI_CRn_XS ||
+	      (sys_reg_CRn(instr) == TLBI_CRn_nXS &&
+	       kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP))))
+		return false;
+
+	if (CRm == TLBI_CRm_nROS &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
+		return false;
+
+	if ((CRm == TLBI_CRm_RIS || CRm == TLBI_CRm_ROS ||
+	     CRm == TLBI_CRm_RNS) &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
+		return false;
+
+	return true;
+}
+
+static inline bool kvm_supported_tlbi_s1e2_op(struct kvm_vcpu *vpcu, u32 instr)
+{
+	struct kvm *kvm = vpcu->kvm;
+	u8 CRm = sys_reg_CRm(instr);
+
+	if (!(sys_reg_Op0(instr) == TLBI_Op0 &&
+	      sys_reg_Op1(instr) == TLBI_Op1_EL2))
+		return false;
+
+	if (!(sys_reg_CRn(instr) == TLBI_CRn_XS ||
+	      (sys_reg_CRn(instr) == TLBI_CRn_nXS &&
+	       kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP))))
+		return false;
+
+	if (CRm == TLBI_CRm_IPAIS || CRm == TLBI_CRm_IPAONS)
+		return false;
+
+	if (CRm == TLBI_CRm_nROS &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
+		return false;
+
+	if ((CRm == TLBI_CRm_RIS || CRm == TLBI_CRm_ROS ||
+	     CRm == TLBI_CRm_RNS) &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
+		return false;
+
+	return true;
+}
+
 int kvm_init_nv_sysregs(struct kvm *kvm);
 
 #endif /* __ARM64_KVM_NESTED_H */

index 9e8999592f3a..b15194f79273 100644
@@ -654,6 +654,23 @@
 #define OP_AT_S12E0W	sys_insn(AT_Op0, 4, AT_CRn, 8, 7)
 
 /* TLBI instructions */
+#define TLBI_Op0	1
+
+#define TLBI_Op1_EL1	0	/* Accessible from EL1 or higher */
+#define TLBI_Op1_EL2	4	/* Accessible from EL2 or higher */
+
+#define TLBI_CRn_XS	8	/* Extra Slow (the common one) */
+#define TLBI_CRn_nXS	9	/* not Extra Slow (which nobody uses)*/
+
+#define TLBI_CRm_IPAIS	0	/* S2 Inner-Shareable */
+#define TLBI_CRm_nROS	1	/* non-Range, Outer-Sharable */
+#define TLBI_CRm_RIS	2	/* Range, Inner-Sharable */
+#define TLBI_CRm_nRIS	3	/* non-Range, Inner-Sharable */
+#define TLBI_CRm_IPAONS	4	/* S2 Outer and Non-Shareable */
+#define TLBI_CRm_ROS	5	/* Range, Outer-Sharable */
+#define TLBI_CRm_RNS	6	/* Range, Non-Sharable */
+#define TLBI_CRm_nRNS	7	/* non-Range, Non-Sharable */
+
 #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)

60 lines not on this page · raw message

index 136c878b742e..6b647a169f5d 100644
@@ -64,6 +64,13 @@ extern void kvm_init_nested(struct kvm *kvm);
 extern int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu);
 extern void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu);
 extern struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu);
+
+union tlbi_info;
+
+extern void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid,
+				       const union tlbi_info *info,
+				       void (*)(struct kvm_s2_mmu *,
+						const union tlbi_info *));
 extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
 extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);
 

index 3e95f815ad17..645c979a75e5 100644
@@ -349,6 +349,41 @@ int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
 	return ret;
 }
 
+/*
+ * We can have multiple *different* MMU contexts with the same VMID:
+ *
+ * - S2 being enabled or not, hence differing by the HCR_EL2.VM bit
+ *
+ * - Multiple vcpus using private S2s (huh huh...), hence differing by the
+ *   VBBTR_EL2.BADDR address
+ *
+ * - A combination of the above...
+ *
+ * We can always identify which MMU context to pick at run-time.  However,
+ * TLB invalidation involving a VMID must take action on all the TLBs using
+ * this particular VMID. This translates into applying the same invalidation
+ * operation to all the contexts that are using this VMID. Moar phun!
+ */
+void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid,
+				const union tlbi_info *info,
+				void (*tlbi_callback)(struct kvm_s2_mmu *,
+						      const union tlbi_info *))
+{
+	write_lock(&kvm->mmu_lock);
+
+	for (int i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (!kvm_s2_mmu_valid(mmu))
+			continue;
+
+		if (vmid == get_vmid(mmu->tlb_vttbr))
+			tlbi_callback(mmu, info);
+	}
+
+	write_unlock(&kvm->mmu_lock);
+}
+
 struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu)
 {
 	bool nested_stage2_enabled;

92 lines not on this page · raw message

index 4a0317883cd0..4be090ceb2ba 100644
@@ -2728,6 +2728,22 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG(SP_EL2, NULL, reset_unknown, 0),
 };
 
+static bool kvm_supported_tlbi_s12_op(struct kvm_vcpu *vpcu, u32 instr)
+{
+	struct kvm *kvm = vpcu->kvm;
+	u8 CRm = sys_reg_CRm(instr);
+
+	if (sys_reg_CRn(instr) == TLBI_CRn_nXS &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP))
+		return false;
+
+	if (CRm == TLBI_CRm_nROS &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
+		return false;
+
+	return true;
+}
+
 /* Only defined here as this is an internal "abstraction" */
 union tlbi_info {
 	struct {

@@ -2745,6 +2761,38 @@ union tlbi_info {
 	} va;
 };
 
+static void s2_mmu_unmap_stage2_range(struct kvm_s2_mmu *mmu,
+				      const union tlbi_info *info)
+{
+	kvm_unmap_stage2_range(mmu, info->range.start, info->range.size);
+}
+
+static bool handle_vmalls12e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+				const struct sys_reg_desc *r)
+{
+	u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
+	u64 limit, vttbr;
+
+	if (!kvm_supported_tlbi_s12_op(vcpu, sys_encoding)) {
+		kvm_inject_undefined(vcpu);
+		return false;
+	}
+
+	vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+	limit = BIT_ULL(kvm_get_pa_bits(vcpu->kvm));
+
+	kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, get_vmid(vttbr),
+				   &(union tlbi_info) {
+					   .range = {
+						   .start = 0,
+						   .size = limit,
+					   },
+				   },
+				   s2_mmu_unmap_stage2_range);
+
+	return true;
+}
+
 static void s2_mmu_tlbi_s1e1(struct kvm_s2_mmu *mmu,
 			     const union tlbi_info *info)
 {

@@ -2818,6 +2866,9 @@ static struct sys_reg_desc sys_insn_descs[] = {
 	SYS_INSN(TLBI_VAAE1, handle_tlbi_el1),
 	SYS_INSN(TLBI_VALE1, handle_tlbi_el1),
 	SYS_INSN(TLBI_VAALE1, handle_tlbi_el1),
+
+	SYS_INSN(TLBI_VMALLS12E1IS, handle_vmalls12e1is),
+	SYS_INSN(TLBI_VMALLS12E1, handle_vmalls12e1is),
 };
 
 static const struct sys_reg_desc *first_idreg;

index 4be090ceb2ba..24e7d9c494c4 100644
@@ -2744,6 +2744,29 @@ static bool kvm_supported_tlbi_s12_op(struct kvm_vcpu *vpcu, u32 instr)
 	return true;
 }
 
+static bool handle_alle1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
+
+	if (!kvm_supported_tlbi_s12_op(vcpu, sys_encoding)) {
+		kvm_inject_undefined(vcpu);
+		return false;
+	}
+
+	write_lock(&vcpu->kvm->mmu_lock);
+
+	/*
+	 * Drop all shadow S2s, resulting in S1/S2 TLBIs for each of the
+	 * corresponding VMIDs.
+	 */
+	kvm_nested_s2_unmap(vcpu->kvm);
+
+	write_unlock(&vcpu->kvm->mmu_lock);
+
+	return true;
+}
+
 /* Only defined here as this is an internal "abstraction" */
 union tlbi_info {
 	struct {

@@ -2867,7 +2890,9 @@ static struct sys_reg_desc sys_insn_descs[] = {
 	SYS_INSN(TLBI_VALE1, handle_tlbi_el1),
 	SYS_INSN(TLBI_VAALE1, handle_tlbi_el1),
 
+	SYS_INSN(TLBI_ALLE1IS, handle_alle1is),
 	SYS_INSN(TLBI_VMALLS12E1IS, handle_vmalls12e1is),
+	SYS_INSN(TLBI_ALLE1, handle_alle1is),
 	SYS_INSN(TLBI_VMALLS12E1, handle_vmalls12e1is),
 };
 

index 24e7d9c494c4..ce477867ec03 100644
@@ -2767,6 +2767,31 @@ static bool handle_alle1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	return true;
 }
 
+static bool kvm_supported_tlbi_ipas2_op(struct kvm_vcpu *vpcu, u32 instr)
+{
+	struct kvm *kvm = vpcu->kvm;
+	u8 CRm = sys_reg_CRm(instr);
+	u8 Op2 = sys_reg_Op2(instr);
+
+	if (sys_reg_CRn(instr) == TLBI_CRn_nXS &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP))
+		return false;
+
+	if (CRm == TLBI_CRm_IPAIS && (Op2 == 2 || Op2 == 6) &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
+		return false;
+
+	if (CRm == TLBI_CRm_IPAONS && (Op2 == 0 || Op2 == 4) &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
+		return false;
+
+	if (CRm == TLBI_CRm_IPAONS && (Op2 == 3 || Op2 == 7) &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
+		return false;
+
+	return true;
+}
+
 /* Only defined here as this is an internal "abstraction" */
 union tlbi_info {
 	struct {

@@ -2816,6 +2841,72 @@ static bool handle_vmalls12e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	return true;
 }
 
+static void s2_mmu_unmap_stage2_ipa(struct kvm_s2_mmu *mmu,
+				    const union tlbi_info *info)
+{
+	unsigned long max_size;
+	u64 base_addr;
+
+	/*
+	 * We drop a number of things from the supplied value:
+	 *
+	 * - NS bit: we're non-secure only.
+	 *
+	 * - TTL field: We already have the granule size from the
+	 *   VTCR_EL2.TG0 field, and the level is only relevant to the
+	 *   guest's S2PT.
+	 *
+	 * - IPA[51:48]: We don't support 52bit IPA just yet...
+	 *
+	 * And of course, adjust the IPA to be on an actual address.
+	 */
+	base_addr = (info->ipa.addr & GENMASK_ULL(35, 0)) << 12;
+
+	/* Compute the maximum extent of the invalidation */
+	switch (mmu->tlb_vtcr & VTCR_EL2_TG0_MASK) {
+	case VTCR_EL2_TG0_4K:
+		max_size = SZ_1G;
+		break;
+	case VTCR_EL2_TG0_16K:
+		max_size = SZ_32M;
+		break;
+	case VTCR_EL2_TG0_64K:
+	default:	    /* IMPDEF: treat any other value as 64k */
+		/*
+		 * No, we do not support 52bit IPA in nested yet. Once
+		 * we do, this should be 4TB.
+		 */
+		max_size = SZ_512M;
+		break;
+	}
+
+	base_addr &= ~(max_size - 1);
+
+	kvm_unmap_stage2_range(mmu, base_addr, max_size);
+}
+
+static bool handle_ipas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			     const struct sys_reg_desc *r)
+{
+	u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
+	u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+
+	if (!kvm_supported_tlbi_ipas2_op(vcpu, sys_encoding)) {
+		kvm_inject_undefined(vcpu);
+		return false;
+	}
+
+	kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, get_vmid(vttbr),
+				   &(union tlbi_info) {
+					   .ipa = {
+						   .addr = p->regval,
+					   },
+				   },
+				   s2_mmu_unmap_stage2_ipa);
+
+	return true;
+}
+
 static void s2_mmu_tlbi_s1e1(struct kvm_s2_mmu *mmu,
 			     const union tlbi_info *info)
 {

@@ -2890,8 +2981,13 @@ static struct sys_reg_desc sys_insn_descs[] = {
 	SYS_INSN(TLBI_VALE1, handle_tlbi_el1),
 	SYS_INSN(TLBI_VAALE1, handle_tlbi_el1),
 
+	SYS_INSN(TLBI_IPAS2E1IS, handle_ipas2e1is),
+	SYS_INSN(TLBI_IPAS2LE1IS, handle_ipas2e1is),
+
 	SYS_INSN(TLBI_ALLE1IS, handle_alle1is),
 	SYS_INSN(TLBI_VMALLS12E1IS, handle_vmalls12e1is),
+	SYS_INSN(TLBI_IPAS2E1, handle_ipas2e1is),
+	SYS_INSN(TLBI_IPAS2LE1, handle_ipas2e1is),
 	SYS_INSN(TLBI_ALLE1, handle_alle1is),
 	SYS_INSN(TLBI_VMALLS12E1, handle_vmalls12e1is),
 };

index 6b647a169f5d..ec79e16d8436 100644
@@ -123,6 +123,8 @@ extern void kvm_nested_s2_wp(struct kvm *kvm);
 extern void kvm_nested_s2_unmap(struct kvm *kvm);
 extern void kvm_nested_s2_flush(struct kvm *kvm);
 
+unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val);
+
 static inline bool kvm_supported_tlbi_s1e1_op(struct kvm_vcpu *vpcu, u32 instr)
 {
 	struct kvm *kvm = vpcu->kvm;

95 lines not on this page · raw message

index ce477867ec03..810ea3dd2088 100644
@@ -2852,34 +2852,12 @@ static void s2_mmu_unmap_stage2_ipa(struct kvm_s2_mmu *mmu,
 	 *
 	 * - NS bit: we're non-secure only.
 	 *
-	 * - TTL field: We already have the granule size from the
-	 *   VTCR_EL2.TG0 field, and the level is only relevant to the
-	 *   guest's S2PT.
-	 *
 	 * - IPA[51:48]: We don't support 52bit IPA just yet...
 	 *
 	 * And of course, adjust the IPA to be on an actual address.
 	 */
 	base_addr = (info->ipa.addr & GENMASK_ULL(35, 0)) << 12;
-
-	/* Compute the maximum extent of the invalidation */
-	switch (mmu->tlb_vtcr & VTCR_EL2_TG0_MASK) {
-	case VTCR_EL2_TG0_4K:
-		max_size = SZ_1G;
-		break;
-	case VTCR_EL2_TG0_16K:
-		max_size = SZ_32M;
-		break;
-	case VTCR_EL2_TG0_64K:
-	default:	    /* IMPDEF: treat any other value as 64k */
-		/*
-		 * No, we do not support 52bit IPA in nested yet. Once
-		 * we do, this should be 4TB.
-		 */
-		max_size = SZ_512M;
-		break;
-	}
-
+	max_size = compute_tlb_inval_range(mmu, info->ipa.addr);
 	base_addr &= ~(max_size - 1);
 
 	kvm_unmap_stage2_range(mmu, base_addr, max_size);

index ec79e16d8436..3119e0a195dc 100644
@@ -5,6 +5,7 @@
 #include <linux/bitfield.h>
 #include <linux/kvm_host.h>
 #include <asm/kvm_emulate.h>
+#include <asm/kvm_pgtable.h>
 
 static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
 {

@@ -182,4 +183,11 @@ static inline bool kvm_supported_tlbi_s1e2_op(struct kvm_vcpu *vpcu, u32 instr)
 
 int kvm_init_nv_sysregs(struct kvm *kvm);
 
+#define KVM_NV_GUEST_MAP_SZ	(KVM_PGTABLE_PROT_SW1 | KVM_PGTABLE_PROT_SW0)
+
+static inline u64 kvm_encode_nested_level(struct kvm_s2_trans *trans)
+{
+	return FIELD_PREP(KVM_NV_GUEST_MAP_SZ, trans->level);
+}
+
 #endif /* __ARM64_KVM_NESTED_H */

index cf31da306622..0412c3c07c75 100644
@@ -1606,11 +1606,17 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * Potentially reduce shadow S2 permissions to match the guest's own
 	 * S2. For exec faults, we'd only reach this point if the guest
 	 * actually allowed it (see kvm_s2_handle_perm_fault).
+	 *
+	 * Also encode the level of the nested translation in the SW bits of
+	 * the PTE/PMD/PUD. This will be retrived on TLB invalidation from
+	 * the guest.
 	 */
 	if (nested) {
 		writable &= kvm_s2_trans_writable(nested);
 		if (!kvm_s2_trans_readable(nested))
 			prot &= ~KVM_PGTABLE_PROT_R;
+
+		prot |= kvm_encode_nested_level(nested);
 	}
 
 	read_lock(&kvm->mmu_lock);

@@ -1667,14 +1673,20 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * permissions only if vma_pagesize equals fault_granule. Otherwise,
 	 * kvm_pgtable_stage2_map() should be called to change block size.
 	 */
-	if (fault_is_perm && vma_pagesize == fault_granule)
+	if (fault_is_perm && vma_pagesize == fault_granule) {
+		/*
+		 * Drop the SW bits in favour of those stored in the
+		 * PTE, which will be preserved.
+		 */
+		prot &= ~KVM_NV_GUEST_MAP_SZ;
 		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
-	else
+	} else {
 		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
 					     __pfn_to_phys(pfn), prot,
 					     memcache,
 					     KVM_PGTABLE_WALK_HANDLE_FAULT |
 					     KVM_PGTABLE_WALK_SHARED);
+	}
 
 	/* Mark the page dirty only if the fault is handled successfully */
 	if (writable && !ret) {

index 5abdf82bb9a4..8163f7308b82 100644
@@ -4,6 +4,7 @@
  * Author: Jintack Lim <[email protected]>
  */
 
+#include <linux/bitfield.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 

@@ -405,12 +406,92 @@ static unsigned int ttl_to_size(u8 ttl)
 	return max_size;
 }
 
+/*
+ * Compute the equivalent of the TTL field by parsing the shadow PT.  The
+ * granule size is extracted from the cached VTCR_EL2.TG0 while the level is
+ * retrieved from first entry carrying the level as a tag.
+ */
+static u8 get_guest_mapping_ttl(struct kvm_s2_mmu *mmu, u64 addr)
+{
+	u64 tmp, sz = 0, vtcr = mmu->tlb_vtcr;
+	kvm_pte_t pte;
+	u8 ttl, level;
+
+	switch (vtcr & VTCR_EL2_TG0_MASK) {
+	case VTCR_EL2_TG0_4K:
+		ttl = (TLBI_TTL_TG_4K << 2);
+		break;
+	case VTCR_EL2_TG0_16K:
+		ttl = (TLBI_TTL_TG_16K << 2);
+		break;
+	case VTCR_EL2_TG0_64K:
+	default:	    /* IMPDEF: treat any other value as 64k */
+		ttl = (TLBI_TTL_TG_64K << 2);
+		break;
+	}
+
+	tmp = addr;
+
+again:
+	/* Iteratively compute the block sizes for a particular granule size */
+	switch (vtcr & VTCR_EL2_TG0_MASK) {
+	case VTCR_EL2_TG0_4K:
+		if	(sz < SZ_4K)	sz = SZ_4K;
+		else if (sz < SZ_2M)	sz = SZ_2M;
+		else if (sz < SZ_1G)	sz = SZ_1G;
+		else			sz = 0;
+		break;
+	case VTCR_EL2_TG0_16K:
+		if	(sz < SZ_16K)	sz = SZ_16K;
+		else if (sz < SZ_32M)	sz = SZ_32M;
+		else			sz = 0;
+		break;
+	case VTCR_EL2_TG0_64K:
+	default:	    /* IMPDEF: treat any other value as 64k */
+		if	(sz < SZ_64K)	sz = SZ_64K;
+		else if (sz < SZ_512M)	sz = SZ_512M;
+		else			sz = 0;
+		break;
+	}
+
+	if (sz == 0)
+		return 0;
+
+	tmp &= ~(sz - 1);
+	if (kvm_pgtable_get_leaf(mmu->pgt, tmp, &pte, NULL))
+		goto again;
+	if (!(pte & PTE_VALID))
+		goto again;
+	level = FIELD_GET(KVM_NV_GUEST_MAP_SZ, pte);
+	if (!level)
+		goto again;
+
+	ttl |= level;
+
+	/*
+	 * We now have found some level information in the shadow S2. Check
+	 * that the resulting range is actually including the original IPA.
+	 */
+	sz = ttl_to_size(ttl);
+	if (addr < (tmp + sz))
+		return ttl;
+
+	return 0;
+}
+
 unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val)
 {
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
 	unsigned long max_size;
 	u8 ttl;
 
-	ttl = FIELD_GET(GENMASK_ULL(47, 44), val);
+	ttl = FIELD_GET(TLBI_TTL_MASK, val);
+
+	if (!ttl || !kvm_has_feat(kvm, ID_AA64MMFR2_EL1, TTL, IMP)) {
+		/* No TTL, check the shadow S2 for a hint */
+		u64 addr = (val & GENMASK_ULL(35, 0)) << 12;
+		ttl = get_guest_mapping_ttl(mmu, addr);
+	}
 
 	max_size = ttl_to_size(ttl);
 

index 7ffc3f4b09f0..a5e6c01ccdde 100644
@@ -226,6 +226,7 @@ void __kvm_flush_vm_context(void)
  *
  * - a TLBI targeting EL2 S1 is remapped to EL1 S1
  * - a non-shareable TLBI is upgraded to being inner-shareable
+ * - an outer-shareable TLBI is also mapped to inner-shareable
  */
 int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
 {

@@ -245,32 +246,41 @@ int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
 	switch (sys_encoding) {
 	case OP_TLBI_ALLE2:
 	case OP_TLBI_ALLE2IS:
+	case OP_TLBI_ALLE2OS:
 	case OP_TLBI_VMALLE1:
 	case OP_TLBI_VMALLE1IS:
+	case OP_TLBI_VMALLE1OS:
 		__tlbi(vmalle1is);
 		break;
 	case OP_TLBI_VAE2:
 	case OP_TLBI_VAE2IS:
+	case OP_TLBI_VAE2OS:
 	case OP_TLBI_VAE1:
 	case OP_TLBI_VAE1IS:
+	case OP_TLBI_VAE1OS:
 		__tlbi(vae1is, va);
 		break;
 	case OP_TLBI_VALE2:
 	case OP_TLBI_VALE2IS:
+	case OP_TLBI_VALE2OS:
 	case OP_TLBI_VALE1:
 	case OP_TLBI_VALE1IS:
+	case OP_TLBI_VALE1OS:
 		__tlbi(vale1is, va);
 		break;
 	case OP_TLBI_ASIDE1:
 	case OP_TLBI_ASIDE1IS:
+	case OP_TLBI_ASIDE1OS:
 		__tlbi(aside1is, va);
 		break;
 	case OP_TLBI_VAAE1:
 	case OP_TLBI_VAAE1IS:
+	case OP_TLBI_VAAE1OS:
 		__tlbi(vaae1is, va);
 		break;
 	case OP_TLBI_VAALE1:
 	case OP_TLBI_VAALE1IS:
+	case OP_TLBI_VAALE1OS:
 		__tlbi(vaale1is, va);
 		break;
 	default:

index 8163f7308b82..f9487c04840a 100644
@@ -791,9 +791,12 @@ static u64 limit_nv_id_reg(u32 id, u64 val)
 
 	switch (id) {
 	case SYS_ID_AA64ISAR0_EL1:
-		/* Support everything but TME, O.S. and Range TLBIs */
+		/* Support everything but TME and Range TLBIs */
+		tmp = FIELD_GET(NV_FTR(ISAR0, TLB), val);
+		tmp = min(tmp, ID_AA64ISAR0_EL1_TLB_OS);
 		val &= ~(NV_FTR(ISAR0, TLB)		|
 			 NV_FTR(ISAR0, TME));
+		val |= FIELD_PREP(NV_FTR(ISAR0, TLB), tmp);
 		break;
 
 	case SYS_ID_AA64ISAR1_EL1:

index 810ea3dd2088..a7c5fa320cda 100644
@@ -2946,6 +2946,13 @@ static struct sys_reg_desc sys_insn_descs[] = {
 	{ SYS_DESC(SYS_DC_CIGSW), access_dcgsw },
 	{ SYS_DESC(SYS_DC_CIGDSW), access_dcgsw },
 
+	SYS_INSN(TLBI_VMALLE1OS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAE1OS, handle_tlbi_el1),
+	SYS_INSN(TLBI_ASIDE1OS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAAE1OS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VALE1OS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAALE1OS, handle_tlbi_el1),
+
 	SYS_INSN(TLBI_VMALLE1IS, handle_tlbi_el1),
 	SYS_INSN(TLBI_VAE1IS, handle_tlbi_el1),
 	SYS_INSN(TLBI_ASIDE1IS, handle_tlbi_el1),

@@ -2962,9 +2969,17 @@ static struct sys_reg_desc sys_insn_descs[] = {
 	SYS_INSN(TLBI_IPAS2E1IS, handle_ipas2e1is),
 	SYS_INSN(TLBI_IPAS2LE1IS, handle_ipas2e1is),
 
+	SYS_INSN(TLBI_ALLE2OS, trap_undef),
+	SYS_INSN(TLBI_VAE2OS, trap_undef),
+	SYS_INSN(TLBI_ALLE1OS, handle_alle1is),
+	SYS_INSN(TLBI_VALE2OS, trap_undef),
+	SYS_INSN(TLBI_VMALLS12E1OS, handle_vmalls12e1is),
+
 	SYS_INSN(TLBI_ALLE1IS, handle_alle1is),
 	SYS_INSN(TLBI_VMALLS12E1IS, handle_vmalls12e1is),
+	SYS_INSN(TLBI_IPAS2E1OS, handle_ipas2e1is),
 	SYS_INSN(TLBI_IPAS2E1, handle_ipas2e1is),
+	SYS_INSN(TLBI_IPAS2LE1OS, handle_ipas2e1is),
 	SYS_INSN(TLBI_IPAS2LE1, handle_ipas2e1is),
 	SYS_INSN(TLBI_ALLE1, handle_alle1is),
 	SYS_INSN(TLBI_VMALLS12E1, handle_vmalls12e1is),

index a5e6c01ccdde..8afaa237f5d4 100644
@@ -283,6 +283,32 @@ int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
 	case OP_TLBI_VAALE1OS:
 		__tlbi(vaale1is, va);
 		break;
+	case OP_TLBI_RVAE2:
+	case OP_TLBI_RVAE2IS:
+	case OP_TLBI_RVAE2OS:
+	case OP_TLBI_RVAE1:
+	case OP_TLBI_RVAE1IS:
+	case OP_TLBI_RVAE1OS:
+		__tlbi(rvae1is, va);
+		break;
+	case OP_TLBI_RVALE2:
+	case OP_TLBI_RVALE2IS:
+	case OP_TLBI_RVALE2OS:
+	case OP_TLBI_RVALE1:
+	case OP_TLBI_RVALE1IS:
+	case OP_TLBI_RVALE1OS:
+		__tlbi(rvale1is, va);
+		break;
+	case OP_TLBI_RVAAE1:
+	case OP_TLBI_RVAAE1IS:
+	case OP_TLBI_RVAAE1OS:
+		__tlbi(rvaae1is, va);
+		break;
+	case OP_TLBI_RVAALE1:
+	case OP_TLBI_RVAALE1IS:
+	case OP_TLBI_RVAALE1OS:
+		__tlbi(rvaale1is, va);
+		break;
 	default:
 		ret = -EINVAL;
 	}

index f9487c04840a..c63824479647 100644
@@ -791,12 +791,8 @@ static u64 limit_nv_id_reg(u32 id, u64 val)
 
 	switch (id) {
 	case SYS_ID_AA64ISAR0_EL1:
-		/* Support everything but TME and Range TLBIs */
-		tmp = FIELD_GET(NV_FTR(ISAR0, TLB), val);
-		tmp = min(tmp, ID_AA64ISAR0_EL1_TLB_OS);
-		val &= ~(NV_FTR(ISAR0, TLB)		|
-			 NV_FTR(ISAR0, TME));
-		val |= FIELD_PREP(NV_FTR(ISAR0, TLB), tmp);
+		/* Support everything but TME */
+		val &= ~NV_FTR(ISAR0, TME);
 		break;
 
 	case SYS_ID_AA64ISAR1_EL1:

117 lines not on this page · raw message

index 8afaa237f5d4..c43ecbce1201 100644
@@ -227,6 +227,7 @@ void __kvm_flush_vm_context(void)
  * - a TLBI targeting EL2 S1 is remapped to EL1 S1
  * - a non-shareable TLBI is upgraded to being inner-shareable
  * - an outer-shareable TLBI is also mapped to inner-shareable
+ * - an nXS TLBI is upgraded to XS
  */
 int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
 {

@@ -250,6 +251,12 @@ int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
 	case OP_TLBI_VMALLE1:
 	case OP_TLBI_VMALLE1IS:
 	case OP_TLBI_VMALLE1OS:
+	case OP_TLBI_ALLE2NXS:
+	case OP_TLBI_ALLE2ISNXS:
+	case OP_TLBI_ALLE2OSNXS:
+	case OP_TLBI_VMALLE1NXS:
+	case OP_TLBI_VMALLE1ISNXS:
+	case OP_TLBI_VMALLE1OSNXS:
 		__tlbi(vmalle1is);
 		break;
 	case OP_TLBI_VAE2:

@@ -258,6 +265,12 @@ int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
 	case OP_TLBI_VAE1:
 	case OP_TLBI_VAE1IS:
 	case OP_TLBI_VAE1OS:
+	case OP_TLBI_VAE2NXS:
+	case OP_TLBI_VAE2ISNXS:
+	case OP_TLBI_VAE2OSNXS:
+	case OP_TLBI_VAE1NXS:
+	case OP_TLBI_VAE1ISNXS:
+	case OP_TLBI_VAE1OSNXS:
 		__tlbi(vae1is, va);
 		break;
 	case OP_TLBI_VALE2:

@@ -266,21 +279,36 @@ int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
 	case OP_TLBI_VALE1:
 	case OP_TLBI_VALE1IS:
 	case OP_TLBI_VALE1OS:
+	case OP_TLBI_VALE2NXS:
+	case OP_TLBI_VALE2ISNXS:
+	case OP_TLBI_VALE2OSNXS:
+	case OP_TLBI_VALE1NXS:
+	case OP_TLBI_VALE1ISNXS:
+	case OP_TLBI_VALE1OSNXS:
 		__tlbi(vale1is, va);
 		break;
 	case OP_TLBI_ASIDE1:
 	case OP_TLBI_ASIDE1IS:
 	case OP_TLBI_ASIDE1OS:
+	case OP_TLBI_ASIDE1NXS:
+	case OP_TLBI_ASIDE1ISNXS:
+	case OP_TLBI_ASIDE1OSNXS:
 		__tlbi(aside1is, va);
 		break;
 	case OP_TLBI_VAAE1:
 	case OP_TLBI_VAAE1IS:
 	case OP_TLBI_VAAE1OS:
+	case OP_TLBI_VAAE1NXS:
+	case OP_TLBI_VAAE1ISNXS:
+	case OP_TLBI_VAAE1OSNXS:
 		__tlbi(vaae1is, va);
 		break;
 	case OP_TLBI_VAALE1:
 	case OP_TLBI_VAALE1IS:
 	case OP_TLBI_VAALE1OS:
+	case OP_TLBI_VAALE1NXS:
+	case OP_TLBI_VAALE1ISNXS:
+	case OP_TLBI_VAALE1OSNXS:
 		__tlbi(vaale1is, va);
 		break;
 	case OP_TLBI_RVAE2:

@@ -289,6 +317,12 @@ int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
 	case OP_TLBI_RVAE1:
 	case OP_TLBI_RVAE1IS:
 	case OP_TLBI_RVAE1OS:
+	case OP_TLBI_RVAE2NXS:
+	case OP_TLBI_RVAE2ISNXS:
+	case OP_TLBI_RVAE2OSNXS:
+	case OP_TLBI_RVAE1NXS:
+	case OP_TLBI_RVAE1ISNXS:
+	case OP_TLBI_RVAE1OSNXS:
 		__tlbi(rvae1is, va);
 		break;
 	case OP_TLBI_RVALE2:

@@ -297,16 +331,28 @@ int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
 	case OP_TLBI_RVALE1:
 	case OP_TLBI_RVALE1IS:
 	case OP_TLBI_RVALE1OS:
+	case OP_TLBI_RVALE2NXS:
+	case OP_TLBI_RVALE2ISNXS:
+	case OP_TLBI_RVALE2OSNXS:
+	case OP_TLBI_RVALE1NXS:
+	case OP_TLBI_RVALE1ISNXS:
+	case OP_TLBI_RVALE1OSNXS:
 		__tlbi(rvale1is, va);
 		break;
 	case OP_TLBI_RVAAE1:
 	case OP_TLBI_RVAAE1IS:
 	case OP_TLBI_RVAAE1OS:
+	case OP_TLBI_RVAAE1NXS:
+	case OP_TLBI_RVAAE1ISNXS:
+	case OP_TLBI_RVAAE1OSNXS:
 		__tlbi(rvaae1is, va);
 		break;
 	case OP_TLBI_RVAALE1:
 	case OP_TLBI_RVAALE1IS:
 	case OP_TLBI_RVAALE1OS:
+	case OP_TLBI_RVAALE1NXS:
+	case OP_TLBI_RVAALE1ISNXS:
+	case OP_TLBI_RVAALE1OSNXS:
 		__tlbi(rvaale1is, va);
 		break;
 	default:

85 lines not on this page · raw message