[PATCH v4 1/3] KVM: s390: Add map/unmap ioctl and clean mappings post-guest

[Douglas Freimuth <freimuth@linux.ibm.com>]

S390 needs map/unmap ioctls, which map the adapter set
indicator pages, so the pages can be accessed when interrupts are
disabled. The mappings are cleaned up when the guest is removed.

Map/Unmap ioctls are fenced in order to avoid the longterm pinning
in Secure Execution environments. In Secure Execution
environments the path of execution available before this patch is followed.

Statistical counters to count map/unmap functions for adapter indicator
pages are added. The counters can be used to analyze
map/unmap functions in non-Secure Execution environments and similarly
can be used to analyze Secure Execution environments where the counters
will not be incremented as the adapter indicator pages are not mapped.

Signed-off-by: Douglas Freimuth <freimuth@linux.ibm.com>
---
 arch/s390/include/asm/kvm_host.h |   5 +
 arch/s390/kvm/interrupt.c        | 159 ++++++++++++++++++++++++++-----
 arch/s390/kvm/kvm-s390.c         |  30 ++++++
 3 files changed, 169 insertions(+), 25 deletions(-)

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 3039c88daa63..e84532eca75f 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -448,6 +448,8 @@ struct kvm_vcpu_arch {
 struct kvm_vm_stat {
 	struct kvm_vm_stat_generic generic;
 	u64 inject_io;
+	u64 io_390_adapter_map;
+	u64 io_390_adapter_unmap;
 	u64 inject_float_mchk;
 	u64 inject_pfault_done;
 	u64 inject_service_signal;
@@ -479,6 +481,9 @@ struct s390_io_adapter {
 	bool masked;
 	bool swap;
 	bool suppressible;
+	raw_spinlock_t maps_lock;
+	struct list_head maps;
+	unsigned int nr_maps;
 };
 
 #define MAX_S390_IO_ADAPTERS ((MAX_ISC + 1) * 8)
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 7cb8ce833b62..49c95c1eb9b1 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -2426,6 +2426,9 @@ static int register_io_adapter(struct kvm_device *dev,
 	if (!adapter)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&adapter->maps);
+	raw_spin_lock_init(&adapter->maps_lock);
+	adapter->nr_maps = 0;
 	adapter->id = adapter_info.id;
 	adapter->isc = adapter_info.isc;
 	adapter->maskable = adapter_info.maskable;
@@ -2450,12 +2453,128 @@ int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked)
 	return ret;
 }
 
+static struct page *get_map_page(struct kvm *kvm, u64 uaddr)
+{
+	struct mm_struct *mm = kvm->mm;
+	struct page *page = NULL;
+	int locked = 1;
+
+	if (mmget_not_zero(mm)) {
+		mmap_read_lock(mm);
+		get_user_pages_remote(mm, uaddr, 1, FOLL_WRITE,
+				      &page, &locked);
+		if (locked)
+			mmap_read_unlock(mm);
+		mmput(mm);
+	}
+
+	return page;
+}
+
+static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr)
+{
+	struct s390_io_adapter *adapter = get_io_adapter(kvm, id);
+	struct s390_map_info *map;
+	unsigned long flags;
+	__u64 host_addr;
+	int ret, idx;
+
+	if (!adapter || !addr)
+		return -EINVAL;
+
+	map = kzalloc_obj(*map, GFP_KERNEL_ACCOUNT);
+	if (!map)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&map->list);
+	idx = srcu_read_lock(&kvm->srcu);
+	host_addr = gpa_to_hva(kvm, addr);
+	if (kvm_is_error_hva(host_addr)) {
+		srcu_read_unlock(&kvm->srcu, idx);
+		kfree(map);
+		ret = -EFAULT;
+		goto out;
+	}
+	srcu_read_unlock(&kvm->srcu, idx);
+	map->guest_addr = addr;
+	map->addr = host_addr;
+	map->page = get_map_page(kvm, host_addr);
+	if (!map->page) {
+		ret = -EINVAL;
+		goto out;
+	}
+	raw_spin_lock_irqsave(&adapter->maps_lock, flags);
+	if (adapter->nr_maps < MAX_S390_ADAPTER_MAPS) {
+		list_add_tail(&map->list, &adapter->maps);
+		adapter->nr_maps++;
+		ret = 0;
+	} else {
+		put_page(map->page);
+		ret = -EINVAL;
+	}
+	raw_spin_unlock_irqrestore(&adapter->maps_lock, flags);
+out:
+	if (ret)
+		kfree(map);
+	return ret;
+}
+
+static int kvm_s390_adapter_unmap(struct kvm *kvm, unsigned int id, __u64 addr)
+{
+	struct s390_io_adapter *adapter = get_io_adapter(kvm, id);
+	struct s390_map_info *map, *tmp;
+	struct page *map_page_to_put = NULL;
+	u64 map_addr_to_mark = 0;
+	unsigned long flags;
+	int found = 0, idx;
+
+	if (!adapter || !addr)
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&adapter->maps_lock, flags);
+	list_for_each_entry_safe(map, tmp, &adapter->maps, list) {
+		if (map->guest_addr == addr) {
+			found = 1;
+			adapter->nr_maps--;
+			list_del(&map->list);
+			map_page_to_put = map->page;
+			map_addr_to_mark = map->guest_addr;
+			kfree(map);
+			break;
+		}
+	}
+	raw_spin_unlock_irqrestore(&adapter->maps_lock, flags);
+
+	if (found) {
+		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);
+		put_page(map_page_to_put);
+	}
+
+	return found ? 0 : -ENOENT;
+}
+
 void kvm_s390_destroy_adapters(struct kvm *kvm)
 {
 	int i;
+	struct s390_map_info *map, *tmp;
+	unsigned long flags;
 
-	for (i = 0; i < MAX_S390_IO_ADAPTERS; i++)
+	for (i = 0; i < MAX_S390_IO_ADAPTERS; i++) {
+		if (!kvm->arch.adapters[i])
+			continue;
+		raw_spin_lock_irqsave(&kvm->arch.adapters[i]->maps_lock, flags);
+		list_for_each_entry_safe(map, tmp,
+					 &kvm->arch.adapters[i]->maps, list) {
+			list_del(&map->list);
+			put_page(map->page);
+			kfree(map);
+		}
+		raw_spin_unlock_irqrestore(&kvm->arch.adapters[i]->maps_lock, flags);
 		kfree(kvm->arch.adapters[i]);
+	}
 }
 
 static int modify_io_adapter(struct kvm_device *dev,
@@ -2477,14 +2596,22 @@ static int modify_io_adapter(struct kvm_device *dev,
 		if (ret > 0)
 			ret = 0;
 		break;
-	/*
-	 * The following operations are no longer needed and therefore no-ops.
-	 * The gpa to hva translation is done when an IRQ route is set up. The
-	 * set_irq code uses get_user_pages_remote() to do the actual write.
-	 */
 	case KVM_S390_IO_ADAPTER_MAP:
 	case KVM_S390_IO_ADAPTER_UNMAP:
-		ret = 0;
+		/* If in Secure Execution mode do not long term pin. */
+		mutex_lock(&dev->kvm->lock);
+		if (kvm_s390_pv_is_protected(dev->kvm)) {
+			mutex_unlock(&dev->kvm->lock);
+			return 0;
+		}
+		if (req.type == KVM_S390_IO_ADAPTER_MAP) {
+			dev->kvm->stat.io_390_adapter_map++;
+			ret = kvm_s390_adapter_map(dev->kvm, req.id, req.addr);
+		} else {
+			dev->kvm->stat.io_390_adapter_unmap++;
+			ret = kvm_s390_adapter_unmap(dev->kvm, req.id, req.addr);
+		}
+		mutex_unlock(&dev->kvm->lock);
 		break;
 	default:
 		ret = -EINVAL;
@@ -2730,24 +2857,6 @@ static unsigned long get_ind_bit(__u64 addr, unsigned long bit_nr, bool swap)
 	return swap ? (bit ^ (BITS_PER_LONG - 1)) : bit;
 }
 
-static struct page *get_map_page(struct kvm *kvm, u64 uaddr)
-{
-	struct mm_struct *mm = kvm->mm;
-	struct page *page = NULL;
-	int locked = 1;
-
-	if (mmget_not_zero(mm)) {
-		mmap_read_lock(mm);
-		get_user_pages_remote(mm, uaddr, 1, FOLL_WRITE,
-				      &page, &locked);
-		if (locked)
-			mmap_read_unlock(mm);
-		mmput(mm);
-	}
-
-	return page;
-}
-
 static int adapter_indicators_set(struct kvm *kvm,
 				  struct s390_io_adapter *adapter,
 				  struct kvm_s390_adapter_int *adapter_int)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index d7838334a338..d1e1bed42c79 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -68,6 +68,8 @@
 const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS(),
 	STATS_DESC_COUNTER(VM, inject_io),
+	STATS_DESC_COUNTER(VM, io_390_adapter_map),
+	STATS_DESC_COUNTER(VM, io_390_adapter_unmap),
 	STATS_DESC_COUNTER(VM, inject_float_mchk),
 	STATS_DESC_COUNTER(VM, inject_pfault_done),
 	STATS_DESC_COUNTER(VM, inject_service_signal),
@@ -2491,6 +2493,33 @@ static int kvm_s390_pv_dmp(struct kvm *kvm, struct kvm_pv_cmd *cmd,
 	return r;
 }
 
+static void kvm_s390_unmap_all_adapters_pv(struct kvm *kvm)
+{
+	struct s390_map_info *map, *tmp;
+	LIST_HEAD(local_list);
+	unsigned long flags;
+	int i, idx;
+
+	for (i = 0; i < MAX_S390_IO_ADAPTERS; i++) {
+		if (!kvm->arch.adapters[i])
+			continue;
+		raw_spin_lock_irqsave(&kvm->arch.adapters[i]->maps_lock, flags);
+		list_splice_init(&kvm->arch.adapters[i]->maps, &local_list);
+		kvm->arch.adapters[i]->nr_maps = 0;
+		raw_spin_unlock_irqrestore(&kvm->arch.adapters[i]->maps_lock, flags);
+
+		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);
+			put_page(map->page);
+			kfree(map);
+		}
+	}
+}
+
 static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
 {
 	const bool need_lock = (cmd->cmd != KVM_PV_ASYNC_CLEANUP_PERFORM);
@@ -2507,6 +2536,7 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
 		if (kvm_s390_pv_is_protected(kvm))
 			break;
 
+		kvm_s390_unmap_all_adapters_pv(kvm);
 		mmap_write_lock(kvm->mm);
 		/*
 		 * Disable creation of new THPs. Existing THPs can stay, they
-- 
2.52.0