The vfio_ap device driver registers a group notifier with VFIO when the file descriptor for a VFIO mediated device attached to a KVM guest is opened. The group notifier is registered to receive notification that the KVM pointer for the guest is set (VFIO_GROUP_NOTIFY_SET_KVM event). When the KVM pointer is set to a non-NULL value, the vfio_ap driver takes the following actions: 1. Stashes the KVM pointer in the vfio_ap_mdev struct that holds the state of the mediated device. 2. Calls the kvm_get_kvm() function to increment its reference counter. 3. Sets the function pointer to the function that handles interception of the instruction that enables/disables interrupt processing for the KVM guest. 4. Plugs the AP devices assigned to the mediated device into the KVM guest.
These actions are reversed by the release callback which is invoked when userspace closes the mediated device's file descriptor. In this case, the group notifier does not get called to invalidate the KVM pointer because the notifier is unregistered by the release callback; however, there are no guarantees that userspace will do the right thing before shutting down. To ensure that there are no resource leaks should the group notifier get called to set the KVM pointer to NULL, the notifier should also reverse the actions taken when it was called to set the pointer. This patch series ensures proper clean up is done via the group notifier.
Tony Krowiak (2): s390/vfio-ap: No need to disable IRQ after queue reset s390/vfio-ap: reverse group notifier actions when KVM pointer invalidated
drivers/s390/crypto/vfio_ap_drv.c | 1 - drivers/s390/crypto/vfio_ap_ops.c | 80 +++++++++++++++++---------- drivers/s390/crypto/vfio_ap_private.h | 1 - 3 files changed, 50 insertions(+), 32 deletions(-)
The queues assigned to a matrix mediated device are currently reset when:
* The VFIO_DEVICE_RESET ioctl is invoked * The mdev fd is closed by userspace (QEMU) * The mdev is removed from sysfs.
Immediately after the reset of a queue, a call is made to disable interrupts for the queue. This is entirely unnecessary because the reset of a queue disables interrupts, so this will be removed.
Signed-off-by: Tony Krowiak akrowiak@linux.ibm.com --- drivers/s390/crypto/vfio_ap_drv.c | 1 - drivers/s390/crypto/vfio_ap_ops.c | 40 +++++++++++++++++---------- drivers/s390/crypto/vfio_ap_private.h | 1 - 3 files changed, 26 insertions(+), 16 deletions(-)
diff --git a/drivers/s390/crypto/vfio_ap_drv.c b/drivers/s390/crypto/vfio_ap_drv.c index be2520cc010b..ca18c91afec9 100644 --- a/drivers/s390/crypto/vfio_ap_drv.c +++ b/drivers/s390/crypto/vfio_ap_drv.c @@ -79,7 +79,6 @@ static void vfio_ap_queue_dev_remove(struct ap_device *apdev) apid = AP_QID_CARD(q->apqn); apqi = AP_QID_QUEUE(q->apqn); vfio_ap_mdev_reset_queue(apid, apqi, 1); - vfio_ap_irq_disable(q); kfree(q); mutex_unlock(&matrix_dev->lock); } diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index e0bde8518745..c854d7ab2079 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -25,6 +25,7 @@ #define VFIO_AP_MDEV_NAME_HWVIRT "VFIO AP Passthrough Device"
static int vfio_ap_mdev_reset_queues(struct mdev_device *mdev); +static struct vfio_ap_queue *vfio_ap_find_queue(int apqn);
static int match_apqn(struct device *dev, const void *data) { @@ -49,20 +50,15 @@ static struct vfio_ap_queue *vfio_ap_get_queue( int apqn) { struct vfio_ap_queue *q; - struct device *dev;
if (!test_bit_inv(AP_QID_CARD(apqn), matrix_mdev->matrix.apm)) return NULL; if (!test_bit_inv(AP_QID_QUEUE(apqn), matrix_mdev->matrix.aqm)) return NULL;
- dev = driver_find_device(&matrix_dev->vfio_ap_drv->driver, NULL, - &apqn, match_apqn); - if (!dev) - return NULL; - q = dev_get_drvdata(dev); - q->matrix_mdev = matrix_mdev; - put_device(dev); + q = vfio_ap_find_queue(apqn); + if (q) + q->matrix_mdev = matrix_mdev;
return q; } @@ -1114,24 +1110,27 @@ static int vfio_ap_mdev_group_notifier(struct notifier_block *nb, return NOTIFY_OK; }
-static void vfio_ap_irq_disable_apqn(int apqn) +static struct vfio_ap_queue *vfio_ap_find_queue(int apqn) { struct device *dev; - struct vfio_ap_queue *q; + struct vfio_ap_queue *q = NULL;
dev = driver_find_device(&matrix_dev->vfio_ap_drv->driver, NULL, &apqn, match_apqn); if (dev) { q = dev_get_drvdata(dev); - vfio_ap_irq_disable(q); put_device(dev); } + + return q; }
int vfio_ap_mdev_reset_queue(unsigned int apid, unsigned int apqi, unsigned int retry) { struct ap_queue_status status; + struct vfio_ap_queue *q; + int ret; int retry2 = 2; int apqn = AP_MKQID(apid, apqi);
@@ -1144,18 +1143,32 @@ int vfio_ap_mdev_reset_queue(unsigned int apid, unsigned int apqi, status = ap_tapq(apqn, NULL); } WARN_ON_ONCE(retry2 <= 0); - return 0; + ret = 0; + goto free_aqic_resources; case AP_RESPONSE_RESET_IN_PROGRESS: case AP_RESPONSE_BUSY: msleep(20); break; default: /* things are really broken, give up */ - return -EIO; + ret = -EIO; + goto free_aqic_resources; } } while (retry--);
return -EBUSY; + +free_aqic_resources: + /* + * In order to free the aqic resources, the queue must be linked to + * the matrix_mdev to which its APQN is assigned and the KVM pointer + * must be available. + */ + q = vfio_ap_find_queue(apqn); + if (q && q->matrix_mdev && q->matrix_mdev->kvm) + vfio_ap_free_aqic_resources(q); + + return ret; }
static int vfio_ap_mdev_reset_queues(struct mdev_device *mdev) @@ -1177,7 +1190,6 @@ static int vfio_ap_mdev_reset_queues(struct mdev_device *mdev) */ if (ret) rc = ret; - vfio_ap_irq_disable_apqn(AP_MKQID(apid, apqi)); } }
diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h index f46dde56b464..0db6fb3d56d5 100644 --- a/drivers/s390/crypto/vfio_ap_private.h +++ b/drivers/s390/crypto/vfio_ap_private.h @@ -100,5 +100,4 @@ struct vfio_ap_queue { #define VFIO_AP_ISC_INVALID 0xff unsigned char saved_isc; }; -struct ap_queue_status vfio_ap_irq_disable(struct vfio_ap_queue *q); #endif /* _VFIO_AP_PRIVATE_H_ */
On Fri, Dec 11, 2020 at 05:22:10PM -0500, Tony Krowiak wrote:
The queues assigned to a matrix mediated device are currently reset when:
- The VFIO_DEVICE_RESET ioctl is invoked
- The mdev fd is closed by userspace (QEMU)
- The mdev is removed from sysfs.
Immediately after the reset of a queue, a call is made to disable interrupts for the queue. This is entirely unnecessary because the reset of a queue disables interrupts, so this will be removed.
Signed-off-by: Tony Krowiak akrowiak@linux.ibm.com
drivers/s390/crypto/vfio_ap_drv.c | 1 - drivers/s390/crypto/vfio_ap_ops.c | 40 +++++++++++++++++---------- drivers/s390/crypto/vfio_ap_private.h | 1 - 3 files changed, 26 insertions(+), 16 deletions(-)
<formletter>
This is not the correct way to submit patches for inclusion in the stable kernel tree. Please read: https://www.kernel.org/doc/html/latest/process/stable-kernel-rules.html for how to do this properly.
</formletter>
The vfio_ap device driver registers a group notifier with VFIO when the file descriptor for a VFIO mediated device for a KVM guest is opened to receive notification that the KVM pointer is set (VFIO_GROUP_NOTIFY_SET_KVM event). When the KVM pointer is set, the vfio_ap driver takes the following actions: 1. Stashes the KVM pointer in the vfio_ap_mdev struct that holds the state of the mediated device. 2. Calls the kvm_get_kvm() function to increment its reference counter. 3. Sets the function pointer to the function that handles interception of the instruction that enables/disables interrupt processing.
When the notifier is called to make notification that the KVM pointer has been set to NULL, the driver should reverse the actions taken when the KVM pointer was set as well as unplugging the AP devices passed through to the KVM guest.
Fixes: 258287c994de ("s390: vfio-ap: implement mediated device open callback") Signed-off-by: Tony Krowiak akrowiak@linux.ibm.com --- drivers/s390/crypto/vfio_ap_ops.c | 40 ++++++++++++++++++------------- 1 file changed, 24 insertions(+), 16 deletions(-)
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index c854d7ab2079..1c3c2a0898b9 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -1033,8 +1033,6 @@ static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev, { struct ap_matrix_mdev *m;
- mutex_lock(&matrix_dev->lock); - list_for_each_entry(m, &matrix_dev->mdev_list, node) { if ((m != matrix_mdev) && (m->kvm == kvm)) { mutex_unlock(&matrix_dev->lock); @@ -1045,7 +1043,6 @@ static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev, matrix_mdev->kvm = kvm; kvm_get_kvm(kvm); kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook; - mutex_unlock(&matrix_dev->lock);
return 0; } @@ -1079,35 +1076,49 @@ static int vfio_ap_mdev_iommu_notifier(struct notifier_block *nb, return NOTIFY_DONE; }
+static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) +{ + kvm_arch_crypto_clear_masks(matrix_mdev->kvm); + matrix_mdev->kvm->arch.crypto.pqap_hook = NULL; + vfio_ap_mdev_reset_queues(matrix_mdev->mdev); + kvm_put_kvm(matrix_mdev->kvm); + matrix_mdev->kvm = NULL; +} + static int vfio_ap_mdev_group_notifier(struct notifier_block *nb, unsigned long action, void *data) { - int ret; + int ret, notify_rc = NOTIFY_DONE; struct ap_matrix_mdev *matrix_mdev;
if (action != VFIO_GROUP_NOTIFY_SET_KVM) return NOTIFY_OK;
matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier); + mutex_lock(&matrix_dev->lock);
if (!data) { - matrix_mdev->kvm = NULL; - return NOTIFY_OK; + if (matrix_mdev->kvm) + vfio_ap_mdev_unset_kvm(matrix_mdev); + notify_rc = NOTIFY_OK; + goto notify_done; }
ret = vfio_ap_mdev_set_kvm(matrix_mdev, data); if (ret) - return NOTIFY_DONE; + goto notify_done;
/* If there is no CRYCB pointer, then we can't copy the masks */ if (!matrix_mdev->kvm->arch.crypto.crycbd) - return NOTIFY_DONE; + goto notify_done;
kvm_arch_crypto_set_masks(matrix_mdev->kvm, matrix_mdev->matrix.apm, matrix_mdev->matrix.aqm, matrix_mdev->matrix.adm);
- return NOTIFY_OK; +notify_done: + mutex_unlock(&matrix_dev->lock); + return notify_rc; }
static struct vfio_ap_queue *vfio_ap_find_queue(int apqn) @@ -1234,13 +1245,10 @@ static void vfio_ap_mdev_release(struct mdev_device *mdev) struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
mutex_lock(&matrix_dev->lock); - if (matrix_mdev->kvm) { - kvm_arch_crypto_clear_masks(matrix_mdev->kvm); - matrix_mdev->kvm->arch.crypto.pqap_hook = NULL; - vfio_ap_mdev_reset_queues(mdev); - kvm_put_kvm(matrix_mdev->kvm); - matrix_mdev->kvm = NULL; - } + if (matrix_mdev->kvm) + vfio_ap_mdev_unset_kvm(matrix_mdev); + else + vfio_ap_mdev_reset_queues(matrix_mdev->mdev); mutex_unlock(&matrix_dev->lock);
vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
On Fri, Dec 11, 2020 at 05:22:11PM -0500, Tony Krowiak wrote:
The vfio_ap device driver registers a group notifier with VFIO when the file descriptor for a VFIO mediated device for a KVM guest is opened to receive notification that the KVM pointer is set (VFIO_GROUP_NOTIFY_SET_KVM event). When the KVM pointer is set, the vfio_ap driver takes the following actions:
- Stashes the KVM pointer in the vfio_ap_mdev struct that holds the state of the mediated device.
- Calls the kvm_get_kvm() function to increment its reference counter.
- Sets the function pointer to the function that handles interception of the instruction that enables/disables interrupt processing.
When the notifier is called to make notification that the KVM pointer has been set to NULL, the driver should reverse the actions taken when the KVM pointer was set as well as unplugging the AP devices passed through to the KVM guest.
Fixes: 258287c994de ("s390: vfio-ap: implement mediated device open callback") Signed-off-by: Tony Krowiak akrowiak@linux.ibm.com
drivers/s390/crypto/vfio_ap_ops.c | 40 ++++++++++++++++++------------- 1 file changed, 24 insertions(+), 16 deletions(-)
<formletter>
This is not the correct way to submit patches for inclusion in the stable kernel tree. Please read: https://www.kernel.org/doc/html/latest/process/stable-kernel-rules.html for how to do this properly.
</formletter>
linux-stable-mirror@lists.linaro.org
-
Greg KH -
Tony Krowiak