[PATCH v2 RESEND 0/5] vfio/pci: Add PCIe TPH support

[PATCH v2 RESEND 0/5] vfio/pci: Add PCIe TPH support

[Chengwen Feng]

This series adds support for PCIe TLP Processing Hints (TPH) to
vfio-pci, allowing userspace to manage device steering tags for
improved performance and QoS in virtualized deployments.

The implementation follows a clean incremental structure:
- Patch 1: Export pcie_tph_get_st_modes()
- Patch 2: Introduce UAPI ABI and implement capability query to
  let userspace discover supported TPH modes, ST table presence
  and size.
- Patch 3: Add TPH enable/disable with mode selection.
- Patch 4: Add interface to batch get per-CPU steering tags for
  device-specific mode without standard ST table.
- Patch 5: Add interface to batch program steering tag table
  entries for standard TPH modes.

All user API definitions are finalized in the first patch and
remain stable across the series. The design follows existing
VFIO conventions and relies on kernel pcie-tph infrastructure.

This series addresses the TPH management requirements discussed
in the RFC "Proposal: Add sysfs interface for PCIe TPH Steering
Tag retrieval and configuration".

Instead of introducing a sysfs interface, we choose to implement
TPH management via a VFIO-specific ioctl for these reasons:
1. VFIO is the standard userspace interface for PCI devices.
2. An ioctl approach provides better type safety, batch support
   and stable ABI compared to sysfs for configuration.
3. VFIO properly isolates TPH operations to the assigned device,
   avoiding conflicts with other kernel management paths.

Based on earlier RFC work by Wathsala Vithanage.

v2:
- Export pcie_tph_get_st_modes()
- Add detailed comment for UAPI structures and operations
- Add batch entry limit VFIO_TPH_MAX_ENTRIES
- Improve robustness and error handling

Chengwen Feng (5):
  pci/tph: Export pcie_tph_get_st_modes() for external use
  vfio/pci: Add PCIe TPH interface with capability query
  vfio/pci: Add PCIe TPH enable/disable support
  vfio/pci: Add PCIe TPH GET_ST interface
  vfio/pci: Add PCIe TPH SET_ST interface

 drivers/pci/tph.c                |  13 +-
 drivers/vfio/pci/vfio_pci_core.c | 213 +++++++++++++++++++++++++++++++
 include/linux/pci-tph.h          |   7 +
 include/uapi/linux/vfio.h        | 131 +++++++++++++++++++
 4 files changed, 362 insertions(+), 2 deletions(-)

-- 
2.17.1

[PATCH v2 RESEND 1/5] pci/tph: Export pcie_tph_get_st_modes() for external use

[Chengwen Feng]

Export the helper to retrieve supported PCIe TPH steering tag modes so
that drivers like VFIO can query and expose device capabilities to
userspace.

And also add pcie_tph_get_st_table_size() and
pcie_tph_get_st_table_loc() stub implementation in the !CONFIG_PCI_TPH
case.

Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
---
 drivers/pci/tph.c       | 13 +++++++++++--
 include/linux/pci-tph.h |  7 +++++++
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/tph.c b/drivers/pci/tph.c
index 91145e8d9d95..f8767bf6fee9 100644
--- a/drivers/pci/tph.c
+++ b/drivers/pci/tph.c
@@ -145,7 +145,15 @@ static void set_ctrl_reg_req_en(struct pci_dev *pdev, u8 req_type)
 	pci_write_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, reg);
 }
 
-static u8 get_st_modes(struct pci_dev *pdev)
+/**
+ * pcie_tph_get_st_modes - Get supported Steering Tag modes
+ * @pdev: PCI device to query
+ *
+ * Return:
+ *  Bitmask of supported ST modes (PCI_TPH_CAP_ST_NS, PCI_TPH_CAP_ST_IV,
+ *                                 PCI_TPH_CAP_ST_DS)
+ */
+u8 pcie_tph_get_st_modes(struct pci_dev *pdev)
 {
 	u32 reg;
 
@@ -154,6 +162,7 @@ static u8 get_st_modes(struct pci_dev *pdev)
 
 	return reg;
 }
+EXPORT_SYMBOL(pcie_tph_get_st_modes);
 
 /**
  * pcie_tph_get_st_table_loc - Return the device's ST table location
@@ -400,7 +409,7 @@ int pcie_enable_tph(struct pci_dev *pdev, int mode)
 
 	/* Sanitize and check ST mode compatibility */
 	mode &= PCI_TPH_CTRL_MODE_SEL_MASK;
-	dev_modes = get_st_modes(pdev);
+	dev_modes = pcie_tph_get_st_modes(pdev);
 	if (!((1 << mode) & dev_modes))
 		return -EINVAL;
 
diff --git a/include/linux/pci-tph.h b/include/linux/pci-tph.h
index be68cd17f2f8..586c75b19e01 100644
--- a/include/linux/pci-tph.h
+++ b/include/linux/pci-tph.h
@@ -30,6 +30,7 @@ void pcie_disable_tph(struct pci_dev *pdev);
 int pcie_enable_tph(struct pci_dev *pdev, int mode);
 u16 pcie_tph_get_st_table_size(struct pci_dev *pdev);
 u32 pcie_tph_get_st_table_loc(struct pci_dev *pdev);
+u8 pcie_tph_get_st_modes(struct pci_dev *pdev);
 #else
 static inline int pcie_tph_set_st_entry(struct pci_dev *pdev,
 					unsigned int index, u16 tag)
@@ -41,6 +42,12 @@ static inline int pcie_tph_get_cpu_st(struct pci_dev *dev,
 static inline void pcie_disable_tph(struct pci_dev *pdev) { }
 static inline int pcie_enable_tph(struct pci_dev *pdev, int mode)
 { return -EINVAL; }
+static inline u16 pcie_tph_get_st_table_size(struct pci_dev *pdev)
+{ return 0; }
+static inline u32 pcie_tph_get_st_table_loc(struct pci_dev *pdev)
+{ return 0x7FF; /* Values that do not appear in normal case */ }
+static inline u8 pcie_tph_get_st_modes(struct pci_dev *pdev)
+{ return 0; }
 #endif
 
 #endif /* LINUX_PCI_TPH_H */
-- 
2.17.1

Re: [PATCH v2 RESEND 1/5] pci/tph: Export pcie_tph_get_st_modes() for external use

[Bjorn Helgaas]

On Thu, Apr 16, 2026 at 05:30:37PM +0800, Chengwen Feng wrote:
> Export the helper to retrieve supported PCIe TPH steering tag modes so
> that drivers like VFIO can query and expose device capabilities to
> userspace.
> 
> And also add pcie_tph_get_st_table_size() and
> pcie_tph_get_st_table_loc() stub implementation in the !CONFIG_PCI_TPH
> case.
> 
> Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>

Update subject to "PCI/TPH: Export ..." to match history.

Acked-by: Bjorn Helgaas <bhelgaas@google.com>

I notice commit logs of other patches could be rewrapped to fill 75
columns.

> ---
>  drivers/pci/tph.c       | 13 +++++++++++--
>  include/linux/pci-tph.h |  7 +++++++
>  2 files changed, 18 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/pci/tph.c b/drivers/pci/tph.c
> index 91145e8d9d95..f8767bf6fee9 100644
> --- a/drivers/pci/tph.c
> +++ b/drivers/pci/tph.c
> @@ -145,7 +145,15 @@ static void set_ctrl_reg_req_en(struct pci_dev *pdev, u8 req_type)
>  	pci_write_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, reg);
>  }
>  
> -static u8 get_st_modes(struct pci_dev *pdev)
> +/**
> + * pcie_tph_get_st_modes - Get supported Steering Tag modes
> + * @pdev: PCI device to query
> + *
> + * Return:
> + *  Bitmask of supported ST modes (PCI_TPH_CAP_ST_NS, PCI_TPH_CAP_ST_IV,
> + *                                 PCI_TPH_CAP_ST_DS)
> + */
> +u8 pcie_tph_get_st_modes(struct pci_dev *pdev)
>  {
>  	u32 reg;
>  
> @@ -154,6 +162,7 @@ static u8 get_st_modes(struct pci_dev *pdev)
>  
>  	return reg;
>  }
> +EXPORT_SYMBOL(pcie_tph_get_st_modes);
>  
>  /**
>   * pcie_tph_get_st_table_loc - Return the device's ST table location
> @@ -400,7 +409,7 @@ int pcie_enable_tph(struct pci_dev *pdev, int mode)
>  
>  	/* Sanitize and check ST mode compatibility */
>  	mode &= PCI_TPH_CTRL_MODE_SEL_MASK;
> -	dev_modes = get_st_modes(pdev);
> +	dev_modes = pcie_tph_get_st_modes(pdev);
>  	if (!((1 << mode) & dev_modes))
>  		return -EINVAL;
>  
> diff --git a/include/linux/pci-tph.h b/include/linux/pci-tph.h
> index be68cd17f2f8..586c75b19e01 100644
> --- a/include/linux/pci-tph.h
> +++ b/include/linux/pci-tph.h
> @@ -30,6 +30,7 @@ void pcie_disable_tph(struct pci_dev *pdev);
>  int pcie_enable_tph(struct pci_dev *pdev, int mode);
>  u16 pcie_tph_get_st_table_size(struct pci_dev *pdev);
>  u32 pcie_tph_get_st_table_loc(struct pci_dev *pdev);
> +u8 pcie_tph_get_st_modes(struct pci_dev *pdev);
>  #else
>  static inline int pcie_tph_set_st_entry(struct pci_dev *pdev,
>  					unsigned int index, u16 tag)
> @@ -41,6 +42,12 @@ static inline int pcie_tph_get_cpu_st(struct pci_dev *dev,
>  static inline void pcie_disable_tph(struct pci_dev *pdev) { }
>  static inline int pcie_enable_tph(struct pci_dev *pdev, int mode)
>  { return -EINVAL; }
> +static inline u16 pcie_tph_get_st_table_size(struct pci_dev *pdev)
> +{ return 0; }
> +static inline u32 pcie_tph_get_st_table_loc(struct pci_dev *pdev)
> +{ return 0x7FF; /* Values that do not appear in normal case */ }
> +static inline u8 pcie_tph_get_st_modes(struct pci_dev *pdev)
> +{ return 0; }
>  #endif
>  
>  #endif /* LINUX_PCI_TPH_H */
> -- 
> 2.17.1
> 

Re: [PATCH v2 RESEND 1/5] pci/tph: Export pcie_tph_get_st_modes() for external use

[fengchengwen]

On 4/17/2026 4:49 AM, Bjorn Helgaas wrote:
> On Thu, Apr 16, 2026 at 05:30:37PM +0800, Chengwen Feng wrote:
>> Export the helper to retrieve supported PCIe TPH steering tag modes so
>> that drivers like VFIO can query and expose device capabilities to
>> userspace.
>>
>> And also add pcie_tph_get_st_table_size() and
>> pcie_tph_get_st_table_loc() stub implementation in the !CONFIG_PCI_TPH
>> case.
>>
>> Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
> Update subject to "PCI/TPH: Export ..." to match history.
> 
> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
> 
> I notice commit logs of other patches could be rewrapped to fill 75
> columns.

Hi Bjorn,

Thank you for the review and the Ack!

I'll fix the subject to "PCI/TPH: Export ..." and rewrap the commit
messages to 75 columns in the next revision.

Thanks

[PATCH v2 RESEND 2/5] vfio/pci: Add PCIe TPH interface with capability query

[Chengwen Feng]

Add the VFIO_DEVICE_PCI_TPH IOCTL and implement the basic
capability query operation to let userspace discover device
TPH support, supported modes and ST table information.

Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
---
 drivers/vfio/pci/vfio_pci_core.c |  50 ++++++++++++
 include/uapi/linux/vfio.h        | 131 +++++++++++++++++++++++++++++++
 2 files changed, 181 insertions(+)

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 3fea064d00de..fc82ab845737 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -29,6 +29,7 @@
 #include <linux/sched/mm.h>
 #include <linux/iommufd.h>
 #include <linux/pci-p2pdma.h>
+#include <linux/pci-tph.h>
 #if IS_ENABLED(CONFIG_EEH)
 #include <asm/eeh.h>
 #endif
@@ -1461,6 +1462,53 @@ static int vfio_pci_ioctl_ioeventfd(struct vfio_pci_core_device *vdev,
 				  ioeventfd.fd);
 }
 
+static int vfio_pci_tph_get_cap(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_cap cap = {0};
+
+	if (mode == 0 || mode == PCI_TPH_CAP_ST_NS)
+		return -EOPNOTSUPP;
+
+	if (mode & PCI_TPH_CAP_ST_IV)
+		cap.supported_modes |= VFIO_PCI_TPH_MODE_IV;
+	if (mode & PCI_TPH_CAP_ST_DS)
+		cap.supported_modes |= VFIO_PCI_TPH_MODE_DS;
+
+	if (pcie_tph_get_st_table_loc(pdev) != PCI_TPH_LOC_NONE)
+		cap.st_table_sz = pcie_tph_get_st_table_size(pdev);
+
+	if (copy_to_user(uarg, &cap, sizeof(cap)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int vfio_pci_ioctl_tph(struct vfio_pci_core_device *vdev,
+			      void __user *uarg)
+{
+	struct vfio_device_pci_tph_op op;
+	size_t minsz;
+
+	if (copy_from_user(&op, uarg, sizeof(op.argsz) + sizeof(op.op)))
+		return -EFAULT;
+
+	minsz = offsetof(struct vfio_device_pci_tph_op, cap);
+	if (op.argsz < minsz)
+		return -EINVAL;
+
+	switch (op.op) {
+	case VFIO_PCI_TPH_GET_CAP:
+		return vfio_pci_tph_get_cap(vdev, &op, uarg + minsz);
+	default:
+		/* Other ops are not implemented yet */
+		return -EINVAL;
+	}
+}
+
 long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd,
 			 unsigned long arg)
 {
@@ -1483,6 +1531,8 @@ long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd,
 		return vfio_pci_ioctl_reset(vdev, uarg);
 	case VFIO_DEVICE_SET_IRQS:
 		return vfio_pci_ioctl_set_irqs(vdev, uarg);
+	case VFIO_DEVICE_PCI_TPH:
+		return vfio_pci_ioctl_tph(vdev, uarg);
 	default:
 		return -ENOTTY;
 	}
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index bb7b89330d35..6a748d3dbb88 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -1307,6 +1307,137 @@ struct vfio_precopy_info {
 
 #define VFIO_MIG_GET_PRECOPY_INFO _IO(VFIO_TYPE, VFIO_BASE + 21)
 
+/**
+ * struct vfio_pci_tph_cap - PCIe TPH capability information
+ * @supported_modes: Supported TPH operating modes
+ * @st_table_sz: Number of entries in ST table; 0 means no ST table
+ * @reserved: Must be zero
+ *
+ * Used with VFIO_PCI_TPH_GET_CAP operation to return device
+ * TLP Processing Hints (TPH) capabilities to userspace.
+ */
+struct vfio_pci_tph_cap {
+	__u8  supported_modes;
+#define VFIO_PCI_TPH_MODE_IV	(1u << 0) /* Interrupt vector */
+#define VFIO_PCI_TPH_MODE_DS	(1u << 1) /* Device specific */
+	__u8  reserved0;
+	__u16 st_table_sz;
+	__u32 reserved;
+};
+
+/**
+ * struct vfio_pci_tph_ctrl - TPH enable control structure
+ * @mode: Selected TPH operating mode (VFIO_PCI_TPH_MODE_*)
+ * @reserved: Must be zero
+ *
+ * Used with VFIO_PCI_TPH_ENABLE operation to specify the
+ * operating mode when enabling TPH on the device.
+ */
+struct vfio_pci_tph_ctrl {
+	__u8 mode;
+	__u8 reserved[7];
+};
+
+/**
+ * struct vfio_pci_tph_entry - Single TPH steering tag entry
+ * @cpu: CPU identifier for steering tag calculation
+ * @mem_type: Memory type (VFIO_PCI_TPH_MEM_TYPE_*)
+ * @reserved0: Must be zero
+ * @index: ST table index for programming
+ * @st: Unused for SET_ST
+ * @reserved1: Must be zero
+ *
+ * For VFIO_PCI_TPH_GET_ST:
+ *   Userspace sets @cpu and @mem_type; kernel returns @st.
+ *
+ * For VFIO_PCI_TPH_SET_ST:
+ *   Userspace sets @index, @cpu, and @mem_type.
+ *   Kernel internally computes the steering tag and programs
+ *   it into the specified @index.
+ *
+ *   If @cpu == U32_MAX, kernel clears the steering tag at
+ *   the specified @index.
+ */
+struct vfio_pci_tph_entry {
+	__u32 cpu;
+	__u8  mem_type;
+#define VFIO_PCI_TPH_MEM_TYPE_VM	0
+#define VFIO_PCI_TPH_MEM_TYPE_PM	1
+	__u8  reserved0;
+	__u16 index;
+	__u16 st;
+	__u16 reserved1;
+};
+
+/**
+ * struct vfio_pci_tph_st - Batch steering tag request
+ * @count: Number of entries in the array
+ * @reserved: Must be zero
+ * @ents: Flexible array of steering tag entries
+ *
+ * Container structure for batch get/set operations.
+ * Used with both VFIO_PCI_TPH_GET_ST and VFIO_PCI_TPH_SET_ST.
+ */
+struct vfio_pci_tph_st {
+	__u32 count;
+	__u32 reserved;
+	struct vfio_pci_tph_entry ents[];
+#define VFIO_PCI_TPH_MAX_ENTRIES    2048
+};
+
+/**
+ * struct vfio_device_pci_tph_op - Argument for VFIO_DEVICE_PCI_TPH
+ * @argsz: User allocated size of this structure
+ * @op: TPH operation (VFIO_PCI_TPH_*)
+ * @cap: Capability data for GET_CAP
+ * @ctrl: Control data for ENABLE
+ * @st: Batch entry data for GET_ST/SET_ST
+ *
+ * @argsz must be set by the user to the size of the structure
+ * being executed. Kernel validates input and returns data
+ * only within the specified size.
+ *
+ * Operations:
+ * - VFIO_PCI_TPH_GET_CAP: Query device TPH capabilities.
+ * - VFIO_PCI_TPH_ENABLE:  Enable TPH using mode from &ctrl.
+ * - VFIO_PCI_TPH_DISABLE: Disable TPH on the device.
+ * - VFIO_PCI_TPH_GET_ST:  Retrieve CPU's steering tags.
+ *                         Valid only for Device-Specific mode and
+ *                         no ST table is present.
+ * - VFIO_PCI_TPH_SET_ST:  Program steering tags into device table.
+ *                         If any entry fails, previously programmed entries
+ *                         are rolled back to 0 before returning error.
+ */
+struct vfio_device_pci_tph_op {
+	__u32 argsz;
+	__u32 op;
+#define VFIO_PCI_TPH_GET_CAP	0
+#define VFIO_PCI_TPH_ENABLE	1
+#define VFIO_PCI_TPH_DISABLE	2
+#define VFIO_PCI_TPH_GET_ST	3
+#define VFIO_PCI_TPH_SET_ST	4
+	union {
+		struct vfio_pci_tph_cap cap;
+		struct vfio_pci_tph_ctrl ctrl;
+		struct vfio_pci_tph_st st;
+	};
+};
+
+/**
+ * VFIO_DEVICE_PCI_TPH - _IO(VFIO_TYPE, VFIO_BASE + 22)
+ *
+ * IOCTL for managing PCIe TLP Processing Hints (TPH) on
+ * a VFIO-assigned PCI device. Provides operations to query
+ * device capabilities, enable/disable TPH, retrieve CPU's
+ * steering tags, and program steering tag tables.
+ *
+ * Return: 0 on success, negative errno on failure.
+ *         -EOPNOTSUPP: Operation not supported
+ *         -ENODEV: Device or required functionality not present
+ *         -EINVAL: Invalid argument or TPH not supported
+ */
+#define VFIO_DEVICE_PCI_TPH	_IO(VFIO_TYPE, VFIO_BASE + 22)
+
 /*
  * Upon VFIO_DEVICE_FEATURE_SET, allow the device to be moved into a low power
  * state with the platform-based power management.  Device use of lower power
-- 
2.17.1

[PATCH v2 RESEND 3/5] vfio/pci: Add PCIe TPH enable/disable support

[Chengwen Feng]

Add support to enable and disable TPH function with
mode selection.

Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
---
 drivers/vfio/pci/vfio_pci_core.c | 36 ++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index fc82ab845737..22c16662f533 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1487,6 +1487,38 @@ static int vfio_pci_tph_get_cap(struct vfio_pci_core_device *vdev,
 	return 0;
 }
 
+static int vfio_pci_tph_enable(struct vfio_pci_core_device *vdev,
+			      struct vfio_device_pci_tph_op *op,
+			      void __user *uarg)
+{
+	struct vfio_pci_tph_ctrl ctrl;
+	int mode;
+
+	if (op->argsz < offsetofend(struct vfio_device_pci_tph_op, ctrl))
+		return -EINVAL;
+
+	if (copy_from_user(&ctrl, uarg, sizeof(ctrl)))
+		return -EFAULT;
+
+	if (ctrl.mode != VFIO_PCI_TPH_MODE_IV &&
+	    ctrl.mode != VFIO_PCI_TPH_MODE_DS)
+		return -EINVAL;
+
+	/* Reserved must be zero */
+	if (memchr_inv(ctrl.reserved, 0, sizeof(ctrl.reserved)))
+		return -EINVAL;
+
+	mode = (ctrl.mode == VFIO_PCI_TPH_MODE_IV) ? PCI_TPH_ST_IV_MODE :
+						     PCI_TPH_ST_DS_MODE;
+	return pcie_enable_tph(vdev->pdev, mode);
+}
+
+static int vfio_pci_tph_disable(struct vfio_pci_core_device *vdev)
+{
+	pcie_disable_tph(vdev->pdev);
+	return 0;
+}
+
 static int vfio_pci_ioctl_tph(struct vfio_pci_core_device *vdev,
 			      void __user *uarg)
 {
@@ -1503,6 +1535,10 @@ static int vfio_pci_ioctl_tph(struct vfio_pci_core_device *vdev,
 	switch (op.op) {
 	case VFIO_PCI_TPH_GET_CAP:
 		return vfio_pci_tph_get_cap(vdev, &op, uarg + minsz);
+	case VFIO_PCI_TPH_ENABLE:
+		return vfio_pci_tph_enable(vdev, &op, uarg + minsz);
+	case VFIO_PCI_TPH_DISABLE:
+		return vfio_pci_tph_disable(vdev);
 	default:
 		/* Other ops are not implemented yet */
 		return -EINVAL;
-- 
2.17.1

[PATCH v2 RESEND 4/5] vfio/pci: Add PCIe TPH GET_ST interface

[Chengwen Feng]

Add support to batch get CPU's Steering Tags. This interface is only
valid for Device-Specific mode when the device does not implement an ST
table.

Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
---
 drivers/vfio/pci/vfio_pci_core.c | 56 ++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 22c16662f533..a036e7d795be 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1519,6 +1519,60 @@ 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;
+	struct vfio_pci_tph_entry *ents;
+	struct vfio_pci_tph_st st;
+	enum tph_mem_type mtype;
+	size_t size;
+	int i, err;
+
+	if (pcie_tph_get_st_table_loc(pdev) != PCI_TPH_LOC_NONE)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&st, uarg, sizeof(st)))
+		return -EFAULT;
+
+	if (!st.count || st.count > VFIO_PCI_TPH_MAX_ENTRIES)
+		return -EINVAL;
+
+	size = st.count * sizeof(*ents);
+	ents = kvmalloc(size, GFP_KERNEL);
+	if (!ents)
+		return -ENOMEM;
+
+	if (copy_from_user(ents, uarg + sizeof(st), size)) {
+		err = -EFAULT;
+		goto out;
+	}
+
+	for (i = 0; i < st.count; i++) {
+		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 + sizeof(st), ents, size))
+		err = -EFAULT;
+
+out:
+	kvfree(ents);
+	return err;
+}
+
 static int vfio_pci_ioctl_tph(struct vfio_pci_core_device *vdev,
 			      void __user *uarg)
 {
@@ -1539,6 +1593,8 @@ 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

[PATCH v2 RESEND 5/5] vfio/pci: Add PCIe TPH SET_ST interface

[Chengwen Feng]

Add VFIO_PCI_TPH_SET_ST operation to support batch programming
of steering tag entries. If any entry fails, all previously
programmed entries are rolled back to 0 to avoid partial
device state.

Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
---
 drivers/vfio/pci/vfio_pci_core.c | 71 ++++++++++++++++++++++++++++++++
 1 file changed, 71 insertions(+)

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index a036e7d795be..35b8849ecf39 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1573,6 +1573,75 @@ static int vfio_pci_tph_get_st(struct vfio_pci_core_device *vdev,
 	return err;
 }
 
+static int vfio_pci_tph_set_st(struct vfio_pci_core_device *vdev,
+			       struct vfio_device_pci_tph_op *op,
+			       void __user *uarg)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	struct vfio_pci_tph_entry *ents;
+	struct vfio_pci_tph_st st;
+	enum tph_mem_type mtype;
+	int i = 0, j, err, size;
+	u32 tab_loc;
+	u16 st_val;
+
+	tab_loc = pcie_tph_get_st_table_loc(pdev);
+	if (tab_loc != PCI_TPH_LOC_CAP && tab_loc != PCI_TPH_LOC_MSIX)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&st, uarg, sizeof(st)))
+		return -EFAULT;
+
+	if (!st.count || st.count > VFIO_PCI_TPH_MAX_ENTRIES)
+		return -EINVAL;
+
+	size = st.count * sizeof(*ents);
+	ents = kvmalloc(size, GFP_KERNEL);
+	if (!ents)
+		return -ENOMEM;
+
+	if (copy_from_user(ents, uarg + sizeof(st), size)) {
+		err = -EFAULT;
+		goto out;
+	}
+
+	for (; i < st.count; i++) {
+		if (ents[i].cpu == U32_MAX) {
+			err = pcie_tph_set_st_entry(pdev, ents[i].index, 0);
+			if (err)
+				goto out;
+			continue;
+		}
+
+		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, &st_val);
+		if (err)
+			goto out;
+		err = pcie_tph_set_st_entry(pdev, ents[i].index, st_val);
+		if (err)
+			goto out;
+	}
+
+out:
+	if (err) {
+		/* Roll back previously programmed entries to 0 */
+		for (j = 0; j < i; j++) {
+			if (ents[j].cpu != U32_MAX)
+				pcie_tph_set_st_entry(pdev, ents[j].index, 0);
+		}
+	}
+	kvfree(ents);
+	return err;
+}
+
 static int vfio_pci_ioctl_tph(struct vfio_pci_core_device *vdev,
 			      void __user *uarg)
 {
@@ -1595,6 +1664,8 @@ static int vfio_pci_ioctl_tph(struct vfio_pci_core_device *vdev,
 		return vfio_pci_tph_disable(vdev);
 	case VFIO_PCI_TPH_GET_ST:
 		return vfio_pci_tph_get_st(vdev, &op, uarg + minsz);
+	case VFIO_PCI_TPH_SET_ST:
+		return vfio_pci_tph_set_st(vdev, &op, uarg + minsz);
 	default:
 		/* Other ops are not implemented yet */
 		return -EINVAL;
-- 
2.17.1