From: Chengwen Feng <fengchengwen@huawei.com>
To: <alex@shazbot.org>, <jgg@ziepe.ca>
Cc: <wathsala.vithanage@arm.com>, <helgaas@kernel.org>,
<wei.huang2@amd.com>, <wangzhou1@hisilicon.com>,
<wangyushan12@huawei.com>, <liuyonglong@huawei.com>,
<kvm@vger.kernel.org>, <linux-pci@vger.kernel.org>
Subject: [PATCH v8 4/7] vfio/pci: Add PCIe TPH interface with capability query
Date: Fri, 8 May 2026 14:40:50 +0800 [thread overview]
Message-ID: <20260508064053.37529-5-fengchengwen@huawei.com> (raw)
In-Reply-To: <20260508064053.37529-1-fengchengwen@huawei.com>
Add VFIO_DEVICE_PCI_TPH IOCTL to allow userspace to query device TPH
capabilities, supported modes, and steering tag table information.
Add module parameter 'enable_unsafe_tph_ds_mode' to restrict unsafe
device-specific TPH mode to trusted userspace only.
Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
---
drivers/vfio/pci/vfio_pci.c | 13 ++-
drivers/vfio/pci/vfio_pci_core.c | 56 ++++++++++++-
include/linux/vfio_pci_core.h | 3 +-
include/uapi/linux/vfio.h | 133 +++++++++++++++++++++++++++++++
4 files changed, 202 insertions(+), 3 deletions(-)
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 0c771064c0b8..40bf5aa9fd0b 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -60,6 +60,12 @@ static bool disable_denylist;
module_param(disable_denylist, bool, 0444);
MODULE_PARM_DESC(disable_denylist, "Disable use of device denylist. Disabling the denylist allows binding to devices with known errata that may lead to exploitable stability or security issues when accessed by untrusted users.");
+#ifdef CONFIG_PCIE_TPH
+static bool enable_unsafe_tph_ds_mode;
+module_param(enable_unsafe_tph_ds_mode, bool, 0444);
+MODULE_PARM_DESC(enable_unsafe_tph_ds_mode, "Enable UNSAFE TPH device-specific (DS) mode. This mode provides weak isolation, cannot be safely used for virtual machines. If you do not know what this is for, step away. (default: false)");
+#endif
+
static bool vfio_pci_dev_in_denylist(struct pci_dev *pdev)
{
switch (pdev->vendor) {
@@ -257,12 +263,17 @@ static int __init vfio_pci_init(void)
{
int ret;
bool is_disable_vga = true;
+ bool is_enable_unsafe_tph_ds_mode = false;
#ifdef CONFIG_VFIO_PCI_VGA
is_disable_vga = disable_vga;
#endif
+#ifdef CONFIG_PCIE_TPH
+ is_enable_unsafe_tph_ds_mode = enable_unsafe_tph_ds_mode;
+#endif
- vfio_pci_core_set_params(nointxmask, is_disable_vga, disable_idle_d3);
+ vfio_pci_core_set_params(nointxmask, is_disable_vga, disable_idle_d3,
+ is_enable_unsafe_tph_ds_mode);
/* Register and scan for devices */
ret = pci_register_driver(&vfio_pci_driver);
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 3f8d093aacf8..0e97b128fd63 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
@@ -41,6 +42,7 @@
static bool nointxmask;
static bool disable_vga;
static bool disable_idle_d3;
+static bool enable_unsafe_tph_ds_mode;
static void vfio_pci_eventfd_rcu_free(struct rcu_head *rcu)
{
@@ -1461,6 +1463,54 @@ 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;
+ struct vfio_pci_tph_cap cap = {0};
+ u8 mode;
+
+ if (op->argsz < offsetofend(struct vfio_device_pci_tph_op, cap))
+ return -EINVAL;
+
+ mode = pcie_tph_get_st_modes(pdev);
+ /* Hide unsafe device-specific (DS) mode by default */
+ if (!enable_unsafe_tph_ds_mode)
+ mode &= ~PCI_TPH_CAP_ST_DS;
+ 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;
+ 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 = {0};
+ size_t minsz = sizeof(op.argsz) + sizeof(op.op);
+
+ if (copy_from_user(&op, uarg, minsz))
+ return -EFAULT;
+
+ 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 +1533,8 @@ 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;
}
@@ -2570,11 +2622,13 @@ static void vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set)
}
void vfio_pci_core_set_params(bool is_nointxmask, bool is_disable_vga,
- bool is_disable_idle_d3)
+ bool is_disable_idle_d3,
+ bool is_enable_unsafe_tph_ds_mode)
{
nointxmask = is_nointxmask;
disable_vga = is_disable_vga;
disable_idle_d3 = is_disable_idle_d3;
+ enable_unsafe_tph_ds_mode = is_enable_unsafe_tph_ds_mode;
}
EXPORT_SYMBOL_GPL(vfio_pci_core_set_params);
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 2ebba746c18f..5af2a2e04ca7 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -157,7 +157,8 @@ int vfio_pci_core_register_dev_region(struct vfio_pci_core_device *vdev,
const struct vfio_pci_regops *ops,
size_t size, u32 flags, void *data);
void vfio_pci_core_set_params(bool nointxmask, bool is_disable_vga,
- bool is_disable_idle_d3);
+ bool is_disable_idle_d3,
+ bool is_enable_unsafe_tph_ds_mode);
void vfio_pci_core_close_device(struct vfio_device *core_vdev);
int vfio_pci_core_init_dev(struct vfio_device *core_vdev);
void vfio_pci_core_release_dev(struct vfio_device *core_vdev);
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 5de618a3a5ee..81da2bd0c21b 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -1321,6 +1321,139 @@ 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 steering tags for Device-Specific (DS)
+ * mode. Used when device requires SW to obtain ST
+ * values for programming.
+ * - VFIO_PCI_TPH_SET_ST: Program steering tag entries into device ST table.
+ * Valid when ST table resides in TPH Requester
+ * Capability or MSI-X Table.
+ * If any entry fails, all 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
next prev parent reply other threads:[~2026-05-08 6:41 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-08 6:40 [PATCH v8 0/7] vfio/pci: Add PCIe TPH support Chengwen Feng
2026-05-08 6:40 ` [PATCH v8 1/7] PCI/TPH: Fix pcie_tph_get_st_table_loc() field extraction Chengwen Feng
2026-05-08 6:40 ` [PATCH v8 2/7] PCI/TPH: Export pcie_tph_get_st_modes() for external use Chengwen Feng
2026-05-08 19:02 ` sashiko-bot
2026-05-08 6:40 ` [PATCH v8 3/7] PCI/TPH: Fix pcie_tph_get_st_table_size() for MSI-X table location Chengwen Feng
2026-05-08 19:31 ` sashiko-bot
2026-05-08 6:40 ` Chengwen Feng [this message]
2026-05-08 20:03 ` [PATCH v8 4/7] vfio/pci: Add PCIe TPH interface with capability query sashiko-bot
2026-05-08 22:40 ` Alex Williamson
2026-05-09 3:28 ` fengchengwen
2026-05-11 4:36 ` Alex Williamson
2026-05-08 6:40 ` [PATCH v8 5/7] vfio/pci: Add PCIe TPH enable/disable support Chengwen Feng
2026-05-08 20:46 ` sashiko-bot
2026-05-08 6:40 ` [PATCH v8 6/7] vfio/pci: Add PCIe TPH GET_ST interface Chengwen Feng
2026-05-08 6:40 ` [PATCH v8 7/7] vfio/pci: Add PCIe TPH SET_ST interface Chengwen Feng
2026-05-08 21:49 ` sashiko-bot
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260508064053.37529-5-fengchengwen@huawei.com \
--to=fengchengwen@huawei.com \
--cc=alex@shazbot.org \
--cc=helgaas@kernel.org \
--cc=jgg@ziepe.ca \
--cc=kvm@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=liuyonglong@huawei.com \
--cc=wangyushan12@huawei.com \
--cc=wangzhou1@hisilicon.com \
--cc=wathsala.vithanage@arm.com \
--cc=wei.huang2@amd.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox