Merge branch kvm-arm64/misc-6.18 into kvmarm-master/next

* kvm-arm64/misc-6.18:
: .
: .
: Misc improvements and bug fixes:
:
: - Fix XN handling in the S2 page table dumper
: ([e-mail])
:
: - Fix sanitity checks for huge mapping with pKVM running np guests
: ([e-mail])
:
: - Fix use of TRBE when KVM is disabled, and Linux running under
: a lesser hypervisor ([e-mail])
:
: - Fix out of date MTE-related comments ([e-mail])
:
: - Fix PSCI BE support when running a NV guest ([e-mail])
:
: - Fix page reference leak when refusing to map a page due to mismatched attributes
: ([e-mail])
:
: - Add trap handling for PMSDSFR_EL1
: ([e-mail])
:
: - Add advertisement from FEAT_LSFE (Large System Float Extension)
: ([e-mail])
: .
KVM: arm64: Expose FEAT_LSFE to guests
KVM: arm64: Add trap configs for PMSDSFR_EL1
KVM: arm64: Fix page leak in user_mem_abort()
KVM: arm64: Fix kvm_vcpu_{set,is}_be() to deal with EL2 state
KVM: arm64: Update stale comment for sanitise_mte_tags()
KVM: arm64: Return early from trace helpers when KVM isn't available
KVM: arm64: Fix debug checking for np-guests using huge mappings
KVM: arm64: ptdump: Don't test PTE_VALID alongside other attributes

Signed-off-by: Marc Zyngier <[e-mail]>

arch/arm64/include/asm/kvm_emulate.h

···
 	if (vcpu_mode_is_32bit(vcpu)) {
 		*vcpu_cpsr(vcpu) |= PSR_AA32_E_BIT;
 	} else {
-		u64 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
+		enum vcpu_sysreg r;
+		u64 sctlr;
+
+		r = vcpu_has_nv(vcpu) ? SCTLR_EL2 : SCTLR_EL1;
+
+		sctlr = vcpu_read_sys_reg(vcpu, r);
 		sctlr |= SCTLR_ELx_EE;
-		vcpu_write_sys_reg(vcpu, sctlr, SCTLR_EL1);
+		vcpu_write_sys_reg(vcpu, sctlr, r);
 	}
 }
 
 static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu)
 {
+	enum vcpu_sysreg r;
+	u64 bit;
+
 	if (vcpu_mode_is_32bit(vcpu))
 		return !!(*vcpu_cpsr(vcpu) & PSR_AA32_E_BIT);
 
-	if (vcpu_mode_priv(vcpu))
-		return !!(vcpu_read_sys_reg(vcpu, SCTLR_EL1) & SCTLR_ELx_EE);
-	else
-		return !!(vcpu_read_sys_reg(vcpu, SCTLR_EL1) & SCTLR_EL1_E0E);
+	r = is_hyp_ctxt(vcpu) ? SCTLR_EL2 : SCTLR_EL1;
+	bit = vcpu_mode_priv(vcpu) ? SCTLR_ELx_EE : SCTLR_EL1_E0E;
+
+	return vcpu_read_sys_reg(vcpu, r) & bit;
 }
 
 static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,

arch/arm64/include/asm/vncr_mapping.h

···
 #define VNCR_PMSICR_EL1         0x838
 #define VNCR_PMSIRR_EL1         0x840
 #define VNCR_PMSLATFR_EL1       0x848
+#define VNCR_PMSNEVFR_EL1       0x850
+#define VNCR_PMSDSFR_EL1        0x858
 #define VNCR_TRFCR_EL1          0x880
 #define VNCR_MPAM1_EL1          0x900
 #define VNCR_MPAMHCR_EL2        0x930

arch/arm64/kvm/debug.c

···
 	preempt_enable();
 }
 
+static bool skip_trbe_access(bool skip_condition)
+{
+	return (WARN_ON_ONCE(preemptible()) || skip_condition ||
+		is_protected_kvm_enabled() || !is_kvm_arm_initialised());
+}
+
 void kvm_enable_trbe(void)
 {
-	if (has_vhe() || is_protected_kvm_enabled() ||
-	    WARN_ON_ONCE(preemptible()))
-		return;
-
-	host_data_set_flag(TRBE_ENABLED);
+	if (!skip_trbe_access(has_vhe()))
+		host_data_set_flag(TRBE_ENABLED);
 }
 EXPORT_SYMBOL_GPL(kvm_enable_trbe);
 
 void kvm_disable_trbe(void)
 {
-	if (has_vhe() || is_protected_kvm_enabled() ||
-	    WARN_ON_ONCE(preemptible()))
-		return;
-
-	host_data_clear_flag(TRBE_ENABLED);
+	if (!skip_trbe_access(has_vhe()))
+		host_data_clear_flag(TRBE_ENABLED);
 }
 EXPORT_SYMBOL_GPL(kvm_disable_trbe);
 
 void kvm_tracing_set_el1_configuration(u64 trfcr_while_in_guest)
 {
-	if (is_protected_kvm_enabled() || WARN_ON_ONCE(preemptible()))
+	if (skip_trbe_access(false))
 		return;
 
 	if (has_vhe()) {

arch/arm64/kvm/emulate-nested.c

···
 	SR_TRAP(SYS_PMSIRR_EL1,		CGT_MDCR_TPMS),
 	SR_TRAP(SYS_PMSLATFR_EL1,	CGT_MDCR_TPMS),
 	SR_TRAP(SYS_PMSNEVFR_EL1,	CGT_MDCR_TPMS),
+	SR_TRAP(SYS_PMSDSFR_EL1,	CGT_MDCR_TPMS),
 	SR_TRAP(SYS_TRFCR_EL1,		CGT_MDCR_TTRF),
 	SR_TRAP(SYS_TRBBASER_EL1,	CGT_MDCR_E2TB),
 	SR_TRAP(SYS_TRBLIMITR_EL1,	CGT_MDCR_E2TB),

arch/arm64/kvm/hyp/nvhe/mem_protect.c

···
 		return ret;
 	if (!kvm_pte_valid(pte))
 		return -ENOENT;
-	if (kvm_granule_size(level) != size)
+	if (size && kvm_granule_size(level) != size)
 		return -E2BIG;
+
+	if (!size)
+		size = kvm_granule_size(level);
 
 	state = guest_get_page_state(pte, ipa);
 	if (state != PKVM_PAGE_SHARED_BORROWED)
···
 	if (prot & ~KVM_PGTABLE_PROT_RWX)
 		return -EINVAL;
 
-	assert_host_shared_guest(vm, ipa, PAGE_SIZE);
+	assert_host_shared_guest(vm, ipa, 0);
 	guest_lock_component(vm);
 	ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0);
 	guest_unlock_component(vm);
···
 	if (pkvm_hyp_vm_is_protected(vm))
 		return -EPERM;
 
-	assert_host_shared_guest(vm, ipa, PAGE_SIZE);
+	assert_host_shared_guest(vm, ipa, 0);
 	guest_lock_component(vm);
 	kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0);
 	guest_unlock_component(vm);

arch/arm64/kvm/mmu.c

···
  * able to see the page's tags and therefore they must be initialised first. If
  * PG_mte_tagged is set, tags have already been initialised.
  *
- * The race in the test/set of the PG_mte_tagged flag is handled by:
- * - preventing VM_SHARED mappings in a memslot with MTE preventing two VMs
- *   racing to santise the same page
- * - mmap_lock protects between a VM faulting a page in and the VMM performing
- *   an mprotect() to add VM_MTE
+ * Must be called with kvm->mmu_lock held to ensure the memory remains mapped
+ * while the tags are zeroed.
  */
 static void sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn,
 			      unsigned long size)
···
 			 * cache maintenance.
 			 */
 			if (!kvm_supports_cacheable_pfnmap())
-				return -EFAULT;
+				ret = -EFAULT;
 		} else {
 			/*
 			 * If the page was identified as device early by looking at
···
 	}
 
 	if (exec_fault && s2_force_noncacheable)
-		return -ENOEXEC;
+		ret = -ENOEXEC;
+
+	if (ret) {
+		kvm_release_page_unused(page);
+		return ret;
+	}
 
 	/*
 	 * Potentially reduce shadow S2 permissions to match the guest's own

arch/arm64/kvm/ptdump.c

···
 		.set	= " ",
 		.clear	= "F",
 	}, {
-		.mask	= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R | PTE_VALID,
-		.val	= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R | PTE_VALID,
+		.mask	= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R,
+		.val	= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R,
 		.set	= "R",
 		.clear	= " ",
 	}, {
-		.mask	= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W | PTE_VALID,
-		.val	= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W | PTE_VALID,
+		.mask	= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W,
+		.val	= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W,
 		.set	= "W",
 		.clear	= " ",
 	}, {
-		.mask	= KVM_PTE_LEAF_ATTR_HI_S2_XN | PTE_VALID,
-		.val	= PTE_VALID,
-		.set	= " ",
-		.clear	= "X",
+		.mask	= KVM_PTE_LEAF_ATTR_HI_S2_XN,
+		.val	= KVM_PTE_LEAF_ATTR_HI_S2_XN,
+		.set	= "NX",
+		.clear	= "x ",
 	}, {
-		.mask	= KVM_PTE_LEAF_ATTR_LO_S2_AF | PTE_VALID,
-		.val	= KVM_PTE_LEAF_ATTR_LO_S2_AF | PTE_VALID,
+		.mask	= KVM_PTE_LEAF_ATTR_LO_S2_AF,
+		.val	= KVM_PTE_LEAF_ATTR_LO_S2_AF,
 		.set	= "AF",
 		.clear	= "  ",
 	}, {

arch/arm64/kvm/sys_regs.c

···
 			val &= ~ID_AA64ISAR2_EL1_WFxT;
 		break;
 	case SYS_ID_AA64ISAR3_EL1:
-		val &= ID_AA64ISAR3_EL1_FPRCVT | ID_AA64ISAR3_EL1_FAMINMAX;
+		val &= ID_AA64ISAR3_EL1_FPRCVT | ID_AA64ISAR3_EL1_LSFE |
+			ID_AA64ISAR3_EL1_FAMINMAX;
 		break;
 	case SYS_ID_AA64MMFR2_EL1:
 		val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK;
···
 					ID_AA64ISAR2_EL1_APA3 |
 					ID_AA64ISAR2_EL1_GPA3)),
 	ID_WRITABLE(ID_AA64ISAR3_EL1, (ID_AA64ISAR3_EL1_FPRCVT |
+				       ID_AA64ISAR3_EL1_LSFE |
 				       ID_AA64ISAR3_EL1_FAMINMAX)),
 	ID_UNALLOCATED(6,4),
 	ID_UNALLOCATED(6,5),
···
 	{ SYS_DESC(SYS_PMBLIMITR_EL1), undef_access },
 	{ SYS_DESC(SYS_PMBPTR_EL1), undef_access },
 	{ SYS_DESC(SYS_PMBSR_EL1), undef_access },
+	{ SYS_DESC(SYS_PMSDSFR_EL1), undef_access },
 	/* PMBIDR_EL1 is not trapped */
 
 	{ PMU_SYS_REG(PMINTENSET_EL1),