FAILED: patch "[PATCH] s390/vfio-ap: fix stale pqap_hook pointer on error in" failed to apply to 6.1-stable tree

FAILED: patch "[PATCH] s390/vfio-ap: fix stale pqap_hook pointer on error in" 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 4400270ec0348d05dc0439d8f0130853ce7f9e20
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2026090928-anguished-delighted-2103@gregkh' --subject-prefix 'PATCH 6.1.y' 'HEAD^..'

Possible dependencies:



thanks,

greg k-h

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

From 4400270ec0348d05dc0439d8f0130853ce7f9e20 Mon Sep 17 00:00:00 2001
From: Anthony Krowiak <akrowiak@linux.ibm.com>
Date: Thu, 6 Aug 2026 13:34:35 -0400
Subject: [PATCH] s390/vfio-ap: fix stale pqap_hook pointer on error in
 vfio_ap_mdev_set_kvm()

In vfio_ap_mdev_set_kvm(), kvm->arch.crypto.pqap_hook is set to
&matrix_mdev->pqap_hook before the update locks are acquired and the
mdev list is checked for a conflicting assignment. If another mdev is
already attached to the same KVM instance, the function returns -EPERM
without restoring the hook pointer, leaving kvm->arch.crypto.pqap_hook
pointing at the failing matrix_mdev instead of the mdev that legitimately
owns the KVM.

Since matrix_mdev->kvm is never set on this error path,
vfio_ap_mdev_unset_kvm() will not clean up the hook when matrix_mdev
is later closed. If matrix_mdev is subsequently freed, any PQAP
instruction executed by the guest will dereference the stale pointer
through pqap_hook_rwsem, resulting in a use-after-free.

Since kvm->arch.crypto.pqap_hook is only set in the vfio_ap_mdev_set_kvm()
function and is cleared in the vfio_ap_mdev_unset_kvm() function, a check
for 'kvm->arch.crypto.pqap_hook != NULL' is all that is needed to determine
whether it belongs to another mdev. This will alleviate the need to iterate
the matrix_dev->mdev_list list to see if the kvm object is assigned to
another mdev.This was introduced in v3 to alleviate the need to take the
mdevs_lock while iterating the list; however, this did not prevent a
potential race condition.

The pqap_hook_rwsem(write) is now performed inside
get_update_locks_for_kvm(), which is updated to acquire
pqap_hook_rwsem(write) between kvm->lock and mdevs_lock. This ordering
is consistent with the PQAP intercept path, which acquires pqap_hook_rwsem
in read mode while srcu is held under vcpu->mutex, establishing the
dependency: kvm->lock -> vcpu->mutex -> srcu -> pqap_hook_rwsem(read).

The pqap_hook_rwsem is now released inside the
release_update_locks_for_kvm(), which is updated to release
pqap_hook_rwsem(write) between mdevs_lock and kvm->lock.

Additionally, kvm_put_kvm() in vfio_ap_mdev_unset_kvm() is moved
after release_update_locks_for_kvm(). Previously it was called while
kvm->lock was held; if it were ever the last reference, kvm_destroy_vm()
would run under kvm->lock, which would deadlock.

Fixes: 86956e70761b3 ("s390/vfio-ap: replace open coded locks for VFIO_GROUP_NOTIFY_SET_KVM notification")
Cc: stable@vger.kernel.org
Co-developed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Anthony Krowiak <akrowiak@linux.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Message-ID: <20260806173435.105044-1-akrowiak@linux.ibm.com>

diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 44b3a1dcc1b3..99a0efd999ef 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -48,15 +48,19 @@ static void vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q);
  * 1. matrix_dev->guests_lock: required to use the KVM pointer to update a KVM
  *			       guest's APCB.
  * 2. kvm->lock:	       required to update a guest's APCB
- * 3. matrix_dev->mdevs_lock:  required to access data stored in a matrix_mdev
+ * 3. kvm->arch.crypto.pqap_hook_rwsem: required to update pqap_hook and
+ *					serialize against PQAP intercepts
+ * 4. matrix_dev->mdevs_lock:  required to access data stored in a matrix_mdev
  *
- * Note: If @kvm is NULL, the KVM lock will not be taken.
+ * Note: If @kvm is NULL, the KVM lock and pqap_hook_rwsem will not be taken.
  */
 static inline void get_update_locks_for_kvm(struct kvm *kvm)
 {
 	mutex_lock(&matrix_dev->guests_lock);
-	if (kvm)
+	if (kvm) {
 		mutex_lock(&kvm->lock);
+		down_write(&kvm->arch.crypto.pqap_hook_rwsem);
+	}
 	mutex_lock(&matrix_dev->mdevs_lock);
 }
 
@@ -68,16 +72,19 @@ static inline void get_update_locks_for_kvm(struct kvm *kvm)
  *
  * The proper unlocking order is:
  * 1. matrix_dev->mdevs_lock
- * 2. kvm->lock
- * 3. matrix_dev->guests_lock
+ * 2. kvm->arch.crypto.pqap_hook_rwsem
+ * 3. kvm->lock
+ * 4. matrix_dev->guests_lock
  *
- * Note: If @kvm is NULL, the KVM lock will not be released.
+ * Note: If @kvm is NULL, the KVM lock and pqap_hook_rwsem will not be released.
  */
 static inline void release_update_locks_for_kvm(struct kvm *kvm)
 {
 	mutex_unlock(&matrix_dev->mdevs_lock);
-	if (kvm)
+	if (kvm) {
+		up_write(&kvm->arch.crypto.pqap_hook_rwsem);
 		mutex_unlock(&kvm->lock);
+	}
 	mutex_unlock(&matrix_dev->guests_lock);
 }
 
@@ -1821,26 +1828,17 @@ static const struct attribute_group *vfio_ap_mdev_attr_groups[] = {
 static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev,
 				struct kvm *kvm)
 {
-	struct ap_matrix_mdev *m;
-
 	if (kvm->arch.crypto.crycbd) {
-		down_write(&kvm->arch.crypto.pqap_hook_rwsem);
-		kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook;
-		up_write(&kvm->arch.crypto.pqap_hook_rwsem);
-
 		get_update_locks_for_kvm(kvm);
-
-		list_for_each_entry(m, &matrix_dev->mdev_list, node) {
-			if (m != matrix_mdev && m->kvm == kvm) {
-				release_update_locks_for_kvm(kvm);
-				return -EPERM;
-			}
+		if (kvm->arch.crypto.pqap_hook) {
+			release_update_locks_for_kvm(kvm);
+			return -EPERM;
 		}
+		kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook;
 
 		kvm_get_kvm(kvm);
 		matrix_mdev->kvm = kvm;
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
-
 		release_update_locks_for_kvm(kvm);
 	}
 
@@ -1883,18 +1881,15 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev)
 	struct kvm *kvm = matrix_mdev->kvm;
 
 	if (kvm && kvm->arch.crypto.crycbd) {
-		down_write(&kvm->arch.crypto.pqap_hook_rwsem);
-		kvm->arch.crypto.pqap_hook = NULL;
-		up_write(&kvm->arch.crypto.pqap_hook_rwsem);
-
 		get_update_locks_for_kvm(kvm);
+		kvm->arch.crypto.pqap_hook = NULL;
 
 		kvm_arch_crypto_clear_masks(kvm);
 		vfio_ap_mdev_reset_queues(matrix_mdev);
-		kvm_put_kvm(kvm);
 		matrix_mdev->kvm = NULL;
 
 		release_update_locks_for_kvm(kvm);
+		kvm_put_kvm(kvm);
 	}
 }
 

[PATCH 6.1.y 1/2] s390/vfio-ap: wait for response code 05 to clear on queue reset

[Sasha Levin]

From: Tony Krowiak <akrowiak@linux.ibm.com>

[ Upstream commit 411b0109daa52d1cc5be39635631e22a5590c5d8 ]

Response code 05, AP busy, is a valid response code for a ZAPQ or TAPQ.
Instead of returning error -EIO when a ZAPQ fails with response code 05,
let's wait until the queue is no longer busy and try the ZAPQ again.

Signed-off-by: Tony Krowiak <akrowiak@linux.ibm.com>
Acked-by: Janosch Frank <frankja@linux.ibm.com>
Tested-by: Viktor Mihajlovski <mihajlov@linux.ibm.com>
Link: https://lore.kernel.org/r/20230815184333.6554-4-akrowiak@linux.ibm.com
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>

[Backport to 6.1: keep the existing bounded queue-reset implementation
and handle AP_RESPONSE_BUSY through its reset-in-progress retry path.
Drop the apq_status_check() hunk because that helper is absent here; do
not introduce the newer reset helpers or their prerequisite refactors.

Prepare for 4400270ec034 ("s390/vfio-ap: fix stale pqap_hook pointer on
error in vfio_ap_mdev_set_kvm()") by changing the existing
vfio_ap_mdev_reset_queues() argument from a queue table to its matrix
mdev. Keep the same table traversal and error propagation. The adapter
and domain hot-unplug paths reset their detached queue tables directly
with the existing single-queue helper before unlinking, preserving the
reset order, retry count, and ignored aggregate return value. No new
functions are introduced.]

Stable-dep-of: 4400270ec034 ("s390/vfio-ap: fix stale pqap_hook pointer on error in vfio_ap_mdev_set_kvm()")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/s390/crypto/vfio_ap_ops.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 11fe917fbd9d4..5016c157a3010 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -30,7 +30,7 @@
 #define AP_QUEUE_UNASSIGNED "unassigned"
 #define AP_QUEUE_IN_USE "in use"
 
-static int vfio_ap_mdev_reset_queues(struct ap_queue_table *qtable);
+static int vfio_ap_mdev_reset_queues(struct ap_matrix_mdev *matrix_mdev);
 static struct vfio_ap_queue *vfio_ap_find_queue(int apqn);
 static const struct vfio_device_ops vfio_ap_matrix_dev_ops;
 static int vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q, unsigned int retry);
@@ -781,7 +781,7 @@ static void vfio_ap_mdev_remove(struct mdev_device *mdev)
 
 	mutex_lock(&matrix_dev->guests_lock);
 	mutex_lock(&matrix_dev->mdevs_lock);
-	vfio_ap_mdev_reset_queues(&matrix_mdev->qtable);
+	vfio_ap_mdev_reset_queues(matrix_mdev);
 	vfio_ap_mdev_unlink_fr_queues(matrix_mdev);
 	list_del(&matrix_mdev->node);
 	mutex_unlock(&matrix_dev->mdevs_lock);
@@ -1048,7 +1048,8 @@ static void vfio_ap_mdev_hot_unplug_adapter(struct ap_matrix_mdev *matrix_mdev,
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
 	}
 
-	vfio_ap_mdev_reset_queues(qtable);
+	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode)
+		vfio_ap_mdev_reset_queue(q, 1);
 
 	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) {
 		vfio_ap_unlink_mdev_fr_queue(q);
@@ -1231,7 +1232,8 @@ static void vfio_ap_mdev_hot_unplug_domain(struct ap_matrix_mdev *matrix_mdev,
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
 	}
 
-	vfio_ap_mdev_reset_queues(qtable);
+	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode)
+		vfio_ap_mdev_reset_queue(q, 1);
 
 	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) {
 		vfio_ap_unlink_mdev_fr_queue(q);
@@ -1577,7 +1579,7 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev)
 		get_update_locks_for_kvm(kvm);
 
 		kvm_arch_crypto_clear_masks(kvm);
-		vfio_ap_mdev_reset_queues(&matrix_mdev->qtable);
+		vfio_ap_mdev_reset_queues(matrix_mdev);
 		kvm_put_kvm(kvm);
 		matrix_mdev->kvm = NULL;
 
@@ -1619,6 +1621,7 @@ static int vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q,
 		ret = 0;
 		break;
 	case AP_RESPONSE_RESET_IN_PROGRESS:
+	case AP_RESPONSE_BUSY:
 		if (retry--) {
 			msleep(20);
 			goto retry_zapq;
@@ -1659,8 +1662,9 @@ static int vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q,
 	return ret;
 }
 
-static int vfio_ap_mdev_reset_queues(struct ap_queue_table *qtable)
+static int vfio_ap_mdev_reset_queues(struct ap_matrix_mdev *matrix_mdev)
 {
+	struct ap_queue_table *qtable = &matrix_mdev->qtable;
 	int ret, loop_cursor, rc = 0;
 	struct vfio_ap_queue *q;
 
@@ -1730,7 +1734,7 @@ static ssize_t vfio_ap_mdev_ioctl(struct vfio_device *vdev,
 		ret = vfio_ap_mdev_get_device_info(arg);
 		break;
 	case VFIO_DEVICE_RESET:
-		ret = vfio_ap_mdev_reset_queues(&matrix_mdev->qtable);
+		ret = vfio_ap_mdev_reset_queues(matrix_mdev);
 		break;
 	default:
 		ret = -EOPNOTSUPP;
-- 
2.53.0

[PATCH 6.1.y 2/2] s390/vfio-ap: fix stale pqap_hook pointer on error in vfio_ap_mdev_set_kvm()

[Sasha Levin]

From: Anthony Krowiak <akrowiak@linux.ibm.com>

[ Upstream commit 4400270ec0348d05dc0439d8f0130853ce7f9e20 ]

In vfio_ap_mdev_set_kvm(), kvm->arch.crypto.pqap_hook is set to
&matrix_mdev->pqap_hook before the update locks are acquired and the
mdev list is checked for a conflicting assignment. If another mdev is
already attached to the same KVM instance, the function returns -EPERM
without restoring the hook pointer, leaving kvm->arch.crypto.pqap_hook
pointing at the failing matrix_mdev instead of the mdev that legitimately
owns the KVM.

Since matrix_mdev->kvm is never set on this error path,
vfio_ap_mdev_unset_kvm() will not clean up the hook when matrix_mdev
is later closed. If matrix_mdev is subsequently freed, any PQAP
instruction executed by the guest will dereference the stale pointer
through pqap_hook_rwsem, resulting in a use-after-free.

Since kvm->arch.crypto.pqap_hook is only set in the vfio_ap_mdev_set_kvm()
function and is cleared in the vfio_ap_mdev_unset_kvm() function, a check
for 'kvm->arch.crypto.pqap_hook != NULL' is all that is needed to determine
whether it belongs to another mdev. This will alleviate the need to iterate
the matrix_dev->mdev_list list to see if the kvm object is assigned to
another mdev.This was introduced in v3 to alleviate the need to take the
mdevs_lock while iterating the list; however, this did not prevent a
potential race condition.

The pqap_hook_rwsem(write) is now performed inside
get_update_locks_for_kvm(), which is updated to acquire
pqap_hook_rwsem(write) between kvm->lock and mdevs_lock. This ordering
is consistent with the PQAP intercept path, which acquires pqap_hook_rwsem
in read mode while srcu is held under vcpu->mutex, establishing the
dependency: kvm->lock -> vcpu->mutex -> srcu -> pqap_hook_rwsem(read).

The pqap_hook_rwsem is now released inside the
release_update_locks_for_kvm(), which is updated to release
pqap_hook_rwsem(write) between mdevs_lock and kvm->lock.

Additionally, kvm_put_kvm() in vfio_ap_mdev_unset_kvm() is moved
after release_update_locks_for_kvm(). Previously it was called while
kvm->lock was held; if it were ever the last reference, kvm_destroy_vm()
would run under kvm->lock, which would deadlock.

Fixes: 86956e70761b3 ("s390/vfio-ap: replace open coded locks for VFIO_GROUP_NOTIFY_SET_KVM notification")
Cc: stable@vger.kernel.org
Co-developed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Anthony Krowiak <akrowiak@linux.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Message-ID: <20260806173435.105044-1-akrowiak@linux.ibm.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/s390/crypto/vfio_ap_ops.c | 45 ++++++++++++++-----------------
 1 file changed, 20 insertions(+), 25 deletions(-)

diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 5016c157a3010..93464f9034e23 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -45,15 +45,19 @@ static int vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q, unsigned int retry)
  * 1. matrix_dev->guests_lock: required to use the KVM pointer to update a KVM
  *			       guest's APCB.
  * 2. kvm->lock:	       required to update a guest's APCB
- * 3. matrix_dev->mdevs_lock:  required to access data stored in a matrix_mdev
+ * 3. kvm->arch.crypto.pqap_hook_rwsem: required to update pqap_hook and
+ *					serialize against PQAP intercepts
+ * 4. matrix_dev->mdevs_lock:  required to access data stored in a matrix_mdev
  *
- * Note: If @kvm is NULL, the KVM lock will not be taken.
+ * Note: If @kvm is NULL, the KVM lock and pqap_hook_rwsem will not be taken.
  */
 static inline void get_update_locks_for_kvm(struct kvm *kvm)
 {
 	mutex_lock(&matrix_dev->guests_lock);
-	if (kvm)
+	if (kvm) {
 		mutex_lock(&kvm->lock);
+		down_write(&kvm->arch.crypto.pqap_hook_rwsem);
+	}
 	mutex_lock(&matrix_dev->mdevs_lock);
 }
 
@@ -65,16 +69,19 @@ static inline void get_update_locks_for_kvm(struct kvm *kvm)
  *
  * The proper unlocking order is:
  * 1. matrix_dev->mdevs_lock
- * 2. kvm->lock
- * 3. matrix_dev->guests_lock
+ * 2. kvm->arch.crypto.pqap_hook_rwsem
+ * 3. kvm->lock
+ * 4. matrix_dev->guests_lock
  *
- * Note: If @kvm is NULL, the KVM lock will not be released.
+ * Note: If @kvm is NULL, the KVM lock and pqap_hook_rwsem will not be released.
  */
 static inline void release_update_locks_for_kvm(struct kvm *kvm)
 {
 	mutex_unlock(&matrix_dev->mdevs_lock);
-	if (kvm)
+	if (kvm) {
+		up_write(&kvm->arch.crypto.pqap_hook_rwsem);
 		mutex_unlock(&kvm->lock);
+	}
 	mutex_unlock(&matrix_dev->guests_lock);
 }
 
@@ -1526,26 +1533,17 @@ static const struct attribute_group *vfio_ap_mdev_attr_groups[] = {
 static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev,
 				struct kvm *kvm)
 {
-	struct ap_matrix_mdev *m;
-
 	if (kvm->arch.crypto.crycbd) {
-		down_write(&kvm->arch.crypto.pqap_hook_rwsem);
-		kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook;
-		up_write(&kvm->arch.crypto.pqap_hook_rwsem);
-
 		get_update_locks_for_kvm(kvm);
-
-		list_for_each_entry(m, &matrix_dev->mdev_list, node) {
-			if (m != matrix_mdev && m->kvm == kvm) {
-				release_update_locks_for_kvm(kvm);
-				return -EPERM;
-			}
+		if (kvm->arch.crypto.pqap_hook) {
+			release_update_locks_for_kvm(kvm);
+			return -EPERM;
 		}
+		kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook;
 
 		kvm_get_kvm(kvm);
 		matrix_mdev->kvm = kvm;
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
-
 		release_update_locks_for_kvm(kvm);
 	}
 
@@ -1572,18 +1570,15 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev)
 	struct kvm *kvm = matrix_mdev->kvm;
 
 	if (kvm && kvm->arch.crypto.crycbd) {
-		down_write(&kvm->arch.crypto.pqap_hook_rwsem);
-		kvm->arch.crypto.pqap_hook = NULL;
-		up_write(&kvm->arch.crypto.pqap_hook_rwsem);
-
 		get_update_locks_for_kvm(kvm);
+		kvm->arch.crypto.pqap_hook = NULL;
 
 		kvm_arch_crypto_clear_masks(kvm);
 		vfio_ap_mdev_reset_queues(matrix_mdev);
-		kvm_put_kvm(kvm);
 		matrix_mdev->kvm = NULL;
 
 		release_update_locks_for_kvm(kvm);
+		kvm_put_kvm(kvm);
 	}
 }
 
-- 
2.53.0