summaryrefslogtreecommitdiffstats
path: root/arch/x86/pci
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/pci')
-rw-r--r--arch/x86/pci/Makefile27
-rw-r--r--arch/x86/pci/acpi.c509
-rw-r--r--arch/x86/pci/amd_bus.c412
-rw-r--r--arch/x86/pci/broadcom_bus.c112
-rw-r--r--arch/x86/pci/bus_numa.c146
-rw-r--r--arch/x86/pci/bus_numa.h27
-rw-r--r--arch/x86/pci/ce4100.c324
-rw-r--r--arch/x86/pci/common.c734
-rw-r--r--arch/x86/pci/direct.c315
-rw-r--r--arch/x86/pci/early.c59
-rw-r--r--arch/x86/pci/fixup.c965
-rw-r--r--arch/x86/pci/i386.c409
-rw-r--r--arch/x86/pci/init.c51
-rw-r--r--arch/x86/pci/intel_mid_pci.c406
-rw-r--r--arch/x86/pci/irq.c1810
-rw-r--r--arch/x86/pci/legacy.c77
-rw-r--r--arch/x86/pci/mmconfig-shared.c858
-rw-r--r--arch/x86/pci/mmconfig_32.c156
-rw-r--r--arch/x86/pci/mmconfig_64.c154
-rw-r--r--arch/x86/pci/numachip.c127
-rw-r--r--arch/x86/pci/olpc.c311
-rw-r--r--arch/x86/pci/pcbios.c429
-rw-r--r--arch/x86/pci/sta2x11-fixup.c232
-rw-r--r--arch/x86/pci/xen.c590
24 files changed, 9240 insertions, 0 deletions
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
new file mode 100644
index 0000000000..48bcada5ca
--- /dev/null
+++ b/arch/x86/pci/Makefile
@@ -0,0 +1,27 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-y := i386.o init.o
+
+obj-$(CONFIG_PCI_BIOS) += pcbios.o
+obj-$(CONFIG_PCI_MMCONFIG) += mmconfig_$(BITS).o direct.o mmconfig-shared.o
+obj-$(CONFIG_PCI_DIRECT) += direct.o
+obj-$(CONFIG_PCI_OLPC) += olpc.o
+obj-$(CONFIG_PCI_XEN) += xen.o
+
+obj-y += fixup.o
+obj-$(CONFIG_X86_INTEL_CE) += ce4100.o
+obj-$(CONFIG_ACPI) += acpi.o
+obj-y += legacy.o irq.o
+
+obj-$(CONFIG_STA2X11) += sta2x11-fixup.o
+
+obj-$(CONFIG_X86_NUMACHIP) += numachip.o
+
+obj-$(CONFIG_X86_INTEL_MID) += intel_mid_pci.o
+
+obj-y += common.o early.o
+obj-y += bus_numa.o
+
+obj-$(CONFIG_AMD_NB) += amd_bus.o
+obj-$(CONFIG_PCI_CNB20LE_QUIRK) += broadcom_bus.o
+
+ccflags-$(CONFIG_PCI_DEBUG) += -DDEBUG
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
new file mode 100644
index 0000000000..ea2eb2ec90
--- /dev/null
+++ b/arch/x86/pci/acpi.c
@@ -0,0 +1,509 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define pr_fmt(fmt) "PCI: " fmt
+
+#include <linux/pci.h>
+#include <linux/acpi.h>
+#include <linux/init.h>
+#include <linux/irq.h>
+#include <linux/dmi.h>
+#include <linux/slab.h>
+#include <linux/pci-acpi.h>
+#include <asm/numa.h>
+#include <asm/pci_x86.h>
+
+struct pci_root_info {
+ struct acpi_pci_root_info common;
+ struct pci_sysdata sd;
+#ifdef CONFIG_PCI_MMCONFIG
+ bool mcfg_added;
+ u8 start_bus;
+ u8 end_bus;
+#endif
+};
+
+bool pci_use_e820 = true;
+static bool pci_use_crs = true;
+static bool pci_ignore_seg;
+
+static int __init set_use_crs(const struct dmi_system_id *id)
+{
+ pci_use_crs = true;
+ return 0;
+}
+
+static int __init set_nouse_crs(const struct dmi_system_id *id)
+{
+ pci_use_crs = false;
+ return 0;
+}
+
+static int __init set_ignore_seg(const struct dmi_system_id *id)
+{
+ pr_info("%s detected: ignoring ACPI _SEG\n", id->ident);
+ pci_ignore_seg = true;
+ return 0;
+}
+
+static int __init set_no_e820(const struct dmi_system_id *id)
+{
+ pr_info("%s detected: not clipping E820 regions from _CRS\n",
+ id->ident);
+ pci_use_e820 = false;
+ return 0;
+}
+
+static const struct dmi_system_id pci_crs_quirks[] __initconst = {
+ /* http://bugzilla.kernel.org/show_bug.cgi?id=14183 */
+ {
+ .callback = set_use_crs,
+ .ident = "IBM System x3800",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "x3800"),
+ },
+ },
+ /* https://bugzilla.kernel.org/show_bug.cgi?id=16007 */
+ /* 2006 AMD HT/VIA system with two host bridges */
+ {
+ .callback = set_use_crs,
+ .ident = "ASRock ALiveSATA2-GLAN",
+ .matches = {
+ DMI_MATCH(DMI_PRODUCT_NAME, "ALiveSATA2-GLAN"),
+ },
+ },
+ /* https://bugzilla.kernel.org/show_bug.cgi?id=30552 */
+ /* 2006 AMD HT/VIA system with two host bridges */
+ {
+ .callback = set_use_crs,
+ .ident = "ASUS M2V-MX SE",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
+ DMI_MATCH(DMI_BOARD_NAME, "M2V-MX SE"),
+ DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."),
+ },
+ },
+ /* https://bugzilla.kernel.org/show_bug.cgi?id=42619 */
+ {
+ .callback = set_use_crs,
+ .ident = "MSI MS-7253",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"),
+ DMI_MATCH(DMI_BOARD_NAME, "MS-7253"),
+ DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
+ },
+ },
+ /* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/931368 */
+ /* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/1033299 */
+ {
+ .callback = set_use_crs,
+ .ident = "Foxconn K8M890-8237A",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Foxconn"),
+ DMI_MATCH(DMI_BOARD_NAME, "K8M890-8237A"),
+ DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
+ },
+ },
+
+ /* Now for the blacklist.. */
+
+ /* https://bugzilla.redhat.com/show_bug.cgi?id=769657 */
+ {
+ .callback = set_nouse_crs,
+ .ident = "Dell Studio 1557",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Studio 1557"),
+ DMI_MATCH(DMI_BIOS_VERSION, "A09"),
+ },
+ },
+ /* https://bugzilla.redhat.com/show_bug.cgi?id=769657 */
+ {
+ .callback = set_nouse_crs,
+ .ident = "Thinkpad SL510",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_BOARD_NAME, "2847DFG"),
+ DMI_MATCH(DMI_BIOS_VERSION, "6JET85WW (1.43 )"),
+ },
+ },
+ /* https://bugzilla.kernel.org/show_bug.cgi?id=42606 */
+ {
+ .callback = set_nouse_crs,
+ .ident = "Supermicro X8DTH",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Supermicro"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "X8DTH-i/6/iF/6F"),
+ DMI_MATCH(DMI_BIOS_VERSION, "2.0a"),
+ },
+ },
+
+ /* https://bugzilla.kernel.org/show_bug.cgi?id=15362 */
+ {
+ .callback = set_ignore_seg,
+ .ident = "HP xw9300",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP xw9300 Workstation"),
+ },
+ },
+
+ /*
+ * Many Lenovo models with "IIL" in their DMI_PRODUCT_VERSION have
+ * an E820 reserved region that covers the entire 32-bit host
+ * bridge memory window from _CRS. Using the E820 region to clip
+ * _CRS means no space is available for hot-added or uninitialized
+ * PCI devices. This typically breaks I2C controllers for touchpads
+ * and hot-added Thunderbolt devices. See the commit log for
+ * models known to require this quirk and related bug reports.
+ */
+ {
+ .callback = set_no_e820,
+ .ident = "Lenovo *IIL* product version",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "IIL"),
+ },
+ },
+
+ /*
+ * The Acer Spin 5 (SP513-54N) has the same E820 reservation covering
+ * the entire _CRS 32-bit window issue as the Lenovo *IIL* models.
+ * See https://bugs.launchpad.net/bugs/1884232
+ */
+ {
+ .callback = set_no_e820,
+ .ident = "Acer Spin 5 (SP513-54N)",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Spin SP513-54N"),
+ },
+ },
+
+ /*
+ * Clevo X170KM-G barebones have the same E820 reservation covering
+ * the entire _CRS 32-bit window issue as the Lenovo *IIL* models.
+ * See https://bugzilla.kernel.org/show_bug.cgi?id=214259
+ */
+ {
+ .callback = set_no_e820,
+ .ident = "Clevo X170KM-G Barebone",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_NAME, "X170KM-G"),
+ },
+ },
+ {}
+};
+
+void __init pci_acpi_crs_quirks(void)
+{
+ int year = dmi_get_bios_year();
+
+ if (year >= 0 && year < 2008 && iomem_resource.end <= 0xffffffff)
+ pci_use_crs = false;
+
+ /*
+ * Some firmware includes unusable space (host bridge registers,
+ * hidden PCI device BARs, etc) in PCI host bridge _CRS. This is a
+ * firmware defect, and 4dc2287c1805 ("x86: avoid E820 regions when
+ * allocating address space") has clipped out the unusable space in
+ * the past.
+ *
+ * But other firmware supplies E820 reserved regions that cover
+ * entire _CRS windows, so clipping throws away the entire window,
+ * leaving none for hot-added or uninitialized devices. These E820
+ * entries are probably *not* a firmware defect, so disable the
+ * clipping by default for post-2022 machines.
+ *
+ * We already have quirks to disable clipping for pre-2023
+ * machines, and we'll likely need quirks to *enable* clipping for
+ * post-2022 machines that incorrectly include unusable space in
+ * _CRS.
+ */
+ if (year >= 2023)
+ pci_use_e820 = false;
+
+ dmi_check_system(pci_crs_quirks);
+
+ /*
+ * If the user specifies "pci=use_crs" or "pci=nocrs" explicitly, that
+ * takes precedence over anything we figured out above.
+ */
+ if (pci_probe & PCI_ROOT_NO_CRS)
+ pci_use_crs = false;
+ else if (pci_probe & PCI_USE__CRS)
+ pci_use_crs = true;
+
+ pr_info("%s host bridge windows from ACPI; if necessary, use \"pci=%s\" and report a bug\n",
+ pci_use_crs ? "Using" : "Ignoring",
+ pci_use_crs ? "nocrs" : "use_crs");
+
+ /* "pci=use_e820"/"pci=no_e820" on the kernel cmdline takes precedence */
+ if (pci_probe & PCI_NO_E820)
+ pci_use_e820 = false;
+ else if (pci_probe & PCI_USE_E820)
+ pci_use_e820 = true;
+
+ pr_info("%s E820 reservations for host bridge windows\n",
+ pci_use_e820 ? "Using" : "Ignoring");
+ if (pci_probe & (PCI_NO_E820 | PCI_USE_E820))
+ pr_info("Please notify linux-pci@vger.kernel.org so future kernels can do this automatically\n");
+}
+
+#ifdef CONFIG_PCI_MMCONFIG
+static int check_segment(u16 seg, struct device *dev, char *estr)
+{
+ if (seg) {
+ dev_err(dev, "%s can't access configuration space under this host bridge\n",
+ estr);
+ return -EIO;
+ }
+
+ /*
+ * Failure in adding MMCFG information is not fatal,
+ * just can't access extended configuration space of
+ * devices under this host bridge.
+ */
+ dev_warn(dev, "%s can't access extended configuration space under this bridge\n",
+ estr);
+
+ return 0;
+}
+
+static int setup_mcfg_map(struct acpi_pci_root_info *ci)
+{
+ int result, seg;
+ struct pci_root_info *info;
+ struct acpi_pci_root *root = ci->root;
+ struct device *dev = &ci->bridge->dev;
+
+ info = container_of(ci, struct pci_root_info, common);
+ info->start_bus = (u8)root->secondary.start;
+ info->end_bus = (u8)root->secondary.end;
+ info->mcfg_added = false;
+ seg = info->sd.domain;
+
+ /* return success if MMCFG is not in use */
+ if (raw_pci_ext_ops && raw_pci_ext_ops != &pci_mmcfg)
+ return 0;
+
+ if (!(pci_probe & PCI_PROBE_MMCONF))
+ return check_segment(seg, dev, "MMCONFIG is disabled,");
+
+ result = pci_mmconfig_insert(dev, seg, info->start_bus, info->end_bus,
+ root->mcfg_addr);
+ if (result == 0) {
+ /* enable MMCFG if it hasn't been enabled yet */
+ if (raw_pci_ext_ops == NULL)
+ raw_pci_ext_ops = &pci_mmcfg;
+ info->mcfg_added = true;
+ } else if (result != -EEXIST)
+ return check_segment(seg, dev,
+ "fail to add MMCONFIG information,");
+
+ return 0;
+}
+
+static void teardown_mcfg_map(struct acpi_pci_root_info *ci)
+{
+ struct pci_root_info *info;
+
+ info = container_of(ci, struct pci_root_info, common);
+ if (info->mcfg_added) {
+ pci_mmconfig_delete(info->sd.domain,
+ info->start_bus, info->end_bus);
+ info->mcfg_added = false;
+ }
+}
+#else
+static int setup_mcfg_map(struct acpi_pci_root_info *ci)
+{
+ return 0;
+}
+
+static void teardown_mcfg_map(struct acpi_pci_root_info *ci)
+{
+}
+#endif
+
+static int pci_acpi_root_get_node(struct acpi_pci_root *root)
+{
+ int busnum = root->secondary.start;
+ struct acpi_device *device = root->device;
+ int node = acpi_get_node(device->handle);
+
+ if (node == NUMA_NO_NODE) {
+ node = x86_pci_root_bus_node(busnum);
+ if (node != 0 && node != NUMA_NO_NODE)
+ dev_info(&device->dev, FW_BUG "no _PXM; falling back to node %d from hardware (may be inconsistent with ACPI node numbers)\n",
+ node);
+ }
+ if (node != NUMA_NO_NODE && !node_online(node))
+ node = NUMA_NO_NODE;
+
+ return node;
+}
+
+static int pci_acpi_root_init_info(struct acpi_pci_root_info *ci)
+{
+ return setup_mcfg_map(ci);
+}
+
+static void pci_acpi_root_release_info(struct acpi_pci_root_info *ci)
+{
+ teardown_mcfg_map(ci);
+ kfree(container_of(ci, struct pci_root_info, common));
+}
+
+/*
+ * An IO port or MMIO resource assigned to a PCI host bridge may be
+ * consumed by the host bridge itself or available to its child
+ * bus/devices. The ACPI specification defines a bit (Producer/Consumer)
+ * to tell whether the resource is consumed by the host bridge itself,
+ * but firmware hasn't used that bit consistently, so we can't rely on it.
+ *
+ * On x86 and IA64 platforms, all IO port and MMIO resources are assumed
+ * to be available to child bus/devices except one special case:
+ * IO port [0xCF8-0xCFF] is consumed by the host bridge itself
+ * to access PCI configuration space.
+ *
+ * So explicitly filter out PCI CFG IO ports[0xCF8-0xCFF].
+ */
+static bool resource_is_pcicfg_ioport(struct resource *res)
+{
+ return (res->flags & IORESOURCE_IO) &&
+ res->start == 0xCF8 && res->end == 0xCFF;
+}
+
+static int pci_acpi_root_prepare_resources(struct acpi_pci_root_info *ci)
+{
+ struct acpi_device *device = ci->bridge;
+ int busnum = ci->root->secondary.start;
+ struct resource_entry *entry, *tmp;
+ int status;
+
+ status = acpi_pci_probe_root_resources(ci);
+
+ if (pci_use_crs) {
+ resource_list_for_each_entry_safe(entry, tmp, &ci->resources)
+ if (resource_is_pcicfg_ioport(entry->res))
+ resource_list_destroy_entry(entry);
+ return status;
+ }
+
+ resource_list_for_each_entry_safe(entry, tmp, &ci->resources) {
+ dev_printk(KERN_DEBUG, &device->dev,
+ "host bridge window %pR (ignored)\n", entry->res);
+ resource_list_destroy_entry(entry);
+ }
+ x86_pci_root_bus_resources(busnum, &ci->resources);
+
+ return 0;
+}
+
+static struct acpi_pci_root_ops acpi_pci_root_ops = {
+ .pci_ops = &pci_root_ops,
+ .init_info = pci_acpi_root_init_info,
+ .release_info = pci_acpi_root_release_info,
+ .prepare_resources = pci_acpi_root_prepare_resources,
+};
+
+struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
+{
+ int domain = root->segment;
+ int busnum = root->secondary.start;
+ int node = pci_acpi_root_get_node(root);
+ struct pci_bus *bus;
+
+ if (pci_ignore_seg)
+ root->segment = domain = 0;
+
+ if (domain && !pci_domains_supported) {
+ pr_warn("pci_bus %04x:%02x: ignored (multiple domains not supported)\n",
+ domain, busnum);
+ return NULL;
+ }
+
+ bus = pci_find_bus(domain, busnum);
+ if (bus) {
+ /*
+ * If the desired bus has been scanned already, replace
+ * its bus->sysdata.
+ */
+ struct pci_sysdata sd = {
+ .domain = domain,
+ .node = node,
+ .companion = root->device
+ };
+
+ memcpy(bus->sysdata, &sd, sizeof(sd));
+ } else {
+ struct pci_root_info *info;
+
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
+ if (!info)
+ dev_err(&root->device->dev,
+ "pci_bus %04x:%02x: ignored (out of memory)\n",
+ domain, busnum);
+ else {
+ info->sd.domain = domain;
+ info->sd.node = node;
+ info->sd.companion = root->device;
+ bus = acpi_pci_root_create(root, &acpi_pci_root_ops,
+ &info->common, &info->sd);
+ }
+ }
+
+ /* After the PCI-E bus has been walked and all devices discovered,
+ * configure any settings of the fabric that might be necessary.
+ */
+ if (bus) {
+ struct pci_bus *child;
+ list_for_each_entry(child, &bus->children, node)
+ pcie_bus_configure_settings(child);
+ }
+
+ return bus;
+}
+
+int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
+{
+ /*
+ * We pass NULL as parent to pci_create_root_bus(), so if it is not NULL
+ * here, pci_create_root_bus() has been called by someone else and
+ * sysdata is likely to be different from what we expect. Let it go in
+ * that case.
+ */
+ if (!bridge->dev.parent) {
+ struct pci_sysdata *sd = bridge->bus->sysdata;
+ ACPI_COMPANION_SET(&bridge->dev, sd->companion);
+ }
+ return 0;
+}
+
+int __init pci_acpi_init(void)
+{
+ struct pci_dev *dev = NULL;
+
+ if (acpi_noirq)
+ return -ENODEV;
+
+ pr_info("Using ACPI for IRQ routing\n");
+ acpi_irq_penalty_init();
+ pcibios_enable_irq = acpi_pci_irq_enable;
+ pcibios_disable_irq = acpi_pci_irq_disable;
+ x86_init.pci.init_irq = x86_init_noop;
+
+ if (pci_routeirq) {
+ /*
+ * PCI IRQ routing is set up by pci_enable_device(), but we
+ * also do it here in case there are still broken drivers that
+ * don't use pci_enable_device().
+ */
+ pr_info("Routing PCI interrupts for all devices because \"pci=routeirq\" specified\n");
+ for_each_pci_dev(dev)
+ acpi_pci_irq_enable(dev);
+ }
+
+ return 0;
+}
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
new file mode 100644
index 0000000000..631512f7ec
--- /dev/null
+++ b/arch/x86/pci/amd_bus.c
@@ -0,0 +1,412 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/topology.h>
+#include <linux/cpu.h>
+#include <linux/range.h>
+
+#include <asm/amd_nb.h>
+#include <asm/pci_x86.h>
+
+#include <asm/pci-direct.h>
+
+#include "bus_numa.h"
+
+#define AMD_NB_F0_NODE_ID 0x60
+#define AMD_NB_F0_UNIT_ID 0x64
+#define AMD_NB_F1_CONFIG_MAP_REG 0xe0
+
+#define RANGE_NUM 16
+#define AMD_NB_F1_CONFIG_MAP_RANGES 4
+
+struct amd_hostbridge {
+ u32 bus;
+ u32 slot;
+ u32 device;
+};
+
+/*
+ * IMPORTANT NOTE:
+ * hb_probes[] and early_root_info_init() is in maintenance mode.
+ * It only supports K8, Fam10h, Fam11h, and Fam15h_00h-0fh .
+ * Future processor will rely on information in ACPI.
+ */
+static struct amd_hostbridge hb_probes[] __initdata = {
+ { 0, 0x18, 0x1100 }, /* K8 */
+ { 0, 0x18, 0x1200 }, /* Family10h */
+ { 0xff, 0, 0x1200 }, /* Family10h */
+ { 0, 0x18, 0x1300 }, /* Family11h */
+ { 0, 0x18, 0x1600 }, /* Family15h */
+};
+
+static struct pci_root_info __init *find_pci_root_info(int node, int link)
+{
+ struct pci_root_info *info;
+
+ /* find the position */
+ list_for_each_entry(info, &pci_root_infos, list)
+ if (info->node == node && info->link == link)
+ return info;
+
+ return NULL;
+}
+
+static inline resource_size_t cap_resource(u64 val)
+{
+ if (val > RESOURCE_SIZE_MAX)
+ return RESOURCE_SIZE_MAX;
+
+ return val;
+}
+
+/**
+ * early_root_info_init()
+ * called before pcibios_scan_root and pci_scan_bus
+ * fills the mp_bus_to_cpumask array based according
+ * to the LDT Bus Number Registers found in the northbridge.
+ */
+static int __init early_root_info_init(void)
+{
+ int i;
+ unsigned bus;
+ unsigned slot;
+ int node;
+ int link;
+ int def_node;
+ int def_link;
+ struct pci_root_info *info;
+ u32 reg;
+ u64 start;
+ u64 end;
+ struct range range[RANGE_NUM];
+ u64 val;
+ u32 address;
+ bool found;
+ struct resource fam10h_mmconf_res, *fam10h_mmconf;
+ u64 fam10h_mmconf_start;
+ u64 fam10h_mmconf_end;
+
+ if (!early_pci_allowed())
+ return -1;
+
+ found = false;
+ for (i = 0; i < ARRAY_SIZE(hb_probes); i++) {
+ u32 id;
+ u16 device;
+ u16 vendor;
+
+ bus = hb_probes[i].bus;
+ slot = hb_probes[i].slot;
+ id = read_pci_config(bus, slot, 0, PCI_VENDOR_ID);
+ vendor = id & 0xffff;
+ device = (id>>16) & 0xffff;
+
+ if (vendor != PCI_VENDOR_ID_AMD &&
+ vendor != PCI_VENDOR_ID_HYGON)
+ continue;
+
+ if (hb_probes[i].device == device) {
+ found = true;
+ break;
+ }
+ }
+
+ if (!found)
+ return 0;
+
+ /*
+ * We should learn topology and routing information from _PXM and
+ * _CRS methods in the ACPI namespace. We extract node numbers
+ * here to work around BIOSes that don't supply _PXM.
+ */
+ for (i = 0; i < AMD_NB_F1_CONFIG_MAP_RANGES; i++) {
+ int min_bus;
+ int max_bus;
+ reg = read_pci_config(bus, slot, 1,
+ AMD_NB_F1_CONFIG_MAP_REG + (i << 2));
+
+ /* Check if that register is enabled for bus range */
+ if ((reg & 7) != 3)
+ continue;
+
+ min_bus = (reg >> 16) & 0xff;
+ max_bus = (reg >> 24) & 0xff;
+ node = (reg >> 4) & 0x07;
+ link = (reg >> 8) & 0x03;
+
+ alloc_pci_root_info(min_bus, max_bus, node, link);
+ }
+
+ /*
+ * The following code extracts routing information for use on old
+ * systems where Linux doesn't automatically use host bridge _CRS
+ * methods (or when the user specifies "pci=nocrs").
+ *
+ * We only do this through Fam11h, because _CRS should be enough on
+ * newer systems.
+ */
+ if (boot_cpu_data.x86 > 0x11)
+ return 0;
+
+ /* get the default node and link for left over res */
+ reg = read_pci_config(bus, slot, 0, AMD_NB_F0_NODE_ID);
+ def_node = (reg >> 8) & 0x07;
+ reg = read_pci_config(bus, slot, 0, AMD_NB_F0_UNIT_ID);
+ def_link = (reg >> 8) & 0x03;
+
+ memset(range, 0, sizeof(range));
+ add_range(range, RANGE_NUM, 0, 0, 0xffff + 1);
+ /* io port resource */
+ for (i = 0; i < 4; i++) {
+ reg = read_pci_config(bus, slot, 1, 0xc0 + (i << 3));
+ if (!(reg & 3))
+ continue;
+
+ start = reg & 0xfff000;
+ reg = read_pci_config(bus, slot, 1, 0xc4 + (i << 3));
+ node = reg & 0x07;
+ link = (reg >> 4) & 0x03;
+ end = (reg & 0xfff000) | 0xfff;
+
+ info = find_pci_root_info(node, link);
+ if (!info)
+ continue; /* not found */
+
+ printk(KERN_DEBUG "node %d link %d: io port [%llx, %llx]\n",
+ node, link, start, end);
+
+ /* kernel only handle 16 bit only */
+ if (end > 0xffff)
+ end = 0xffff;
+ update_res(info, start, end, IORESOURCE_IO, 1);
+ subtract_range(range, RANGE_NUM, start, end + 1);
+ }
+ /* add left over io port range to def node/link, [0, 0xffff] */
+ /* find the position */
+ info = find_pci_root_info(def_node, def_link);
+ if (info) {
+ for (i = 0; i < RANGE_NUM; i++) {
+ if (!range[i].end)
+ continue;
+
+ update_res(info, range[i].start, range[i].end - 1,
+ IORESOURCE_IO, 1);
+ }
+ }
+
+ memset(range, 0, sizeof(range));
+ /* 0xfd00000000-0xffffffffff for HT */
+ end = cap_resource((0xfdULL<<32) - 1);
+ end++;
+ add_range(range, RANGE_NUM, 0, 0, end);
+
+ /* need to take out [0, TOM) for RAM*/
+ address = MSR_K8_TOP_MEM1;
+ rdmsrl(address, val);
+ end = (val & 0xffffff800000ULL);
+ printk(KERN_INFO "TOM: %016llx aka %lldM\n", end, end>>20);
+ if (end < (1ULL<<32))
+ subtract_range(range, RANGE_NUM, 0, end);
+
+ /* get mmconfig */
+ fam10h_mmconf = amd_get_mmconfig_range(&fam10h_mmconf_res);
+ /* need to take out mmconf range */
+ if (fam10h_mmconf) {
+ printk(KERN_DEBUG "Fam 10h mmconf %pR\n", fam10h_mmconf);
+ fam10h_mmconf_start = fam10h_mmconf->start;
+ fam10h_mmconf_end = fam10h_mmconf->end;
+ subtract_range(range, RANGE_NUM, fam10h_mmconf_start,
+ fam10h_mmconf_end + 1);
+ } else {
+ fam10h_mmconf_start = 0;
+ fam10h_mmconf_end = 0;
+ }
+
+ /* mmio resource */
+ for (i = 0; i < 8; i++) {
+ reg = read_pci_config(bus, slot, 1, 0x80 + (i << 3));
+ if (!(reg & 3))
+ continue;
+
+ start = reg & 0xffffff00; /* 39:16 on 31:8*/
+ start <<= 8;
+ reg = read_pci_config(bus, slot, 1, 0x84 + (i << 3));
+ node = reg & 0x07;
+ link = (reg >> 4) & 0x03;
+ end = (reg & 0xffffff00);
+ end <<= 8;
+ end |= 0xffff;
+
+ info = find_pci_root_info(node, link);
+
+ if (!info)
+ continue;
+
+ printk(KERN_DEBUG "node %d link %d: mmio [%llx, %llx]",
+ node, link, start, end);
+ /*
+ * some sick allocation would have range overlap with fam10h
+ * mmconf range, so need to update start and end.
+ */
+ if (fam10h_mmconf_end) {
+ int changed = 0;
+ u64 endx = 0;
+ if (start >= fam10h_mmconf_start &&
+ start <= fam10h_mmconf_end) {
+ start = fam10h_mmconf_end + 1;
+ changed = 1;
+ }
+
+ if (end >= fam10h_mmconf_start &&
+ end <= fam10h_mmconf_end) {
+ end = fam10h_mmconf_start - 1;
+ changed = 1;
+ }
+
+ if (start < fam10h_mmconf_start &&
+ end > fam10h_mmconf_end) {
+ /* we got a hole */
+ endx = fam10h_mmconf_start - 1;
+ update_res(info, start, endx, IORESOURCE_MEM, 0);
+ subtract_range(range, RANGE_NUM, start,
+ endx + 1);
+ printk(KERN_CONT " ==> [%llx, %llx]", start, endx);
+ start = fam10h_mmconf_end + 1;
+ changed = 1;
+ }
+ if (changed) {
+ if (start <= end) {
+ printk(KERN_CONT " %s [%llx, %llx]", endx ? "and" : "==>", start, end);
+ } else {
+ printk(KERN_CONT "%s\n", endx?"":" ==> none");
+ continue;
+ }
+ }
+ }
+
+ update_res(info, cap_resource(start), cap_resource(end),
+ IORESOURCE_MEM, 1);
+ subtract_range(range, RANGE_NUM, start, end + 1);
+ printk(KERN_CONT "\n");
+ }
+
+ /* need to take out [4G, TOM2) for RAM*/
+ /* SYS_CFG */
+ address = MSR_AMD64_SYSCFG;
+ rdmsrl(address, val);
+ /* TOP_MEM2 is enabled? */
+ if (val & (1<<21)) {
+ /* TOP_MEM2 */
+ address = MSR_K8_TOP_MEM2;
+ rdmsrl(address, val);
+ end = (val & 0xffffff800000ULL);
+ printk(KERN_INFO "TOM2: %016llx aka %lldM\n", end, end>>20);
+ subtract_range(range, RANGE_NUM, 1ULL<<32, end);
+ }
+
+ /*
+ * add left over mmio range to def node/link ?
+ * that is tricky, just record range in from start_min to 4G
+ */
+ info = find_pci_root_info(def_node, def_link);
+ if (info) {
+ for (i = 0; i < RANGE_NUM; i++) {
+ if (!range[i].end)
+ continue;
+
+ update_res(info, cap_resource(range[i].start),
+ cap_resource(range[i].end - 1),
+ IORESOURCE_MEM, 1);
+ }
+ }
+
+ list_for_each_entry(info, &pci_root_infos, list) {
+ int busnum;
+ struct pci_root_res *root_res;
+
+ busnum = info->busn.start;
+ printk(KERN_DEBUG "bus: %pR on node %x link %x\n",
+ &info->busn, info->node, info->link);
+ list_for_each_entry(root_res, &info->resources, list)
+ printk(KERN_DEBUG "bus: %02x %pR\n",
+ busnum, &root_res->res);
+ }
+
+ return 0;
+}
+
+#define ENABLE_CF8_EXT_CFG (1ULL << 46)
+
+static int amd_bus_cpu_online(unsigned int cpu)
+{
+ u64 reg;
+
+ rdmsrl(MSR_AMD64_NB_CFG, reg);
+ if (!(reg & ENABLE_CF8_EXT_CFG)) {
+ reg |= ENABLE_CF8_EXT_CFG;
+ wrmsrl(MSR_AMD64_NB_CFG, reg);
+ }
+ return 0;
+}
+
+static void __init pci_enable_pci_io_ecs(void)
+{
+#ifdef CONFIG_AMD_NB
+ unsigned int i, n;
+
+ for (n = i = 0; !n && amd_nb_bus_dev_ranges[i].dev_limit; ++i) {
+ u8 bus = amd_nb_bus_dev_ranges[i].bus;
+ u8 slot = amd_nb_bus_dev_ranges[i].dev_base;
+ u8 limit = amd_nb_bus_dev_ranges[i].dev_limit;
+
+ for (; slot < limit; ++slot) {
+ u32 val = read_pci_config(bus, slot, 3, 0);
+
+ if (!early_is_amd_nb(val))
+ continue;
+
+ val = read_pci_config(bus, slot, 3, 0x8c);
+ if (!(val & (ENABLE_CF8_EXT_CFG >> 32))) {
+ val |= ENABLE_CF8_EXT_CFG >> 32;
+ write_pci_config(bus, slot, 3, 0x8c, val);
+ }
+ ++n;
+ }
+ }
+#endif
+}
+
+static int __init pci_io_ecs_init(void)
+{
+ int ret;
+
+ /* assume all cpus from fam10h have IO ECS */
+ if (boot_cpu_data.x86 < 0x10)
+ return 0;
+
+ /* Try the PCI method first. */
+ if (early_pci_allowed())
+ pci_enable_pci_io_ecs();
+
+ ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "pci/amd_bus:online",
+ amd_bus_cpu_online, NULL);
+ WARN_ON(ret < 0);
+
+ pci_probe |= PCI_HAS_IO_ECS;
+
+ return 0;
+}
+
+static int __init amd_postcore_init(void)
+{
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
+ return 0;
+
+ early_root_info_init();
+ pci_io_ecs_init();
+
+ return 0;
+}
+
+postcore_initcall(amd_postcore_init);
diff --git a/arch/x86/pci/broadcom_bus.c b/arch/x86/pci/broadcom_bus.c
new file mode 100644
index 0000000000..2db73613ca
--- /dev/null
+++ b/arch/x86/pci/broadcom_bus.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Read address ranges from a Broadcom CNB20LE Host Bridge
+ *
+ * Copyright (c) 2010 Ira W. Snyder <iws@ovro.caltech.edu>
+ */
+
+#include <linux/acpi.h>
+#include <linux/delay.h>
+#include <linux/dmi.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <asm/pci_x86.h>
+#include <asm/pci-direct.h>
+
+#include "bus_numa.h"
+
+static void __init cnb20le_res(u8 bus, u8 slot, u8 func)
+{
+ struct pci_root_info *info;
+ struct pci_root_res *root_res;
+ struct resource res;
+ u16 word1, word2;
+ u8 fbus, lbus;
+
+ /* read the PCI bus numbers */
+ fbus = read_pci_config_byte(bus, slot, func, 0x44);
+ lbus = read_pci_config_byte(bus, slot, func, 0x45);
+ info = alloc_pci_root_info(fbus, lbus, 0, 0);
+
+ /*
+ * Add the legacy IDE ports on bus 0
+ *
+ * These do not exist anywhere in the bridge registers, AFAICT. I do
+ * not have the datasheet, so this is the best I can do.
+ */
+ if (fbus == 0) {
+ update_res(info, 0x01f0, 0x01f7, IORESOURCE_IO, 0);
+ update_res(info, 0x03f6, 0x03f6, IORESOURCE_IO, 0);
+ update_res(info, 0x0170, 0x0177, IORESOURCE_IO, 0);
+ update_res(info, 0x0376, 0x0376, IORESOURCE_IO, 0);
+ update_res(info, 0xffa0, 0xffaf, IORESOURCE_IO, 0);
+ }
+
+ /* read the non-prefetchable memory window */
+ word1 = read_pci_config_16(bus, slot, func, 0xc0);
+ word2 = read_pci_config_16(bus, slot, func, 0xc2);
+ if (word1 != word2) {
+ res.start = ((resource_size_t) word1 << 16) | 0x0000;
+ res.end = ((resource_size_t) word2 << 16) | 0xffff;
+ res.flags = IORESOURCE_MEM;
+ update_res(info, res.start, res.end, res.flags, 0);
+ }
+
+ /* read the prefetchable memory window */
+ word1 = read_pci_config_16(bus, slot, func, 0xc4);
+ word2 = read_pci_config_16(bus, slot, func, 0xc6);
+ if (word1 != word2) {
+ res.start = ((resource_size_t) word1 << 16) | 0x0000;
+ res.end = ((resource_size_t) word2 << 16) | 0xffff;
+ res.flags = IORESOURCE_MEM | IORESOURCE_PREFETCH;
+ update_res(info, res.start, res.end, res.flags, 0);
+ }
+
+ /* read the IO port window */
+ word1 = read_pci_config_16(bus, slot, func, 0xd0);
+ word2 = read_pci_config_16(bus, slot, func, 0xd2);
+ if (word1 != word2) {
+ res.start = word1;
+ res.end = word2;
+ res.flags = IORESOURCE_IO;
+ update_res(info, res.start, res.end, res.flags, 0);
+ }
+
+ /* print information about this host bridge */
+ res.start = fbus;
+ res.end = lbus;
+ res.flags = IORESOURCE_BUS;
+ printk(KERN_INFO "CNB20LE PCI Host Bridge (domain 0000 %pR)\n", &res);
+
+ list_for_each_entry(root_res, &info->resources, list)
+ printk(KERN_INFO "host bridge window %pR\n", &root_res->res);
+}
+
+static int __init broadcom_postcore_init(void)
+{
+ u8 bus = 0, slot = 0;
+ u32 id;
+ u16 vendor, device;
+
+#ifdef CONFIG_ACPI
+ /*
+ * We should get host bridge information from ACPI unless the BIOS
+ * doesn't support it.
+ */
+ if (!acpi_disabled && acpi_os_get_root_pointer())
+ return 0;
+#endif
+
+ id = read_pci_config(bus, slot, 0, PCI_VENDOR_ID);
+ vendor = id & 0xffff;
+ device = (id >> 16) & 0xffff;
+
+ if (vendor == PCI_VENDOR_ID_SERVERWORKS &&
+ device == PCI_DEVICE_ID_SERVERWORKS_LE) {
+ cnb20le_res(bus, slot, 0);
+ cnb20le_res(bus, slot, 1);
+ }
+ return 0;
+}
+
+postcore_initcall(broadcom_postcore_init);
diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c
new file mode 100644
index 0000000000..e4a525e59e
--- /dev/null
+++ b/arch/x86/pci/bus_numa.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/range.h>
+
+#include "bus_numa.h"
+
+LIST_HEAD(pci_root_infos);
+
+static struct pci_root_info *x86_find_pci_root_info(int bus)
+{
+ struct pci_root_info *info;
+
+ list_for_each_entry(info, &pci_root_infos, list)
+ if (info->busn.start == bus)
+ return info;
+
+ return NULL;
+}
+
+int x86_pci_root_bus_node(int bus)
+{
+ struct pci_root_info *info = x86_find_pci_root_info(bus);
+
+ if (!info)
+ return NUMA_NO_NODE;
+
+ return info->node;
+}
+
+void x86_pci_root_bus_resources(int bus, struct list_head *resources)
+{
+ struct pci_root_info *info = x86_find_pci_root_info(bus);
+ struct pci_root_res *root_res;
+ struct resource_entry *window;
+ bool found = false;
+
+ if (!info)
+ goto default_resources;
+
+ printk(KERN_DEBUG "PCI: root bus %02x: hardware-probed resources\n",
+ bus);
+
+ /* already added by acpi ? */
+ resource_list_for_each_entry(window, resources)
+ if (window->res->flags & IORESOURCE_BUS) {
+ found = true;
+ break;
+ }
+
+ if (!found)
+ pci_add_resource(resources, &info->busn);
+
+ list_for_each_entry(root_res, &info->resources, list)
+ pci_add_resource(resources, &root_res->res);
+
+ return;
+
+default_resources:
+ /*
+ * We don't have any host bridge aperture information from the
+ * "native host bridge drivers," e.g., amd_bus or broadcom_bus,
+ * so fall back to the defaults historically used by pci_create_bus().
+ */
+ printk(KERN_DEBUG "PCI: root bus %02x: using default resources\n", bus);
+ pci_add_resource(resources, &ioport_resource);
+ pci_add_resource(resources, &iomem_resource);
+}
+
+struct pci_root_info __init *alloc_pci_root_info(int bus_min, int bus_max,
+ int node, int link)
+{
+ struct pci_root_info *info;
+
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
+
+ if (!info)
+ return info;
+
+ sprintf(info->name, "PCI Bus #%02x", bus_min);
+
+ INIT_LIST_HEAD(&info->resources);
+ info->busn.name = info->name;
+ info->busn.start = bus_min;
+ info->busn.end = bus_max;
+ info->busn.flags = IORESOURCE_BUS;
+ info->node = node;
+ info->link = link;
+
+ list_add_tail(&info->list, &pci_root_infos);
+
+ return info;
+}
+
+void update_res(struct pci_root_info *info, resource_size_t start,
+ resource_size_t end, unsigned long flags, int merge)
+{
+ struct resource *res;
+ struct pci_root_res *root_res;
+
+ if (start > end)
+ return;
+
+ if (start == RESOURCE_SIZE_MAX)
+ return;
+
+ if (!merge)
+ goto addit;
+
+ /* try to merge it with old one */
+ list_for_each_entry(root_res, &info->resources, list) {
+ resource_size_t final_start, final_end;
+ resource_size_t common_start, common_end;
+
+ res = &root_res->res;
+ if (res->flags != flags)
+ continue;
+
+ common_start = max(res->start, start);
+ common_end = min(res->end, end);
+ if (common_start > common_end + 1)
+ continue;
+
+ final_start = min(res->start, start);
+ final_end = max(res->end, end);
+
+ res->start = final_start;
+ res->end = final_end;
+ return;
+ }
+
+addit:
+
+ /* need to add that */
+ root_res = kzalloc(sizeof(*root_res), GFP_KERNEL);
+ if (!root_res)
+ return;
+
+ res = &root_res->res;
+ res->name = info->name;
+ res->flags = flags;
+ res->start = start;
+ res->end = end;
+
+ list_add_tail(&root_res->list, &info->resources);
+}
diff --git a/arch/x86/pci/bus_numa.h b/arch/x86/pci/bus_numa.h
new file mode 100644
index 0000000000..697dd841b1
--- /dev/null
+++ b/arch/x86/pci/bus_numa.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BUS_NUMA_H
+#define __BUS_NUMA_H
+/*
+ * sub bus (transparent) will use entres from 3 to store extra from
+ * root, so need to make sure we have enough slot there.
+ */
+struct pci_root_res {
+ struct list_head list;
+ struct resource res;
+};
+
+struct pci_root_info {
+ struct list_head list;
+ char name[12];
+ struct list_head resources;
+ struct resource busn;
+ int node;
+ int link;
+};
+
+extern struct list_head pci_root_infos;
+struct pci_root_info *alloc_pci_root_info(int bus_min, int bus_max,
+ int node, int link);
+extern void update_res(struct pci_root_info *info, resource_size_t start,
+ resource_size_t end, unsigned long flags, int merge);
+#endif
diff --git a/arch/x86/pci/ce4100.c b/arch/x86/pci/ce4100.c
new file mode 100644
index 0000000000..87313701f0
--- /dev/null
+++ b/arch/x86/pci/ce4100.c
@@ -0,0 +1,324 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright(c) 2010 Intel Corporation. All rights reserved.
+ *
+ * Contact Information:
+ * Intel Corporation
+ * 2200 Mission College Blvd.
+ * Santa Clara, CA 97052
+ *
+ * This provides access methods for PCI registers that mis-behave on
+ * the CE4100. Each register can be assigned a private init, read and
+ * write routine. The exception to this is the bridge device. The
+ * bridge device is the only device on bus zero (0) that requires any
+ * fixup so it is a special case ATM
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+
+#include <asm/ce4100.h>
+#include <asm/pci_x86.h>
+
+struct sim_reg {
+ u32 value;
+ u32 mask;
+};
+
+struct sim_dev_reg {
+ int dev_func;
+ int reg;
+ void (*init)(struct sim_dev_reg *reg);
+ void (*read)(struct sim_dev_reg *reg, u32 *value);
+ void (*write)(struct sim_dev_reg *reg, u32 value);
+ struct sim_reg sim_reg;
+};
+
+struct sim_reg_op {
+ void (*init)(struct sim_dev_reg *reg);
+ void (*read)(struct sim_dev_reg *reg, u32 value);
+ void (*write)(struct sim_dev_reg *reg, u32 value);
+};
+
+#define MB (1024 * 1024)
+#define KB (1024)
+#define SIZE_TO_MASK(size) (~(size - 1))
+
+#define DEFINE_REG(device, func, offset, size, init_op, read_op, write_op)\
+{ PCI_DEVFN(device, func), offset, init_op, read_op, write_op,\
+ {0, SIZE_TO_MASK(size)} },
+
+/*
+ * All read/write functions are called with pci_config_lock held.
+ */
+static void reg_init(struct sim_dev_reg *reg)
+{
+ pci_direct_conf1.read(0, 1, reg->dev_func, reg->reg, 4,
+ &reg->sim_reg.value);
+}
+
+static void reg_read(struct sim_dev_reg *reg, u32 *value)
+{
+ *value = reg->sim_reg.value;
+}
+
+static void reg_write(struct sim_dev_reg *reg, u32 value)
+{
+ reg->sim_reg.value = (value & reg->sim_reg.mask) |
+ (reg->sim_reg.value & ~reg->sim_reg.mask);
+}
+
+static void sata_reg_init(struct sim_dev_reg *reg)
+{
+ pci_direct_conf1.read(0, 1, PCI_DEVFN(14, 0), 0x10, 4,
+ &reg->sim_reg.value);
+ reg->sim_reg.value += 0x400;
+}
+
+static void ehci_reg_read(struct sim_dev_reg *reg, u32 *value)
+{
+ reg_read(reg, value);
+ if (*value != reg->sim_reg.mask)
+ *value |= 0x100;
+}
+
+static void sata_revid_init(struct sim_dev_reg *reg)
+{
+ reg->sim_reg.value = 0x01060100;
+ reg->sim_reg.mask = 0;
+}
+
+static void sata_revid_read(struct sim_dev_reg *reg, u32 *value)
+{
+ reg_read(reg, value);
+}
+
+static void reg_noirq_read(struct sim_dev_reg *reg, u32 *value)
+{
+ /* force interrupt pin value to 0 */
+ *value = reg->sim_reg.value & 0xfff00ff;
+}
+
+static struct sim_dev_reg bus1_fixups[] = {
+ DEFINE_REG(2, 0, 0x10, (16*MB), reg_init, reg_read, reg_write)
+ DEFINE_REG(2, 0, 0x14, (256), reg_init, reg_read, reg_write)
+ DEFINE_REG(2, 1, 0x10, (64*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(3, 0, 0x10, (64*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(4, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(4, 1, 0x10, (128*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(6, 0, 0x10, (512*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(6, 1, 0x10, (512*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(6, 2, 0x10, (64*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(8, 0, 0x10, (1*MB), reg_init, reg_read, reg_write)
+ DEFINE_REG(8, 1, 0x10, (64*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(8, 2, 0x10, (64*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(9, 0, 0x10 , (1*MB), reg_init, reg_read, reg_write)
+ DEFINE_REG(9, 0, 0x14, (64*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(10, 0, 0x10, (256), reg_init, reg_read, reg_write)
+ DEFINE_REG(10, 0, 0x14, (256*MB), reg_init, reg_read, reg_write)
+ DEFINE_REG(11, 0, 0x10, (256), reg_init, reg_read, reg_write)
+ DEFINE_REG(11, 0, 0x14, (256), reg_init, reg_read, reg_write)
+ DEFINE_REG(11, 1, 0x10, (256), reg_init, reg_read, reg_write)
+ DEFINE_REG(11, 2, 0x10, (256), reg_init, reg_read, reg_write)
+ DEFINE_REG(11, 2, 0x14, (256), reg_init, reg_read, reg_write)
+ DEFINE_REG(11, 2, 0x18, (256), reg_init, reg_read, reg_write)
+ DEFINE_REG(11, 3, 0x10, (256), reg_init, reg_read, reg_write)
+ DEFINE_REG(11, 3, 0x14, (256), reg_init, reg_read, reg_write)
+ DEFINE_REG(11, 4, 0x10, (256), reg_init, reg_read, reg_write)
+ DEFINE_REG(11, 5, 0x10, (64*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(11, 6, 0x10, (256), reg_init, reg_read, reg_write)
+ DEFINE_REG(11, 7, 0x10, (64*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(11, 7, 0x3c, 256, reg_init, reg_noirq_read, reg_write)
+ DEFINE_REG(12, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(12, 0, 0x14, (256), reg_init, reg_read, reg_write)
+ DEFINE_REG(12, 1, 0x10, (1024), reg_init, reg_read, reg_write)
+ DEFINE_REG(13, 0, 0x10, (32*KB), reg_init, ehci_reg_read, reg_write)
+ DEFINE_REG(13, 1, 0x10, (32*KB), reg_init, ehci_reg_read, reg_write)
+ DEFINE_REG(14, 0, 0x8, 0, sata_revid_init, sata_revid_read, 0)
+ DEFINE_REG(14, 0, 0x10, 0, reg_init, reg_read, reg_write)
+ DEFINE_REG(14, 0, 0x14, 0, reg_init, reg_read, reg_write)
+ DEFINE_REG(14, 0, 0x18, 0, reg_init, reg_read, reg_write)
+ DEFINE_REG(14, 0, 0x1C, 0, reg_init, reg_read, reg_write)
+ DEFINE_REG(14, 0, 0x20, 0, reg_init, reg_read, reg_write)
+ DEFINE_REG(14, 0, 0x24, (0x200), sata_reg_init, reg_read, reg_write)
+ DEFINE_REG(15, 0, 0x10, (64*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(15, 0, 0x14, (64*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(16, 0, 0x10, (64*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(16, 0, 0x14, (64*MB), reg_init, reg_read, reg_write)
+ DEFINE_REG(16, 0, 0x18, (64*MB), reg_init, reg_read, reg_write)
+ DEFINE_REG(16, 0, 0x3c, 256, reg_init, reg_noirq_read, reg_write)
+ DEFINE_REG(17, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(18, 0, 0x10, (1*KB), reg_init, reg_read, reg_write)
+ DEFINE_REG(18, 0, 0x3c, 256, reg_init, reg_noirq_read, reg_write)
+};
+
+static void __init init_sim_regs(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(bus1_fixups); i++) {
+ if (bus1_fixups[i].init)
+ bus1_fixups[i].init(&bus1_fixups[i]);
+ }
+}
+
+static inline void extract_bytes(u32 *value, int reg, int len)
+{
+ uint32_t mask;
+
+ *value >>= ((reg & 3) * 8);
+ mask = 0xFFFFFFFF >> ((4 - len) * 8);
+ *value &= mask;
+}
+
+static int bridge_read(unsigned int devfn, int reg, int len, u32 *value)
+{
+ u32 av_bridge_base, av_bridge_limit;
+ int retval = 0;
+
+ switch (reg) {
+ /* Make BARs appear to not request any memory. */
+ case PCI_BASE_ADDRESS_0:
+ case PCI_BASE_ADDRESS_0 + 1:
+ case PCI_BASE_ADDRESS_0 + 2:
+ case PCI_BASE_ADDRESS_0 + 3:
+ *value = 0;
+ break;
+
+ /* Since subordinate bus number register is hardwired
+ * to zero and read only, so do the simulation.
+ */
+ case PCI_PRIMARY_BUS:
+ if (len == 4)
+ *value = 0x00010100;
+ break;
+
+ case PCI_SUBORDINATE_BUS:
+ *value = 1;
+ break;
+
+ case PCI_MEMORY_BASE:
+ case PCI_MEMORY_LIMIT:
+ /* Get the A/V bridge base address. */
+ pci_direct_conf1.read(0, 0, devfn,
+ PCI_BASE_ADDRESS_0, 4, &av_bridge_base);
+
+ av_bridge_limit = av_bridge_base + (512*MB - 1);
+ av_bridge_limit >>= 16;
+ av_bridge_limit &= 0xFFF0;
+
+ av_bridge_base >>= 16;
+ av_bridge_base &= 0xFFF0;
+
+ if (reg == PCI_MEMORY_LIMIT)
+ *value = av_bridge_limit;
+ else if (len == 2)
+ *value = av_bridge_base;
+ else
+ *value = (av_bridge_limit << 16) | av_bridge_base;
+ break;
+ /* Make prefetchable memory limit smaller than prefetchable
+ * memory base, so not claim prefetchable memory space.
+ */
+ case PCI_PREF_MEMORY_BASE:
+ *value = 0xFFF0;
+ break;
+ case PCI_PREF_MEMORY_LIMIT:
+ *value = 0x0;
+ break;
+ /* Make IO limit smaller than IO base, so not claim IO space. */
+ case PCI_IO_BASE:
+ *value = 0xF0;
+ break;
+ case PCI_IO_LIMIT:
+ *value = 0;
+ break;
+ default:
+ retval = 1;
+ }
+ return retval;
+}
+
+static int ce4100_bus1_read(unsigned int devfn, int reg, int len, u32 *value)
+{
+ unsigned long flags;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(bus1_fixups); i++) {
+ if (bus1_fixups[i].dev_func == devfn &&
+ bus1_fixups[i].reg == (reg & ~3) &&
+ bus1_fixups[i].read) {
+
+ raw_spin_lock_irqsave(&pci_config_lock, flags);
+ bus1_fixups[i].read(&(bus1_fixups[i]), value);
+ raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+ extract_bytes(value, reg, len);
+ return 0;
+ }
+ }
+ return -1;
+}
+
+static int ce4100_conf_read(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 *value)
+{
+ WARN_ON(seg);
+
+ if (bus == 1 && !ce4100_bus1_read(devfn, reg, len, value))
+ return 0;
+
+ if (bus == 0 && (PCI_DEVFN(1, 0) == devfn) &&
+ !bridge_read(devfn, reg, len, value))
+ return 0;
+
+ return pci_direct_conf1.read(seg, bus, devfn, reg, len, value);
+}
+
+static int ce4100_bus1_write(unsigned int devfn, int reg, int len, u32 value)
+{
+ unsigned long flags;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(bus1_fixups); i++) {
+ if (bus1_fixups[i].dev_func == devfn &&
+ bus1_fixups[i].reg == (reg & ~3) &&
+ bus1_fixups[i].write) {
+
+ raw_spin_lock_irqsave(&pci_config_lock, flags);
+ bus1_fixups[i].write(&(bus1_fixups[i]), value);
+ raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+ return 0;
+ }
+ }
+ return -1;
+}
+
+static int ce4100_conf_write(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 value)
+{
+ WARN_ON(seg);
+
+ if (bus == 1 && !ce4100_bus1_write(devfn, reg, len, value))
+ return 0;
+
+ /* Discard writes to A/V bridge BAR. */
+ if (bus == 0 && PCI_DEVFN(1, 0) == devfn &&
+ ((reg & ~3) == PCI_BASE_ADDRESS_0))
+ return 0;
+
+ return pci_direct_conf1.write(seg, bus, devfn, reg, len, value);
+}
+
+static const struct pci_raw_ops ce4100_pci_conf = {
+ .read = ce4100_conf_read,
+ .write = ce4100_conf_write,
+};
+
+int __init ce4100_pci_init(void)
+{
+ init_sim_regs();
+ raw_pci_ops = &ce4100_pci_conf;
+ /* Indicate caller that it should invoke pci_legacy_init() */
+ return 1;
+}
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
new file mode 100644
index 0000000000..ddb7986032
--- /dev/null
+++ b/arch/x86/pci/common.c
@@ -0,0 +1,734 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Low-Level PCI Support for PC
+ *
+ * (c) 1999--2000 Martin Mares <mj@ucw.cz>
+ */
+
+#include <linux/sched.h>
+#include <linux/pci.h>
+#include <linux/pci-acpi.h>
+#include <linux/ioport.h>
+#include <linux/init.h>
+#include <linux/dmi.h>
+#include <linux/slab.h>
+
+#include <asm/acpi.h>
+#include <asm/segment.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/pci_x86.h>
+#include <asm/setup.h>
+#include <asm/irqdomain.h>
+
+unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 |
+ PCI_PROBE_MMCONF;
+
+static int pci_bf_sort;
+int pci_routeirq;
+int noioapicquirk;
+#ifdef CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS
+int noioapicreroute = 0;
+#else
+int noioapicreroute = 1;
+#endif
+int pcibios_last_bus = -1;
+unsigned long pirq_table_addr;
+const struct pci_raw_ops *__read_mostly raw_pci_ops;
+const struct pci_raw_ops *__read_mostly raw_pci_ext_ops;
+
+int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn,
+ int reg, int len, u32 *val)
+{
+ if (domain == 0 && reg < 256 && raw_pci_ops)
+ return raw_pci_ops->read(domain, bus, devfn, reg, len, val);
+ if (raw_pci_ext_ops)
+ return raw_pci_ext_ops->read(domain, bus, devfn, reg, len, val);
+ return -EINVAL;
+}
+
+int raw_pci_write(unsigned int domain, unsigned int bus, unsigned int devfn,
+ int reg, int len, u32 val)
+{
+ if (domain == 0 && reg < 256 && raw_pci_ops)
+ return raw_pci_ops->write(domain, bus, devfn, reg, len, val);
+ if (raw_pci_ext_ops)
+ return raw_pci_ext_ops->write(domain, bus, devfn, reg, len, val);
+ return -EINVAL;
+}
+
+static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *value)
+{
+ return raw_pci_read(pci_domain_nr(bus), bus->number,
+ devfn, where, size, value);
+}
+
+static int pci_write(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 value)
+{
+ return raw_pci_write(pci_domain_nr(bus), bus->number,
+ devfn, where, size, value);
+}
+
+struct pci_ops pci_root_ops = {
+ .read = pci_read,
+ .write = pci_write,
+};
+
+/*
+ * This interrupt-safe spinlock protects all accesses to PCI configuration
+ * space, except for the mmconfig (ECAM) based operations.
+ */
+DEFINE_RAW_SPINLOCK(pci_config_lock);
+
+static int __init can_skip_ioresource_align(const struct dmi_system_id *d)
+{
+ pci_probe |= PCI_CAN_SKIP_ISA_ALIGN;
+ printk(KERN_INFO "PCI: %s detected, can skip ISA alignment\n", d->ident);
+ return 0;
+}
+
+static const struct dmi_system_id can_skip_pciprobe_dmi_table[] __initconst = {
+/*
+ * Systems where PCI IO resource ISA alignment can be skipped
+ * when the ISA enable bit in the bridge control is not set
+ */
+ {
+ .callback = can_skip_ioresource_align,
+ .ident = "IBM System x3800",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "x3800"),
+ },
+ },
+ {
+ .callback = can_skip_ioresource_align,
+ .ident = "IBM System x3850",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "x3850"),
+ },
+ },
+ {
+ .callback = can_skip_ioresource_align,
+ .ident = "IBM System x3950",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "x3950"),
+ },
+ },
+ {}
+};
+
+void __init dmi_check_skip_isa_align(void)
+{
+ dmi_check_system(can_skip_pciprobe_dmi_table);
+}
+
+static void pcibios_fixup_device_resources(struct pci_dev *dev)
+{
+ struct resource *rom_r = &dev->resource[PCI_ROM_RESOURCE];
+ struct resource *bar_r;
+ int bar;
+
+ if (pci_probe & PCI_NOASSIGN_BARS) {
+ /*
+ * If the BIOS did not assign the BAR, zero out the
+ * resource so the kernel doesn't attempt to assign
+ * it later on in pci_assign_unassigned_resources
+ */
+ for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) {
+ bar_r = &dev->resource[bar];
+ if (bar_r->start == 0 && bar_r->end != 0) {
+ bar_r->flags = 0;
+ bar_r->end = 0;
+ }
+ }
+ }
+
+ if (pci_probe & PCI_NOASSIGN_ROMS) {
+ if (rom_r->parent)
+ return;
+ if (rom_r->start) {
+ /* we deal with BIOS assigned ROM later */
+ return;
+ }
+ rom_r->start = rom_r->end = rom_r->flags = 0;
+ }
+}
+
+/*
+ * Called after each bus is probed, but before its children
+ * are examined.
+ */
+
+void pcibios_fixup_bus(struct pci_bus *b)
+{
+ struct pci_dev *dev;
+
+ pci_read_bridge_bases(b);
+ list_for_each_entry(dev, &b->devices, bus_list)
+ pcibios_fixup_device_resources(dev);
+}
+
+void pcibios_add_bus(struct pci_bus *bus)
+{
+ acpi_pci_add_bus(bus);
+}
+
+void pcibios_remove_bus(struct pci_bus *bus)
+{
+ acpi_pci_remove_bus(bus);
+}
+
+/*
+ * Only use DMI information to set this if nothing was passed
+ * on the kernel command line (which was parsed earlier).
+ */
+
+static int __init set_bf_sort(const struct dmi_system_id *d)
+{
+ if (pci_bf_sort == pci_bf_sort_default) {
+ pci_bf_sort = pci_dmi_bf;
+ printk(KERN_INFO "PCI: %s detected, enabling pci=bfsort.\n", d->ident);
+ }
+ return 0;
+}
+
+static void __init read_dmi_type_b1(const struct dmi_header *dm,
+ void *private_data)
+{
+ u8 *data = (u8 *)dm + 4;
+
+ if (dm->type != 0xB1)
+ return;
+ if ((((*(u32 *)data) >> 9) & 0x03) == 0x01)
+ set_bf_sort((const struct dmi_system_id *)private_data);
+}
+
+static int __init find_sort_method(const struct dmi_system_id *d)
+{
+ dmi_walk(read_dmi_type_b1, (void *)d);
+ return 0;
+}
+
+/*
+ * Enable renumbering of PCI bus# ranges to reach all PCI busses (Cardbus)
+ */
+#ifdef __i386__
+static int __init assign_all_busses(const struct dmi_system_id *d)
+{
+ pci_probe |= PCI_ASSIGN_ALL_BUSSES;
+ printk(KERN_INFO "%s detected: enabling PCI bus# renumbering"
+ " (pci=assign-busses)\n", d->ident);
+ return 0;
+}
+#endif
+
+static int __init set_scan_all(const struct dmi_system_id *d)
+{
+ printk(KERN_INFO "PCI: %s detected, enabling pci=pcie_scan_all\n",
+ d->ident);
+ pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS);
+ return 0;
+}
+
+static const struct dmi_system_id pciprobe_dmi_table[] __initconst = {
+#ifdef __i386__
+/*
+ * Laptops which need pci=assign-busses to see Cardbus cards
+ */
+ {
+ .callback = assign_all_busses,
+ .ident = "Samsung X20 Laptop",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Samsung Electronics"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "SX20S"),
+ },
+ },
+#endif /* __i386__ */
+ {
+ .callback = set_bf_sort,
+ .ident = "Dell PowerEdge 1950",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 1950"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "Dell PowerEdge 1955",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 1955"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "Dell PowerEdge 2900",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 2900"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "Dell PowerEdge 2950",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 2950"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "Dell PowerEdge R900",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R900"),
+ },
+ },
+ {
+ .callback = find_sort_method,
+ .ident = "Dell System",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "HP ProLiant BL20p G3",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL20p G3"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "HP ProLiant BL20p G4",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL20p G4"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "HP ProLiant BL30p G1",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL30p G1"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "HP ProLiant BL25p G1",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL25p G1"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "HP ProLiant BL35p G1",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL35p G1"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "HP ProLiant BL45p G1",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL45p G1"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "HP ProLiant BL45p G2",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL45p G2"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "HP ProLiant BL460c G1",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL460c G1"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "HP ProLiant BL465c G1",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL465c G1"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "HP ProLiant BL480c G1",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL480c G1"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "HP ProLiant BL685c G1",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL685c G1"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "HP ProLiant DL360",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL360"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "HP ProLiant DL380",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL380"),
+ },
+ },
+#ifdef __i386__
+ {
+ .callback = assign_all_busses,
+ .ident = "Compaq EVO N800c",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Compaq"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "EVO N800c"),
+ },
+ },
+#endif
+ {
+ .callback = set_bf_sort,
+ .ident = "HP ProLiant DL385 G2",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL385 G2"),
+ },
+ },
+ {
+ .callback = set_bf_sort,
+ .ident = "HP ProLiant DL585 G2",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL585 G2"),
+ },
+ },
+ {
+ .callback = set_scan_all,
+ .ident = "Stratus/NEC ftServer",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Stratus"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ftServer"),
+ },
+ },
+ {
+ .callback = set_scan_all,
+ .ident = "Stratus/NEC ftServer",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R32"),
+ },
+ },
+ {
+ .callback = set_scan_all,
+ .ident = "Stratus/NEC ftServer",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R31"),
+ },
+ },
+ {}
+};
+
+void __init dmi_check_pciprobe(void)
+{
+ dmi_check_system(pciprobe_dmi_table);
+}
+
+void pcibios_scan_root(int busnum)
+{
+ struct pci_bus *bus;
+ struct pci_sysdata *sd;
+ LIST_HEAD(resources);
+
+ sd = kzalloc(sizeof(*sd), GFP_KERNEL);
+ if (!sd) {
+ printk(KERN_ERR "PCI: OOM, skipping PCI bus %02x\n", busnum);
+ return;
+ }
+ sd->node = x86_pci_root_bus_node(busnum);
+ x86_pci_root_bus_resources(busnum, &resources);
+ printk(KERN_DEBUG "PCI: Probing PCI hardware (bus %02x)\n", busnum);
+ bus = pci_scan_root_bus(NULL, busnum, &pci_root_ops, sd, &resources);
+ if (!bus) {
+ pci_free_resource_list(&resources);
+ kfree(sd);
+ return;
+ }
+ pci_bus_add_devices(bus);
+}
+
+void __init pcibios_set_cache_line_size(void)
+{
+ struct cpuinfo_x86 *c = &boot_cpu_data;
+
+ /*
+ * Set PCI cacheline size to that of the CPU if the CPU has reported it.
+ * (For older CPUs that don't support cpuid, we se it to 32 bytes
+ * It's also good for 386/486s (which actually have 16)
+ * as quite a few PCI devices do not support smaller values.
+ */
+ if (c->x86_clflush_size > 0) {
+ pci_dfl_cache_line_size = c->x86_clflush_size >> 2;
+ printk(KERN_DEBUG "PCI: pci_cache_line_size set to %d bytes\n",
+ pci_dfl_cache_line_size << 2);
+ } else {
+ pci_dfl_cache_line_size = 32 >> 2;
+ printk(KERN_DEBUG "PCI: Unknown cacheline size. Setting to 32 bytes\n");
+ }
+}
+
+int __init pcibios_init(void)
+{
+ if (!raw_pci_ops && !raw_pci_ext_ops) {
+ printk(KERN_WARNING "PCI: System does not support PCI\n");
+ return 0;
+ }
+
+ pcibios_set_cache_line_size();
+ pcibios_resource_survey();
+
+ if (pci_bf_sort >= pci_force_bf)
+ pci_sort_breadthfirst();
+ return 0;
+}
+
+char *__init pcibios_setup(char *str)
+{
+ if (!strcmp(str, "off")) {
+ pci_probe = 0;
+ return NULL;
+ } else if (!strcmp(str, "bfsort")) {
+ pci_bf_sort = pci_force_bf;
+ return NULL;
+ } else if (!strcmp(str, "nobfsort")) {
+ pci_bf_sort = pci_force_nobf;
+ return NULL;
+ }
+#ifdef CONFIG_PCI_BIOS
+ else if (!strcmp(str, "bios")) {
+ pci_probe = PCI_PROBE_BIOS;
+ return NULL;
+ } else if (!strcmp(str, "nobios")) {
+ pci_probe &= ~PCI_PROBE_BIOS;
+ return NULL;
+ } else if (!strcmp(str, "biosirq")) {
+ pci_probe |= PCI_BIOS_IRQ_SCAN;
+ return NULL;
+ } else if (!strncmp(str, "pirqaddr=", 9)) {
+ pirq_table_addr = simple_strtoul(str+9, NULL, 0);
+ return NULL;
+ }
+#endif
+#ifdef CONFIG_PCI_DIRECT
+ else if (!strcmp(str, "conf1")) {
+ pci_probe = PCI_PROBE_CONF1 | PCI_NO_CHECKS;
+ return NULL;
+ }
+ else if (!strcmp(str, "conf2")) {
+ pci_probe = PCI_PROBE_CONF2 | PCI_NO_CHECKS;
+ return NULL;
+ }
+#endif
+#ifdef CONFIG_PCI_MMCONFIG
+ else if (!strcmp(str, "nommconf")) {
+ pci_probe &= ~PCI_PROBE_MMCONF;
+ return NULL;
+ }
+ else if (!strcmp(str, "check_enable_amd_mmconf")) {
+ pci_probe |= PCI_CHECK_ENABLE_AMD_MMCONF;
+ return NULL;
+ }
+#endif
+ else if (!strcmp(str, "noacpi")) {
+ acpi_noirq_set();
+ return NULL;
+ }
+ else if (!strcmp(str, "noearly")) {
+ pci_probe |= PCI_PROBE_NOEARLY;
+ return NULL;
+ }
+ else if (!strcmp(str, "usepirqmask")) {
+ pci_probe |= PCI_USE_PIRQ_MASK;
+ return NULL;
+ } else if (!strncmp(str, "irqmask=", 8)) {
+ pcibios_irq_mask = simple_strtol(str+8, NULL, 0);
+ return NULL;
+ } else if (!strncmp(str, "lastbus=", 8)) {
+ pcibios_last_bus = simple_strtol(str+8, NULL, 0);
+ return NULL;
+ } else if (!strcmp(str, "rom")) {
+ pci_probe |= PCI_ASSIGN_ROMS;
+ return NULL;
+ } else if (!strcmp(str, "norom")) {
+ pci_probe |= PCI_NOASSIGN_ROMS;
+ return NULL;
+ } else if (!strcmp(str, "nobar")) {
+ pci_probe |= PCI_NOASSIGN_BARS;
+ return NULL;
+ } else if (!strcmp(str, "assign-busses")) {
+ pci_probe |= PCI_ASSIGN_ALL_BUSSES;
+ return NULL;
+ } else if (!strcmp(str, "use_crs")) {
+ pci_probe |= PCI_USE__CRS;
+ return NULL;
+ } else if (!strcmp(str, "nocrs")) {
+ pci_probe |= PCI_ROOT_NO_CRS;
+ return NULL;
+ } else if (!strcmp(str, "use_e820")) {
+ pci_probe |= PCI_USE_E820;
+ add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+ return NULL;
+ } else if (!strcmp(str, "no_e820")) {
+ pci_probe |= PCI_NO_E820;
+ add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+ return NULL;
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+ } else if (!strcmp(str, "big_root_window")) {
+ pci_probe |= PCI_BIG_ROOT_WINDOW;
+ return NULL;
+#endif
+ } else if (!strcmp(str, "routeirq")) {
+ pci_routeirq = 1;
+ return NULL;
+ } else if (!strcmp(str, "skip_isa_align")) {
+ pci_probe |= PCI_CAN_SKIP_ISA_ALIGN;
+ return NULL;
+ } else if (!strcmp(str, "noioapicquirk")) {
+ noioapicquirk = 1;
+ return NULL;
+ } else if (!strcmp(str, "ioapicreroute")) {
+ if (noioapicreroute != -1)
+ noioapicreroute = 0;
+ return NULL;
+ } else if (!strcmp(str, "noioapicreroute")) {
+ if (noioapicreroute != -1)
+ noioapicreroute = 1;
+ return NULL;
+ }
+ return str;
+}
+
+unsigned int pcibios_assign_all_busses(void)
+{
+ return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0;
+}
+
+static void set_dev_domain_options(struct pci_dev *pdev)
+{
+ if (is_vmd(pdev->bus))
+ pdev->hotplug_user_indicators = 1;
+}
+
+int pcibios_device_add(struct pci_dev *dev)
+{
+ struct pci_setup_rom *rom;
+ struct irq_domain *msidom;
+ struct setup_data *data;
+ u64 pa_data;
+
+ pa_data = boot_params.hdr.setup_data;
+ while (pa_data) {
+ data = memremap(pa_data, sizeof(*rom), MEMREMAP_WB);
+ if (!data)
+ return -ENOMEM;
+
+ if (data->type == SETUP_PCI) {
+ rom = (struct pci_setup_rom *)data;
+
+ if ((pci_domain_nr(dev->bus) == rom->segment) &&
+ (dev->bus->number == rom->bus) &&
+ (PCI_SLOT(dev->devfn) == rom->device) &&
+ (PCI_FUNC(dev->devfn) == rom->function) &&
+ (dev->vendor == rom->vendor) &&
+ (dev->device == rom->devid)) {
+ dev->rom = pa_data +
+ offsetof(struct pci_setup_rom, romdata);
+ dev->romlen = rom->pcilen;
+ }
+ }
+ pa_data = data->next;
+ memunmap(data);
+ }
+ set_dev_domain_options(dev);
+
+ /*
+ * Setup the initial MSI domain of the device. If the underlying
+ * bus has a PCI/MSI irqdomain associated use the bus domain,
+ * otherwise set the default domain. This ensures that special irq
+ * domains e.g. VMD are preserved. The default ensures initial
+ * operation if irq remapping is not active. If irq remapping is
+ * active it will overwrite the domain pointer when the device is
+ * associated to a remapping domain.
+ */
+ msidom = dev_get_msi_domain(&dev->bus->dev);
+ if (!msidom)
+ msidom = x86_pci_msi_default_domain;
+ dev_set_msi_domain(&dev->dev, msidom);
+ return 0;
+}
+
+int pcibios_enable_device(struct pci_dev *dev, int mask)
+{
+ int err;
+
+ if ((err = pci_enable_resources(dev, mask)) < 0)
+ return err;
+
+ if (!pci_dev_msi_enabled(dev))
+ return pcibios_enable_irq(dev);
+ return 0;
+}
+
+void pcibios_disable_device (struct pci_dev *dev)
+{
+ if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq)
+ pcibios_disable_irq(dev);
+}
+
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+void pcibios_release_device(struct pci_dev *dev)
+{
+ if (atomic_dec_return(&dev->enable_cnt) >= 0)
+ pcibios_disable_device(dev);
+
+}
+#endif
+
+int pci_ext_cfg_avail(void)
+{
+ if (raw_pci_ext_ops)
+ return 1;
+ else
+ return 0;
+}
+
+#if IS_ENABLED(CONFIG_VMD)
+struct pci_dev *pci_real_dma_dev(struct pci_dev *dev)
+{
+ if (is_vmd(dev->bus))
+ return to_pci_sysdata(dev->bus)->vmd_dev;
+
+ return dev;
+}
+#endif
diff --git a/arch/x86/pci/direct.c b/arch/x86/pci/direct.c
new file mode 100644
index 0000000000..a51074c559
--- /dev/null
+++ b/arch/x86/pci/direct.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * direct.c - Low-level direct PCI config space access
+ */
+
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/dmi.h>
+#include <asm/pci_x86.h>
+
+/*
+ * Functions for accessing PCI base (first 256 bytes) and extended
+ * (4096 bytes per PCI function) configuration space with type 1
+ * accesses.
+ */
+
+#define PCI_CONF1_ADDRESS(bus, devfn, reg) \
+ (0x80000000 | ((reg & 0xF00) << 16) | (bus << 16) \
+ | (devfn << 8) | (reg & 0xFC))
+
+static int pci_conf1_read(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 *value)
+{
+ unsigned long flags;
+
+ if (seg || (bus > 255) || (devfn > 255) || (reg > 4095)) {
+ *value = -1;
+ return -EINVAL;
+ }
+
+ raw_spin_lock_irqsave(&pci_config_lock, flags);
+
+ outl(PCI_CONF1_ADDRESS(bus, devfn, reg), 0xCF8);
+
+ switch (len) {
+ case 1:
+ *value = inb(0xCFC + (reg & 3));
+ break;
+ case 2:
+ *value = inw(0xCFC + (reg & 2));
+ break;
+ case 4:
+ *value = inl(0xCFC);
+ break;
+ }
+
+ raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+
+ return 0;
+}
+
+static int pci_conf1_write(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 value)
+{
+ unsigned long flags;
+
+ if (seg || (bus > 255) || (devfn > 255) || (reg > 4095))
+ return -EINVAL;
+
+ raw_spin_lock_irqsave(&pci_config_lock, flags);
+
+ outl(PCI_CONF1_ADDRESS(bus, devfn, reg), 0xCF8);
+
+ switch (len) {
+ case 1:
+ outb((u8)value, 0xCFC + (reg & 3));
+ break;
+ case 2:
+ outw((u16)value, 0xCFC + (reg & 2));
+ break;
+ case 4:
+ outl((u32)value, 0xCFC);
+ break;
+ }
+
+ raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+
+ return 0;
+}
+
+#undef PCI_CONF1_ADDRESS
+
+const struct pci_raw_ops pci_direct_conf1 = {
+ .read = pci_conf1_read,
+ .write = pci_conf1_write,
+};
+
+
+/*
+ * Functions for accessing PCI configuration space with type 2 accesses
+ */
+
+#define PCI_CONF2_ADDRESS(dev, reg) (u16)(0xC000 | (dev << 8) | reg)
+
+static int pci_conf2_read(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 *value)
+{
+ unsigned long flags;
+ int dev, fn;
+
+ WARN_ON(seg);
+ if ((bus > 255) || (devfn > 255) || (reg > 255)) {
+ *value = -1;
+ return -EINVAL;
+ }
+
+ dev = PCI_SLOT(devfn);
+ fn = PCI_FUNC(devfn);
+
+ if (dev & 0x10)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+
+ raw_spin_lock_irqsave(&pci_config_lock, flags);
+
+ outb((u8)(0xF0 | (fn << 1)), 0xCF8);
+ outb((u8)bus, 0xCFA);
+
+ switch (len) {
+ case 1:
+ *value = inb(PCI_CONF2_ADDRESS(dev, reg));
+ break;
+ case 2:
+ *value = inw(PCI_CONF2_ADDRESS(dev, reg));
+ break;
+ case 4:
+ *value = inl(PCI_CONF2_ADDRESS(dev, reg));
+ break;
+ }
+
+ outb(0, 0xCF8);
+
+ raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+
+ return 0;
+}
+
+static int pci_conf2_write(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 value)
+{
+ unsigned long flags;
+ int dev, fn;
+
+ WARN_ON(seg);
+ if ((bus > 255) || (devfn > 255) || (reg > 255))
+ return -EINVAL;
+
+ dev = PCI_SLOT(devfn);
+ fn = PCI_FUNC(devfn);
+
+ if (dev & 0x10)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+
+ raw_spin_lock_irqsave(&pci_config_lock, flags);
+
+ outb((u8)(0xF0 | (fn << 1)), 0xCF8);
+ outb((u8)bus, 0xCFA);
+
+ switch (len) {
+ case 1:
+ outb((u8)value, PCI_CONF2_ADDRESS(dev, reg));
+ break;
+ case 2:
+ outw((u16)value, PCI_CONF2_ADDRESS(dev, reg));
+ break;
+ case 4:
+ outl((u32)value, PCI_CONF2_ADDRESS(dev, reg));
+ break;
+ }
+
+ outb(0, 0xCF8);
+
+ raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+
+ return 0;
+}
+
+#undef PCI_CONF2_ADDRESS
+
+static const struct pci_raw_ops pci_direct_conf2 = {
+ .read = pci_conf2_read,
+ .write = pci_conf2_write,
+};
+
+
+/*
+ * Before we decide to use direct hardware access mechanisms, we try to do some
+ * trivial checks to ensure it at least _seems_ to be working -- we just test
+ * whether bus 00 contains a host bridge (this is similar to checking
+ * techniques used in XFree86, but ours should be more reliable since we
+ * attempt to make use of direct access hints provided by the PCI BIOS).
+ *
+ * This should be close to trivial, but it isn't, because there are buggy
+ * chipsets (yes, you guessed it, by Intel and Compaq) that have no class ID.
+ */
+static int __init pci_sanity_check(const struct pci_raw_ops *o)
+{
+ u32 x = 0;
+ int devfn;
+
+ if (pci_probe & PCI_NO_CHECKS)
+ return 1;
+ /* Assume Type 1 works for newer systems.
+ This handles machines that don't have anything on PCI Bus 0. */
+ if (dmi_get_bios_year() >= 2001)
+ return 1;
+
+ for (devfn = 0; devfn < 0x100; devfn++) {
+ if (o->read(0, 0, devfn, PCI_CLASS_DEVICE, 2, &x))
+ continue;
+ if (x == PCI_CLASS_BRIDGE_HOST || x == PCI_CLASS_DISPLAY_VGA)
+ return 1;
+
+ if (o->read(0, 0, devfn, PCI_VENDOR_ID, 2, &x))
+ continue;
+ if (x == PCI_VENDOR_ID_INTEL || x == PCI_VENDOR_ID_COMPAQ)
+ return 1;
+ }
+
+ DBG(KERN_WARNING "PCI: Sanity check failed\n");
+ return 0;
+}
+
+static int __init pci_check_type1(void)
+{
+ unsigned long flags;
+ unsigned int tmp;
+ int works = 0;
+
+ local_irq_save(flags);
+
+ outb(0x01, 0xCFB);
+ tmp = inl(0xCF8);
+ outl(0x80000000, 0xCF8);
+ if (inl(0xCF8) == 0x80000000 && pci_sanity_check(&pci_direct_conf1)) {
+ works = 1;
+ }
+ outl(tmp, 0xCF8);
+ local_irq_restore(flags);
+
+ return works;
+}
+
+static int __init pci_check_type2(void)
+{
+ unsigned long flags;
+ int works = 0;
+
+ local_irq_save(flags);
+
+ outb(0x00, 0xCFB);
+ outb(0x00, 0xCF8);
+ outb(0x00, 0xCFA);
+ if (inb(0xCF8) == 0x00 && inb(0xCFA) == 0x00 &&
+ pci_sanity_check(&pci_direct_conf2)) {
+ works = 1;
+ }
+
+ local_irq_restore(flags);
+
+ return works;
+}
+
+void __init pci_direct_init(int type)
+{
+ if (type == 0)
+ return;
+ printk(KERN_INFO "PCI: Using configuration type %d for base access\n",
+ type);
+ if (type == 1) {
+ raw_pci_ops = &pci_direct_conf1;
+ if (raw_pci_ext_ops)
+ return;
+ if (!(pci_probe & PCI_HAS_IO_ECS))
+ return;
+ printk(KERN_INFO "PCI: Using configuration type 1 "
+ "for extended access\n");
+ raw_pci_ext_ops = &pci_direct_conf1;
+ return;
+ }
+ raw_pci_ops = &pci_direct_conf2;
+}
+
+int __init pci_direct_probe(void)
+{
+ if ((pci_probe & PCI_PROBE_CONF1) == 0)
+ goto type2;
+ if (!request_region(0xCF8, 8, "PCI conf1"))
+ goto type2;
+
+ if (pci_check_type1()) {
+ raw_pci_ops = &pci_direct_conf1;
+ port_cf9_safe = true;
+ return 1;
+ }
+ release_region(0xCF8, 8);
+
+ type2:
+ if ((pci_probe & PCI_PROBE_CONF2) == 0)
+ return 0;
+ if (!request_region(0xCF8, 4, "PCI conf2"))
+ return 0;
+ if (!request_region(0xC000, 0x1000, "PCI conf2"))
+ goto fail2;
+
+ if (pci_check_type2()) {
+ raw_pci_ops = &pci_direct_conf2;
+ port_cf9_safe = true;
+ return 2;
+ }
+
+ release_region(0xC000, 0x1000);
+ fail2:
+ release_region(0xCF8, 4);
+ return 0;
+}
diff --git a/arch/x86/pci/early.c b/arch/x86/pci/early.c
new file mode 100644
index 0000000000..f5fc953e58
--- /dev/null
+++ b/arch/x86/pci/early.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <asm/pci-direct.h>
+#include <asm/io.h>
+#include <asm/pci_x86.h>
+
+/* Direct PCI access. This is used for PCI accesses in early boot before
+ the PCI subsystem works. */
+
+u32 read_pci_config(u8 bus, u8 slot, u8 func, u8 offset)
+{
+ u32 v;
+ outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
+ v = inl(0xcfc);
+ return v;
+}
+
+u8 read_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset)
+{
+ u8 v;
+ outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
+ v = inb(0xcfc + (offset&3));
+ return v;
+}
+
+u16 read_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset)
+{
+ u16 v;
+ outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
+ v = inw(0xcfc + (offset&2));
+ return v;
+}
+
+void write_pci_config(u8 bus, u8 slot, u8 func, u8 offset,
+ u32 val)
+{
+ outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
+ outl(val, 0xcfc);
+}
+
+void write_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset, u8 val)
+{
+ outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
+ outb(val, 0xcfc + (offset&3));
+}
+
+void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val)
+{
+ outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
+ outw(val, 0xcfc + (offset&2));
+}
+
+int early_pci_allowed(void)
+{
+ return (pci_probe & (PCI_PROBE_CONF1|PCI_PROBE_NOEARLY)) ==
+ PCI_PROBE_CONF1;
+}
+
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
new file mode 100644
index 0000000000..f347c20247
--- /dev/null
+++ b/arch/x86/pci/fixup.c
@@ -0,0 +1,965 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Exceptions for specific devices. Usually work-arounds for fatal design flaws.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/dmi.h>
+#include <linux/pci.h>
+#include <linux/suspend.h>
+#include <linux/vgaarb.h>
+#include <asm/amd_nb.h>
+#include <asm/hpet.h>
+#include <asm/pci_x86.h>
+
+static void pci_fixup_i450nx(struct pci_dev *d)
+{
+ /*
+ * i450NX -- Find and scan all secondary buses on all PXB's.
+ */
+ int pxb, reg;
+ u8 busno, suba, subb;
+
+ dev_warn(&d->dev, "Searching for i450NX host bridges\n");
+ reg = 0xd0;
+ for(pxb = 0; pxb < 2; pxb++) {
+ pci_read_config_byte(d, reg++, &busno);
+ pci_read_config_byte(d, reg++, &suba);
+ pci_read_config_byte(d, reg++, &subb);
+ dev_dbg(&d->dev, "i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno,
+ suba, subb);
+ if (busno)
+ pcibios_scan_root(busno); /* Bus A */
+ if (suba < subb)
+ pcibios_scan_root(suba+1); /* Bus B */
+ }
+ pcibios_last_bus = -1;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82451NX, pci_fixup_i450nx);
+
+static void pci_fixup_i450gx(struct pci_dev *d)
+{
+ /*
+ * i450GX and i450KX -- Find and scan all secondary buses.
+ * (called separately for each PCI bridge found)
+ */
+ u8 busno;
+ pci_read_config_byte(d, 0x4a, &busno);
+ dev_info(&d->dev, "i440KX/GX host bridge; secondary bus %02x\n", busno);
+ pcibios_scan_root(busno);
+ pcibios_last_bus = -1;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82454GX, pci_fixup_i450gx);
+
+static void pci_fixup_umc_ide(struct pci_dev *d)
+{
+ /*
+ * UM8886BF IDE controller sets region type bits incorrectly,
+ * therefore they look like memory despite of them being I/O.
+ */
+ int i;
+
+ dev_warn(&d->dev, "Fixing base address flags\n");
+ for(i = 0; i < 4; i++)
+ d->resource[i].flags |= PCI_BASE_ADDRESS_SPACE_IO;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_UMC, PCI_DEVICE_ID_UMC_UM8886BF, pci_fixup_umc_ide);
+
+static void pci_fixup_latency(struct pci_dev *d)
+{
+ /*
+ * SiS 5597 and 5598 chipsets require latency timer set to
+ * at most 32 to avoid lockups.
+ */
+ dev_dbg(&d->dev, "Setting max latency to 32\n");
+ pcibios_max_latency = 32;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SI, PCI_DEVICE_ID_SI_5597, pci_fixup_latency);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SI, PCI_DEVICE_ID_SI_5598, pci_fixup_latency);
+
+static void pci_fixup_piix4_acpi(struct pci_dev *d)
+{
+ /*
+ * PIIX4 ACPI device: hardwired IRQ9
+ */
+ d->irq = 9;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371AB_3, pci_fixup_piix4_acpi);
+
+/*
+ * Addresses issues with problems in the memory write queue timer in
+ * certain VIA Northbridges. This bugfix is per VIA's specifications,
+ * except for the KL133/KM133: clearing bit 5 on those Northbridges seems
+ * to trigger a bug in its integrated ProSavage video card, which
+ * causes screen corruption. We only clear bits 6 and 7 for that chipset,
+ * until VIA can provide us with definitive information on why screen
+ * corruption occurs, and what exactly those bits do.
+ *
+ * VIA 8363,8622,8361 Northbridges:
+ * - bits 5, 6, 7 at offset 0x55 need to be turned off
+ * VIA 8367 (KT266x) Northbridges:
+ * - bits 5, 6, 7 at offset 0x95 need to be turned off
+ * VIA 8363 rev 0x81/0x84 (KL133/KM133) Northbridges:
+ * - bits 6, 7 at offset 0x55 need to be turned off
+ */
+
+#define VIA_8363_KL133_REVISION_ID 0x81
+#define VIA_8363_KM133_REVISION_ID 0x84
+
+static void pci_fixup_via_northbridge_bug(struct pci_dev *d)
+{
+ u8 v;
+ int where = 0x55;
+ int mask = 0x1f; /* clear bits 5, 6, 7 by default */
+
+ if (d->device == PCI_DEVICE_ID_VIA_8367_0) {
+ /* fix pci bus latency issues resulted by NB bios error
+ it appears on bug free^Wreduced kt266x's bios forces
+ NB latency to zero */
+ pci_write_config_byte(d, PCI_LATENCY_TIMER, 0);
+
+ where = 0x95; /* the memory write queue timer register is
+ different for the KT266x's: 0x95 not 0x55 */
+ } else if (d->device == PCI_DEVICE_ID_VIA_8363_0 &&
+ (d->revision == VIA_8363_KL133_REVISION_ID ||
+ d->revision == VIA_8363_KM133_REVISION_ID)) {
+ mask = 0x3f; /* clear only bits 6 and 7; clearing bit 5
+ causes screen corruption on the KL133/KM133 */
+ }
+
+ pci_read_config_byte(d, where, &v);
+ if (v & ~mask) {
+ dev_warn(&d->dev, "Disabling VIA memory write queue (PCI ID %04x, rev %02x): [%02x] %02x & %02x -> %02x\n", \
+ d->device, d->revision, where, v, mask, v & mask);
+ v &= mask;
+ pci_write_config_byte(d, where, v);
+ }
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8363_0, pci_fixup_via_northbridge_bug);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8622, pci_fixup_via_northbridge_bug);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8361, pci_fixup_via_northbridge_bug);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8367_0, pci_fixup_via_northbridge_bug);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8363_0, pci_fixup_via_northbridge_bug);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8622, pci_fixup_via_northbridge_bug);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8361, pci_fixup_via_northbridge_bug);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8367_0, pci_fixup_via_northbridge_bug);
+
+/*
+ * For some reasons Intel decided that certain parts of their
+ * 815, 845 and some other chipsets must look like PCI-to-PCI bridges
+ * while they are obviously not. The 82801 family (AA, AB, BAM/CAM,
+ * BA/CA/DB and E) PCI bridges are actually HUB-to-PCI ones, according
+ * to Intel terminology. These devices do forward all addresses from
+ * system to PCI bus no matter what are their window settings, so they are
+ * "transparent" (or subtractive decoding) from programmers point of view.
+ */
+static void pci_fixup_transparent_bridge(struct pci_dev *dev)
+{
+ if ((dev->device & 0xff00) == 0x2400)
+ dev->transparent = 1;
+}
+DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
+ PCI_CLASS_BRIDGE_PCI, 8, pci_fixup_transparent_bridge);
+
+/*
+ * Fixup for C1 Halt Disconnect problem on nForce2 systems.
+ *
+ * From information provided by "Allen Martin" <AMartin@nvidia.com>:
+ *
+ * A hang is caused when the CPU generates a very fast CONNECT/HALT cycle
+ * sequence. Workaround is to set the SYSTEM_IDLE_TIMEOUT to 80 ns.
+ * This allows the state-machine and timer to return to a proper state within
+ * 80 ns of the CONNECT and probe appearing together. Since the CPU will not
+ * issue another HALT within 80 ns of the initial HALT, the failure condition
+ * is avoided.
+ */
+static void pci_fixup_nforce2(struct pci_dev *dev)
+{
+ u32 val;
+
+ /*
+ * Chip Old value New value
+ * C17 0x1F0FFF01 0x1F01FF01
+ * C18D 0x9F0FFF01 0x9F01FF01
+ *
+ * Northbridge chip version may be determined by
+ * reading the PCI revision ID (0xC1 or greater is C18D).
+ */
+ pci_read_config_dword(dev, 0x6c, &val);
+
+ /*
+ * Apply fixup if needed, but don't touch disconnect state
+ */
+ if ((val & 0x00FF0000) != 0x00010000) {
+ dev_warn(&dev->dev, "nForce2 C1 Halt Disconnect fixup\n");
+ pci_write_config_dword(dev, 0x6c, (val & 0xFF00FFFF) | 0x00010000);
+ }
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE2, pci_fixup_nforce2);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE2, pci_fixup_nforce2);
+
+/* Max PCI Express root ports */
+#define MAX_PCIEROOT 6
+static int quirk_aspm_offset[MAX_PCIEROOT << 3];
+
+#define GET_INDEX(a, b) ((((a) - PCI_DEVICE_ID_INTEL_MCH_PA) << 3) + ((b) & 7))
+
+static int quirk_pcie_aspm_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *value)
+{
+ return raw_pci_read(pci_domain_nr(bus), bus->number,
+ devfn, where, size, value);
+}
+
+/*
+ * Replace the original pci bus ops for write with a new one that will filter
+ * the request to insure ASPM cannot be enabled.
+ */
+static int quirk_pcie_aspm_write(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 value)
+{
+ u8 offset;
+
+ offset = quirk_aspm_offset[GET_INDEX(bus->self->device, devfn)];
+
+ if ((offset) && (where == offset))
+ value = value & ~PCI_EXP_LNKCTL_ASPMC;
+
+ return raw_pci_write(pci_domain_nr(bus), bus->number,
+ devfn, where, size, value);
+}
+
+static struct pci_ops quirk_pcie_aspm_ops = {
+ .read = quirk_pcie_aspm_read,
+ .write = quirk_pcie_aspm_write,
+};
+
+/*
+ * Prevents PCI Express ASPM (Active State Power Management) being enabled.
+ *
+ * Save the register offset, where the ASPM control bits are located,
+ * for each PCI Express device that is in the device list of
+ * the root port in an array for fast indexing. Replace the bus ops
+ * with the modified one.
+ */
+static void pcie_rootport_aspm_quirk(struct pci_dev *pdev)
+{
+ int i;
+ struct pci_bus *pbus;
+ struct pci_dev *dev;
+
+ if ((pbus = pdev->subordinate) == NULL)
+ return;
+
+ /*
+ * Check if the DID of pdev matches one of the six root ports. This
+ * check is needed in the case this function is called directly by the
+ * hot-plug driver.
+ */
+ if ((pdev->device < PCI_DEVICE_ID_INTEL_MCH_PA) ||
+ (pdev->device > PCI_DEVICE_ID_INTEL_MCH_PC1))
+ return;
+
+ if (list_empty(&pbus->devices)) {
+ /*
+ * If no device is attached to the root port at power-up or
+ * after hot-remove, the pbus->devices is empty and this code
+ * will set the offsets to zero and the bus ops to parent's bus
+ * ops, which is unmodified.
+ */
+ for (i = GET_INDEX(pdev->device, 0); i <= GET_INDEX(pdev->device, 7); ++i)
+ quirk_aspm_offset[i] = 0;
+
+ pci_bus_set_ops(pbus, pbus->parent->ops);
+ } else {
+ /*
+ * If devices are attached to the root port at power-up or
+ * after hot-add, the code loops through the device list of
+ * each root port to save the register offsets and replace the
+ * bus ops.
+ */
+ list_for_each_entry(dev, &pbus->devices, bus_list)
+ /* There are 0 to 8 devices attached to this bus */
+ quirk_aspm_offset[GET_INDEX(pdev->device, dev->devfn)] =
+ dev->pcie_cap + PCI_EXP_LNKCTL;
+
+ pci_bus_set_ops(pbus, &quirk_pcie_aspm_ops);
+ dev_info(&pbus->dev, "writes to ASPM control bits will be ignored\n");
+ }
+
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PA, pcie_rootport_aspm_quirk);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PA1, pcie_rootport_aspm_quirk);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PB, pcie_rootport_aspm_quirk);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PB1, pcie_rootport_aspm_quirk);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PC, pcie_rootport_aspm_quirk);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PC1, pcie_rootport_aspm_quirk);
+
+/*
+ * Fixup to mark boot BIOS video selected by BIOS before it changes
+ *
+ * From information provided by "Jon Smirl" <jonsmirl@gmail.com>
+ *
+ * The standard boot ROM sequence for an x86 machine uses the BIOS
+ * to select an initial video card for boot display. This boot video
+ * card will have its BIOS copied to 0xC0000 in system RAM.
+ * IORESOURCE_ROM_SHADOW is used to associate the boot video
+ * card with this copy. On laptops this copy has to be used since
+ * the main ROM may be compressed or combined with another image.
+ * See pci_map_rom() for use of this flag. Before marking the device
+ * with IORESOURCE_ROM_SHADOW check if a vga_default_device is already set
+ * by either arch code or vga-arbitration; if so only apply the fixup to this
+ * already-determined primary video card.
+ */
+
+static void pci_fixup_video(struct pci_dev *pdev)
+{
+ struct pci_dev *bridge;
+ struct pci_bus *bus;
+ u16 config;
+ struct resource *res;
+
+ /* Is VGA routed to us? */
+ bus = pdev->bus;
+ while (bus) {
+ bridge = bus->self;
+
+ /*
+ * From information provided by
+ * "David Miller" <davem@davemloft.net>
+ * The bridge control register is valid for PCI header
+ * type BRIDGE, or CARDBUS. Host to PCI controllers use
+ * PCI header type NORMAL.
+ */
+ if (bridge && (pci_is_bridge(bridge))) {
+ pci_read_config_word(bridge, PCI_BRIDGE_CONTROL,
+ &config);
+ if (!(config & PCI_BRIDGE_CTL_VGA))
+ return;
+ }
+ bus = bus->parent;
+ }
+ if (!vga_default_device() || pdev == vga_default_device()) {
+ pci_read_config_word(pdev, PCI_COMMAND, &config);
+ if (config & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) {
+ res = &pdev->resource[PCI_ROM_RESOURCE];
+
+ pci_disable_rom(pdev);
+ if (res->parent)
+ release_resource(res);
+
+ res->start = 0xC0000;
+ res->end = res->start + 0x20000 - 1;
+ res->flags = IORESOURCE_MEM | IORESOURCE_ROM_SHADOW |
+ IORESOURCE_PCI_FIXED;
+ dev_info(&pdev->dev, "Video device with shadowed ROM at %pR\n",
+ res);
+ }
+ }
+}
+DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_ANY_ID, PCI_ANY_ID,
+ PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_video);
+
+
+static const struct dmi_system_id msi_k8t_dmi_table[] = {
+ {
+ .ident = "MSI-K8T-Neo2Fir",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "MSI"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MS-6702E"),
+ },
+ },
+ {}
+};
+
+/*
+ * The AMD-Athlon64 board MSI "K8T Neo2-FIR" disables the onboard sound
+ * card if a PCI-soundcard is added.
+ *
+ * The BIOS only gives options "DISABLED" and "AUTO". This code sets
+ * the corresponding register-value to enable the soundcard.
+ *
+ * The soundcard is only enabled, if the mainboard is identified
+ * via DMI-tables and the soundcard is detected to be off.
+ */
+static void pci_fixup_msi_k8t_onboard_sound(struct pci_dev *dev)
+{
+ unsigned char val;
+ if (!dmi_check_system(msi_k8t_dmi_table))
+ return; /* only applies to MSI K8T Neo2-FIR */
+
+ pci_read_config_byte(dev, 0x50, &val);
+ if (val & 0x40) {
+ pci_write_config_byte(dev, 0x50, val & (~0x40));
+
+ /* verify the change for status output */
+ pci_read_config_byte(dev, 0x50, &val);
+ if (val & 0x40)
+ dev_info(&dev->dev, "Detected MSI K8T Neo2-FIR; "
+ "can't enable onboard soundcard!\n");
+ else
+ dev_info(&dev->dev, "Detected MSI K8T Neo2-FIR; "
+ "enabled onboard soundcard\n");
+ }
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237,
+ pci_fixup_msi_k8t_onboard_sound);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237,
+ pci_fixup_msi_k8t_onboard_sound);
+
+/*
+ * Some Toshiba laptops need extra code to enable their TI TSB43AB22/A.
+ *
+ * We pretend to bring them out of full D3 state, and restore the proper
+ * IRQ, PCI cache line size, and BARs, otherwise the device won't function
+ * properly. In some cases, the device will generate an interrupt on
+ * the wrong IRQ line, causing any devices sharing the line it's
+ * *supposed* to use to be disabled by the kernel's IRQ debug code.
+ */
+static u16 toshiba_line_size;
+
+static const struct dmi_system_id toshiba_ohci1394_dmi_table[] = {
+ {
+ .ident = "Toshiba PS5 based laptop",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "PS5"),
+ },
+ },
+ {
+ .ident = "Toshiba PSM4 based laptop",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "PSM4"),
+ },
+ },
+ {
+ .ident = "Toshiba A40 based laptop",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "PSA40U"),
+ },
+ },
+ { }
+};
+
+static void pci_pre_fixup_toshiba_ohci1394(struct pci_dev *dev)
+{
+ if (!dmi_check_system(toshiba_ohci1394_dmi_table))
+ return; /* only applies to certain Toshibas (so far) */
+
+ dev->current_state = PCI_D3cold;
+ pci_read_config_word(dev, PCI_CACHE_LINE_SIZE, &toshiba_line_size);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TI, 0x8032,
+ pci_pre_fixup_toshiba_ohci1394);
+
+static void pci_post_fixup_toshiba_ohci1394(struct pci_dev *dev)
+{
+ if (!dmi_check_system(toshiba_ohci1394_dmi_table))
+ return; /* only applies to certain Toshibas (so far) */
+
+ /* Restore config space on Toshiba laptops */
+ pci_write_config_word(dev, PCI_CACHE_LINE_SIZE, toshiba_line_size);
+ pci_read_config_byte(dev, PCI_INTERRUPT_LINE, (u8 *)&dev->irq);
+ pci_write_config_dword(dev, PCI_BASE_ADDRESS_0,
+ pci_resource_start(dev, 0));
+ pci_write_config_dword(dev, PCI_BASE_ADDRESS_1,
+ pci_resource_start(dev, 1));
+}
+DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_TI, 0x8032,
+ pci_post_fixup_toshiba_ohci1394);
+
+
+/*
+ * Prevent the BIOS trapping accesses to the Cyrix CS5530A video device
+ * configuration space.
+ */
+static void pci_early_fixup_cyrix_5530(struct pci_dev *dev)
+{
+ u8 r;
+ /* clear 'F4 Video Configuration Trap' bit */
+ pci_read_config_byte(dev, 0x42, &r);
+ r &= 0xfd;
+ pci_write_config_byte(dev, 0x42, r);
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY,
+ pci_early_fixup_cyrix_5530);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY,
+ pci_early_fixup_cyrix_5530);
+
+/*
+ * Siemens Nixdorf AG FSC Multiprocessor Interrupt Controller:
+ * prevent update of the BAR0, which doesn't look like a normal BAR.
+ */
+static void pci_siemens_interrupt_controller(struct pci_dev *dev)
+{
+ dev->resource[0].flags |= IORESOURCE_PCI_FIXED;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SIEMENS, 0x0015,
+ pci_siemens_interrupt_controller);
+
+/*
+ * SB600: Disable BAR1 on device 14.0 to avoid HPET resources from
+ * confusing the PCI engine:
+ */
+static void sb600_disable_hpet_bar(struct pci_dev *dev)
+{
+ u8 val;
+
+ /*
+ * The SB600 and SB700 both share the same device
+ * ID, but the PM register 0x55 does something different
+ * for the SB700, so make sure we are dealing with the
+ * SB600 before touching the bit:
+ */
+
+ pci_read_config_byte(dev, 0x08, &val);
+
+ if (val < 0x2F) {
+ outb(0x55, 0xCD6);
+ val = inb(0xCD7);
+
+ /* Set bit 7 in PM register 0x55 */
+ outb(0x55, 0xCD6);
+ outb(val | 0x80, 0xCD7);
+ }
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_ATI, 0x4385, sb600_disable_hpet_bar);
+
+#ifdef CONFIG_HPET_TIMER
+static void sb600_hpet_quirk(struct pci_dev *dev)
+{
+ struct resource *r = &dev->resource[1];
+
+ if (r->flags & IORESOURCE_MEM && r->start == hpet_address) {
+ r->flags |= IORESOURCE_PCI_FIXED;
+ dev_info(&dev->dev, "reg 0x14 contains HPET; making it immovable\n");
+ }
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, 0x4385, sb600_hpet_quirk);
+#endif
+
+/*
+ * Twinhead H12Y needs us to block out a region otherwise we map devices
+ * there and any access kills the box.
+ *
+ * See: https://bugzilla.kernel.org/show_bug.cgi?id=10231
+ *
+ * Match off the LPC and svid/sdid (older kernels lose the bridge subvendor)
+ */
+static void twinhead_reserve_killing_zone(struct pci_dev *dev)
+{
+ if (dev->subsystem_vendor == 0x14FF && dev->subsystem_device == 0xA003) {
+ pr_info("Reserving memory on Twinhead H12Y\n");
+ request_mem_region(0xFFB00000, 0x100000, "twinhead");
+ }
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone);
+
+/*
+ * Device [8086:2fc0]
+ * Erratum HSE43
+ * CONFIG_TDP_NOMINAL CSR Implemented at Incorrect Offset
+ * https://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v3-spec-update.html
+ *
+ * Devices [8086:6f60,6fa0,6fc0]
+ * Erratum BDF2
+ * PCI BARs in the Home Agent Will Return Non-Zero Values During Enumeration
+ * https://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html
+ */
+static void pci_invalid_bar(struct pci_dev *dev)
+{
+ dev->non_compliant_bars = 1;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa1ec, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa1ed, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa26c, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa26d, pci_invalid_bar);
+
+/*
+ * Device [1022:7808]
+ * 23. USB Wake on Connect/Disconnect with Low Speed Devices
+ * https://support.amd.com/TechDocs/46837.pdf
+ * Appendix A2
+ * https://support.amd.com/TechDocs/42413.pdf
+ */
+static void pci_fixup_amd_ehci_pme(struct pci_dev *dev)
+{
+ dev_info(&dev->dev, "PME# does not work under D3, disabling it\n");
+ dev->pme_support &= ~((PCI_PM_CAP_PME_D3hot | PCI_PM_CAP_PME_D3cold)
+ >> PCI_PM_CAP_PME_SHIFT);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x7808, pci_fixup_amd_ehci_pme);
+
+/*
+ * Device [1022:7914]
+ * When in D0, PME# doesn't get asserted when plugging USB 2.0 device.
+ */
+static void pci_fixup_amd_fch_xhci_pme(struct pci_dev *dev)
+{
+ dev_info(&dev->dev, "PME# does not work under D0, disabling it\n");
+ dev->pme_support &= ~(PCI_PM_CAP_PME_D0 >> PCI_PM_CAP_PME_SHIFT);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x7914, pci_fixup_amd_fch_xhci_pme);
+
+/*
+ * Apple MacBook Pro: Avoid [mem 0x7fa00000-0x7fbfffff]
+ *
+ * Using the [mem 0x7fa00000-0x7fbfffff] region, e.g., by assigning it to
+ * the 00:1c.0 Root Port, causes a conflict with [io 0x1804], which is used
+ * for soft poweroff and suspend-to-RAM.
+ *
+ * As far as we know, this is related to the address space, not to the Root
+ * Port itself. Attaching the quirk to the Root Port is a convenience, but
+ * it could probably also be a standalone DMI quirk.
+ *
+ * https://bugzilla.kernel.org/show_bug.cgi?id=103211
+ */
+static void quirk_apple_mbp_poweroff(struct pci_dev *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct resource *res;
+
+ if ((!dmi_match(DMI_PRODUCT_NAME, "MacBookPro11,4") &&
+ !dmi_match(DMI_PRODUCT_NAME, "MacBookPro11,5")) ||
+ pdev->bus->number != 0 || pdev->devfn != PCI_DEVFN(0x1c, 0))
+ return;
+
+ res = request_mem_region(0x7fa00000, 0x200000,
+ "MacBook Pro poweroff workaround");
+ if (res)
+ dev_info(dev, "claimed %s %pR\n", res->name, res);
+ else
+ dev_info(dev, "can't work around MacBook Pro poweroff issue\n");
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8c10, quirk_apple_mbp_poweroff);
+
+/*
+ * VMD-enabled root ports will change the source ID for all messages
+ * to the VMD device. Rather than doing device matching with the source
+ * ID, the AER driver should traverse the child device tree, reading
+ * AER registers to find the faulting device.
+ */
+static void quirk_no_aersid(struct pci_dev *pdev)
+{
+ /* VMD Domain */
+ if (is_vmd(pdev->bus) && pci_is_root_bus(pdev->bus))
+ pdev->bus->bus_flags |= PCI_BUS_FLAGS_NO_AERSID;
+}
+DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
+ PCI_CLASS_BRIDGE_PCI, 8, quirk_no_aersid);
+
+static void quirk_intel_th_dnv(struct pci_dev *dev)
+{
+ struct resource *r = &dev->resource[4];
+
+ /*
+ * Denverton reports 2k of RTIT_BAR (intel_th resource 4), which
+ * appears to be 4 MB in reality.
+ */
+ if (r->end == r->start + 0x7ff) {
+ r->start = 0;
+ r->end = 0x3fffff;
+ r->flags |= IORESOURCE_UNSET;
+ }
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x19e1, quirk_intel_th_dnv);
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+
+#define AMD_141b_MMIO_BASE(x) (0x80 + (x) * 0x8)
+#define AMD_141b_MMIO_BASE_RE_MASK BIT(0)
+#define AMD_141b_MMIO_BASE_WE_MASK BIT(1)
+#define AMD_141b_MMIO_BASE_MMIOBASE_MASK GENMASK(31,8)
+
+#define AMD_141b_MMIO_LIMIT(x) (0x84 + (x) * 0x8)
+#define AMD_141b_MMIO_LIMIT_MMIOLIMIT_MASK GENMASK(31,8)
+
+#define AMD_141b_MMIO_HIGH(x) (0x180 + (x) * 0x4)
+#define AMD_141b_MMIO_HIGH_MMIOBASE_MASK GENMASK(7,0)
+#define AMD_141b_MMIO_HIGH_MMIOLIMIT_SHIFT 16
+#define AMD_141b_MMIO_HIGH_MMIOLIMIT_MASK GENMASK(23,16)
+
+/*
+ * The PCI Firmware Spec, rev 3.2, notes that ACPI should optionally allow
+ * configuring host bridge windows using the _PRS and _SRS methods.
+ *
+ * But this is rarely implemented, so we manually enable a large 64bit BAR for
+ * PCIe device on AMD Family 15h (Models 00h-1fh, 30h-3fh, 60h-7fh) Processors
+ * here.
+ */
+static void pci_amd_enable_64bit_bar(struct pci_dev *dev)
+{
+ static const char *name = "PCI Bus 0000:00";
+ struct resource *res, *conflict;
+ u32 base, limit, high;
+ struct pci_dev *other;
+ unsigned i;
+
+ if (!(pci_probe & PCI_BIG_ROOT_WINDOW))
+ return;
+
+ /* Check that we are the only device of that type */
+ other = pci_get_device(dev->vendor, dev->device, NULL);
+ if (other != dev ||
+ (other = pci_get_device(dev->vendor, dev->device, other))) {
+ /* This is a multi-socket system, don't touch it for now */
+ pci_dev_put(other);
+ return;
+ }
+
+ for (i = 0; i < 8; i++) {
+ pci_read_config_dword(dev, AMD_141b_MMIO_BASE(i), &base);
+ pci_read_config_dword(dev, AMD_141b_MMIO_HIGH(i), &high);
+
+ /* Is this slot free? */
+ if (!(base & (AMD_141b_MMIO_BASE_RE_MASK |
+ AMD_141b_MMIO_BASE_WE_MASK)))
+ break;
+
+ base >>= 8;
+ base |= high << 24;
+
+ /* Abort if a slot already configures a 64bit BAR. */
+ if (base > 0x10000)
+ return;
+ }
+ if (i == 8)
+ return;
+
+ res = kzalloc(sizeof(*res), GFP_KERNEL);
+ if (!res)
+ return;
+
+ /*
+ * Allocate a 256GB window directly below the 0xfd00000000 hardware
+ * limit (see AMD Family 15h Models 30h-3Fh BKDG, sec 2.4.6).
+ */
+ res->name = name;
+ res->flags = IORESOURCE_PREFETCH | IORESOURCE_MEM |
+ IORESOURCE_MEM_64 | IORESOURCE_WINDOW;
+ res->start = 0xbd00000000ull;
+ res->end = 0xfd00000000ull - 1;
+
+ conflict = request_resource_conflict(&iomem_resource, res);
+ if (conflict) {
+ kfree(res);
+ if (conflict->name != name)
+ return;
+
+ /* We are resuming from suspend; just reenable the window */
+ res = conflict;
+ } else {
+ dev_info(&dev->dev, "adding root bus resource %pR (tainting kernel)\n",
+ res);
+ add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+ pci_bus_add_resource(dev->bus, res, 0);
+ }
+
+ base = ((res->start >> 8) & AMD_141b_MMIO_BASE_MMIOBASE_MASK) |
+ AMD_141b_MMIO_BASE_RE_MASK | AMD_141b_MMIO_BASE_WE_MASK;
+ limit = ((res->end + 1) >> 8) & AMD_141b_MMIO_LIMIT_MMIOLIMIT_MASK;
+ high = ((res->start >> 40) & AMD_141b_MMIO_HIGH_MMIOBASE_MASK) |
+ ((((res->end + 1) >> 40) << AMD_141b_MMIO_HIGH_MMIOLIMIT_SHIFT)
+ & AMD_141b_MMIO_HIGH_MMIOLIMIT_MASK);
+
+ pci_write_config_dword(dev, AMD_141b_MMIO_HIGH(i), high);
+ pci_write_config_dword(dev, AMD_141b_MMIO_LIMIT(i), limit);
+ pci_write_config_dword(dev, AMD_141b_MMIO_BASE(i), base);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar);
+
+#define RS690_LOWER_TOP_OF_DRAM2 0x30
+#define RS690_LOWER_TOP_OF_DRAM2_VALID 0x1
+#define RS690_UPPER_TOP_OF_DRAM2 0x31
+#define RS690_HTIU_NB_INDEX 0xA8
+#define RS690_HTIU_NB_INDEX_WR_ENABLE 0x100
+#define RS690_HTIU_NB_DATA 0xAC
+
+/*
+ * Some BIOS implementations support RAM above 4GB, but do not configure the
+ * PCI host to respond to bus master accesses for these addresses. These
+ * implementations set the TOP_OF_DRAM_SLOT1 register correctly, so PCI DMA
+ * works as expected for addresses below 4GB.
+ *
+ * Reference: "AMD RS690 ASIC Family Register Reference Guide" (pg. 2-57)
+ * https://www.amd.com/system/files/TechDocs/43372_rs690_rrg_3.00o.pdf
+ */
+static void rs690_fix_64bit_dma(struct pci_dev *pdev)
+{
+ u32 val = 0;
+ phys_addr_t top_of_dram = __pa(high_memory - 1) + 1;
+
+ if (top_of_dram <= (1ULL << 32))
+ return;
+
+ pci_write_config_dword(pdev, RS690_HTIU_NB_INDEX,
+ RS690_LOWER_TOP_OF_DRAM2);
+ pci_read_config_dword(pdev, RS690_HTIU_NB_DATA, &val);
+
+ if (val)
+ return;
+
+ pci_info(pdev, "Adjusting top of DRAM to %pa for 64-bit DMA support\n", &top_of_dram);
+
+ pci_write_config_dword(pdev, RS690_HTIU_NB_INDEX,
+ RS690_UPPER_TOP_OF_DRAM2 | RS690_HTIU_NB_INDEX_WR_ENABLE);
+ pci_write_config_dword(pdev, RS690_HTIU_NB_DATA, top_of_dram >> 32);
+
+ pci_write_config_dword(pdev, RS690_HTIU_NB_INDEX,
+ RS690_LOWER_TOP_OF_DRAM2 | RS690_HTIU_NB_INDEX_WR_ENABLE);
+ pci_write_config_dword(pdev, RS690_HTIU_NB_DATA,
+ top_of_dram | RS690_LOWER_TOP_OF_DRAM2_VALID);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7910, rs690_fix_64bit_dma);
+
+#endif
+
+#ifdef CONFIG_AMD_NB
+
+#define AMD_15B8_RCC_DEV2_EPF0_STRAP2 0x10136008
+#define AMD_15B8_RCC_DEV2_EPF0_STRAP2_NO_SOFT_RESET_DEV2_F0_MASK 0x00000080L
+
+static void quirk_clear_strap_no_soft_reset_dev2_f0(struct pci_dev *dev)
+{
+ u32 data;
+
+ if (!amd_smn_read(0, AMD_15B8_RCC_DEV2_EPF0_STRAP2, &data)) {
+ data &= ~AMD_15B8_RCC_DEV2_EPF0_STRAP2_NO_SOFT_RESET_DEV2_F0_MASK;
+ if (amd_smn_write(0, AMD_15B8_RCC_DEV2_EPF0_STRAP2, data))
+ pci_err(dev, "Failed to write data 0x%x\n", data);
+ } else {
+ pci_err(dev, "Failed to read data\n");
+ }
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15b8, quirk_clear_strap_no_soft_reset_dev2_f0);
+#endif
+
+/*
+ * When returning from D3cold to D0, firmware on some Google Coral and Reef
+ * family Chromebooks with Intel Apollo Lake SoC clobbers the headers of
+ * both the L1 PM Substates capability and the previous capability for the
+ * "Celeron N3350/Pentium N4200/Atom E3900 Series PCI Express Port B #1".
+ *
+ * Save those values at enumeration-time and restore them at resume.
+ */
+
+static u16 prev_cap, l1ss_cap;
+static u32 prev_header, l1ss_header;
+
+static void chromeos_save_apl_pci_l1ss_capability(struct pci_dev *dev)
+{
+ int pos = PCI_CFG_SPACE_SIZE, prev = 0;
+ u32 header, pheader = 0;
+
+ while (pos) {
+ pci_read_config_dword(dev, pos, &header);
+ if (PCI_EXT_CAP_ID(header) == PCI_EXT_CAP_ID_L1SS) {
+ prev_cap = prev;
+ prev_header = pheader;
+ l1ss_cap = pos;
+ l1ss_header = header;
+ return;
+ }
+
+ prev = pos;
+ pheader = header;
+ pos = PCI_EXT_CAP_NEXT(header);
+ }
+}
+
+static void chromeos_fixup_apl_pci_l1ss_capability(struct pci_dev *dev)
+{
+ u32 header;
+
+ if (!prev_cap || !prev_header || !l1ss_cap || !l1ss_header)
+ return;
+
+ /* Fixup the header of L1SS Capability if missing */
+ pci_read_config_dword(dev, l1ss_cap, &header);
+ if (header != l1ss_header) {
+ pci_write_config_dword(dev, l1ss_cap, l1ss_header);
+ pci_info(dev, "restore L1SS Capability header (was %#010x now %#010x)\n",
+ header, l1ss_header);
+ }
+
+ /* Fixup the link to L1SS Capability if missing */
+ pci_read_config_dword(dev, prev_cap, &header);
+ if (header != prev_header) {
+ pci_write_config_dword(dev, prev_cap, prev_header);
+ pci_info(dev, "restore previous Capability header (was %#010x now %#010x)\n",
+ header, prev_header);
+ }
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x5ad6, chromeos_save_apl_pci_l1ss_capability);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, 0x5ad6, chromeos_fixup_apl_pci_l1ss_capability);
+
+#ifdef CONFIG_SUSPEND
+/*
+ * Root Ports on some AMD SoCs advertise PME_Support for D3hot and D3cold, but
+ * if the SoC is put into a hardware sleep state by the amd-pmc driver, the
+ * Root Ports don't generate wakeup interrupts for USB devices.
+ *
+ * When suspending, remove D3hot and D3cold from the PME_Support advertised
+ * by the Root Port so we don't use those states if we're expecting wakeup
+ * interrupts. Restore the advertised PME_Support when resuming.
+ */
+static void amd_rp_pme_suspend(struct pci_dev *dev)
+{
+ struct pci_dev *rp;
+
+ /*
+ * PM_SUSPEND_ON means we're doing runtime suspend, which means
+ * amd-pmc will not be involved so PMEs during D3 work as advertised.
+ *
+ * The PMEs *do* work if amd-pmc doesn't put the SoC in the hardware
+ * sleep state, but we assume amd-pmc is always present.
+ */
+ if (pm_suspend_target_state == PM_SUSPEND_ON)
+ return;
+
+ rp = pcie_find_root_port(dev);
+ if (!rp->pm_cap)
+ return;
+
+ rp->pme_support &= ~((PCI_PM_CAP_PME_D3hot|PCI_PM_CAP_PME_D3cold) >>
+ PCI_PM_CAP_PME_SHIFT);
+ dev_info_once(&rp->dev, "quirk: disabling D3cold for suspend\n");
+}
+
+static void amd_rp_pme_resume(struct pci_dev *dev)
+{
+ struct pci_dev *rp;
+ u16 pmc;
+
+ rp = pcie_find_root_port(dev);
+ if (!rp->pm_cap)
+ return;
+
+ pci_read_config_word(rp, rp->pm_cap + PCI_PM_PMC, &pmc);
+ rp->pme_support = FIELD_GET(PCI_PM_CAP_PME_MASK, pmc);
+}
+/* Rembrandt (yellow_carp) */
+DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x162e, amd_rp_pme_suspend);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x162e, amd_rp_pme_resume);
+DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x162f, amd_rp_pme_suspend);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x162f, amd_rp_pme_resume);
+/* Phoenix (pink_sardine) */
+DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x1668, amd_rp_pme_suspend);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1668, amd_rp_pme_resume);
+DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x1669, amd_rp_pme_suspend);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1669, amd_rp_pme_resume);
+#endif /* CONFIG_SUSPEND */
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
new file mode 100644
index 0000000000..f2f4a5d50b
--- /dev/null
+++ b/arch/x86/pci/i386.c
@@ -0,0 +1,409 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Low-Level PCI Access for i386 machines
+ *
+ * Copyright 1993, 1994 Drew Eckhardt
+ * Visionary Computing
+ * (Unix and Linux consulting and custom programming)
+ * Drew@Colorado.EDU
+ * +1 (303) 786-7975
+ *
+ * Drew's work was sponsored by:
+ * iX Multiuser Multitasking Magazine
+ * Hannover, Germany
+ * hm@ix.de
+ *
+ * Copyright 1997--2000 Martin Mares <mj@ucw.cz>
+ *
+ * For more information, please consult the following manuals (look at
+ * http://www.pcisig.com/ for how to get them):
+ *
+ * PCI BIOS Specification
+ * PCI Local Bus Specification
+ * PCI to PCI Bridge Specification
+ * PCI System Design Guide
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/errno.h>
+#include <linux/memblock.h>
+
+#include <asm/memtype.h>
+#include <asm/e820/api.h>
+#include <asm/pci_x86.h>
+#include <asm/io_apic.h>
+
+
+/*
+ * This list of dynamic mappings is for temporarily maintaining
+ * original BIOS BAR addresses for possible reinstatement.
+ */
+struct pcibios_fwaddrmap {
+ struct list_head list;
+ struct pci_dev *dev;
+ resource_size_t fw_addr[DEVICE_COUNT_RESOURCE];
+};
+
+static LIST_HEAD(pcibios_fwaddrmappings);
+static DEFINE_SPINLOCK(pcibios_fwaddrmap_lock);
+static bool pcibios_fw_addr_done;
+
+/* Must be called with 'pcibios_fwaddrmap_lock' lock held. */
+static struct pcibios_fwaddrmap *pcibios_fwaddrmap_lookup(struct pci_dev *dev)
+{
+ struct pcibios_fwaddrmap *map;
+
+ lockdep_assert_held(&pcibios_fwaddrmap_lock);
+
+ list_for_each_entry(map, &pcibios_fwaddrmappings, list)
+ if (map->dev == dev)
+ return map;
+
+ return NULL;
+}
+
+static void
+pcibios_save_fw_addr(struct pci_dev *dev, int idx, resource_size_t fw_addr)
+{
+ unsigned long flags;
+ struct pcibios_fwaddrmap *map;
+
+ if (pcibios_fw_addr_done)
+ return;
+
+ spin_lock_irqsave(&pcibios_fwaddrmap_lock, flags);
+ map = pcibios_fwaddrmap_lookup(dev);
+ if (!map) {
+ spin_unlock_irqrestore(&pcibios_fwaddrmap_lock, flags);
+ map = kzalloc(sizeof(*map), GFP_KERNEL);
+ if (!map)
+ return;
+
+ map->dev = pci_dev_get(dev);
+ map->fw_addr[idx] = fw_addr;
+ INIT_LIST_HEAD(&map->list);
+
+ spin_lock_irqsave(&pcibios_fwaddrmap_lock, flags);
+ list_add_tail(&map->list, &pcibios_fwaddrmappings);
+ } else
+ map->fw_addr[idx] = fw_addr;
+ spin_unlock_irqrestore(&pcibios_fwaddrmap_lock, flags);
+}
+
+resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx)
+{
+ unsigned long flags;
+ struct pcibios_fwaddrmap *map;
+ resource_size_t fw_addr = 0;
+
+ if (pcibios_fw_addr_done)
+ return 0;
+
+ spin_lock_irqsave(&pcibios_fwaddrmap_lock, flags);
+ map = pcibios_fwaddrmap_lookup(dev);
+ if (map)
+ fw_addr = map->fw_addr[idx];
+ spin_unlock_irqrestore(&pcibios_fwaddrmap_lock, flags);
+
+ return fw_addr;
+}
+
+static void __init pcibios_fw_addr_list_del(void)
+{
+ unsigned long flags;
+ struct pcibios_fwaddrmap *entry, *next;
+
+ spin_lock_irqsave(&pcibios_fwaddrmap_lock, flags);
+ list_for_each_entry_safe(entry, next, &pcibios_fwaddrmappings, list) {
+ list_del(&entry->list);
+ pci_dev_put(entry->dev);
+ kfree(entry);
+ }
+ spin_unlock_irqrestore(&pcibios_fwaddrmap_lock, flags);
+ pcibios_fw_addr_done = true;
+}
+
+static int
+skip_isa_ioresource_align(struct pci_dev *dev) {
+
+ if ((pci_probe & PCI_CAN_SKIP_ISA_ALIGN) &&
+ !(dev->bus->bridge_ctl & PCI_BRIDGE_CTL_ISA))
+ return 1;
+ return 0;
+}
+
+/*
+ * We need to avoid collisions with `mirrored' VGA ports
+ * and other strange ISA hardware, so we always want the
+ * addresses to be allocated in the 0x000-0x0ff region
+ * modulo 0x400.
+ *
+ * Why? Because some silly external IO cards only decode
+ * the low 10 bits of the IO address. The 0x00-0xff region
+ * is reserved for motherboard devices that decode all 16
+ * bits, so it's ok to allocate at, say, 0x2800-0x28ff,
+ * but we want to try to avoid allocating at 0x2900-0x2bff
+ * which might have be mirrored at 0x0100-0x03ff..
+ */
+resource_size_t
+pcibios_align_resource(void *data, const struct resource *res,
+ resource_size_t size, resource_size_t align)
+{
+ struct pci_dev *dev = data;
+ resource_size_t start = res->start;
+
+ if (res->flags & IORESOURCE_IO) {
+ if (skip_isa_ioresource_align(dev))
+ return start;
+ if (start & 0x300)
+ start = (start + 0x3ff) & ~0x3ff;
+ } else if (res->flags & IORESOURCE_MEM) {
+ /* The low 1MB range is reserved for ISA cards */
+ if (start < BIOS_END)
+ start = BIOS_END;
+ }
+ return start;
+}
+EXPORT_SYMBOL(pcibios_align_resource);
+
+/*
+ * Handle resources of PCI devices. If the world were perfect, we could
+ * just allocate all the resource regions and do nothing more. It isn't.
+ * On the other hand, we cannot just re-allocate all devices, as it would
+ * require us to know lots of host bridge internals. So we attempt to
+ * keep as much of the original configuration as possible, but tweak it
+ * when it's found to be wrong.
+ *
+ * Known BIOS problems we have to work around:
+ * - I/O or memory regions not configured
+ * - regions configured, but not enabled in the command register
+ * - bogus I/O addresses above 64K used
+ * - expansion ROMs left enabled (this may sound harmless, but given
+ * the fact the PCI specs explicitly allow address decoders to be
+ * shared between expansion ROMs and other resource regions, it's
+ * at least dangerous)
+ * - bad resource sizes or overlaps with other regions
+ *
+ * Our solution:
+ * (1) Allocate resources for all buses behind PCI-to-PCI bridges.
+ * This gives us fixed barriers on where we can allocate.
+ * (2) Allocate resources for all enabled devices. If there is
+ * a collision, just mark the resource as unallocated. Also
+ * disable expansion ROMs during this step.
+ * (3) Try to allocate resources for disabled devices. If the
+ * resources were assigned correctly, everything goes well,
+ * if they weren't, they won't disturb allocation of other
+ * resources.
+ * (4) Assign new addresses to resources which were either
+ * not configured at all or misconfigured. If explicitly
+ * requested by the user, configure expansion ROM address
+ * as well.
+ */
+
+static void pcibios_allocate_bridge_resources(struct pci_dev *dev)
+{
+ int idx;
+ struct resource *r;
+
+ for (idx = PCI_BRIDGE_RESOURCES; idx < PCI_NUM_RESOURCES; idx++) {
+ r = &dev->resource[idx];
+ if (!r->flags)
+ continue;
+ if (r->parent) /* Already allocated */
+ continue;
+ if (!r->start || pci_claim_bridge_resource(dev, idx) < 0) {
+ /*
+ * Something is wrong with the region.
+ * Invalidate the resource to prevent
+ * child resource allocations in this
+ * range.
+ */
+ r->start = r->end = 0;
+ r->flags = 0;
+ }
+ }
+}
+
+static void pcibios_allocate_bus_resources(struct pci_bus *bus)
+{
+ struct pci_bus *child;
+
+ /* Depth-First Search on bus tree */
+ if (bus->self)
+ pcibios_allocate_bridge_resources(bus->self);
+ list_for_each_entry(child, &bus->children, node)
+ pcibios_allocate_bus_resources(child);
+}
+
+struct pci_check_idx_range {
+ int start;
+ int end;
+};
+
+static void pcibios_allocate_dev_resources(struct pci_dev *dev, int pass)
+{
+ int idx, disabled, i;
+ u16 command;
+ struct resource *r;
+
+ struct pci_check_idx_range idx_range[] = {
+ { PCI_STD_RESOURCES, PCI_STD_RESOURCE_END },
+#ifdef CONFIG_PCI_IOV
+ { PCI_IOV_RESOURCES, PCI_IOV_RESOURCE_END },
+#endif
+ };
+
+ pci_read_config_word(dev, PCI_COMMAND, &command);
+ for (i = 0; i < ARRAY_SIZE(idx_range); i++)
+ for (idx = idx_range[i].start; idx <= idx_range[i].end; idx++) {
+ r = &dev->resource[idx];
+ if (r->parent) /* Already allocated */
+ continue;
+ if (!r->start) /* Address not assigned at all */
+ continue;
+ if (r->flags & IORESOURCE_IO)
+ disabled = !(command & PCI_COMMAND_IO);
+ else
+ disabled = !(command & PCI_COMMAND_MEMORY);
+ if (pass == disabled) {
+ dev_dbg(&dev->dev,
+ "BAR %d: reserving %pr (d=%d, p=%d)\n",
+ idx, r, disabled, pass);
+ if (pci_claim_resource(dev, idx) < 0) {
+ if (r->flags & IORESOURCE_PCI_FIXED) {
+ dev_info(&dev->dev, "BAR %d %pR is immovable\n",
+ idx, r);
+ } else {
+ /* We'll assign a new address later */
+ pcibios_save_fw_addr(dev,
+ idx, r->start);
+ r->end -= r->start;
+ r->start = 0;
+ }
+ }
+ }
+ }
+ if (!pass) {
+ r = &dev->resource[PCI_ROM_RESOURCE];
+ if (r->flags & IORESOURCE_ROM_ENABLE) {
+ /* Turn the ROM off, leave the resource region,
+ * but keep it unregistered. */
+ u32 reg;
+ dev_dbg(&dev->dev, "disabling ROM %pR\n", r);
+ r->flags &= ~IORESOURCE_ROM_ENABLE;
+ pci_read_config_dword(dev, dev->rom_base_reg, &reg);
+ pci_write_config_dword(dev, dev->rom_base_reg,
+ reg & ~PCI_ROM_ADDRESS_ENABLE);
+ }
+ }
+}
+
+static void pcibios_allocate_resources(struct pci_bus *bus, int pass)
+{
+ struct pci_dev *dev;
+ struct pci_bus *child;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ pcibios_allocate_dev_resources(dev, pass);
+
+ child = dev->subordinate;
+ if (child)
+ pcibios_allocate_resources(child, pass);
+ }
+}
+
+static void pcibios_allocate_dev_rom_resource(struct pci_dev *dev)
+{
+ struct resource *r;
+
+ /*
+ * Try to use BIOS settings for ROMs, otherwise let
+ * pci_assign_unassigned_resources() allocate the new
+ * addresses.
+ */
+ r = &dev->resource[PCI_ROM_RESOURCE];
+ if (!r->flags || !r->start)
+ return;
+ if (r->parent) /* Already allocated */
+ return;
+
+ if (pci_claim_resource(dev, PCI_ROM_RESOURCE) < 0) {
+ r->end -= r->start;
+ r->start = 0;
+ }
+}
+static void pcibios_allocate_rom_resources(struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+ struct pci_bus *child;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ pcibios_allocate_dev_rom_resource(dev);
+
+ child = dev->subordinate;
+ if (child)
+ pcibios_allocate_rom_resources(child);
+ }
+}
+
+static int __init pcibios_assign_resources(void)
+{
+ struct pci_bus *bus;
+
+ if (!(pci_probe & PCI_ASSIGN_ROMS))
+ list_for_each_entry(bus, &pci_root_buses, node)
+ pcibios_allocate_rom_resources(bus);
+
+ pci_assign_unassigned_resources();
+ pcibios_fw_addr_list_del();
+
+ return 0;
+}
+
+/*
+ * This is an fs_initcall (one below subsys_initcall) in order to reserve
+ * resources properly.
+ */
+fs_initcall(pcibios_assign_resources);
+
+void pcibios_resource_survey_bus(struct pci_bus *bus)
+{
+ dev_printk(KERN_DEBUG, &bus->dev, "Allocating resources\n");
+
+ pcibios_allocate_bus_resources(bus);
+
+ pcibios_allocate_resources(bus, 0);
+ pcibios_allocate_resources(bus, 1);
+
+ if (!(pci_probe & PCI_ASSIGN_ROMS))
+ pcibios_allocate_rom_resources(bus);
+}
+
+void __init pcibios_resource_survey(void)
+{
+ struct pci_bus *bus;
+
+ DBG("PCI: Allocating resources\n");
+
+ list_for_each_entry(bus, &pci_root_buses, node)
+ pcibios_allocate_bus_resources(bus);
+
+ list_for_each_entry(bus, &pci_root_buses, node)
+ pcibios_allocate_resources(bus, 0);
+ list_for_each_entry(bus, &pci_root_buses, node)
+ pcibios_allocate_resources(bus, 1);
+
+ e820__reserve_resources_late();
+ /*
+ * Insert the IO APIC resources after PCI initialization has
+ * occurred to handle IO APICS that are mapped in on a BAR in
+ * PCI space, but before trying to assign unassigned pci res.
+ */
+ ioapic_insert_resources();
+}
diff --git a/arch/x86/pci/init.c b/arch/x86/pci/init.c
new file mode 100644
index 0000000000..0bb3b8b44e
--- /dev/null
+++ b/arch/x86/pci/init.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <asm/pci_x86.h>
+#include <asm/x86_init.h>
+#include <asm/irqdomain.h>
+
+/* arch_initcall has too random ordering, so call the initializers
+ in the right sequence from here. */
+static __init int pci_arch_init(void)
+{
+ int type, pcbios = 1;
+
+ type = pci_direct_probe();
+
+ if (!(pci_probe & PCI_PROBE_NOEARLY))
+ pci_mmcfg_early_init();
+
+ if (x86_init.pci.arch_init)
+ pcbios = x86_init.pci.arch_init();
+
+ /*
+ * Must happen after x86_init.pci.arch_init(). Xen sets up the
+ * x86_init.irqs.create_pci_msi_domain there.
+ */
+ x86_create_pci_msi_domain();
+
+ if (!pcbios)
+ return 0;
+
+ pci_pcbios_init();
+
+ /*
+ * don't check for raw_pci_ops here because we want pcbios as last
+ * fallback, yet it's needed to run first to set pcibios_last_bus
+ * in case legacy PCI probing is used. otherwise detecting peer busses
+ * fails.
+ */
+ pci_direct_init(type);
+
+ if (!raw_pci_ops && !raw_pci_ext_ops)
+ printk(KERN_ERR
+ "PCI: Fatal: No config space access function found\n");
+
+ dmi_check_pciprobe();
+
+ dmi_check_skip_isa_align();
+
+ return 0;
+}
+arch_initcall(pci_arch_init);
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
new file mode 100644
index 0000000000..8edd622066
--- /dev/null
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -0,0 +1,406 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel MID PCI support
+ * Copyright (c) 2008 Intel Corporation
+ * Jesse Barnes <jesse.barnes@intel.com>
+ *
+ * Moorestown has an interesting PCI implementation:
+ * - configuration space is memory mapped (as defined by MCFG)
+ * - Lincroft devices also have a real, type 1 configuration space
+ * - Early Lincroft silicon has a type 1 access bug that will cause
+ * a hang if non-existent devices are accessed
+ * - some devices have the "fixed BAR" capability, which means
+ * they can't be relocated or modified; check for that during
+ * BAR sizing
+ *
+ * So, we use the MCFG space for all reads and writes, but also send
+ * Lincroft writes to type 1 space. But only read/write if the device
+ * actually exists, otherwise return all 1s for reads and bit bucket
+ * the writes.
+ */
+
+#include <linux/sched.h>
+#include <linux/pci.h>
+#include <linux/ioport.h>
+#include <linux/init.h>
+#include <linux/dmi.h>
+#include <linux/acpi.h>
+#include <linux/io.h>
+#include <linux/smp.h>
+
+#include <asm/cpu_device_id.h>
+#include <asm/segment.h>
+#include <asm/pci_x86.h>
+#include <asm/hw_irq.h>
+#include <asm/io_apic.h>
+#include <asm/intel-family.h>
+#include <asm/intel-mid.h>
+#include <asm/acpi.h>
+
+#define PCIE_CAP_OFFSET 0x100
+
+/* Quirks for the listed devices */
+#define PCI_DEVICE_ID_INTEL_MRFLD_MMC 0x1190
+#define PCI_DEVICE_ID_INTEL_MRFLD_HSU 0x1191
+
+/* Fixed BAR fields */
+#define PCIE_VNDR_CAP_ID_FIXED_BAR 0x00 /* Fixed BAR (TBD) */
+#define PCI_FIXED_BAR_0_SIZE 0x04
+#define PCI_FIXED_BAR_1_SIZE 0x08
+#define PCI_FIXED_BAR_2_SIZE 0x0c
+#define PCI_FIXED_BAR_3_SIZE 0x10
+#define PCI_FIXED_BAR_4_SIZE 0x14
+#define PCI_FIXED_BAR_5_SIZE 0x1c
+
+static int pci_soc_mode;
+
+/**
+ * fixed_bar_cap - return the offset of the fixed BAR cap if found
+ * @bus: PCI bus
+ * @devfn: device in question
+ *
+ * Look for the fixed BAR cap on @bus and @devfn, returning its offset
+ * if found or 0 otherwise.
+ */
+static int fixed_bar_cap(struct pci_bus *bus, unsigned int devfn)
+{
+ int pos;
+ u32 pcie_cap = 0, cap_data;
+
+ pos = PCIE_CAP_OFFSET;
+
+ if (!raw_pci_ext_ops)
+ return 0;
+
+ while (pos) {
+ if (raw_pci_ext_ops->read(pci_domain_nr(bus), bus->number,
+ devfn, pos, 4, &pcie_cap))
+ return 0;
+
+ if (PCI_EXT_CAP_ID(pcie_cap) == 0x0000 ||
+ PCI_EXT_CAP_ID(pcie_cap) == 0xffff)
+ break;
+
+ if (PCI_EXT_CAP_ID(pcie_cap) == PCI_EXT_CAP_ID_VNDR) {
+ raw_pci_ext_ops->read(pci_domain_nr(bus), bus->number,
+ devfn, pos + 4, 4, &cap_data);
+ if ((cap_data & 0xffff) == PCIE_VNDR_CAP_ID_FIXED_BAR)
+ return pos;
+ }
+
+ pos = PCI_EXT_CAP_NEXT(pcie_cap);
+ }
+
+ return 0;
+}
+
+static int pci_device_update_fixed(struct pci_bus *bus, unsigned int devfn,
+ int reg, int len, u32 val, int offset)
+{
+ u32 size;
+ unsigned int domain, busnum;
+ int bar = (reg - PCI_BASE_ADDRESS_0) >> 2;
+
+ domain = pci_domain_nr(bus);
+ busnum = bus->number;
+
+ if (val == ~0 && len == 4) {
+ unsigned long decode;
+
+ raw_pci_ext_ops->read(domain, busnum, devfn,
+ offset + 8 + (bar * 4), 4, &size);
+
+ /* Turn the size into a decode pattern for the sizing code */
+ if (size) {
+ decode = size - 1;
+ decode |= decode >> 1;
+ decode |= decode >> 2;
+ decode |= decode >> 4;
+ decode |= decode >> 8;
+ decode |= decode >> 16;
+ decode++;
+ decode = ~(decode - 1);
+ } else {
+ decode = 0;
+ }
+
+ /*
+ * If val is all ones, the core code is trying to size the reg,
+ * so update the mmconfig space with the real size.
+ *
+ * Note: this assumes the fixed size we got is a power of two.
+ */
+ return raw_pci_ext_ops->write(domain, busnum, devfn, reg, 4,
+ decode);
+ }
+
+ /* This is some other kind of BAR write, so just do it. */
+ return raw_pci_ext_ops->write(domain, busnum, devfn, reg, len, val);
+}
+
+/**
+ * type1_access_ok - check whether to use type 1
+ * @bus: bus number
+ * @devfn: device & function in question
+ * @reg: configuration register offset
+ *
+ * If the bus is on a Lincroft chip and it exists, or is not on a Lincroft at
+ * all, the we can go ahead with any reads & writes. If it's on a Lincroft,
+ * but doesn't exist, avoid the access altogether to keep the chip from
+ * hanging.
+ */
+static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg)
+{
+ /*
+ * This is a workaround for A0 LNC bug where PCI status register does
+ * not have new CAP bit set. can not be written by SW either.
+ *
+ * PCI header type in real LNC indicates a single function device, this
+ * will prevent probing other devices under the same function in PCI
+ * shim. Therefore, use the header type in shim instead.
+ */
+ if (reg >= 0x100 || reg == PCI_STATUS || reg == PCI_HEADER_TYPE)
+ return false;
+ if (bus == 0 && (devfn == PCI_DEVFN(2, 0)
+ || devfn == PCI_DEVFN(0, 0)
+ || devfn == PCI_DEVFN(3, 0)))
+ return true;
+ return false; /* Langwell on others */
+}
+
+static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
+ int size, u32 *value)
+{
+ if (type1_access_ok(bus->number, devfn, where))
+ return pci_direct_conf1.read(pci_domain_nr(bus), bus->number,
+ devfn, where, size, value);
+ return raw_pci_ext_ops->read(pci_domain_nr(bus), bus->number,
+ devfn, where, size, value);
+}
+
+static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
+ int size, u32 value)
+{
+ int offset;
+
+ /*
+ * On MRST, there is no PCI ROM BAR, this will cause a subsequent read
+ * to ROM BAR return 0 then being ignored.
+ */
+ if (where == PCI_ROM_ADDRESS)
+ return 0;
+
+ /*
+ * Devices with fixed BARs need special handling:
+ * - BAR sizing code will save, write ~0, read size, restore
+ * - so writes to fixed BARs need special handling
+ * - other writes to fixed BAR devices should go through mmconfig
+ */
+ offset = fixed_bar_cap(bus, devfn);
+ if (offset &&
+ (where >= PCI_BASE_ADDRESS_0 && where <= PCI_BASE_ADDRESS_5)) {
+ return pci_device_update_fixed(bus, devfn, where, size, value,
+ offset);
+ }
+
+ /*
+ * On Moorestown update both real & mmconfig space
+ * Note: early Lincroft silicon can't handle type 1 accesses to
+ * non-existent devices, so just eat the write in that case.
+ */
+ if (type1_access_ok(bus->number, devfn, where))
+ return pci_direct_conf1.write(pci_domain_nr(bus), bus->number,
+ devfn, where, size, value);
+ return raw_pci_ext_ops->write(pci_domain_nr(bus), bus->number, devfn,
+ where, size, value);
+}
+
+static const struct x86_cpu_id intel_mid_cpu_ids[] = {
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID, NULL),
+ {}
+};
+
+static int intel_mid_pci_irq_enable(struct pci_dev *dev)
+{
+ const struct x86_cpu_id *id;
+ struct irq_alloc_info info;
+ bool polarity_low;
+ u16 model = 0;
+ int ret;
+ u8 gsi;
+
+ if (dev->irq_managed && dev->irq > 0)
+ return 0;
+
+ ret = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi);
+ if (ret < 0) {
+ dev_warn(&dev->dev, "Failed to read interrupt line: %d\n", ret);
+ return ret;
+ }
+
+ id = x86_match_cpu(intel_mid_cpu_ids);
+ if (id)
+ model = id->model;
+
+ switch (model) {
+ case INTEL_FAM6_ATOM_SILVERMONT_MID:
+ polarity_low = false;
+
+ /* Special treatment for IRQ0 */
+ if (gsi == 0) {
+ /*
+ * Skip HS UART common registers device since it has
+ * IRQ0 assigned and not used by the kernel.
+ */
+ if (dev->device == PCI_DEVICE_ID_INTEL_MRFLD_HSU)
+ return -EBUSY;
+ /*
+ * TNG has IRQ0 assigned to eMMC controller. But there
+ * are also other devices with bogus PCI configuration
+ * that have IRQ0 assigned. This check ensures that
+ * eMMC gets it. The rest of devices still could be
+ * enabled without interrupt line being allocated.
+ */
+ if (dev->device != PCI_DEVICE_ID_INTEL_MRFLD_MMC)
+ return 0;
+ }
+ break;
+ default:
+ polarity_low = true;
+ break;
+ }
+
+ ioapic_set_alloc_attr(&info, dev_to_node(&dev->dev), 1, polarity_low);
+
+ /*
+ * MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to
+ * IOAPIC RTE entries, so we just enable RTE for the device.
+ */
+ ret = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info);
+ if (ret < 0)
+ return ret;
+
+ dev->irq = ret;
+ dev->irq_managed = 1;
+
+ return 0;
+}
+
+static void intel_mid_pci_irq_disable(struct pci_dev *dev)
+{
+ if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed &&
+ dev->irq > 0) {
+ mp_unmap_irq(dev->irq);
+ dev->irq_managed = 0;
+ }
+}
+
+static const struct pci_ops intel_mid_pci_ops __initconst = {
+ .read = pci_read,
+ .write = pci_write,
+};
+
+/**
+ * intel_mid_pci_init - installs intel_mid_pci_ops
+ *
+ * Moorestown has an interesting PCI implementation (see above).
+ * Called when the early platform detection installs it.
+ */
+int __init intel_mid_pci_init(void)
+{
+ pr_info("Intel MID platform detected, using MID PCI ops\n");
+ pci_mmcfg_late_init();
+ pcibios_enable_irq = intel_mid_pci_irq_enable;
+ pcibios_disable_irq = intel_mid_pci_irq_disable;
+ pci_root_ops = intel_mid_pci_ops;
+ pci_soc_mode = 1;
+ /* Continue with standard init */
+ acpi_noirq_set();
+ return 1;
+}
+
+/*
+ * Langwell devices are not true PCI devices; they are not subject to 10 ms
+ * d3 to d0 delay required by PCI spec.
+ */
+static void pci_d3delay_fixup(struct pci_dev *dev)
+{
+ /*
+ * PCI fixups are effectively decided compile time. If we have a dual
+ * SoC/non-SoC kernel we don't want to mangle d3 on non-SoC devices.
+ */
+ if (!pci_soc_mode)
+ return;
+ /*
+ * True PCI devices in Lincroft should allow type 1 access, the rest
+ * are Langwell fake PCI devices.
+ */
+ if (type1_access_ok(dev->bus->number, dev->devfn, PCI_DEVICE_ID))
+ return;
+ dev->d3hot_delay = 0;
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_d3delay_fixup);
+
+static void mid_power_off_one_device(struct pci_dev *dev)
+{
+ u16 pmcsr;
+
+ /*
+ * Update current state first, otherwise PCI core enforces PCI_D0 in
+ * pci_set_power_state() for devices which status was PCI_UNKNOWN.
+ */
+ pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
+ dev->current_state = (pci_power_t __force)(pmcsr & PCI_PM_CTRL_STATE_MASK);
+
+ pci_set_power_state(dev, PCI_D3hot);
+}
+
+static void mid_power_off_devices(struct pci_dev *dev)
+{
+ int id;
+
+ if (!pci_soc_mode)
+ return;
+
+ id = intel_mid_pwr_get_lss_id(dev);
+ if (id < 0)
+ return;
+
+ /*
+ * This sets only PMCSR bits. The actual power off will happen in
+ * arch/x86/platform/intel-mid/pwr.c.
+ */
+ mid_power_off_one_device(dev);
+}
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, mid_power_off_devices);
+
+/*
+ * Langwell devices reside at fixed offsets, don't try to move them.
+ */
+static void pci_fixed_bar_fixup(struct pci_dev *dev)
+{
+ unsigned long offset;
+ u32 size;
+ int i;
+
+ if (!pci_soc_mode)
+ return;
+
+ /* Must have extended configuration space */
+ if (dev->cfg_size < PCIE_CAP_OFFSET + 4)
+ return;
+
+ /* Fixup the BAR sizes for fixed BAR devices and make them unmoveable */
+ offset = fixed_bar_cap(dev->bus, dev->devfn);
+ if (!offset || PCI_DEVFN(2, 0) == dev->devfn ||
+ PCI_DEVFN(2, 2) == dev->devfn)
+ return;
+
+ for (i = 0; i < PCI_STD_NUM_BARS; i++) {
+ pci_read_config_dword(dev, offset + 8 + (i * 4), &size);
+ dev->resource[i].end = dev->resource[i].start + size - 1;
+ dev->resource[i].flags |= IORESOURCE_PCI_FIXED;
+ }
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_fixed_bar_fixup);
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
new file mode 100644
index 0000000000..0de436316a
--- /dev/null
+++ b/arch/x86/pci/irq.c
@@ -0,0 +1,1810 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Low-Level PCI Support for PC -- Routing of Interrupts
+ *
+ * (c) 1999--2000 Martin Mares <mj@ucw.cz>
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/dmi.h>
+#include <linux/io.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+#include <asm/io_apic.h>
+#include <linux/irq.h>
+#include <linux/acpi.h>
+
+#include <asm/i8259.h>
+#include <asm/pc-conf-reg.h>
+#include <asm/pci_x86.h>
+
+#define PIRQ_SIGNATURE (('$' << 0) + ('P' << 8) + ('I' << 16) + ('R' << 24))
+#define PIRQ_VERSION 0x0100
+
+#define IRT_SIGNATURE (('$' << 0) + ('I' << 8) + ('R' << 16) + ('T' << 24))
+
+static int broken_hp_bios_irq9;
+static int acer_tm360_irqrouting;
+
+static struct irq_routing_table *pirq_table;
+
+static int pirq_enable_irq(struct pci_dev *dev);
+static void pirq_disable_irq(struct pci_dev *dev);
+
+/*
+ * Never use: 0, 1, 2 (timer, keyboard, and cascade)
+ * Avoid using: 13, 14 and 15 (FP error and IDE).
+ * Penalize: 3, 4, 6, 7, 12 (known ISA uses: serial, floppy, parallel and mouse)
+ */
+unsigned int pcibios_irq_mask = 0xfff8;
+
+static int pirq_penalty[16] = {
+ 1000000, 1000000, 1000000, 1000, 1000, 0, 1000, 1000,
+ 0, 0, 0, 0, 1000, 100000, 100000, 100000
+};
+
+struct irq_router {
+ char *name;
+ u16 vendor, device;
+ int (*get)(struct pci_dev *router, struct pci_dev *dev, int pirq);
+ int (*set)(struct pci_dev *router, struct pci_dev *dev, int pirq,
+ int new);
+ int (*lvl)(struct pci_dev *router, struct pci_dev *dev, int pirq,
+ int irq);
+};
+
+struct irq_router_handler {
+ u16 vendor;
+ int (*probe)(struct irq_router *r, struct pci_dev *router, u16 device);
+};
+
+int (*pcibios_enable_irq)(struct pci_dev *dev) = pirq_enable_irq;
+void (*pcibios_disable_irq)(struct pci_dev *dev) = pirq_disable_irq;
+
+/*
+ * Check passed address for the PCI IRQ Routing Table signature
+ * and perform checksum verification.
+ */
+
+static inline struct irq_routing_table *pirq_check_routing_table(u8 *addr,
+ u8 *limit)
+{
+ struct irq_routing_table *rt;
+ int i;
+ u8 sum;
+
+ rt = (struct irq_routing_table *)addr;
+ if (rt->signature != PIRQ_SIGNATURE ||
+ rt->version != PIRQ_VERSION ||
+ rt->size % 16 ||
+ rt->size < sizeof(struct irq_routing_table) ||
+ (limit && rt->size > limit - addr))
+ return NULL;
+ sum = 0;
+ for (i = 0; i < rt->size; i++)
+ sum += addr[i];
+ if (!sum) {
+ DBG(KERN_DEBUG "PCI: Interrupt Routing Table found at 0x%lx\n",
+ __pa(rt));
+ return rt;
+ }
+ return NULL;
+}
+
+/*
+ * Handle the $IRT PCI IRQ Routing Table format used by AMI for its BCP
+ * (BIOS Configuration Program) external tool meant for tweaking BIOS
+ * structures without the need to rebuild it from sources. The $IRT
+ * format has been invented by AMI before Microsoft has come up with its
+ * $PIR format and a $IRT table is therefore there in some systems that
+ * lack a $PIR table.
+ *
+ * It uses the same PCI BIOS 2.1 format for interrupt routing entries
+ * themselves but has a different simpler header prepended instead,
+ * occupying 8 bytes, where a `$IRT' signature is followed by one byte
+ * specifying the total number of interrupt routing entries allocated in
+ * the table, then one byte specifying the actual number of entries used
+ * (which the BCP tool can take advantage of when modifying the table),
+ * and finally a 16-bit word giving the IRQs devoted exclusively to PCI.
+ * Unlike with the $PIR table there is no alignment guarantee.
+ *
+ * Given the similarity of the two formats the $IRT one is trivial to
+ * convert to the $PIR one, which we do here, except that obviously we
+ * have no information as to the router device to use, but we can handle
+ * it by matching PCI device IDs actually seen on the bus against ones
+ * that our individual routers recognise.
+ *
+ * Reportedly there is another $IRT table format where a 16-bit word
+ * follows the header instead that points to interrupt routing entries
+ * in a $PIR table provided elsewhere. In that case this code will not
+ * be reached though as the $PIR table will have been chosen instead.
+ */
+static inline struct irq_routing_table *pirq_convert_irt_table(u8 *addr,
+ u8 *limit)
+{
+ struct irt_routing_table *ir;
+ struct irq_routing_table *rt;
+ u16 size;
+ u8 sum;
+ int i;
+
+ ir = (struct irt_routing_table *)addr;
+ if (ir->signature != IRT_SIGNATURE || !ir->used || ir->size < ir->used)
+ return NULL;
+
+ size = struct_size(ir, slots, ir->used);
+ if (size > limit - addr)
+ return NULL;
+
+ DBG(KERN_DEBUG "PCI: $IRT Interrupt Routing Table found at 0x%lx\n",
+ __pa(ir));
+
+ size = struct_size(rt, slots, ir->used);
+ rt = kzalloc(size, GFP_KERNEL);
+ if (!rt)
+ return NULL;
+
+ rt->signature = PIRQ_SIGNATURE;
+ rt->version = PIRQ_VERSION;
+ rt->size = size;
+ rt->exclusive_irqs = ir->exclusive_irqs;
+ for (i = 0; i < ir->used; i++)
+ rt->slots[i] = ir->slots[i];
+
+ addr = (u8 *)rt;
+ sum = 0;
+ for (i = 0; i < size; i++)
+ sum += addr[i];
+ rt->checksum = -sum;
+
+ return rt;
+}
+
+/*
+ * Search 0xf0000 -- 0xfffff for the PCI IRQ Routing Table.
+ */
+
+static struct irq_routing_table * __init pirq_find_routing_table(void)
+{
+ u8 * const bios_start = (u8 *)__va(0xf0000);
+ u8 * const bios_end = (u8 *)__va(0x100000);
+ u8 *addr;
+ struct irq_routing_table *rt;
+
+ if (pirq_table_addr) {
+ rt = pirq_check_routing_table((u8 *)__va(pirq_table_addr),
+ NULL);
+ if (rt)
+ return rt;
+ printk(KERN_WARNING "PCI: PIRQ table NOT found at pirqaddr\n");
+ }
+ for (addr = bios_start;
+ addr < bios_end - sizeof(struct irq_routing_table);
+ addr += 16) {
+ rt = pirq_check_routing_table(addr, bios_end);
+ if (rt)
+ return rt;
+ }
+ for (addr = bios_start;
+ addr < bios_end - sizeof(struct irt_routing_table);
+ addr++) {
+ rt = pirq_convert_irt_table(addr, bios_end);
+ if (rt)
+ return rt;
+ }
+ return NULL;
+}
+
+/*
+ * If we have a IRQ routing table, use it to search for peer host
+ * bridges. It's a gross hack, but since there are no other known
+ * ways how to get a list of buses, we have to go this way.
+ */
+
+static void __init pirq_peer_trick(void)
+{
+ struct irq_routing_table *rt = pirq_table;
+ u8 busmap[256];
+ int i;
+ struct irq_info *e;
+
+ memset(busmap, 0, sizeof(busmap));
+ for (i = 0; i < (rt->size - sizeof(struct irq_routing_table)) / sizeof(struct irq_info); i++) {
+ e = &rt->slots[i];
+#ifdef DEBUG
+ {
+ int j;
+ DBG(KERN_DEBUG "%02x:%02x.%x slot=%02x",
+ e->bus, e->devfn / 8, e->devfn % 8, e->slot);
+ for (j = 0; j < 4; j++)
+ DBG(" %d:%02x/%04x", j, e->irq[j].link, e->irq[j].bitmap);
+ DBG("\n");
+ }
+#endif
+ busmap[e->bus] = 1;
+ }
+ for (i = 1; i < 256; i++) {
+ if (!busmap[i] || pci_find_bus(0, i))
+ continue;
+ pcibios_scan_root(i);
+ }
+ pcibios_last_bus = -1;
+}
+
+/*
+ * Code for querying and setting of IRQ routes on various interrupt routers.
+ * PIC Edge/Level Control Registers (ELCR) 0x4d0 & 0x4d1.
+ */
+
+void elcr_set_level_irq(unsigned int irq)
+{
+ unsigned char mask = 1 << (irq & 7);
+ unsigned int port = PIC_ELCR1 + (irq >> 3);
+ unsigned char val;
+ static u16 elcr_irq_mask;
+
+ if (irq >= 16 || (1 << irq) & elcr_irq_mask)
+ return;
+
+ elcr_irq_mask |= (1 << irq);
+ printk(KERN_DEBUG "PCI: setting IRQ %u as level-triggered\n", irq);
+ val = inb(port);
+ if (!(val & mask)) {
+ DBG(KERN_DEBUG " -> edge");
+ outb(val | mask, port);
+ }
+}
+
+/*
+ * PIRQ routing for the M1487 ISA Bus Controller (IBC) ASIC used
+ * with the ALi FinALi 486 chipset. The IBC is not decoded in the
+ * PCI configuration space, so we identify it by the accompanying
+ * M1489 Cache-Memory PCI Controller (CMP) ASIC.
+ *
+ * There are four 4-bit mappings provided, spread across two PCI
+ * INTx Routing Table Mapping Registers, available in the port I/O
+ * space accessible indirectly via the index/data register pair at
+ * 0x22/0x23, located at indices 0x42 and 0x43 for the INT1/INT2
+ * and INT3/INT4 lines respectively. The INT1/INT3 and INT2/INT4
+ * lines are mapped in the low and the high 4-bit nibble of the
+ * corresponding register as follows:
+ *
+ * 0000 : Disabled
+ * 0001 : IRQ9
+ * 0010 : IRQ3
+ * 0011 : IRQ10
+ * 0100 : IRQ4
+ * 0101 : IRQ5
+ * 0110 : IRQ7
+ * 0111 : IRQ6
+ * 1000 : Reserved
+ * 1001 : IRQ11
+ * 1010 : Reserved
+ * 1011 : IRQ12
+ * 1100 : Reserved
+ * 1101 : IRQ14
+ * 1110 : Reserved
+ * 1111 : IRQ15
+ *
+ * In addition to the usual ELCR register pair there is a separate
+ * PCI INTx Sensitivity Register at index 0x44 in the same port I/O
+ * space, whose bits 3:0 select the trigger mode for INT[4:1] lines
+ * respectively. Any bit set to 1 causes interrupts coming on the
+ * corresponding line to be passed to ISA as edge-triggered and
+ * otherwise they are passed as level-triggered. Manufacturer's
+ * documentation says this register has to be set consistently with
+ * the relevant ELCR register.
+ *
+ * Accesses to the port I/O space concerned here need to be unlocked
+ * by writing the value of 0xc5 to the Lock Register at index 0x03
+ * beforehand. Any other value written to said register prevents
+ * further accesses from reaching the register file, except for the
+ * Lock Register being written with 0xc5 again.
+ *
+ * References:
+ *
+ * "M1489/M1487: 486 PCI Chip Set", Version 1.2, Acer Laboratories
+ * Inc., July 1997
+ */
+
+#define PC_CONF_FINALI_LOCK 0x03u
+#define PC_CONF_FINALI_PCI_INTX_RT1 0x42u
+#define PC_CONF_FINALI_PCI_INTX_RT2 0x43u
+#define PC_CONF_FINALI_PCI_INTX_SENS 0x44u
+
+#define PC_CONF_FINALI_LOCK_KEY 0xc5u
+
+static u8 read_pc_conf_nybble(u8 base, u8 index)
+{
+ u8 reg = base + (index >> 1);
+ u8 x;
+
+ x = pc_conf_get(reg);
+ return index & 1 ? x >> 4 : x & 0xf;
+}
+
+static void write_pc_conf_nybble(u8 base, u8 index, u8 val)
+{
+ u8 reg = base + (index >> 1);
+ u8 x;
+
+ x = pc_conf_get(reg);
+ x = index & 1 ? (x & 0x0f) | (val << 4) : (x & 0xf0) | val;
+ pc_conf_set(reg, x);
+}
+
+/*
+ * FinALi pirq rules are as follows:
+ *
+ * - bit 0 selects between INTx Routing Table Mapping Registers,
+ *
+ * - bit 3 selects the nibble within the INTx Routing Table Mapping Register,
+ *
+ * - bits 7:4 map to bits 3:0 of the PCI INTx Sensitivity Register.
+ */
+static int pirq_finali_get(struct pci_dev *router, struct pci_dev *dev,
+ int pirq)
+{
+ static const u8 irqmap[16] = {
+ 0, 9, 3, 10, 4, 5, 7, 6, 0, 11, 0, 12, 0, 14, 0, 15
+ };
+ unsigned long flags;
+ u8 index;
+ u8 x;
+
+ index = (pirq & 1) << 1 | (pirq & 8) >> 3;
+ raw_spin_lock_irqsave(&pc_conf_lock, flags);
+ pc_conf_set(PC_CONF_FINALI_LOCK, PC_CONF_FINALI_LOCK_KEY);
+ x = irqmap[read_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, index)];
+ pc_conf_set(PC_CONF_FINALI_LOCK, 0);
+ raw_spin_unlock_irqrestore(&pc_conf_lock, flags);
+ return x;
+}
+
+static int pirq_finali_set(struct pci_dev *router, struct pci_dev *dev,
+ int pirq, int irq)
+{
+ static const u8 irqmap[16] = {
+ 0, 0, 0, 2, 4, 5, 7, 6, 0, 1, 3, 9, 11, 0, 13, 15
+ };
+ u8 val = irqmap[irq];
+ unsigned long flags;
+ u8 index;
+
+ if (!val)
+ return 0;
+
+ index = (pirq & 1) << 1 | (pirq & 8) >> 3;
+ raw_spin_lock_irqsave(&pc_conf_lock, flags);
+ pc_conf_set(PC_CONF_FINALI_LOCK, PC_CONF_FINALI_LOCK_KEY);
+ write_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, index, val);
+ pc_conf_set(PC_CONF_FINALI_LOCK, 0);
+ raw_spin_unlock_irqrestore(&pc_conf_lock, flags);
+ return 1;
+}
+
+static int pirq_finali_lvl(struct pci_dev *router, struct pci_dev *dev,
+ int pirq, int irq)
+{
+ u8 mask = ~((pirq & 0xf0u) >> 4);
+ unsigned long flags;
+ u8 trig;
+
+ elcr_set_level_irq(irq);
+ raw_spin_lock_irqsave(&pc_conf_lock, flags);
+ pc_conf_set(PC_CONF_FINALI_LOCK, PC_CONF_FINALI_LOCK_KEY);
+ trig = pc_conf_get(PC_CONF_FINALI_PCI_INTX_SENS);
+ trig &= mask;
+ pc_conf_set(PC_CONF_FINALI_PCI_INTX_SENS, trig);
+ pc_conf_set(PC_CONF_FINALI_LOCK, 0);
+ raw_spin_unlock_irqrestore(&pc_conf_lock, flags);
+ return 1;
+}
+
+/*
+ * Common IRQ routing practice: nibbles in config space,
+ * offset by some magic constant.
+ */
+static unsigned int read_config_nybble(struct pci_dev *router, unsigned offset, unsigned nr)
+{
+ u8 x;
+ unsigned reg = offset + (nr >> 1);
+
+ pci_read_config_byte(router, reg, &x);
+ return (nr & 1) ? (x >> 4) : (x & 0xf);
+}
+
+static void write_config_nybble(struct pci_dev *router, unsigned offset,
+ unsigned nr, unsigned int val)
+{
+ u8 x;
+ unsigned reg = offset + (nr >> 1);
+
+ pci_read_config_byte(router, reg, &x);
+ x = (nr & 1) ? ((x & 0x0f) | (val << 4)) : ((x & 0xf0) | val);
+ pci_write_config_byte(router, reg, x);
+}
+
+/*
+ * ALI pirq entries are damn ugly, and completely undocumented.
+ * This has been figured out from pirq tables, and it's not a pretty
+ * picture.
+ */
+static int pirq_ali_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ static const unsigned char irqmap[16] = { 0, 9, 3, 10, 4, 5, 7, 6, 1, 11, 0, 12, 0, 14, 0, 15 };
+
+ WARN_ON_ONCE(pirq > 16);
+ return irqmap[read_config_nybble(router, 0x48, pirq-1)];
+}
+
+static int pirq_ali_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq)
+{
+ static const unsigned char irqmap[16] = { 0, 8, 0, 2, 4, 5, 7, 6, 0, 1, 3, 9, 11, 0, 13, 15 };
+ unsigned int val = irqmap[irq];
+
+ WARN_ON_ONCE(pirq > 16);
+ if (val) {
+ write_config_nybble(router, 0x48, pirq-1, val);
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * PIRQ routing for the 82374EB/82374SB EISA System Component (ESC)
+ * ASIC used with the Intel 82420 and 82430 PCIsets. The ESC is not
+ * decoded in the PCI configuration space, so we identify it by the
+ * accompanying 82375EB/82375SB PCI-EISA Bridge (PCEB) ASIC.
+ *
+ * There are four PIRQ Route Control registers, available in the
+ * port I/O space accessible indirectly via the index/data register
+ * pair at 0x22/0x23, located at indices 0x60/0x61/0x62/0x63 for the
+ * PIRQ0/1/2/3# lines respectively. The semantics is the same as
+ * with the PIIX router.
+ *
+ * Accesses to the port I/O space concerned here need to be unlocked
+ * by writing the value of 0x0f to the ESC ID Register at index 0x02
+ * beforehand. Any other value written to said register prevents
+ * further accesses from reaching the register file, except for the
+ * ESC ID Register being written with 0x0f again.
+ *
+ * References:
+ *
+ * "82374EB/82374SB EISA System Component (ESC)", Intel Corporation,
+ * Order Number: 290476-004, March 1996
+ *
+ * "82375EB/82375SB PCI-EISA Bridge (PCEB)", Intel Corporation, Order
+ * Number: 290477-004, March 1996
+ */
+
+#define PC_CONF_I82374_ESC_ID 0x02u
+#define PC_CONF_I82374_PIRQ_ROUTE_CONTROL 0x60u
+
+#define PC_CONF_I82374_ESC_ID_KEY 0x0fu
+
+static int pirq_esc_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ unsigned long flags;
+ int reg;
+ u8 x;
+
+ reg = pirq;
+ if (reg >= 1 && reg <= 4)
+ reg += PC_CONF_I82374_PIRQ_ROUTE_CONTROL - 1;
+
+ raw_spin_lock_irqsave(&pc_conf_lock, flags);
+ pc_conf_set(PC_CONF_I82374_ESC_ID, PC_CONF_I82374_ESC_ID_KEY);
+ x = pc_conf_get(reg);
+ pc_conf_set(PC_CONF_I82374_ESC_ID, 0);
+ raw_spin_unlock_irqrestore(&pc_conf_lock, flags);
+ return (x < 16) ? x : 0;
+}
+
+static int pirq_esc_set(struct pci_dev *router, struct pci_dev *dev, int pirq,
+ int irq)
+{
+ unsigned long flags;
+ int reg;
+
+ reg = pirq;
+ if (reg >= 1 && reg <= 4)
+ reg += PC_CONF_I82374_PIRQ_ROUTE_CONTROL - 1;
+
+ raw_spin_lock_irqsave(&pc_conf_lock, flags);
+ pc_conf_set(PC_CONF_I82374_ESC_ID, PC_CONF_I82374_ESC_ID_KEY);
+ pc_conf_set(reg, irq);
+ pc_conf_set(PC_CONF_I82374_ESC_ID, 0);
+ raw_spin_unlock_irqrestore(&pc_conf_lock, flags);
+ return 1;
+}
+
+/*
+ * The Intel PIIX4 pirq rules are fairly simple: "pirq" is
+ * just a pointer to the config space.
+ */
+static int pirq_piix_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ u8 x;
+
+ pci_read_config_byte(router, pirq, &x);
+ return (x < 16) ? x : 0;
+}
+
+static int pirq_piix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq)
+{
+ pci_write_config_byte(router, pirq, irq);
+ return 1;
+}
+
+/*
+ * PIRQ routing for the 82426EX ISA Bridge (IB) ASIC used with the
+ * Intel 82420EX PCIset.
+ *
+ * There are only two PIRQ Route Control registers, available in the
+ * combined 82425EX/82426EX PCI configuration space, at 0x66 and 0x67
+ * for the PIRQ0# and PIRQ1# lines respectively. The semantics is
+ * the same as with the PIIX router.
+ *
+ * References:
+ *
+ * "82420EX PCIset Data Sheet, 82425EX PCI System Controller (PSC)
+ * and 82426EX ISA Bridge (IB)", Intel Corporation, Order Number:
+ * 290488-004, December 1995
+ */
+
+#define PCI_I82426EX_PIRQ_ROUTE_CONTROL 0x66u
+
+static int pirq_ib_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ int reg;
+ u8 x;
+
+ reg = pirq;
+ if (reg >= 1 && reg <= 2)
+ reg += PCI_I82426EX_PIRQ_ROUTE_CONTROL - 1;
+
+ pci_read_config_byte(router, reg, &x);
+ return (x < 16) ? x : 0;
+}
+
+static int pirq_ib_set(struct pci_dev *router, struct pci_dev *dev, int pirq,
+ int irq)
+{
+ int reg;
+
+ reg = pirq;
+ if (reg >= 1 && reg <= 2)
+ reg += PCI_I82426EX_PIRQ_ROUTE_CONTROL - 1;
+
+ pci_write_config_byte(router, reg, irq);
+ return 1;
+}
+
+/*
+ * The VIA pirq rules are nibble-based, like ALI,
+ * but without the ugly irq number munging.
+ * However, PIRQD is in the upper instead of lower 4 bits.
+ */
+static int pirq_via_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ return read_config_nybble(router, 0x55, pirq == 4 ? 5 : pirq);
+}
+
+static int pirq_via_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq)
+{
+ write_config_nybble(router, 0x55, pirq == 4 ? 5 : pirq, irq);
+ return 1;
+}
+
+/*
+ * The VIA pirq rules are nibble-based, like ALI,
+ * but without the ugly irq number munging.
+ * However, for 82C586, nibble map is different .
+ */
+static int pirq_via586_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ static const unsigned int pirqmap[5] = { 3, 2, 5, 1, 1 };
+
+ WARN_ON_ONCE(pirq > 5);
+ return read_config_nybble(router, 0x55, pirqmap[pirq-1]);
+}
+
+static int pirq_via586_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq)
+{
+ static const unsigned int pirqmap[5] = { 3, 2, 5, 1, 1 };
+
+ WARN_ON_ONCE(pirq > 5);
+ write_config_nybble(router, 0x55, pirqmap[pirq-1], irq);
+ return 1;
+}
+
+/*
+ * ITE 8330G pirq rules are nibble-based
+ * FIXME: pirqmap may be { 1, 0, 3, 2 },
+ * 2+3 are both mapped to irq 9 on my system
+ */
+static int pirq_ite_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ static const unsigned char pirqmap[4] = { 1, 0, 2, 3 };
+
+ WARN_ON_ONCE(pirq > 4);
+ return read_config_nybble(router, 0x43, pirqmap[pirq-1]);
+}
+
+static int pirq_ite_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq)
+{
+ static const unsigned char pirqmap[4] = { 1, 0, 2, 3 };
+
+ WARN_ON_ONCE(pirq > 4);
+ write_config_nybble(router, 0x43, pirqmap[pirq-1], irq);
+ return 1;
+}
+
+/*
+ * OPTI: high four bits are nibble pointer..
+ * I wonder what the low bits do?
+ */
+static int pirq_opti_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ return read_config_nybble(router, 0xb8, pirq >> 4);
+}
+
+static int pirq_opti_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq)
+{
+ write_config_nybble(router, 0xb8, pirq >> 4, irq);
+ return 1;
+}
+
+/*
+ * Cyrix: nibble offset 0x5C
+ * 0x5C bits 7:4 is INTB bits 3:0 is INTA
+ * 0x5D bits 7:4 is INTD bits 3:0 is INTC
+ */
+static int pirq_cyrix_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ return read_config_nybble(router, 0x5C, (pirq-1)^1);
+}
+
+static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq)
+{
+ write_config_nybble(router, 0x5C, (pirq-1)^1, irq);
+ return 1;
+}
+
+
+/*
+ * PIRQ routing for the SiS85C497 AT Bus Controller & Megacell (ATM)
+ * ISA bridge used with the SiS 85C496/497 486 Green PC VESA/ISA/PCI
+ * Chipset.
+ *
+ * There are four PCI INTx#-to-IRQ Link registers provided in the
+ * SiS85C497 part of the peculiar combined 85C496/497 configuration
+ * space decoded by the SiS85C496 PCI & CPU Memory Controller (PCM)
+ * host bridge, at 0xc0/0xc1/0xc2/0xc3 respectively for the PCI INT
+ * A/B/C/D lines. Bit 7 enables the respective link if set and bits
+ * 3:0 select the 8259A IRQ line as follows:
+ *
+ * 0000 : Reserved
+ * 0001 : Reserved
+ * 0010 : Reserved
+ * 0011 : IRQ3
+ * 0100 : IRQ4
+ * 0101 : IRQ5
+ * 0110 : IRQ6
+ * 0111 : IRQ7
+ * 1000 : Reserved
+ * 1001 : IRQ9
+ * 1010 : IRQ10
+ * 1011 : IRQ11
+ * 1100 : IRQ12
+ * 1101 : Reserved
+ * 1110 : IRQ14
+ * 1111 : IRQ15
+ *
+ * We avoid using a reserved value for disabled links, hence the
+ * choice of IRQ15 for that case.
+ *
+ * References:
+ *
+ * "486 Green PC VESA/ISA/PCI Chipset, SiS 85C496/497", Rev 3.0,
+ * Silicon Integrated Systems Corp., July 1995
+ */
+
+#define PCI_SIS497_INTA_TO_IRQ_LINK 0xc0u
+
+#define PIRQ_SIS497_IRQ_MASK 0x0fu
+#define PIRQ_SIS497_IRQ_ENABLE 0x80u
+
+static int pirq_sis497_get(struct pci_dev *router, struct pci_dev *dev,
+ int pirq)
+{
+ int reg;
+ u8 x;
+
+ reg = pirq;
+ if (reg >= 1 && reg <= 4)
+ reg += PCI_SIS497_INTA_TO_IRQ_LINK - 1;
+
+ pci_read_config_byte(router, reg, &x);
+ return (x & PIRQ_SIS497_IRQ_ENABLE) ? (x & PIRQ_SIS497_IRQ_MASK) : 0;
+}
+
+static int pirq_sis497_set(struct pci_dev *router, struct pci_dev *dev,
+ int pirq, int irq)
+{
+ int reg;
+ u8 x;
+
+ reg = pirq;
+ if (reg >= 1 && reg <= 4)
+ reg += PCI_SIS497_INTA_TO_IRQ_LINK - 1;
+
+ pci_read_config_byte(router, reg, &x);
+ x &= ~(PIRQ_SIS497_IRQ_MASK | PIRQ_SIS497_IRQ_ENABLE);
+ x |= irq ? (PIRQ_SIS497_IRQ_ENABLE | irq) : PIRQ_SIS497_IRQ_MASK;
+ pci_write_config_byte(router, reg, x);
+ return 1;
+}
+
+/*
+ * PIRQ routing for SiS 85C503 router used in several SiS chipsets.
+ * We have to deal with the following issues here:
+ * - vendors have different ideas about the meaning of link values
+ * - some onboard devices (integrated in the chipset) have special
+ * links and are thus routed differently (i.e. not via PCI INTA-INTD)
+ * - different revision of the router have a different layout for
+ * the routing registers, particularly for the onchip devices
+ *
+ * For all routing registers the common thing is we have one byte
+ * per routeable link which is defined as:
+ * bit 7 IRQ mapping enabled (0) or disabled (1)
+ * bits [6:4] reserved (sometimes used for onchip devices)
+ * bits [3:0] IRQ to map to
+ * allowed: 3-7, 9-12, 14-15
+ * reserved: 0, 1, 2, 8, 13
+ *
+ * The config-space registers located at 0x41/0x42/0x43/0x44 are
+ * always used to route the normal PCI INT A/B/C/D respectively.
+ * Apparently there are systems implementing PCI routing table using
+ * link values 0x01-0x04 and others using 0x41-0x44 for PCI INTA..D.
+ * We try our best to handle both link mappings.
+ *
+ * Currently (2003-05-21) it appears most SiS chipsets follow the
+ * definition of routing registers from the SiS-5595 southbridge.
+ * According to the SiS 5595 datasheets the revision id's of the
+ * router (ISA-bridge) should be 0x01 or 0xb0.
+ *
+ * Furthermore we've also seen lspci dumps with revision 0x00 and 0xb1.
+ * Looks like these are used in a number of SiS 5xx/6xx/7xx chipsets.
+ * They seem to work with the current routing code. However there is
+ * some concern because of the two USB-OHCI HCs (original SiS 5595
+ * had only one). YMMV.
+ *
+ * Onchip routing for router rev-id 0x01/0xb0 and probably 0x00/0xb1:
+ *
+ * 0x61: IDEIRQ:
+ * bits [6:5] must be written 01
+ * bit 4 channel-select primary (0), secondary (1)
+ *
+ * 0x62: USBIRQ:
+ * bit 6 OHCI function disabled (0), enabled (1)
+ *
+ * 0x6a: ACPI/SCI IRQ: bits 4-6 reserved
+ *
+ * 0x7e: Data Acq. Module IRQ - bits 4-6 reserved
+ *
+ * We support USBIRQ (in addition to INTA-INTD) and keep the
+ * IDE, ACPI and DAQ routing untouched as set by the BIOS.
+ *
+ * Currently the only reported exception is the new SiS 65x chipset
+ * which includes the SiS 69x southbridge. Here we have the 85C503
+ * router revision 0x04 and there are changes in the register layout
+ * mostly related to the different USB HCs with USB 2.0 support.
+ *
+ * Onchip routing for router rev-id 0x04 (try-and-error observation)
+ *
+ * 0x60/0x61/0x62/0x63: 1xEHCI and 3xOHCI (companion) USB-HCs
+ * bit 6-4 are probably unused, not like 5595
+ */
+
+#define PIRQ_SIS503_IRQ_MASK 0x0f
+#define PIRQ_SIS503_IRQ_DISABLE 0x80
+#define PIRQ_SIS503_USB_ENABLE 0x40
+
+static int pirq_sis503_get(struct pci_dev *router, struct pci_dev *dev,
+ int pirq)
+{
+ u8 x;
+ int reg;
+
+ reg = pirq;
+ if (reg >= 0x01 && reg <= 0x04)
+ reg += 0x40;
+ pci_read_config_byte(router, reg, &x);
+ return (x & PIRQ_SIS503_IRQ_DISABLE) ? 0 : (x & PIRQ_SIS503_IRQ_MASK);
+}
+
+static int pirq_sis503_set(struct pci_dev *router, struct pci_dev *dev,
+ int pirq, int irq)
+{
+ u8 x;
+ int reg;
+
+ reg = pirq;
+ if (reg >= 0x01 && reg <= 0x04)
+ reg += 0x40;
+ pci_read_config_byte(router, reg, &x);
+ x &= ~(PIRQ_SIS503_IRQ_MASK | PIRQ_SIS503_IRQ_DISABLE);
+ x |= irq ? irq : PIRQ_SIS503_IRQ_DISABLE;
+ pci_write_config_byte(router, reg, x);
+ return 1;
+}
+
+
+/*
+ * VLSI: nibble offset 0x74 - educated guess due to routing table and
+ * config space of VLSI 82C534 PCI-bridge/router (1004:0102)
+ * Tested on HP OmniBook 800 covering PIRQ 1, 2, 4, 8 for onboard
+ * devices, PIRQ 3 for non-pci(!) soundchip and (untested) PIRQ 6
+ * for the busbridge to the docking station.
+ */
+
+static int pirq_vlsi_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ WARN_ON_ONCE(pirq >= 9);
+ if (pirq > 8) {
+ dev_info(&dev->dev, "VLSI router PIRQ escape (%d)\n", pirq);
+ return 0;
+ }
+ return read_config_nybble(router, 0x74, pirq-1);
+}
+
+static int pirq_vlsi_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq)
+{
+ WARN_ON_ONCE(pirq >= 9);
+ if (pirq > 8) {
+ dev_info(&dev->dev, "VLSI router PIRQ escape (%d)\n", pirq);
+ return 0;
+ }
+ write_config_nybble(router, 0x74, pirq-1, irq);
+ return 1;
+}
+
+/*
+ * ServerWorks: PCI interrupts mapped to system IRQ lines through Index
+ * and Redirect I/O registers (0x0c00 and 0x0c01). The Index register
+ * format is (PCIIRQ## | 0x10), e.g.: PCIIRQ10=0x1a. The Redirect
+ * register is a straight binary coding of desired PIC IRQ (low nibble).
+ *
+ * The 'link' value in the PIRQ table is already in the correct format
+ * for the Index register. There are some special index values:
+ * 0x00 for ACPI (SCI), 0x01 for USB, 0x02 for IDE0, 0x04 for IDE1,
+ * and 0x03 for SMBus.
+ */
+static int pirq_serverworks_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ outb(pirq, 0xc00);
+ return inb(0xc01) & 0xf;
+}
+
+static int pirq_serverworks_set(struct pci_dev *router, struct pci_dev *dev,
+ int pirq, int irq)
+{
+ outb(pirq, 0xc00);
+ outb(irq, 0xc01);
+ return 1;
+}
+
+/* Support for AMD756 PCI IRQ Routing
+ * Jhon H. Caicedo <jhcaiced@osso.org.co>
+ * Jun/21/2001 0.2.0 Release, fixed to use "nybble" functions... (jhcaiced)
+ * Jun/19/2001 Alpha Release 0.1.0 (jhcaiced)
+ * The AMD756 pirq rules are nibble-based
+ * offset 0x56 0-3 PIRQA 4-7 PIRQB
+ * offset 0x57 0-3 PIRQC 4-7 PIRQD
+ */
+static int pirq_amd756_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ u8 irq;
+ irq = 0;
+ if (pirq <= 4)
+ irq = read_config_nybble(router, 0x56, pirq - 1);
+ dev_info(&dev->dev,
+ "AMD756: dev [%04x:%04x], router PIRQ %d get IRQ %d\n",
+ dev->vendor, dev->device, pirq, irq);
+ return irq;
+}
+
+static int pirq_amd756_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq)
+{
+ dev_info(&dev->dev,
+ "AMD756: dev [%04x:%04x], router PIRQ %d set IRQ %d\n",
+ dev->vendor, dev->device, pirq, irq);
+ if (pirq <= 4)
+ write_config_nybble(router, 0x56, pirq - 1, irq);
+ return 1;
+}
+
+/*
+ * PicoPower PT86C523
+ */
+static int pirq_pico_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
+{
+ outb(0x10 + ((pirq - 1) >> 1), 0x24);
+ return ((pirq - 1) & 1) ? (inb(0x26) >> 4) : (inb(0x26) & 0xf);
+}
+
+static int pirq_pico_set(struct pci_dev *router, struct pci_dev *dev, int pirq,
+ int irq)
+{
+ unsigned int x;
+ outb(0x10 + ((pirq - 1) >> 1), 0x24);
+ x = inb(0x26);
+ x = ((pirq - 1) & 1) ? ((x & 0x0f) | (irq << 4)) : ((x & 0xf0) | (irq));
+ outb(x, 0x26);
+ return 1;
+}
+
+#ifdef CONFIG_PCI_BIOS
+
+static int pirq_bios_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq)
+{
+ struct pci_dev *bridge;
+ int pin = pci_get_interrupt_pin(dev, &bridge);
+ return pcibios_set_irq_routing(bridge, pin - 1, irq);
+}
+
+#endif
+
+static __init int intel_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
+{
+ static struct pci_device_id __initdata pirq_440gx[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443GX_0) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443GX_2) },
+ { },
+ };
+
+ /* 440GX has a proprietary PIRQ router -- don't use it */
+ if (pci_dev_present(pirq_440gx))
+ return 0;
+
+ switch (device) {
+ case PCI_DEVICE_ID_INTEL_82375:
+ r->name = "PCEB/ESC";
+ r->get = pirq_esc_get;
+ r->set = pirq_esc_set;
+ return 1;
+ case PCI_DEVICE_ID_INTEL_82371FB_0:
+ case PCI_DEVICE_ID_INTEL_82371SB_0:
+ case PCI_DEVICE_ID_INTEL_82371AB_0:
+ case PCI_DEVICE_ID_INTEL_82371MX:
+ case PCI_DEVICE_ID_INTEL_82443MX_0:
+ case PCI_DEVICE_ID_INTEL_82801AA_0:
+ case PCI_DEVICE_ID_INTEL_82801AB_0:
+ case PCI_DEVICE_ID_INTEL_82801BA_0:
+ case PCI_DEVICE_ID_INTEL_82801BA_10:
+ case PCI_DEVICE_ID_INTEL_82801CA_0:
+ case PCI_DEVICE_ID_INTEL_82801CA_12:
+ case PCI_DEVICE_ID_INTEL_82801DB_0:
+ case PCI_DEVICE_ID_INTEL_82801E_0:
+ case PCI_DEVICE_ID_INTEL_82801EB_0:
+ case PCI_DEVICE_ID_INTEL_ESB_1:
+ case PCI_DEVICE_ID_INTEL_ICH6_0:
+ case PCI_DEVICE_ID_INTEL_ICH6_1:
+ case PCI_DEVICE_ID_INTEL_ICH7_0:
+ case PCI_DEVICE_ID_INTEL_ICH7_1:
+ case PCI_DEVICE_ID_INTEL_ICH7_30:
+ case PCI_DEVICE_ID_INTEL_ICH7_31:
+ case PCI_DEVICE_ID_INTEL_TGP_LPC:
+ case PCI_DEVICE_ID_INTEL_ESB2_0:
+ case PCI_DEVICE_ID_INTEL_ICH8_0:
+ case PCI_DEVICE_ID_INTEL_ICH8_1:
+ case PCI_DEVICE_ID_INTEL_ICH8_2:
+ case PCI_DEVICE_ID_INTEL_ICH8_3:
+ case PCI_DEVICE_ID_INTEL_ICH8_4:
+ case PCI_DEVICE_ID_INTEL_ICH9_0:
+ case PCI_DEVICE_ID_INTEL_ICH9_1:
+ case PCI_DEVICE_ID_INTEL_ICH9_2:
+ case PCI_DEVICE_ID_INTEL_ICH9_3:
+ case PCI_DEVICE_ID_INTEL_ICH9_4:
+ case PCI_DEVICE_ID_INTEL_ICH9_5:
+ case PCI_DEVICE_ID_INTEL_EP80579_0:
+ case PCI_DEVICE_ID_INTEL_ICH10_0:
+ case PCI_DEVICE_ID_INTEL_ICH10_1:
+ case PCI_DEVICE_ID_INTEL_ICH10_2:
+ case PCI_DEVICE_ID_INTEL_ICH10_3:
+ case PCI_DEVICE_ID_INTEL_PATSBURG_LPC_0:
+ case PCI_DEVICE_ID_INTEL_PATSBURG_LPC_1:
+ r->name = "PIIX/ICH";
+ r->get = pirq_piix_get;
+ r->set = pirq_piix_set;
+ return 1;
+ case PCI_DEVICE_ID_INTEL_82425:
+ r->name = "PSC/IB";
+ r->get = pirq_ib_get;
+ r->set = pirq_ib_set;
+ return 1;
+ }
+
+ if ((device >= PCI_DEVICE_ID_INTEL_5_3400_SERIES_LPC_MIN &&
+ device <= PCI_DEVICE_ID_INTEL_5_3400_SERIES_LPC_MAX)
+ || (device >= PCI_DEVICE_ID_INTEL_COUGARPOINT_LPC_MIN &&
+ device <= PCI_DEVICE_ID_INTEL_COUGARPOINT_LPC_MAX)
+ || (device >= PCI_DEVICE_ID_INTEL_DH89XXCC_LPC_MIN &&
+ device <= PCI_DEVICE_ID_INTEL_DH89XXCC_LPC_MAX)
+ || (device >= PCI_DEVICE_ID_INTEL_PANTHERPOINT_LPC_MIN &&
+ device <= PCI_DEVICE_ID_INTEL_PANTHERPOINT_LPC_MAX)) {
+ r->name = "PIIX/ICH";
+ r->get = pirq_piix_get;
+ r->set = pirq_piix_set;
+ return 1;
+ }
+
+ return 0;
+}
+
+static __init int via_router_probe(struct irq_router *r,
+ struct pci_dev *router, u16 device)
+{
+ /* FIXME: We should move some of the quirk fixup stuff here */
+
+ /*
+ * workarounds for some buggy BIOSes
+ */
+ if (device == PCI_DEVICE_ID_VIA_82C586_0) {
+ switch (router->device) {
+ case PCI_DEVICE_ID_VIA_82C686:
+ /*
+ * Asus k7m bios wrongly reports 82C686A
+ * as 586-compatible
+ */
+ device = PCI_DEVICE_ID_VIA_82C686;
+ break;
+ case PCI_DEVICE_ID_VIA_8235:
+ /**
+ * Asus a7v-x bios wrongly reports 8235
+ * as 586-compatible
+ */
+ device = PCI_DEVICE_ID_VIA_8235;
+ break;
+ case PCI_DEVICE_ID_VIA_8237:
+ /**
+ * Asus a7v600 bios wrongly reports 8237
+ * as 586-compatible
+ */
+ device = PCI_DEVICE_ID_VIA_8237;
+ break;
+ }
+ }
+
+ switch (device) {
+ case PCI_DEVICE_ID_VIA_82C586_0:
+ r->name = "VIA";
+ r->get = pirq_via586_get;
+ r->set = pirq_via586_set;
+ return 1;
+ case PCI_DEVICE_ID_VIA_82C596:
+ case PCI_DEVICE_ID_VIA_82C686:
+ case PCI_DEVICE_ID_VIA_8231:
+ case PCI_DEVICE_ID_VIA_8233A:
+ case PCI_DEVICE_ID_VIA_8235:
+ case PCI_DEVICE_ID_VIA_8237:
+ /* FIXME: add new ones for 8233/5 */
+ r->name = "VIA";
+ r->get = pirq_via_get;
+ r->set = pirq_via_set;
+ return 1;
+ }
+ return 0;
+}
+
+static __init int vlsi_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
+{
+ switch (device) {
+ case PCI_DEVICE_ID_VLSI_82C534:
+ r->name = "VLSI 82C534";
+ r->get = pirq_vlsi_get;
+ r->set = pirq_vlsi_set;
+ return 1;
+ }
+ return 0;
+}
+
+
+static __init int serverworks_router_probe(struct irq_router *r,
+ struct pci_dev *router, u16 device)
+{
+ switch (device) {
+ case PCI_DEVICE_ID_SERVERWORKS_OSB4:
+ case PCI_DEVICE_ID_SERVERWORKS_CSB5:
+ r->name = "ServerWorks";
+ r->get = pirq_serverworks_get;
+ r->set = pirq_serverworks_set;
+ return 1;
+ }
+ return 0;
+}
+
+static __init int sis_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
+{
+ switch (device) {
+ case PCI_DEVICE_ID_SI_496:
+ r->name = "SiS85C497";
+ r->get = pirq_sis497_get;
+ r->set = pirq_sis497_set;
+ return 1;
+ case PCI_DEVICE_ID_SI_503:
+ r->name = "SiS85C503";
+ r->get = pirq_sis503_get;
+ r->set = pirq_sis503_set;
+ return 1;
+ }
+ return 0;
+}
+
+static __init int cyrix_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
+{
+ switch (device) {
+ case PCI_DEVICE_ID_CYRIX_5520:
+ r->name = "NatSemi";
+ r->get = pirq_cyrix_get;
+ r->set = pirq_cyrix_set;
+ return 1;
+ }
+ return 0;
+}
+
+static __init int opti_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
+{
+ switch (device) {
+ case PCI_DEVICE_ID_OPTI_82C700:
+ r->name = "OPTI";
+ r->get = pirq_opti_get;
+ r->set = pirq_opti_set;
+ return 1;
+ }
+ return 0;
+}
+
+static __init int ite_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
+{
+ switch (device) {
+ case PCI_DEVICE_ID_ITE_IT8330G_0:
+ r->name = "ITE";
+ r->get = pirq_ite_get;
+ r->set = pirq_ite_set;
+ return 1;
+ }
+ return 0;
+}
+
+static __init int ali_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
+{
+ switch (device) {
+ case PCI_DEVICE_ID_AL_M1489:
+ r->name = "FinALi";
+ r->get = pirq_finali_get;
+ r->set = pirq_finali_set;
+ r->lvl = pirq_finali_lvl;
+ return 1;
+ case PCI_DEVICE_ID_AL_M1533:
+ case PCI_DEVICE_ID_AL_M1563:
+ r->name = "ALI";
+ r->get = pirq_ali_get;
+ r->set = pirq_ali_set;
+ return 1;
+ }
+ return 0;
+}
+
+static __init int amd_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
+{
+ switch (device) {
+ case PCI_DEVICE_ID_AMD_VIPER_740B:
+ r->name = "AMD756";
+ break;
+ case PCI_DEVICE_ID_AMD_VIPER_7413:
+ r->name = "AMD766";
+ break;
+ case PCI_DEVICE_ID_AMD_VIPER_7443:
+ r->name = "AMD768";
+ break;
+ default:
+ return 0;
+ }
+ r->get = pirq_amd756_get;
+ r->set = pirq_amd756_set;
+ return 1;
+}
+
+static __init int pico_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
+{
+ switch (device) {
+ case PCI_DEVICE_ID_PICOPOWER_PT86C523:
+ r->name = "PicoPower PT86C523";
+ r->get = pirq_pico_get;
+ r->set = pirq_pico_set;
+ return 1;
+
+ case PCI_DEVICE_ID_PICOPOWER_PT86C523BBP:
+ r->name = "PicoPower PT86C523 rev. BB+";
+ r->get = pirq_pico_get;
+ r->set = pirq_pico_set;
+ return 1;
+ }
+ return 0;
+}
+
+static __initdata struct irq_router_handler pirq_routers[] = {
+ { PCI_VENDOR_ID_INTEL, intel_router_probe },
+ { PCI_VENDOR_ID_AL, ali_router_probe },
+ { PCI_VENDOR_ID_ITE, ite_router_probe },
+ { PCI_VENDOR_ID_VIA, via_router_probe },
+ { PCI_VENDOR_ID_OPTI, opti_router_probe },
+ { PCI_VENDOR_ID_SI, sis_router_probe },
+ { PCI_VENDOR_ID_CYRIX, cyrix_router_probe },
+ { PCI_VENDOR_ID_VLSI, vlsi_router_probe },
+ { PCI_VENDOR_ID_SERVERWORKS, serverworks_router_probe },
+ { PCI_VENDOR_ID_AMD, amd_router_probe },
+ { PCI_VENDOR_ID_PICOPOWER, pico_router_probe },
+ /* Someone with docs needs to add the ATI Radeon IGP */
+ { 0, NULL }
+};
+static struct irq_router pirq_router;
+static struct pci_dev *pirq_router_dev;
+
+
+/*
+ * FIXME: should we have an option to say "generic for
+ * chipset" ?
+ */
+
+static bool __init pirq_try_router(struct irq_router *r,
+ struct irq_routing_table *rt,
+ struct pci_dev *dev)
+{
+ struct irq_router_handler *h;
+
+ DBG(KERN_DEBUG "PCI: Trying IRQ router for [%04x:%04x]\n",
+ dev->vendor, dev->device);
+
+ for (h = pirq_routers; h->vendor; h++) {
+ /* First look for a router match */
+ if (rt->rtr_vendor == h->vendor &&
+ h->probe(r, dev, rt->rtr_device))
+ return true;
+ /* Fall back to a device match */
+ if (dev->vendor == h->vendor &&
+ h->probe(r, dev, dev->device))
+ return true;
+ }
+ return false;
+}
+
+static void __init pirq_find_router(struct irq_router *r)
+{
+ struct irq_routing_table *rt = pirq_table;
+ struct pci_dev *dev;
+
+#ifdef CONFIG_PCI_BIOS
+ if (!rt->signature) {
+ printk(KERN_INFO "PCI: Using BIOS for IRQ routing\n");
+ r->set = pirq_bios_set;
+ r->name = "BIOS";
+ return;
+ }
+#endif
+
+ /* Default unless a driver reloads it */
+ r->name = "default";
+ r->get = NULL;
+ r->set = NULL;
+
+ DBG(KERN_DEBUG "PCI: Attempting to find IRQ router for [%04x:%04x]\n",
+ rt->rtr_vendor, rt->rtr_device);
+
+ /* Use any vendor:device provided by the routing table or try all. */
+ if (rt->rtr_vendor) {
+ dev = pci_get_domain_bus_and_slot(0, rt->rtr_bus,
+ rt->rtr_devfn);
+ if (dev && pirq_try_router(r, rt, dev))
+ pirq_router_dev = dev;
+ } else {
+ dev = NULL;
+ for_each_pci_dev(dev) {
+ if (pirq_try_router(r, rt, dev)) {
+ pirq_router_dev = dev;
+ break;
+ }
+ }
+ }
+
+ if (pirq_router_dev)
+ dev_info(&pirq_router_dev->dev, "%s IRQ router [%04x:%04x]\n",
+ pirq_router.name,
+ pirq_router_dev->vendor, pirq_router_dev->device);
+ else
+ DBG(KERN_DEBUG "PCI: Interrupt router not found at "
+ "%02x:%02x\n", rt->rtr_bus, rt->rtr_devfn);
+
+ /* The device remains referenced for the kernel lifetime */
+}
+
+/*
+ * We're supposed to match on the PCI device only and not the function,
+ * but some BIOSes build their tables with the PCI function included
+ * for motherboard devices, so if a complete match is found, then give
+ * it precedence over a slot match.
+ */
+static struct irq_info *pirq_get_dev_info(struct pci_dev *dev)
+{
+ struct irq_routing_table *rt = pirq_table;
+ int entries = (rt->size - sizeof(struct irq_routing_table)) /
+ sizeof(struct irq_info);
+ struct irq_info *slotinfo = NULL;
+ struct irq_info *info;
+
+ for (info = rt->slots; entries--; info++)
+ if (info->bus == dev->bus->number) {
+ if (info->devfn == dev->devfn)
+ return info;
+ if (!slotinfo &&
+ PCI_SLOT(info->devfn) == PCI_SLOT(dev->devfn))
+ slotinfo = info;
+ }
+ return slotinfo;
+}
+
+/*
+ * Buses behind bridges are typically not listed in the PIRQ routing table.
+ * Do the usual dance then and walk the tree of bridges up adjusting the
+ * pin number accordingly on the way until the originating root bus device
+ * has been reached and then use its routing information.
+ */
+static struct irq_info *pirq_get_info(struct pci_dev *dev, u8 *pin)
+{
+ struct pci_dev *temp_dev = dev;
+ struct irq_info *info;
+ u8 temp_pin = *pin;
+ u8 dpin = temp_pin;
+
+ info = pirq_get_dev_info(dev);
+ while (!info && temp_dev->bus->parent) {
+ struct pci_dev *bridge = temp_dev->bus->self;
+
+ temp_pin = pci_swizzle_interrupt_pin(temp_dev, temp_pin);
+ info = pirq_get_dev_info(bridge);
+ if (info)
+ dev_warn(&dev->dev,
+ "using bridge %s INT %c to get INT %c\n",
+ pci_name(bridge),
+ 'A' + temp_pin - 1, 'A' + dpin - 1);
+
+ temp_dev = bridge;
+ }
+ *pin = temp_pin;
+ return info;
+}
+
+static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
+{
+ struct irq_info *info;
+ int i, pirq, newirq;
+ u8 dpin, pin;
+ int irq = 0;
+ u32 mask;
+ struct irq_router *r = &pirq_router;
+ struct pci_dev *dev2 = NULL;
+ char *msg = NULL;
+
+ /* Find IRQ pin */
+ pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &dpin);
+ if (!dpin) {
+ dev_dbg(&dev->dev, "no interrupt pin\n");
+ return 0;
+ }
+
+ if (io_apic_assign_pci_irqs)
+ return 0;
+
+ /* Find IRQ routing entry */
+
+ if (!pirq_table)
+ return 0;
+
+ pin = dpin;
+ info = pirq_get_info(dev, &pin);
+ if (!info) {
+ dev_dbg(&dev->dev, "PCI INT %c not found in routing table\n",
+ 'A' + dpin - 1);
+ return 0;
+ }
+ pirq = info->irq[pin - 1].link;
+ mask = info->irq[pin - 1].bitmap;
+ if (!pirq) {
+ dev_dbg(&dev->dev, "PCI INT %c not routed\n", 'A' + dpin - 1);
+ return 0;
+ }
+ dev_dbg(&dev->dev, "PCI INT %c -> PIRQ %02x, mask %04x, excl %04x",
+ 'A' + dpin - 1, pirq, mask, pirq_table->exclusive_irqs);
+ mask &= pcibios_irq_mask;
+
+ /* Work around broken HP Pavilion Notebooks which assign USB to
+ IRQ 9 even though it is actually wired to IRQ 11 */
+
+ if (broken_hp_bios_irq9 && pirq == 0x59 && dev->irq == 9) {
+ dev->irq = 11;
+ pci_write_config_byte(dev, PCI_INTERRUPT_LINE, 11);
+ r->set(pirq_router_dev, dev, pirq, 11);
+ }
+
+ /* same for Acer Travelmate 360, but with CB and irq 11 -> 10 */
+ if (acer_tm360_irqrouting && dev->irq == 11 &&
+ dev->vendor == PCI_VENDOR_ID_O2) {
+ pirq = 0x68;
+ mask = 0x400;
+ dev->irq = r->get(pirq_router_dev, dev, pirq);
+ pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq);
+ }
+
+ /*
+ * Find the best IRQ to assign: use the one
+ * reported by the device if possible.
+ */
+ newirq = dev->irq;
+ if (newirq && !((1 << newirq) & mask)) {
+ if (pci_probe & PCI_USE_PIRQ_MASK)
+ newirq = 0;
+ else
+ dev_warn(&dev->dev, "IRQ %d doesn't match PIRQ mask "
+ "%#x; try pci=usepirqmask\n", newirq, mask);
+ }
+ if (!newirq && assign) {
+ for (i = 0; i < 16; i++) {
+ if (!(mask & (1 << i)))
+ continue;
+ if (pirq_penalty[i] < pirq_penalty[newirq] &&
+ can_request_irq(i, IRQF_SHARED))
+ newirq = i;
+ }
+ }
+ dev_dbg(&dev->dev, "PCI INT %c -> newirq %d", 'A' + dpin - 1, newirq);
+
+ /* Check if it is hardcoded */
+ if ((pirq & 0xf0) == 0xf0) {
+ irq = pirq & 0xf;
+ msg = "hardcoded";
+ } else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \
+ ((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) {
+ msg = "found";
+ if (r->lvl)
+ r->lvl(pirq_router_dev, dev, pirq, irq);
+ else
+ elcr_set_level_irq(irq);
+ } else if (newirq && r->set &&
+ (dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) {
+ if (r->set(pirq_router_dev, dev, pirq, newirq)) {
+ if (r->lvl)
+ r->lvl(pirq_router_dev, dev, pirq, newirq);
+ else
+ elcr_set_level_irq(newirq);
+ msg = "assigned";
+ irq = newirq;
+ }
+ }
+
+ if (!irq) {
+ if (newirq && mask == (1 << newirq)) {
+ msg = "guessed";
+ irq = newirq;
+ } else {
+ dev_dbg(&dev->dev, "can't route interrupt\n");
+ return 0;
+ }
+ }
+ dev_info(&dev->dev, "%s PCI INT %c -> IRQ %d\n",
+ msg, 'A' + dpin - 1, irq);
+
+ /* Update IRQ for all devices with the same pirq value */
+ for_each_pci_dev(dev2) {
+ pci_read_config_byte(dev2, PCI_INTERRUPT_PIN, &dpin);
+ if (!dpin)
+ continue;
+
+ pin = dpin;
+ info = pirq_get_info(dev2, &pin);
+ if (!info)
+ continue;
+ if (info->irq[pin - 1].link == pirq) {
+ /*
+ * We refuse to override the dev->irq
+ * information. Give a warning!
+ */
+ if (dev2->irq && dev2->irq != irq && \
+ (!(pci_probe & PCI_USE_PIRQ_MASK) || \
+ ((1 << dev2->irq) & mask))) {
+#ifndef CONFIG_PCI_MSI
+ dev_info(&dev2->dev, "IRQ routing conflict: "
+ "have IRQ %d, want IRQ %d\n",
+ dev2->irq, irq);
+#endif
+ continue;
+ }
+ dev2->irq = irq;
+ pirq_penalty[irq]++;
+ if (dev != dev2)
+ dev_info(&dev->dev, "sharing IRQ %d with %s\n",
+ irq, pci_name(dev2));
+ }
+ }
+ return 1;
+}
+
+void __init pcibios_fixup_irqs(void)
+{
+ struct pci_dev *dev = NULL;
+ u8 pin;
+
+ DBG(KERN_DEBUG "PCI: IRQ fixup\n");
+ for_each_pci_dev(dev) {
+ /*
+ * If the BIOS has set an out of range IRQ number, just
+ * ignore it. Also keep track of which IRQ's are
+ * already in use.
+ */
+ if (dev->irq >= 16) {
+ dev_dbg(&dev->dev, "ignoring bogus IRQ %d\n", dev->irq);
+ dev->irq = 0;
+ }
+ /*
+ * If the IRQ is already assigned to a PCI device,
+ * ignore its ISA use penalty
+ */
+ if (pirq_penalty[dev->irq] >= 100 &&
+ pirq_penalty[dev->irq] < 100000)
+ pirq_penalty[dev->irq] = 0;
+ pirq_penalty[dev->irq]++;
+ }
+
+ if (io_apic_assign_pci_irqs)
+ return;
+
+ dev = NULL;
+ for_each_pci_dev(dev) {
+ pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+ if (!pin)
+ continue;
+
+ /*
+ * Still no IRQ? Try to lookup one...
+ */
+ if (!dev->irq)
+ pcibios_lookup_irq(dev, 0);
+ }
+}
+
+/*
+ * Work around broken HP Pavilion Notebooks which assign USB to
+ * IRQ 9 even though it is actually wired to IRQ 11
+ */
+static int __init fix_broken_hp_bios_irq9(const struct dmi_system_id *d)
+{
+ if (!broken_hp_bios_irq9) {
+ broken_hp_bios_irq9 = 1;
+ printk(KERN_INFO "%s detected - fixing broken IRQ routing\n",
+ d->ident);
+ }
+ return 0;
+}
+
+/*
+ * Work around broken Acer TravelMate 360 Notebooks which assign
+ * Cardbus to IRQ 11 even though it is actually wired to IRQ 10
+ */
+static int __init fix_acer_tm360_irqrouting(const struct dmi_system_id *d)
+{
+ if (!acer_tm360_irqrouting) {
+ acer_tm360_irqrouting = 1;
+ printk(KERN_INFO "%s detected - fixing broken IRQ routing\n",
+ d->ident);
+ }
+ return 0;
+}
+
+static const struct dmi_system_id pciirq_dmi_table[] __initconst = {
+ {
+ .callback = fix_broken_hp_bios_irq9,
+ .ident = "HP Pavilion N5400 Series Laptop",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_BIOS_VERSION, "GE.M1.03"),
+ DMI_MATCH(DMI_PRODUCT_VERSION,
+ "HP Pavilion Notebook Model GE"),
+ DMI_MATCH(DMI_BOARD_VERSION, "OmniBook N32N-736"),
+ },
+ },
+ {
+ .callback = fix_acer_tm360_irqrouting,
+ .ident = "Acer TravelMate 36x Laptop",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 360"),
+ },
+ },
+ { }
+};
+
+void __init pcibios_irq_init(void)
+{
+ struct irq_routing_table *rtable = NULL;
+
+ DBG(KERN_DEBUG "PCI: IRQ init\n");
+
+ if (raw_pci_ops == NULL)
+ return;
+
+ dmi_check_system(pciirq_dmi_table);
+
+ pirq_table = pirq_find_routing_table();
+
+#ifdef CONFIG_PCI_BIOS
+ if (!pirq_table && (pci_probe & PCI_BIOS_IRQ_SCAN)) {
+ pirq_table = pcibios_get_irq_routing_table();
+ rtable = pirq_table;
+ }
+#endif
+ if (pirq_table) {
+ pirq_peer_trick();
+ pirq_find_router(&pirq_router);
+ if (pirq_table->exclusive_irqs) {
+ int i;
+ for (i = 0; i < 16; i++)
+ if (!(pirq_table->exclusive_irqs & (1 << i)))
+ pirq_penalty[i] += 100;
+ }
+ /*
+ * If we're using the I/O APIC, avoid using the PCI IRQ
+ * routing table
+ */
+ if (io_apic_assign_pci_irqs) {
+ kfree(rtable);
+ pirq_table = NULL;
+ }
+ }
+
+ x86_init.pci.fixup_irqs();
+
+ if (io_apic_assign_pci_irqs && pci_routeirq) {
+ struct pci_dev *dev = NULL;
+ /*
+ * PCI IRQ routing is set up by pci_enable_device(), but we
+ * also do it here in case there are still broken drivers that
+ * don't use pci_enable_device().
+ */
+ printk(KERN_INFO "PCI: Routing PCI interrupts for all devices because \"pci=routeirq\" specified\n");
+ for_each_pci_dev(dev)
+ pirq_enable_irq(dev);
+ }
+}
+
+static void pirq_penalize_isa_irq(int irq, int active)
+{
+ /*
+ * If any ISAPnP device reports an IRQ in its list of possible
+ * IRQ's, we try to avoid assigning it to PCI devices.
+ */
+ if (irq < 16) {
+ if (active)
+ pirq_penalty[irq] += 1000;
+ else
+ pirq_penalty[irq] += 100;
+ }
+}
+
+void pcibios_penalize_isa_irq(int irq, int active)
+{
+#ifdef CONFIG_ACPI
+ if (!acpi_noirq)
+ acpi_penalize_isa_irq(irq, active);
+ else
+#endif
+ pirq_penalize_isa_irq(irq, active);
+}
+
+static int pirq_enable_irq(struct pci_dev *dev)
+{
+ u8 pin = 0;
+
+ pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+ if (pin && !pcibios_lookup_irq(dev, 1)) {
+ char *msg = "";
+
+ if (!io_apic_assign_pci_irqs && dev->irq)
+ return 0;
+
+ if (io_apic_assign_pci_irqs) {
+#ifdef CONFIG_X86_IO_APIC
+ struct pci_dev *temp_dev;
+ int irq;
+
+ if (dev->irq_managed && dev->irq > 0)
+ return 0;
+
+ irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
+ PCI_SLOT(dev->devfn), pin - 1);
+ /*
+ * Busses behind bridges are typically not listed in the MP-table.
+ * In this case we have to look up the IRQ based on the parent bus,
+ * parent slot, and pin number. The SMP code detects such bridged
+ * busses itself so we should get into this branch reliably.
+ */
+ temp_dev = dev;
+ while (irq < 0 && dev->bus->parent) { /* go back to the bridge */
+ struct pci_dev *bridge = dev->bus->self;
+
+ pin = pci_swizzle_interrupt_pin(dev, pin);
+ irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number,
+ PCI_SLOT(bridge->devfn),
+ pin - 1);
+ if (irq >= 0)
+ dev_warn(&dev->dev, "using bridge %s "
+ "INT %c to get IRQ %d\n",
+ pci_name(bridge), 'A' + pin - 1,
+ irq);
+ dev = bridge;
+ }
+ dev = temp_dev;
+ if (irq >= 0) {
+ dev->irq_managed = 1;
+ dev->irq = irq;
+ dev_info(&dev->dev, "PCI->APIC IRQ transform: "
+ "INT %c -> IRQ %d\n", 'A' + pin - 1, irq);
+ return 0;
+ } else
+ msg = "; probably buggy MP table";
+#endif
+ } else if (pci_probe & PCI_BIOS_IRQ_SCAN)
+ msg = "";
+ else
+ msg = "; please try using pci=biosirq";
+
+ /*
+ * With IDE legacy devices the IRQ lookup failure is not
+ * a problem..
+ */
+ if (dev->class >> 8 == PCI_CLASS_STORAGE_IDE &&
+ !(dev->class & 0x5))
+ return 0;
+
+ dev_warn(&dev->dev, "can't find IRQ for PCI INT %c%s\n",
+ 'A' + pin - 1, msg);
+ }
+ return 0;
+}
+
+bool mp_should_keep_irq(struct device *dev)
+{
+ if (dev->power.is_prepared)
+ return true;
+#ifdef CONFIG_PM
+ if (dev->power.runtime_status == RPM_SUSPENDING)
+ return true;
+#endif
+
+ return false;
+}
+
+static void pirq_disable_irq(struct pci_dev *dev)
+{
+ if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) &&
+ dev->irq_managed && dev->irq) {
+ mp_unmap_irq(dev->irq);
+ dev->irq = 0;
+ dev->irq_managed = 0;
+ }
+}
diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c
new file mode 100644
index 0000000000..467311b1ee
--- /dev/null
+++ b/arch/x86/pci/legacy.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * legacy.c - traditional, old school PCI bus probing
+ */
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/pci.h>
+#include <asm/jailhouse_para.h>
+#include <asm/pci_x86.h>
+
+/*
+ * Discover remaining PCI buses in case there are peer host bridges.
+ * We use the number of last PCI bus provided by the PCI BIOS.
+ */
+static void pcibios_fixup_peer_bridges(void)
+{
+ int n;
+
+ if (pcibios_last_bus <= 0 || pcibios_last_bus > 0xff)
+ return;
+ DBG("PCI: Peer bridge fixup\n");
+
+ for (n=0; n <= pcibios_last_bus; n++)
+ pcibios_scan_specific_bus(n);
+}
+
+int __init pci_legacy_init(void)
+{
+ if (!raw_pci_ops)
+ return 1;
+
+ pr_info("PCI: Probing PCI hardware\n");
+ pcibios_scan_root(0);
+ return 0;
+}
+
+void pcibios_scan_specific_bus(int busn)
+{
+ int stride = jailhouse_paravirt() ? 1 : 8;
+ int devfn;
+ u32 l;
+
+ if (pci_find_bus(0, busn))
+ return;
+
+ for (devfn = 0; devfn < 256; devfn += stride) {
+ if (!raw_pci_read(0, busn, devfn, PCI_VENDOR_ID, 2, &l) &&
+ l != 0x0000 && l != 0xffff) {
+ DBG("Found device at %02x:%02x [%04x]\n", busn, devfn, l);
+ pr_info("PCI: Discovered peer bus %02x\n", busn);
+ pcibios_scan_root(busn);
+ return;
+ }
+ }
+}
+EXPORT_SYMBOL_GPL(pcibios_scan_specific_bus);
+
+static int __init pci_subsys_init(void)
+{
+ /*
+ * The init function returns an non zero value when
+ * pci_legacy_init should be invoked.
+ */
+ if (x86_init.pci.init()) {
+ if (pci_legacy_init()) {
+ pr_info("PCI: System does not support PCI\n");
+ return -ENODEV;
+ }
+ }
+
+ pcibios_fixup_peer_bridges();
+ x86_init.pci.init_irq();
+ pcibios_init();
+
+ return 0;
+}
+subsys_initcall(pci_subsys_init);
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
new file mode 100644
index 0000000000..e9497ee0f8
--- /dev/null
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -0,0 +1,858 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * mmconfig-shared.c - Low-level direct PCI config space access via
+ * MMCONFIG - common code between i386 and x86-64.
+ *
+ * This code does:
+ * - known chipset handling
+ * - ACPI decoding and validation
+ *
+ * Per-architecture code takes care of the mappings and accesses
+ * themselves.
+ */
+
+#include <linux/acpi.h>
+#include <linux/efi.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/bitmap.h>
+#include <linux/dmi.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/rculist.h>
+#include <asm/e820/api.h>
+#include <asm/pci_x86.h>
+#include <asm/acpi.h>
+
+#define PREFIX "PCI: "
+
+/* Indicate if the mmcfg resources have been placed into the resource table. */
+static bool pci_mmcfg_running_state;
+static bool pci_mmcfg_arch_init_failed;
+static DEFINE_MUTEX(pci_mmcfg_lock);
+#define pci_mmcfg_lock_held() lock_is_held(&(pci_mmcfg_lock).dep_map)
+
+LIST_HEAD(pci_mmcfg_list);
+
+static void __init pci_mmconfig_remove(struct pci_mmcfg_region *cfg)
+{
+ if (cfg->res.parent)
+ release_resource(&cfg->res);
+ list_del(&cfg->list);
+ kfree(cfg);
+}
+
+static void __init free_all_mmcfg(void)
+{
+ struct pci_mmcfg_region *cfg, *tmp;
+
+ pci_mmcfg_arch_free();
+ list_for_each_entry_safe(cfg, tmp, &pci_mmcfg_list, list)
+ pci_mmconfig_remove(cfg);
+}
+
+static void list_add_sorted(struct pci_mmcfg_region *new)
+{
+ struct pci_mmcfg_region *cfg;
+
+ /* keep list sorted by segment and starting bus number */
+ list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list, pci_mmcfg_lock_held()) {
+ if (cfg->segment > new->segment ||
+ (cfg->segment == new->segment &&
+ cfg->start_bus >= new->start_bus)) {
+ list_add_tail_rcu(&new->list, &cfg->list);
+ return;
+ }
+ }
+ list_add_tail_rcu(&new->list, &pci_mmcfg_list);
+}
+
+static struct pci_mmcfg_region *pci_mmconfig_alloc(int segment, int start,
+ int end, u64 addr)
+{
+ struct pci_mmcfg_region *new;
+ struct resource *res;
+
+ if (addr == 0)
+ return NULL;
+
+ new = kzalloc(sizeof(*new), GFP_KERNEL);
+ if (!new)
+ return NULL;
+
+ new->address = addr;
+ new->segment = segment;
+ new->start_bus = start;
+ new->end_bus = end;
+
+ res = &new->res;
+ res->start = addr + PCI_MMCFG_BUS_OFFSET(start);
+ res->end = addr + PCI_MMCFG_BUS_OFFSET(end + 1) - 1;
+ res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+ snprintf(new->name, PCI_MMCFG_RESOURCE_NAME_LEN,
+ "PCI MMCONFIG %04x [bus %02x-%02x]", segment, start, end);
+ res->name = new->name;
+
+ return new;
+}
+
+struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start,
+ int end, u64 addr)
+{
+ struct pci_mmcfg_region *new;
+
+ new = pci_mmconfig_alloc(segment, start, end, addr);
+ if (new) {
+ mutex_lock(&pci_mmcfg_lock);
+ list_add_sorted(new);
+ mutex_unlock(&pci_mmcfg_lock);
+
+ pr_info(PREFIX
+ "MMCONFIG for domain %04x [bus %02x-%02x] at %pR "
+ "(base %#lx)\n",
+ segment, start, end, &new->res, (unsigned long)addr);
+ }
+
+ return new;
+}
+
+struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus)
+{
+ struct pci_mmcfg_region *cfg;
+
+ list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list, pci_mmcfg_lock_held())
+ if (cfg->segment == segment &&
+ cfg->start_bus <= bus && bus <= cfg->end_bus)
+ return cfg;
+
+ return NULL;
+}
+
+static const char *__init pci_mmcfg_e7520(void)
+{
+ u32 win;
+ raw_pci_ops->read(0, 0, PCI_DEVFN(0, 0), 0xce, 2, &win);
+
+ win = win & 0xf000;
+ if (win == 0x0000 || win == 0xf000)
+ return NULL;
+
+ if (pci_mmconfig_add(0, 0, 255, win << 16) == NULL)
+ return NULL;
+
+ return "Intel Corporation E7520 Memory Controller Hub";
+}
+
+static const char *__init pci_mmcfg_intel_945(void)
+{
+ u32 pciexbar, mask = 0, len = 0;
+
+ raw_pci_ops->read(0, 0, PCI_DEVFN(0, 0), 0x48, 4, &pciexbar);
+
+ /* Enable bit */
+ if (!(pciexbar & 1))
+ return NULL;
+
+ /* Size bits */
+ switch ((pciexbar >> 1) & 3) {
+ case 0:
+ mask = 0xf0000000U;
+ len = 0x10000000U;
+ break;
+ case 1:
+ mask = 0xf8000000U;
+ len = 0x08000000U;
+ break;
+ case 2:
+ mask = 0xfc000000U;
+ len = 0x04000000U;
+ break;
+ default:
+ return NULL;
+ }
+
+ /* Errata #2, things break when not aligned on a 256Mb boundary */
+ /* Can only happen in 64M/128M mode */
+
+ if ((pciexbar & mask) & 0x0fffffffU)
+ return NULL;
+
+ /* Don't hit the APIC registers and their friends */
+ if ((pciexbar & mask) >= 0xf0000000U)
+ return NULL;
+
+ if (pci_mmconfig_add(0, 0, (len >> 20) - 1, pciexbar & mask) == NULL)
+ return NULL;
+
+ return "Intel Corporation 945G/GZ/P/PL Express Memory Controller Hub";
+}
+
+static const char *__init pci_mmcfg_amd_fam10h(void)
+{
+ u32 low, high, address;
+ u64 base, msr;
+ int i;
+ unsigned segnbits = 0, busnbits, end_bus;
+
+ if (!(pci_probe & PCI_CHECK_ENABLE_AMD_MMCONF))
+ return NULL;
+
+ address = MSR_FAM10H_MMIO_CONF_BASE;
+ if (rdmsr_safe(address, &low, &high))
+ return NULL;
+
+ msr = high;
+ msr <<= 32;
+ msr |= low;
+
+ /* mmconfig is not enable */
+ if (!(msr & FAM10H_MMIO_CONF_ENABLE))
+ return NULL;
+
+ base = msr & (FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT);
+
+ busnbits = (msr >> FAM10H_MMIO_CONF_BUSRANGE_SHIFT) &
+ FAM10H_MMIO_CONF_BUSRANGE_MASK;
+
+ /*
+ * only handle bus 0 ?
+ * need to skip it
+ */
+ if (!busnbits)
+ return NULL;
+
+ if (busnbits > 8) {
+ segnbits = busnbits - 8;
+ busnbits = 8;
+ }
+
+ end_bus = (1 << busnbits) - 1;
+ for (i = 0; i < (1 << segnbits); i++)
+ if (pci_mmconfig_add(i, 0, end_bus,
+ base + (1<<28) * i) == NULL) {
+ free_all_mmcfg();
+ return NULL;
+ }
+
+ return "AMD Family 10h NB";
+}
+
+static bool __initdata mcp55_checked;
+static const char *__init pci_mmcfg_nvidia_mcp55(void)
+{
+ int bus;
+ int mcp55_mmconf_found = 0;
+
+ static const u32 extcfg_regnum __initconst = 0x90;
+ static const u32 extcfg_regsize __initconst = 4;
+ static const u32 extcfg_enable_mask __initconst = 1 << 31;
+ static const u32 extcfg_start_mask __initconst = 0xff << 16;
+ static const int extcfg_start_shift __initconst = 16;
+ static const u32 extcfg_size_mask __initconst = 0x3 << 28;
+ static const int extcfg_size_shift __initconst = 28;
+ static const int extcfg_sizebus[] __initconst = {
+ 0x100, 0x80, 0x40, 0x20
+ };
+ static const u32 extcfg_base_mask[] __initconst = {
+ 0x7ff8, 0x7ffc, 0x7ffe, 0x7fff
+ };
+ static const int extcfg_base_lshift __initconst = 25;
+
+ /*
+ * do check if amd fam10h already took over
+ */
+ if (!acpi_disabled || !list_empty(&pci_mmcfg_list) || mcp55_checked)
+ return NULL;
+
+ mcp55_checked = true;
+ for (bus = 0; bus < 256; bus++) {
+ u64 base;
+ u32 l, extcfg;
+ u16 vendor, device;
+ int start, size_index, end;
+
+ raw_pci_ops->read(0, bus, PCI_DEVFN(0, 0), 0, 4, &l);
+ vendor = l & 0xffff;
+ device = (l >> 16) & 0xffff;
+
+ if (PCI_VENDOR_ID_NVIDIA != vendor || 0x0369 != device)
+ continue;
+
+ raw_pci_ops->read(0, bus, PCI_DEVFN(0, 0), extcfg_regnum,
+ extcfg_regsize, &extcfg);
+
+ if (!(extcfg & extcfg_enable_mask))
+ continue;
+
+ size_index = (extcfg & extcfg_size_mask) >> extcfg_size_shift;
+ base = extcfg & extcfg_base_mask[size_index];
+ /* base could > 4G */
+ base <<= extcfg_base_lshift;
+ start = (extcfg & extcfg_start_mask) >> extcfg_start_shift;
+ end = start + extcfg_sizebus[size_index] - 1;
+ if (pci_mmconfig_add(0, start, end, base) == NULL)
+ continue;
+ mcp55_mmconf_found++;
+ }
+
+ if (!mcp55_mmconf_found)
+ return NULL;
+
+ return "nVidia MCP55";
+}
+
+struct pci_mmcfg_hostbridge_probe {
+ u32 bus;
+ u32 devfn;
+ u32 vendor;
+ u32 device;
+ const char *(*probe)(void);
+};
+
+static const struct pci_mmcfg_hostbridge_probe pci_mmcfg_probes[] __initconst = {
+ { 0, PCI_DEVFN(0, 0), PCI_VENDOR_ID_INTEL,
+ PCI_DEVICE_ID_INTEL_E7520_MCH, pci_mmcfg_e7520 },
+ { 0, PCI_DEVFN(0, 0), PCI_VENDOR_ID_INTEL,
+ PCI_DEVICE_ID_INTEL_82945G_HB, pci_mmcfg_intel_945 },
+ { 0, PCI_DEVFN(0x18, 0), PCI_VENDOR_ID_AMD,
+ 0x1200, pci_mmcfg_amd_fam10h },
+ { 0xff, PCI_DEVFN(0, 0), PCI_VENDOR_ID_AMD,
+ 0x1200, pci_mmcfg_amd_fam10h },
+ { 0, PCI_DEVFN(0, 0), PCI_VENDOR_ID_NVIDIA,
+ 0x0369, pci_mmcfg_nvidia_mcp55 },
+};
+
+static void __init pci_mmcfg_check_end_bus_number(void)
+{
+ struct pci_mmcfg_region *cfg, *cfgx;
+
+ /* Fixup overlaps */
+ list_for_each_entry(cfg, &pci_mmcfg_list, list) {
+ if (cfg->end_bus < cfg->start_bus)
+ cfg->end_bus = 255;
+
+ /* Don't access the list head ! */
+ if (cfg->list.next == &pci_mmcfg_list)
+ break;
+
+ cfgx = list_entry(cfg->list.next, typeof(*cfg), list);
+ if (cfg->end_bus >= cfgx->start_bus)
+ cfg->end_bus = cfgx->start_bus - 1;
+ }
+}
+
+static int __init pci_mmcfg_check_hostbridge(void)
+{
+ u32 l;
+ u32 bus, devfn;
+ u16 vendor, device;
+ int i;
+ const char *name;
+
+ if (!raw_pci_ops)
+ return 0;
+
+ free_all_mmcfg();
+
+ for (i = 0; i < ARRAY_SIZE(pci_mmcfg_probes); i++) {
+ bus = pci_mmcfg_probes[i].bus;
+ devfn = pci_mmcfg_probes[i].devfn;
+ raw_pci_ops->read(0, bus, devfn, 0, 4, &l);
+ vendor = l & 0xffff;
+ device = (l >> 16) & 0xffff;
+
+ name = NULL;
+ if (pci_mmcfg_probes[i].vendor == vendor &&
+ pci_mmcfg_probes[i].device == device)
+ name = pci_mmcfg_probes[i].probe();
+
+ if (name)
+ pr_info(PREFIX "%s with MMCONFIG support\n", name);
+ }
+
+ /* some end_bus_number is crazy, fix it */
+ pci_mmcfg_check_end_bus_number();
+
+ return !list_empty(&pci_mmcfg_list);
+}
+
+static acpi_status check_mcfg_resource(struct acpi_resource *res, void *data)
+{
+ struct resource *mcfg_res = data;
+ struct acpi_resource_address64 address;
+ acpi_status status;
+
+ if (res->type == ACPI_RESOURCE_TYPE_FIXED_MEMORY32) {
+ struct acpi_resource_fixed_memory32 *fixmem32 =
+ &res->data.fixed_memory32;
+ if (!fixmem32)
+ return AE_OK;
+ if ((mcfg_res->start >= fixmem32->address) &&
+ (mcfg_res->end < (fixmem32->address +
+ fixmem32->address_length))) {
+ mcfg_res->flags = 1;
+ return AE_CTRL_TERMINATE;
+ }
+ }
+ if ((res->type != ACPI_RESOURCE_TYPE_ADDRESS32) &&
+ (res->type != ACPI_RESOURCE_TYPE_ADDRESS64))
+ return AE_OK;
+
+ status = acpi_resource_to_address64(res, &address);
+ if (ACPI_FAILURE(status) ||
+ (address.address.address_length <= 0) ||
+ (address.resource_type != ACPI_MEMORY_RANGE))
+ return AE_OK;
+
+ if ((mcfg_res->start >= address.address.minimum) &&
+ (mcfg_res->end < (address.address.minimum + address.address.address_length))) {
+ mcfg_res->flags = 1;
+ return AE_CTRL_TERMINATE;
+ }
+ return AE_OK;
+}
+
+static acpi_status find_mboard_resource(acpi_handle handle, u32 lvl,
+ void *context, void **rv)
+{
+ struct resource *mcfg_res = context;
+
+ acpi_walk_resources(handle, METHOD_NAME__CRS,
+ check_mcfg_resource, context);
+
+ if (mcfg_res->flags)
+ return AE_CTRL_TERMINATE;
+
+ return AE_OK;
+}
+
+static bool is_acpi_reserved(u64 start, u64 end, enum e820_type not_used)
+{
+ struct resource mcfg_res;
+
+ mcfg_res.start = start;
+ mcfg_res.end = end - 1;
+ mcfg_res.flags = 0;
+
+ acpi_get_devices("PNP0C01", find_mboard_resource, &mcfg_res, NULL);
+
+ if (!mcfg_res.flags)
+ acpi_get_devices("PNP0C02", find_mboard_resource, &mcfg_res,
+ NULL);
+
+ return mcfg_res.flags;
+}
+
+static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used)
+{
+#ifdef CONFIG_EFI
+ efi_memory_desc_t *md;
+ u64 size, mmio_start, mmio_end;
+
+ for_each_efi_memory_desc(md) {
+ if (md->type == EFI_MEMORY_MAPPED_IO) {
+ size = md->num_pages << EFI_PAGE_SHIFT;
+ mmio_start = md->phys_addr;
+ mmio_end = mmio_start + size;
+
+ /*
+ * N.B. Caller supplies (start, start + size),
+ * so to match, mmio_end is the first address
+ * *past* the EFI_MEMORY_MAPPED_IO area.
+ */
+ if (mmio_start <= start && end <= mmio_end)
+ return true;
+ }
+ }
+#endif
+
+ return false;
+}
+
+typedef bool (*check_reserved_t)(u64 start, u64 end, enum e820_type type);
+
+static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
+ struct pci_mmcfg_region *cfg,
+ struct device *dev, const char *method)
+{
+ u64 addr = cfg->res.start;
+ u64 size = resource_size(&cfg->res);
+ u64 old_size = size;
+ int num_buses;
+
+ while (!is_reserved(addr, addr + size, E820_TYPE_RESERVED)) {
+ size >>= 1;
+ if (size < (16UL<<20))
+ break;
+ }
+
+ if (size < (16UL<<20) && size != old_size)
+ return false;
+
+ if (dev)
+ dev_info(dev, "MMCONFIG at %pR reserved as %s\n",
+ &cfg->res, method);
+ else
+ pr_info(PREFIX "MMCONFIG at %pR reserved as %s\n",
+ &cfg->res, method);
+
+ if (old_size != size) {
+ /* update end_bus */
+ cfg->end_bus = cfg->start_bus + ((size>>20) - 1);
+ num_buses = cfg->end_bus - cfg->start_bus + 1;
+ cfg->res.end = cfg->res.start +
+ PCI_MMCFG_BUS_OFFSET(num_buses) - 1;
+ snprintf(cfg->name, PCI_MMCFG_RESOURCE_NAME_LEN,
+ "PCI MMCONFIG %04x [bus %02x-%02x]",
+ cfg->segment, cfg->start_bus, cfg->end_bus);
+
+ if (dev)
+ dev_info(dev,
+ "MMCONFIG "
+ "at %pR (base %#lx) (size reduced!)\n",
+ &cfg->res, (unsigned long) cfg->address);
+ else
+ pr_info(PREFIX
+ "MMCONFIG for %04x [bus%02x-%02x] "
+ "at %pR (base %#lx) (size reduced!)\n",
+ cfg->segment, cfg->start_bus, cfg->end_bus,
+ &cfg->res, (unsigned long) cfg->address);
+ }
+
+ return true;
+}
+
+static bool __ref
+pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early)
+{
+ struct resource *conflict;
+
+ if (!early && !acpi_disabled) {
+ if (is_mmconf_reserved(is_acpi_reserved, cfg, dev,
+ "ACPI motherboard resource"))
+ return true;
+
+ if (dev)
+ dev_info(dev, FW_INFO
+ "MMCONFIG at %pR not reserved in "
+ "ACPI motherboard resources\n",
+ &cfg->res);
+ else
+ pr_info(FW_INFO PREFIX
+ "MMCONFIG at %pR not reserved in "
+ "ACPI motherboard resources\n",
+ &cfg->res);
+
+ if (is_mmconf_reserved(is_efi_mmio, cfg, dev,
+ "EfiMemoryMappedIO")) {
+ conflict = insert_resource_conflict(&iomem_resource,
+ &cfg->res);
+ if (conflict)
+ pr_warn("MMCONFIG %pR conflicts with %s %pR\n",
+ &cfg->res, conflict->name, conflict);
+ else
+ pr_info("MMCONFIG %pR reserved to work around lack of ACPI motherboard _CRS\n",
+ &cfg->res);
+ return true;
+ }
+ }
+
+ /*
+ * e820__mapped_all() is marked as __init.
+ * All entries from ACPI MCFG table have been checked at boot time.
+ * For MCFG information constructed from hotpluggable host bridge's
+ * _CBA method, just assume it's reserved.
+ */
+ if (pci_mmcfg_running_state)
+ return true;
+
+ /* Don't try to do this check unless configuration
+ type 1 is available. how about type 2 ?*/
+ if (raw_pci_ops)
+ return is_mmconf_reserved(e820__mapped_all, cfg, dev,
+ "E820 entry");
+
+ return false;
+}
+
+static void __init pci_mmcfg_reject_broken(int early)
+{
+ struct pci_mmcfg_region *cfg;
+
+ list_for_each_entry(cfg, &pci_mmcfg_list, list) {
+ if (pci_mmcfg_check_reserved(NULL, cfg, early) == 0) {
+ pr_info(PREFIX "not using MMCONFIG\n");
+ free_all_mmcfg();
+ return;
+ }
+ }
+}
+
+static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg,
+ struct acpi_mcfg_allocation *cfg)
+{
+ if (cfg->address < 0xFFFFFFFF)
+ return 0;
+
+ if (!strncmp(mcfg->header.oem_id, "SGI", 3))
+ return 0;
+
+ if ((mcfg->header.revision >= 1) && (dmi_get_bios_year() >= 2010))
+ return 0;
+
+ pr_err(PREFIX "MCFG region for %04x [bus %02x-%02x] at %#llx "
+ "is above 4GB, ignored\n", cfg->pci_segment,
+ cfg->start_bus_number, cfg->end_bus_number, cfg->address);
+ return -EINVAL;
+}
+
+static int __init pci_parse_mcfg(struct acpi_table_header *header)
+{
+ struct acpi_table_mcfg *mcfg;
+ struct acpi_mcfg_allocation *cfg_table, *cfg;
+ unsigned long i;
+ int entries;
+
+ if (!header)
+ return -EINVAL;
+
+ mcfg = (struct acpi_table_mcfg *)header;
+
+ /* how many config structures do we have */
+ free_all_mmcfg();
+ entries = 0;
+ i = header->length - sizeof(struct acpi_table_mcfg);
+ while (i >= sizeof(struct acpi_mcfg_allocation)) {
+ entries++;
+ i -= sizeof(struct acpi_mcfg_allocation);
+ }
+ if (entries == 0) {
+ pr_err(PREFIX "MMCONFIG has no entries\n");
+ return -ENODEV;
+ }
+
+ cfg_table = (struct acpi_mcfg_allocation *) &mcfg[1];
+ for (i = 0; i < entries; i++) {
+ cfg = &cfg_table[i];
+ if (acpi_mcfg_check_entry(mcfg, cfg)) {
+ free_all_mmcfg();
+ return -ENODEV;
+ }
+
+ if (pci_mmconfig_add(cfg->pci_segment, cfg->start_bus_number,
+ cfg->end_bus_number, cfg->address) == NULL) {
+ pr_warn(PREFIX "no memory for MCFG entries\n");
+ free_all_mmcfg();
+ return -ENOMEM;
+ }
+ }
+
+ return 0;
+}
+
+#ifdef CONFIG_ACPI_APEI
+extern int (*arch_apei_filter_addr)(int (*func)(__u64 start, __u64 size,
+ void *data), void *data);
+
+static int pci_mmcfg_for_each_region(int (*func)(__u64 start, __u64 size,
+ void *data), void *data)
+{
+ struct pci_mmcfg_region *cfg;
+ int rc;
+
+ if (list_empty(&pci_mmcfg_list))
+ return 0;
+
+ list_for_each_entry(cfg, &pci_mmcfg_list, list) {
+ rc = func(cfg->res.start, resource_size(&cfg->res), data);
+ if (rc)
+ return rc;
+ }
+
+ return 0;
+}
+#define set_apei_filter() (arch_apei_filter_addr = pci_mmcfg_for_each_region)
+#else
+#define set_apei_filter()
+#endif
+
+static void __init __pci_mmcfg_init(int early)
+{
+ pci_mmcfg_reject_broken(early);
+ if (list_empty(&pci_mmcfg_list))
+ return;
+
+ if (pcibios_last_bus < 0) {
+ const struct pci_mmcfg_region *cfg;
+
+ list_for_each_entry(cfg, &pci_mmcfg_list, list) {
+ if (cfg->segment)
+ break;
+ pcibios_last_bus = cfg->end_bus;
+ }
+ }
+
+ if (pci_mmcfg_arch_init())
+ pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF;
+ else {
+ free_all_mmcfg();
+ pci_mmcfg_arch_init_failed = true;
+ }
+}
+
+static int __initdata known_bridge;
+
+void __init pci_mmcfg_early_init(void)
+{
+ if (pci_probe & PCI_PROBE_MMCONF) {
+ if (pci_mmcfg_check_hostbridge())
+ known_bridge = 1;
+ else
+ acpi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg);
+ __pci_mmcfg_init(1);
+
+ set_apei_filter();
+ }
+}
+
+void __init pci_mmcfg_late_init(void)
+{
+ /* MMCONFIG disabled */
+ if ((pci_probe & PCI_PROBE_MMCONF) == 0)
+ return;
+
+ if (known_bridge)
+ return;
+
+ /* MMCONFIG hasn't been enabled yet, try again */
+ if (pci_probe & PCI_PROBE_MASK & ~PCI_PROBE_MMCONF) {
+ acpi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg);
+ __pci_mmcfg_init(0);
+ }
+}
+
+static int __init pci_mmcfg_late_insert_resources(void)
+{
+ struct pci_mmcfg_region *cfg;
+
+ pci_mmcfg_running_state = true;
+
+ /* If we are not using MMCONFIG, don't insert the resources. */
+ if ((pci_probe & PCI_PROBE_MMCONF) == 0)
+ return 1;
+
+ /*
+ * Attempt to insert the mmcfg resources but not with the busy flag
+ * marked so it won't cause request errors when __request_region is
+ * called.
+ */
+ list_for_each_entry(cfg, &pci_mmcfg_list, list)
+ if (!cfg->res.parent)
+ insert_resource(&iomem_resource, &cfg->res);
+
+ return 0;
+}
+
+/*
+ * Perform MMCONFIG resource insertion after PCI initialization to allow for
+ * misprogrammed MCFG tables that state larger sizes but actually conflict
+ * with other system resources.
+ */
+late_initcall(pci_mmcfg_late_insert_resources);
+
+/* Add MMCFG information for host bridges */
+int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
+ phys_addr_t addr)
+{
+ int rc;
+ struct resource *tmp = NULL;
+ struct pci_mmcfg_region *cfg;
+
+ if (!(pci_probe & PCI_PROBE_MMCONF) || pci_mmcfg_arch_init_failed)
+ return -ENODEV;
+
+ if (start > end)
+ return -EINVAL;
+
+ mutex_lock(&pci_mmcfg_lock);
+ cfg = pci_mmconfig_lookup(seg, start);
+ if (cfg) {
+ if (cfg->end_bus < end)
+ dev_info(dev, FW_INFO
+ "MMCONFIG for "
+ "domain %04x [bus %02x-%02x] "
+ "only partially covers this bridge\n",
+ cfg->segment, cfg->start_bus, cfg->end_bus);
+ mutex_unlock(&pci_mmcfg_lock);
+ return -EEXIST;
+ }
+
+ if (!addr) {
+ mutex_unlock(&pci_mmcfg_lock);
+ return -EINVAL;
+ }
+
+ rc = -EBUSY;
+ cfg = pci_mmconfig_alloc(seg, start, end, addr);
+ if (cfg == NULL) {
+ dev_warn(dev, "fail to add MMCONFIG (out of memory)\n");
+ rc = -ENOMEM;
+ } else if (!pci_mmcfg_check_reserved(dev, cfg, 0)) {
+ dev_warn(dev, FW_BUG "MMCONFIG %pR isn't reserved\n",
+ &cfg->res);
+ } else {
+ /* Insert resource if it's not in boot stage */
+ if (pci_mmcfg_running_state)
+ tmp = insert_resource_conflict(&iomem_resource,
+ &cfg->res);
+
+ if (tmp) {
+ dev_warn(dev,
+ "MMCONFIG %pR conflicts with "
+ "%s %pR\n",
+ &cfg->res, tmp->name, tmp);
+ } else if (pci_mmcfg_arch_map(cfg)) {
+ dev_warn(dev, "fail to map MMCONFIG %pR.\n",
+ &cfg->res);
+ } else {
+ list_add_sorted(cfg);
+ dev_info(dev, "MMCONFIG at %pR (base %#lx)\n",
+ &cfg->res, (unsigned long)addr);
+ cfg = NULL;
+ rc = 0;
+ }
+ }
+
+ if (cfg) {
+ if (cfg->res.parent)
+ release_resource(&cfg->res);
+ kfree(cfg);
+ }
+
+ mutex_unlock(&pci_mmcfg_lock);
+
+ return rc;
+}
+
+/* Delete MMCFG information for host bridges */
+int pci_mmconfig_delete(u16 seg, u8 start, u8 end)
+{
+ struct pci_mmcfg_region *cfg;
+
+ mutex_lock(&pci_mmcfg_lock);
+ list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list)
+ if (cfg->segment == seg && cfg->start_bus == start &&
+ cfg->end_bus == end) {
+ list_del_rcu(&cfg->list);
+ synchronize_rcu();
+ pci_mmcfg_arch_unmap(cfg);
+ if (cfg->res.parent)
+ release_resource(&cfg->res);
+ mutex_unlock(&pci_mmcfg_lock);
+ kfree(cfg);
+ return 0;
+ }
+ mutex_unlock(&pci_mmcfg_lock);
+
+ return -ENOENT;
+}
diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c
new file mode 100644
index 0000000000..bfa7898753
--- /dev/null
+++ b/arch/x86/pci/mmconfig_32.c
@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004 Matthew Wilcox <matthew@wil.cx>
+ * Copyright (C) 2004 Intel Corp.
+ */
+
+/*
+ * mmconfig.c - Low-level direct PCI config space access via MMCONFIG
+ */
+
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/rcupdate.h>
+#include <asm/e820/api.h>
+#include <asm/pci_x86.h>
+
+/* Assume systems with more busses have correct MCFG */
+#define mmcfg_virt_addr ((void __iomem *) fix_to_virt(FIX_PCIE_MCFG))
+
+/* The base address of the last MMCONFIG device accessed */
+static u32 mmcfg_last_accessed_device;
+static int mmcfg_last_accessed_cpu;
+
+/*
+ * Functions for accessing PCI configuration space with MMCONFIG accesses
+ */
+static u32 get_base_addr(unsigned int seg, int bus, unsigned devfn)
+{
+ struct pci_mmcfg_region *cfg = pci_mmconfig_lookup(seg, bus);
+
+ if (cfg)
+ return cfg->address;
+ return 0;
+}
+
+/*
+ * This is always called under pci_config_lock
+ */
+static void pci_exp_set_dev_base(unsigned int base, int bus, int devfn)
+{
+ u32 dev_base = base | PCI_MMCFG_BUS_OFFSET(bus) | (devfn << 12);
+ int cpu = smp_processor_id();
+ if (dev_base != mmcfg_last_accessed_device ||
+ cpu != mmcfg_last_accessed_cpu) {
+ mmcfg_last_accessed_device = dev_base;
+ mmcfg_last_accessed_cpu = cpu;
+ set_fixmap_nocache(FIX_PCIE_MCFG, dev_base);
+ }
+}
+
+static int pci_mmcfg_read(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 *value)
+{
+ unsigned long flags;
+ u32 base;
+
+ if ((bus > 255) || (devfn > 255) || (reg > 4095)) {
+err: *value = -1;
+ return -EINVAL;
+ }
+
+ rcu_read_lock();
+ base = get_base_addr(seg, bus, devfn);
+ if (!base) {
+ rcu_read_unlock();
+ goto err;
+ }
+
+ raw_spin_lock_irqsave(&pci_config_lock, flags);
+
+ pci_exp_set_dev_base(base, bus, devfn);
+
+ switch (len) {
+ case 1:
+ *value = mmio_config_readb(mmcfg_virt_addr + reg);
+ break;
+ case 2:
+ *value = mmio_config_readw(mmcfg_virt_addr + reg);
+ break;
+ case 4:
+ *value = mmio_config_readl(mmcfg_virt_addr + reg);
+ break;
+ }
+ raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+ rcu_read_unlock();
+
+ return 0;
+}
+
+static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 value)
+{
+ unsigned long flags;
+ u32 base;
+
+ if ((bus > 255) || (devfn > 255) || (reg > 4095))
+ return -EINVAL;
+
+ rcu_read_lock();
+ base = get_base_addr(seg, bus, devfn);
+ if (!base) {
+ rcu_read_unlock();
+ return -EINVAL;
+ }
+
+ raw_spin_lock_irqsave(&pci_config_lock, flags);
+
+ pci_exp_set_dev_base(base, bus, devfn);
+
+ switch (len) {
+ case 1:
+ mmio_config_writeb(mmcfg_virt_addr + reg, value);
+ break;
+ case 2:
+ mmio_config_writew(mmcfg_virt_addr + reg, value);
+ break;
+ case 4:
+ mmio_config_writel(mmcfg_virt_addr + reg, value);
+ break;
+ }
+ raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+ rcu_read_unlock();
+
+ return 0;
+}
+
+const struct pci_raw_ops pci_mmcfg = {
+ .read = pci_mmcfg_read,
+ .write = pci_mmcfg_write,
+};
+
+int __init pci_mmcfg_arch_init(void)
+{
+ printk(KERN_INFO "PCI: Using MMCONFIG for extended config space\n");
+ raw_pci_ext_ops = &pci_mmcfg;
+ return 1;
+}
+
+void __init pci_mmcfg_arch_free(void)
+{
+}
+
+int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg)
+{
+ return 0;
+}
+
+void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg)
+{
+ unsigned long flags;
+
+ /* Invalidate the cached mmcfg map entry. */
+ raw_spin_lock_irqsave(&pci_config_lock, flags);
+ mmcfg_last_accessed_device = 0;
+ raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+}
diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c
new file mode 100644
index 0000000000..0c7b6e66c6
--- /dev/null
+++ b/arch/x86/pci/mmconfig_64.c
@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * mmconfig.c - Low-level direct PCI config space access via MMCONFIG
+ *
+ * This is an 64bit optimized version that always keeps the full mmconfig
+ * space mapped. This allows lockless config space operation.
+ */
+
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/bitmap.h>
+#include <linux/rcupdate.h>
+#include <asm/e820/api.h>
+#include <asm/pci_x86.h>
+
+#define PREFIX "PCI: "
+
+static char __iomem *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn)
+{
+ struct pci_mmcfg_region *cfg = pci_mmconfig_lookup(seg, bus);
+
+ if (cfg && cfg->virt)
+ return cfg->virt + (PCI_MMCFG_BUS_OFFSET(bus) | (devfn << 12));
+ return NULL;
+}
+
+static int pci_mmcfg_read(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 *value)
+{
+ char __iomem *addr;
+
+ /* Why do we have this when nobody checks it. How about a BUG()!? -AK */
+ if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095))) {
+err: *value = -1;
+ return -EINVAL;
+ }
+
+ rcu_read_lock();
+ addr = pci_dev_base(seg, bus, devfn);
+ if (!addr) {
+ rcu_read_unlock();
+ goto err;
+ }
+
+ switch (len) {
+ case 1:
+ *value = mmio_config_readb(addr + reg);
+ break;
+ case 2:
+ *value = mmio_config_readw(addr + reg);
+ break;
+ case 4:
+ *value = mmio_config_readl(addr + reg);
+ break;
+ }
+ rcu_read_unlock();
+
+ return 0;
+}
+
+static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 value)
+{
+ char __iomem *addr;
+
+ /* Why do we have this when nobody checks it. How about a BUG()!? -AK */
+ if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095)))
+ return -EINVAL;
+
+ rcu_read_lock();
+ addr = pci_dev_base(seg, bus, devfn);
+ if (!addr) {
+ rcu_read_unlock();
+ return -EINVAL;
+ }
+
+ switch (len) {
+ case 1:
+ mmio_config_writeb(addr + reg, value);
+ break;
+ case 2:
+ mmio_config_writew(addr + reg, value);
+ break;
+ case 4:
+ mmio_config_writel(addr + reg, value);
+ break;
+ }
+ rcu_read_unlock();
+
+ return 0;
+}
+
+const struct pci_raw_ops pci_mmcfg = {
+ .read = pci_mmcfg_read,
+ .write = pci_mmcfg_write,
+};
+
+static void __iomem *mcfg_ioremap(struct pci_mmcfg_region *cfg)
+{
+ void __iomem *addr;
+ u64 start, size;
+ int num_buses;
+
+ start = cfg->address + PCI_MMCFG_BUS_OFFSET(cfg->start_bus);
+ num_buses = cfg->end_bus - cfg->start_bus + 1;
+ size = PCI_MMCFG_BUS_OFFSET(num_buses);
+ addr = ioremap(start, size);
+ if (addr)
+ addr -= PCI_MMCFG_BUS_OFFSET(cfg->start_bus);
+ return addr;
+}
+
+int __init pci_mmcfg_arch_init(void)
+{
+ struct pci_mmcfg_region *cfg;
+
+ list_for_each_entry(cfg, &pci_mmcfg_list, list)
+ if (pci_mmcfg_arch_map(cfg)) {
+ pci_mmcfg_arch_free();
+ return 0;
+ }
+
+ raw_pci_ext_ops = &pci_mmcfg;
+
+ return 1;
+}
+
+void __init pci_mmcfg_arch_free(void)
+{
+ struct pci_mmcfg_region *cfg;
+
+ list_for_each_entry(cfg, &pci_mmcfg_list, list)
+ pci_mmcfg_arch_unmap(cfg);
+}
+
+int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg)
+{
+ cfg->virt = mcfg_ioremap(cfg);
+ if (!cfg->virt) {
+ pr_err(PREFIX "can't map MMCONFIG at %pR\n", &cfg->res);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg)
+{
+ if (cfg && cfg->virt) {
+ iounmap(cfg->virt + PCI_MMCFG_BUS_OFFSET(cfg->start_bus));
+ cfg->virt = NULL;
+ }
+}
diff --git a/arch/x86/pci/numachip.c b/arch/x86/pci/numachip.c
new file mode 100644
index 0000000000..4f0147d4e2
--- /dev/null
+++ b/arch/x86/pci/numachip.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Numascale NumaConnect-specific PCI code
+ *
+ * Copyright (C) 2012 Numascale AS. All rights reserved.
+ *
+ * Send feedback to <support@numascale.com>
+ *
+ * PCI accessor functions derived from mmconfig_64.c
+ *
+ */
+
+#include <linux/pci.h>
+#include <asm/pci_x86.h>
+#include <asm/numachip/numachip.h>
+
+static u8 limit __read_mostly;
+
+static inline char __iomem *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn)
+{
+ struct pci_mmcfg_region *cfg = pci_mmconfig_lookup(seg, bus);
+
+ if (cfg && cfg->virt)
+ return cfg->virt + (PCI_MMCFG_BUS_OFFSET(bus) | (devfn << 12));
+ return NULL;
+}
+
+static int pci_mmcfg_read_numachip(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 *value)
+{
+ char __iomem *addr;
+
+ /* Why do we have this when nobody checks it. How about a BUG()!? -AK */
+ if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095))) {
+err: *value = -1;
+ return -EINVAL;
+ }
+
+ /* Ensure AMD Northbridges don't decode reads to other devices */
+ if (unlikely(bus == 0 && devfn >= limit)) {
+ *value = -1;
+ return 0;
+ }
+
+ rcu_read_lock();
+ addr = pci_dev_base(seg, bus, devfn);
+ if (!addr) {
+ rcu_read_unlock();
+ goto err;
+ }
+
+ switch (len) {
+ case 1:
+ *value = mmio_config_readb(addr + reg);
+ break;
+ case 2:
+ *value = mmio_config_readw(addr + reg);
+ break;
+ case 4:
+ *value = mmio_config_readl(addr + reg);
+ break;
+ }
+ rcu_read_unlock();
+
+ return 0;
+}
+
+static int pci_mmcfg_write_numachip(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 value)
+{
+ char __iomem *addr;
+
+ /* Why do we have this when nobody checks it. How about a BUG()!? -AK */
+ if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095)))
+ return -EINVAL;
+
+ /* Ensure AMD Northbridges don't decode writes to other devices */
+ if (unlikely(bus == 0 && devfn >= limit))
+ return 0;
+
+ rcu_read_lock();
+ addr = pci_dev_base(seg, bus, devfn);
+ if (!addr) {
+ rcu_read_unlock();
+ return -EINVAL;
+ }
+
+ switch (len) {
+ case 1:
+ mmio_config_writeb(addr + reg, value);
+ break;
+ case 2:
+ mmio_config_writew(addr + reg, value);
+ break;
+ case 4:
+ mmio_config_writel(addr + reg, value);
+ break;
+ }
+ rcu_read_unlock();
+
+ return 0;
+}
+
+static const struct pci_raw_ops pci_mmcfg_numachip = {
+ .read = pci_mmcfg_read_numachip,
+ .write = pci_mmcfg_write_numachip,
+};
+
+int __init pci_numachip_init(void)
+{
+ int ret = 0;
+ u32 val;
+
+ /* For remote I/O, restrict bus 0 access to the actual number of AMD
+ Northbridges, which starts at device number 0x18 */
+ ret = raw_pci_read(0, 0, PCI_DEVFN(0x18, 0), 0x60, sizeof(val), &val);
+ if (ret)
+ goto out;
+
+ /* HyperTransport fabric size in bits 6:4 */
+ limit = PCI_DEVFN(0x18 + ((val >> 4) & 7) + 1, 0);
+
+ /* Use NumaChip PCI accessors for non-extended and extended access */
+ raw_pci_ops = raw_pci_ext_ops = &pci_mmcfg_numachip;
+out:
+ return ret;
+}
diff --git a/arch/x86/pci/olpc.c b/arch/x86/pci/olpc.c
new file mode 100644
index 0000000000..f3aab76e35
--- /dev/null
+++ b/arch/x86/pci/olpc.c
@@ -0,0 +1,311 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Low-level PCI config space access for OLPC systems who lack the VSA
+ * PCI virtualization software.
+ *
+ * Copyright © 2006 Advanced Micro Devices, Inc.
+ *
+ * The AMD Geode chipset (ie: GX2 processor, cs5536 I/O companion device)
+ * has some I/O functions (display, southbridge, sound, USB HCIs, etc)
+ * that more or less behave like PCI devices, but the hardware doesn't
+ * directly implement the PCI configuration space headers. AMD provides
+ * "VSA" (Virtual System Architecture) software that emulates PCI config
+ * space for these devices, by trapping I/O accesses to PCI config register
+ * (CF8/CFC) and running some code in System Management Mode interrupt state.
+ * On the OLPC platform, we don't want to use that VSA code because
+ * (a) it slows down suspend/resume, and (b) recompiling it requires special
+ * compilers that are hard to get. So instead of letting the complex VSA
+ * code simulate the PCI config registers for the on-chip devices, we
+ * just simulate them the easy way, by inserting the code into the
+ * pci_write_config and pci_read_config path. Most of the config registers
+ * are read-only anyway, so the bulk of the simulation is just table lookup.
+ */
+
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <asm/olpc.h>
+#include <asm/geode.h>
+#include <asm/pci_x86.h>
+
+/*
+ * In the tables below, the first two line (8 longwords) are the
+ * size masks that are used when the higher level PCI code determines
+ * the size of the region by writing ~0 to a base address register
+ * and reading back the result.
+ *
+ * The following lines are the values that are read during normal
+ * PCI config access cycles, i.e. not after just having written
+ * ~0 to a base address register.
+ */
+
+static const uint32_t lxnb_hdr[] = { /* dev 1 function 0 - devfn = 8 */
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+
+ 0x281022, 0x2200005, 0x6000021, 0x80f808, /* AMD Vendor ID */
+ 0x0, 0x0, 0x0, 0x0, /* No virtual registers, hence no BAR */
+ 0x0, 0x0, 0x0, 0x28100b,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+};
+
+static const uint32_t gxnb_hdr[] = { /* dev 1 function 0 - devfn = 8 */
+ 0xfffffffd, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+
+ 0x28100b, 0x2200005, 0x6000021, 0x80f808, /* NSC Vendor ID */
+ 0xac1d, 0x0, 0x0, 0x0, /* I/O BAR - base of virtual registers */
+ 0x0, 0x0, 0x0, 0x28100b,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+};
+
+static const uint32_t lxfb_hdr[] = { /* dev 1 function 1 - devfn = 9 */
+ 0xff000008, 0xffffc000, 0xffffc000, 0xffffc000,
+ 0xffffc000, 0x0, 0x0, 0x0,
+
+ 0x20811022, 0x2200003, 0x3000000, 0x0, /* AMD Vendor ID */
+ 0xfd000000, 0xfe000000, 0xfe004000, 0xfe008000, /* FB, GP, VG, DF */
+ 0xfe00c000, 0x0, 0x0, 0x30100b, /* VIP */
+ 0x0, 0x0, 0x0, 0x10e, /* INTA, IRQ14 for graphics accel */
+ 0x0, 0x0, 0x0, 0x0,
+ 0x3d0, 0x3c0, 0xa0000, 0x0, /* VG IO, VG IO, EGA FB, MONO FB */
+ 0x0, 0x0, 0x0, 0x0,
+};
+
+static const uint32_t gxfb_hdr[] = { /* dev 1 function 1 - devfn = 9 */
+ 0xff800008, 0xffffc000, 0xffffc000, 0xffffc000,
+ 0x0, 0x0, 0x0, 0x0,
+
+ 0x30100b, 0x2200003, 0x3000000, 0x0, /* NSC Vendor ID */
+ 0xfd000000, 0xfe000000, 0xfe004000, 0xfe008000, /* FB, GP, VG, DF */
+ 0x0, 0x0, 0x0, 0x30100b,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x3d0, 0x3c0, 0xa0000, 0x0, /* VG IO, VG IO, EGA FB, MONO FB */
+ 0x0, 0x0, 0x0, 0x0,
+};
+
+static const uint32_t aes_hdr[] = { /* dev 1 function 2 - devfn = 0xa */
+ 0xffffc000, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+
+ 0x20821022, 0x2a00006, 0x10100000, 0x8, /* NSC Vendor ID */
+ 0xfe010000, 0x0, 0x0, 0x0, /* AES registers */
+ 0x0, 0x0, 0x0, 0x20821022,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+};
+
+
+static const uint32_t isa_hdr[] = { /* dev f function 0 - devfn = 78 */
+ 0xfffffff9, 0xffffff01, 0xffffffc1, 0xffffffe1,
+ 0xffffff81, 0xffffffc1, 0x0, 0x0,
+
+ 0x20901022, 0x2a00049, 0x6010003, 0x802000,
+ 0x18b1, 0x1001, 0x1801, 0x1881, /* SMB-8 GPIO-256 MFGPT-64 IRQ-32 */
+ 0x1401, 0x1841, 0x0, 0x20901022, /* PMS-128 ACPI-64 */
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0xaa5b, /* IRQ steering */
+ 0x0, 0x0, 0x0, 0x0,
+};
+
+static const uint32_t ac97_hdr[] = { /* dev f function 3 - devfn = 7b */
+ 0xffffff81, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+
+ 0x20931022, 0x2a00041, 0x4010001, 0x0,
+ 0x1481, 0x0, 0x0, 0x0, /* I/O BAR-128 */
+ 0x0, 0x0, 0x0, 0x20931022,
+ 0x0, 0x0, 0x0, 0x205, /* IntB, IRQ5 */
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+};
+
+static const uint32_t ohci_hdr[] = { /* dev f function 4 - devfn = 7c */
+ 0xfffff000, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+
+ 0x20941022, 0x2300006, 0xc031002, 0x0,
+ 0xfe01a000, 0x0, 0x0, 0x0, /* MEMBAR-1000 */
+ 0x0, 0x0, 0x0, 0x20941022,
+ 0x0, 0x40, 0x0, 0x40a, /* CapPtr INT-D, IRQA */
+ 0xc8020001, 0x0, 0x0, 0x0, /* Capabilities - 40 is R/O,
+ 44 is mask 8103 (power control) */
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+};
+
+static const uint32_t ehci_hdr[] = { /* dev f function 4 - devfn = 7d */
+ 0xfffff000, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+
+ 0x20951022, 0x2300006, 0xc032002, 0x0,
+ 0xfe01b000, 0x0, 0x0, 0x0, /* MEMBAR-1000 */
+ 0x0, 0x0, 0x0, 0x20951022,
+ 0x0, 0x40, 0x0, 0x40a, /* CapPtr INT-D, IRQA */
+ 0xc8020001, 0x0, 0x0, 0x0, /* Capabilities - 40 is R/O, 44 is
+ mask 8103 (power control) */
+#if 0
+ 0x1, 0x40080000, 0x0, 0x0, /* EECP - see EHCI spec section 2.1.7 */
+#endif
+ 0x01000001, 0x0, 0x0, 0x0, /* EECP - see EHCI spec section 2.1.7 */
+ 0x2020, 0x0, 0x0, 0x0, /* (EHCI page 8) 60 SBRN (R/O),
+ 61 FLADJ (R/W), PORTWAKECAP */
+};
+
+static uint32_t ff_loc = ~0;
+static uint32_t zero_loc;
+static int bar_probing; /* Set after a write of ~0 to a BAR */
+static int is_lx;
+
+#define NB_SLOT 0x1 /* Northbridge - GX chip - Device 1 */
+#define SB_SLOT 0xf /* Southbridge - CS5536 chip - Device F */
+
+static int is_simulated(unsigned int bus, unsigned int devfn)
+{
+ return (!bus && ((PCI_SLOT(devfn) == NB_SLOT) ||
+ (PCI_SLOT(devfn) == SB_SLOT)));
+}
+
+static uint32_t *hdr_addr(const uint32_t *hdr, int reg)
+{
+ uint32_t addr;
+
+ /*
+ * This is a little bit tricky. The header maps consist of
+ * 0x20 bytes of size masks, followed by 0x70 bytes of header data.
+ * In the normal case, when not probing a BAR's size, we want
+ * to access the header data, so we add 0x20 to the reg offset,
+ * thus skipping the size mask area.
+ * In the BAR probing case, we want to access the size mask for
+ * the BAR, so we subtract 0x10 (the config header offset for
+ * BAR0), and don't skip the size mask area.
+ */
+
+ addr = (uint32_t)hdr + reg + (bar_probing ? -0x10 : 0x20);
+
+ bar_probing = 0;
+ return (uint32_t *)addr;
+}
+
+static int pci_olpc_read(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, uint32_t *value)
+{
+ uint32_t *addr;
+
+ WARN_ON(seg);
+
+ /* Use the hardware mechanism for non-simulated devices */
+ if (!is_simulated(bus, devfn))
+ return pci_direct_conf1.read(seg, bus, devfn, reg, len, value);
+
+ /*
+ * No device has config registers past 0x70, so we save table space
+ * by not storing entries for the nonexistent registers
+ */
+ if (reg >= 0x70)
+ addr = &zero_loc;
+ else {
+ switch (devfn) {
+ case 0x8:
+ addr = hdr_addr(is_lx ? lxnb_hdr : gxnb_hdr, reg);
+ break;
+ case 0x9:
+ addr = hdr_addr(is_lx ? lxfb_hdr : gxfb_hdr, reg);
+ break;
+ case 0xa:
+ addr = is_lx ? hdr_addr(aes_hdr, reg) : &ff_loc;
+ break;
+ case 0x78:
+ addr = hdr_addr(isa_hdr, reg);
+ break;
+ case 0x7b:
+ addr = hdr_addr(ac97_hdr, reg);
+ break;
+ case 0x7c:
+ addr = hdr_addr(ohci_hdr, reg);
+ break;
+ case 0x7d:
+ addr = hdr_addr(ehci_hdr, reg);
+ break;
+ default:
+ addr = &ff_loc;
+ break;
+ }
+ }
+ switch (len) {
+ case 1:
+ *value = *(uint8_t *)addr;
+ break;
+ case 2:
+ *value = *(uint16_t *)addr;
+ break;
+ case 4:
+ *value = *addr;
+ break;
+ default:
+ BUG();
+ }
+
+ return 0;
+}
+
+static int pci_olpc_write(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, uint32_t value)
+{
+ WARN_ON(seg);
+
+ /* Use the hardware mechanism for non-simulated devices */
+ if (!is_simulated(bus, devfn))
+ return pci_direct_conf1.write(seg, bus, devfn, reg, len, value);
+
+ /* XXX we may want to extend this to simulate EHCI power management */
+
+ /*
+ * Mostly we just discard writes, but if the write is a size probe
+ * (i.e. writing ~0 to a BAR), we remember it and arrange to return
+ * the appropriate size mask on the next read. This is cheating
+ * to some extent, because it depends on the fact that the next
+ * access after such a write will always be a read to the same BAR.
+ */
+
+ if ((reg >= 0x10) && (reg < 0x2c)) {
+ /* write is to a BAR */
+ if (value == ~0)
+ bar_probing = 1;
+ } else {
+ /*
+ * No warning on writes to ROM BAR, CMD, LATENCY_TIMER,
+ * CACHE_LINE_SIZE, or PM registers.
+ */
+ if ((reg != PCI_ROM_ADDRESS) && (reg != PCI_COMMAND_MASTER) &&
+ (reg != PCI_LATENCY_TIMER) &&
+ (reg != PCI_CACHE_LINE_SIZE) && (reg != 0x44))
+ printk(KERN_WARNING "OLPC PCI: Config write to devfn"
+ " %x reg %x value %x\n", devfn, reg, value);
+ }
+
+ return 0;
+}
+
+static const struct pci_raw_ops pci_olpc_conf = {
+ .read = pci_olpc_read,
+ .write = pci_olpc_write,
+};
+
+int __init pci_olpc_init(void)
+{
+ printk(KERN_INFO "PCI: Using configuration type OLPC XO-1\n");
+ raw_pci_ops = &pci_olpc_conf;
+ is_lx = is_geode_lx();
+ return 0;
+}
diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c
new file mode 100644
index 0000000000..4f15280732
--- /dev/null
+++ b/arch/x86/pci/pcbios.c
@@ -0,0 +1,429 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * BIOS32 and PCI BIOS handling.
+ */
+
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+
+#include <asm/pci_x86.h>
+#include <asm/e820/types.h>
+#include <asm/pci-functions.h>
+#include <asm/set_memory.h>
+
+/* BIOS32 signature: "_32_" */
+#define BIOS32_SIGNATURE (('_' << 0) + ('3' << 8) + ('2' << 16) + ('_' << 24))
+
+/* PCI signature: "PCI " */
+#define PCI_SIGNATURE (('P' << 0) + ('C' << 8) + ('I' << 16) + (' ' << 24))
+
+/* PCI service signature: "$PCI" */
+#define PCI_SERVICE (('$' << 0) + ('P' << 8) + ('C' << 16) + ('I' << 24))
+
+/* PCI BIOS hardware mechanism flags */
+#define PCIBIOS_HW_TYPE1 0x01
+#define PCIBIOS_HW_TYPE2 0x02
+#define PCIBIOS_HW_TYPE1_SPEC 0x10
+#define PCIBIOS_HW_TYPE2_SPEC 0x20
+
+int pcibios_enabled;
+
+/* According to the BIOS specification at:
+ * http://members.datafast.net.au/dft0802/specs/bios21.pdf, we could
+ * restrict the x zone to some pages and make it ro. But this may be
+ * broken on some bios, complex to handle with static_protections.
+ * We could make the 0xe0000-0x100000 range rox, but this can break
+ * some ISA mapping.
+ *
+ * So we let's an rw and x hole when pcibios is used. This shouldn't
+ * happen for modern system with mmconfig, and if you don't want it
+ * you could disable pcibios...
+ */
+static inline void set_bios_x(void)
+{
+ pcibios_enabled = 1;
+ set_memory_x(PAGE_OFFSET + BIOS_BEGIN, (BIOS_END - BIOS_BEGIN) >> PAGE_SHIFT);
+ if (__supported_pte_mask & _PAGE_NX)
+ printk(KERN_INFO "PCI: PCI BIOS area is rw and x. Use pci=nobios if you want it NX.\n");
+}
+
+/*
+ * This is the standard structure used to identify the entry point
+ * to the BIOS32 Service Directory, as documented in
+ * Standard BIOS 32-bit Service Directory Proposal
+ * Revision 0.4 May 24, 1993
+ * Phoenix Technologies Ltd.
+ * Norwood, MA
+ * and the PCI BIOS specification.
+ */
+
+union bios32 {
+ struct {
+ unsigned long signature; /* _32_ */
+ unsigned long entry; /* 32 bit physical address */
+ unsigned char revision; /* Revision level, 0 */
+ unsigned char length; /* Length in paragraphs should be 01 */
+ unsigned char checksum; /* All bytes must add up to zero */
+ unsigned char reserved[5]; /* Must be zero */
+ } fields;
+ char chars[16];
+};
+
+/*
+ * Physical address of the service directory. I don't know if we're
+ * allowed to have more than one of these or not, so just in case
+ * we'll make pcibios_present() take a memory start parameter and store
+ * the array there.
+ */
+
+static struct {
+ unsigned long address;
+ unsigned short segment;
+} bios32_indirect __initdata = { 0, __KERNEL_CS };
+
+/*
+ * Returns the entry point for the given service, NULL on error
+ */
+
+static unsigned long __init bios32_service(unsigned long service)
+{
+ unsigned char return_code; /* %al */
+ unsigned long address; /* %ebx */
+ unsigned long length; /* %ecx */
+ unsigned long entry; /* %edx */
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __asm__("lcall *(%%edi); cld"
+ : "=a" (return_code),
+ "=b" (address),
+ "=c" (length),
+ "=d" (entry)
+ : "0" (service),
+ "1" (0),
+ "D" (&bios32_indirect));
+ local_irq_restore(flags);
+
+ switch (return_code) {
+ case 0:
+ return address + entry;
+ case 0x80: /* Not present */
+ printk(KERN_WARNING "bios32_service(0x%lx): not present\n", service);
+ return 0;
+ default: /* Shouldn't happen */
+ printk(KERN_WARNING "bios32_service(0x%lx): returned 0x%x -- BIOS bug!\n",
+ service, return_code);
+ return 0;
+ }
+}
+
+static struct {
+ unsigned long address;
+ unsigned short segment;
+} pci_indirect __ro_after_init = {
+ .address = 0,
+ .segment = __KERNEL_CS,
+};
+
+static int pci_bios_present __ro_after_init;
+
+static int __init check_pcibios(void)
+{
+ u32 signature, eax, ebx, ecx;
+ u8 status, major_ver, minor_ver, hw_mech;
+ unsigned long flags, pcibios_entry;
+
+ if ((pcibios_entry = bios32_service(PCI_SERVICE))) {
+ pci_indirect.address = pcibios_entry + PAGE_OFFSET;
+
+ local_irq_save(flags);
+ __asm__(
+ "lcall *(%%edi); cld\n\t"
+ "jc 1f\n\t"
+ "xor %%ah, %%ah\n"
+ "1:"
+ : "=d" (signature),
+ "=a" (eax),
+ "=b" (ebx),
+ "=c" (ecx)
+ : "1" (PCIBIOS_PCI_BIOS_PRESENT),
+ "D" (&pci_indirect)
+ : "memory");
+ local_irq_restore(flags);
+
+ status = (eax >> 8) & 0xff;
+ hw_mech = eax & 0xff;
+ major_ver = (ebx >> 8) & 0xff;
+ minor_ver = ebx & 0xff;
+ if (pcibios_last_bus < 0)
+ pcibios_last_bus = ecx & 0xff;
+ DBG("PCI: BIOS probe returned s=%02x hw=%02x ver=%02x.%02x l=%02x\n",
+ status, hw_mech, major_ver, minor_ver, pcibios_last_bus);
+ if (status || signature != PCI_SIGNATURE) {
+ printk (KERN_ERR "PCI: BIOS BUG #%x[%08x] found\n",
+ status, signature);
+ return 0;
+ }
+ printk(KERN_INFO "PCI: PCI BIOS revision %x.%02x entry at 0x%lx, last bus=%d\n",
+ major_ver, minor_ver, pcibios_entry, pcibios_last_bus);
+#ifdef CONFIG_PCI_DIRECT
+ if (!(hw_mech & PCIBIOS_HW_TYPE1))
+ pci_probe &= ~PCI_PROBE_CONF1;
+ if (!(hw_mech & PCIBIOS_HW_TYPE2))
+ pci_probe &= ~PCI_PROBE_CONF2;
+#endif
+ return 1;
+ }
+ return 0;
+}
+
+static int pci_bios_read(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 *value)
+{
+ unsigned long result = 0;
+ unsigned long flags;
+ unsigned long bx = (bus << 8) | devfn;
+ u16 number = 0, mask = 0;
+
+ WARN_ON(seg);
+ if (!value || (bus > 255) || (devfn > 255) || (reg > 255))
+ return -EINVAL;
+
+ raw_spin_lock_irqsave(&pci_config_lock, flags);
+
+ switch (len) {
+ case 1:
+ number = PCIBIOS_READ_CONFIG_BYTE;
+ mask = 0xff;
+ break;
+ case 2:
+ number = PCIBIOS_READ_CONFIG_WORD;
+ mask = 0xffff;
+ break;
+ case 4:
+ number = PCIBIOS_READ_CONFIG_DWORD;
+ break;
+ }
+
+ __asm__("lcall *(%%esi); cld\n\t"
+ "jc 1f\n\t"
+ "xor %%ah, %%ah\n"
+ "1:"
+ : "=c" (*value),
+ "=a" (result)
+ : "1" (number),
+ "b" (bx),
+ "D" ((long)reg),
+ "S" (&pci_indirect));
+ /*
+ * Zero-extend the result beyond 8 or 16 bits, do not trust the
+ * BIOS having done it:
+ */
+ if (mask)
+ *value &= mask;
+
+ raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+
+ return (int)((result & 0xff00) >> 8);
+}
+
+static int pci_bios_write(unsigned int seg, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 value)
+{
+ unsigned long result = 0;
+ unsigned long flags;
+ unsigned long bx = (bus << 8) | devfn;
+ u16 number = 0;
+
+ WARN_ON(seg);
+ if ((bus > 255) || (devfn > 255) || (reg > 255))
+ return -EINVAL;
+
+ raw_spin_lock_irqsave(&pci_config_lock, flags);
+
+ switch (len) {
+ case 1:
+ number = PCIBIOS_WRITE_CONFIG_BYTE;
+ break;
+ case 2:
+ number = PCIBIOS_WRITE_CONFIG_WORD;
+ break;
+ case 4:
+ number = PCIBIOS_WRITE_CONFIG_DWORD;
+ break;
+ }
+
+ __asm__("lcall *(%%esi); cld\n\t"
+ "jc 1f\n\t"
+ "xor %%ah, %%ah\n"
+ "1:"
+ : "=a" (result)
+ : "0" (number),
+ "c" (value),
+ "b" (bx),
+ "D" ((long)reg),
+ "S" (&pci_indirect));
+
+ raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+
+ return (int)((result & 0xff00) >> 8);
+}
+
+
+/*
+ * Function table for BIOS32 access
+ */
+
+static const struct pci_raw_ops pci_bios_access = {
+ .read = pci_bios_read,
+ .write = pci_bios_write
+};
+
+/*
+ * Try to find PCI BIOS.
+ */
+
+static const struct pci_raw_ops *__init pci_find_bios(void)
+{
+ union bios32 *check;
+ unsigned char sum;
+ int i, length;
+
+ /*
+ * Follow the standard procedure for locating the BIOS32 Service
+ * directory by scanning the permissible address range from
+ * 0xe0000 through 0xfffff for a valid BIOS32 structure.
+ */
+
+ for (check = (union bios32 *) __va(0xe0000);
+ check <= (union bios32 *) __va(0xffff0);
+ ++check) {
+ long sig;
+ if (get_kernel_nofault(sig, &check->fields.signature))
+ continue;
+
+ if (check->fields.signature != BIOS32_SIGNATURE)
+ continue;
+ length = check->fields.length * 16;
+ if (!length)
+ continue;
+ sum = 0;
+ for (i = 0; i < length ; ++i)
+ sum += check->chars[i];
+ if (sum != 0)
+ continue;
+ if (check->fields.revision != 0) {
+ printk("PCI: unsupported BIOS32 revision %d at 0x%p\n",
+ check->fields.revision, check);
+ continue;
+ }
+ DBG("PCI: BIOS32 Service Directory structure at 0x%p\n", check);
+ if (check->fields.entry >= 0x100000) {
+ printk("PCI: BIOS32 entry (0x%p) in high memory, "
+ "cannot use.\n", check);
+ return NULL;
+ } else {
+ unsigned long bios32_entry = check->fields.entry;
+ DBG("PCI: BIOS32 Service Directory entry at 0x%lx\n",
+ bios32_entry);
+ bios32_indirect.address = bios32_entry + PAGE_OFFSET;
+ set_bios_x();
+ if (check_pcibios())
+ return &pci_bios_access;
+ }
+ break; /* Hopefully more than one BIOS32 cannot happen... */
+ }
+
+ return NULL;
+}
+
+/*
+ * BIOS Functions for IRQ Routing
+ */
+
+struct irq_routing_options {
+ u16 size;
+ struct irq_info *table;
+ u16 segment;
+} __attribute__((packed));
+
+struct irq_routing_table * pcibios_get_irq_routing_table(void)
+{
+ struct irq_routing_options opt;
+ struct irq_routing_table *rt = NULL;
+ int ret, map;
+ unsigned long page;
+
+ if (!pci_bios_present)
+ return NULL;
+ page = __get_free_page(GFP_KERNEL);
+ if (!page)
+ return NULL;
+ opt.table = (struct irq_info *) page;
+ opt.size = PAGE_SIZE;
+ opt.segment = __KERNEL_DS;
+
+ DBG("PCI: Fetching IRQ routing table... ");
+ __asm__("push %%es\n\t"
+ "push %%ds\n\t"
+ "pop %%es\n\t"
+ "lcall *(%%esi); cld\n\t"
+ "pop %%es\n\t"
+ "jc 1f\n\t"
+ "xor %%ah, %%ah\n"
+ "1:"
+ : "=a" (ret),
+ "=b" (map),
+ "=m" (opt)
+ : "0" (PCIBIOS_GET_ROUTING_OPTIONS),
+ "1" (0),
+ "D" ((long) &opt),
+ "S" (&pci_indirect),
+ "m" (opt)
+ : "memory");
+ DBG("OK ret=%d, size=%d, map=%x\n", ret, opt.size, map);
+ if (ret & 0xff00)
+ printk(KERN_ERR "PCI: Error %02x when fetching IRQ routing table.\n", (ret >> 8) & 0xff);
+ else if (opt.size) {
+ rt = kmalloc(sizeof(struct irq_routing_table) + opt.size, GFP_KERNEL);
+ if (rt) {
+ memset(rt, 0, sizeof(struct irq_routing_table));
+ rt->size = opt.size + sizeof(struct irq_routing_table);
+ rt->exclusive_irqs = map;
+ memcpy(rt->slots, (void *) page, opt.size);
+ printk(KERN_INFO "PCI: Using BIOS Interrupt Routing Table\n");
+ }
+ }
+ free_page(page);
+ return rt;
+}
+EXPORT_SYMBOL(pcibios_get_irq_routing_table);
+
+int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq)
+{
+ int ret;
+
+ __asm__("lcall *(%%esi); cld\n\t"
+ "jc 1f\n\t"
+ "xor %%ah, %%ah\n"
+ "1:"
+ : "=a" (ret)
+ : "0" (PCIBIOS_SET_PCI_HW_INT),
+ "b" ((dev->bus->number << 8) | dev->devfn),
+ "c" ((irq << 8) | (pin + 10)),
+ "S" (&pci_indirect));
+ return !(ret & 0xff00);
+}
+EXPORT_SYMBOL(pcibios_set_irq_routing);
+
+void __init pci_pcbios_init(void)
+{
+ if ((pci_probe & PCI_PROBE_BIOS)
+ && ((raw_pci_ops = pci_find_bios()))) {
+ pci_bios_present = 1;
+ }
+}
+
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
new file mode 100644
index 0000000000..7368afc039
--- /dev/null
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -0,0 +1,232 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * DMA translation between STA2x11 AMBA memory mapping and the x86 memory mapping
+ *
+ * ST Microelectronics ConneXt (STA2X11/STA2X10)
+ *
+ * Copyright (c) 2010-2011 Wind River Systems, Inc.
+ */
+
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/export.h>
+#include <linux/list.h>
+#include <linux/dma-map-ops.h>
+#include <linux/swiotlb.h>
+#include <asm/iommu.h>
+
+#define STA2X11_SWIOTLB_SIZE (4*1024*1024)
+
+/*
+ * We build a list of bus numbers that are under the ConneXt. The
+ * main bridge hosts 4 busses, which are the 4 endpoints, in order.
+ */
+#define STA2X11_NR_EP 4 /* 0..3 included */
+#define STA2X11_NR_FUNCS 8 /* 0..7 included */
+#define STA2X11_AMBA_SIZE (512 << 20)
+
+struct sta2x11_ahb_regs { /* saved during suspend */
+ u32 base, pexlbase, pexhbase, crw;
+};
+
+struct sta2x11_mapping {
+ int is_suspended;
+ struct sta2x11_ahb_regs regs[STA2X11_NR_FUNCS];
+};
+
+struct sta2x11_instance {
+ struct list_head list;
+ int bus0;
+ struct sta2x11_mapping map[STA2X11_NR_EP];
+};
+
+static LIST_HEAD(sta2x11_instance_list);
+
+/* At probe time, record new instances of this bridge (likely one only) */
+static void sta2x11_new_instance(struct pci_dev *pdev)
+{
+ struct sta2x11_instance *instance;
+
+ instance = kzalloc(sizeof(*instance), GFP_ATOMIC);
+ if (!instance)
+ return;
+ /* This has a subordinate bridge, with 4 more-subordinate ones */
+ instance->bus0 = pdev->subordinate->number + 1;
+
+ if (list_empty(&sta2x11_instance_list)) {
+ int size = STA2X11_SWIOTLB_SIZE;
+ /* First instance: register your own swiotlb area */
+ dev_info(&pdev->dev, "Using SWIOTLB (size %i)\n", size);
+ if (swiotlb_init_late(size, GFP_DMA, NULL))
+ dev_emerg(&pdev->dev, "init swiotlb failed\n");
+ }
+ list_add(&instance->list, &sta2x11_instance_list);
+}
+DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, 0xcc17, sta2x11_new_instance);
+
+/*
+ * Utility functions used in this file from below
+ */
+static struct sta2x11_instance *sta2x11_pdev_to_instance(struct pci_dev *pdev)
+{
+ struct sta2x11_instance *instance;
+ int ep;
+
+ list_for_each_entry(instance, &sta2x11_instance_list, list) {
+ ep = pdev->bus->number - instance->bus0;
+ if (ep >= 0 && ep < STA2X11_NR_EP)
+ return instance;
+ }
+ return NULL;
+}
+
+static int sta2x11_pdev_to_ep(struct pci_dev *pdev)
+{
+ struct sta2x11_instance *instance;
+
+ instance = sta2x11_pdev_to_instance(pdev);
+ if (!instance)
+ return -1;
+
+ return pdev->bus->number - instance->bus0;
+}
+
+/* This is exported, as some devices need to access the MFD registers */
+struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev)
+{
+ return sta2x11_pdev_to_instance(pdev);
+}
+EXPORT_SYMBOL(sta2x11_get_instance);
+
+/* At setup time, we use our own ops if the device is a ConneXt one */
+static void sta2x11_setup_pdev(struct pci_dev *pdev)
+{
+ struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
+
+ if (!instance) /* either a sta2x11 bridge or another ST device */
+ return;
+
+ /* We must enable all devices as master, for audio DMA to work */
+ pci_set_master(pdev);
+}
+DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, sta2x11_setup_pdev);
+
+/*
+ * At boot we must set up the mappings for the pcie-to-amba bridge.
+ * It involves device access, and the same happens at suspend/resume time
+ */
+
+#define AHB_MAPB 0xCA4
+#define AHB_CRW(i) (AHB_MAPB + 0 + (i) * 0x10)
+#define AHB_CRW_SZMASK 0xfffffc00UL
+#define AHB_CRW_ENABLE (1 << 0)
+#define AHB_CRW_WTYPE_MEM (2 << 1)
+#define AHB_CRW_ROE (1UL << 3) /* Relax Order Ena */
+#define AHB_CRW_NSE (1UL << 4) /* No Snoop Enable */
+#define AHB_BASE(i) (AHB_MAPB + 4 + (i) * 0x10)
+#define AHB_PEXLBASE(i) (AHB_MAPB + 8 + (i) * 0x10)
+#define AHB_PEXHBASE(i) (AHB_MAPB + 12 + (i) * 0x10)
+
+/* At probe time, enable mapping for each endpoint, using the pdev */
+static void sta2x11_map_ep(struct pci_dev *pdev)
+{
+ struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
+ struct device *dev = &pdev->dev;
+ u32 amba_base, max_amba_addr;
+ int i, ret;
+
+ if (!instance)
+ return;
+
+ pci_read_config_dword(pdev, AHB_BASE(0), &amba_base);
+ max_amba_addr = amba_base + STA2X11_AMBA_SIZE - 1;
+
+ ret = dma_direct_set_offset(dev, 0, amba_base, STA2X11_AMBA_SIZE);
+ if (ret)
+ dev_err(dev, "sta2x11: could not set DMA offset\n");
+
+ dev->bus_dma_limit = max_amba_addr;
+ dma_set_mask_and_coherent(&pdev->dev, max_amba_addr);
+
+ /* Configure AHB mapping */
+ pci_write_config_dword(pdev, AHB_PEXLBASE(0), 0);
+ pci_write_config_dword(pdev, AHB_PEXHBASE(0), 0);
+ pci_write_config_dword(pdev, AHB_CRW(0), STA2X11_AMBA_SIZE |
+ AHB_CRW_WTYPE_MEM | AHB_CRW_ENABLE);
+
+ /* Disable all the other windows */
+ for (i = 1; i < STA2X11_NR_FUNCS; i++)
+ pci_write_config_dword(pdev, AHB_CRW(i), 0);
+
+ dev_info(&pdev->dev,
+ "sta2x11: Map EP %i: AMBA address %#8x-%#8x\n",
+ sta2x11_pdev_to_ep(pdev), amba_base, max_amba_addr);
+}
+DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, sta2x11_map_ep);
+
+#ifdef CONFIG_PM /* Some register values must be saved and restored */
+
+static struct sta2x11_mapping *sta2x11_pdev_to_mapping(struct pci_dev *pdev)
+{
+ struct sta2x11_instance *instance;
+ int ep;
+
+ instance = sta2x11_pdev_to_instance(pdev);
+ if (!instance)
+ return NULL;
+ ep = sta2x11_pdev_to_ep(pdev);
+ return instance->map + ep;
+}
+
+static void suspend_mapping(struct pci_dev *pdev)
+{
+ struct sta2x11_mapping *map = sta2x11_pdev_to_mapping(pdev);
+ int i;
+
+ if (!map)
+ return;
+
+ if (map->is_suspended)
+ return;
+ map->is_suspended = 1;
+
+ /* Save all window configs */
+ for (i = 0; i < STA2X11_NR_FUNCS; i++) {
+ struct sta2x11_ahb_regs *regs = map->regs + i;
+
+ pci_read_config_dword(pdev, AHB_BASE(i), &regs->base);
+ pci_read_config_dword(pdev, AHB_PEXLBASE(i), &regs->pexlbase);
+ pci_read_config_dword(pdev, AHB_PEXHBASE(i), &regs->pexhbase);
+ pci_read_config_dword(pdev, AHB_CRW(i), &regs->crw);
+ }
+}
+DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, suspend_mapping);
+
+static void resume_mapping(struct pci_dev *pdev)
+{
+ struct sta2x11_mapping *map = sta2x11_pdev_to_mapping(pdev);
+ int i;
+
+ if (!map)
+ return;
+
+
+ if (!map->is_suspended)
+ goto out;
+ map->is_suspended = 0;
+
+ /* Restore all window configs */
+ for (i = 0; i < STA2X11_NR_FUNCS; i++) {
+ struct sta2x11_ahb_regs *regs = map->regs + i;
+
+ pci_write_config_dword(pdev, AHB_BASE(i), regs->base);
+ pci_write_config_dword(pdev, AHB_PEXLBASE(i), regs->pexlbase);
+ pci_write_config_dword(pdev, AHB_PEXHBASE(i), regs->pexhbase);
+ pci_write_config_dword(pdev, AHB_CRW(i), regs->crw);
+ }
+out:
+ pci_set_master(pdev); /* Like at boot, enable master on all devices */
+}
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, resume_mapping);
+
+#endif /* CONFIG_PM */
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
new file mode 100644
index 0000000000..652cd53e77
--- /dev/null
+++ b/arch/x86/pci/xen.c
@@ -0,0 +1,590 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Xen PCI - handle PCI (INTx) and MSI infrastructure calls for PV, HVM and
+ * initial domain support. We also handle the DSDT _PRT callbacks for GSI's
+ * used in HVM and initial domain mode (PV does not parse ACPI, so it has no
+ * concept of GSIs). Under PV we hook under the pnbbios API for IRQs and
+ * 0xcf8 PCI configuration read/write.
+ *
+ * Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ * Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+ * Stefano Stabellini <stefano.stabellini@eu.citrix.com>
+ */
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/acpi.h>
+
+#include <linux/io.h>
+#include <asm/io_apic.h>
+#include <asm/pci_x86.h>
+
+#include <asm/xen/hypervisor.h>
+
+#include <xen/features.h>
+#include <xen/events.h>
+#include <xen/pci.h>
+#include <asm/xen/pci.h>
+#include <asm/xen/cpuid.h>
+#include <asm/apic.h>
+#include <asm/acpi.h>
+#include <asm/i8259.h>
+
+static int xen_pcifront_enable_irq(struct pci_dev *dev)
+{
+ int rc;
+ int share = 1;
+ int pirq;
+ u8 gsi;
+
+ rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi);
+ if (rc < 0) {
+ dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n",
+ rc);
+ return rc;
+ }
+ /* In PV DomU the Xen PCI backend puts the PIRQ in the interrupt line.*/
+ pirq = gsi;
+
+ if (gsi < nr_legacy_irqs())
+ share = 0;
+
+ rc = xen_bind_pirq_gsi_to_irq(gsi, pirq, share, "pcifront");
+ if (rc < 0) {
+ dev_warn(&dev->dev, "Xen PCI: failed to bind GSI%d (PIRQ%d) to IRQ: %d\n",
+ gsi, pirq, rc);
+ return rc;
+ }
+
+ dev->irq = rc;
+ dev_info(&dev->dev, "Xen PCI mapped GSI%d to IRQ%d\n", gsi, dev->irq);
+ return 0;
+}
+
+#ifdef CONFIG_ACPI
+static int xen_register_pirq(u32 gsi, int triggering, bool set_pirq)
+{
+ int rc, pirq = -1, irq;
+ struct physdev_map_pirq map_irq;
+ int shareable = 0;
+ char *name;
+
+ irq = xen_irq_from_gsi(gsi);
+ if (irq > 0)
+ return irq;
+
+ if (set_pirq)
+ pirq = gsi;
+
+ map_irq.domid = DOMID_SELF;
+ map_irq.type = MAP_PIRQ_TYPE_GSI;
+ map_irq.index = gsi;
+ map_irq.pirq = pirq;
+
+ rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
+ if (rc) {
+ printk(KERN_WARNING "xen map irq failed %d\n", rc);
+ return -1;
+ }
+
+ if (triggering == ACPI_EDGE_SENSITIVE) {
+ shareable = 0;
+ name = "ioapic-edge";
+ } else {
+ shareable = 1;
+ name = "ioapic-level";
+ }
+
+ irq = xen_bind_pirq_gsi_to_irq(gsi, map_irq.pirq, shareable, name);
+ if (irq < 0)
+ goto out;
+
+ printk(KERN_DEBUG "xen: --> pirq=%d -> irq=%d (gsi=%d)\n", map_irq.pirq, irq, gsi);
+out:
+ return irq;
+}
+
+static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi,
+ int trigger, int polarity)
+{
+ if (!xen_hvm_domain())
+ return -1;
+
+ return xen_register_pirq(gsi, trigger,
+ false /* no mapping of GSI to PIRQ */);
+}
+
+#ifdef CONFIG_XEN_PV_DOM0
+static int xen_register_gsi(u32 gsi, int triggering, int polarity)
+{
+ int rc, irq;
+ struct physdev_setup_gsi setup_gsi;
+
+ if (!xen_pv_domain())
+ return -1;
+
+ printk(KERN_DEBUG "xen: registering gsi %u triggering %d polarity %d\n",
+ gsi, triggering, polarity);
+
+ irq = xen_register_pirq(gsi, triggering, true);
+
+ setup_gsi.gsi = gsi;
+ setup_gsi.triggering = (triggering == ACPI_EDGE_SENSITIVE ? 0 : 1);
+ setup_gsi.polarity = (polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
+
+ rc = HYPERVISOR_physdev_op(PHYSDEVOP_setup_gsi, &setup_gsi);
+ if (rc == -EEXIST)
+ printk(KERN_INFO "Already setup the GSI :%d\n", gsi);
+ else if (rc) {
+ printk(KERN_ERR "Failed to setup GSI :%d, err_code:%d\n",
+ gsi, rc);
+ }
+
+ return irq;
+}
+
+static int acpi_register_gsi_xen(struct device *dev, u32 gsi,
+ int trigger, int polarity)
+{
+ return xen_register_gsi(gsi, trigger, polarity);
+}
+#endif
+#endif
+
+#if defined(CONFIG_PCI_MSI)
+#include <linux/msi.h>
+
+struct xen_pci_frontend_ops *xen_pci_frontend;
+EXPORT_SYMBOL_GPL(xen_pci_frontend);
+
+struct xen_msi_ops {
+ int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
+ void (*teardown_msi_irqs)(struct pci_dev *dev);
+};
+
+static struct xen_msi_ops xen_msi_ops __ro_after_init;
+
+static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+ int irq, ret, i;
+ struct msi_desc *msidesc;
+ int *v;
+
+ if (type == PCI_CAP_ID_MSI && nvec > 1)
+ return 1;
+
+ v = kcalloc(max(1, nvec), sizeof(int), GFP_KERNEL);
+ if (!v)
+ return -ENOMEM;
+
+ if (type == PCI_CAP_ID_MSIX)
+ ret = xen_pci_frontend_enable_msix(dev, v, nvec);
+ else
+ ret = xen_pci_frontend_enable_msi(dev, v);
+ if (ret)
+ goto error;
+ i = 0;
+ msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_NOTASSOCIATED) {
+ irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i],
+ (type == PCI_CAP_ID_MSI) ? nvec : 1,
+ (type == PCI_CAP_ID_MSIX) ?
+ "pcifront-msi-x" :
+ "pcifront-msi",
+ DOMID_SELF);
+ if (irq < 0) {
+ ret = irq;
+ goto free;
+ }
+ i++;
+ }
+ kfree(v);
+ return msi_device_populate_sysfs(&dev->dev);
+
+error:
+ if (ret == -ENOSYS)
+ dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n");
+ else if (ret)
+ dev_err(&dev->dev, "Xen PCI frontend error: %d!\n", ret);
+free:
+ kfree(v);
+ return ret;
+}
+
+static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq,
+ struct msi_msg *msg)
+{
+ /*
+ * We set vector == 0 to tell the hypervisor we don't care about
+ * it, but we want a pirq setup instead. We use the dest_id fields
+ * to pass the pirq that we want.
+ */
+ memset(msg, 0, sizeof(*msg));
+ msg->address_hi = X86_MSI_BASE_ADDRESS_HIGH;
+ msg->arch_addr_hi.destid_8_31 = pirq >> 8;
+ msg->arch_addr_lo.destid_0_7 = pirq & 0xFF;
+ msg->arch_addr_lo.base_address = X86_MSI_BASE_ADDRESS_LOW;
+ msg->arch_data.delivery_mode = APIC_DELIVERY_MODE_EXTINT;
+}
+
+static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+ int irq, pirq;
+ struct msi_desc *msidesc;
+ struct msi_msg msg;
+
+ if (type == PCI_CAP_ID_MSI && nvec > 1)
+ return 1;
+
+ msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_NOTASSOCIATED) {
+ pirq = xen_allocate_pirq_msi(dev, msidesc);
+ if (pirq < 0) {
+ irq = -ENODEV;
+ goto error;
+ }
+ xen_msi_compose_msg(dev, pirq, &msg);
+ __pci_write_msi_msg(msidesc, &msg);
+ dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
+ irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq,
+ (type == PCI_CAP_ID_MSI) ? nvec : 1,
+ (type == PCI_CAP_ID_MSIX) ?
+ "msi-x" : "msi",
+ DOMID_SELF);
+ if (irq < 0)
+ goto error;
+ dev_dbg(&dev->dev,
+ "xen: msi --> pirq=%d --> irq=%d\n", pirq, irq);
+ }
+ return msi_device_populate_sysfs(&dev->dev);
+
+error:
+ dev_err(&dev->dev, "Failed to create MSI%s! ret=%d!\n",
+ type == PCI_CAP_ID_MSI ? "" : "-X", irq);
+ return irq;
+}
+
+#ifdef CONFIG_XEN_PV_DOM0
+static bool __read_mostly pci_seg_supported = true;
+
+static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+ int ret = 0;
+ struct msi_desc *msidesc;
+
+ msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_NOTASSOCIATED) {
+ struct physdev_map_pirq map_irq;
+ domid_t domid;
+
+ domid = ret = xen_find_device_domain_owner(dev);
+ /* N.B. Casting int's -ENODEV to uint16_t results in 0xFFED,
+ * hence check ret value for < 0. */
+ if (ret < 0)
+ domid = DOMID_SELF;
+
+ memset(&map_irq, 0, sizeof(map_irq));
+ map_irq.domid = domid;
+ map_irq.type = MAP_PIRQ_TYPE_MSI_SEG;
+ map_irq.index = -1;
+ map_irq.pirq = -1;
+ map_irq.bus = dev->bus->number |
+ (pci_domain_nr(dev->bus) << 16);
+ map_irq.devfn = dev->devfn;
+
+ if (type == PCI_CAP_ID_MSI && nvec > 1) {
+ map_irq.type = MAP_PIRQ_TYPE_MULTI_MSI;
+ map_irq.entry_nr = nvec;
+ } else if (type == PCI_CAP_ID_MSIX) {
+ int pos;
+ unsigned long flags;
+ u32 table_offset, bir;
+
+ pos = dev->msix_cap;
+ pci_read_config_dword(dev, pos + PCI_MSIX_TABLE,
+ &table_offset);
+ bir = (u8)(table_offset & PCI_MSIX_TABLE_BIR);
+ flags = pci_resource_flags(dev, bir);
+ if (!flags || (flags & IORESOURCE_UNSET))
+ return -EINVAL;
+
+ map_irq.table_base = pci_resource_start(dev, bir);
+ map_irq.entry_nr = msidesc->msi_index;
+ }
+
+ ret = -EINVAL;
+ if (pci_seg_supported)
+ ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq,
+ &map_irq);
+ if (type == PCI_CAP_ID_MSI && nvec > 1 && ret) {
+ /*
+ * If MAP_PIRQ_TYPE_MULTI_MSI is not available
+ * there's nothing else we can do in this case.
+ * Just set ret > 0 so driver can retry with
+ * single MSI.
+ */
+ ret = 1;
+ goto out;
+ }
+ if (ret == -EINVAL && !pci_domain_nr(dev->bus)) {
+ map_irq.type = MAP_PIRQ_TYPE_MSI;
+ map_irq.index = -1;
+ map_irq.pirq = -1;
+ map_irq.bus = dev->bus->number;
+ ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq,
+ &map_irq);
+ if (ret != -EINVAL)
+ pci_seg_supported = false;
+ }
+ if (ret) {
+ dev_warn(&dev->dev, "xen map irq failed %d for %d domain\n",
+ ret, domid);
+ goto out;
+ }
+
+ ret = xen_bind_pirq_msi_to_irq(dev, msidesc, map_irq.pirq,
+ (type == PCI_CAP_ID_MSI) ? nvec : 1,
+ (type == PCI_CAP_ID_MSIX) ? "msi-x" : "msi",
+ domid);
+ if (ret < 0)
+ goto out;
+ }
+ ret = msi_device_populate_sysfs(&dev->dev);
+out:
+ return ret;
+}
+
+bool xen_initdom_restore_msi(struct pci_dev *dev)
+{
+ int ret = 0;
+
+ if (!xen_initial_domain())
+ return true;
+
+ if (pci_seg_supported) {
+ struct physdev_pci_device restore_ext;
+
+ restore_ext.seg = pci_domain_nr(dev->bus);
+ restore_ext.bus = dev->bus->number;
+ restore_ext.devfn = dev->devfn;
+ ret = HYPERVISOR_physdev_op(PHYSDEVOP_restore_msi_ext,
+ &restore_ext);
+ if (ret == -ENOSYS)
+ pci_seg_supported = false;
+ WARN(ret && ret != -ENOSYS, "restore_msi_ext -> %d\n", ret);
+ }
+ if (!pci_seg_supported) {
+ struct physdev_restore_msi restore;
+
+ restore.bus = dev->bus->number;
+ restore.devfn = dev->devfn;
+ ret = HYPERVISOR_physdev_op(PHYSDEVOP_restore_msi, &restore);
+ WARN(ret && ret != -ENOSYS, "restore_msi -> %d\n", ret);
+ }
+ return false;
+}
+#else /* CONFIG_XEN_PV_DOM0 */
+#define xen_initdom_setup_msi_irqs NULL
+#endif /* !CONFIG_XEN_PV_DOM0 */
+
+static void xen_teardown_msi_irqs(struct pci_dev *dev)
+{
+ struct msi_desc *msidesc;
+ int i;
+
+ msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_ASSOCIATED) {
+ for (i = 0; i < msidesc->nvec_used; i++)
+ xen_destroy_irq(msidesc->irq + i);
+ msidesc->irq = 0;
+ }
+
+ msi_device_destroy_sysfs(&dev->dev);
+}
+
+static void xen_pv_teardown_msi_irqs(struct pci_dev *dev)
+{
+ if (dev->msix_enabled)
+ xen_pci_frontend_disable_msix(dev);
+ else
+ xen_pci_frontend_disable_msi(dev);
+
+ xen_teardown_msi_irqs(dev);
+}
+
+static int xen_msi_domain_alloc_irqs(struct irq_domain *domain,
+ struct device *dev, int nvec)
+{
+ int type;
+
+ if (WARN_ON_ONCE(!dev_is_pci(dev)))
+ return -EINVAL;
+
+ type = to_pci_dev(dev)->msix_enabled ? PCI_CAP_ID_MSIX : PCI_CAP_ID_MSI;
+
+ return xen_msi_ops.setup_msi_irqs(to_pci_dev(dev), nvec, type);
+}
+
+static void xen_msi_domain_free_irqs(struct irq_domain *domain,
+ struct device *dev)
+{
+ if (WARN_ON_ONCE(!dev_is_pci(dev)))
+ return;
+
+ xen_msi_ops.teardown_msi_irqs(to_pci_dev(dev));
+}
+
+static struct msi_domain_ops xen_pci_msi_domain_ops = {
+ .domain_alloc_irqs = xen_msi_domain_alloc_irqs,
+ .domain_free_irqs = xen_msi_domain_free_irqs,
+};
+
+static struct msi_domain_info xen_pci_msi_domain_info = {
+ .flags = MSI_FLAG_PCI_MSIX | MSI_FLAG_FREE_MSI_DESCS | MSI_FLAG_DEV_SYSFS,
+ .ops = &xen_pci_msi_domain_ops,
+};
+
+/*
+ * This irq domain is a blatant violation of the irq domain design, but
+ * distangling XEN into real irq domains is not a job for mere mortals with
+ * limited XENology. But it's the least dangerous way for a mere mortal to
+ * get rid of the arch_*_msi_irqs() hackery in order to store the irq
+ * domain pointer in struct device. This irq domain wrappery allows to do
+ * that without breaking XEN terminally.
+ */
+static __init struct irq_domain *xen_create_pci_msi_domain(void)
+{
+ struct irq_domain *d = NULL;
+ struct fwnode_handle *fn;
+
+ fn = irq_domain_alloc_named_fwnode("XEN-MSI");
+ if (fn)
+ d = msi_create_irq_domain(fn, &xen_pci_msi_domain_info, NULL);
+
+ /* FIXME: No idea how to survive if this fails */
+ BUG_ON(!d);
+
+ return d;
+}
+
+static __init void xen_setup_pci_msi(void)
+{
+ if (xen_pv_domain()) {
+ if (xen_initial_domain())
+ xen_msi_ops.setup_msi_irqs = xen_initdom_setup_msi_irqs;
+ else
+ xen_msi_ops.setup_msi_irqs = xen_setup_msi_irqs;
+ xen_msi_ops.teardown_msi_irqs = xen_pv_teardown_msi_irqs;
+ } else if (xen_hvm_domain()) {
+ xen_msi_ops.setup_msi_irqs = xen_hvm_setup_msi_irqs;
+ xen_msi_ops.teardown_msi_irqs = xen_teardown_msi_irqs;
+ } else {
+ WARN_ON_ONCE(1);
+ return;
+ }
+
+ /*
+ * Override the PCI/MSI irq domain init function. No point
+ * in allocating the native domain and never use it.
+ */
+ x86_init.irqs.create_pci_msi_domain = xen_create_pci_msi_domain;
+ /*
+ * With XEN PIRQ/Eventchannels in use PCI/MSI[-X] masking is solely
+ * controlled by the hypervisor.
+ */
+ pci_msi_ignore_mask = 1;
+}
+
+#else /* CONFIG_PCI_MSI */
+static inline void xen_setup_pci_msi(void) { }
+#endif /* CONFIG_PCI_MSI */
+
+int __init pci_xen_init(void)
+{
+ if (!xen_pv_domain() || xen_initial_domain())
+ return -ENODEV;
+
+ printk(KERN_INFO "PCI: setting up Xen PCI frontend stub\n");
+
+ pcibios_set_cache_line_size();
+
+ pcibios_enable_irq = xen_pcifront_enable_irq;
+ pcibios_disable_irq = NULL;
+
+ /* Keep ACPI out of the picture */
+ acpi_noirq_set();
+
+ xen_setup_pci_msi();
+ return 0;
+}
+
+#ifdef CONFIG_PCI_MSI
+static void __init xen_hvm_msi_init(void)
+{
+ if (!apic_is_disabled) {
+ /*
+ * If hardware supports (x2)APIC virtualization (as indicated
+ * by hypervisor's leaf 4) then we don't need to use pirqs/
+ * event channels for MSI handling and instead use regular
+ * APIC processing
+ */
+ uint32_t eax = cpuid_eax(xen_cpuid_base() + 4);
+
+ if (((eax & XEN_HVM_CPUID_X2APIC_VIRT) && x2apic_mode) ||
+ ((eax & XEN_HVM_CPUID_APIC_ACCESS_VIRT) && boot_cpu_has(X86_FEATURE_APIC)))
+ return;
+ }
+ xen_setup_pci_msi();
+}
+#endif
+
+int __init pci_xen_hvm_init(void)
+{
+ if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs))
+ return 0;
+
+#ifdef CONFIG_ACPI
+ /*
+ * We don't want to change the actual ACPI delivery model,
+ * just how GSIs get registered.
+ */
+ __acpi_register_gsi = acpi_register_gsi_xen_hvm;
+ __acpi_unregister_gsi = NULL;
+#endif
+
+#ifdef CONFIG_PCI_MSI
+ /*
+ * We need to wait until after x2apic is initialized
+ * before we can set MSI IRQ ops.
+ */
+ x86_platform.apic_post_init = xen_hvm_msi_init;
+#endif
+ return 0;
+}
+
+#ifdef CONFIG_XEN_PV_DOM0
+int __init pci_xen_initial_domain(void)
+{
+ int irq;
+
+ xen_setup_pci_msi();
+ __acpi_register_gsi = acpi_register_gsi_xen;
+ __acpi_unregister_gsi = NULL;
+ /*
+ * Pre-allocate the legacy IRQs. Use NR_LEGACY_IRQS here
+ * because we don't have a PIC and thus nr_legacy_irqs() is zero.
+ */
+ for (irq = 0; irq < NR_IRQS_LEGACY; irq++) {
+ int trigger, polarity;
+
+ if (acpi_get_override_irq(irq, &trigger, &polarity) == -1)
+ continue;
+
+ xen_register_pirq(irq,
+ trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE,
+ true /* Map GSI to PIRQ */);
+ }
+ if (0 == nr_ioapics) {
+ for (irq = 0; irq < nr_legacy_irqs(); irq++)
+ xen_bind_pirq_gsi_to_irq(irq, irq, 0, "xt-pic");
+ }
+ return 0;
+}
+#endif
+