Commit 407d1a51 authored by Lizhi Hou's avatar Lizhi Hou Committed by Rob Herring
Browse files

PCI: Create device tree node for bridge 



The PCI endpoint device such as Xilinx Alveo PCI card maps the register
spaces from multiple hardware peripherals to its PCI BAR. Normally,
the PCI core discovers devices and BARs using the PCI enumeration process.
There is no infrastructure to discover the hardware peripherals that are
present in a PCI device, and which can be accessed through the PCI BARs.

Apparently, the device tree framework requires a device tree node for the
PCI device. Thus, it can generate the device tree nodes for hardware
peripherals underneath. Because PCI is self discoverable bus, there might
not be a device tree node created for PCI devices. Furthermore, if the PCI
device is hot pluggable, when it is plugged in, the device tree nodes for
its parent bridges are required. Add support to generate device tree node
for PCI bridges.

Add an of_pci_make_dev_node() interface that can be used to create device
tree node for PCI devices.

Add a PCI_DYNAMIC_OF_NODES config option. When the option is turned on,
the kernel will generate device tree nodes for PCI bridges unconditionally.

Initially, add the basic properties for the dynamically generated device
tree nodes which include #address-cells, #size-cells, device_type,
compatible, ranges, reg.

Acked-by: default avatarBjorn Helgaas <bhelgaas@google.com>
Signed-off-by: default avatarLizhi Hou <lizhi.hou@amd.com>
Link: https://lore.kernel.org/r/1692120000-46900-3-git-send-email-lizhi.hou@amd.com


Signed-off-by: default avatarRob Herring <robh@kernel.org>
parent b544fc2b

drivers/pci/Kconfig

+12 −0
Original line number Diff line number Diff line
@@ -194,6 +194,18 @@ config PCI_HYPERV 
	  The PCI device frontend driver allows the kernel to import arbitrary

	  PCI devices from a PCI backend to support PCI driver domains.



config PCI_DYNAMIC_OF_NODES

	bool "Create Device tree nodes for PCI devices"

	depends on OF

	select OF_DYNAMIC

	help

	  This option enables support for generating device tree nodes for some

	  PCI devices. Thus, the driver of this kind can load and overlay

	  flattened device tree for its downstream devices.



	  Once this option is selected, the device tree nodes will be generated

	  for all PCI bridges.



choice

	prompt "PCI Express hierarchy optimization setting"

	default PCIE_BUS_DEFAULT

drivers/pci/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -32,6 +32,7 @@ obj-$(CONFIG_PCI_P2PDMA) += p2pdma.o 
obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o

obj-$(CONFIG_VGA_ARB)		+= vgaarb.o

obj-$(CONFIG_PCI_DOE)		+= doe.o

obj-$(CONFIG_PCI_DYNAMIC_OF_NODES) += of_property.o



# Endpoint library must be initialized before its users

obj-$(CONFIG_PCI_ENDPOINT)	+= endpoint/

drivers/pci/bus.c

+2 −0
Original line number Diff line number Diff line
@@ -340,6 +340,8 @@ void pci_bus_add_device(struct pci_dev *dev) 
	 */

	pcibios_bus_add_device(dev);

	pci_fixup_device(pci_fixup_final, dev);

	if (pci_is_bridge(dev))

		of_pci_make_dev_node(dev);

	pci_create_sysfs_dev_files(dev);

	pci_proc_attach_device(dev);

	pci_bridge_d3_update(dev);

drivers/pci/of.c

+79 −0
Original line number Diff line number Diff line
@@ -611,6 +611,85 @@ int devm_of_pci_bridge_init(struct device *dev, struct pci_host_bridge *bridge) 
	return pci_parse_request_of_pci_ranges(dev, bridge);

}



#ifdef CONFIG_PCI_DYNAMIC_OF_NODES



void of_pci_remove_node(struct pci_dev *pdev)

{

	struct device_node *np;



	np = pci_device_to_OF_node(pdev);

	if (!np || !of_node_check_flag(np, OF_DYNAMIC))

		return;

	pdev->dev.of_node = NULL;



	of_changeset_revert(np->data);

	of_changeset_destroy(np->data);

	of_node_put(np);

}



void of_pci_make_dev_node(struct pci_dev *pdev)

{

	struct device_node *ppnode, *np = NULL;

	const char *pci_type;

	struct of_changeset *cset;

	const char *name;

	int ret;



	/*

	 * If there is already a device tree node linked to this device,

	 * return immediately.

	 */

	if (pci_device_to_OF_node(pdev))

		return;



	/* Check if there is device tree node for parent device */

	if (!pdev->bus->self)

		ppnode = pdev->bus->dev.of_node;

	else

		ppnode = pdev->bus->self->dev.of_node;

	if (!ppnode)

		return;



	if (pci_is_bridge(pdev))

		pci_type = "pci";

	else

		pci_type = "dev";



	name = kasprintf(GFP_KERNEL, "%s@%x,%x", pci_type,

			 PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn));

	if (!name)

		return;



	cset = kmalloc(sizeof(*cset), GFP_KERNEL);

	if (!cset)

		goto failed;

	of_changeset_init(cset);



	np = of_changeset_create_node(cset, ppnode, name);

	if (!np)

		goto failed;

	np->data = cset;



	ret = of_pci_add_properties(pdev, cset, np);

	if (ret)

		goto failed;



	ret = of_changeset_apply(cset);

	if (ret)

		goto failed;



	pdev->dev.of_node = np;

	kfree(name);



	return;



failed:

	if (np)

		of_node_put(np);

	kfree(name);

}

#endif



#endif /* CONFIG_PCI */



/**

drivers/pci/of_property.c

0 → 100644
+355 −0
Original line number Diff line number Diff line 
// SPDX-License-Identifier: GPL-2.0+

/*

 * Copyright (C) 2022-2023, Advanced Micro Devices, Inc.

 */



#include <linux/pci.h>

#include <linux/of.h>

#include <linux/of_irq.h>

#include <linux/bitfield.h>

#include <linux/bits.h>

#include "pci.h"



#define OF_PCI_ADDRESS_CELLS		3

#define OF_PCI_SIZE_CELLS		2

#define OF_PCI_MAX_INT_PIN		4



struct of_pci_addr_pair {

	u32		phys_addr[OF_PCI_ADDRESS_CELLS];

	u32		size[OF_PCI_SIZE_CELLS];

};



/*

 * Each entry in the ranges table is a tuple containing the child address,

 * the parent address, and the size of the region in the child address space.

 * Thus, for PCI, in each entry parent address is an address on the primary

 * side and the child address is the corresponding address on the secondary

 * side.

 */

struct of_pci_range {

	u32		child_addr[OF_PCI_ADDRESS_CELLS];

	u32		parent_addr[OF_PCI_ADDRESS_CELLS];

	u32		size[OF_PCI_SIZE_CELLS];

};



#define OF_PCI_ADDR_SPACE_IO		0x1

#define OF_PCI_ADDR_SPACE_MEM32		0x2

#define OF_PCI_ADDR_SPACE_MEM64		0x3



#define OF_PCI_ADDR_FIELD_NONRELOC	BIT(31)

#define OF_PCI_ADDR_FIELD_SS		GENMASK(25, 24)

#define OF_PCI_ADDR_FIELD_PREFETCH	BIT(30)

#define OF_PCI_ADDR_FIELD_BUS		GENMASK(23, 16)

#define OF_PCI_ADDR_FIELD_DEV		GENMASK(15, 11)

#define OF_PCI_ADDR_FIELD_FUNC		GENMASK(10, 8)

#define OF_PCI_ADDR_FIELD_REG		GENMASK(7, 0)



enum of_pci_prop_compatible {

	PROP_COMPAT_PCI_VVVV_DDDD,

	PROP_COMPAT_PCICLASS_CCSSPP,

	PROP_COMPAT_PCICLASS_CCSS,

	PROP_COMPAT_NUM,

};



static void of_pci_set_address(struct pci_dev *pdev, u32 *prop, u64 addr,

			       u32 reg_num, u32 flags, bool reloc)

{

	prop[0] = FIELD_PREP(OF_PCI_ADDR_FIELD_BUS, pdev->bus->number) |

		FIELD_PREP(OF_PCI_ADDR_FIELD_DEV, PCI_SLOT(pdev->devfn)) |

		FIELD_PREP(OF_PCI_ADDR_FIELD_FUNC, PCI_FUNC(pdev->devfn));

	prop[0] |= flags | reg_num;

	if (!reloc) {

		prop[0] |= OF_PCI_ADDR_FIELD_NONRELOC;

		prop[1] = upper_32_bits(addr);

		prop[2] = lower_32_bits(addr);

	}

}



static int of_pci_get_addr_flags(struct resource *res, u32 *flags)

{

	u32 ss;



	if (res->flags & IORESOURCE_IO)

		ss = OF_PCI_ADDR_SPACE_IO;

	else if (res->flags & IORESOURCE_MEM_64)

		ss = OF_PCI_ADDR_SPACE_MEM64;

	else if (res->flags & IORESOURCE_MEM)

		ss = OF_PCI_ADDR_SPACE_MEM32;

	else

		return -EINVAL;



	*flags = 0;

	if (res->flags & IORESOURCE_PREFETCH)

		*flags |= OF_PCI_ADDR_FIELD_PREFETCH;



	*flags |= FIELD_PREP(OF_PCI_ADDR_FIELD_SS, ss);



	return 0;

}



static int of_pci_prop_bus_range(struct pci_dev *pdev,

				 struct of_changeset *ocs,

				 struct device_node *np)

{

	u32 bus_range[] = { pdev->subordinate->busn_res.start,

			    pdev->subordinate->busn_res.end };



	return of_changeset_add_prop_u32_array(ocs, np, "bus-range", bus_range,

					       ARRAY_SIZE(bus_range));

}



static int of_pci_prop_ranges(struct pci_dev *pdev, struct of_changeset *ocs,

			      struct device_node *np)

{

	struct of_pci_range *rp;

	struct resource *res;

	int i, j, ret;

	u32 flags, num;

	u64 val64;



	if (pci_is_bridge(pdev)) {

		num = PCI_BRIDGE_RESOURCE_NUM;

		res = &pdev->resource[PCI_BRIDGE_RESOURCES];

	} else {

		num = PCI_STD_NUM_BARS;

		res = &pdev->resource[PCI_STD_RESOURCES];

	}



	rp = kcalloc(num, sizeof(*rp), GFP_KERNEL);

	if (!rp)

		return -ENOMEM;



	for (i = 0, j = 0; j < num; j++) {

		if (!resource_size(&res[j]))

			continue;



		if (of_pci_get_addr_flags(&res[j], &flags))

			continue;



		val64 = res[j].start;

		of_pci_set_address(pdev, rp[i].parent_addr, val64, 0, flags,

				   false);

		if (pci_is_bridge(pdev)) {

			memcpy(rp[i].child_addr, rp[i].parent_addr,

			       sizeof(rp[i].child_addr));

		} else {

			/*

			 * For endpoint device, the lower 64-bits of child

			 * address is always zero.

			 */

			rp[i].child_addr[0] = j;

		}



		val64 = resource_size(&res[j]);

		rp[i].size[0] = upper_32_bits(val64);

		rp[i].size[1] = lower_32_bits(val64);



		i++;

	}



	ret = of_changeset_add_prop_u32_array(ocs, np, "ranges", (u32 *)rp,

					      i * sizeof(*rp) / sizeof(u32));

	kfree(rp);



	return ret;

}



static int of_pci_prop_reg(struct pci_dev *pdev, struct of_changeset *ocs,

			   struct device_node *np)

{

	struct of_pci_addr_pair reg = { 0 };



	/* configuration space */

	of_pci_set_address(pdev, reg.phys_addr, 0, 0, 0, true);



	return of_changeset_add_prop_u32_array(ocs, np, "reg", (u32 *)&reg,

					       sizeof(reg) / sizeof(u32));

}



static int of_pci_prop_interrupts(struct pci_dev *pdev,

				  struct of_changeset *ocs,

				  struct device_node *np)

{

	int ret;

	u8 pin;



	ret = pci_read_config_byte(pdev, PCI_INTERRUPT_PIN, &pin);

	if (ret != 0)

		return ret;



	if (!pin)

		return 0;



	return of_changeset_add_prop_u32(ocs, np, "interrupts", (u32)pin);

}



static int of_pci_prop_intr_map(struct pci_dev *pdev, struct of_changeset *ocs,

				struct device_node *np)

{

	struct of_phandle_args out_irq[OF_PCI_MAX_INT_PIN];

	u32 i, addr_sz[OF_PCI_MAX_INT_PIN], map_sz = 0;

	__be32 laddr[OF_PCI_ADDRESS_CELLS] = { 0 };

	u32 int_map_mask[] = { 0xffff00, 0, 0, 7 };

	struct device_node *pnode;

	struct pci_dev *child;

	u32 *int_map, *mapp;

	int ret;

	u8 pin;



	pnode = pci_device_to_OF_node(pdev->bus->self);

	if (!pnode)

		pnode = pci_bus_to_OF_node(pdev->bus);



	if (!pnode) {

		pci_err(pdev, "failed to get parent device node");

		return -EINVAL;

	}



	laddr[0] = cpu_to_be32((pdev->bus->number << 16) | (pdev->devfn << 8));

	for (pin = 1; pin <= OF_PCI_MAX_INT_PIN;  pin++) {

		i = pin - 1;

		out_irq[i].np = pnode;

		out_irq[i].args_count = 1;

		out_irq[i].args[0] = pin;

		ret = of_irq_parse_raw(laddr, &out_irq[i]);

		if (ret) {

			pci_err(pdev, "parse irq %d failed, ret %d", pin, ret);

			continue;

		}

		ret = of_property_read_u32(out_irq[i].np, "#address-cells",

					   &addr_sz[i]);

		if (ret)

			addr_sz[i] = 0;

	}



	list_for_each_entry(child, &pdev->subordinate->devices, bus_list) {

		for (pin = 1; pin <= OF_PCI_MAX_INT_PIN; pin++) {

			i = pci_swizzle_interrupt_pin(child, pin) - 1;

			map_sz += 5 + addr_sz[i] + out_irq[i].args_count;

		}

	}



	int_map = kcalloc(map_sz, sizeof(u32), GFP_KERNEL);

	mapp = int_map;



	list_for_each_entry(child, &pdev->subordinate->devices, bus_list) {

		for (pin = 1; pin <= OF_PCI_MAX_INT_PIN; pin++) {

			*mapp = (child->bus->number << 16) |

				(child->devfn << 8);

			mapp += OF_PCI_ADDRESS_CELLS;

			*mapp = pin;

			mapp++;

			i = pci_swizzle_interrupt_pin(child, pin) - 1;

			*mapp = out_irq[i].np->phandle;

			mapp++;

			if (addr_sz[i]) {

				ret = of_property_read_u32_array(out_irq[i].np,

								 "reg", mapp,

								 addr_sz[i]);

				if (ret)

					goto failed;

			}

			mapp += addr_sz[i];

			memcpy(mapp, out_irq[i].args,

			       out_irq[i].args_count * sizeof(u32));

			mapp += out_irq[i].args_count;

		}

	}



	ret = of_changeset_add_prop_u32_array(ocs, np, "interrupt-map", int_map,

					      map_sz);

	if (ret)

		goto failed;



	ret = of_changeset_add_prop_u32(ocs, np, "#interrupt-cells", 1);

	if (ret)

		goto failed;



	ret = of_changeset_add_prop_u32_array(ocs, np, "interrupt-map-mask",

					      int_map_mask,

					      ARRAY_SIZE(int_map_mask));

	if (ret)

		goto failed;



	kfree(int_map);

	return 0;



failed:

	kfree(int_map);

	return ret;

}



static int of_pci_prop_compatible(struct pci_dev *pdev,

				  struct of_changeset *ocs,

				  struct device_node *np)

{

	const char *compat_strs[PROP_COMPAT_NUM] = { 0 };

	int i, ret;



	compat_strs[PROP_COMPAT_PCI_VVVV_DDDD] =

		kasprintf(GFP_KERNEL, "pci%x,%x", pdev->vendor, pdev->device);

	compat_strs[PROP_COMPAT_PCICLASS_CCSSPP] =

		kasprintf(GFP_KERNEL, "pciclass,%06x", pdev->class);

	compat_strs[PROP_COMPAT_PCICLASS_CCSS] =

		kasprintf(GFP_KERNEL, "pciclass,%04x", pdev->class >> 8);



	ret = of_changeset_add_prop_string_array(ocs, np, "compatible",

						 compat_strs, PROP_COMPAT_NUM);

	for (i = 0; i < PROP_COMPAT_NUM; i++)

		kfree(compat_strs[i]);



	return ret;

}



int of_pci_add_properties(struct pci_dev *pdev, struct of_changeset *ocs,

			  struct device_node *np)

{

	int ret;



	/*

	 * The added properties will be released when the

	 * changeset is destroyed.

	 */

	if (pci_is_bridge(pdev)) {

		ret = of_changeset_add_prop_string(ocs, np, "device_type",

						   "pci");

		if (ret)

			return ret;



		ret = of_pci_prop_bus_range(pdev, ocs, np);

		if (ret)

			return ret;



		ret = of_pci_prop_intr_map(pdev, ocs, np);

		if (ret)

			return ret;

	}



	ret = of_pci_prop_ranges(pdev, ocs, np);

	if (ret)

		return ret;



	ret = of_changeset_add_prop_u32(ocs, np, "#address-cells",

					OF_PCI_ADDRESS_CELLS);

	if (ret)

		return ret;



	ret = of_changeset_add_prop_u32(ocs, np, "#size-cells",

					OF_PCI_SIZE_CELLS);

	if (ret)

		return ret;



	ret = of_pci_prop_reg(pdev, ocs, np);

	if (ret)

		return ret;



	ret = of_pci_prop_compatible(pdev, ocs, np);

	if (ret)

		return ret;



	ret = of_pci_prop_interrupts(pdev, ocs, np);

	if (ret)

		return ret;



	return 0;

}