#define VFIO_AP_MDEV_TYPE_HWVIRT "passthrough"
#define VFIO_AP_MDEV_NAME_HWVIRT "VFIO AP Passthrough Device"
+static int vfio_ap_mdev_reset_queues(struct mdev_device *mdev);
+
+static int match_apqn(struct device *dev, const void *data)
+{
+ struct vfio_ap_queue *q = dev_get_drvdata(dev);
+
+ return (q->apqn == *(int *)(data)) ? 1 : 0;
+}
+
+/**
+ * vfio_ap_get_queue: Retrieve a queue with a specific APQN from a list
+ * @matrix_mdev: the associated mediated matrix
+ * @apqn: The queue APQN
+ *
+ * Retrieve a queue with a specific APQN from the list of the
+ * devices of the vfio_ap_drv.
+ * Verify that the APID and the APQI are set in the matrix.
+ *
+ * Returns the pointer to the associated vfio_ap_queue
+ */
+static struct vfio_ap_queue *vfio_ap_get_queue(
+ struct ap_matrix_mdev *matrix_mdev,
+ 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);
+
+ return q;
+}
+
+/**
+ * vfio_ap_wait_for_irqclear
+ * @apqn: The AP Queue number
+ *
+ * Checks the IRQ bit for the status of this APQN using ap_tapq.
+ * Returns if the ap_tapq function succeeded and the bit is clear.
+ * Returns if ap_tapq function failed with invalid, deconfigured or
+ * checkstopped AP.
+ * Otherwise retries up to 5 times after waiting 20ms.
+ *
+ */
+static void vfio_ap_wait_for_irqclear(int apqn)
+{
+ struct ap_queue_status status;
+ int retry = 5;
+
+ do {
+ status = ap_tapq(apqn, NULL);
+ switch (status.response_code) {
+ case AP_RESPONSE_NORMAL:
+ case AP_RESPONSE_RESET_IN_PROGRESS:
+ if (!status.irq_enabled)
+ return;
+ /* Fall through */
+ case AP_RESPONSE_BUSY:
+ msleep(20);
+ break;
+ case AP_RESPONSE_Q_NOT_AVAIL:
+ case AP_RESPONSE_DECONFIGURED:
+ case AP_RESPONSE_CHECKSTOPPED:
+ default:
+ WARN_ONCE(1, "%s: tapq rc %02x: %04x\n", __func__,
+ status.response_code, apqn);
+ return;
+ }
+ } while (--retry);
+
+ WARN_ONCE(1, "%s: tapq rc %02x: %04x could not clear IR bit\n",
+ __func__, status.response_code, apqn);
+}
+
+/**
+ * vfio_ap_free_aqic_resources
+ * @q: The vfio_ap_queue
+ *
+ * Unregisters the ISC in the GIB when the saved ISC not invalid.
+ * Unpin the guest's page holding the NIB when it exist.
+ * Reset the saved_pfn and saved_isc to invalid values.
+ * Clear the pointer to the matrix mediated device.
+ *
+ */
+static void vfio_ap_free_aqic_resources(struct vfio_ap_queue *q)
+{
+ if (q->saved_isc != VFIO_AP_ISC_INVALID && q->matrix_mdev)
+ kvm_s390_gisc_unregister(q->matrix_mdev->kvm, q->saved_isc);
+ if (q->saved_pfn && q->matrix_mdev)
+ vfio_unpin_pages(mdev_dev(q->matrix_mdev->mdev),
+ &q->saved_pfn, 1);
+ q->saved_pfn = 0;
+ q->saved_isc = VFIO_AP_ISC_INVALID;
+ q->matrix_mdev = NULL;
+}
+
+/**
+ * vfio_ap_irq_disable
+ * @q: The vfio_ap_queue
+ *
+ * Uses ap_aqic to disable the interruption and in case of success, reset
+ * in progress or IRQ disable command already proceeded: calls
+ * vfio_ap_wait_for_irqclear() to check for the IRQ bit to be clear
+ * and calls vfio_ap_free_aqic_resources() to free the resources associated
+ * with the AP interrupt handling.
+ *
+ * In the case the AP is busy, or a reset is in progress,
+ * retries after 20ms, up to 5 times.
+ *
+ * Returns if ap_aqic function failed with invalid, deconfigured or
+ * checkstopped AP.
+ */
+struct ap_queue_status vfio_ap_irq_disable(struct vfio_ap_queue *q)
+{
+ struct ap_qirq_ctrl aqic_gisa = {};
+ struct ap_queue_status status;
+ int retries = 5;
+
+ do {
+ status = ap_aqic(q->apqn, aqic_gisa, NULL);
+ switch (status.response_code) {
+ case AP_RESPONSE_OTHERWISE_CHANGED:
+ case AP_RESPONSE_NORMAL:
+ vfio_ap_wait_for_irqclear(q->apqn);
+ goto end_free;
+ case AP_RESPONSE_RESET_IN_PROGRESS:
+ case AP_RESPONSE_BUSY:
+ msleep(20);
+ break;
+ case AP_RESPONSE_Q_NOT_AVAIL:
+ case AP_RESPONSE_DECONFIGURED:
+ case AP_RESPONSE_CHECKSTOPPED:
+ case AP_RESPONSE_INVALID_ADDRESS:
+ default:
+ /* All cases in default means AP not operational */
+ WARN_ONCE(1, "%s: ap_aqic status %d\n", __func__,
+ status.response_code);
+ goto end_free;
+ }
+ } while (retries--);
+
+ WARN_ONCE(1, "%s: ap_aqic status %d\n", __func__,
+ status.response_code);
+end_free:
+ vfio_ap_free_aqic_resources(q);
+ return status;
+}
+
+/**
+ * vfio_ap_setirq: Enable Interruption for a APQN
+ *
+ * @dev: the device associated with the ap_queue
+ * @q: the vfio_ap_queue holding AQIC parameters
+ *
+ * Pin the NIB saved in *q
+ * Register the guest ISC to GIB interface and retrieve the
+ * host ISC to issue the host side PQAP/AQIC
+ *
+ * Response.status may be set to AP_RESPONSE_INVALID_ADDRESS in case the
+ * vfio_pin_pages failed.
+ *
+ * Otherwise return the ap_queue_status returned by the ap_aqic(),
+ * all retry handling will be done by the guest.
+ */
+static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q,
+ int isc,
+ unsigned long nib)
+{
+ struct ap_qirq_ctrl aqic_gisa = {};
+ struct ap_queue_status status = {};
+ struct kvm_s390_gisa *gisa;
+ struct kvm *kvm;
+ unsigned long h_nib, g_pfn, h_pfn;
+ int ret;
+
+ g_pfn = nib >> PAGE_SHIFT;
+ ret = vfio_pin_pages(mdev_dev(q->matrix_mdev->mdev), &g_pfn, 1,
+ IOMMU_READ | IOMMU_WRITE, &h_pfn);
+ switch (ret) {
+ case 1:
+ break;
+ default:
+ status.response_code = AP_RESPONSE_INVALID_ADDRESS;
+ return status;
+ }
+
+ kvm = q->matrix_mdev->kvm;
+ gisa = kvm->arch.gisa_int.origin;
+
+ h_nib = (h_pfn << PAGE_SHIFT) | (nib & ~PAGE_MASK);
+ aqic_gisa.gisc = isc;
+ aqic_gisa.isc = kvm_s390_gisc_register(kvm, isc);
+ aqic_gisa.ir = 1;
+ aqic_gisa.gisa = (uint64_t)gisa >> 4;
+
+ status = ap_aqic(q->apqn, aqic_gisa, (void *)h_nib);
+ switch (status.response_code) {
+ case AP_RESPONSE_NORMAL:
+ /* See if we did clear older IRQ configuration */
+ vfio_ap_free_aqic_resources(q);
+ q->saved_pfn = g_pfn;
+ q->saved_isc = isc;
+ break;
+ case AP_RESPONSE_OTHERWISE_CHANGED:
+ /* We could not modify IRQ setings: clear new configuration */
+ vfio_unpin_pages(mdev_dev(q->matrix_mdev->mdev), &g_pfn, 1);
+ kvm_s390_gisc_unregister(kvm, isc);
+ break;
+ default:
+ pr_warn("%s: apqn %04x: response: %02x\n", __func__, q->apqn,
+ status.response_code);
+ vfio_ap_irq_disable(q);
+ break;
+ }
+
+ return status;
+}
+
+/**
+ * handle_pqap: PQAP instruction callback
+ *
+ * @vcpu: The vcpu on which we received the PQAP instruction
+ *
+ * Get the general register contents to initialize internal variables.
+ * REG[0]: APQN
+ * REG[1]: IR and ISC
+ * REG[2]: NIB
+ *
+ * Response.status may be set to following Response Code:
+ * - AP_RESPONSE_Q_NOT_AVAIL: if the queue is not available
+ * - AP_RESPONSE_DECONFIGURED: if the queue is not configured
+ * - AP_RESPONSE_NORMAL (0) : in case of successs
+ * Check vfio_ap_setirq() and vfio_ap_clrirq() for other possible RC.
+ * We take the matrix_dev lock to ensure serialization on queues and
+ * mediated device access.
+ *
+ * Return 0 if we could handle the request inside KVM.
+ * otherwise, returns -EOPNOTSUPP to let QEMU handle the fault.
+ */
+static int handle_pqap(struct kvm_vcpu *vcpu)
+{
+ uint64_t status;
+ uint16_t apqn;
+ struct vfio_ap_queue *q;
+ struct ap_queue_status qstatus = {
+ .response_code = AP_RESPONSE_Q_NOT_AVAIL, };
+ struct ap_matrix_mdev *matrix_mdev;
+
+ /* If we do not use the AIV facility just go to userland */
+ if (!(vcpu->arch.sie_block->eca & ECA_AIV))
+ return -EOPNOTSUPP;
+
+ apqn = vcpu->run->s.regs.gprs[0] & 0xffff;
+ mutex_lock(&matrix_dev->lock);
+
+ if (!vcpu->kvm->arch.crypto.pqap_hook)
+ goto out_unlock;
+ matrix_mdev = container_of(vcpu->kvm->arch.crypto.pqap_hook,
+ struct ap_matrix_mdev, pqap_hook);
+
+ q = vfio_ap_get_queue(matrix_mdev, apqn);
+ if (!q)
+ goto out_unlock;
+
+ status = vcpu->run->s.regs.gprs[1];
+
+ /* If IR bit(16) is set we enable the interrupt */
+ if ((status >> (63 - 16)) & 0x01)
+ qstatus = vfio_ap_irq_enable(q, status & 0x07,
+ vcpu->run->s.regs.gprs[2]);
+ else
+ qstatus = vfio_ap_irq_disable(q);
+
+out_unlock:
+ memcpy(&vcpu->run->s.regs.gprs[1], &qstatus, sizeof(qstatus));
+ vcpu->run->s.regs.gprs[1] >>= 32;
+ mutex_unlock(&matrix_dev->lock);
+ return 0;
+}
+
static void vfio_ap_matrix_init(struct ap_config_info *info,
struct ap_matrix *matrix)
{
return -ENOMEM;
}
+ matrix_mdev->mdev = mdev;
vfio_ap_matrix_init(&matrix_dev->info, &matrix_mdev->matrix);
mdev_set_drvdata(mdev, matrix_mdev);
+ matrix_mdev->pqap_hook.hook = handle_pqap;
+ matrix_mdev->pqap_hook.owner = THIS_MODULE;
mutex_lock(&matrix_dev->lock);
list_add(&matrix_mdev->node, &matrix_dev->mdev_list);
mutex_unlock(&matrix_dev->lock);
return -EBUSY;
mutex_lock(&matrix_dev->lock);
+ vfio_ap_mdev_reset_queues(mdev);
list_del(&matrix_mdev->node);
mutex_unlock(&matrix_dev->lock);
}
matrix_mdev->kvm = kvm;
+ kvm_get_kvm(kvm);
+ kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook;
mutex_unlock(&matrix_dev->lock);
return 0;
}
+/*
+ * vfio_ap_mdev_iommu_notifier: IOMMU notifier callback
+ *
+ * @nb: The notifier block
+ * @action: Action to be taken
+ * @data: data associated with the request
+ *
+ * For an UNMAP request, unpin the guest IOVA (the NIB guest address we
+ * pinned before). Other requests are ignored.
+ *
+ */
+static int vfio_ap_mdev_iommu_notifier(struct notifier_block *nb,
+ unsigned long action, void *data)
+{
+ struct ap_matrix_mdev *matrix_mdev;
+
+ matrix_mdev = container_of(nb, struct ap_matrix_mdev, iommu_notifier);
+
+ if (action == VFIO_IOMMU_NOTIFY_DMA_UNMAP) {
+ struct vfio_iommu_type1_dma_unmap *unmap = data;
+ unsigned long g_pfn = unmap->iova >> PAGE_SHIFT;
+
+ vfio_unpin_pages(mdev_dev(matrix_mdev->mdev), &g_pfn, 1);
+ return NOTIFY_OK;
+ }
+
+ return NOTIFY_DONE;
+}
+
static int vfio_ap_mdev_group_notifier(struct notifier_block *nb,
unsigned long action, void *data)
{
return NOTIFY_OK;
}
-static int vfio_ap_mdev_reset_queue(unsigned int apid, unsigned int apqi,
- unsigned int retry)
+static void vfio_ap_irq_disable_apqn(int apqn)
+{
+ struct device *dev;
+ struct vfio_ap_queue *q;
+
+ 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);
+ }
+}
+
+int vfio_ap_mdev_reset_queue(unsigned int apid, unsigned int apqi,
+ unsigned int retry)
{
struct ap_queue_status status;
+ int retry2 = 2;
+ int apqn = AP_MKQID(apid, apqi);
do {
- status = ap_zapq(AP_MKQID(apid, apqi));
+ status = ap_zapq(apqn);
switch (status.response_code) {
case AP_RESPONSE_NORMAL:
+ while (!status.queue_empty && retry2--) {
+ msleep(20);
+ status = ap_tapq(apqn, NULL);
+ }
+ WARN_ON_ONCE(retry <= 0);
return 0;
case AP_RESPONSE_RESET_IN_PROGRESS:
case AP_RESPONSE_BUSY:
*/
if (ret)
rc = ret;
+ vfio_ap_irq_disable_apqn(AP_MKQID(apid, apqi));
}
}
return ret;
}
- return 0;
+ matrix_mdev->iommu_notifier.notifier_call = vfio_ap_mdev_iommu_notifier;
+ events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
+ ret = vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
+ &events, &matrix_mdev->iommu_notifier);
+ if (!ret)
+ return ret;
+
+ vfio_unregister_notifier(mdev_dev(mdev), VFIO_GROUP_NOTIFY,
+ &matrix_mdev->group_notifier);
+ module_put(THIS_MODULE);
+ return ret;
}
static void vfio_ap_mdev_release(struct mdev_device *mdev)
{
struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
- if (matrix_mdev->kvm)
+ 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;
+ }
+ mutex_unlock(&matrix_dev->lock);
- vfio_ap_mdev_reset_queues(mdev);
+ vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
+ &matrix_mdev->iommu_notifier);
vfio_unregister_notifier(mdev_dev(mdev), VFIO_GROUP_NOTIFY,
&matrix_mdev->group_notifier);
- matrix_mdev->kvm = NULL;
module_put(THIS_MODULE);
}
{
int ret;
+ mutex_lock(&matrix_dev->lock);
switch (cmd) {
case VFIO_DEVICE_GET_INFO:
ret = vfio_ap_mdev_get_device_info(arg);
ret = -EOPNOTSUPP;
break;
}
+ mutex_unlock(&matrix_dev->lock);
return ret;
}
git.samba.org / sfrench / cifs-2.6.git / blobdiff