On 2/14/19 8:51 AM, Pierre Morel wrote:
When the device is remove, we must make sure to
clear the interruption and reset the AP device.
We also need to clear the CRYCB of the guest.
Signed-off-by: Pierre Morel <pmorel@xxxxxxxxxxxxx>
---
drivers/s390/crypto/vfio_ap_drv.c | 92 +++++++++++++++++++++++++++++++++++
drivers/s390/crypto/vfio_ap_ops.c | 2 +-
drivers/s390/crypto/vfio_ap_private.h | 2 +
3 files changed, 95 insertions(+), 1 deletion(-)
diff --git a/drivers/s390/crypto/vfio_ap_drv.c b/drivers/s390/crypto/vfio_ap_drv.c
index 03153e6..50428be 100644
--- a/drivers/s390/crypto/vfio_ap_drv.c
+++ b/drivers/s390/crypto/vfio_ap_drv.c
@@ -5,6 +5,7 @@
* Copyright IBM Corp. 2018
*
* Author(s): Tony Krowiak <akrowiak@xxxxxxxxxxxxx>
+ * Pierre Morel <pmorel@xxxxxxxxxxxxx>
*/
#include <linux/module.h>
@@ -12,6 +13,8 @@
#include <linux/slab.h>
#include <linux/string.h>
#include <asm/facility.h>
+#include <linux/bitops.h>
+#include <linux/kvm_host.h>
#include "vfio_ap_private.h"
#define VFIO_AP_ROOT_NAME "vfio_ap"
@@ -64,6 +67,88 @@ static int vfio_ap_queue_dev_probe(struct ap_device *apdev)
return 0;
}
+/*
+ * vfio_ap_drain_queue
+ * @q: the queue to drain
+ *
+ * This function waits until the queue is empty.
+ */
+static void vfio_ap_drain_queue(struct vfio_ap_queue *q)
+{
+ struct ap_queue_status status;
+ int retry = 20;
+
+ status = ap_tapq(q->apqn, NULL);
+ while (!status.queue_empty && retry--) {
+ msleep(200);
+ status = ap_tapq(q->apqn, NULL);
+ }
+ if (retry <= 0) {
+ pr_warn("%s: queue not empty after zapq on apqn 0x%04x\n",
+ __func__, q->apqn);
+ }
+}
+
+/*
+ * vfio_ap_zapq
+ * @q: The queue to zerro
+ *
+ * It is best effort, no return value is done, however on success
+ * we will drain the queue before getting the queue back to the
+ * AP bus.
+ */
+static void vfio_ap_zapq(struct vfio_ap_queue *q)
+{
+ struct ap_queue_status status;
+ int retry = 20;
+
+ do {
+ status = ap_zapq(q->apqn);
+ switch (status.response_code) {
+ case AP_RESPONSE_RESET_IN_PROGRESS:
+ case AP_RESPONSE_BUSY:
+ msleep(20);
+ break;
+ default:
+ pr_warn("%s: zapq error %02x on apqn 0x%04x\n",
+ __func__, status.response_code, q->apqn);
+ return;
+ case AP_RESPONSE_NORMAL:
+ vfio_ap_drain_queue(q);
+ return;
+ }
+ } while (retry--);
+ pr_warn("%s: zapq retry count exceeded code %02x on apqn 0x%04x\n",
+ __func__, status.response_code, q->apqn);
+}
+
+/**
+ * vfio_ap_update_crycb
+ * @q: A pointer to the queue being removed
+ *
+ * We clear the APID of the queue, making this queue unusable for the guest.
+ * After this function we can reset the queue without to fear a race with
+ * the guest to access the queue again.
+ * We do not fear race with the host as we still get the device.
+ */
+static void vfio_ap_update_crycb(struct vfio_ap_queue *q)
+{
+ struct ap_matrix_mdev *matrix_mdev = q->matrix;
+
+ if (!matrix_mdev)
+ return;
+
+ clear_bit_inv(AP_QID_CARD(q->apqn), matrix_mdev->matrix.apm);
+
+ if (!matrix_mdev->kvm)
+ return;
+
+ kvm_arch_crypto_set_masks(matrix_mdev->kvm,
+ matrix_mdev->matrix.apm,
+ matrix_mdev->matrix.aqm,
+ matrix_mdev->matrix.adm);
+}
+
/**
* vfio_ap_queue_dev_remove:
*
@@ -74,6 +159,13 @@ static void vfio_ap_queue_dev_remove(struct ap_device *apdev)
struct vfio_ap_queue *q;
q = dev_get_drvdata(&apdev->device);
+ if (!q)
+ return;
+
+ vfio_ap_update_crycb(q);
The root user is warned in the Limitations section of the vfio-ap.txt
doc delivered with the AP pass-through support warns that the
administrator (i.e., root user) should ensure that AP devices are not
removed without taking proper care to ensure they are not in use by a
guest. I am currently working on a patch set to handle this, so this
may simply get ripped out when those patches are integrated. That may
very well be simultaneously with this patch series as I plan on posting
those soon.
If this call is to remain, then you ought to update the vfio-ap.txt
document to let users know that when queues are unbound, the guests
will lose access to them unbeknown to the admin of the guest.
+ vfio_ap_zapq(q);
One last thing. I've explained before that prior to the AP bus
invoking this remove callback, it flushes and zeroizes the
queue. Why do you insist it needs to be done again in the remove
callback?
+
+ vfio_ap_free_irq(q);
kfree(q);
}
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 5664cf3..7ec957c 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -85,7 +85,7 @@ static void vfio_ap_put_queue(struct vfio_ap_queue *q)
* Unregister the ISC from the GIB alert
* Clear the vfio_ap_queue intern fields
*/
-static void vfio_ap_free_irq(struct vfio_ap_queue *q)
+void vfio_ap_free_irq(struct vfio_ap_queue *q)
{
unsigned long pfn = q->nib >> PAGE_SHIFT;
diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h
index 16c99e9..d108c6d 100644
--- a/drivers/s390/crypto/vfio_ap_private.h
+++ b/drivers/s390/crypto/vfio_ap_private.h
@@ -4,6 +4,7 @@
*
* Author(s): Tony Krowiak <akrowiak@xxxxxxxxxxxxx>
* Halil Pasic <pasic@xxxxxxxxxxxxx>
+ * Pierre Morel <pmorel@xxxxxxxxxxxxx>
*
* Copyright IBM Corp. 2018
*/
@@ -95,4 +96,5 @@ struct vfio_ap_queue {
unsigned long nib;
unsigned char isc;
};
+void vfio_ap_free_irq(struct vfio_ap_queue *q);
#endif /* _VFIO_AP_PRIVATE_H_ */
