1 files changed, 260 insertions, 76 deletions

diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 983b3b16196c..a52c2690933f 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -360,10 +360,26 @@ static int vfio_ap_validate_nib(struct kvm_vcpu *vcpu, dma_addr_t *nib)
 	return 0;
 }
 
-static int ensure_nib_shared(unsigned long addr, struct gmap *gmap)
+/**
+ * ensure_nib_shared() - Ensure the address of the NIB is secure and shared
+ * @addr: the physical (absolute) address of the NIB
+ *
+ * This function checks whether the NIB page, which has been pinned with
+ * vfio_pin_pages(), is a shared page belonging to a secure guest.
+ *
+ * It will call uv_pin_shared() on it; if the page was already pinned shared
+ * (i.e. if the NIB belongs to a secure guest and is shared), then 0
+ * (success) is returned. If the NIB was not shared, vfio_pin_pages() had
+ * exported it and now it does not belong to the secure guest anymore. In
+ * that case, an error is returned.
+ *
+ * Context: the NIB (at physical address @addr) has to be pinned with
+ *	    vfio_pin_pages() before calling this function.
+ *
+ * Return: 0 in case of success, otherwise an error < 0.
+ */
+static int ensure_nib_shared(unsigned long addr)
 {
-	int ret;
-
 	/*
 	 * The nib has to be located in shared storage since guest and
 	 * host access it. vfio_pin_pages() will do a pin shared and
@@ -374,12 +390,7 @@ static int ensure_nib_shared(unsigned long addr, struct gmap *gmap)
 	 *
 	 * If the page is already pinned shared the UV will return a success.
 	 */
-	ret = uv_pin_shared(addr);
-	if (ret) {
-		/* vfio_pin_pages() likely exported the page so let's re-import */
-		gmap_convert_to_secure(gmap, addr);
-	}
-	return ret;
+	return uv_pin_shared(addr);
 }
 
 /**
@@ -425,6 +436,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q,
 		return status;
 	}
 
+	/* The pin will probably be successful even if the NIB was not shared */
 	ret = vfio_pin_pages(&q->matrix_mdev->vdev, nib, 1,
 			     IOMMU_READ | IOMMU_WRITE, &h_page);
 	switch (ret) {
@@ -447,7 +459,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q,
 
 	/* NIB in non-shared storage is a rc 6 for PV guests */
 	if (kvm_s390_pv_cpu_is_protected(vcpu) &&
-	    ensure_nib_shared(h_nib & PAGE_MASK, kvm->arch.gmap)) {
+	    ensure_nib_shared(h_nib & PAGE_MASK)) {
 		vfio_unpin_pages(&q->matrix_mdev->vdev, nib, 1);
 		status.response_code = AP_RESPONSE_INVALID_ADDRESS;
 		return status;
@@ -659,6 +671,21 @@ static bool vfio_ap_mdev_filter_cdoms(struct ap_matrix_mdev *matrix_mdev)
 			     AP_DOMAINS);
 }
 
+static bool _queue_passable(struct vfio_ap_queue *q)
+{
+	if (!q)
+		return false;
+
+	switch (q->reset_status.response_code) {
+	case AP_RESPONSE_NORMAL:
+	case AP_RESPONSE_DECONFIGURED:
+	case AP_RESPONSE_CHECKSTOPPED:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /*
  * vfio_ap_mdev_filter_matrix - filter the APQNs assigned to the matrix mdev
  *				to ensure no queue devices are passed through to
@@ -687,7 +714,6 @@ static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev,
 	unsigned long apid, apqi, apqn;
 	DECLARE_BITMAP(prev_shadow_apm, AP_DEVICES);
 	DECLARE_BITMAP(prev_shadow_aqm, AP_DOMAINS);
-	struct vfio_ap_queue *q;
 
 	bitmap_copy(prev_shadow_apm, matrix_mdev->shadow_apcb.apm, AP_DEVICES);
 	bitmap_copy(prev_shadow_aqm, matrix_mdev->shadow_apcb.aqm, AP_DOMAINS);
@@ -716,8 +742,7 @@ static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev,
 			 * hardware device.
 			 */
 			apqn = AP_MKQID(apid, apqi);
-			q = vfio_ap_mdev_get_queue(matrix_mdev, apqn);
-			if (!q || q->reset_status.response_code) {
+			if (!_queue_passable(vfio_ap_mdev_get_queue(matrix_mdev, apqn))) {
 				clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm);
 
 				/*
@@ -781,10 +806,11 @@ err_put_vdev:
 static void vfio_ap_mdev_link_queue(struct ap_matrix_mdev *matrix_mdev,
 				    struct vfio_ap_queue *q)
 {
-	if (q) {
-		q->matrix_mdev = matrix_mdev;
-		hash_add(matrix_mdev->qtable.queues, &q->mdev_qnode, q->apqn);
-	}
+	if (!q || vfio_ap_mdev_get_queue(matrix_mdev, q->apqn))
+		return;
+
+	q->matrix_mdev = matrix_mdev;
+	hash_add(matrix_mdev->qtable.queues, &q->mdev_qnode, q->apqn);
 }
 
 static void vfio_ap_mdev_link_apqn(struct ap_matrix_mdev *matrix_mdev, int apqn)
@@ -1105,20 +1131,29 @@ static void vfio_ap_mdev_unlink_adapter(struct ap_matrix_mdev *matrix_mdev,
 	}
 }
 
-static void vfio_ap_mdev_hot_unplug_adapter(struct ap_matrix_mdev *matrix_mdev,
-					    unsigned long apid)
+static void vfio_ap_mdev_hot_unplug_adapters(struct ap_matrix_mdev *matrix_mdev,
+					     unsigned long *apids)
 {
 	struct vfio_ap_queue *q, *tmpq;
 	struct list_head qlist;
+	unsigned long apid;
+	bool apcb_update = false;
 
 	INIT_LIST_HEAD(&qlist);
-	vfio_ap_mdev_unlink_adapter(matrix_mdev, apid, &qlist);
 
-	if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm)) {
-		clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm);
-		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+	for_each_set_bit_inv(apid, apids, AP_DEVICES) {
+		vfio_ap_mdev_unlink_adapter(matrix_mdev, apid, &qlist);
+
+		if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm)) {
+			clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm);
+			apcb_update = true;
+		}
 	}
 
+	/* Only update apcb if needed to avoid impacting guest */
+	if (apcb_update)
+		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+
 	vfio_ap_mdev_reset_qlist(&qlist);
 
 	list_for_each_entry_safe(q, tmpq, &qlist, reset_qnode) {
@@ -1127,6 +1162,16 @@ static void vfio_ap_mdev_hot_unplug_adapter(struct ap_matrix_mdev *matrix_mdev,
 	}
 }
 
+static void vfio_ap_mdev_hot_unplug_adapter(struct ap_matrix_mdev *matrix_mdev,
+					    unsigned long apid)
+{
+	DECLARE_BITMAP(apids, AP_DEVICES);
+
+	bitmap_zero(apids, AP_DEVICES);
+	set_bit_inv(apid, apids);
+	vfio_ap_mdev_hot_unplug_adapters(matrix_mdev, apids);
+}
+
 /**
  * unassign_adapter_store - parses the APID from @buf and clears the
  * corresponding bit in the mediated matrix device's APM
@@ -1287,20 +1332,29 @@ static void vfio_ap_mdev_unlink_domain(struct ap_matrix_mdev *matrix_mdev,
 	}
 }
 
-static void vfio_ap_mdev_hot_unplug_domain(struct ap_matrix_mdev *matrix_mdev,
-					   unsigned long apqi)
+static void vfio_ap_mdev_hot_unplug_domains(struct ap_matrix_mdev *matrix_mdev,
+					    unsigned long *apqis)
 {
 	struct vfio_ap_queue *q, *tmpq;
 	struct list_head qlist;
+	unsigned long apqi;
+	bool apcb_update = false;
 
 	INIT_LIST_HEAD(&qlist);
-	vfio_ap_mdev_unlink_domain(matrix_mdev, apqi, &qlist);
 
-	if (test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) {
-		clear_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm);
-		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+	for_each_set_bit_inv(apqi, apqis, AP_DOMAINS) {
+		vfio_ap_mdev_unlink_domain(matrix_mdev, apqi, &qlist);
+
+		if (test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) {
+			clear_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm);
+			apcb_update = true;
+		}
 	}
 
+	/* Only update apcb if needed to avoid impacting guest */
+	if (apcb_update)
+		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+
 	vfio_ap_mdev_reset_qlist(&qlist);
 
 	list_for_each_entry_safe(q, tmpq, &qlist, reset_qnode) {
@@ -1309,6 +1363,16 @@ static void vfio_ap_mdev_hot_unplug_domain(struct ap_matrix_mdev *matrix_mdev,
 	}
 }
 
+static void vfio_ap_mdev_hot_unplug_domain(struct ap_matrix_mdev *matrix_mdev,
+					   unsigned long apqi)
+{
+	DECLARE_BITMAP(apqis, AP_DOMAINS);
+
+	bitmap_zero(apqis, AP_DEVICES);
+	set_bit_inv(apqi, apqis);
+	vfio_ap_mdev_hot_unplug_domains(matrix_mdev, apqis);
+}
+
 /**
  * unassign_domain_store - parses the APQI from @buf and clears the
  * corresponding bit in the mediated matrix device's AQM
@@ -1469,18 +1533,13 @@ static ssize_t control_domains_show(struct device *dev,
 				    char *buf)
 {
 	unsigned long id;
-	int nchars = 0;
-	int n;
-	char *bufpos = buf;
 	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);
 	unsigned long max_domid = matrix_mdev->matrix.adm_max;
+	int nchars = 0;
 
 	mutex_lock(&matrix_dev->mdevs_lock);
-	for_each_set_bit_inv(id, matrix_mdev->matrix.adm, max_domid + 1) {
-		n = sprintf(bufpos, "%04lx\n", id);
-		bufpos += n;
-		nchars += n;
-	}
+	for_each_set_bit_inv(id, matrix_mdev->matrix.adm, max_domid + 1)
+		nchars += sysfs_emit_at(buf, nchars, "%04lx\n", id);
 	mutex_unlock(&matrix_dev->mdevs_lock);
 
 	return nchars;
@@ -1489,7 +1548,6 @@ static DEVICE_ATTR_RO(control_domains);
 
 static ssize_t vfio_ap_mdev_matrix_show(struct ap_matrix *matrix, char *buf)
 {
-	char *bufpos = buf;
 	unsigned long apid;
 	unsigned long apqi;
 	unsigned long apid1;
@@ -1497,33 +1555,21 @@ static ssize_t vfio_ap_mdev_matrix_show(struct ap_matrix *matrix, char *buf)
 	unsigned long napm_bits = matrix->apm_max + 1;
 	unsigned long naqm_bits = matrix->aqm_max + 1;
 	int nchars = 0;
-	int n;
 
 	apid1 = find_first_bit_inv(matrix->apm, napm_bits);
 	apqi1 = find_first_bit_inv(matrix->aqm, naqm_bits);
 
 	if ((apid1 < napm_bits) && (apqi1 < naqm_bits)) {
 		for_each_set_bit_inv(apid, matrix->apm, napm_bits) {
-			for_each_set_bit_inv(apqi, matrix->aqm,
-					     naqm_bits) {
-				n = sprintf(bufpos, "%02lx.%04lx\n", apid,
-					    apqi);
-				bufpos += n;
-				nchars += n;
-			}
+			for_each_set_bit_inv(apqi, matrix->aqm, naqm_bits)
+				nchars += sysfs_emit_at(buf, nchars, "%02lx.%04lx\n", apid, apqi);
 		}
 	} else if (apid1 < napm_bits) {
-		for_each_set_bit_inv(apid, matrix->apm, napm_bits) {
-			n = sprintf(bufpos, "%02lx.\n", apid);
-			bufpos += n;
-			nchars += n;
-		}
+		for_each_set_bit_inv(apid, matrix->apm, napm_bits)
+			nchars += sysfs_emit_at(buf, nchars, "%02lx.\n", apid);
 	} else if (apqi1 < naqm_bits) {
-		for_each_set_bit_inv(apqi, matrix->aqm, naqm_bits) {
-			n = sprintf(bufpos, ".%04lx\n", apqi);
-			bufpos += n;
-			nchars += n;
-		}
+		for_each_set_bit_inv(apqi, matrix->aqm, naqm_bits)
+			nchars += sysfs_emit_at(buf, nchars, ".%04lx\n", apqi);
 	}
 
 	return nchars;
@@ -1557,6 +1603,158 @@ static ssize_t guest_matrix_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(guest_matrix);
 
+static ssize_t write_ap_bitmap(unsigned long *bitmap, char *buf, int offset, char sep)
+{
+	return sysfs_emit_at(buf, offset, "0x%016lx%016lx%016lx%016lx%c",
+			 bitmap[0], bitmap[1], bitmap[2], bitmap[3], sep);
+}
+
+static ssize_t ap_config_show(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);
+	int idx = 0;
+
+	idx += write_ap_bitmap(matrix_mdev->matrix.apm, buf, idx, ',');
+	idx += write_ap_bitmap(matrix_mdev->matrix.aqm, buf, idx, ',');
+	idx += write_ap_bitmap(matrix_mdev->matrix.adm, buf, idx, '\n');
+
+	return idx;
+}
+
+/* Number of characters needed for a complete hex mask representing the bits in ..  */
+#define AP_DEVICES_STRLEN	(AP_DEVICES / 4 + 3)
+#define AP_DOMAINS_STRLEN	(AP_DOMAINS / 4 + 3)
+#define AP_CONFIG_STRLEN	(AP_DEVICES_STRLEN + 2 * AP_DOMAINS_STRLEN)
+
+static int parse_bitmap(char **strbufptr, unsigned long *bitmap, int nbits)
+{
+	char *curmask;
+
+	curmask = strsep(strbufptr, ",\n");
+	if (!curmask)
+		return -EINVAL;
+
+	bitmap_clear(bitmap, 0, nbits);
+	return ap_hex2bitmap(curmask, bitmap, nbits);
+}
+
+static int ap_matrix_overflow_check(struct ap_matrix_mdev *matrix_mdev)
+{
+	unsigned long bit;
+
+	for_each_set_bit_inv(bit, matrix_mdev->matrix.apm, AP_DEVICES) {
+		if (bit > matrix_mdev->matrix.apm_max)
+			return -ENODEV;
+	}
+
+	for_each_set_bit_inv(bit, matrix_mdev->matrix.aqm, AP_DOMAINS) {
+		if (bit > matrix_mdev->matrix.aqm_max)
+			return -ENODEV;
+	}
+
+	for_each_set_bit_inv(bit, matrix_mdev->matrix.adm, AP_DOMAINS) {
+		if (bit > matrix_mdev->matrix.adm_max)
+			return -ENODEV;
+	}
+
+	return 0;
+}
+
+static void ap_matrix_copy(struct ap_matrix *dst, struct ap_matrix *src)
+{
+	/* This check works around false positive gcc -Wstringop-overread */
+	if (!src)
+		return;
+
+	bitmap_copy(dst->apm, src->apm, AP_DEVICES);
+	bitmap_copy(dst->aqm, src->aqm, AP_DOMAINS);
+	bitmap_copy(dst->adm, src->adm, AP_DOMAINS);
+}
+
+static ssize_t ap_config_store(struct device *dev, struct device_attribute *attr,
+			       const char *buf, size_t count)
+{
+	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);
+	struct ap_matrix m_new, m_old, m_added, m_removed;
+	DECLARE_BITMAP(apm_filtered, AP_DEVICES);
+	unsigned long newbit;
+	char *newbuf, *rest;
+	int rc = count;
+	bool do_update;
+
+	newbuf = kstrndup(buf, AP_CONFIG_STRLEN, GFP_KERNEL);
+	if (!newbuf)
+		return -ENOMEM;
+	rest = newbuf;
+
+	mutex_lock(&ap_perms_mutex);
+	get_update_locks_for_mdev(matrix_mdev);
+
+	/* Save old state */
+	ap_matrix_copy(&m_old, &matrix_mdev->matrix);
+	if (parse_bitmap(&rest, m_new.apm, AP_DEVICES) ||
+	    parse_bitmap(&rest, m_new.aqm, AP_DOMAINS) ||
+	    parse_bitmap(&rest, m_new.adm, AP_DOMAINS)) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	bitmap_andnot(m_removed.apm, m_old.apm, m_new.apm, AP_DEVICES);
+	bitmap_andnot(m_removed.aqm, m_old.aqm, m_new.aqm, AP_DOMAINS);
+	bitmap_andnot(m_added.apm, m_new.apm, m_old.apm, AP_DEVICES);
+	bitmap_andnot(m_added.aqm, m_new.aqm, m_old.aqm, AP_DOMAINS);
+
+	/* Need new bitmaps in matrix_mdev for validation */
+	ap_matrix_copy(&matrix_mdev->matrix, &m_new);
+
+	/* Ensure new state is valid, else undo new state */
+	rc = vfio_ap_mdev_validate_masks(matrix_mdev);
+	if (rc) {
+		ap_matrix_copy(&matrix_mdev->matrix, &m_old);
+		goto out;
+	}
+	rc = ap_matrix_overflow_check(matrix_mdev);
+	if (rc) {
+		ap_matrix_copy(&matrix_mdev->matrix, &m_old);
+		goto out;
+	}
+	rc = count;
+
+	/* Need old bitmaps in matrix_mdev for unplug/unlink */
+	ap_matrix_copy(&matrix_mdev->matrix, &m_old);
+
+	/* Unlink removed adapters/domains */
+	vfio_ap_mdev_hot_unplug_adapters(matrix_mdev, m_removed.apm);
+	vfio_ap_mdev_hot_unplug_domains(matrix_mdev, m_removed.aqm);
+
+	/* Need new bitmaps in matrix_mdev for linking new adapters/domains */
+	ap_matrix_copy(&matrix_mdev->matrix, &m_new);
+
+	/* Link newly added adapters */
+	for_each_set_bit_inv(newbit, m_added.apm, AP_DEVICES)
+		vfio_ap_mdev_link_adapter(matrix_mdev, newbit);
+
+	for_each_set_bit_inv(newbit, m_added.aqm, AP_DOMAINS)
+		vfio_ap_mdev_link_domain(matrix_mdev, newbit);
+
+	/* filter resources not bound to vfio-ap */
+	do_update = vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered);
+	do_update |= vfio_ap_mdev_filter_cdoms(matrix_mdev);
+
+	/* Apply changes to shadow apbc if things changed */
+	if (do_update) {
+		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+		reset_queues_for_apids(matrix_mdev, apm_filtered);
+	}
+out:
+	release_update_locks_for_mdev(matrix_mdev);
+	mutex_unlock(&ap_perms_mutex);
+	kfree(newbuf);
+	return rc;
+}
+static DEVICE_ATTR_RW(ap_config);
+
 static struct attribute *vfio_ap_mdev_attrs[] = {
 	&dev_attr_assign_adapter.attr,
 	&dev_attr_unassign_adapter.attr,
@@ -1564,6 +1762,7 @@ static struct attribute *vfio_ap_mdev_attrs[] = {
 	&dev_attr_unassign_domain.attr,
 	&dev_attr_assign_control_domain.attr,
 	&dev_attr_unassign_control_domain.attr,
+	&dev_attr_ap_config.attr,
 	&dev_attr_control_domains.attr,
 	&dev_attr_matrix.attr,
 	&dev_attr_guest_matrix.attr,
@@ -1691,6 +1890,7 @@ static int apq_status_check(int apqn, struct ap_queue_status *status)
 	switch (status->response_code) {
 	case AP_RESPONSE_NORMAL:
 	case AP_RESPONSE_DECONFIGURED:
+	case AP_RESPONSE_CHECKSTOPPED:
 		return 0;
 	case AP_RESPONSE_RESET_IN_PROGRESS:
 	case AP_RESPONSE_BUSY:
@@ -1747,14 +1947,6 @@ static void apq_reset_check(struct work_struct *reset_work)
 				memcpy(&q->reset_status, &status, sizeof(status));
 				continue;
 			}
-			/*
-			 * When an AP adapter is deconfigured, the
-			 * associated queues are reset, so let's set the
-			 * status response code to 0 so the queue may be
-			 * passed through (i.e., not filtered)
-			 */
-			if (status.response_code == AP_RESPONSE_DECONFIGURED)
-				q->reset_status.response_code = 0;
 			if (q->saved_isc != VFIO_AP_ISC_INVALID)
 				vfio_ap_free_aqic_resources(q);
 			break;
@@ -1781,12 +1973,7 @@ static void vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q)
 		queue_work(system_long_wq, &q->reset_work);
 		break;
 	case AP_RESPONSE_DECONFIGURED:
-		/*
-		 * When an AP adapter is deconfigured, the associated
-		 * queues are reset, so let's set the status response code to 0
-		 * so the queue may be passed through (i.e., not filtered).
-		 */
-		q->reset_status.response_code = 0;
+	case AP_RESPONSE_CHECKSTOPPED:
 		vfio_ap_free_aqic_resources(q);
 		break;
 	default:
@@ -2070,14 +2257,11 @@ static ssize_t status_show(struct device *dev,
 		if (matrix_mdev->kvm &&
 		    test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) &&
 		    test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm))
-			nchars = scnprintf(buf, PAGE_SIZE, "%s\n",
-					   AP_QUEUE_IN_USE);
+			nchars = sysfs_emit(buf, "%s\n", AP_QUEUE_IN_USE);
 		else
-			nchars = scnprintf(buf, PAGE_SIZE, "%s\n",
-					   AP_QUEUE_ASSIGNED);
+			nchars = sysfs_emit(buf, "%s\n", AP_QUEUE_ASSIGNED);
 	} else {
-		nchars = scnprintf(buf, PAGE_SIZE, "%s\n",
-				   AP_QUEUE_UNASSIGNED);
+		nchars = sysfs_emit(buf, "%s\n", AP_QUEUE_UNASSIGNED);
 	}
 
 	mutex_unlock(&matrix_dev->mdevs_lock);