PCI: Add TLP Processing Hints (TPH) support

Add support for PCIe TLP Processing Hints (TPH) support (see PCIe r6.2,
sec 6.17).

Add TPH register definitions in pci_regs.h, including the TPH Requester
capability register, TPH Requester control register, TPH Completer
capability, and the ST fields of MSI-X entry.

Introduce pcie_enable_tph() and pcie_disable_tph(), enabling drivers to
toggle TPH support and configure specific ST mode as needed. Also add a new
kernel parameter, "pci=notph", allowing users to disable TPH support across
the entire system.

Link: https://lore.kernel.org/r/[e-mail]
Co-developed-by: Jing Liu <[e-mail]>
Co-developed-by: Paul Luse <[e-mail]>
Co-developed-by: Eric Van Tassell <[e-mail]>
Signed-off-by: Jing Liu <[e-mail]>
Signed-off-by: Paul Luse <[e-mail]>
Signed-off-by: Eric Van Tassell <[e-mail]>
Signed-off-by: Wei Huang <[e-mail]>
Signed-off-by: Bjorn Helgaas <[e-mail]>
Reviewed-by: Ajit Khaparde <[e-mail]>
Reviewed-by: Somnath Kotur <[e-mail]>
Reviewed-by: Andy Gospodarek <[e-mail]>
Reviewed-by: Jonathan Cameron <[e-mail]>
Reviewed-by: Lukas Wunner <[e-mail]>

Documentation/admin-guide/kernel-parameters.txt

···
 		nomio		[S390] Do not use MIO instructions.
 		norid		[S390] ignore the RID field and force use of
 				one PCI domain per PCI function
+		notph		[PCIE] If the PCIE_TPH kernel config parameter
+				is enabled, this kernel boot option can be used
+				to disable PCIe TLP Processing Hints support
+				system-wide.
 
 	pcie_aspm=	[PCIE] Forcibly enable or ignore PCIe Active State Power
 			Management.

drivers/pci/Kconfig

···
 
 	  If unsure, say N.
 
+config PCIE_TPH
+	bool "TLP Processing Hints"
+	help
+	  This option adds support for PCIe TLP Processing Hints (TPH).
+	  TPH allows endpoint devices to provide optimization hints, such as
+	  desired caching behavior, for requests that target memory space.
+	  These hints, called Steering Tags, can empower the system hardware
+	  to optimize the utilization of platform resources.
+
 config PCI_P2PDMA
 	bool "PCI peer-to-peer transfer support"
 	depends on ZONE_DEVICE

drivers/pci/Makefile

···
 obj-$(CONFIG_PCI_DOE)		+= doe.o
 obj-$(CONFIG_PCI_DYNAMIC_OF_NODES) += of_property.o
 obj-$(CONFIG_PCI_NPEM)		+= npem.o
+obj-$(CONFIG_PCIE_TPH)		+= tph.o
 
 # Endpoint library must be initialized before its users
 obj-$(CONFIG_PCI_ENDPOINT)	+= endpoint/

drivers/pci/pci.c

···
 	pci_save_dpc_state(dev);
 	pci_save_aer_state(dev);
 	pci_save_ptm_state(dev);
+	pci_save_tph_state(dev);
 	return pci_save_vc_state(dev);
 }
 EXPORT_SYMBOL(pci_save_state);
···
 	pci_restore_rebar_state(dev);
 	pci_restore_dpc_state(dev);
 	pci_restore_ptm_state(dev);
+	pci_restore_tph_state(dev);
 
 	pci_aer_clear_status(dev);
 	pci_restore_aer_state(dev);
···
 				pci_no_domains();
 			} else if (!strncmp(str, "noari", 5)) {
 				pcie_ari_disabled = true;
+			} else if (!strncmp(str, "notph", 5)) {
+				pci_no_tph();
 			} else if (!strncmp(str, "cbiosize=", 9)) {
 				pci_cardbus_io_size = memparse(str + 9, &str);
 			} else if (!strncmp(str, "cbmemsize=", 10)) {

drivers/pci/pci.h

···
 
 #endif /* CONFIG_PCI_IOV */
 
+#ifdef CONFIG_PCIE_TPH
+void pci_restore_tph_state(struct pci_dev *dev);
+void pci_save_tph_state(struct pci_dev *dev);
+void pci_no_tph(void);
+void pci_tph_init(struct pci_dev *dev);
+#else
+static inline void pci_restore_tph_state(struct pci_dev *dev) { }
+static inline void pci_save_tph_state(struct pci_dev *dev) { }
+static inline void pci_no_tph(void) { }
+static inline void pci_tph_init(struct pci_dev *dev) { }
+#endif
+
 #ifdef CONFIG_PCIE_PTM
 void pci_ptm_init(struct pci_dev *dev);
 void pci_save_ptm_state(struct pci_dev *dev);

drivers/pci/probe.c

···
 	pci_dpc_init(dev);		/* Downstream Port Containment */
 	pci_rcec_init(dev);		/* Root Complex Event Collector */
 	pci_doe_init(dev);		/* Data Object Exchange */
+	pci_tph_init(dev);		/* TLP Processing Hints */
 
 	pcie_report_downtraining(dev);
 	pci_init_reset_methods(dev);

drivers/pci/tph.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * TPH (TLP Processing Hints) support
+ *
+ * Copyright (C) 2024 Advanced Micro Devices, Inc.
+ *     Eric Van Tassell <[e-mail]>
+ *     Wei Huang <[e-mail]>
+ */
+#include <linux/pci.h>
+#include <linux/bitfield.h>
+#include <linux/pci-tph.h>
+
+#include "pci.h"
+
+/* System-wide TPH disabled */
+static bool pci_tph_disabled;
+
+static u8 get_st_modes(struct pci_dev *pdev)
+{
+	u32 reg;
+
+	pci_read_config_dword(pdev, pdev->tph_cap + PCI_TPH_CAP, &reg);
+	reg &= PCI_TPH_CAP_ST_NS | PCI_TPH_CAP_ST_IV | PCI_TPH_CAP_ST_DS;
+
+	return reg;
+}
+
+/* Return device's Root Port completer capability */
+static u8 get_rp_completer_type(struct pci_dev *pdev)
+{
+	struct pci_dev *rp;
+	u32 reg;
+	int ret;
+
+	rp = pcie_find_root_port(pdev);
+	if (!rp)
+		return 0;
+
+	ret = pcie_capability_read_dword(rp, PCI_EXP_DEVCAP2, &reg);
+	if (ret)
+		return 0;
+
+	return FIELD_GET(PCI_EXP_DEVCAP2_TPH_COMP_MASK, reg);
+}
+
+/**
+ * pcie_disable_tph - Turn off TPH support for device
+ * @pdev: PCI device
+ *
+ * Return: none
+ */
+void pcie_disable_tph(struct pci_dev *pdev)
+{
+	if (!pdev->tph_cap)
+		return;
+
+	if (!pdev->tph_enabled)
+		return;
+
+	pci_write_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, 0);
+
+	pdev->tph_mode = 0;
+	pdev->tph_req_type = 0;
+	pdev->tph_enabled = 0;
+}
+EXPORT_SYMBOL(pcie_disable_tph);
+
+/**
+ * pcie_enable_tph - Enable TPH support for device using a specific ST mode
+ * @pdev: PCI device
+ * @mode: ST mode to enable. Current supported modes include:
+ *
+ *   - PCI_TPH_ST_NS_MODE: NO ST Mode
+ *   - PCI_TPH_ST_IV_MODE: Interrupt Vector Mode
+ *   - PCI_TPH_ST_DS_MODE: Device Specific Mode
+ *
+ * Check whether the mode is actually supported by the device before enabling
+ * and return an error if not. Additionally determine what types of requests,
+ * TPH or extended TPH, can be issued by the device based on its TPH requester
+ * capability and the Root Port's completer capability.
+ *
+ * Return: 0 on success, otherwise negative value (-errno)
+ */
+int pcie_enable_tph(struct pci_dev *pdev, int mode)
+{
+	u32 reg;
+	u8 dev_modes;
+	u8 rp_req_type;
+
+	/* Honor "notph" kernel parameter */
+	if (pci_tph_disabled)
+		return -EINVAL;
+
+	if (!pdev->tph_cap)
+		return -EINVAL;
+
+	if (pdev->tph_enabled)
+		return -EBUSY;
+
+	/* Sanitize and check ST mode compatibility */
+	mode &= PCI_TPH_CTRL_MODE_SEL_MASK;
+	dev_modes = get_st_modes(pdev);
+	if (!((1 << mode) & dev_modes))
+		return -EINVAL;
+
+	pdev->tph_mode = mode;
+
+	/* Get req_type supported by device and its Root Port */
+	pci_read_config_dword(pdev, pdev->tph_cap + PCI_TPH_CAP, &reg);
+	if (FIELD_GET(PCI_TPH_CAP_EXT_TPH, reg))
+		pdev->tph_req_type = PCI_TPH_REQ_EXT_TPH;
+	else
+		pdev->tph_req_type = PCI_TPH_REQ_TPH_ONLY;
+
+	rp_req_type = get_rp_completer_type(pdev);
+
+	/* Final req_type is the smallest value of two */
+	pdev->tph_req_type = min(pdev->tph_req_type, rp_req_type);
+
+	if (pdev->tph_req_type == PCI_TPH_REQ_DISABLE)
+		return -EINVAL;
+
+	/* Write them into TPH control register */
+	pci_read_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, &reg);
+
+	reg &= ~PCI_TPH_CTRL_MODE_SEL_MASK;
+	reg |= FIELD_PREP(PCI_TPH_CTRL_MODE_SEL_MASK, pdev->tph_mode);
+
+	reg &= ~PCI_TPH_CTRL_REQ_EN_MASK;
+	reg |= FIELD_PREP(PCI_TPH_CTRL_REQ_EN_MASK, pdev->tph_req_type);
+
+	pci_write_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, reg);
+
+	pdev->tph_enabled = 1;
+
+	return 0;
+}
+EXPORT_SYMBOL(pcie_enable_tph);
+
+void pci_restore_tph_state(struct pci_dev *pdev)
+{
+	struct pci_cap_saved_state *save_state;
+	u32 *cap;
+
+	if (!pdev->tph_cap)
+		return;
+
+	if (!pdev->tph_enabled)
+		return;
+
+	save_state = pci_find_saved_ext_cap(pdev, PCI_EXT_CAP_ID_TPH);
+	if (!save_state)
+		return;
+
+	/* Restore control register and all ST entries */
+	cap = &save_state->cap.data[0];
+	pci_write_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, *cap++);
+}
+
+void pci_save_tph_state(struct pci_dev *pdev)
+{
+	struct pci_cap_saved_state *save_state;
+	u32 *cap;
+
+	if (!pdev->tph_cap)
+		return;
+
+	if (!pdev->tph_enabled)
+		return;
+
+	save_state = pci_find_saved_ext_cap(pdev, PCI_EXT_CAP_ID_TPH);
+	if (!save_state)
+		return;
+
+	/* Save control register */
+	cap = &save_state->cap.data[0];
+	pci_read_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, cap++);
+}
+
+void pci_no_tph(void)
+{
+	pci_tph_disabled = true;
+
+	pr_info("PCIe TPH is disabled\n");
+}
+
+void pci_tph_init(struct pci_dev *pdev)
+{
+	u32 save_size;
+
+	pdev->tph_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_TPH);
+	if (!pdev->tph_cap)
+		return;
+
+	save_size = sizeof(u32);
+	pci_add_ext_cap_save_buffer(pdev, PCI_EXT_CAP_ID_TPH, save_size);
+}

include/linux/pci-tph.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * TPH (TLP Processing Hints)
+ *
+ * Copyright (C) 2024 Advanced Micro Devices, Inc.
+ *     Eric Van Tassell <[e-mail]>
+ *     Wei Huang <[e-mail]>
+ */
+#ifndef LINUX_PCI_TPH_H
+#define LINUX_PCI_TPH_H
+
+#ifdef CONFIG_PCIE_TPH
+void pcie_disable_tph(struct pci_dev *pdev);
+int pcie_enable_tph(struct pci_dev *pdev, int mode);
+#else
+static inline void pcie_disable_tph(struct pci_dev *pdev) { }
+static inline int pcie_enable_tph(struct pci_dev *pdev, int mode)
+{ return -EINVAL; }
+#endif
+
+#endif /* LINUX_PCI_TPH_H */

include/linux/pci.h

···
 	unsigned int	ats_enabled:1;		/* Address Translation Svc */
 	unsigned int	pasid_enabled:1;	/* Process Address Space ID */
 	unsigned int	pri_enabled:1;		/* Page Request Interface */
+	unsigned int	tph_enabled:1;		/* TLP Processing Hints */
 	unsigned int	is_managed:1;		/* Managed via devres */
 	unsigned int	is_msi_managed:1;	/* MSI release via devres installed */
 	unsigned int	needs_freset:1;		/* Requires fundamental reset */
···
 
 	/* These methods index pci_reset_fn_methods[] */
 	u8 reset_methods[PCI_NUM_RESET_METHODS]; /* In priority order */
+
+#ifdef CONFIG_PCIE_TPH
+	u16		tph_cap;	/* TPH capability offset */
+	u8		tph_mode;	/* TPH mode */
+	u8		tph_req_type;	/* TPH requester type */
+#endif
 };
 
 static inline struct pci_dev *pci_physfn(struct pci_dev *dev)

include/uapi/linux/pci_regs.h

···
 #define PCI_MSIX_ENTRY_UPPER_ADDR	0x4  /* Message Upper Address */
 #define PCI_MSIX_ENTRY_DATA		0x8  /* Message Data */
 #define PCI_MSIX_ENTRY_VECTOR_CTRL	0xc  /* Vector Control */
-#define  PCI_MSIX_ENTRY_CTRL_MASKBIT	0x00000001
+#define  PCI_MSIX_ENTRY_CTRL_MASKBIT	0x00000001  /* Mask Bit */
+#define  PCI_MSIX_ENTRY_CTRL_ST		0xffff0000  /* Steering Tag */
 
 /* CompactPCI Hotswap Register */
 
···
 #define  PCI_EXP_DEVCAP2_ATOMIC_COMP64	0x00000100 /* 64b AtomicOp completion */
 #define  PCI_EXP_DEVCAP2_ATOMIC_COMP128	0x00000200 /* 128b AtomicOp completion */
 #define  PCI_EXP_DEVCAP2_LTR		0x00000800 /* Latency tolerance reporting */
+#define  PCI_EXP_DEVCAP2_TPH_COMP_MASK	0x00003000 /* TPH completer support */
 #define  PCI_EXP_DEVCAP2_OBFF_MASK	0x000c0000 /* OBFF support mechanism */
 #define  PCI_EXP_DEVCAP2_OBFF_MSG	0x00040000 /* New message signaling */
 #define  PCI_EXP_DEVCAP2_OBFF_WAKE	0x00080000 /* Re-use WAKE# for OBFF */
···
 #define  PCI_DPA_CAP_SUBSTATE_MASK	0x1F	/* # substates - 1 */
 #define PCI_DPA_BASE_SIZEOF	16	/* size with 0 substates */
 
+/* TPH Completer Support */
+#define PCI_EXP_DEVCAP2_TPH_COMP_NONE		0x0 /* None */
+#define PCI_EXP_DEVCAP2_TPH_COMP_TPH_ONLY	0x1 /* TPH only */
+#define PCI_EXP_DEVCAP2_TPH_COMP_EXT_TPH	0x3 /* TPH and Extended TPH */
+
 /* TPH Requester */
 #define PCI_TPH_CAP		4	/* capability register */
-#define  PCI_TPH_CAP_LOC_MASK	0x600	/* location mask */
-#define   PCI_TPH_LOC_NONE	0x000	/* no location */
-#define   PCI_TPH_LOC_CAP	0x200	/* in capability */
-#define   PCI_TPH_LOC_MSIX	0x400	/* in MSI-X */
-#define PCI_TPH_CAP_ST_MASK	0x07FF0000	/* ST table mask */
-#define PCI_TPH_CAP_ST_SHIFT	16	/* ST table shift */
-#define PCI_TPH_BASE_SIZEOF	0xc	/* size with no ST table */
+#define  PCI_TPH_CAP_ST_NS	0x00000001 /* No ST Mode Supported */
+#define  PCI_TPH_CAP_ST_IV	0x00000002 /* Interrupt Vector Mode Supported */
+#define  PCI_TPH_CAP_ST_DS	0x00000004 /* Device Specific Mode Supported */
+#define  PCI_TPH_CAP_EXT_TPH	0x00000100 /* Ext TPH Requester Supported */
+#define  PCI_TPH_CAP_LOC_MASK	0x00000600 /* ST Table Location */
+#define   PCI_TPH_LOC_NONE	0x00000000 /* Not present */
+#define   PCI_TPH_LOC_CAP	0x00000200 /* In capability */
+#define   PCI_TPH_LOC_MSIX	0x00000400 /* In MSI-X */
+#define  PCI_TPH_CAP_ST_MASK	0x07FF0000 /* ST Table Size */
+#define  PCI_TPH_CAP_ST_SHIFT	16	/* ST Table Size shift */
+#define PCI_TPH_BASE_SIZEOF	0xc	/* Size with no ST table */
+
+#define PCI_TPH_CTRL		8	/* control register */
+#define  PCI_TPH_CTRL_MODE_SEL_MASK	0x00000007 /* ST Mode Select */
+#define   PCI_TPH_ST_NS_MODE		0x0 /* No ST Mode */
+#define   PCI_TPH_ST_IV_MODE		0x1 /* Interrupt Vector Mode */
+#define   PCI_TPH_ST_DS_MODE		0x2 /* Device Specific Mode */
+#define  PCI_TPH_CTRL_REQ_EN_MASK	0x00000300 /* TPH Requester Enable */
+#define   PCI_TPH_REQ_DISABLE		0x0 /* No TPH requests allowed */
+#define   PCI_TPH_REQ_TPH_ONLY		0x1 /* TPH only requests allowed */
+#define   PCI_TPH_REQ_EXT_TPH		0x3 /* Extended TPH requests allowed */
 
 /* Downstream Port Containment */
 #define PCI_EXP_DPC_CAP			0x04	/* DPC Capability */