Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "ARM:
   - Fix alignment of the new HYP sections
   - Fix GICR_TYPER access from userspace

  S390:
   - do not reset the global diag318 data for per-cpu reset
   - do not mark memory as protected too early
   - fix for destroy page ultravisor call

  x86:
   - fix for SEV debugging
   - fix incorrect return code
   - fix for 'noapic' with PIC in userspace and LAPIC in kernel
   - fix for 5-level paging"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  kvm: x86/mmu: Fix get_mmio_spte() on CPUs supporting 5-level PT
  KVM: x86: Fix split-irqchip vs interrupt injection window request
  KVM: x86: handle !lapic_in_kernel case in kvm_cpu_*_extint
  MAINTAINERS: Update email address for Sean Christopherson
  MAINTAINERS: add uv.c also to KVM/s390
  s390/uv: handle destroy page legacy interface
  KVM: arm64: vgic-v3: Drop the reporting of GICR_TYPER.Last for userspace
  KVM: SVM: fix error return code in svm_create_vcpu()
  KVM: SVM: Fix offset computation bug in __sev_dbg_decrypt().
  KVM: arm64: Correctly align nVHE percpu data
  KVM: s390: remove diag318 reset code
  KVM: s390: pv: Mark mm as protected after the set secure parameters and improve cleanup

15 files changed, 91 insertions, 70 deletions

diff --git a/.mailmap b/.mailmap
index 505b3d771964..d9fb83d67055 100644
--- a/.mailmap
+++ b/.mailmap
@@ -290,6 +290,7 @@ Santosh Shilimkar <ssantosh@kernel.org>
 Sarangdhar Joshi <spjoshi@codeaurora.org>
 Sascha Hauer <s.hauer@pengutronix.de>
 S.Çağlar Onur <caglar@pardus.org.tr>
+Sean Christopherson <seanjc@google.com> <sean.j.christopherson@intel.com>
 Sean Nyekjaer <sean@geanix.com> <sean.nyekjaer@prevas.dk>
 Sebastian Reichel <sre@kernel.org> <sebastian.reichel@collabora.co.uk>
 Sebastian Reichel <sre@kernel.org> <sre@debian.org>
diff --git a/MAINTAINERS b/MAINTAINERS
index a008b70f3c16..0d80c24c114e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9646,6 +9646,7 @@ F:	Documentation/virt/kvm/s390*
 F:	arch/s390/include/asm/gmap.h
 F:	arch/s390/include/asm/kvm*
 F:	arch/s390/include/uapi/asm/kvm*
+F:	arch/s390/kernel/uv.c
 F:	arch/s390/kvm/
 F:	arch/s390/mm/gmap.c
 F:	tools/testing/selftests/kvm/*/s390x/
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S
index bb2d986ff696..a797abace13f 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S
@@ -13,6 +13,11 @@
 
 SECTIONS {
 	HYP_SECTION(.text)
+	/*
+	 * .hyp..data..percpu needs to be page aligned to maintain the same
+	 * alignment for when linking into vmlinux.
+	 */
+	. = ALIGN(PAGE_SIZE);
 	HYP_SECTION_NAME(.data..percpu) : {
 		PERCPU_INPUT(L1_CACHE_BYTES)
 	}
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index 52d6f24f65dc..15a6c98ee92f 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -273,6 +273,23 @@ static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu,
 	return extract_bytes(value, addr & 7, len);
 }
 
+static unsigned long vgic_uaccess_read_v3r_typer(struct kvm_vcpu *vcpu,
+						 gpa_t addr, unsigned int len)
+{
+	unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
+	int target_vcpu_id = vcpu->vcpu_id;
+	u64 value;
+
+	value = (u64)(mpidr & GENMASK(23, 0)) << 32;
+	value |= ((target_vcpu_id & 0xffff) << 8);
+
+	if (vgic_has_its(vcpu->kvm))
+		value |= GICR_TYPER_PLPIS;
+
+	/* reporting of the Last bit is not supported for userspace */
+	return extract_bytes(value, addr & 7, len);
+}
+
 static unsigned long vgic_mmio_read_v3r_iidr(struct kvm_vcpu *vcpu,
 					     gpa_t addr, unsigned int len)
 {
@@ -593,8 +610,9 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = {
 	REGISTER_DESC_WITH_LENGTH(GICR_IIDR,
 		vgic_mmio_read_v3r_iidr, vgic_mmio_write_wi, 4,
 		VGIC_ACCESS_32bit),
-	REGISTER_DESC_WITH_LENGTH(GICR_TYPER,
-		vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, 8,
+	REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_TYPER,
+		vgic_mmio_read_v3r_typer, vgic_mmio_write_wi,
+		vgic_uaccess_read_v3r_typer, vgic_mmio_uaccess_write_wi, 8,
 		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH(GICR_WAKER,
 		vgic_mmio_read_raz, vgic_mmio_write_wi, 4,
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index 14bd9d58edc9..883bfed9f5c2 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -129,8 +129,15 @@ int uv_destroy_page(unsigned long paddr)
 		.paddr = paddr
 	};
 
-	if (uv_call(0, (u64)&uvcb))
+	if (uv_call(0, (u64)&uvcb)) {
+		/*
+		 * Older firmware uses 107/d as an indication of a non secure
+		 * page. Let us emulate the newer variant (no-op).
+		 */
+		if (uvcb.header.rc == 0x107 && uvcb.header.rrc == 0xd)
+			return 0;
 		return -EINVAL;
+	}
 	return 0;
 }
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 6b74b92c1a58..425d3d75320b 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2312,7 +2312,7 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
 		struct kvm_s390_pv_unp unp = {};
 
 		r = -EINVAL;
-		if (!kvm_s390_pv_is_protected(kvm))
+		if (!kvm_s390_pv_is_protected(kvm) || !mm_is_protected(kvm->mm))
 			break;
 
 		r = -EFAULT;
@@ -3564,7 +3564,6 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->pp = 0;
 		vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
 		vcpu->arch.sie_block->todpr = 0;
-		vcpu->arch.sie_block->cpnc = 0;
 	}
 }
 
@@ -3582,7 +3581,6 @@ static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu)
 
 	regs->etoken = 0;
 	regs->etoken_extension = 0;
-	regs->diag318 = 0;
 }
 
 int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index eb99e2f95ebe..f5847f9dec7c 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -208,7 +208,6 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
 		return -EIO;
 	}
 	kvm->arch.gmap->guest_handle = uvcb.guest_handle;
-	atomic_set(&kvm->mm->context.is_protected, 1);
 	return 0;
 }
 
@@ -228,6 +227,8 @@ int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc,
 	*rrc = uvcb.header.rrc;
 	KVM_UV_EVENT(kvm, 3, "PROTVIRT VM SET PARMS: rc %x rrc %x",
 		     *rc, *rrc);
+	if (!cc)
+		atomic_set(&kvm->mm->context.is_protected, 1);
 	return cc ? -EINVAL : 0;
 }
 
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index cfb0017f33a7..64795d034926 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2690,6 +2690,8 @@ static const struct mm_walk_ops reset_acc_walk_ops = {
 #include <linux/sched/mm.h>
 void s390_reset_acc(struct mm_struct *mm)
 {
+	if (!mm_is_protected(mm))
+		return;
 	/*
 	 * we might be called during
 	 * reset:                             we walk the pages and clear
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 324ddd7fd0aa..7e5f33a0d0e2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1656,6 +1656,7 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
+int kvm_cpu_has_extint(struct kvm_vcpu *v);
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 99d118ffc67d..814698e5b152 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -40,29 +40,10 @@ static int pending_userspace_extint(struct kvm_vcpu *v)
  * check if there is pending interrupt from
  * non-APIC source without intack.
  */
-static int kvm_cpu_has_extint(struct kvm_vcpu *v)
-{
-	u8 accept = kvm_apic_accept_pic_intr(v);
-
-	if (accept) {
-		if (irqchip_split(v->kvm))
-			return pending_userspace_extint(v);
-		else
-			return v->kvm->arch.vpic->output;
-	} else
-		return 0;
-}
-
-/*
- * check if there is injectable interrupt:
- * when virtual interrupt delivery enabled,
- * interrupt from apic will handled by hardware,
- * we don't need to check it here.
- */
-int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+int kvm_cpu_has_extint(struct kvm_vcpu *v)
 {
 	/*
-	 * FIXME: interrupt.injected represents an interrupt that it's
+	 * FIXME: interrupt.injected represents an interrupt whose
 	 * side-effects have already been applied (e.g. bit from IRR
 	 * already moved to ISR). Therefore, it is incorrect to rely
 	 * on interrupt.injected to know if there is a pending
@@ -75,6 +56,23 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
 	if (!lapic_in_kernel(v))
 		return v->arch.interrupt.injected;
 
+	if (!kvm_apic_accept_pic_intr(v))
+		return 0;
+
+	if (irqchip_split(v->kvm))
+		return pending_userspace_extint(v);
+	else
+		return v->kvm->arch.vpic->output;
+}
+
+/*
+ * check if there is injectable interrupt:
+ * when virtual interrupt delivery enabled,
+ * interrupt from apic will handled by hardware,
+ * we don't need to check it here.
+ */
+int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+{
 	if (kvm_cpu_has_extint(v))
 		return 1;
 
@@ -91,20 +89,6 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_injectable_intr);
  */
 int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
 {
-	/*
-	 * FIXME: interrupt.injected represents an interrupt that it's
-	 * side-effects have already been applied (e.g. bit from IRR
-	 * already moved to ISR). Therefore, it is incorrect to rely
-	 * on interrupt.injected to know if there is a pending
-	 * interrupt in the user-mode LAPIC.
-	 * This leads to nVMX/nSVM not be able to distinguish
-	 * if it should exit from L2 to L1 on EXTERNAL_INTERRUPT on
-	 * pending interrupt or should re-inject an injected
-	 * interrupt.
-	 */
-	if (!lapic_in_kernel(v))
-		return v->arch.interrupt.injected;
-
 	if (kvm_cpu_has_extint(v))
 		return 1;
 
@@ -118,16 +102,21 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt);
  */
 static int kvm_cpu_get_extint(struct kvm_vcpu *v)
 {
-	if (kvm_cpu_has_extint(v)) {
-		if (irqchip_split(v->kvm)) {
-			int vector = v->arch.pending_external_vector;
-
-			v->arch.pending_external_vector = -1;
-			return vector;
-		} else
-			return kvm_pic_read_irq(v->kvm); /* PIC */
-	} else
+	if (!kvm_cpu_has_extint(v)) {
+		WARN_ON(!lapic_in_kernel(v));
 		return -1;
+	}
+
+	if (!lapic_in_kernel(v))
+		return v->arch.interrupt.nr;
+
+	if (irqchip_split(v->kvm)) {
+		int vector = v->arch.pending_external_vector;
+
+		v->arch.pending_external_vector = -1;
+		return vector;
+	} else
+		return kvm_pic_read_irq(v->kvm); /* PIC */
 }
 
 /*
@@ -135,13 +124,7 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v)
  */
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 {
-	int vector;
-
-	if (!lapic_in_kernel(v))
-		return v->arch.interrupt.nr;
-
-	vector = kvm_cpu_get_extint(v);
-
+	int vector = kvm_cpu_get_extint(v);
 	if (vector != -1)
 		return vector;			/* PIC */
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 105e7859d1f2..86c33d53c90a 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2465,7 +2465,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u32 ppr;
 
-	if (!kvm_apic_hw_enabled(apic))
+	if (!kvm_apic_present(vcpu))
 		return -1;
 
 	__apic_update_ppr(apic, &ppr);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 5bb1939b65d8..7a6ae9e90bd7 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3517,7 +3517,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 {
 	u64 sptes[PT64_ROOT_MAX_LEVEL];
 	struct rsvd_bits_validate *rsvd_check;
-	int root = vcpu->arch.mmu->root_level;
+	int root = vcpu->arch.mmu->shadow_root_level;
 	int leaf;
 	int level;
 	bool reserved = false;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index c0b14106258a..566f4d18185b 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -642,8 +642,8 @@ static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr,
 	 * Its safe to read more than we are asked, caller should ensure that
 	 * destination has enough space.
 	 */
-	src_paddr = round_down(src_paddr, 16);
 	offset = src_paddr & 15;
+	src_paddr = round_down(src_paddr, 16);
 	sz = round_up(sz + offset, 16);
 
 	return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 1e81cfebd491..79b3a564f1c9 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1309,8 +1309,10 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 		svm->avic_is_running = true;
 
 	svm->msrpm = svm_vcpu_alloc_msrpm();
-	if (!svm->msrpm)
+	if (!svm->msrpm) {
+		err = -ENOMEM;
 		goto error_free_vmcb_page;
+	}
 
 	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 078a39d489fe..e545a8a613b1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4051,21 +4051,23 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
 
 static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * We can accept userspace's request for interrupt injection
+	 * as long as we have a place to store the interrupt number.
+	 * The actual injection will happen when the CPU is able to
+	 * deliver the interrupt.
+	 */
+	if (kvm_cpu_has_extint(vcpu))
+		return false;
+
+	/* Acknowledging ExtINT does not happen if LINT0 is masked.  */
 	return (!lapic_in_kernel(vcpu) ||
 		kvm_apic_accept_pic_intr(vcpu));
 }
 
-/*
- * if userspace requested an interrupt window, check that the
- * interrupt window is open.
- *
- * No need to exit to userspace if we already have an interrupt queued.
- */
 static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
 {
 	return kvm_arch_interrupt_allowed(vcpu) &&
-		!kvm_cpu_has_interrupt(vcpu) &&
-		!kvm_event_needs_reinjection(vcpu) &&
 		kvm_cpu_accept_dm_intr(vcpu);
 }