1// SPDX-License-Identifier: GPL-2.0 2 3#define pr_fmt(fmt) "PCI: " fmt 4 5#include <linux/pci.h> 6#include <linux/acpi.h> 7#include <linux/init.h> 8#include <linux/irq.h> 9#include <linux/dmi.h> 10#include <linux/slab.h> 11#include <linux/pci-acpi.h> 12#include <asm/numa.h> 13#include <asm/pci_x86.h> 14 15struct pci_root_info { 16 struct acpi_pci_root_info common; 17 struct pci_sysdata sd; 18#ifdef CONFIG_PCI_MMCONFIG 19 bool mcfg_added; 20 u8 start_bus; 21 u8 end_bus; 22#endif 23}; 24 25bool pci_use_e820 = true; 26static bool pci_use_crs = true; 27static bool pci_ignore_seg; 28 29static int __init set_use_crs(const struct dmi_system_id *id) 30{ 31 pci_use_crs = true; 32 return 0; 33} 34 35static int __init set_nouse_crs(const struct dmi_system_id *id) 36{ 37 pci_use_crs = false; 38 return 0; 39} 40 41static int __init set_ignore_seg(const struct dmi_system_id *id) 42{ 43 pr_info("%s detected: ignoring ACPI _SEG\n", id->ident); 44 pci_ignore_seg = true; 45 return 0; 46} 47 48static int __init set_no_e820(const struct dmi_system_id *id) 49{ 50 pr_info("%s detected: not clipping E820 regions from _CRS\n", 51 id->ident); 52 pci_use_e820 = false; 53 return 0; 54} 55 56static const struct dmi_system_id pci_crs_quirks[] __initconst = { 57 /* http://bugzilla.kernel.org/show_bug.cgi?id=14183 */ 58 { 59 .callback = set_use_crs, 60 .ident = "IBM System x3800", 61 .matches = { 62 DMI_MATCH(DMI_SYS_VENDOR, "IBM"), 63 DMI_MATCH(DMI_PRODUCT_NAME, "x3800"), 64 }, 65 }, 66 /* https://bugzilla.kernel.org/show_bug.cgi?id=16007 */ 67 /* 2006 AMD HT/VIA system with two host bridges */ 68 { 69 .callback = set_use_crs, 70 .ident = "ASRock ALiveSATA2-GLAN", 71 .matches = { 72 DMI_MATCH(DMI_PRODUCT_NAME, "ALiveSATA2-GLAN"), 73 }, 74 }, 75 /* https://bugzilla.kernel.org/show_bug.cgi?id=30552 */ 76 /* 2006 AMD HT/VIA system with two host bridges */ 77 { 78 .callback = set_use_crs, 79 .ident = "ASUS M2V-MX SE", 80 .matches = { 81 DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), 82 DMI_MATCH(DMI_BOARD_NAME, "M2V-MX SE"), 83 DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."), 84 }, 85 }, 86 /* https://bugzilla.kernel.org/show_bug.cgi?id=42619 */ 87 { 88 .callback = set_use_crs, 89 .ident = "MSI MS-7253", 90 .matches = { 91 DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"), 92 DMI_MATCH(DMI_BOARD_NAME, "MS-7253"), 93 DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"), 94 }, 95 }, 96 /* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/931368 */ 97 /* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/1033299 */ 98 { 99 .callback = set_use_crs, 100 .ident = "Foxconn K8M890-8237A", 101 .matches = { 102 DMI_MATCH(DMI_BOARD_VENDOR, "Foxconn"), 103 DMI_MATCH(DMI_BOARD_NAME, "K8M890-8237A"), 104 DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"), 105 }, 106 }, 107 108 /* Now for the blacklist.. */ 109 110 /* https://bugzilla.redhat.com/show_bug.cgi?id=769657 */ 111 { 112 .callback = set_nouse_crs, 113 .ident = "Dell Studio 1557", 114 .matches = { 115 DMI_MATCH(DMI_BOARD_VENDOR, "Dell Inc."), 116 DMI_MATCH(DMI_PRODUCT_NAME, "Studio 1557"), 117 DMI_MATCH(DMI_BIOS_VERSION, "A09"), 118 }, 119 }, 120 /* https://bugzilla.redhat.com/show_bug.cgi?id=769657 */ 121 { 122 .callback = set_nouse_crs, 123 .ident = "Thinkpad SL510", 124 .matches = { 125 DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), 126 DMI_MATCH(DMI_BOARD_NAME, "2847DFG"), 127 DMI_MATCH(DMI_BIOS_VERSION, "6JET85WW (1.43 )"), 128 }, 129 }, 130 /* https://bugzilla.kernel.org/show_bug.cgi?id=42606 */ 131 { 132 .callback = set_nouse_crs, 133 .ident = "Supermicro X8DTH", 134 .matches = { 135 DMI_MATCH(DMI_SYS_VENDOR, "Supermicro"), 136 DMI_MATCH(DMI_PRODUCT_NAME, "X8DTH-i/6/iF/6F"), 137 DMI_MATCH(DMI_BIOS_VERSION, "2.0a"), 138 }, 139 }, 140 141 /* https://bugzilla.kernel.org/show_bug.cgi?id=15362 */ 142 { 143 .callback = set_ignore_seg, 144 .ident = "HP xw9300", 145 .matches = { 146 DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), 147 DMI_MATCH(DMI_PRODUCT_NAME, "HP xw9300 Workstation"), 148 }, 149 }, 150 151 /* 152 * Many Lenovo models with "IIL" in their DMI_PRODUCT_VERSION have 153 * an E820 reserved region that covers the entire 32-bit host 154 * bridge memory window from _CRS. Using the E820 region to clip 155 * _CRS means no space is available for hot-added or uninitialized 156 * PCI devices. This typically breaks I2C controllers for touchpads 157 * and hot-added Thunderbolt devices. See the commit log for 158 * models known to require this quirk and related bug reports. 159 */ 160 { 161 .callback = set_no_e820, 162 .ident = "Lenovo *IIL* product version", 163 .matches = { 164 DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), 165 DMI_MATCH(DMI_PRODUCT_VERSION, "IIL"), 166 }, 167 }, 168 169 /* 170 * The Acer Spin 5 (SP513-54N) has the same E820 reservation covering 171 * the entire _CRS 32-bit window issue as the Lenovo *IIL* models. 172 * See https://bugs.launchpad.net/bugs/1884232 173 */ 174 { 175 .callback = set_no_e820, 176 .ident = "Acer Spin 5 (SP513-54N)", 177 .matches = { 178 DMI_MATCH(DMI_SYS_VENDOR, "Acer"), 179 DMI_MATCH(DMI_PRODUCT_NAME, "Spin SP513-54N"), 180 }, 181 }, 182 183 /* 184 * Clevo X170KM-G barebones have the same E820 reservation covering 185 * the entire _CRS 32-bit window issue as the Lenovo *IIL* models. 186 * See https://bugzilla.kernel.org/show_bug.cgi?id=214259 187 */ 188 { 189 .callback = set_no_e820, 190 .ident = "Clevo X170KM-G Barebone", 191 .matches = { 192 DMI_MATCH(DMI_BOARD_NAME, "X170KM-G"), 193 }, 194 }, 195 {} 196}; 197 198void __init pci_acpi_crs_quirks(void) 199{ 200 int year = dmi_get_bios_year(); 201 202 if (year >= 0 && year < 2008 && iomem_resource.end <= 0xffffffff) 203 pci_use_crs = false; 204 205 /* 206 * Some firmware includes unusable space (host bridge registers, 207 * hidden PCI device BARs, etc) in PCI host bridge _CRS. This is a 208 * firmware defect, and 4dc2287c1805 ("x86: avoid E820 regions when 209 * allocating address space") has clipped out the unusable space in 210 * the past. 211 * 212 * But other firmware supplies E820 reserved regions that cover 213 * entire _CRS windows, so clipping throws away the entire window, 214 * leaving none for hot-added or uninitialized devices. These E820 215 * entries are probably *not* a firmware defect, so disable the 216 * clipping by default for post-2022 machines. 217 * 218 * We already have quirks to disable clipping for pre-2023 219 * machines, and we'll likely need quirks to *enable* clipping for 220 * post-2022 machines that incorrectly include unusable space in 221 * _CRS. 222 */ 223 if (year >= 2023) 224 pci_use_e820 = false; 225 226 dmi_check_system(pci_crs_quirks); 227 228 /* 229 * If the user specifies "pci=use_crs" or "pci=nocrs" explicitly, that 230 * takes precedence over anything we figured out above. 231 */ 232 if (pci_probe & PCI_ROOT_NO_CRS) 233 pci_use_crs = false; 234 else if (pci_probe & PCI_USE__CRS) 235 pci_use_crs = true; 236 237 pr_info("%s host bridge windows from ACPI; if necessary, use \"pci=%s\" and report a bug\n", 238 pci_use_crs ? "Using" : "Ignoring", 239 pci_use_crs ? "nocrs" : "use_crs"); 240 241 /* "pci=use_e820"/"pci=no_e820" on the kernel cmdline takes precedence */ 242 if (pci_probe & PCI_NO_E820) 243 pci_use_e820 = false; 244 else if (pci_probe & PCI_USE_E820) 245 pci_use_e820 = true; 246 247 pr_info("%s E820 reservations for host bridge windows\n", 248 pci_use_e820 ? "Using" : "Ignoring"); 249 if (pci_probe & (PCI_NO_E820 | PCI_USE_E820)) 250 pr_info("Please notify linux-pci@vger.kernel.org so future kernels can do this automatically\n"); 251} 252 253#ifdef CONFIG_PCI_MMCONFIG 254static int check_segment(u16 seg, struct device *dev, char *estr) 255{ 256 if (seg) { 257 dev_err(dev, "%s can't access configuration space under this host bridge\n", 258 estr); 259 return -EIO; 260 } 261 262 /* 263 * Failure in adding MMCFG information is not fatal, 264 * just can't access extended configuration space of 265 * devices under this host bridge. 266 */ 267 dev_warn(dev, "%s can't access extended configuration space under this bridge\n", 268 estr); 269 270 return 0; 271} 272 273static int setup_mcfg_map(struct acpi_pci_root_info *ci) 274{ 275 int result, seg; 276 struct pci_root_info *info; 277 struct acpi_pci_root *root = ci->root; 278 struct device *dev = &ci->bridge->dev; 279 280 info = container_of(ci, struct pci_root_info, common); 281 info->start_bus = (u8)root->secondary.start; 282 info->end_bus = (u8)root->secondary.end; 283 info->mcfg_added = false; 284 seg = info->sd.domain; 285 286 /* return success if MMCFG is not in use */ 287 if (raw_pci_ext_ops && raw_pci_ext_ops != &pci_mmcfg) 288 return 0; 289 290 if (!(pci_probe & PCI_PROBE_MMCONF)) 291 return check_segment(seg, dev, "MMCONFIG is disabled,"); 292 293 result = pci_mmconfig_insert(dev, seg, info->start_bus, info->end_bus, 294 root->mcfg_addr); 295 if (result == 0) { 296 /* enable MMCFG if it hasn't been enabled yet */ 297 if (raw_pci_ext_ops == NULL) 298 raw_pci_ext_ops = &pci_mmcfg; 299 info->mcfg_added = true; 300 } else if (result != -EEXIST) 301 return check_segment(seg, dev, 302 "fail to add MMCONFIG information,"); 303 304 return 0; 305} 306 307static void teardown_mcfg_map(struct acpi_pci_root_info *ci) 308{ 309 struct pci_root_info *info; 310 311 info = container_of(ci, struct pci_root_info, common); 312 if (info->mcfg_added) { 313 pci_mmconfig_delete(info->sd.domain, 314 info->start_bus, info->end_bus); 315 info->mcfg_added = false; 316 } 317} 318#else 319static int setup_mcfg_map(struct acpi_pci_root_info *ci) 320{ 321 return 0; 322} 323 324static void teardown_mcfg_map(struct acpi_pci_root_info *ci) 325{ 326} 327#endif 328 329static int pci_acpi_root_get_node(struct acpi_pci_root *root) 330{ 331 int busnum = root->secondary.start; 332 struct acpi_device *device = root->device; 333 int node = acpi_get_node(device->handle); 334 335 if (node == NUMA_NO_NODE) { 336 node = x86_pci_root_bus_node(busnum); 337 if (node != 0 && node != NUMA_NO_NODE) 338 dev_info(&device->dev, FW_BUG "no _PXM; falling back to node %d from hardware (may be inconsistent with ACPI node numbers)\n", 339 node); 340 } 341 if (node != NUMA_NO_NODE && !node_online(node)) 342 node = NUMA_NO_NODE; 343 344 return node; 345} 346 347static int pci_acpi_root_init_info(struct acpi_pci_root_info *ci) 348{ 349 return setup_mcfg_map(ci); 350} 351 352static void pci_acpi_root_release_info(struct acpi_pci_root_info *ci) 353{ 354 teardown_mcfg_map(ci); 355 kfree(container_of(ci, struct pci_root_info, common)); 356} 357 358/* 359 * An IO port or MMIO resource assigned to a PCI host bridge may be 360 * consumed by the host bridge itself or available to its child 361 * bus/devices. The ACPI specification defines a bit (Producer/Consumer) 362 * to tell whether the resource is consumed by the host bridge itself, 363 * but firmware hasn't used that bit consistently, so we can't rely on it. 364 * 365 * On x86 and IA64 platforms, all IO port and MMIO resources are assumed 366 * to be available to child bus/devices except one special case: 367 * IO port [0xCF8-0xCFF] is consumed by the host bridge itself 368 * to access PCI configuration space. 369 * 370 * So explicitly filter out PCI CFG IO ports[0xCF8-0xCFF]. 371 */ 372static bool resource_is_pcicfg_ioport(struct resource *res) 373{ 374 return (res->flags & IORESOURCE_IO) && 375 res->start == 0xCF8 && res->end == 0xCFF; 376} 377 378static int pci_acpi_root_prepare_resources(struct acpi_pci_root_info *ci) 379{ 380 struct acpi_device *device = ci->bridge; 381 int busnum = ci->root->secondary.start; 382 struct resource_entry *entry, *tmp; 383 int status; 384 385 status = acpi_pci_probe_root_resources(ci); 386 387 if (pci_use_crs) { 388 resource_list_for_each_entry_safe(entry, tmp, &ci->resources) 389 if (resource_is_pcicfg_ioport(entry->res)) 390 resource_list_destroy_entry(entry); 391 return status; 392 } 393 394 resource_list_for_each_entry_safe(entry, tmp, &ci->resources) { 395 dev_printk(KERN_DEBUG, &device->dev, 396 "host bridge window %pR (ignored)\n", entry->res); 397 resource_list_destroy_entry(entry); 398 } 399 x86_pci_root_bus_resources(busnum, &ci->resources); 400 401 return 0; 402} 403 404static struct acpi_pci_root_ops acpi_pci_root_ops = { 405 .pci_ops = &pci_root_ops, 406 .init_info = pci_acpi_root_init_info, 407 .release_info = pci_acpi_root_release_info, 408 .prepare_resources = pci_acpi_root_prepare_resources, 409}; 410 411struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) 412{ 413 int domain = root->segment; 414 int busnum = root->secondary.start; 415 int node = pci_acpi_root_get_node(root); 416 struct pci_bus *bus; 417 418 if (pci_ignore_seg) 419 root->segment = domain = 0; 420 421 if (domain && !pci_domains_supported) { 422 pr_warn("pci_bus %04x:%02x: ignored (multiple domains not supported)\n", 423 domain, busnum); 424 return NULL; 425 } 426 427 bus = pci_find_bus(domain, busnum); 428 if (bus) { 429 /* 430 * If the desired bus has been scanned already, replace 431 * its bus->sysdata. 432 */ 433 struct pci_sysdata sd = { 434 .domain = domain, 435 .node = node, 436 .companion = root->device 437 }; 438 439 memcpy(bus->sysdata, &sd, sizeof(sd)); 440 } else { 441 struct pci_root_info *info; 442 443 info = kzalloc(sizeof(*info), GFP_KERNEL); 444 if (!info) 445 dev_err(&root->device->dev, 446 "pci_bus %04x:%02x: ignored (out of memory)\n", 447 domain, busnum); 448 else { 449 info->sd.domain = domain; 450 info->sd.node = node; 451 info->sd.companion = root->device; 452 bus = acpi_pci_root_create(root, &acpi_pci_root_ops, 453 &info->common, &info->sd); 454 } 455 } 456 457 /* After the PCI-E bus has been walked and all devices discovered, 458 * configure any settings of the fabric that might be necessary. 459 */ 460 if (bus) { 461 struct pci_bus *child; 462 list_for_each_entry(child, &bus->children, node) 463 pcie_bus_configure_settings(child); 464 } 465 466 return bus; 467} 468 469int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge) 470{ 471 /* 472 * We pass NULL as parent to pci_create_root_bus(), so if it is not NULL 473 * here, pci_create_root_bus() has been called by someone else and 474 * sysdata is likely to be different from what we expect. Let it go in 475 * that case. 476 */ 477 if (!bridge->dev.parent) { 478 struct pci_sysdata *sd = bridge->bus->sysdata; 479 ACPI_COMPANION_SET(&bridge->dev, sd->companion); 480 } 481 return 0; 482} 483 484int __init pci_acpi_init(void) 485{ 486 struct pci_dev *dev = NULL; 487 488 if (acpi_noirq) 489 return -ENODEV; 490 491 pr_info("Using ACPI for IRQ routing\n"); 492 acpi_irq_penalty_init(); 493 pcibios_enable_irq = acpi_pci_irq_enable; 494 pcibios_disable_irq = acpi_pci_irq_disable; 495 x86_init.pci.init_irq = x86_init_noop; 496 497 if (pci_routeirq) { 498 /* 499 * PCI IRQ routing is set up by pci_enable_device(), but we 500 * also do it here in case there are still broken drivers that 501 * don't use pci_enable_device(). 502 */ 503 pr_info("Routing PCI interrupts for all devices because \"pci=routeirq\" specified\n"); 504 for_each_pci_dev(dev) 505 acpi_pci_irq_enable(dev); 506 } 507 508 return 0; 509} 510