Merge tag 'kvm-s390-master-7.2-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

KVM: s390: Fixes for 7.2

- several fixes for PCI passthru in s390 kvm
- fix a 7.2-rc regression in the adapter interrupt mapping code

Documentation/virt/kvm/devices/s390_flic.rst

@@ -112,9 +112,20 @@ Groups:
       mask or unmask the adapter, as specified in mask
 
     KVM_S390_IO_ADAPTER_MAP
-      This is now a no-op. The mapping is purely done by the irq route.
+      Map an adapter indicator or summary page for long-term pinning so that
+      interrupt injection can be performed in atomic context. If long-term
+      pinning is not possible (e.g. file-backed memory), the page is verified
+      via a short-term pin and the ioctl returns success; interrupt injection
+      will use the non-atomic irqfd path with short-term pinning on each
+      interrupt. In Secure Execution mode this is a no-op and the ioctl
+      returns success.
+
     KVM_S390_IO_ADAPTER_UNMAP
-      This is now a no-op. The mapping is purely done by the irq route.
+      Unmap a previously mapped adapter indicator or summary page and release
+      the long-term pin. If the page was not long-term pinned (e.g. file-backed
+      memory), the map entry is removed and success is returned; if no prior
+      map entry exists, -ENOENT is returned. In Secure Execution mode this is
+      a no-op and the ioctl returns success.
 
   KVM_DEV_FLIC_AISM
     modify the adapter-interruption-suppression mode for a given isc if the

arch/s390/include/asm/kvm_host.h

@@ -476,6 +476,11 @@ struct s390_map_info {
 	__u64 guest_addr;
 	__u64 addr;
 	struct page *page;
+	/*
+	 * True if the page is long-term pinned. False if long-term pinning
+	 * failed and this entry exists only to preserve MAP/UNMAP symmetry.
+	 */
+	bool pinned;
 };
 
 struct s390_io_adapter {

arch/s390/kvm/interrupt.c

@@ -2520,8 +2520,22 @@ static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr)
 	map->addr = host_addr;
 	map->page = pin_map_page(kvm, host_addr, FOLL_LONGTERM);
 	if (!map->page) {
-		ret = -EINVAL;
-		goto out;
+		/*
+		 * Long-term pinning may fail for memory types such as file-backed
+		 * memory. Verify that short-term pinning succeeds so that the
+		 * non-atomic irqfd path can handle interrupt injection.
+		 */
+		map->page = pin_map_page(kvm, host_addr, 0);
+		if (!map->page) {
+			ret = -EINVAL;
+			goto out;
+		}
+		unpin_user_page(map->page);
+		map->page = NULL;
+		map->pinned = false;
+		/* Add an entry to preserve MAP/UNMAP symmetry. */
+	} else {
+		map->pinned = true;
 	}
 	spin_lock_irqsave(&adapter->maps_lock, flags);
 	if (adapter->nr_maps < MAX_S390_ADAPTER_MAPS) {
@@ -2532,7 +2546,7 @@ static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr)
 		ret = -EINVAL;
 	}
 	spin_unlock_irqrestore(&adapter->maps_lock, flags);
-	if (ret)
+	if (ret && map->page)
 		unpin_user_page(map->page);
 out:
 	if (ret)
@@ -2546,6 +2560,7 @@ static int kvm_s390_adapter_unmap(struct kvm *kvm, unsigned int id, __u64 addr)
 	struct s390_map_info *map, *tmp, *map_to_free;
 	struct page *map_page_to_put = NULL;
 	u64 map_addr_to_mark = 0;
+	bool map_pinned = false;
 	unsigned long flags;
 	int found = 0, idx;
 
@@ -2560,6 +2575,7 @@ static int kvm_s390_adapter_unmap(struct kvm *kvm, unsigned int id, __u64 addr)
 			list_del(&map->list);
 			map_page_to_put = map->page;
 			map_addr_to_mark = map->guest_addr;
+			map_pinned = map->pinned;
 			map_to_free = map;
 			break;
 		}
@@ -2568,11 +2584,18 @@ static int kvm_s390_adapter_unmap(struct kvm *kvm, unsigned int id, __u64 addr)
 
 	if (found) {
 		kfree(map_to_free);
-		idx = srcu_read_lock(&kvm->srcu);
-		mark_page_dirty(kvm, map_addr_to_mark >> PAGE_SHIFT);
-		set_page_dirty_lock(map_page_to_put);
-		srcu_read_unlock(&kvm->srcu, idx);
-		unpin_user_page(map_page_to_put);
+		if (map_pinned) {
+			/*
+			 * Only long-term pinned pages need to be marked dirty
+			 * and released. Fallback entries exist only for
+			 * MAP/UNMAP symmetry.
+			 */
+			idx = srcu_read_lock(&kvm->srcu);
+			mark_page_dirty(kvm, map_addr_to_mark >> PAGE_SHIFT);
+			set_page_dirty_lock(map_page_to_put);
+			srcu_read_unlock(&kvm->srcu, idx);
+			unpin_user_page(map_page_to_put);
+		}
 	}
 
 	return found ? 0 : -ENOENT;
@@ -2598,11 +2621,13 @@ void kvm_s390_unmap_all_adapters(struct kvm *kvm)
 
 		list_for_each_entry_safe(map, tmp, &local_list, list) {
 			list_del(&map->list);
-			idx = srcu_read_lock(&kvm->srcu);
-			mark_page_dirty(kvm, map->guest_addr >> PAGE_SHIFT);
-			set_page_dirty_lock(map->page);
-			srcu_read_unlock(&kvm->srcu, idx);
-			unpin_user_page(map->page);
+			if (map->pinned) {
+				idx = srcu_read_lock(&kvm->srcu);
+				mark_page_dirty(kvm, map->guest_addr >> PAGE_SHIFT);
+				set_page_dirty_lock(map->page);
+				srcu_read_unlock(&kvm->srcu, idx);
+				unpin_user_page(map->page);
+			}
 			kfree(map);
 		}
 	}
@@ -2929,8 +2954,11 @@ static struct s390_map_info *get_map_info(struct s390_io_adapter *adapter,
 		return NULL;
 
 	list_for_each_entry(map, &adapter->maps, list) {
-		if (map->addr == addr)
+		if (map->addr == addr) {
+			if (!map->pinned)
+				return NULL;
 			return map;
+		}
 	}
 	return NULL;
 }

arch/s390/kvm/pci.c

@@ -190,40 +190,61 @@ static int kvm_zpci_clear_airq(struct zpci_dev *zdev)
 	return cc ? -EIO : 0;
 }
 
-static inline void unaccount_mem(unsigned long nr_pages)
+static inline void unaccount_mem(struct kvm_zdev *kzdev, unsigned long nr_pages)
 {
-	struct user_struct *user = get_uid(current_user());
+	struct user_struct *user = kzdev->user_account;
+	struct mm_struct *mm_account = kzdev->mm_account;
 
-	if (user)
+	if (user) {
 		atomic_long_sub(nr_pages, &user->locked_vm);
-	if (current->mm)
-		atomic64_sub(nr_pages, &current->mm->pinned_vm);
+		free_uid(user);
+		kzdev->user_account = NULL;
+	}
+
+	if (mm_account) {
+		atomic64_sub(nr_pages, &mm_account->pinned_vm);
+		mmdrop(mm_account);
+		kzdev->mm_account = NULL;
+	}
 }
 
-static inline int account_mem(unsigned long nr_pages)
+static inline int account_mem(struct kvm_zdev *kzdev, unsigned long nr_pages)
 {
 	struct user_struct *user = get_uid(current_user());
 	unsigned long page_limit, cur_pages, new_pages;
+	int rc = 0;
 
 	page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 
 	cur_pages = atomic_long_read(&user->locked_vm);
 	do {
 		new_pages = cur_pages + nr_pages;
-		if (new_pages > page_limit)
-			return -ENOMEM;
+		if (new_pages > page_limit) {
+			rc = -ENOMEM;
+			goto out;
+		}
 	} while (!atomic_long_try_cmpxchg(&user->locked_vm, &cur_pages, new_pages));
 
-	atomic64_add(nr_pages, &current->mm->pinned_vm);
+	if (current->mm) {
+		mmgrab(current->mm);
+		atomic64_add(nr_pages, &current->mm->pinned_vm);
+	}
+
+	kzdev->user_account = user;
+	kzdev->mm_account = current->mm;
 
 	return 0;
+
+out:
+	free_uid(user);
+	return rc;
 }
 
 static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib,
 				   bool assist)
 {
 	struct page *pages[1], *aibv_page, *aisb_page = NULL;
-	unsigned int msi_vecs, idx;
+	unsigned int msi_vecs, idx, size;
 	struct zpci_gaite *gaite;
 	unsigned long hva, bit;
 	struct kvm *kvm;
@@ -237,6 +258,10 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib,
 	if (zdev->gisa == 0)
 		return -EINVAL;
 
+	/* AIF already enabled for the device */
+	if (zdev->kzdev->fib.fmt0.aibv != 0)
+		return -EINVAL;
+
 	kvm = zdev->kzdev->kvm;
 	msi_vecs = min_t(unsigned int, fib->fmt0.noi, zdev->max_msi);
 
@@ -246,6 +271,14 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib,
 		return gisc;
 
 	/* Replace AIBV address */
+	size = BITS_TO_LONGS(msi_vecs + fib->fmt0.aibvo) * sizeof(unsigned long);
+	npages = DIV_ROUND_UP((fib->fmt0.aibv & ~PAGE_MASK) + size, PAGE_SIZE);
+	/* AIBV cannot span more than 1 page */
+	if (npages > 1) {
+		rc = -EINVAL;
+		goto out;
+	}
+
 	idx = srcu_read_lock(&kvm->srcu);
 	hva = gfn_to_hva(kvm, gpa_to_gfn((gpa_t)fib->fmt0.aibv));
 	npages = pin_user_pages_fast(hva, 1, FOLL_WRITE | FOLL_LONGTERM, pages);
@@ -261,6 +294,12 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib,
 
 	/* Pin the guest AISB if one was specified */
 	if (fib->fmt0.sum == 1) {
+		/* AISB must be dword aligned */
+		if (fib->fmt0.aisb & 0x7) {
+			rc = -EINVAL;
+			goto unpin1;
+		}
+
 		idx = srcu_read_lock(&kvm->srcu);
 		hva = gfn_to_hva(kvm, gpa_to_gfn((gpa_t)fib->fmt0.aisb));
 		npages = pin_user_pages_fast(hva, 1, FOLL_WRITE | FOLL_LONGTERM,
@@ -275,20 +314,28 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib,
 	}
 
 	/* Account for pinned pages, roll back on failure */
-	if (account_mem(pcount))
+	rc = account_mem(zdev->kzdev, pcount);
+	if (rc)
 		goto unpin2;
 
 	/* AISB must be allocated before we can fill in GAITE */
 	mutex_lock(&aift->aift_lock);
 	bit = airq_iv_alloc_bit(aift->sbv);
-	if (bit == -1UL)
+	if (bit == -1UL) {
+		rc = -ENOMEM;
 		goto unlock;
+	}
 	zdev->aisb = bit; /* store the summary bit number */
 	zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA |
 				    AIRQ_IV_BITLOCK |
 				    AIRQ_IV_GUESTVEC,
 				    phys_to_virt(fib->fmt0.aibv));
 
+	if (!zdev->aibv) {
+		rc = -ENOMEM;
+		goto free_aisb;
+	}
+
 	spin_lock_irq(&aift->gait_lock);
 	gaite = aift->gait + zdev->aisb;
 
@@ -311,21 +358,39 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib,
 	aift->kzdev[zdev->aisb] = zdev->kzdev;
 	spin_unlock_irq(&aift->gait_lock);
 
-	/* Update guest FIB for re-issue */
-	fib->fmt0.aisbo = zdev->aisb & 63;
-	fib->fmt0.aisb = virt_to_phys(aift->sbv->vector) + (zdev->aisb / 64) * 8;
-	fib->fmt0.isc = gisc;
-
 	/* Save some guest fib values in the host for later use */
-	zdev->kzdev->fib.fmt0.isc = fib->fmt0.isc;
+	zdev->kzdev->fib.fmt0.isc = gisc;
 	zdev->kzdev->fib.fmt0.aibv = fib->fmt0.aibv;
-	mutex_unlock(&aift->aift_lock);
 
 	/* Issue the clp to setup the irq now */
 	rc = kvm_zpci_set_airq(zdev);
-	return rc;
+	if (!rc) {
+		mutex_unlock(&aift->aift_lock);
+		return rc;
+	}
 
+	/* Start cleanup */
+	zdev->kzdev->fib.fmt0.isc = 0;
+	zdev->kzdev->fib.fmt0.aibv = 0;
+
+	spin_lock_irq(&aift->gait_lock);
+	gaite->count--;
+	gaite->aisb = 0;
+	gaite->gisc = 0;
+	gaite->aisbo = 0;
+	gaite->gisa = 0;
+	aift->kzdev[zdev->aisb] = NULL;
+	spin_unlock_irq(&aift->gait_lock);
+
+	airq_iv_release(zdev->aibv);
+	zdev->aibv = NULL;
+
+free_aisb:
+	airq_iv_free_bit(aift->sbv, zdev->aisb);
+	zdev->aisb = 0;
 unlock:
+	if (pcount > 0)
+		unaccount_mem(zdev->kzdev, pcount);
 	mutex_unlock(&aift->aift_lock);
 unpin2:
 	if (fib->fmt0.sum == 1)
@@ -396,7 +461,7 @@ static int kvm_s390_pci_aif_disable(struct zpci_dev *zdev, bool force)
 		pcount++;
 	}
 	if (pcount > 0)
-		unaccount_mem(pcount);
+		unaccount_mem(kzdev, pcount);
 out:
 	mutex_unlock(&aift->aift_lock);
 

arch/s390/kvm/pci.h

@@ -22,6 +22,8 @@ struct kvm_zdev {
 	struct kvm *kvm;
 	struct zpci_fib fib;
 	struct list_head entry;
+	struct user_struct *user_account;
+	struct mm_struct *mm_account;
 };
 
 struct zpci_gaite {