diff options
Diffstat (limited to 'drivers/pci/probe.c')
| -rw-r--r-- | drivers/pci/probe.c | 701 |
1 files changed, 418 insertions, 283 deletions
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 6186f03d84f..e3cf8a2e629 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -16,7 +16,7 @@ #define CARDBUS_LATENCY_TIMER 176 /* secondary latency timer */ #define CARDBUS_RESERVE_BUSNR 3 -struct resource busn_resource = { +static struct resource busn_resource = { .name = "PCI busn", .start = 0, .end = 255, @@ -96,7 +96,7 @@ static void release_pcibus_dev(struct device *dev) static struct class pcibus_class = { .name = "pci_bus", .dev_release = &release_pcibus_dev, - .dev_attrs = pcibus_dev_attrs, + .dev_groups = pcibus_groups, }; static int __init pcibus_class_init(void) @@ -156,6 +156,8 @@ static inline unsigned long decode_bar(struct pci_dev *dev, u32 bar) return flags; } +#define PCI_COMMAND_DECODE_ENABLE (PCI_COMMAND_MEMORY | PCI_COMMAND_IO) + /** * pci_read_base - read a PCI BAR * @dev: the PCI device @@ -166,20 +168,23 @@ static inline unsigned long decode_bar(struct pci_dev *dev, u32 bar) * Returns 1 if the BAR is 64-bit, or 0 if 32-bit. */ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, - struct resource *res, unsigned int pos) + struct resource *res, unsigned int pos) { u32 l, sz, mask; + u64 l64, sz64, mask64; u16 orig_cmd; - struct pci_bus_region region; - bool bar_too_big = false, bar_disabled = false; + struct pci_bus_region region, inverted_region; + bool bar_too_big = false, bar_too_high = false, bar_invalid = false; mask = type ? PCI_ROM_ADDRESS_MASK : ~0; /* No printks while decoding is disabled! */ if (!dev->mmio_always_on) { pci_read_config_word(dev, PCI_COMMAND, &orig_cmd); - pci_write_config_word(dev, PCI_COMMAND, - orig_cmd & ~(PCI_COMMAND_MEMORY | PCI_COMMAND_IO)); + if (orig_cmd & PCI_COMMAND_DECODE_ENABLE) { + pci_write_config_word(dev, PCI_COMMAND, + orig_cmd & ~PCI_COMMAND_DECODE_ENABLE); + } } res->name = pci_name(dev); @@ -222,9 +227,9 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, } if (res->flags & IORESOURCE_MEM_64) { - u64 l64 = l; - u64 sz64 = sz; - u64 mask64 = mask | (u64)~0 << 32; + l64 = l; + sz64 = sz; + mask64 = mask | (u64)~0 << 32; pci_read_config_dword(dev, pos + 4, &l); pci_write_config_dword(dev, pos + 4, ~0); @@ -239,23 +244,25 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, if (!sz64) goto fail; - if ((sizeof(resource_size_t) < 8) && (sz64 > 0x100000000ULL)) { + if ((sizeof(dma_addr_t) < 8 || sizeof(resource_size_t) < 8) && + sz64 > 0x100000000ULL) { + res->flags |= IORESOURCE_UNSET | IORESOURCE_DISABLED; + res->start = 0; + res->end = 0; bar_too_big = true; - goto fail; + goto out; } - if ((sizeof(resource_size_t) < 8) && l) { - /* Address above 32-bit boundary; disable the BAR */ - pci_write_config_dword(dev, pos, 0); - pci_write_config_dword(dev, pos + 4, 0); - region.start = 0; - region.end = sz64; - pcibios_bus_to_resource(dev, res, ®ion); - bar_disabled = true; + if ((sizeof(dma_addr_t) < 8) && l) { + /* Above 32-bit boundary; try to reallocate */ + res->flags |= IORESOURCE_UNSET; + res->start = 0; + res->end = sz64; + bar_too_high = true; + goto out; } else { region.start = l64; region.end = l64 + sz64; - pcibios_bus_to_resource(dev, res, ®ion); } } else { sz = pci_size(l, sz, mask); @@ -265,7 +272,27 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, region.start = l; region.end = l + sz; - pcibios_bus_to_resource(dev, res, ®ion); + } + + pcibios_bus_to_resource(dev->bus, res, ®ion); + pcibios_resource_to_bus(dev->bus, &inverted_region, res); + + /* + * If "A" is a BAR value (a bus address), "bus_to_resource(A)" is + * the corresponding resource address (the physical address used by + * the CPU. Converting that resource address back to a bus address + * should yield the original BAR value: + * + * resource_to_bus(bus_to_resource(A)) == A + * + * If it doesn't, CPU accesses to "bus_to_resource(A)" will not + * be claimed by the device. + */ + if (inverted_region.start != region.start) { + res->flags |= IORESOURCE_UNSET; + res->start = 0; + res->end = region.end - region.start; + bar_invalid = true; } goto out; @@ -274,13 +301,21 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, fail: res->flags = 0; out: - if (!dev->mmio_always_on) + if (!dev->mmio_always_on && + (orig_cmd & PCI_COMMAND_DECODE_ENABLE)) pci_write_config_word(dev, PCI_COMMAND, orig_cmd); if (bar_too_big) - dev_err(&dev->dev, "reg %x: can't handle 64-bit BAR\n", pos); - if (res->flags && !bar_disabled) - dev_printk(KERN_DEBUG, &dev->dev, "reg %x: %pR\n", pos, res); + dev_err(&dev->dev, "reg 0x%x: can't handle BAR larger than 4GB (size %#010llx)\n", + pos, (unsigned long long) sz64); + if (bar_too_high) + dev_info(&dev->dev, "reg 0x%x: can't handle BAR above 4G (bus address %#010llx)\n", + pos, (unsigned long long) l64); + if (bar_invalid) + dev_info(&dev->dev, "reg 0x%x: initial BAR value %#010llx invalid\n", + pos, (unsigned long long) region.start); + if (res->flags) + dev_printk(KERN_DEBUG, &dev->dev, "reg 0x%x: %pR\n", pos, res); return (res->flags & IORESOURCE_MEM_64) ? 1 : 0; } @@ -340,7 +375,7 @@ static void pci_read_bridge_io(struct pci_bus *child) res->flags = (io_base_lo & PCI_IO_RANGE_TYPE_MASK) | IORESOURCE_IO; region.start = base; region.end = limit + io_granularity - 1; - pcibios_bus_to_resource(dev, res, ®ion); + pcibios_bus_to_resource(dev->bus, res, ®ion); dev_printk(KERN_DEBUG, &dev->dev, " bridge window %pR\n", res); } } @@ -362,7 +397,7 @@ static void pci_read_bridge_mmio(struct pci_bus *child) res->flags = (mem_base_lo & PCI_MEMORY_RANGE_TYPE_MASK) | IORESOURCE_MEM; region.start = base; region.end = limit + 0xfffff; - pcibios_bus_to_resource(dev, res, ®ion); + pcibios_bus_to_resource(dev->bus, res, ®ion); dev_printk(KERN_DEBUG, &dev->dev, " bridge window %pR\n", res); } } @@ -398,8 +433,7 @@ static void pci_read_bridge_mmio_pref(struct pci_bus *child) limit |= ((unsigned long) mem_limit_hi) << 32; #else if (mem_base_hi || mem_limit_hi) { - dev_err(&dev->dev, "can't handle 64-bit " - "address space for bridge\n"); + dev_err(&dev->dev, "can't handle 64-bit address space for bridge\n"); return; } #endif @@ -412,7 +446,7 @@ static void pci_read_bridge_mmio_pref(struct pci_bus *child) res->flags |= IORESOURCE_MEM_64; region.start = base; region.end = limit + 0xfffff; - pcibios_bus_to_resource(dev, res, ®ion); + pcibios_bus_to_resource(dev->bus, res, ®ion); dev_printk(KERN_DEBUG, &dev->dev, " bridge window %pR\n", res); } } @@ -440,7 +474,7 @@ void pci_read_bridge_bases(struct pci_bus *child) if (dev->transparent) { pci_bus_for_each_resource(child->parent, res, i) { - if (res) { + if (res && res->flags) { pci_bus_add_resource(child, res, PCI_SUBTRACTIVE_DECODE); dev_printk(KERN_DEBUG, &dev->dev, @@ -451,37 +485,50 @@ void pci_read_bridge_bases(struct pci_bus *child) } } -static struct pci_bus * pci_alloc_bus(void) +static struct pci_bus *pci_alloc_bus(void) { struct pci_bus *b; b = kzalloc(sizeof(*b), GFP_KERNEL); - if (b) { - INIT_LIST_HEAD(&b->node); - INIT_LIST_HEAD(&b->children); - INIT_LIST_HEAD(&b->devices); - INIT_LIST_HEAD(&b->slots); - INIT_LIST_HEAD(&b->resources); - b->max_bus_speed = PCI_SPEED_UNKNOWN; - b->cur_bus_speed = PCI_SPEED_UNKNOWN; - } + if (!b) + return NULL; + + INIT_LIST_HEAD(&b->node); + INIT_LIST_HEAD(&b->children); + INIT_LIST_HEAD(&b->devices); + INIT_LIST_HEAD(&b->slots); + INIT_LIST_HEAD(&b->resources); + b->max_bus_speed = PCI_SPEED_UNKNOWN; + b->cur_bus_speed = PCI_SPEED_UNKNOWN; return b; } +static void pci_release_host_bridge_dev(struct device *dev) +{ + struct pci_host_bridge *bridge = to_pci_host_bridge(dev); + + if (bridge->release_fn) + bridge->release_fn(bridge); + + pci_free_resource_list(&bridge->windows); + + kfree(bridge); +} + static struct pci_host_bridge *pci_alloc_host_bridge(struct pci_bus *b) { struct pci_host_bridge *bridge; bridge = kzalloc(sizeof(*bridge), GFP_KERNEL); - if (bridge) { - INIT_LIST_HEAD(&bridge->windows); - bridge->bus = b; - } + if (!bridge) + return NULL; + INIT_LIST_HEAD(&bridge->windows); + bridge->bus = b; return bridge; } -static unsigned char pcix_bus_speed[] = { +static const unsigned char pcix_bus_speed[] = { PCI_SPEED_UNKNOWN, /* 0 */ PCI_SPEED_66MHz_PCIX, /* 1 */ PCI_SPEED_100MHz_PCIX, /* 2 */ @@ -500,7 +547,7 @@ static unsigned char pcix_bus_speed[] = { PCI_SPEED_133MHz_PCIX_533 /* F */ }; -static unsigned char pcie_link_speed[] = { +const unsigned char pcie_link_speed[] = { PCI_SPEED_UNKNOWN, /* 0 */ PCIE_SPEED_2_5GT, /* 1 */ PCIE_SPEED_5_0GT, /* 2 */ @@ -545,7 +592,7 @@ static enum pci_bus_speed agp_speed(int agp3, int agpstat) index = 1; else goto out; - + if (agp3) { index += 2; if (index == 5) @@ -556,7 +603,6 @@ static enum pci_bus_speed agp_speed(int agp3, int agpstat) return agp_speeds[index]; } - static void pci_set_bus_speed(struct pci_bus *bus) { struct pci_dev *bridge = bus->self; @@ -588,11 +634,10 @@ static void pci_set_bus_speed(struct pci_bus *bus) } else if (status & PCI_X_SSTATUS_266MHZ) { max = PCI_SPEED_133MHz_PCIX_266; } else if (status & PCI_X_SSTATUS_133MHZ) { - if ((status & PCI_X_SSTATUS_VERS) == PCI_X_SSTATUS_V2) { + if ((status & PCI_X_SSTATUS_VERS) == PCI_X_SSTATUS_V2) max = PCI_SPEED_133MHz_PCIX_ECC; - } else { + else max = PCI_SPEED_133MHz_PCIX; - } } else { max = PCI_SPEED_66MHz_PCIX; } @@ -604,8 +649,7 @@ static void pci_set_bus_speed(struct pci_bus *bus) return; } - pos = pci_find_capability(bridge, PCI_CAP_ID_EXP); - if (pos) { + if (pci_is_pcie(bridge)) { u32 linkcap; u16 linksta; @@ -617,12 +661,12 @@ static void pci_set_bus_speed(struct pci_bus *bus) } } - static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent, struct pci_dev *bridge, int busnr) { struct pci_bus *child; int i; + int ret; /* * Allocate a new bus, and inherit stuff from the parent.. @@ -633,12 +677,12 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent, child->parent = parent; child->ops = parent->ops; + child->msi = parent->msi; child->sysdata = parent->sysdata; child->bus_flags = parent->bus_flags; /* initialize some portions of the bus device, but don't register it - * now as the parent is not properly set up yet. This device will get - * registered later in pci_bus_add_devices() + * now as the parent is not properly set up yet. */ child->dev.class = &pcibus_class; dev_set_name(&child->dev, "%04x:%02x", pci_domain_nr(child), busnr); @@ -651,11 +695,14 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent, child->primary = parent->busn_res.start; child->busn_res.end = 0xff; - if (!bridge) - return child; + if (!bridge) { + child->dev.parent = parent->bridge; + goto add_dev; + } child->self = bridge; child->bridge = get_device(&bridge->dev); + child->dev.parent = child->bridge; pci_set_bus_of_node(child); pci_set_bus_speed(child); @@ -666,10 +713,20 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent, } bridge->subordinate = child; +add_dev: + ret = device_register(&child->dev); + WARN_ON(ret < 0); + + pcibios_add_bus(child); + + /* Create legacy_io and legacy_mem files for this bus */ + pci_create_legacy_files(child); + return child; } -struct pci_bus *__ref pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev, int busnr) +struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev, + int busnr) { struct pci_bus *child; @@ -681,22 +738,7 @@ struct pci_bus *__ref pci_add_new_bus(struct pci_bus *parent, struct pci_dev *de } return child; } - -static void pci_fixup_parent_subordinate_busnr(struct pci_bus *child, int max) -{ - struct pci_bus *parent = child->parent; - - /* Attempts to fix that up are really dangerous unless - we're going to re-assign all bus numbers. */ - if (!pcibios_assign_all_busses()) - return; - - while (parent->parent && parent->busn_res.end < max) { - parent->busn_res.end = max; - pci_write_config_byte(parent->self, PCI_SUBORDINATE_BUS, max); - parent = parent->parent; - } -} +EXPORT_SYMBOL(pci_add_new_bus); /* * If it's a bridge, configure it and scan the bus behind it. @@ -733,14 +775,14 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass) /* Check if setup is sensible at all */ if (!pass && (primary != bus->number || secondary <= bus->number || - secondary > subordinate)) { + secondary > subordinate || subordinate > bus->busn_res.end)) { dev_info(&dev->dev, "bridge configuration invalid ([bus %02x-%02x]), reconfiguring\n", secondary, subordinate); broken = 1; } /* Disable MasterAbortMode during probing to avoid reporting - of bus errors (in some architectures) */ + of bus errors (in some architectures) */ pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &bctl); pci_write_config_word(dev, PCI_BRIDGE_CONTROL, bctl & ~PCI_BRIDGE_CTL_MASTER_ABORT); @@ -756,11 +798,10 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass) goto out; /* - * If we already got to this bus through a different bridge, - * don't re-add it. This can happen with the i450NX chipset. - * - * However, we continue to descend down the hierarchy and - * scan remaining child buses. + * The bus might already exist for two reasons: Either we are + * rescanning the bus or the bus is reachable through more than + * one bridge. The second case can happen with the i450NX + * chipset. */ child = pci_find_bus(pci_domain_nr(bus), secondary); if (!child) { @@ -773,17 +814,19 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass) } cmax = pci_scan_child_bus(child); - if (cmax > max) - max = cmax; - if (child->busn_res.end > max) - max = child->busn_res.end; + if (cmax > subordinate) + dev_warn(&dev->dev, "bridge has subordinate %02x but max busn %02x\n", + subordinate, cmax); + /* subordinate should equal child->busn_res.end */ + if (subordinate > max) + max = subordinate; } else { /* * We need to assign a number to this bus which we always * do in the second pass. */ if (!pass) { - if (pcibios_assign_all_busses() || broken) + if (pcibios_assign_all_busses() || broken || is_cardbus) /* Temporarily disable forwarding of the configuration cycles on all bridges in this bus segment to avoid possible @@ -795,19 +838,25 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass) goto out; } + if (max >= bus->busn_res.end) { + dev_warn(&dev->dev, "can't allocate child bus %02x from %pR\n", + max, &bus->busn_res); + goto out; + } + /* Clear errors */ pci_write_config_word(dev, PCI_STATUS, 0xffff); - /* Prevent assigning a bus number that already exists. - * This can happen when a bridge is hot-plugged, so in - * this case we only re-scan this bus. */ + /* The bus will already exist if we are rescanning */ child = pci_find_bus(pci_domain_nr(bus), max+1); if (!child) { - child = pci_add_new_bus(bus, dev, ++max); + child = pci_add_new_bus(bus, dev, max+1); if (!child) goto out; - pci_bus_insert_busn_res(child, max, 0xff); + pci_bus_insert_busn_res(child, max+1, + bus->busn_res.end); } + max++; buses = (buses & 0xff000000) | ((unsigned int)(child->primary) << 0) | ((unsigned int)(child->busn_res.start) << 8) @@ -829,27 +878,14 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass) if (!is_cardbus) { child->bridge_ctl = bctl; - /* - * Adjust subordinate busnr in parent buses. - * We do this before scanning for children because - * some devices may not be detected if the bios - * was lazy. - */ - pci_fixup_parent_subordinate_busnr(child, max); - /* Now we can scan all subordinate buses... */ max = pci_scan_child_bus(child); - /* - * now fix it up again since we have found - * the real value of max. - */ - pci_fixup_parent_subordinate_busnr(child, max); } else { /* * For CardBus bridges, we leave 4 bus numbers * as cards with a PCI-to-PCI bridge can be * inserted later. */ - for (i=0; i<CARDBUS_RESERVE_BUSNR; i++) { + for (i = 0; i < CARDBUS_RESERVE_BUSNR; i++) { struct pci_bus *parent = bus; if (pci_find_bus(pci_domain_nr(bus), max+i+1)) @@ -873,11 +909,15 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass) } } max += i; - pci_fixup_parent_subordinate_busnr(child, max); } /* * Set the subordinate bus number to its real value. */ + if (max > bus->busn_res.end) { + dev_warn(&dev->dev, "max busn %02x is outside %pR\n", + max, &bus->busn_res); + max = bus->busn_res.end; + } pci_bus_update_busn_res_end(child, max); pci_write_config_byte(dev, PCI_SUBORDINATE_BUS, max); } @@ -892,8 +932,7 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass) (child->number > bus->busn_res.end) || (child->number < bus->number) || (child->busn_res.end < bus->number)) { - dev_info(&child->dev, "%pR %s " - "hidden behind%s bridge %s %pR\n", + dev_info(&child->dev, "%pR %s hidden behind%s bridge %s %pR\n", &child->busn_res, (bus->number > child->busn_res.end && bus->busn_res.end < child->number) ? @@ -910,6 +949,7 @@ out: return max; } +EXPORT_SYMBOL(pci_scan_bridge); /* * Read interrupt line and base address registers. @@ -934,7 +974,6 @@ void set_pcie_port_type(struct pci_dev *pdev) pos = pci_find_capability(pdev, PCI_CAP_ID_EXP); if (!pos) return; - pdev->is_pcie = 1; pdev->pcie_cap = pos; pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, ®16); pdev->pcie_flags_reg = reg16; @@ -951,13 +990,103 @@ void set_pcie_hotplug_bridge(struct pci_dev *pdev) pdev->is_hotplug_bridge = 1; } +/** + * pci_ext_cfg_is_aliased - is ext config space just an alias of std config? + * @dev: PCI device + * + * PCI Express to PCI/PCI-X Bridge Specification, rev 1.0, 4.1.4 says that + * when forwarding a type1 configuration request the bridge must check that + * the extended register address field is zero. The bridge is not permitted + * to forward the transactions and must handle it as an Unsupported Request. + * Some bridges do not follow this rule and simply drop the extended register + * bits, resulting in the standard config space being aliased, every 256 + * bytes across the entire configuration space. Test for this condition by + * comparing the first dword of each potential alias to the vendor/device ID. + * Known offenders: + * ASM1083/1085 PCIe-to-PCI Reversible Bridge (1b21:1080, rev 01 & 03) + * AMD/ATI SBx00 PCI to PCI Bridge (1002:4384, rev 40) + */ +static bool pci_ext_cfg_is_aliased(struct pci_dev *dev) +{ +#ifdef CONFIG_PCI_QUIRKS + int pos; + u32 header, tmp; + + pci_read_config_dword(dev, PCI_VENDOR_ID, &header); + + for (pos = PCI_CFG_SPACE_SIZE; + pos < PCI_CFG_SPACE_EXP_SIZE; pos += PCI_CFG_SPACE_SIZE) { + if (pci_read_config_dword(dev, pos, &tmp) != PCIBIOS_SUCCESSFUL + || header != tmp) + return false; + } + + return true; +#else + return false; +#endif +} + +/** + * pci_cfg_space_size - get the configuration space size of the PCI device. + * @dev: PCI device + * + * Regular PCI devices have 256 bytes, but PCI-X 2 and PCI Express devices + * have 4096 bytes. Even if the device is capable, that doesn't mean we can + * access it. Maybe we don't have a way to generate extended config space + * accesses, or the device is behind a reverse Express bridge. So we try + * reading the dword at 0x100 which must either be 0 or a valid extended + * capability header. + */ +static int pci_cfg_space_size_ext(struct pci_dev *dev) +{ + u32 status; + int pos = PCI_CFG_SPACE_SIZE; + + if (pci_read_config_dword(dev, pos, &status) != PCIBIOS_SUCCESSFUL) + goto fail; + if (status == 0xffffffff || pci_ext_cfg_is_aliased(dev)) + goto fail; + + return PCI_CFG_SPACE_EXP_SIZE; + + fail: + return PCI_CFG_SPACE_SIZE; +} + +int pci_cfg_space_size(struct pci_dev *dev) +{ + int pos; + u32 status; + u16 class; + + class = dev->class >> 8; + if (class == PCI_CLASS_BRIDGE_HOST) + return pci_cfg_space_size_ext(dev); + + if (!pci_is_pcie(dev)) { + pos = pci_find_capability(dev, PCI_CAP_ID_PCIX); + if (!pos) + goto fail; + + pci_read_config_dword(dev, pos + PCI_X_STATUS, &status); + if (!(status & (PCI_X_STATUS_266MHZ | PCI_X_STATUS_533MHZ))) + goto fail; + } + + return pci_cfg_space_size_ext(dev); + + fail: + return PCI_CFG_SPACE_SIZE; +} + #define LEGACY_IO_RESOURCE (IORESOURCE_IO | IORESOURCE_PCI_FIXED) /** * pci_setup_device - fill in class and map information of a device * @dev: the device structure to fill * - * Initialize the device structure with information about the device's + * Initialize the device structure with information about the device's * vendor,class,memory and IO-space addresses,IRQ lines etc. * Called at initialisation of the PCI subsystem and by CardBus services. * Returns 0 on success and negative if unknown type of device (not normal, @@ -978,7 +1107,6 @@ int pci_setup_device(struct pci_dev *dev) dev->sysdata = dev->bus->sysdata; dev->dev.parent = dev->bus->bridge; dev->dev.bus = &pci_bus_type; - dev->dev.type = &pci_dev_type; dev->hdr_type = hdr_type & 0x7f; dev->multifunction = !!(hdr_type & 0x80); dev->error_state = pci_channel_io_normal; @@ -1024,10 +1152,10 @@ int pci_setup_device(struct pci_dev *dev) pci_read_config_word(dev, PCI_SUBSYSTEM_ID, &dev->subsystem_device); /* - * Do the ugly legacy mode stuff here rather than broken chip - * quirk code. Legacy mode ATA controllers have fixed - * addresses. These are not always echoed in BAR0-3, and - * BAR0-3 in a few cases contain junk! + * Do the ugly legacy mode stuff here rather than broken chip + * quirk code. Legacy mode ATA controllers have fixed + * addresses. These are not always echoed in BAR0-3, and + * BAR0-3 in a few cases contain junk! */ if (class == PCI_CLASS_STORAGE_IDE) { u8 progif; @@ -1037,24 +1165,32 @@ int pci_setup_device(struct pci_dev *dev) region.end = 0x1F7; res = &dev->resource[0]; res->flags = LEGACY_IO_RESOURCE; - pcibios_bus_to_resource(dev, res, ®ion); + pcibios_bus_to_resource(dev->bus, res, ®ion); + dev_info(&dev->dev, "legacy IDE quirk: reg 0x10: %pR\n", + res); region.start = 0x3F6; region.end = 0x3F6; res = &dev->resource[1]; res->flags = LEGACY_IO_RESOURCE; - pcibios_bus_to_resource(dev, res, ®ion); + pcibios_bus_to_resource(dev->bus, res, ®ion); + dev_info(&dev->dev, "legacy IDE quirk: reg 0x14: %pR\n", + res); } if ((progif & 4) == 0) { region.start = 0x170; region.end = 0x177; res = &dev->resource[2]; res->flags = LEGACY_IO_RESOURCE; - pcibios_bus_to_resource(dev, res, ®ion); + pcibios_bus_to_resource(dev->bus, res, ®ion); + dev_info(&dev->dev, "legacy IDE quirk: reg 0x18: %pR\n", + res); region.start = 0x376; region.end = 0x376; res = &dev->resource[3]; res->flags = LEGACY_IO_RESOURCE; - pcibios_bus_to_resource(dev, res, ®ion); + pcibios_bus_to_resource(dev->bus, res, ®ion); + dev_info(&dev->dev, "legacy IDE quirk: reg 0x1c: %pR\n", + res); } } break; @@ -1064,7 +1200,7 @@ int pci_setup_device(struct pci_dev *dev) goto bad; /* The PCI-to-PCI bridge spec requires that subtractive decoding (i.e. transparent) bridge must have programming - interface code of 0x01. */ + interface code of 0x01. */ pci_read_irq(dev); dev->transparent = ((dev->class & 0xff) == 1); pci_read_bases(dev, 2, PCI_ROM_ADDRESS1); @@ -1086,13 +1222,13 @@ int pci_setup_device(struct pci_dev *dev) break; default: /* unknown header */ - dev_err(&dev->dev, "unknown header type %02x, " - "ignoring device\n", dev->hdr_type); + dev_err(&dev->dev, "unknown header type %02x, ignoring device\n", + dev->hdr_type); return -EIO; bad: - dev_err(&dev->dev, "ignoring class %#08x (doesn't match header " - "type %02x)\n", dev->class, dev->hdr_type); + dev_err(&dev->dev, "ignoring class %#08x (doesn't match header type %02x)\n", + dev->class, dev->hdr_type); dev->class = PCI_CLASS_NOT_DEFINED; } @@ -1121,75 +1257,13 @@ static void pci_release_dev(struct device *dev) pci_dev = to_pci_dev(dev); pci_release_capabilities(pci_dev); pci_release_of_node(pci_dev); + pcibios_release_device(pci_dev); + pci_bus_put(pci_dev->bus); + kfree(pci_dev->driver_override); kfree(pci_dev); } -/** - * pci_cfg_space_size - get the configuration space size of the PCI device. - * @dev: PCI device - * - * Regular PCI devices have 256 bytes, but PCI-X 2 and PCI Express devices - * have 4096 bytes. Even if the device is capable, that doesn't mean we can - * access it. Maybe we don't have a way to generate extended config space - * accesses, or the device is behind a reverse Express bridge. So we try - * reading the dword at 0x100 which must either be 0 or a valid extended - * capability header. - */ -int pci_cfg_space_size_ext(struct pci_dev *dev) -{ - u32 status; - int pos = PCI_CFG_SPACE_SIZE; - - if (pci_read_config_dword(dev, pos, &status) != PCIBIOS_SUCCESSFUL) - goto fail; - if (status == 0xffffffff) - goto fail; - - return PCI_CFG_SPACE_EXP_SIZE; - - fail: - return PCI_CFG_SPACE_SIZE; -} - -int pci_cfg_space_size(struct pci_dev *dev) -{ - int pos; - u32 status; - u16 class; - - class = dev->class >> 8; - if (class == PCI_CLASS_BRIDGE_HOST) - return pci_cfg_space_size_ext(dev); - - if (!pci_is_pcie(dev)) { - pos = pci_find_capability(dev, PCI_CAP_ID_PCIX); - if (!pos) - goto fail; - - pci_read_config_dword(dev, pos + PCI_X_STATUS, &status); - if (!(status & (PCI_X_STATUS_266MHZ | PCI_X_STATUS_533MHZ))) - goto fail; - } - - return pci_cfg_space_size_ext(dev); - - fail: - return PCI_CFG_SPACE_SIZE; -} - -static void pci_release_bus_bridge_dev(struct device *dev) -{ - struct pci_host_bridge *bridge = to_pci_host_bridge(dev); - - if (bridge->release_fn) - bridge->release_fn(bridge); - - pci_free_resource_list(&bridge->windows); - - kfree(bridge); -} - -struct pci_dev *alloc_pci_dev(void) +struct pci_dev *pci_alloc_dev(struct pci_bus *bus) { struct pci_dev *dev; @@ -1198,13 +1272,15 @@ struct pci_dev *alloc_pci_dev(void) return NULL; INIT_LIST_HEAD(&dev->bus_list); + dev->dev.type = &pci_dev_type; + dev->bus = pci_bus_get(bus); return dev; } -EXPORT_SYMBOL(alloc_pci_dev); +EXPORT_SYMBOL(pci_alloc_dev); bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l, - int crs_timeout) + int crs_timeout) { int delay = 1; @@ -1227,10 +1303,9 @@ bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l, return false; /* Card hasn't responded in 60 seconds? Must be stuck. */ if (delay > crs_timeout) { - printk(KERN_WARNING "pci %04x:%02x:%02x.%d: not " - "responding\n", pci_domain_nr(bus), - bus->number, PCI_SLOT(devfn), - PCI_FUNC(devfn)); + printk(KERN_WARNING "pci %04x:%02x:%02x.%d: not responding\n", + pci_domain_nr(bus), bus->number, PCI_SLOT(devfn), + PCI_FUNC(devfn)); return false; } } @@ -1251,11 +1326,10 @@ static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn) if (!pci_bus_read_dev_vendor_id(bus, devfn, &l, 60*1000)) return NULL; - dev = alloc_pci_dev(); + dev = pci_alloc_dev(bus); if (!dev) return NULL; - dev->bus = bus; dev->devfn = devfn; dev->vendor = l & 0xffff; dev->device = (l >> 16) & 0xffff; @@ -1263,6 +1337,7 @@ static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn) pci_set_of_node(dev); if (pci_setup_device(dev)) { + pci_bus_put(dev->bus); kfree(dev); return NULL; } @@ -1280,13 +1355,12 @@ static void pci_init_capabilities(struct pci_dev *dev) /* Power Management */ pci_pm_init(dev); - platform_pci_wakeup_init(dev); /* Vital Product Data */ pci_vpd_pci22_init(dev); /* Alternative Routing-ID Forwarding */ - pci_enable_ari(dev); + pci_configure_ari(dev); /* Single Root I/O Virtualization */ pci_iov_init(dev); @@ -1297,10 +1371,12 @@ static void pci_init_capabilities(struct pci_dev *dev) void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) { + int ret; + device_initialize(&dev->dev); dev->dev.release = pci_release_dev; - pci_dev_get(dev); + set_dev_node(&dev->dev, pcibus_to_node(bus)); dev->dev.dma_mask = &dev->dma_mask; dev->dev.dma_parms = &dev->dma_parms; dev->dev.coherent_dma_mask = 0xffffffffull; @@ -1327,9 +1403,17 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) down_write(&pci_bus_sem); list_add_tail(&dev->bus_list, &bus->devices); up_write(&pci_bus_sem); + + ret = pcibios_add_device(dev); + WARN_ON(ret < 0); + + /* Notifier could use PCI capabilities */ + dev->match_driver = false; + ret = device_add(&dev->dev); + WARN_ON(ret < 0); } -struct pci_dev *__ref pci_scan_single_device(struct pci_bus *bus, int devfn) +struct pci_dev *pci_scan_single_device(struct pci_bus *bus, int devfn) { struct pci_dev *dev; @@ -1349,31 +1433,31 @@ struct pci_dev *__ref pci_scan_single_device(struct pci_bus *bus, int devfn) } EXPORT_SYMBOL(pci_scan_single_device); -static unsigned next_ari_fn(struct pci_dev *dev, unsigned fn) +static unsigned next_fn(struct pci_bus *bus, struct pci_dev *dev, unsigned fn) { - u16 cap; - unsigned pos, next_fn; + int pos; + u16 cap = 0; + unsigned next_fn; - if (!dev) - return 0; + if (pci_ari_enabled(bus)) { + if (!dev) + return 0; + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ARI); + if (!pos) + return 0; - pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ARI); - if (!pos) - return 0; - pci_read_config_word(dev, pos + 4, &cap); - next_fn = cap >> 8; - if (next_fn <= fn) - return 0; - return next_fn; -} + pci_read_config_word(dev, pos + PCI_ARI_CAP, &cap); + next_fn = PCI_ARI_CAP_NFN(cap); + if (next_fn <= fn) + return 0; /* protect against malformed list */ -static unsigned next_trad_fn(struct pci_dev *dev, unsigned fn) -{ - return (fn + 1) % 8; -} + return next_fn; + } + + /* dev may be NULL for non-contiguous multifunction devices */ + if (!dev || dev->multifunction) + return (fn + 1) % 8; -static unsigned no_next_fn(struct pci_dev *dev, unsigned fn) -{ return 0; } @@ -1406,7 +1490,6 @@ int pci_scan_slot(struct pci_bus *bus, int devfn) { unsigned fn, nr = 0; struct pci_dev *dev; - unsigned (*next_fn)(struct pci_dev *, unsigned) = no_next_fn; if (only_one_child(bus) && (devfn > 0)) return 0; /* Already scanned the entire slot */ @@ -1417,12 +1500,7 @@ int pci_scan_slot(struct pci_bus *bus, int devfn) if (!dev->is_added) nr++; - if (pci_ari_enabled(bus)) - next_fn = next_ari_fn; - else if (dev->multifunction) - next_fn = next_trad_fn; - - for (fn = next_fn(dev, 0); fn > 0; fn = next_fn(dev, fn)) { + for (fn = next_fn(bus, dev, 0); fn > 0; fn = next_fn(bus, dev, fn)) { dev = pci_scan_single_device(bus, devfn + fn); if (dev) { if (!dev->is_added) @@ -1437,6 +1515,7 @@ int pci_scan_slot(struct pci_bus *bus, int devfn) return nr; } +EXPORT_SYMBOL(pci_scan_slot); static int pcie_find_smpss(struct pci_dev *dev, void *data) { @@ -1445,24 +1524,23 @@ static int pcie_find_smpss(struct pci_dev *dev, void *data) if (!pci_is_pcie(dev)) return 0; - /* For PCIE hotplug enabled slots not connected directly to a - * PCI-E root port, there can be problems when hotplugging - * devices. This is due to the possibility of hotplugging a - * device into the fabric with a smaller MPS that the devices - * currently running have configured. Modifying the MPS on the - * running devices could cause a fatal bus error due to an - * incoming frame being larger than the newly configured MPS. - * To work around this, the MPS for the entire fabric must be - * set to the minimum size. Any devices hotplugged into this - * fabric will have the minimum MPS set. If the PCI hotplug - * slot is directly connected to the root port and there are not - * other devices on the fabric (which seems to be the most - * common case), then this is not an issue and MPS discovery - * will occur as normal. + /* + * We don't have a way to change MPS settings on devices that have + * drivers attached. A hot-added device might support only the minimum + * MPS setting (MPS=128). Therefore, if the fabric contains a bridge + * where devices may be hot-added, we limit the fabric MPS to 128 so + * hot-added devices will work correctly. + * + * However, if we hot-add a device to a slot directly below a Root + * Port, it's impossible for there to be other existing devices below + * the port. We don't limit the MPS in this case because we can + * reconfigure MPS on both the Root Port and the hot-added device, + * and there are no other devices involved. + * + * Note that this PCIE_BUS_SAFE path assumes no peer-to-peer DMA. */ - if (dev->is_hotplug_bridge && (!list_is_singular(&dev->bus->devices) || - (dev->bus->self && - pci_pcie_type(dev->bus->self) != PCI_EXP_TYPE_ROOT_PORT))) + if (dev->is_hotplug_bridge && + pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT) *smpss = 0; if (*smpss > dev->pcie_mpss) @@ -1521,7 +1599,7 @@ static void pcie_write_mrrs(struct pci_dev *dev) * subsequent read will verify if the value is acceptable or not. * If the MRRS value provided is not acceptable (e.g., too large), * shrink the value until it is acceptable to the HW. - */ + */ while (mrrs != pcie_get_readrq(dev) && mrrs >= 128) { rc = pcie_set_readrq(dev, mrrs); if (!rc) @@ -1532,9 +1610,23 @@ static void pcie_write_mrrs(struct pci_dev *dev) } if (mrrs < 128) - dev_err(&dev->dev, "MRRS was unable to be configured with a " - "safe value. If problems are experienced, try running " - "with pci=pcie_bus_safe.\n"); + dev_err(&dev->dev, "MRRS was unable to be configured with a safe value. If problems are experienced, try running with pci=pcie_bus_safe\n"); +} + +static void pcie_bus_detect_mps(struct pci_dev *dev) +{ + struct pci_dev *bridge = dev->bus->self; + int mps, p_mps; + + if (!bridge) + return; + + mps = pcie_get_mps(dev); + p_mps = pcie_get_mps(bridge); + + if (mps != p_mps) + dev_warn(&dev->dev, "Max Payload Size %d, but upstream %s set to %d; if necessary, use \"pci=pcie_bus_safe\" and report a bug\n", + mps, pci_name(bridge), p_mps); } static int pcie_bus_configure_set(struct pci_dev *dev, void *data) @@ -1544,14 +1636,19 @@ static int pcie_bus_configure_set(struct pci_dev *dev, void *data) if (!pci_is_pcie(dev)) return 0; + if (pcie_bus_config == PCIE_BUS_TUNE_OFF) { + pcie_bus_detect_mps(dev); + return 0; + } + mps = 128 << *(u8 *)data; orig_mps = pcie_get_mps(dev); pcie_write_mps(dev, mps); pcie_write_mrrs(dev); - dev_info(&dev->dev, "PCI-E Max Payload Size set to %4d/%4d (was %4d), " - "Max Read Rq %4d\n", pcie_get_mps(dev), 128 << dev->pcie_mpss, + dev_info(&dev->dev, "Max Payload Size set to %4d/%4d (was %4d), Max Read Rq %4d\n", + pcie_get_mps(dev), 128 << dev->pcie_mpss, orig_mps, pcie_get_readrq(dev)); return 0; @@ -1561,25 +1658,25 @@ static int pcie_bus_configure_set(struct pci_dev *dev, void *data) * parents then children fashion. If this changes, then this code will not * work as designed. */ -void pcie_bus_configure_settings(struct pci_bus *bus, u8 mpss) +void pcie_bus_configure_settings(struct pci_bus *bus) { - u8 smpss; + u8 smpss = 0; - if (!pci_is_pcie(bus->self)) + if (!bus->self) return; - if (pcie_bus_config == PCIE_BUS_TUNE_OFF) + if (!pci_is_pcie(bus->self)) return; /* FIXME - Peer to peer DMA is possible, though the endpoint would need - * to be aware to the MPS of the destination. To work around this, + * to be aware of the MPS of the destination. To work around this, * simply force the MPS of the entire system to the smallest possible. */ if (pcie_bus_config == PCIE_BUS_PEER2PEER) smpss = 0; if (pcie_bus_config == PCIE_BUS_SAFE) { - smpss = mpss; + smpss = bus->self->pcie_mpss; pcie_find_smpss(bus->self, &smpss); pci_walk_bus(bus, pcie_find_smpss, &smpss); @@ -1611,14 +1708,12 @@ unsigned int pci_scan_child_bus(struct pci_bus *bus) if (!bus->is_added) { dev_dbg(&bus->dev, "fixups for bus\n"); pcibios_fixup_bus(bus); - if (pci_is_root_bus(bus)) - bus->is_added = 1; + bus->is_added = 1; } - for (pass=0; pass < 2; pass++) + for (pass = 0; pass < 2; pass++) list_for_each_entry(dev, &bus->devices, bus_list) { - if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || - dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) + if (pci_is_bridge(dev)) max = pci_scan_bridge(bus, dev, max, pass); } @@ -1632,6 +1727,27 @@ unsigned int pci_scan_child_bus(struct pci_bus *bus) dev_dbg(&bus->dev, "bus scan returning with max=%02x\n", max); return max; } +EXPORT_SYMBOL_GPL(pci_scan_child_bus); + +/** + * pcibios_root_bridge_prepare - Platform-specific host bridge setup. + * @bridge: Host bridge to set up. + * + * Default empty implementation. Replace with an architecture-specific setup + * routine, if necessary. + */ +int __weak pcibios_root_bridge_prepare(struct pci_host_bridge *bridge) +{ + return 0; +} + +void __weak pcibios_add_bus(struct pci_bus *bus) +{ +} + +void __weak pcibios_remove_bus(struct pci_bus *bus) +{ +} struct pci_bus *pci_create_root_bus(struct device *parent, int bus, struct pci_ops *ops, void *sysdata, struct list_head *resources) @@ -1645,13 +1761,13 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus, char bus_addr[64]; char *fmt; - b = pci_alloc_bus(); if (!b) return NULL; b->sysdata = sysdata; b->ops = ops; + b->number = b->busn_res.start = bus; b2 = pci_find_bus(pci_domain_nr(b), bus); if (b2) { /* If we already got to this bus through a different bridge, ignore it */ @@ -1664,11 +1780,19 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus, goto err_out; bridge->dev.parent = parent; - bridge->dev.release = pci_release_bus_bridge_dev; + bridge->dev.release = pci_release_host_bridge_dev; dev_set_name(&bridge->dev, "pci%04x:%02x", pci_domain_nr(b), bus); + error = pcibios_root_bridge_prepare(bridge); + if (error) { + kfree(bridge); + goto err_out; + } + error = device_register(&bridge->dev); - if (error) - goto bridge_dev_reg_err; + if (error) { + put_device(&bridge->dev); + goto err_out; + } b->bridge = get_device(&bridge->dev); device_enable_async_suspend(b->bridge); pci_set_bus_of_node(b); @@ -1683,11 +1807,11 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus, if (error) goto class_dev_reg_err; + pcibios_add_bus(b); + /* Create legacy_io and legacy_mem files for this bus */ pci_create_legacy_files(b); - b->number = b->busn_res.start = bus; - if (parent) dev_info(parent, "PCI host bridge to bus %s\n", dev_name(&b->dev)); else @@ -1724,8 +1848,6 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus, class_dev_reg_err: put_device(&bridge->dev); device_unregister(&bridge->dev); -bridge_dev_reg_err: - kfree(bridge); err_out: kfree(b); return NULL; @@ -1747,7 +1869,7 @@ int pci_bus_insert_busn_res(struct pci_bus *b, int bus, int bus_max) res->flags |= IORESOURCE_PCI_FIXED; } - conflict = insert_resource_conflict(parent_res, res); + conflict = request_resource_conflict(parent_res, res); if (conflict) dev_printk(KERN_DEBUG, &b->dev, @@ -1879,7 +2001,7 @@ EXPORT_SYMBOL(pci_scan_bus); * * Returns the max number of subordinate bus discovered. */ -unsigned int __ref pci_rescan_bus_bridge_resize(struct pci_dev *bridge) +unsigned int pci_rescan_bus_bridge_resize(struct pci_dev *bridge) { unsigned int max; struct pci_bus *bus = bridge->subordinate; @@ -1902,25 +2024,38 @@ unsigned int __ref pci_rescan_bus_bridge_resize(struct pci_dev *bridge) * * Returns the max number of subordinate bus discovered. */ -unsigned int __ref pci_rescan_bus(struct pci_bus *bus) +unsigned int pci_rescan_bus(struct pci_bus *bus) { unsigned int max; max = pci_scan_child_bus(bus); pci_assign_unassigned_bus_resources(bus); - pci_enable_bridges(bus); pci_bus_add_devices(bus); return max; } EXPORT_SYMBOL_GPL(pci_rescan_bus); -EXPORT_SYMBOL(pci_add_new_bus); -EXPORT_SYMBOL(pci_scan_slot); -EXPORT_SYMBOL(pci_scan_bridge); -EXPORT_SYMBOL_GPL(pci_scan_child_bus); +/* + * pci_rescan_bus(), pci_rescan_bus_bridge_resize() and PCI device removal + * routines should always be executed under this mutex. + */ +static DEFINE_MUTEX(pci_rescan_remove_lock); + +void pci_lock_rescan_remove(void) +{ + mutex_lock(&pci_rescan_remove_lock); +} +EXPORT_SYMBOL_GPL(pci_lock_rescan_remove); + +void pci_unlock_rescan_remove(void) +{ + mutex_unlock(&pci_rescan_remove_lock); +} +EXPORT_SYMBOL_GPL(pci_unlock_rescan_remove); -static int __init pci_sort_bf_cmp(const struct device *d_a, const struct device *d_b) +static int __init pci_sort_bf_cmp(const struct device *d_a, + const struct device *d_b) { const struct pci_dev *a = to_pci_dev(d_a); const struct pci_dev *b = to_pci_dev(d_b); |