1 files changed, 173 insertions, 184 deletions

diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 30b7ea680f66..5ae18472205a 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -25,7 +25,6 @@
 #include <asm/ptrace.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
-#include <asm/kvm_coproc.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
 #include <asm/virt.h>
@@ -36,93 +35,33 @@ static u32 kvm_ipa_limit;
 /*
  * ARMv8 Reset Values
  */
-static const struct kvm_regs default_regs_reset = {
-	.regs.pstate = (PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT |
-			PSR_F_BIT | PSR_D_BIT),
-};
+#define VCPU_RESET_PSTATE_EL1	(PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | \
+				 PSR_F_BIT | PSR_D_BIT)
 
-static const struct kvm_regs default_regs_reset32 = {
-	.regs.pstate = (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT |
-			PSR_AA32_I_BIT | PSR_AA32_F_BIT),
-};
-
-static bool cpu_has_32bit_el1(void)
-{
-	u64 pfr0;
-
-	pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
-	return !!(pfr0 & 0x20);
-}
-
-/**
- * kvm_arch_vm_ioctl_check_extension
- *
- * We currently assume that the number of HW registers is uniform
- * across all CPUs (see cpuinfo_sanity_check).
- */
-int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
-{
-	int r;
-
-	switch (ext) {
-	case KVM_CAP_ARM_EL1_32BIT:
-		r = cpu_has_32bit_el1();
-		break;
-	case KVM_CAP_GUEST_DEBUG_HW_BPS:
-		r = get_num_brps();
-		break;
-	case KVM_CAP_GUEST_DEBUG_HW_WPS:
-		r = get_num_wrps();
-		break;
-	case KVM_CAP_ARM_PMU_V3:
-		r = kvm_arm_support_pmu_v3();
-		break;
-	case KVM_CAP_ARM_INJECT_SERROR_ESR:
-		r = cpus_have_const_cap(ARM64_HAS_RAS_EXTN);
-		break;
-	case KVM_CAP_SET_GUEST_DEBUG:
-	case KVM_CAP_VCPU_ATTRIBUTES:
-		r = 1;
-		break;
-	case KVM_CAP_ARM_VM_IPA_SIZE:
-		r = kvm_ipa_limit;
-		break;
-	case KVM_CAP_ARM_SVE:
-		r = system_supports_sve();
-		break;
-	case KVM_CAP_ARM_PTRAUTH_ADDRESS:
-	case KVM_CAP_ARM_PTRAUTH_GENERIC:
-		r = has_vhe() && system_supports_address_auth() &&
-				 system_supports_generic_auth();
-		break;
-	default:
-		r = 0;
-	}
-
-	return r;
-}
+#define VCPU_RESET_PSTATE_SVC	(PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \
+				 PSR_AA32_I_BIT | PSR_AA32_F_BIT)
 
 unsigned int kvm_sve_max_vl;
 
 int kvm_arm_init_sve(void)
 {
 	if (system_supports_sve()) {
-		kvm_sve_max_vl = sve_max_virtualisable_vl;
+		kvm_sve_max_vl = sve_max_virtualisable_vl();
 
 		/*
 		 * The get_sve_reg()/set_sve_reg() ioctl interface will need
 		 * to be extended with multiple register slice support in
 		 * order to support vector lengths greater than
-		 * SVE_VL_ARCH_MAX:
+		 * VL_ARCH_MAX:
 		 */
-		if (WARN_ON(kvm_sve_max_vl > SVE_VL_ARCH_MAX))
-			kvm_sve_max_vl = SVE_VL_ARCH_MAX;
+		if (WARN_ON(kvm_sve_max_vl > VL_ARCH_MAX))
+			kvm_sve_max_vl = VL_ARCH_MAX;
 
 		/*
 		 * Don't even try to make use of vector lengths that
 		 * aren't available on all CPUs, for now:
 		 */
-		if (kvm_sve_max_vl < sve_max_vl)
+		if (kvm_sve_max_vl < sve_max_vl())
 			pr_warn("KVM: SVE vector length for guests limited to %u bytes\n",
 				kvm_sve_max_vl);
 	}
@@ -135,10 +74,6 @@ static int kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu)
 	if (!system_supports_sve())
 		return -EINVAL;
 
-	/* Verify that KVM startup enforced this when SVE was detected: */
-	if (WARN_ON(!has_vhe()))
-		return -EINVAL;
-
 	vcpu->arch.sve_max_vl = kvm_sve_max_vl;
 
 	/*
@@ -146,7 +81,7 @@ static int kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu)
 	 * KVM_REG_ARM64_SVE_VLS.  Allocation is deferred until
 	 * kvm_arm_vcpu_finalize(), which freezes the configuration.
 	 */
-	vcpu->arch.flags |= KVM_ARM64_GUEST_HAS_SVE;
+	vcpu_set_flag(vcpu, GUEST_HAS_SVE);
 
 	return 0;
 }
@@ -159,24 +94,33 @@ static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu)
 {
 	void *buf;
 	unsigned int vl;
+	size_t reg_sz;
+	int ret;
 
 	vl = vcpu->arch.sve_max_vl;
 
 	/*
-	 * Resposibility for these properties is shared between
-	 * kvm_arm_init_arch_resources(), kvm_vcpu_enable_sve() and
+	 * Responsibility for these properties is shared between
+	 * kvm_arm_init_sve(), kvm_vcpu_enable_sve() and
 	 * set_sve_vls().  Double-check here just to be sure:
 	 */
-	if (WARN_ON(!sve_vl_valid(vl) || vl > sve_max_virtualisable_vl ||
-		    vl > SVE_VL_ARCH_MAX))
+	if (WARN_ON(!sve_vl_valid(vl) || vl > sve_max_virtualisable_vl() ||
+		    vl > VL_ARCH_MAX))
 		return -EIO;
 
-	buf = kzalloc(SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl)), GFP_KERNEL);
+	reg_sz = vcpu_sve_state_size(vcpu);
+	buf = kzalloc(reg_sz, GFP_KERNEL_ACCOUNT);
 	if (!buf)
 		return -ENOMEM;
 
+	ret = kvm_share_hyp(buf, buf + reg_sz);
+	if (ret) {
+		kfree(buf);
+		return ret;
+	}
+	
 	vcpu->arch.sve_state = buf;
-	vcpu->arch.flags |= KVM_ARM64_VCPU_SVE_FINALIZED;
+	vcpu_set_flag(vcpu, VCPU_SVE_FINALIZED);
 	return 0;
 }
 
@@ -206,7 +150,13 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu)
 
 void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
-	kfree(vcpu->arch.sve_state);
+	void *sve_state = vcpu->arch.sve_state;
+
+	kvm_vcpu_unshare_task_fp(vcpu);
+	kvm_unshare_hyp(vcpu, vcpu + 1);
+	if (sve_state)
+		kvm_unshare_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu));
+	kfree(sve_state);
 }
 
 static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
@@ -217,22 +167,64 @@ static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
 
 static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
 {
-	/* Support ptrauth only if the system supports these capabilities. */
-	if (!has_vhe())
-		return -EINVAL;
-
-	if (!system_supports_address_auth() ||
-	    !system_supports_generic_auth())
-		return -EINVAL;
 	/*
 	 * For now make sure that both address/generic pointer authentication
-	 * features are requested by the userspace together.
+	 * features are requested by the userspace together and the system
+	 * supports these capabilities.
 	 */
 	if (!test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
-	    !test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features))
+	    !test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features) ||
+	    !system_has_full_ptr_auth())
+		return -EINVAL;
+
+	vcpu_set_flag(vcpu, GUEST_HAS_PTRAUTH);
+	return 0;
+}
+
+/**
+ * kvm_set_vm_width() - set the register width for the guest
+ * @vcpu: Pointer to the vcpu being configured
+ *
+ * Set both KVM_ARCH_FLAG_EL1_32BIT and KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED
+ * in the VM flags based on the vcpu's requested register width, the HW
+ * capabilities and other options (such as MTE).
+ * When REG_WIDTH_CONFIGURED is already set, the vcpu settings must be
+ * consistent with the value of the FLAG_EL1_32BIT bit in the flags.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+static int kvm_set_vm_width(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	bool is32bit;
+
+	is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT);
+
+	lockdep_assert_held(&kvm->lock);
+
+	if (test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags)) {
+		/*
+		 * The guest's register width is already configured.
+		 * Make sure that the vcpu is consistent with it.
+		 */
+		if (is32bit == test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags))
+			return 0;
+
 		return -EINVAL;
+	}
+
+	if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit)
+		return -EINVAL;
+
+	/* MTE is incompatible with AArch32 */
+	if (kvm_has_mte(kvm) && is32bit)
+		return -EINVAL;
+
+	if (is32bit)
+		set_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags);
+
+	set_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags);
 
-	vcpu->arch.flags |= KVM_ARM64_GUEST_HAS_PTRAUTH;
 	return 0;
 }
 
@@ -240,16 +232,15 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
  * kvm_reset_vcpu - sets core registers and sys_regs to reset value
  * @vcpu: The VCPU pointer
  *
- * This function finds the right table above and sets the registers on
- * the virtual CPU struct to their architecturally defined reset
- * values, except for registers whose reset is deferred until
- * kvm_arm_vcpu_finalize().
+ * This function sets the registers on the virtual CPU struct to their
+ * architecturally defined reset values, except for registers whose reset is
+ * deferred until kvm_arm_vcpu_finalize().
  *
  * Note: This function can be called from two paths: The KVM_ARM_VCPU_INIT
  * ioctl or as part of handling a request issued by another VCPU in the PSCI
  * handling code.  In the first case, the VCPU will not be loaded, and in the
  * second case the VCPU will be loaded.  Because this function operates purely
- * on the memory-backed valus of system registers, we want to do a full put if
+ * on the memory-backed values of system registers, we want to do a full put if
  * we were loaded (handling a request) and load the values back at the end of
  * the function.  Otherwise we leave the state alone.  In both cases, we
  * disable preemption around the vcpu reset as we would otherwise race with
@@ -257,9 +248,21 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
  */
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {
-	const struct kvm_regs *cpu_reset;
-	int ret = -EINVAL;
+	struct vcpu_reset_state reset_state;
+	int ret;
 	bool loaded;
+	u32 pstate;
+
+	mutex_lock(&vcpu->kvm->lock);
+	ret = kvm_set_vm_width(vcpu);
+	if (!ret) {
+		reset_state = vcpu->arch.reset_state;
+		WRITE_ONCE(vcpu->arch.reset_state.reset, false);
+	}
+	mutex_unlock(&vcpu->kvm->lock);
+
+	if (ret)
+		return ret;
 
 	/* Reset PMU outside of the non-preemptible section */
 	kvm_pmu_vcpu_reset(vcpu);
@@ -281,25 +284,35 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 
 	if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
 	    test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) {
-		if (kvm_vcpu_enable_ptrauth(vcpu))
+		if (kvm_vcpu_enable_ptrauth(vcpu)) {
+			ret = -EINVAL;
 			goto out;
+		}
 	}
 
 	switch (vcpu->arch.target) {
 	default:
-		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
-			if (!cpu_has_32bit_el1())
-				goto out;
-			cpu_reset = &default_regs_reset32;
+		if (vcpu_el1_is_32bit(vcpu)) {
+			pstate = VCPU_RESET_PSTATE_SVC;
 		} else {
-			cpu_reset = &default_regs_reset;
+			pstate = VCPU_RESET_PSTATE_EL1;
 		}
 
+		if (kvm_vcpu_has_pmu(vcpu) && !kvm_arm_support_pmu_v3()) {
+			ret = -EINVAL;
+			goto out;
+		}
 		break;
 	}
 
 	/* Reset core registers */
-	memcpy(vcpu_gp_regs(vcpu), cpu_reset, sizeof(*cpu_reset));
+	memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu)));
+	memset(&vcpu->arch.ctxt.fp_regs, 0, sizeof(vcpu->arch.ctxt.fp_regs));
+	vcpu->arch.ctxt.spsr_abt = 0;
+	vcpu->arch.ctxt.spsr_und = 0;
+	vcpu->arch.ctxt.spsr_irq = 0;
+	vcpu->arch.ctxt.spsr_fiq = 0;
+	vcpu_gp_regs(vcpu)->pstate = pstate;
 
 	/* Reset system registers */
 	kvm_reset_sys_regs(vcpu);
@@ -308,8 +321,8 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	 * Additional reset state handling that PSCI may have imposed on us.
 	 * Must be done after all the sys_reg reset.
 	 */
-	if (vcpu->arch.reset_state.reset) {
-		unsigned long target_pc = vcpu->arch.reset_state.pc;
+	if (reset_state.reset) {
+		unsigned long target_pc = reset_state.pc;
 
 		/* Gracefully handle Thumb2 entry point */
 		if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) {
@@ -318,19 +331,13 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 		}
 
 		/* Propagate caller endianness */
-		if (vcpu->arch.reset_state.be)
+		if (reset_state.be)
 			kvm_vcpu_set_be(vcpu);
 
 		*vcpu_pc(vcpu) = target_pc;
-		vcpu_set_reg(vcpu, 0, vcpu->arch.reset_state.r0);
-
-		vcpu->arch.reset_state.reset = false;
+		vcpu_set_reg(vcpu, 0, reset_state.r0);
 	}
 
-	/* Default workaround setup is enabled (if supported) */
-	if (kvm_arm_have_ssbd() == KVM_SSBD_KERNEL)
-		vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG;
-
 	/* Reset timer */
 	ret = kvm_timer_vcpu_reset(vcpu);
 out:
@@ -340,59 +347,59 @@ out:
 	return ret;
 }
 
-void kvm_set_ipa_limit(void)
+u32 get_kvm_ipa_limit(void)
 {
-	unsigned int ipa_max, pa_max, va_max, parange;
+	return kvm_ipa_limit;
+}
 
-	parange = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1) & 0x7;
-	pa_max = id_aa64mmfr0_parange_to_phys_shift(parange);
+int kvm_set_ipa_limit(void)
+{
+	unsigned int parange;
+	u64 mmfr0;
 
-	/* Clamp the IPA limit to the PA size supported by the kernel */
-	ipa_max = (pa_max > PHYS_MASK_SHIFT) ? PHYS_MASK_SHIFT : pa_max;
+	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	parange = cpuid_feature_extract_unsigned_field(mmfr0,
+				ID_AA64MMFR0_EL1_PARANGE_SHIFT);
 	/*
-	 * Since our stage2 table is dependent on the stage1 page table code,
-	 * we must always honor the following condition:
-	 *
-	 *  Number of levels in Stage1 >= Number of levels in Stage2.
-	 *
-	 * So clamp the ipa limit further down to limit the number of levels.
-	 * Since we can concatenate upto 16 tables at entry level, we could
-	 * go upto 4bits above the maximum VA addressible with the current
-	 * number of levels.
+	 * IPA size beyond 48 bits could not be supported
+	 * on either 4K or 16K page size. Hence let's cap
+	 * it to 48 bits, in case it's reported as larger
+	 * on the system.
 	 */
-	va_max = PGDIR_SHIFT + PAGE_SHIFT - 3;
-	va_max += 4;
-
-	if (va_max < ipa_max)
-		ipa_max = va_max;
+	if (PAGE_SIZE != SZ_64K)
+		parange = min(parange, (unsigned int)ID_AA64MMFR0_EL1_PARANGE_48);
 
 	/*
-	 * If the final limit is lower than the real physical address
-	 * limit of the CPUs, report the reason.
+	 * Check with ARMv8.5-GTG that our PAGE_SIZE is supported at
+	 * Stage-2. If not, things will stop very quickly.
 	 */
-	if (ipa_max < pa_max)
-		pr_info("kvm: Limiting the IPA size due to kernel %s Address limit\n",
-			(va_max < pa_max) ? "Virtual" : "Physical");
-
-	WARN(ipa_max < KVM_PHYS_SHIFT,
-	     "KVM IPA limit (%d bit) is smaller than default size\n", ipa_max);
-	kvm_ipa_limit = ipa_max;
-	kvm_info("IPA Size Limit: %dbits\n", kvm_ipa_limit);
+	switch (cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN_2_SHIFT)) {
+	case ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_NONE:
+		kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n");
+		return -EINVAL;
+	case ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_DEFAULT:
+		kvm_debug("PAGE_SIZE supported at Stage-2 (default)\n");
+		break;
+	case ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MIN ... ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MAX:
+		kvm_debug("PAGE_SIZE supported at Stage-2 (advertised)\n");
+		break;
+	default:
+		kvm_err("Unsupported value for TGRAN_2, giving up\n");
+		return -EINVAL;
+	}
+
+	kvm_ipa_limit = id_aa64mmfr0_parange_to_phys_shift(parange);
+	kvm_info("IPA Size Limit: %d bits%s\n", kvm_ipa_limit,
+		 ((kvm_ipa_limit < KVM_PHYS_SHIFT) ?
+		  " (Reduced IPA size, limited VM/VMM compatibility)" : ""));
+
+	return 0;
 }
 
-/*
- * Configure the VTCR_EL2 for this VM. The VTCR value is common
- * across all the physical CPUs on the system. We use system wide
- * sanitised values to fill in different fields, except for Hardware
- * Management of Access Flags. HA Flag is set unconditionally on
- * all CPUs, as it is safe to run with or without the feature and
- * the bit is RES0 on CPUs that don't support it.
- */
 int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
 {
-	u64 vtcr = VTCR_EL2_FLAGS;
-	u32 parange, phys_shift;
-	u8 lvls;
+	u64 mmfr0, mmfr1;
+	u32 phys_shift;
 
 	if (type & ~KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
 		return -EINVAL;
@@ -400,38 +407,20 @@ int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
 	phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type);
 	if (phys_shift) {
 		if (phys_shift > kvm_ipa_limit ||
-		    phys_shift < 32)
+		    phys_shift < ARM64_MIN_PARANGE_BITS)
 			return -EINVAL;
 	} else {
 		phys_shift = KVM_PHYS_SHIFT;
+		if (phys_shift > kvm_ipa_limit) {
+			pr_warn_once("%s using unsupported default IPA limit, upgrade your VMM\n",
+				     current->comm);
+			return -EINVAL;
+		}
 	}
 
-	parange = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1) & 7;
-	if (parange > ID_AA64MMFR0_PARANGE_MAX)
-		parange = ID_AA64MMFR0_PARANGE_MAX;
-	vtcr |= parange << VTCR_EL2_PS_SHIFT;
-
-	vtcr |= VTCR_EL2_T0SZ(phys_shift);
-	/*
-	 * Use a minimum 2 level page table to prevent splitting
-	 * host PMD huge pages at stage2.
-	 */
-	lvls = stage2_pgtable_levels(phys_shift);
-	if (lvls < 2)
-		lvls = 2;
-	vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls);
-
-	/*
-	 * Enable the Hardware Access Flag management, unconditionally
-	 * on all CPUs. The features is RES0 on CPUs without the support
-	 * and must be ignored by the CPUs.
-	 */
-	vtcr |= VTCR_EL2_HA;
+	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
+	kvm->arch.vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift);
 
-	/* Set the vmid bits */
-	vtcr |= (kvm_get_vmid_bits() == 16) ?
-		VTCR_EL2_VS_16BIT :
-		VTCR_EL2_VS_8BIT;
-	kvm->arch.vtcr = vtcr;
 	return 0;
 }