FAILED: patch "[PATCH] s390/vfio_ccw: Implement a crw lock" failed to apply to 6.1-stable tree

FAILED: patch "[PATCH] s390/vfio_ccw: Implement a crw lock" failed to apply to 6.1-stable tree

[gregkh]

The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable@vger.kernel.org>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 16b0798024c0e9117e395829ddbbe70981c79d9c
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2026082011-january-overcook-6d98@gregkh' --subject-prefix 'PATCH 6.1.y' 'HEAD^..'

Possible dependencies:



thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 16b0798024c0e9117e395829ddbbe70981c79d9c Mon Sep 17 00:00:00 2001
From: Eric Farman <farman@linux.ibm.com>
Date: Tue, 28 Jul 2026 05:30:22 +0200
Subject: [PATCH] s390/vfio_ccw: Implement a crw lock

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: 3f02cb2fd9d2 ("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>

diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c
index 9269b54f5cfd..7708eb4d6de0 100644
--- a/drivers/s390/cio/vfio_ccw_chp.c
+++ b/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);
+	spin_unlock_irqrestore(&private->crw_lock, flags);
+
+out:
+	mutex_unlock(&private->io_mutex);
 
 	return ret;
 }
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 757ff5b2556e..ab6b518cc353 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/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);
+	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);
 }
 
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index 1df6d649565b..5ce91285c7d5 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/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 = kzalloc_objs(struct ccw1, CCWCHAIN_LEN_MAX);
 	if (!private->cp.guest_cp)
@@ -131,6 +132,7 @@ 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
@@ -146,10 +148,12 @@ 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);
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index 739121116ab6..3bd0171d38d0 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/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;

[PATCH 6.1.y 1/4] s390/vfio_ccw: Cancel existing workqueues

[Sasha Levin]

From: Eric Farman <farman@linux.ibm.com>

[ Upstream commit 79c60b2c61105368dcc8444eb45847e21734f7c4 ]

The initialization of the io_work and crw_work workqueues begs the
question of whether they should be un-initialized. Add the corresponding
cleanup tags in _release_dev to ensure work isn't dispatched after
the private struct is free'd.

Suggested-by: Matthew Rosato <mjrosato@linux.ibm.com>
Fixes: e5f84dbaea59 ("vfio: ccw: return I/O results asynchronously")
Fixes: 3f02cb2fd9d2 ("vfio-ccw: Wire up the CRW irq and CRW region")
Cc: stable@vger.kernel.org
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Stable-dep-of: 16b0798024c0 ("s390/vfio_ccw: Implement a crw lock")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/s390/cio/vfio_ccw_ops.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index 5af74d3142492..c73f675ae29a1 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -86,6 +86,13 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev)
 	struct vfio_ccw_private *private =
 		container_of(vdev, struct vfio_ccw_private, vdev);
 
+	/*
+	 * Ensure these work items are fully drained, so none can
+	 * fire after being released.
+	 */
+	cancel_work_sync(&private->io_work);
+	cancel_work_sync(&private->crw_work);
+
 	/*
 	 * We cannot free vfio_ccw_private here because it includes
 	 * parent info which must be free'ed by css driver.
@@ -162,6 +169,14 @@ static void vfio_ccw_mdev_close_device(struct vfio_device *vdev)
 		container_of(vdev, struct vfio_ccw_private, vdev);
 
 	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_CLOSE);
+
+	/*
+	 * Ensure these work items are drained, in the event the
+	 * device is re-opened instead of released.
+	 */
+	cancel_work_sync(&private->io_work);
+	cancel_work_sync(&private->crw_work);
+
 	vfio_ccw_unregister_dev_regions(private);
 }
 
-- 
2.53.0

[PATCH 6.1.y 2/4] s390/vfio_ccw: Move cp cleanup out of not operational

[Sasha Levin]

From: Eric Farman <farman@linux.ibm.com>

[ Upstream commit 0c11f61a876ed6fcca53d442ed3f33ea8362a0f9 ]

The fsm_notoper() routine is called when the device has been
lost, and is (by definition) no longer operational. Since this
can happen asynchronously from the normal behavior of the
driver, the cleanup may happen when holding other locks
in the calling sequence (notably, the cio subchannel lock).

Push the cleanup of the private->cp resources to a workqueue,
where it can be done out from under that lock sequence and
a future patch can safely manage the locking requirements.

Fixes: 204b394a23ad ("vfio/ccw: Move FSM open/close to MDEV open/close")
Cc: stable@vger.kernel.org
Signed-off-by: Eric Farman <farman@linux.ibm.com>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Stable-dep-of: 16b0798024c0 ("s390/vfio_ccw: Implement a crw lock")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/s390/cio/vfio_ccw_drv.c     | 10 ++++++++++
 drivers/s390/cio/vfio_ccw_fsm.c     |  3 +--
 drivers/s390/cio/vfio_ccw_ops.c     | 12 ++++++++++++
 drivers/s390/cio/vfio_ccw_private.h |  2 ++
 4 files changed, 25 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 7f5402fe857a2..dd181752e11a5 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -116,6 +116,15 @@ static void vfio_ccw_crw_todo(struct work_struct *work)
 		eventfd_signal(private->crw_trigger, 1);
 }
 
+static void vfio_ccw_notoper_todo(struct work_struct *work)
+{
+	struct vfio_ccw_private *private;
+
+	private = container_of(work, struct vfio_ccw_private, notoper_work);
+
+	cp_free(&private->cp);
+}
+
 /*
  * Css driver callbacks
  */
@@ -141,6 +150,7 @@ static struct vfio_ccw_private *vfio_ccw_alloc_private(struct subchannel *sch)
 	INIT_LIST_HEAD(&private->crw);
 	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);
 
 	private->cp.guest_cp = kcalloc(CCWCHAIN_LEN_MAX, sizeof(struct ccw1),
 				       GFP_KERNEL);
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index a59c758869f8f..d2a27f50631fa 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -176,8 +176,7 @@ 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 is usually handled during CLOSE event */
-	cp_free(&private->cp);
+	queue_work(vfio_ccw_work_q, &private->notoper_work);
 }
 
 /*
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index c73f675ae29a1..46615f5e2f482 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -89,9 +89,16 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev)
 	/*
 	 * Ensure these work items are fully drained, so none can
 	 * fire after being released.
+	 *
+	 * notoper_work should have nothing to do here, because only
+	 * open devices could have channel_program resources in use
+	 * and those would be released during close. Nevertheless,
+	 * call flush here as well to be certain anything that was
+	 * allocated is freed.
 	 */
 	cancel_work_sync(&private->io_work);
 	cancel_work_sync(&private->crw_work);
+	flush_work(&private->notoper_work);
 
 	/*
 	 * We cannot free vfio_ccw_private here because it includes
@@ -173,9 +180,14 @@ static void vfio_ccw_mdev_close_device(struct vfio_device *vdev)
 	/*
 	 * Ensure these work items are drained, in the event the
 	 * device is re-opened instead of released.
+	 *
+	 * notoper_work needs to be given a chance to run if it
+	 * is queued, so any memory associated with the channel
+	 * program can be returned.
 	 */
 	cancel_work_sync(&private->io_work);
 	cancel_work_sync(&private->crw_work);
+	flush_work(&private->notoper_work);
 
 	vfio_ccw_unregister_dev_regions(private);
 }
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index bd5fb81456af8..a9e1dd9089306 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -88,6 +88,7 @@ struct vfio_ccw_crw {
  * @req_trigger: eventfd ctx for signaling userspace to return device
  * @io_work: work for deferral process of I/O handling
  * @crw_work: work for deferral process of CRW handling
+ * @notoper_work: work for deferred processing in not-operational state
  * @release_comp: synchronization helper for vfio device release
  * @parent: parent data structures for mdevs created
  */
@@ -114,6 +115,7 @@ struct vfio_ccw_private {
 	struct eventfd_ctx	*req_trigger;
 	struct work_struct	io_work;
 	struct work_struct	crw_work;
+	struct work_struct	notoper_work;
 
 	struct completion	release_comp;
 
-- 
2.53.0

[PATCH 6.1.y 3/4] s390/vfio_ccw: Selectively expand io_mutex

[Sasha Levin]

From: Eric Farman <farman@linux.ibm.com>

[ Upstream commit 34f4feff3e90bd09308fad0974e97113b23b812a ]

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. It also
takes advantage of the workqueue element for cp_free() that now gets
called out of fsm_notoper(), which could be invoked out of an interrupt
context and thus cannot acquire a mutex itself.

Fixes: 4f76617378ee ("vfio-ccw: protect the I/O region")
Cc: stable@vger.kernel.org
Signed-off-by: Eric Farman <farman@linux.ibm.com>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Stable-dep-of: 16b0798024c0 ("s390/vfio_ccw: Implement a crw lock")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 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 11264e2adffcb..ee9688738a950 100644
--- a/drivers/s390/cio/vfio_ccw_chp.c
+++ b/drivers/s390/cio/vfio_ccw_chp.c
@@ -97,13 +97,13 @@ 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 8b0fbfd856235..06f1d34095367 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -904,17 +904,23 @@ 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 dd181752e11a5..ead4c9ea8796c 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -82,6 +82,7 @@ static 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) {
@@ -89,9 +90,7 @@ static 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
@@ -101,6 +100,7 @@ static 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, 1);
@@ -122,7 +122,9 @@ static 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 d2a27f50631fa..aefc4ebf40474 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -176,6 +176,7 @@ 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);
 }
 
@@ -412,7 +413,11 @@ 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 a9e1dd9089306..0d78da9597c0c 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -74,7 +74,8 @@ struct vfio_ccw_crw {
  * @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

[PATCH 6.1.y 4/4] s390/vfio_ccw: Implement a crw lock

[Sasha Levin]

From: Eric Farman <farman@linux.ibm.com>

[ Upstream commit 16b0798024c0e9117e395829ddbbe70981c79d9c ]

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: 3f02cb2fd9d2 ("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>
[ Relocated the `spin_lock_init()` and CRW drain loop from `vfio_ccw_mdev_init_dev()`/`release_dev()` in ops.c to `vfio_ccw_alloc_private()`/`vfio_ccw_free_private()` in drv.c, and kept the 2-argument `eventfd_signal()` form. ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/s390/cio/vfio_ccw_chp.c     | 26 ++++++++++++++++----------
 drivers/s390/cio/vfio_ccw_drv.c     | 10 ++++++++++
 drivers/s390/cio/vfio_ccw_private.h |  4 ++++
 3 files changed, 30 insertions(+), 10 deletions(-)

diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c
index ee9688738a950..3ee2444f3d902 100644
--- a/drivers/s390/cio/vfio_ccw_chp.c
+++ b/drivers/s390/cio/vfio_ccw_chp.c
@@ -92,18 +92,13 @@ 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;
@@ -112,6 +107,16 @@ 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));
 
@@ -121,15 +126,16 @@ 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;
 }
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index ead4c9ea8796c..a8340a69a7c84 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -109,11 +109,14 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work)
 static 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);
 }
 
 static void vfio_ccw_notoper_todo(struct work_struct *work)
@@ -153,6 +156,7 @@ static struct vfio_ccw_private *vfio_ccw_alloc_private(struct subchannel *sch)
 	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);
@@ -199,11 +203,14 @@ static struct vfio_ccw_private *vfio_ccw_alloc_private(struct subchannel *sch)
 static void vfio_ccw_free_private(struct vfio_ccw_private *private)
 {
 	struct vfio_ccw_crw *crw, *temp;
+	unsigned long flags;
 
+	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);
@@ -314,6 +321,7 @@ 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
@@ -331,7 +339,9 @@ 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);
 }
 
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index 0d78da9597c0c..5294910e64cc2 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -84,6 +84,8 @@ struct vfio_ccw_crw {
  * @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
@@ -109,6 +111,8 @@ 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;
-- 
2.53.0