[PATCH v7 4/5] vfio/pci: implement get_tph and DMA_BUF_TPH feature

@@ -1569,6 +1569,9 @@ int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags,
 		return vfio_pci_core_feature_token(vdev, flags, arg, argsz);
 	case VFIO_DEVICE_FEATURE_DMA_BUF:
 		return vfio_pci_core_feature_dma_buf(vdev, flags, arg, argsz);
+	case VFIO_DEVICE_FEATURE_DMA_BUF_TPH:
+		return vfio_pci_core_feature_dma_buf_tph(vdev, flags, arg,
+							 argsz);
 	default:
 		return -ENOTTY;
 	}

@@ -3,6 +3,7 @@
  */
 #include <linux/dma-buf-mapping.h>
 #include <linux/pci-p2pdma.h>
+#include <linux/pci-tph.h>
 #include <linux/dma-resv.h>
 
 #include "vfio_pci_priv.h"

@@ -19,7 +20,12 @@ struct vfio_pci_dma_buf {
 	u32 nr_ranges;
 	struct kref kref;
 	struct completion comp;
-	u8 revoked : 1;
+	u8 tph_st_valid:1;
+	u8 tph_st_ext_valid:1;
+	u8 tph_ph:2;
+	u8 tph_st;
+	u16 tph_st_ext;
+	u8 revoked:1;
 };
 
 static int vfio_pci_dma_buf_attach(struct dma_buf *dmabuf,

@@ -69,6 +75,26 @@ vfio_pci_dma_buf_map(struct dma_buf_attachment *attachment,
 	return ret;
 }
 
+static int vfio_pci_dma_buf_get_tph(struct dma_buf *dmabuf, bool extended,
+				    u16 *steering_tag, u8 *ph)
+{
+	struct vfio_pci_dma_buf *priv = dmabuf->priv;
+
+	dma_resv_assert_held(dmabuf->resv);
+
+	if (extended) {
+		if (!priv->tph_st_ext_valid)
+			return -EOPNOTSUPP;
+		*steering_tag = priv->tph_st_ext;
+	} else {
+		if (!priv->tph_st_valid)
+			return -EOPNOTSUPP;
+		*steering_tag = priv->tph_st;
+	}
+	*ph = priv->tph_ph;
+	return 0;
+}
+
 static void vfio_pci_dma_buf_unmap(struct dma_buf_attachment *attachment,
 				   struct sg_table *sgt,
 				   enum dma_data_direction dir)

@@ -101,6 +127,7 @@ static void vfio_pci_dma_buf_release(struct dma_buf *dmabuf)
 
 static const struct dma_buf_ops vfio_pci_dmabuf_ops = {
 	.attach = vfio_pci_dma_buf_attach,
+	.get_tph = vfio_pci_dma_buf_get_tph,
 	.map_dma_buf = vfio_pci_dma_buf_map,
 	.unmap_dma_buf = vfio_pci_dma_buf_unmap,
 	.release = vfio_pci_dma_buf_release,

@@ -333,6 +360,71 @@ int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
 	return ret;
 }
 
+int vfio_pci_core_feature_dma_buf_tph(struct vfio_pci_core_device *vdev,
+				      u32 flags,
+				      struct vfio_device_feature_dma_buf_tph __user *arg,
+				      size_t argsz)
+{
+	struct vfio_device_feature_dma_buf_tph set_tph;
+	struct vfio_pci_dma_buf *priv;
+	struct dma_buf *dmabuf;
+	u8 comp;
+	int ret;
+
+	ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET,
+				 sizeof(set_tph));
+	if (ret != 1)
+		return ret;
+
+	if (copy_from_user(&set_tph, arg, sizeof(set_tph)))
+		return -EFAULT;
+
+	if (set_tph.flags & ~(VFIO_DMA_BUF_TPH_ST | VFIO_DMA_BUF_TPH_ST_EXT))
+		return -EINVAL;
+
+	if (set_tph.ph & ~0x3)
+		return -EINVAL;
+
+	comp = pcie_tph_completer_type(vdev->pdev);
+	if (comp == PCI_EXP_DEVCAP2_TPH_COMP_NONE)
+		return -EOPNOTSUPP;
+	if ((set_tph.flags & VFIO_DMA_BUF_TPH_ST_EXT) &&
+	    comp != PCI_EXP_DEVCAP2_TPH_COMP_EXT_TPH)
+		return -EOPNOTSUPP;
+
+	dmabuf = dma_buf_get(set_tph.dmabuf_fd);
+	if (IS_ERR(dmabuf))
+		return PTR_ERR(dmabuf);
+
+	if (dmabuf->ops != &vfio_pci_dmabuf_ops) {
+		ret = -EINVAL;
+		goto out_put;
+	}
+
+	priv = dmabuf->priv;
+	if (priv->vdev != vdev) {
+		ret = -EINVAL;
+		goto out_put;
+	}
+
+	ret = dma_resv_lock_interruptible(dmabuf->resv, NULL);
+	if (ret)
+		goto out_put;
+
+	priv->tph_st         = set_tph.steering_tag;
+	priv->tph_st_ext     = set_tph.steering_tag_ext;
+	priv->tph_ph         = set_tph.ph;
+	priv->tph_st_valid   = !!(set_tph.flags & VFIO_DMA_BUF_TPH_ST);
+	priv->tph_st_ext_valid =
+		!!(set_tph.flags & VFIO_DMA_BUF_TPH_ST_EXT);
+	dma_resv_unlock(dmabuf->resv);
+	ret = 0;
+
+out_put:
+	dma_buf_put(dmabuf);
+	return ret;
+}
+
 void vfio_pci_dma_buf_move(struct vfio_pci_core_device *vdev, bool revoked)
 {
 	struct vfio_pci_dma_buf *priv;

@@ -118,6 +118,10 @@ static inline bool vfio_pci_is_vga(struct pci_dev *pdev)
 int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
 				  struct vfio_device_feature_dma_buf __user *arg,
 				  size_t argsz);
+int vfio_pci_core_feature_dma_buf_tph(struct vfio_pci_core_device *vdev,
+				      u32 flags,
+				      struct vfio_device_feature_dma_buf_tph __user *arg,
+				      size_t argsz);
 void vfio_pci_dma_buf_cleanup(struct vfio_pci_core_device *vdev);
 void vfio_pci_dma_buf_move(struct vfio_pci_core_device *vdev, bool revoked);
 #else

@@ -128,6 +132,14 @@ vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
 {
 	return -ENOTTY;
 }
+
+static inline int
+vfio_pci_core_feature_dma_buf_tph(struct vfio_pci_core_device *vdev, u32 flags,
+				  struct vfio_device_feature_dma_buf_tph __user *arg,
+				  size_t argsz)
+{
+	return -ENOTTY;
+}
 static inline void vfio_pci_dma_buf_cleanup(struct vfio_pci_core_device *vdev)
 {
 }

@@ -1534,6 +1534,43 @@ struct vfio_device_feature_dma_buf {
  */
 #define VFIO_DEVICE_FEATURE_MIG_PRECOPY_INFOv2  12
 
+/**
+ * Upon VFIO_DEVICE_FEATURE_SET associate TPH (TLP Processing Hints) metadata
+ * with a vfio-exported dma-buf. The dma-buf must have been created by
+ * VFIO_DEVICE_FEATURE_DMA_BUF on this device, and the device must report
+ * TPH Completer support in Device Capabilities 2 (bits 13:12); requests
+ * carrying VFIO_DMA_BUF_TPH_ST_EXT additionally require the device to
+ * report the Extended TPH Completer encoding. Otherwise the ioctl
+ * returns -EOPNOTSUPP.
+ *
+ * dmabuf_fd is the file descriptor returned by VFIO_DEVICE_FEATURE_DMA_BUF.
+ *
+ * 8-bit ST (steering_tag) and 16-bit Extended ST (steering_tag_ext) are
+ * distinct namespaces. Userspace supplies whichever values are valid and sets
+ * the matching VFIO_DMA_BUF_TPH_ST / VFIO_DMA_BUF_TPH_ST_EXT bits in @flags;
+ * an importer requests one namespace and receives the matching value.
+ *
+ * @flags == 0 marks any previously published ST / Extended-ST as invalid
+ * for future get_tph() requests on this dma-buf.
+ *
+ * ph is the 2-bit TLP Processing Hint and must be in the range [0, 3].
+ *
+ * Userspace must publish TPH before handing the dma-buf fd to an importer.
+ * Calling SET again replaces the published values.
+ */
+#define VFIO_DEVICE_FEATURE_DMA_BUF_TPH 13
+
+#define VFIO_DMA_BUF_TPH_ST		(1 << 0)
+#define VFIO_DMA_BUF_TPH_ST_EXT		(1 << 1)
+
+struct vfio_device_feature_dma_buf_tph {
+	__s32	dmabuf_fd;
+	__u32	flags;
+	__u16	steering_tag_ext;
+	__u8	steering_tag;
+	__u8	ph;
+};
+
 /* -------- API for Type1 VFIO IOMMU -------- */
 
 /**