Merge tag 'kvmarm-fixes-5.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 fixes for 5.19, take #1

- Properly reset the SVE/SME flags on vcpu load

- Fix a vgic-v2 regression regarding accessing the pending
  state of a HW interrupt from userspace (and make the code
  common with vgic-v3)

- Fix access to the idreg range for protected guests

- Ignore 'kvm-arm.mode=protected' when using VHE

- Return an error from kvm_arch_init_vm() on allocation failure

- A bunch of small cleanups (comments, annotations, indentation)

14 files changed, 95 insertions, 74 deletions

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 8090130b544b..97c16aa2f53f 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2469,7 +2469,6 @@
 
 			protected: nVHE-based mode with support for guests whose
 				   state is kept private from the host.
-				   Not valid if the kernel is running in EL2.
 
 			Defaults to VHE/nVHE based on hardware support. Setting
 			mode to "protected" will disable kexec and hibernation
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 47a1e25e25bb..de32152cea04 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -363,11 +363,6 @@ struct kvm_vcpu_arch {
 	struct kvm_pmu pmu;
 
 	/*
-	 * Anything that is not used directly from assembly code goes
-	 * here.
-	 */
-
-	/*
 	 * Guest registers we preserve during guest debugging.
 	 *
 	 * These shadow registers are updated by the kvm_handle_sys_reg
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 3c8af033a997..0e80db4327b6 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -113,6 +113,9 @@ static __always_inline bool has_vhe(void)
 	/*
 	 * Code only run in VHE/NVHE hyp context can assume VHE is present or
 	 * absent. Otherwise fall back to caps.
+	 * This allows the compiler to discard VHE-specific code from the
+	 * nVHE object, reducing the number of external symbol references
+	 * needed to link.
 	 */
 	if (is_vhe_hyp_code())
 		return true;
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 42ea2bd856c6..79fac13ab2ef 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1974,15 +1974,7 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap)
 #ifdef CONFIG_KVM
 static bool is_kvm_protected_mode(const struct arm64_cpu_capabilities *entry, int __unused)
 {
-	if (kvm_get_mode() != KVM_MODE_PROTECTED)
-		return false;
-
-	if (is_kernel_in_hyp_mode()) {
-		pr_warn("Protected KVM not available with VHE\n");
-		return false;
-	}
-
-	return true;
+	return kvm_get_mode() == KVM_MODE_PROTECTED;
 }
 #endif /* CONFIG_KVM */
 
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 4e39ace073af..3b8d062e30ea 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -1230,6 +1230,9 @@ bool kvm_arch_timer_get_input_level(int vintid)
 	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
 	struct arch_timer_context *timer;
 
+	if (WARN(!vcpu, "No vcpu context!\n"))
+		return false;
+
 	if (vintid == vcpu_vtimer(vcpu)->irq.irq)
 		timer = vcpu_vtimer(vcpu);
 	else if (vintid == vcpu_ptimer(vcpu)->irq.irq)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 400bb0fe2745..a0188144a122 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -150,8 +150,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (ret)
 		goto out_free_stage2_pgd;
 
-	if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL)) {
+		ret = -ENOMEM;
 		goto out_free_stage2_pgd;
+	}
 	cpumask_copy(kvm->arch.supported_cpus, cpu_possible_mask);
 
 	kvm_vgic_early_init(kvm);
@@ -2271,7 +2273,11 @@ static int __init early_kvm_mode_cfg(char *arg)
 		return -EINVAL;
 
 	if (strcmp(arg, "protected") == 0) {
-		kvm_mode = KVM_MODE_PROTECTED;
+		if (!is_kernel_in_hyp_mode())
+			kvm_mode = KVM_MODE_PROTECTED;
+		else
+			pr_warn_once("Protected KVM not available with VHE\n");
+
 		return 0;
 	}
 
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 3d251a4d2cf7..6012b08ecb14 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -80,6 +80,7 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 	vcpu->arch.flags &= ~KVM_ARM64_FP_ENABLED;
 	vcpu->arch.flags |= KVM_ARM64_FP_HOST;
 
+	vcpu->arch.flags &= ~KVM_ARM64_HOST_SVE_ENABLED;
 	if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
 		vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED;
 
@@ -93,6 +94,7 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 	 * operations. Do this for ZA as well for now for simplicity.
 	 */
 	if (system_supports_sme()) {
+		vcpu->arch.flags &= ~KVM_ARM64_HOST_SME_ENABLED;
 		if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN)
 			vcpu->arch.flags |= KVM_ARM64_HOST_SME_ENABLED;
 
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 78edf077fa3b..1e78acf9662e 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -314,15 +314,11 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 int host_stage2_idmap_locked(phys_addr_t addr, u64 size,
 			     enum kvm_pgtable_prot prot)
 {
-	hyp_assert_lock_held(&host_kvm.lock);
-
 	return host_stage2_try(__host_stage2_idmap, addr, addr + size, prot);
 }
 
 int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
 {
-	hyp_assert_lock_held(&host_kvm.lock);
-
 	return host_stage2_try(kvm_pgtable_stage2_set_owner, &host_kvm.pgt,
 			       addr, size, &host_s2_pool, owner_id);
 }
diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
index b6d86e423319..35a4331ba5f3 100644
--- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c
+++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
@@ -243,15 +243,9 @@ u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id)
 	case SYS_ID_AA64MMFR2_EL1:
 		return get_pvm_id_aa64mmfr2(vcpu);
 	default:
-		/*
-		 * Should never happen because all cases are covered in
-		 * pvm_sys_reg_descs[].
-		 */
-		WARN_ON(1);
-		break;
+		/* Unhandled ID register, RAZ */
+		return 0;
 	}
-
-	return 0;
 }
 
 static u64 read_id_reg(const struct kvm_vcpu *vcpu,
@@ -332,6 +326,16 @@ static bool pvm_gic_read_sre(struct kvm_vcpu *vcpu,
 /* Mark the specified system register as an AArch64 feature id register. */
 #define AARCH64(REG) { SYS_DESC(REG), .access = pvm_access_id_aarch64 }
 
+/*
+ * sys_reg_desc initialiser for architecturally unallocated cpufeature ID
+ * register with encoding Op0=3, Op1=0, CRn=0, CRm=crm, Op2=op2
+ * (1 <= crm < 8, 0 <= Op2 < 8).
+ */
+#define ID_UNALLOCATED(crm, op2) {			\
+	Op0(3), Op1(0), CRn(0), CRm(crm), Op2(op2),	\
+	.access = pvm_access_id_aarch64,		\
+}
+
 /* Mark the specified system register as Read-As-Zero/Write-Ignored */
 #define RAZ_WI(REG) { SYS_DESC(REG), .access = pvm_access_raz_wi }
 
@@ -375,24 +379,46 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = {
 	AARCH32(SYS_MVFR0_EL1),
 	AARCH32(SYS_MVFR1_EL1),
 	AARCH32(SYS_MVFR2_EL1),
+	ID_UNALLOCATED(3,3),
 	AARCH32(SYS_ID_PFR2_EL1),
 	AARCH32(SYS_ID_DFR1_EL1),
 	AARCH32(SYS_ID_MMFR5_EL1),
+	ID_UNALLOCATED(3,7),
 
 	/* AArch64 ID registers */
 	/* CRm=4 */
 	AARCH64(SYS_ID_AA64PFR0_EL1),
 	AARCH64(SYS_ID_AA64PFR1_EL1),
+	ID_UNALLOCATED(4,2),
+	ID_UNALLOCATED(4,3),
 	AARCH64(SYS_ID_AA64ZFR0_EL1),
+	ID_UNALLOCATED(4,5),
+	ID_UNALLOCATED(4,6),
+	ID_UNALLOCATED(4,7),
 	AARCH64(SYS_ID_AA64DFR0_EL1),
 	AARCH64(SYS_ID_AA64DFR1_EL1),
+	ID_UNALLOCATED(5,2),
+	ID_UNALLOCATED(5,3),
 	AARCH64(SYS_ID_AA64AFR0_EL1),
 	AARCH64(SYS_ID_AA64AFR1_EL1),
+	ID_UNALLOCATED(5,6),
+	ID_UNALLOCATED(5,7),
 	AARCH64(SYS_ID_AA64ISAR0_EL1),
 	AARCH64(SYS_ID_AA64ISAR1_EL1),
+	AARCH64(SYS_ID_AA64ISAR2_EL1),
+	ID_UNALLOCATED(6,3),
+	ID_UNALLOCATED(6,4),
+	ID_UNALLOCATED(6,5),
+	ID_UNALLOCATED(6,6),
+	ID_UNALLOCATED(6,7),
 	AARCH64(SYS_ID_AA64MMFR0_EL1),
 	AARCH64(SYS_ID_AA64MMFR1_EL1),
 	AARCH64(SYS_ID_AA64MMFR2_EL1),
+	ID_UNALLOCATED(7,3),
+	ID_UNALLOCATED(7,4),
+	ID_UNALLOCATED(7,5),
+	ID_UNALLOCATED(7,6),
+	ID_UNALLOCATED(7,7),
 
 	/* Scalable Vector Registers are restricted. */
 
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v2.c b/arch/arm64/kvm/vgic/vgic-mmio-v2.c
index 77a67e9d3d14..e070cda86e12 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v2.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v2.c
@@ -429,11 +429,11 @@ static const struct vgic_register_region vgic_v2_dist_registers[] = {
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_SET,
 		vgic_mmio_read_pending, vgic_mmio_write_spending,
-		NULL, vgic_uaccess_write_spending, 1,
+		vgic_uaccess_read_pending, vgic_uaccess_write_spending, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_CLEAR,
 		vgic_mmio_read_pending, vgic_mmio_write_cpending,
-		NULL, vgic_uaccess_write_cpending, 1,
+		vgic_uaccess_read_pending, vgic_uaccess_write_cpending, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_SET,
 		vgic_mmio_read_active, vgic_mmio_write_sactive,
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index f7aa7bcd6fb8..f15e29cc63ce 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -353,42 +353,6 @@ static unsigned long vgic_mmio_read_v3_idregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-static unsigned long vgic_v3_uaccess_read_pending(struct kvm_vcpu *vcpu,
-						  gpa_t addr, unsigned int len)
-{
-	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
-	u32 value = 0;
-	int i;
-
-	/*
-	 * pending state of interrupt is latched in pending_latch variable.
-	 * Userspace will save and restore pending state and line_level
-	 * separately.
-	 * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.rst
-	 * for handling of ISPENDR and ICPENDR.
-	 */
-	for (i = 0; i < len * 8; i++) {
-		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
-		bool state = irq->pending_latch;
-
-		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
-			int err;
-
-			err = irq_get_irqchip_state(irq->host_irq,
-						    IRQCHIP_STATE_PENDING,
-						    &state);
-			WARN_ON(err);
-		}
-
-		if (state)
-			value |= (1U << i);
-
-		vgic_put_irq(vcpu->kvm, irq);
-	}
-
-	return value;
-}
-
 static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu,
 					 gpa_t addr, unsigned int len,
 					 unsigned long val)
@@ -666,7 +630,7 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = {
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISPENDR,
 		vgic_mmio_read_pending, vgic_mmio_write_spending,
-		vgic_v3_uaccess_read_pending, vgic_v3_uaccess_write_pending, 1,
+		vgic_uaccess_read_pending, vgic_v3_uaccess_write_pending, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICPENDR,
 		vgic_mmio_read_pending, vgic_mmio_write_cpending,
@@ -750,7 +714,7 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = {
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISPENDR0,
 		vgic_mmio_read_pending, vgic_mmio_write_spending,
-		vgic_v3_uaccess_read_pending, vgic_v3_uaccess_write_pending, 4,
+		vgic_uaccess_read_pending, vgic_v3_uaccess_write_pending, 4,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICPENDR0,
 		vgic_mmio_read_pending, vgic_mmio_write_cpending,
diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c
index 49837d3a3ef5..997d0fce2088 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio.c
@@ -226,8 +226,9 @@ int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
-				     gpa_t addr, unsigned int len)
+static unsigned long __read_pending(struct kvm_vcpu *vcpu,
+				    gpa_t addr, unsigned int len,
+				    bool is_user)
 {
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	u32 value = 0;
@@ -239,6 +240,15 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 		unsigned long flags;
 		bool val;
 
+		/*
+		 * When used from userspace with a GICv3 model:
+		 *
+		 * Pending state of interrupt is latched in pending_latch
+		 * variable.  Userspace will save and restore pending state
+		 * and line_level separately.
+		 * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.rst
+		 * for handling of ISPENDR and ICPENDR.
+		 */
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
 			int err;
@@ -248,10 +258,20 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 						    IRQCHIP_STATE_PENDING,
 						    &val);
 			WARN_RATELIMIT(err, "IRQ %d", irq->host_irq);
-		} else if (vgic_irq_is_mapped_level(irq)) {
+		} else if (!is_user && vgic_irq_is_mapped_level(irq)) {
 			val = vgic_get_phys_line_level(irq);
 		} else {
-			val = irq_is_pending(irq);
+			switch (vcpu->kvm->arch.vgic.vgic_model) {
+			case KVM_DEV_TYPE_ARM_VGIC_V3:
+				if (is_user) {
+					val = irq->pending_latch;
+					break;
+				}
+				fallthrough;
+			default:
+				val = irq_is_pending(irq);
+				break;
+			}
 		}
 
 		value |= ((u32)val << i);
@@ -263,6 +283,18 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 	return value;
 }
 
+unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
+				     gpa_t addr, unsigned int len)
+{
+	return __read_pending(vcpu, addr, len, false);
+}
+
+unsigned long vgic_uaccess_read_pending(struct kvm_vcpu *vcpu,
+					gpa_t addr, unsigned int len)
+{
+	return __read_pending(vcpu, addr, len, true);
+}
+
 static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
 {
 	return (vgic_irq_is_sgi(irq->intid) &&
diff --git a/arch/arm64/kvm/vgic/vgic-mmio.h b/arch/arm64/kvm/vgic/vgic-mmio.h
index 3fa696f198a3..6082d4b66d39 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio.h
+++ b/arch/arm64/kvm/vgic/vgic-mmio.h
@@ -149,6 +149,9 @@ int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu,
 unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 				     gpa_t addr, unsigned int len);
 
+unsigned long vgic_uaccess_read_pending(struct kvm_vcpu *vcpu,
+					gpa_t addr, unsigned int len);
+
 void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 			      gpa_t addr, unsigned int len,
 			      unsigned long val);
diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c
index 8d5f0506fd87..d78ae63d7c15 100644
--- a/arch/arm64/kvm/vmid.c
+++ b/arch/arm64/kvm/vmid.c
@@ -66,7 +66,7 @@ static void flush_context(void)
 	 * the next context-switch, we broadcast TLB flush + I-cache
 	 * invalidation over the inner shareable domain on rollover.
 	 */
-	 kvm_call_hyp(__kvm_flush_vm_context);
+	kvm_call_hyp(__kvm_flush_vm_context);
 }
 
 static bool check_update_reserved_vmid(u64 vmid, u64 newvmid)