Add a dma-buf callback that returns raw TPH metadata from the exporter so peer devices can reuse the steering tag and processing hint associated with a VFIO-exported buffer. Add a new VFIO_DEVICE_FEATURE_DMA_BUF_TPH ioctl that takes the fd from VFIO_DEVICE_FEATURE_DMA_BUF along with the TPH values, validates the fd is a vfio-exported dma-buf belonging to this device, and stores the TPH metadata under memory_lock. The existing VFIO_DEVICE_FEATURE_DMA_BUF uAPI is unchanged.
8-bit ST and 16-bit Extended ST are distinct namespaces in the PCIe TPH ST table (firmware reports them as separate fields with separate validity bits in the ACPI _DSM ST table), so the uAPI carries both values along with a flags field that indicates which value(s) are valid for this device. The exporter selects the value that matches the importer's requested width and returns -EOPNOTSUPP if that width is not present, instead of substituting a value across namespaces. Publish the TPH fields under memory_lock and gate readers on a release/acquire on the flags field; this lets get_tph() run lockless and avoids inverting the memory_lock -> dma_resv_lock ordering set up by vfio_pci_dma_buf_move(). Convert the @revoked bitfield to a plain bool so concurrent updates of @revoked (under dma_resv_lock) and the new TPH fields (under memory_lock) cannot race on a shared bitfield byte. Signed-off-by: Zhiping Zhang <[email protected]> --- drivers/vfio/pci/vfio_pci_core.c | 3 + drivers/vfio/pci/vfio_pci_dmabuf.c | 113 ++++++++++++++++++++++++++++- drivers/vfio/pci/vfio_pci_priv.h | 11 +++ include/linux/dma-buf.h | 21 ++++++ include/uapi/linux/vfio.h | 35 +++++++++ 5 files changed, 182 insertions(+), 1 deletion(-) diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 3f8d093aacf8..94aa6dd95701 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1534,6 +1534,9 @@ 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; } diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c index f87fd32e4a01..28247602e359 100644 --- a/drivers/vfio/pci/vfio_pci_dmabuf.c +++ b/drivers/vfio/pci/vfio_pci_dmabuf.c @@ -19,7 +19,23 @@ struct vfio_pci_dma_buf { u32 nr_ranges; struct kref kref; struct completion comp; - u8 revoked : 1; + /* + * TPH metadata published by VFIO_DEVICE_FEATURE_DMA_BUF_TPH and + * consumed by the @get_tph dma-buf callback. + * + * @tph_flags is the publish/consume gate: writers populate + * @steering_tag, @steering_tag_ext and @ph first, then store + * @tph_flags with smp_store_release(); readers do + * smp_load_acquire(&tph_flags) before accessing the value fields. + * @tph_flags == 0 means "TPH not set". Writers serialize via + * vdev->memory_lock; readers are lockless to avoid AB-BA against + * the dma_resv_lock held by importers. + */ + u32 tph_flags; + u16 steering_tag; + u16 steering_tag_ext; + u8 ph; + bool revoked; }; static int vfio_pci_dma_buf_attach(struct dma_buf *dmabuf, @@ -69,6 +85,35 @@ vfio_pci_dma_buf_map(struct dma_buf_attachment *attachment, return ret; } +static int vfio_pci_dma_buf_get_tph(struct dma_buf *dmabuf, u16 *steering_tag, + u8 *ph, u8 st_width) +{ + struct vfio_pci_dma_buf *priv = dmabuf->priv; + u32 flags; + + flags = smp_load_acquire(&priv->tph_flags); + if (!flags) + return -EOPNOTSUPP; + + switch (st_width) { + case 8: + if (!(flags & VFIO_DMA_BUF_TPH_ST)) + return -EOPNOTSUPP; + *steering_tag = priv->steering_tag; + break; + case 16: + if (!(flags & VFIO_DMA_BUF_TPH_ST_EXT)) + return -EOPNOTSUPP; + *steering_tag = priv->steering_tag_ext; + break; + default: + return -EINVAL; + } + + *ph = priv->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 +146,7 @@ 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, @@ -331,6 +377,71 @@ 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; + 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.reserved[0] || set_tph.reserved[1] || set_tph.reserved[2]) + return -EINVAL; + + if (set_tph.flags & ~(VFIO_DMA_BUF_TPH_ST | VFIO_DMA_BUF_TPH_ST_EXT)) + return -EINVAL; + + if (!set_tph.flags) + return -EINVAL; + + /* PCIe TLP Processing Hint is a 2-bit field. */ + if (set_tph.ph & ~0x3) + return -EINVAL; + + 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; + down_write(&vdev->memory_lock); + if (priv->vdev != vdev) { + ret = -EINVAL; + goto out_unlock; + } + + priv->steering_tag = set_tph.steering_tag; + priv->steering_tag_ext = set_tph.steering_tag_ext; + priv->ph = set_tph.ph; + /* + * Publish the TPH values before the gate flag, so that lockless + * readers in vfio_pci_dma_buf_get_tph() see fully-initialized + * fields once they observe a non-zero tph_flags. + */ + smp_store_release(&priv->tph_flags, set_tph.flags); + ret = 0; + +out_unlock: + up_write(&vdev->memory_lock); +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; diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h index fca9d0dfac90..200dd061ea5d 100644 --- a/drivers/vfio/pci/vfio_pci_priv.h +++ b/drivers/vfio/pci/vfio_pci_priv.h @@ -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 +132,13 @@ 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) { } diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index d1203da56fc5..d6a1b44052fc 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -113,6 +113,27 @@ struct dma_buf_ops { */ void (*unpin)(struct dma_buf_attachment *attach); + /** + * @get_tph: + * @dmabuf: DMA buffer for which to retrieve TPH metadata + * @steering_tag: Returns the raw TPH steering tag for @st_width + * @ph: Returns the TPH processing hint (2-bit value) + * @st_width: Consumer's supported steering tag width in bits (8 or 16) + * + * Return the TPH (TLP Processing Hints) metadata associated with this + * DMA buffer for the requested steering-tag width. 8-bit ST and 16-bit + * Extended ST are distinct namespaces in the PCIe TPH ST table, so the + * exporter must select the value that matches @st_width and must not + * substitute one for the other. + * + * Return 0 on success, -EOPNOTSUPP if no metadata is available for the + * requested width, or -EINVAL if @st_width is not 8 or 16. + * + * This callback is optional. + */ + int (*get_tph)(struct dma_buf *dmabuf, u16 *steering_tag, u8 *ph, + u8 st_width); + /** * @map_dma_buf: * diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 5de618a3a5ee..53b2bbd9fc1e 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1534,6 +1534,41 @@ 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. + * + * 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 in the PCIe TPH ST table; userspace should populate + * the value(s) it has from the firmware ST table for this device and set + * the matching VFIO_DMA_BUF_TPH_ST / VFIO_DMA_BUF_TPH_ST_EXT bit in @flags. + * An importer requests a specific width and receives the matching value; + * if the requested width is not present, the importer is told TPH is + * unavailable for this dma-buf. + * + * ph is the 2-bit TLP Processing Hint and must be in the range [0, 3]. + * + * The user must set TPH on the dma-buf before the importer consumes it. + * + * Return: 0 on success, -errno on failure. + */ +#define VFIO_DEVICE_FEATURE_DMA_BUF_TPH 13 + +#define VFIO_DMA_BUF_TPH_ST (1 << 0) /* steering_tag valid */ +#define VFIO_DMA_BUF_TPH_ST_EXT (1 << 1) /* steering_tag_ext valid */ + +struct vfio_device_feature_dma_buf_tph { + __s32 dmabuf_fd; + __u32 flags; + __u16 steering_tag; + __u16 steering_tag_ext; + __u8 ph; + __u8 reserved[3]; +}; + /* -------- API for Type1 VFIO IOMMU -------- */ /** -- 2.52.0
