s390/vfio_ccw: Implement a crw lock

commit 16b0798 upstream.

Unlike the channel_program struct, which covers synchronous I/O
submissions and asynchronous interrupts, the CRW region relies
exclusively on asynchronous events coming from hardware.

Implement a lock to manage the list of those payloads, to ensure
they are read cohesively.

Fixes: 3f02cb2 ("vfio-ccw: Wire up the CRW irq and CRW region")
Cc: stable@vger.kernel.org
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Reviewed-by: Farhan Ali <alifm@linux.ibm.com>
Signed-off-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
[farman@linux.ibm.com: resolved merge conflict]
Signed-off-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Author: efarman

drivers/s390/cio/vfio_ccw_chp.c

@@ -93,18 +93,13 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private,
 	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
 	struct ccw_crw_region *region;
 	struct vfio_ccw_crw *crw;
+	unsigned long flags;
 	int ret;
 
 	if (pos + count > sizeof(*region))
 		return -EINVAL;
 
 	mutex_lock(&private->io_mutex);
-	crw = list_first_entry_or_null(&private->crw,
-				       struct vfio_ccw_crw, next);
-
-	if (crw)
-		list_del(&crw->next);
-
 	if (i >= private->num_regions) {
 		ret = -EINVAL;
 		goto out;
@@ -113,6 +108,16 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private,
 	i = array_index_nospec(i, private->num_regions);
 	region = private->region[i].data;
 
+	spin_lock_irqsave(&private->crw_lock, flags);
+	crw = list_first_entry_or_null(&private->crw,
+				       struct vfio_ccw_crw, next);
+
+	if (crw)
+		list_del(&crw->next);
+
+	/* Drop CRW lock while copying to userspace */
+	spin_unlock_irqrestore(&private->crw_lock, flags);
+
 	if (crw)
 		memcpy(&region->crw, &crw->crw, sizeof(region->crw));
 
@@ -122,15 +127,16 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private,
 		ret = count;
 
 	region->crw = 0;
-
-out:
-	mutex_unlock(&private->io_mutex);
-
 	kfree(crw);
 
 	/* Notify the guest if more CRWs are on our queue */
+	spin_lock_irqsave(&private->crw_lock, flags);
 	if (!list_empty(&private->crw) && private->crw_trigger)
 		eventfd_signal(private->crw_trigger, 1);
+	spin_unlock_irqrestore(&private->crw_lock, flags);
+
+out:
+	mutex_unlock(&private->io_mutex);
 
 	return ret;
 }

drivers/s390/cio/vfio_ccw_drv.c

@@ -118,11 +118,14 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 void vfio_ccw_crw_todo(struct work_struct *work)
 {
 	struct vfio_ccw_private *private;
+	unsigned long flags;
 
 	private = container_of(work, struct vfio_ccw_private, crw_work);
 
+	spin_lock_irqsave(&private->crw_lock, flags);
 	if (!list_empty(&private->crw) && private->crw_trigger)
 		eventfd_signal(private->crw_trigger, 1);
+	spin_unlock_irqrestore(&private->crw_lock, flags);
 }
 
 void vfio_ccw_notoper_todo(struct work_struct *work)
@@ -286,6 +289,7 @@ static void vfio_ccw_queue_crw(struct vfio_ccw_private *private,
 			       unsigned int rsid)
 {
 	struct vfio_ccw_crw *crw;
+	unsigned long flags;
 
 	/*
 	 * If unable to allocate a CRW, just drop the event and
@@ -303,7 +307,9 @@ static void vfio_ccw_queue_crw(struct vfio_ccw_private *private,
 	crw->crw.erc = erc;
 	crw->crw.rsid = rsid;
 
+	spin_lock_irqsave(&private->crw_lock, flags);
 	list_add_tail(&crw->next, &private->crw);
+	spin_unlock_irqrestore(&private->crw_lock, flags);
 	queue_work(vfio_ccw_work_q, &private->crw_work);
 }
 

drivers/s390/cio/vfio_ccw_ops.c

@@ -55,6 +55,7 @@ static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev)
 	INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
 	INIT_WORK(&private->crw_work, vfio_ccw_crw_todo);
 	INIT_WORK(&private->notoper_work, vfio_ccw_notoper_todo);
+	spin_lock_init(&private->crw_lock);
 
 	private->cp.guest_cp = kcalloc(CCWCHAIN_LEN_MAX, sizeof(struct ccw1),
 				       GFP_KERNEL);
@@ -132,6 +133,7 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev)
 	struct vfio_ccw_private *private =
 		container_of(vdev, struct vfio_ccw_private, vdev);
 	struct vfio_ccw_crw *crw, *temp;
+	unsigned long flags;
 
 	/*
 	 * Ensure these work items are fully drained, so none can
@@ -147,10 +149,12 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev)
 	cancel_work_sync(&private->crw_work);
 	flush_work(&private->notoper_work);
 
+	spin_lock_irqsave(&private->crw_lock, flags);
 	list_for_each_entry_safe(crw, temp, &private->crw, next) {
 		list_del(&crw->next);
 		kfree(crw);
 	}
+	spin_unlock_irqrestore(&private->crw_lock, flags);
 
 	kmem_cache_free(vfio_ccw_crw_region, private->crw_region);
 	kmem_cache_free(vfio_ccw_schib_region, private->schib_region);

drivers/s390/cio/vfio_ccw_private.h

@@ -98,6 +98,8 @@ struct vfio_ccw_parent {
  * @cp: channel program for the current I/O operation
  * @irb: irb info received from interrupt
  * @scsw: scsw info
+ * @crw_lock: serialization of CRW list information
+ * @crw: list of Channel Report Word elements
  * @io_trigger: eventfd ctx for signaling userspace I/O results
  * @crw_trigger: eventfd ctx for signaling userspace CRW information
  * @req_trigger: eventfd ctx for signaling userspace to return device
@@ -120,6 +122,8 @@ struct vfio_ccw_private {
 	struct channel_program	cp;
 	struct irb		irb;
 	union scsw		scsw;
+
+	spinlock_t		crw_lock;
 	struct list_head	crw;
 
 	struct eventfd_ctx	*io_trigger;