[PATCH v8 09/10] s390/vfio_ccw: selectively expand io_mutex

[Eric Farman <farman@linux.ibm.com>]

The io_mutex was defined to serialize the io_regions, but then has
also sort of been associated with the I/O themselves because of
the close relationship they share.

With the handful of races that are possible, the choices are either to:
 A) expand the scope of io_mutex to close these remaining windows, or
 B) reduce the scope of io_mutex to just io_region, and introduce a new
    lock mechanism for the remaining I/O resources

This patch implements A, since B brings with it a lot more interactions
that would need to be tracked and kept in a correct hierarchy.

The biggest functional change is the introduction of a workqueue
element for the cp_free() called out of fsm_notoper(), which is could
be run in an interrupt context and thus cannot be acquiring mutexes.

Fixes: 4f76617378ee ("vfio-ccw: protect the I/O region")
Cc: stable@vger.kernel.org
Signed-off-by: Eric Farman <farman@linux.ibm.com>
---
 drivers/s390/cio/vfio_ccw_chp.c     | 2 +-
 drivers/s390/cio/vfio_ccw_cp.c      | 8 +++++++-
 drivers/s390/cio/vfio_ccw_drv.c     | 6 ++++--
 drivers/s390/cio/vfio_ccw_fsm.c     | 5 +++++
 drivers/s390/cio/vfio_ccw_private.h | 3 ++-
 5 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c
index f3015132d4b5..9269b54f5cfd 100644
--- a/drivers/s390/cio/vfio_ccw_chp.c
+++ b/drivers/s390/cio/vfio_ccw_chp.c
@@ -98,13 +98,13 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private,
 	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);
 
-	mutex_lock(&private->io_mutex);
 	if (i >= private->num_regions) {
 		ret = -EINVAL;
 		goto out;
diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 5ef082b8289a..58722c4baa25 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -977,17 +977,23 @@ void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
  */
 bool cp_iova_pinned(struct channel_program *cp, u64 iova, u64 length)
 {
+	struct vfio_ccw_private *private =
+		container_of(cp, struct vfio_ccw_private, cp);
 	struct ccwchain *chain;
 	int i;
 
 	if (!cp->initialized)
 		return false;
 
+	mutex_lock(&private->io_mutex);
 	list_for_each_entry(chain, &cp->ccwchain_list, next) {
 		for (i = 0; i < chain->ch_len; i++)
-			if (page_array_iova_pinned(&chain->ch_pa[i], iova, length))
+			if (page_array_iova_pinned(&chain->ch_pa[i], iova, length)) {
+				mutex_unlock(&private->io_mutex);
 				return true;
+			}
 	}
+	mutex_unlock(&private->io_mutex);
 
 	return false;
 }
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index c197ad5ab580..757ff5b2556e 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -91,6 +91,7 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 
 	is_final = !(scsw_actl(&irb->scsw) &
 		     (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT));
+	mutex_lock(&private->io_mutex);
 	if (scsw_is_solicited(&irb->scsw)) {
 		cp_update_scsw(&private->cp, &irb->scsw);
 		if (is_final && private->state == VFIO_CCW_STATE_CP_PENDING) {
@@ -98,9 +99,7 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 			cp_is_finished = true;
 		}
 	}
-	mutex_lock(&private->io_mutex);
 	memcpy(private->io_region->irb_area, irb, sizeof(*irb));
-	mutex_unlock(&private->io_mutex);
 
 	/*
 	 * Reset to IDLE only if processing of a channel program
@@ -110,6 +109,7 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 	 */
 	if (cp_is_finished)
 		private->state = VFIO_CCW_STATE_IDLE;
+	mutex_unlock(&private->io_mutex);
 
 	if (private->io_trigger)
 		eventfd_signal(private->io_trigger);
@@ -131,7 +131,9 @@ void vfio_ccw_notoper_todo(struct work_struct *work)
 
 	private = container_of(work, struct vfio_ccw_private, notoper_work);
 
+	mutex_lock(&private->io_mutex);
 	cp_free(&private->cp);
+	mutex_unlock(&private->io_mutex);
 }
 
 /*
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index 4d47a3c7b9a0..5fd94e9d5c61 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -170,6 +170,7 @@ static void fsm_notoper(struct vfio_ccw_private *private,
 	css_sched_sch_todo(sch, SCH_TODO_UNREG);
 	private->state = VFIO_CCW_STATE_NOT_OPER;
 
+	/* This routine could be called from IRQ context, so defer */
 	queue_work(vfio_ccw_work_q, &private->notoper_work);
 }
 
@@ -409,7 +410,11 @@ static void fsm_close(struct vfio_ccw_private *private,
 
 	private->state = VFIO_CCW_STATE_STANDBY;
 	spin_unlock_irq(&sch->lock);
+
+	mutex_lock(&private->io_mutex);
 	cp_free(&private->cp);
+	mutex_unlock(&private->io_mutex);
+
 	return;
 
 err_unlock:
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index e2256402b089..739121116ab6 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -88,7 +88,8 @@ struct vfio_ccw_parent {
  * @state: internal state of the device
  * @completion: synchronization helper of the I/O completion
  * @io_region: MMIO region to input/output I/O arguments/results
- * @io_mutex: protect against concurrent update of I/O regions
+ * @io_mutex: protect against concurrent update of I/O resources
+ *            and @cp lifecycle
  * @region: additional regions for other subchannel operations
  * @cmd_region: MMIO region for asynchronous I/O commands other than START
  * @schib_region: MMIO region for SCHIB information
-- 
2.53.0