[PATCH v8 6/7] vfio/pci: Add PCIe TPH GET_ST interface

[Chengwen Feng <fengchengwen@huawei.com>]

Add support to batch get CPU steering tags for device-specific TPH mode.
This interface requires enabling the 'enable_unsafe_tph_ds_mode' module
parameter.

Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
---
 drivers/vfio/pci/vfio_pci_core.c | 76 ++++++++++++++++++++++++++++++++
 1 file changed, 76 insertions(+)

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index bfc7e87d190f..7ec2dd32f106 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1532,6 +1532,80 @@ static int vfio_pci_tph_disable(struct vfio_pci_core_device *vdev)
 	return 0;
 }
 
+static int vfio_pci_tph_get_st(struct vfio_pci_core_device *vdev,
+			       struct vfio_device_pci_tph_op *op,
+			       void __user *uarg)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	u8 mode = pcie_tph_get_st_modes(pdev);
+	struct vfio_pci_tph_entry *ents;
+	struct vfio_pci_tph_st st;
+	enum tph_mem_type mtype;
+	size_t size, ents_off;
+	int i, err;
+
+	if (!enable_unsafe_tph_ds_mode || !(mode & PCI_TPH_CAP_ST_DS))
+		return -EOPNOTSUPP;
+
+	if (op->argsz < offsetofend(struct vfio_device_pci_tph_op, st))
+		return -EINVAL;
+
+	if (copy_from_user(&st, uarg, sizeof(st)))
+		return -EFAULT;
+
+	/* Check reserved fields are zero */
+	if (memchr_inv(&st.reserved, 0, sizeof(st.reserved)))
+		return -EINVAL;
+
+	if (!st.count || st.count > VFIO_PCI_TPH_MAX_ENTRIES)
+		return -EINVAL;
+
+	size = st.count * sizeof(*ents);
+	if (op->argsz < offsetofend(struct vfio_device_pci_tph_op, st) + size)
+		return -EINVAL;
+
+	ents = kvmalloc(size, GFP_KERNEL);
+	if (!ents)
+		return -ENOMEM;
+
+	ents_off = offsetof(struct vfio_pci_tph_st, ents);
+	if (copy_from_user(ents, uarg + ents_off, size)) {
+		err = -EFAULT;
+		goto out;
+	}
+
+	for (i = 0; i < st.count; i++) {
+		/* Check reserved fields and index are zero */
+		if (memchr_inv(&ents[i].reserved0, 0, sizeof(ents[i].reserved0)) ||
+		    memchr_inv(&ents[i].reserved1, 0, sizeof(ents[i].reserved1)) ||
+		    ents[i].index != 0) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		if (ents[i].mem_type == VFIO_PCI_TPH_MEM_TYPE_VM) {
+			mtype = TPH_MEM_TYPE_VM;
+		} else if (ents[i].mem_type == VFIO_PCI_TPH_MEM_TYPE_PM) {
+			mtype = TPH_MEM_TYPE_PM;
+		} else {
+			err = -EINVAL;
+			goto out;
+		}
+
+		err = pcie_tph_get_cpu_st(pdev, mtype, ents[i].cpu,
+					  &ents[i].st);
+		if (err)
+			goto out;
+	}
+
+	if (copy_to_user(uarg + ents_off, ents, size))
+		err = -EFAULT;
+
+out:
+	kvfree(ents);
+	return err;
+}
+
 static int vfio_pci_ioctl_tph(struct vfio_pci_core_device *vdev,
 			      void __user *uarg)
 {
@@ -1550,6 +1624,8 @@ static int vfio_pci_ioctl_tph(struct vfio_pci_core_device *vdev,
 		return vfio_pci_tph_enable(vdev, &op, uarg + minsz);
 	case VFIO_PCI_TPH_DISABLE:
 		return vfio_pci_tph_disable(vdev);
+	case VFIO_PCI_TPH_GET_ST:
+		return vfio_pci_tph_get_st(vdev, &op, uarg + minsz);
 	default:
 		/* Other ops are not implemented yet */
 		return -EINVAL;
-- 
2.17.1