KVM: s390: Fall back to short-term pinning in MAP ioctl

FOLL_LONGTERM pinning fails for some memory types, such as file-backed
guest memory. As a result, kvm_s390_adapter_map() returns -EINVAL and
irqfd adapter registration fails even though interrupt delivery could
still work via the existing non-atomic path.

When FOLL_LONGTERM pinning fails, verify that the page is accessible
using a short-term pin instead. If the short-term pin succeeds, unpin
the page and add a map entry with pinned=false to preserve MAP/UNMAP
symmetry. The non-atomic irqfd path already performs short-term pinning
for interrupt delivery, so this restores the previous behavior for
memory that cannot be pinned long-term.

get_map_info() is updated to return NULL for unpinned entries so that
the atomic irqfd fast path falls back to the non-atomic path.
kvm_s390_adapter_unmap() and kvm_s390_unmap_all_adapters() skip dirty
marking and unpin for unpinned entries.

Update Documentation/virt/kvm/devices/s390_flic.rst to reflect the
new MAP/UNMAP behavior.

Fixes: c9a568838086 ("KVM: s390: Add map/unmap ioctl and clean mappings post-guest")
Signed-off-by: Jaehoon Kim <jhkim@linux.ibm.com>
Reviewed-by: Douglas Freimuth <freimuth@linux.ibm.com>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>

3 files changed, 60 insertions, 16 deletions

diff --git a/Documentation/virt/kvm/devices/s390_flic.rst b/Documentation/virt/kvm/devices/s390_flic.rst
index b784f8016748..983c858b444a 100644
--- a/Documentation/virt/kvm/devices/s390_flic.rst
+++ b/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
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index eaa34c5bd3c1..c172f9b212d1 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/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 {
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 9e3e6b0d72ad..7514d9e2403c 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/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;
 }