Merge tag 'kvm-s390-next-5.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

KVM: s390: Fixes and Features for 5.16

- SIGP Fixes
- initial preparations for lazy destroy of secure VMs
- storage key improvements/fixes
- Log the guest CPNC

arch/s390/include/asm/pgtable.h

···
 	pte_t res;
 
 	res = ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID));
+	/* At this point the reference through the mapping is still present */
 	if (mm_is_protected(mm) && pte_present(res))
-		uv_convert_from_secure(pte_val(res) & PAGE_MASK);
+		uv_convert_owned_from_secure(pte_val(res) & PAGE_MASK);
 	return res;
 }
 
···
 	pte_t res;
 
 	res = ptep_xchg_direct(vma->vm_mm, addr, ptep, __pte(_PAGE_INVALID));
+	/* At this point the reference through the mapping is still present */
 	if (mm_is_protected(vma->vm_mm) && pte_present(res))
-		uv_convert_from_secure(pte_val(res) & PAGE_MASK);
+		uv_convert_owned_from_secure(pte_val(res) & PAGE_MASK);
 	return res;
 }
 
···
 	} else {
 		res = ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID));
 	}
+	/* At this point the reference through the mapping is still present */
 	if (mm_is_protected(mm) && pte_present(res))
-		uv_convert_from_secure(pte_val(res) & PAGE_MASK);
+		uv_convert_owned_from_secure(pte_val(res) & PAGE_MASK);
 	return res;
 }
 

arch/s390/include/asm/uv.h

···
 #include <asm/page.h>
 #include <asm/gmap.h>
 
+#define UVC_CC_OK	0
+#define UVC_CC_ERROR	1
+#define UVC_CC_BUSY	2
+#define UVC_CC_PARTIAL	3
+
 #define UVC_RC_EXECUTED		0x0001
 #define UVC_RC_INV_CMD		0x0002
 #define UVC_RC_INV_STATE	0x0003
···
 }
 
 int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb);
-int uv_destroy_page(unsigned long paddr);
+int uv_destroy_owned_page(unsigned long paddr);
 int uv_convert_from_secure(unsigned long paddr);
+int uv_convert_owned_from_secure(unsigned long paddr);
 int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr);
 
 void setup_uv(void);
···
 #define is_prot_virt_host() 0
 static inline void setup_uv(void) {}
 
-static inline int uv_destroy_page(unsigned long paddr)
+static inline int uv_destroy_owned_page(unsigned long paddr)
 {
 	return 0;
 }
 
 static inline int uv_convert_from_secure(unsigned long paddr)
+{
+	return 0;
+}
+
+static inline int uv_convert_owned_from_secure(unsigned long paddr)
 {
 	return 0;
 }

arch/s390/kernel/uv.c

···
  *
  * @paddr: Absolute host address of page to be destroyed
  */
-int uv_destroy_page(unsigned long paddr)
+static int uv_destroy_page(unsigned long paddr)
 {
 	struct uv_cb_cfs uvcb = {
 		.header.cmd = UVC_CMD_DESTR_SEC_STOR,
···
 }
 
 /*
+ * The caller must already hold a reference to the page
+ */
+int uv_destroy_owned_page(unsigned long paddr)
+{
+	struct page *page = phys_to_page(paddr);
+	int rc;
+
+	get_page(page);
+	rc = uv_destroy_page(paddr);
+	if (!rc)
+		clear_bit(PG_arch_1, &page->flags);
+	put_page(page);
+	return rc;
+}
+
+/*
  * Requests the Ultravisor to encrypt a guest page and make it
  * accessible to the host for paging (export).
  *
···
 	if (uv_call(0, (u64)&uvcb))
 		return -EINVAL;
 	return 0;
+}
+
+/*
+ * The caller must already hold a reference to the page
+ */
+int uv_convert_owned_from_secure(unsigned long paddr)
+{
+	struct page *page = phys_to_page(paddr);
+	int rc;
+
+	get_page(page);
+	rc = uv_convert_from_secure(paddr);
+	if (!rc)
+		clear_bit(PG_arch_1, &page->flags);
+	put_page(page);
+	return rc;
 }
 
 /*
···
 {
 	pte_t entry = READ_ONCE(*ptep);
 	struct page *page;
-	int expected, rc = 0;
+	int expected, cc = 0;
 
 	if (!pte_present(entry))
 		return -ENXIO;
···
 	if (!page_ref_freeze(page, expected))
 		return -EBUSY;
 	set_bit(PG_arch_1, &page->flags);
-	rc = uv_call(0, (u64)uvcb);
+	/*
+	 * If the UVC does not succeed or fail immediately, we don't want to
+	 * loop for long, or we might get stall notifications.
+	 * On the other hand, this is a complex scenario and we are holding a lot of
+	 * locks, so we can't easily sleep and reschedule. We try only once,
+	 * and if the UVC returned busy or partial completion, we return
+	 * -EAGAIN and we let the callers deal with it.
+	 */
+	cc = __uv_call(0, (u64)uvcb);
 	page_ref_unfreeze(page, expected);
-	/* Return -ENXIO if the page was not mapped, -EINVAL otherwise */
-	if (rc)
-		rc = uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
-	return rc;
+	/*
+	 * Return -ENXIO if the page was not mapped, -EINVAL for other errors.
+	 * If busy or partially completed, return -EAGAIN.
+	 */
+	if (cc == UVC_CC_OK)
+		return 0;
+	else if (cc == UVC_CC_BUSY || cc == UVC_CC_PARTIAL)
+		return -EAGAIN;
+	return uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
 }
 
 /*
···
 	uaddr = __gmap_translate(gmap, gaddr);
 	if (IS_ERR_VALUE(uaddr))
 		goto out;
-	vma = find_vma(gmap->mm, uaddr);
+	vma = vma_lookup(gmap->mm, uaddr);
 	if (!vma)
 		goto out;
 	/*
···
 	mmap_read_unlock(gmap->mm);
 
 	if (rc == -EAGAIN) {
+		/*
+		 * If we are here because the UVC returned busy or partial
+		 * completion, this is just a useless check, but it is safe.
+		 */
 		wait_on_page_writeback(page);
 	} else if (rc == -EBUSY) {
 		/*

arch/s390/kvm/intercept.c

···
 	 */
 	if (rc == -EINVAL)
 		return 0;
+	/*
+	 * If we got -EAGAIN here, we simply return it. It will eventually
+	 * get propagated all the way to userspace, which should then try
+	 * again.
+	 */
 	return rc;
 }
 

arch/s390/kvm/interrupt.c

···
 	int vcpu_idx, online_vcpus = atomic_read(&kvm->online_vcpus);
 	struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
 	struct kvm_vcpu *vcpu;
+	u8 vcpu_isc_mask;
 
 	for_each_set_bit(vcpu_idx, kvm->arch.idle_mask, online_vcpus) {
 		vcpu = kvm_get_vcpu(kvm, vcpu_idx);
 		if (psw_ioint_disabled(vcpu))
 			continue;
-		deliverable_mask &= (u8)(vcpu->arch.sie_block->gcr[6] >> 24);
-		if (deliverable_mask) {
+		vcpu_isc_mask = (u8)(vcpu->arch.sie_block->gcr[6] >> 24);
+		if (deliverable_mask & vcpu_isc_mask) {
 			/* lately kicked but not yet running */
 			if (test_and_set_bit(vcpu_idx, gi->kicked_mask))
 				return;

arch/s390/kvm/kvm-s390.c

···
 	case KVM_S390_PV_COMMAND: {
 		struct kvm_pv_cmd args;
 
-		/* protvirt means user sigp */
-		kvm->arch.user_cpu_state_ctrl = 1;
+		/* protvirt means user cpu state */
+		kvm_s390_set_user_cpu_state_ctrl(kvm);
 		r = 0;
 		if (!is_prot_virt_host()) {
 			r = -EINVAL;
···
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
+	clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask);
 	return kvm_s390_vcpu_has_irq(vcpu, 0);
 }
 
···
 	vcpu_load(vcpu);
 
 	/* user space knows about this interface - let it control the state */
-	vcpu->kvm->arch.user_cpu_state_ctrl = 1;
+	kvm_s390_set_user_cpu_state_ctrl(vcpu->kvm);
 
 	switch (mp_state->mp_state) {
 	case KVM_MP_STATE_STOPPED:
···
 	if (kvm_run->kvm_dirty_regs & KVM_SYNC_DIAG318) {
 		vcpu->arch.diag318_info.val = kvm_run->s.regs.diag318;
 		vcpu->arch.sie_block->cpnc = vcpu->arch.diag318_info.cpnc;
+		VCPU_EVENT(vcpu, 3, "setting cpnc to %d", vcpu->arch.diag318_info.cpnc);
 	}
 	/*
 	 * If userspace sets the riccb (e.g. after migration) to a valid state,

arch/s390/kvm/kvm-s390.h

···
 	return kvm->arch.user_cpu_state_ctrl != 0;
 }
 
+static inline void kvm_s390_set_user_cpu_state_ctrl(struct kvm *kvm)
+{
+	if (kvm->arch.user_cpu_state_ctrl)
+		return;
+
+	VM_EVENT(kvm, 3, "%s", "ENABLE: Userspace CPU state control");
+	kvm->arch.user_cpu_state_ctrl = 1;
+}
+
 /* implemented in pv.c */
 int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);
 int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);

arch/s390/kvm/priv.c

···
 		mmap_read_unlock(current->mm);
 		if (rc == -EFAULT)
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		if (rc == -EAGAIN)
+			continue;
 		if (rc < 0)
 			return rc;
 		start += PAGE_SIZE;

arch/s390/kvm/pv.c

···
 
 int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
 {
-	int cc = 0;
+	int cc;
 
-	if (kvm_s390_pv_cpu_get_handle(vcpu)) {
-		cc = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu),
-				   UVC_CMD_DESTROY_SEC_CPU, rc, rrc);
+	if (!kvm_s390_pv_cpu_get_handle(vcpu))
+		return 0;
 
-		KVM_UV_EVENT(vcpu->kvm, 3,
-			     "PROTVIRT DESTROY VCPU %d: rc %x rrc %x",
-			     vcpu->vcpu_id, *rc, *rrc);
-		WARN_ONCE(cc, "protvirt destroy cpu failed rc %x rrc %x",
-			  *rc, *rrc);
-	}
+	cc = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), UVC_CMD_DESTROY_SEC_CPU, rc, rrc);
+
+	KVM_UV_EVENT(vcpu->kvm, 3, "PROTVIRT DESTROY VCPU %d: rc %x rrc %x",
+		     vcpu->vcpu_id, *rc, *rrc);
+	WARN_ONCE(cc, "protvirt destroy cpu failed rc %x rrc %x", *rc, *rrc);
+
 	/* Intended memory leak for something that should never happen. */
 	if (!cc)
 		free_pages(vcpu->arch.pv.stor_base,
···
 	uvcb.conf_base_stor_origin = (u64)kvm->arch.pv.stor_base;
 	uvcb.conf_virt_stor_origin = (u64)kvm->arch.pv.stor_var;
 
-	cc = uv_call(0, (u64)&uvcb);
+	cc = uv_call_sched(0, (u64)&uvcb);
 	*rc = uvcb.header.rc;
 	*rrc = uvcb.header.rrc;
 	KVM_UV_EVENT(kvm, 3, "PROTVIRT CREATE VM: handle %llx len %llx rc %x rrc %x",

arch/s390/kvm/sigp.c

···
 static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter,
 			   u64 *status_reg)
 {
-	unsigned int i;
-	struct kvm_vcpu *v;
-	bool all_stopped = true;
-
-	kvm_for_each_vcpu(i, v, vcpu->kvm) {
-		if (v == vcpu)
-			continue;
-		if (!is_vcpu_stopped(v))
-			all_stopped = false;
-	}
-
 	*status_reg &= 0xffffffff00000000UL;
 
 	/* Reject set arch order, with czam we're always in z/Arch mode. */
-	*status_reg |= (all_stopped ? SIGP_STATUS_INVALID_PARAMETER :
-					SIGP_STATUS_INCORRECT_STATE);
+	*status_reg |= SIGP_STATUS_INVALID_PARAMETER;
 	return SIGP_CC_STATUS_STORED;
 }
 

arch/s390/mm/gmap.c

···
  */
 void __gmap_zap(struct gmap *gmap, unsigned long gaddr)
 {
+	struct vm_area_struct *vma;
 	unsigned long vmaddr;
 	spinlock_t *ptl;
 	pte_t *ptep;
···
 						   gaddr >> PMD_SHIFT);
 	if (vmaddr) {
 		vmaddr |= gaddr & ~PMD_MASK;
+
+		vma = vma_lookup(gmap->mm, vmaddr);
+		if (!vma || is_vm_hugetlb_page(vma))
+			return;
+
 		/* Get pointer to the page table entry */
 		ptep = get_locked_pte(gmap->mm, vmaddr, &ptl);
-		if (likely(ptep))
+		if (likely(ptep)) {
 			ptep_zap_unused(gmap->mm, vmaddr, ptep, 0);
-		pte_unmap_unlock(ptep, ptl);
+			pte_unmap_unlock(ptep, ptl);
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(__gmap_zap);
···
 {
 	pte_t pte = READ_ONCE(*ptep);
 
+	/* There is a reference through the mapping */
 	if (pte_present(pte))
-		WARN_ON_ONCE(uv_destroy_page(pte_val(pte) & PAGE_MASK));
+		WARN_ON_ONCE(uv_destroy_owned_page(pte_val(pte) & PAGE_MASK));
+
 	return 0;
 }
 

arch/s390/mm/pgtable.c

···
 }
 
 #ifdef CONFIG_PGSTE
-static pmd_t *pmd_alloc_map(struct mm_struct *mm, unsigned long addr)
+static int pmd_lookup(struct mm_struct *mm, unsigned long addr, pmd_t **pmdp)
 {
+	struct vm_area_struct *vma;
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
-	pmd_t *pmd;
+
+	/* We need a valid VMA, otherwise this is clearly a fault. */
+	vma = vma_lookup(mm, addr);
+	if (!vma)
+		return -EFAULT;
 
 	pgd = pgd_offset(mm, addr);
-	p4d = p4d_alloc(mm, pgd, addr);
-	if (!p4d)
-		return NULL;
-	pud = pud_alloc(mm, p4d, addr);
-	if (!pud)
-		return NULL;
-	pmd = pmd_alloc(mm, pud, addr);
-	return pmd;
+	if (!pgd_present(*pgd))
+		return -ENOENT;
+
+	p4d = p4d_offset(pgd, addr);
+	if (!p4d_present(*p4d))
+		return -ENOENT;
+
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(*pud))
+		return -ENOENT;
+
+	/* Large PUDs are not supported yet. */
+	if (pud_large(*pud))
+		return -EFAULT;
+
+	*pmdp = pmd_offset(pud, addr);
+	return 0;
 }
 #endif
 
···
 	pmd_t *pmdp;
 	pte_t *ptep;
 
-	pmdp = pmd_alloc_map(mm, addr);
-	if (unlikely(!pmdp))
+	/*
+	 * If we don't have a PTE table and if there is no huge page mapped,
+	 * we can ignore attempts to set the key to 0, because it already is 0.
+	 */
+	switch (pmd_lookup(mm, addr, &pmdp)) {
+	case -ENOENT:
+		return key ? -EFAULT : 0;
+	case 0:
+		break;
+	default:
 		return -EFAULT;
+	}
 
 	ptl = pmd_lock(mm, pmdp);
 	if (!pmd_present(*pmdp)) {
 		spin_unlock(ptl);
-		return -EFAULT;
+		return key ? -EFAULT : 0;
 	}
 
 	if (pmd_large(*pmdp)) {
···
 	}
 	spin_unlock(ptl);
 
-	ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
-	if (unlikely(!ptep))
-		return -EFAULT;
-
+	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	new = old = pgste_get_lock(ptep);
 	pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT |
 			    PGSTE_ACC_BITS | PGSTE_FP_BIT);
···
 	pte_t *ptep;
 	int cc = 0;
 
-	pmdp = pmd_alloc_map(mm, addr);
-	if (unlikely(!pmdp))
+	/*
+	 * If we don't have a PTE table and if there is no huge page mapped,
+	 * the storage key is 0 and there is nothing for us to do.
+	 */
+	switch (pmd_lookup(mm, addr, &pmdp)) {
+	case -ENOENT:
+		return 0;
+	case 0:
+		break;
+	default:
 		return -EFAULT;
+	}
 
 	ptl = pmd_lock(mm, pmdp);
 	if (!pmd_present(*pmdp)) {
 		spin_unlock(ptl);
-		return -EFAULT;
+		return 0;
 	}
 
 	if (pmd_large(*pmdp)) {
···
 	}
 	spin_unlock(ptl);
 
-	ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
-	if (unlikely(!ptep))
-		return -EFAULT;
-
+	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	new = old = pgste_get_lock(ptep);
 	/* Reset guest reference bit only */
 	pgste_val(new) &= ~PGSTE_GR_BIT;
···
 	pmd_t *pmdp;
 	pte_t *ptep;
 
-	pmdp = pmd_alloc_map(mm, addr);
-	if (unlikely(!pmdp))
+	/*
+	 * If we don't have a PTE table and if there is no huge page mapped,
+	 * the storage key is 0.
+	 */
+	*key = 0;
+
+	switch (pmd_lookup(mm, addr, &pmdp)) {
+	case -ENOENT:
+		return 0;
+	case 0:
+		break;
+	default:
 		return -EFAULT;
+	}
 
 	ptl = pmd_lock(mm, pmdp);
 	if (!pmd_present(*pmdp)) {
-		/* Not yet mapped memory has a zero key */
 		spin_unlock(ptl);
-		*key = 0;
 		return 0;
 	}
 
···
 	}
 	spin_unlock(ptl);
 
-	ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
-	if (unlikely(!ptep))
-		return -EFAULT;
-
+	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	pgste = pgste_get_lock(ptep);
 	*key = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
 	paddr = pte_val(*ptep) & PAGE_MASK;
···
 int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
 			unsigned long *oldpte, unsigned long *oldpgste)
 {
+	struct vm_area_struct *vma;
 	unsigned long pgstev;
 	spinlock_t *ptl;
 	pgste_t pgste;
···
 	WARN_ON_ONCE(orc > ESSA_MAX);
 	if (unlikely(orc > ESSA_MAX))
 		return -EINVAL;
+
+	vma = vma_lookup(mm, hva);
+	if (!vma || is_vm_hugetlb_page(vma))
+		return -EFAULT;
 	ptep = get_locked_pte(mm, hva, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;
···
 int set_pgste_bits(struct mm_struct *mm, unsigned long hva,
 			unsigned long bits, unsigned long value)
 {
+	struct vm_area_struct *vma;
 	spinlock_t *ptl;
 	pgste_t new;
 	pte_t *ptep;
 
+	vma = vma_lookup(mm, hva);
+	if (!vma || is_vm_hugetlb_page(vma))
+		return -EFAULT;
 	ptep = get_locked_pte(mm, hva, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;
···
  */
 int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep)
 {
+	struct vm_area_struct *vma;
 	spinlock_t *ptl;
 	pte_t *ptep;
 
+	vma = vma_lookup(mm, hva);
+	if (!vma || is_vm_hugetlb_page(vma))
+		return -EFAULT;
 	ptep = get_locked_pte(mm, hva, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;