diff options
Diffstat (limited to 'drivers/pci')
50 files changed, 2192 insertions, 2099 deletions
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile index 1ebd6b4c743..4a7f11d8f43 100644 --- a/drivers/pci/Makefile +++ b/drivers/pci/Makefile @@ -8,6 +8,9 @@ obj-y += access.o bus.o probe.o remove.o pci.o quirks.o \ obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_SYSFS) += slot.o +obj-$(CONFIG_PCI_LEGACY) += legacy.o +CFLAGS_legacy.o += -Wno-deprecated-declarations + # Build PCI Express stuff if needed obj-$(CONFIG_PCIEPORTBUS) += pcie/ diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c index 7b287cb38b7..14bbaa17e2c 100644 --- a/drivers/pci/dmar.c +++ b/drivers/pci/dmar.c @@ -33,9 +33,10 @@ #include <linux/timer.h> #include <linux/irq.h> #include <linux/interrupt.h> +#include <linux/tboot.h> +#include <linux/dmi.h> -#undef PREFIX -#define PREFIX "DMAR:" +#define PREFIX "DMAR: " /* No locks are needed as DMA remapping hardware unit * list is constructed at boot time and hotplug of @@ -413,6 +414,12 @@ parse_dmar_table(void) */ dmar_table_detect(); + /* + * ACPI tables may not be DMA protected by tboot, so use DMAR copy + * SINIT saved in SinitMleData in TXT heap (which is DMA protected) + */ + dmar_tbl = tboot_get_dmar_table(dmar_tbl); + dmar = (struct acpi_table_dmar *)dmar_tbl; if (!dmar) return -ENODEV; @@ -570,9 +577,6 @@ int __init dmar_table_init(void) printk(KERN_INFO PREFIX "No ATSR found\n"); #endif -#ifdef CONFIG_INTR_REMAP - parse_ioapics_under_ir(); -#endif return 0; } @@ -632,20 +636,31 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG); iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG); + if (iommu->cap == (uint64_t)-1 && iommu->ecap == (uint64_t)-1) { + /* Promote an attitude of violence to a BIOS engineer today */ + WARN(1, "Your BIOS is broken; DMAR reported at address %llx returns all ones!\n" + "BIOS vendor: %s; Ver: %s; Product Version: %s\n", + drhd->reg_base_addr, + dmi_get_system_info(DMI_BIOS_VENDOR), + dmi_get_system_info(DMI_BIOS_VERSION), + dmi_get_system_info(DMI_PRODUCT_VERSION)); + goto err_unmap; + } + #ifdef CONFIG_DMAR agaw = iommu_calculate_agaw(iommu); if (agaw < 0) { printk(KERN_ERR "Cannot get a valid agaw for iommu (seq_id = %d)\n", iommu->seq_id); - goto error; + goto err_unmap; } msagaw = iommu_calculate_max_sagaw(iommu); if (msagaw < 0) { printk(KERN_ERR "Cannot get a valid max agaw for iommu (seq_id = %d)\n", iommu->seq_id); - goto error; + goto err_unmap; } #endif iommu->agaw = agaw; @@ -665,7 +680,7 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) } ver = readl(iommu->reg + DMAR_VER_REG); - pr_debug("IOMMU %llx: ver %d:%d cap %llx ecap %llx\n", + pr_info("IOMMU %llx: ver %d:%d cap %llx ecap %llx\n", (unsigned long long)drhd->reg_base_addr, DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver), (unsigned long long)iommu->cap, @@ -675,7 +690,10 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) drhd->iommu = iommu; return 0; -error: + + err_unmap: + iounmap(iommu->reg); + error: kfree(iommu); return -1; } @@ -1212,7 +1230,7 @@ irqreturn_t dmar_fault(int irq, void *dev_id) source_id, guest_addr); fault_index++; - if (fault_index > cap_num_fault_regs(iommu->cap)) + if (fault_index >= cap_num_fault_regs(iommu->cap)) fault_index = 0; spin_lock_irqsave(&iommu->register_lock, flag); } @@ -1305,3 +1323,13 @@ int dmar_reenable_qi(struct intel_iommu *iommu) return 0; } + +/* + * Check interrupt remapping support in DMAR table description. + */ +int dmar_ir_support(void) +{ + struct acpi_table_dmar *dmar; + dmar = (struct acpi_table_dmar *)dmar_tbl; + return dmar->flags & 0x1; +} diff --git a/drivers/pci/hotplug/Makefile b/drivers/pci/hotplug/Makefile index 2aa117c8cd8..3625b094bf7 100644 --- a/drivers/pci/hotplug/Makefile +++ b/drivers/pci/hotplug/Makefile @@ -22,7 +22,7 @@ obj-$(CONFIG_HOTPLUG_PCI_SGI) += sgi_hotplug.o # Link this last so it doesn't claim devices that have a real hotplug driver obj-$(CONFIG_HOTPLUG_PCI_FAKE) += fakephp.o -pci_hotplug-objs := pci_hotplug_core.o +pci_hotplug-objs := pci_hotplug_core.o pcihp_slot.o ifdef CONFIG_HOTPLUG_PCI_CPCI pci_hotplug-objs += cpci_hotplug_core.o \ diff --git a/drivers/pci/hotplug/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c index eb159587d0b..a73028ec52e 100644 --- a/drivers/pci/hotplug/acpi_pcihp.c +++ b/drivers/pci/hotplug/acpi_pcihp.c @@ -41,7 +41,6 @@ #define warn(format, arg...) printk(KERN_WARNING "%s: " format , MY_NAME , ## arg) #define METHOD_NAME__SUN "_SUN" -#define METHOD_NAME__HPP "_HPP" #define METHOD_NAME_OSHP "OSHP" static int debug_acpi; @@ -215,80 +214,41 @@ acpi_run_hpx(acpi_handle handle, struct hotplug_params *hpx) static acpi_status acpi_run_hpp(acpi_handle handle, struct hotplug_params *hpp) { - acpi_status status; - u8 nui[4]; - struct acpi_buffer ret_buf = { 0, NULL}; - struct acpi_buffer string = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *ext_obj, *package; - int i, len = 0; - - acpi_get_name(handle, ACPI_FULL_PATHNAME, &string); + acpi_status status; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + union acpi_object *package, *fields; + int i; - /* Clear the return buffer with zeros */ memset(hpp, 0, sizeof(struct hotplug_params)); - /* get _hpp */ - status = acpi_evaluate_object(handle, METHOD_NAME__HPP, NULL, &ret_buf); - switch (status) { - case AE_BUFFER_OVERFLOW: - ret_buf.pointer = kmalloc (ret_buf.length, GFP_KERNEL); - if (!ret_buf.pointer) { - printk(KERN_ERR "%s:%s alloc for _HPP fail\n", - __func__, (char *)string.pointer); - kfree(string.pointer); - return AE_NO_MEMORY; - } - status = acpi_evaluate_object(handle, METHOD_NAME__HPP, - NULL, &ret_buf); - if (ACPI_SUCCESS(status)) - break; - default: - if (ACPI_FAILURE(status)) { - pr_debug("%s:%s _HPP fail=0x%x\n", __func__, - (char *)string.pointer, status); - kfree(string.pointer); - return status; - } - } + status = acpi_evaluate_object(handle, "_HPP", NULL, &buffer); + if (ACPI_FAILURE(status)) + return status; - ext_obj = (union acpi_object *) ret_buf.pointer; - if (ext_obj->type != ACPI_TYPE_PACKAGE) { - printk(KERN_ERR "%s:%s _HPP obj not a package\n", __func__, - (char *)string.pointer); + package = (union acpi_object *) buffer.pointer; + if (package->type != ACPI_TYPE_PACKAGE || + package->package.count != 4) { status = AE_ERROR; - goto free_and_return; + goto exit; } - len = ext_obj->package.count; - package = (union acpi_object *) ret_buf.pointer; - for ( i = 0; (i < len) || (i < 4); i++) { - ext_obj = (union acpi_object *) &package->package.elements[i]; - switch (ext_obj->type) { - case ACPI_TYPE_INTEGER: - nui[i] = (u8)ext_obj->integer.value; - break; - default: - printk(KERN_ERR "%s:%s _HPP obj type incorrect\n", - __func__, (char *)string.pointer); + fields = package->package.elements; + for (i = 0; i < 4; i++) { + if (fields[i].type != ACPI_TYPE_INTEGER) { status = AE_ERROR; - goto free_and_return; + goto exit; } } hpp->t0 = &hpp->type0_data; - hpp->t0->cache_line_size = nui[0]; - hpp->t0->latency_timer = nui[1]; - hpp->t0->enable_serr = nui[2]; - hpp->t0->enable_perr = nui[3]; - - pr_debug(" _HPP: cache_line_size=0x%x\n", hpp->t0->cache_line_size); - pr_debug(" _HPP: latency timer =0x%x\n", hpp->t0->latency_timer); - pr_debug(" _HPP: enable SERR =0x%x\n", hpp->t0->enable_serr); - pr_debug(" _HPP: enable PERR =0x%x\n", hpp->t0->enable_perr); + hpp->t0->revision = 1; + hpp->t0->cache_line_size = fields[0].integer.value; + hpp->t0->latency_timer = fields[1].integer.value; + hpp->t0->enable_serr = fields[2].integer.value; + hpp->t0->enable_perr = fields[3].integer.value; -free_and_return: - kfree(string.pointer); - kfree(ret_buf.pointer); +exit: + kfree(buffer.pointer); return status; } @@ -322,20 +282,19 @@ static acpi_status acpi_run_oshp(acpi_handle handle) return status; } -/* acpi_get_hp_params_from_firmware +/* pci_get_hp_params * - * @bus - the pci_bus of the bus on which the device is newly added + * @dev - the pci_dev for which we want parameters * @hpp - allocated by the caller */ -acpi_status acpi_get_hp_params_from_firmware(struct pci_bus *bus, - struct hotplug_params *hpp) +int pci_get_hp_params(struct pci_dev *dev, struct hotplug_params *hpp) { - acpi_status status = AE_NOT_FOUND; + acpi_status status; acpi_handle handle, phandle; struct pci_bus *pbus; handle = NULL; - for (pbus = bus; pbus; pbus = pbus->parent) { + for (pbus = dev->bus; pbus; pbus = pbus->parent) { handle = acpi_pci_get_bridge_handle(pbus); if (handle) break; @@ -345,15 +304,15 @@ acpi_status acpi_get_hp_params_from_firmware(struct pci_bus *bus, * _HPP settings apply to all child buses, until another _HPP is * encountered. If we don't find an _HPP for the input pci dev, * look for it in the parent device scope since that would apply to - * this pci dev. If we don't find any _HPP, use hardcoded defaults + * this pci dev. */ while (handle) { status = acpi_run_hpx(handle, hpp); if (ACPI_SUCCESS(status)) - break; + return 0; status = acpi_run_hpp(handle, hpp); if (ACPI_SUCCESS(status)) - break; + return 0; if (acpi_is_root_bridge(handle)) break; status = acpi_get_parent(handle, &phandle); @@ -361,9 +320,9 @@ acpi_status acpi_get_hp_params_from_firmware(struct pci_bus *bus, break; handle = phandle; } - return status; + return -ENODEV; } -EXPORT_SYMBOL_GPL(acpi_get_hp_params_from_firmware); +EXPORT_SYMBOL_GPL(pci_get_hp_params); /** * acpi_get_hp_hw_control_from_firmware @@ -500,18 +459,18 @@ check_hotplug(acpi_handle handle, u32 lvl, void *context, void **rv) /** * acpi_pci_detect_ejectable - check if the PCI bus has ejectable slots - * @pbus - PCI bus to scan + * @handle - handle of the PCI bus to scan * * Returns 1 if the PCI bus has ACPI based ejectable slots, 0 otherwise. */ -int acpi_pci_detect_ejectable(struct pci_bus *pbus) +int acpi_pci_detect_ejectable(acpi_handle handle) { - acpi_handle handle; int found = 0; - if (!(handle = acpi_pci_get_bridge_handle(pbus))) - return 0; - acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1, + if (!handle) + return found; + + acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1, check_hotplug, (void *)&found, NULL); return found; } diff --git a/drivers/pci/hotplug/acpiphp.h b/drivers/pci/hotplug/acpiphp.h index e68d5f20ffb..7d938df7920 100644 --- a/drivers/pci/hotplug/acpiphp.h +++ b/drivers/pci/hotplug/acpiphp.h @@ -91,9 +91,6 @@ struct acpiphp_bridge { /* PCI-to-PCI bridge device */ struct pci_dev *pci_dev; - /* ACPI 2.0 _HPP parameters */ - struct hotplug_params hpp; - spinlock_t res_lock; }; diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 0cb0f830a99..58d25a163a8 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -59,7 +59,7 @@ static DEFINE_SPINLOCK(ioapic_list_lock); static void handle_hotplug_event_bridge (acpi_handle, u32, void *); static void acpiphp_sanitize_bus(struct pci_bus *bus); -static void acpiphp_set_hpp_values(acpi_handle handle, struct pci_bus *bus); +static void acpiphp_set_hpp_values(struct pci_bus *bus); static void handle_hotplug_event_func(acpi_handle handle, u32 type, void *context); /* callback routine to check for the existence of a pci dock device */ @@ -261,51 +261,21 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv) /* see if it's worth looking at this bridge */ -static int detect_ejectable_slots(struct pci_bus *pbus) +static int detect_ejectable_slots(acpi_handle handle) { - int found = acpi_pci_detect_ejectable(pbus); + int found = acpi_pci_detect_ejectable(handle); if (!found) { - acpi_handle bridge_handle = acpi_pci_get_bridge_handle(pbus); - if (!bridge_handle) - return 0; - acpi_walk_namespace(ACPI_TYPE_DEVICE, bridge_handle, (u32)1, + acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1, is_pci_dock_device, (void *)&found, NULL); } return found; } - -/* decode ACPI 2.0 _HPP hot plug parameters */ -static void decode_hpp(struct acpiphp_bridge *bridge) -{ - acpi_status status; - - status = acpi_get_hp_params_from_firmware(bridge->pci_bus, &bridge->hpp); - if (ACPI_FAILURE(status) || - !bridge->hpp.t0 || (bridge->hpp.t0->revision > 1)) { - /* use default numbers */ - printk(KERN_WARNING - "%s: Could not get hotplug parameters. Use defaults\n", - __func__); - bridge->hpp.t0 = &bridge->hpp.type0_data; - bridge->hpp.t0->revision = 0; - bridge->hpp.t0->cache_line_size = 0x10; - bridge->hpp.t0->latency_timer = 0x40; - bridge->hpp.t0->enable_serr = 0; - bridge->hpp.t0->enable_perr = 0; - } -} - - - /* initialize miscellaneous stuff for both root and PCI-to-PCI bridge */ static void init_bridge_misc(struct acpiphp_bridge *bridge) { acpi_status status; - /* decode ACPI 2.0 _HPP (hot plug parameters) */ - decode_hpp(bridge); - /* must be added to the list prior to calling register_slot */ list_add(&bridge->list, &bridge_list); @@ -399,9 +369,10 @@ static inline void config_p2p_bridge_flags(struct acpiphp_bridge *bridge) /* allocate and initialize host bridge data structure */ -static void add_host_bridge(acpi_handle *handle, struct pci_bus *pci_bus) +static void add_host_bridge(acpi_handle *handle) { struct acpiphp_bridge *bridge; + struct acpi_pci_root *root = acpi_pci_find_root(handle); bridge = kzalloc(sizeof(struct acpiphp_bridge), GFP_KERNEL); if (bridge == NULL) @@ -410,7 +381,7 @@ static void add_host_bridge(acpi_handle *handle, struct pci_bus *pci_bus) bridge->type = BRIDGE_TYPE_HOST; bridge->handle = handle; - bridge->pci_bus = pci_bus; + bridge->pci_bus = root->bus; spin_lock_init(&bridge->res_lock); @@ -419,7 +390,7 @@ static void add_host_bridge(acpi_handle *handle, struct pci_bus *pci_bus) /* allocate and initialize PCI-to-PCI bridge data structure */ -static void add_p2p_bridge(acpi_handle *handle, struct pci_dev *pci_dev) +static void add_p2p_bridge(acpi_handle *handle) { struct acpiphp_bridge *bridge; @@ -433,8 +404,8 @@ static void add_p2p_bridge(acpi_handle *handle, struct pci_dev *pci_dev) bridge->handle = handle; config_p2p_bridge_flags(bridge); - bridge->pci_dev = pci_dev_get(pci_dev); - bridge->pci_bus = pci_dev->subordinate; + bridge->pci_dev = acpi_get_pci_dev(handle); + bridge->pci_bus = bridge->pci_dev->subordinate; if (!bridge->pci_bus) { err("This is not a PCI-to-PCI bridge!\n"); goto err; @@ -451,7 +422,7 @@ static void add_p2p_bridge(acpi_handle *handle, struct pci_dev *pci_dev) init_bridge_misc(bridge); return; err: - pci_dev_put(pci_dev); + pci_dev_put(bridge->pci_dev); kfree(bridge); return; } @@ -462,39 +433,21 @@ static acpi_status find_p2p_bridge(acpi_handle handle, u32 lvl, void *context, void **rv) { acpi_status status; - acpi_handle dummy_handle; - unsigned long long tmp; - int device, function; struct pci_dev *dev; - struct pci_bus *pci_bus = context; - - status = acpi_get_handle(handle, "_ADR", &dummy_handle); - if (ACPI_FAILURE(status)) - return AE_OK; /* continue */ - - status = acpi_evaluate_integer(handle, "_ADR", NULL, &tmp); - if (ACPI_FAILURE(status)) { - dbg("%s: _ADR evaluation failure\n", __func__); - return AE_OK; - } - - device = (tmp >> 16) & 0xffff; - function = tmp & 0xffff; - - dev = pci_get_slot(pci_bus, PCI_DEVFN(device, function)); + dev = acpi_get_pci_dev(handle); if (!dev || !dev->subordinate) goto out; /* check if this bridge has ejectable slots */ - if ((detect_ejectable_slots(dev->subordinate) > 0)) { + if ((detect_ejectable_slots(handle) > 0)) { dbg("found PCI-to-PCI bridge at PCI %s\n", pci_name(dev)); - add_p2p_bridge(handle, dev); + add_p2p_bridge(handle); } /* search P2P bridges under this p2p bridge */ status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1, - find_p2p_bridge, dev->subordinate, NULL); + find_p2p_bridge, NULL, NULL); if (ACPI_FAILURE(status)) warn("find_p2p_bridge failed (error code = 0x%x)\n", status); @@ -509,9 +462,7 @@ static int add_bridge(acpi_handle handle) { acpi_status status; unsigned long long tmp; - int seg, bus; acpi_handle dummy_handle; - struct pci_bus *pci_bus; /* if the bridge doesn't have _STA, we assume it is always there */ status = acpi_get_handle(handle, "_STA", &dummy_handle); @@ -526,36 +477,15 @@ static int add_bridge(acpi_handle handle) return 0; } - /* get PCI segment number */ - status = acpi_evaluate_integer(handle, "_SEG", NULL, &tmp); - - seg = ACPI_SUCCESS(status) ? tmp : 0; - - /* get PCI bus number */ - status = acpi_evaluate_integer(handle, "_BBN", NULL, &tmp); - - if (ACPI_SUCCESS(status)) { - bus = tmp; - } else { - warn("can't get bus number, assuming 0\n"); - bus = 0; - } - - pci_bus = pci_find_bus(seg, bus); - if (!pci_bus) { - err("Can't find bus %04x:%02x\n", seg, bus); - return 0; - } - /* check if this bridge has ejectable slots */ - if (detect_ejectable_slots(pci_bus) > 0) { + if (detect_ejectable_slots(handle) > 0) { dbg("found PCI host-bus bridge with hot-pluggable slots\n"); - add_host_bridge(handle, pci_bus); + add_host_bridge(handle); } /* search P2P bridges under this host bridge */ status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1, - find_p2p_bridge, pci_bus, NULL); + find_p2p_bridge, NULL, NULL); if (ACPI_FAILURE(status)) warn("find_p2p_bridge failed (error code = 0x%x)\n", status); @@ -1083,7 +1013,7 @@ static int __ref enable_device(struct acpiphp_slot *slot) pci_bus_assign_resources(bus); acpiphp_sanitize_bus(bus); - acpiphp_set_hpp_values(slot->bridge->handle, bus); + acpiphp_set_hpp_values(bus); list_for_each_entry(func, &slot->funcs, sibling) acpiphp_configure_ioapics(func->handle); pci_enable_bridges(bus); @@ -1294,70 +1224,12 @@ static int acpiphp_check_bridge(struct acpiphp_bridge *bridge) return retval; } -static void program_hpp(struct pci_dev *dev, struct acpiphp_bridge *bridge) +static void acpiphp_set_hpp_values(struct pci_bus *bus) { - u16 pci_cmd, pci_bctl; - struct pci_dev *cdev; - - /* Program hpp values for this device */ - if (!(dev->hdr_type == PCI_HEADER_TYPE_NORMAL || - (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE && - (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI))) - return; - - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_HOST) - return; - - pci_write_config_byte(dev, PCI_CACHE_LINE_SIZE, - bridge->hpp.t0->cache_line_size); - pci_write_config_byte(dev, PCI_LATENCY_TIMER, - bridge->hpp.t0->latency_timer); - pci_read_config_word(dev, PCI_COMMAND, &pci_cmd); - if (bridge->hpp.t0->enable_serr) - pci_cmd |= PCI_COMMAND_SERR; - else - pci_cmd &= ~PCI_COMMAND_SERR; - if (bridge->hpp.t0->enable_perr) - pci_cmd |= PCI_COMMAND_PARITY; - else - pci_cmd &= ~PCI_COMMAND_PARITY; - pci_write_config_word(dev, PCI_COMMAND, pci_cmd); - - /* Program bridge control value and child devices */ - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) { - pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER, - bridge->hpp.t0->latency_timer); - pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &pci_bctl); - if (bridge->hpp.t0->enable_serr) - pci_bctl |= PCI_BRIDGE_CTL_SERR; - else - pci_bctl &= ~PCI_BRIDGE_CTL_SERR; - if (bridge->hpp.t0->enable_perr) - pci_bctl |= PCI_BRIDGE_CTL_PARITY; - else - pci_bctl &= ~PCI_BRIDGE_CTL_PARITY; - pci_write_config_word(dev, PCI_BRIDGE_CONTROL, pci_bctl); - if (dev->subordinate) { - list_for_each_entry(cdev, &dev->subordinate->devices, - bus_list) - program_hpp(cdev, bridge); - } - } -} - -static void acpiphp_set_hpp_values(acpi_handle handle, struct pci_bus *bus) -{ - struct acpiphp_bridge bridge; struct pci_dev *dev; - memset(&bridge, 0, sizeof(bridge)); - bridge.handle = handle; - bridge.pci_bus = bus; - bridge.pci_dev = bus->self; - decode_hpp(&bridge); list_for_each_entry(dev, &bus->devices, bus_list) - program_hpp(dev, &bridge); - + pci_configure_slot(dev); } /* @@ -1387,24 +1259,23 @@ static void acpiphp_sanitize_bus(struct pci_bus *bus) /* Program resources in newly inserted bridge */ static int acpiphp_configure_bridge (acpi_handle handle) { - struct pci_dev *dev; struct pci_bus *bus; - dev = acpi_get_pci_dev(handle); - if (!dev) { - err("cannot get PCI domain and bus number for bridge\n"); - return -EINVAL; + if (acpi_is_root_bridge(handle)) { + struct acpi_pci_root *root = acpi_pci_find_root(handle); + bus = root->bus; + } else { + struct pci_dev *pdev = acpi_get_pci_dev(handle); + bus = pdev->subordinate; + pci_dev_put(pdev); } - bus = dev->bus; - pci_bus_size_bridges(bus); pci_bus_assign_resources(bus); acpiphp_sanitize_bus(bus); - acpiphp_set_hpp_values(handle, bus); + acpiphp_set_hpp_values(bus); pci_enable_bridges(bus); acpiphp_configure_ioapics(handle); - pci_dev_put(dev); return 0; } diff --git a/drivers/pci/hotplug/acpiphp_ibm.c b/drivers/pci/hotplug/acpiphp_ibm.c index 5befa7e379b..e7be66dbac2 100644 --- a/drivers/pci/hotplug/acpiphp_ibm.c +++ b/drivers/pci/hotplug/acpiphp_ibm.c @@ -398,23 +398,20 @@ static acpi_status __init ibm_find_acpi_device(acpi_handle handle, acpi_handle *phandle = (acpi_handle *)context; acpi_status status; struct acpi_device_info *info; - struct acpi_buffer info_buffer = { ACPI_ALLOCATE_BUFFER, NULL }; int retval = 0; - status = acpi_get_object_info(handle, &info_buffer); + status = acpi_get_object_info(handle, &info); if (ACPI_FAILURE(status)) { err("%s: Failed to get device information status=0x%x\n", __func__, status); return retval; } - info = info_buffer.pointer; - info->hardware_id.value[sizeof(info->hardware_id.value) - 1] = '\0'; if (info->current_status && (info->valid & ACPI_VALID_HID) && - (!strcmp(info->hardware_id.value, IBM_HARDWARE_ID1) || - !strcmp(info->hardware_id.value, IBM_HARDWARE_ID2))) { + (!strcmp(info->hardware_id.string, IBM_HARDWARE_ID1) || + !strcmp(info->hardware_id.string, IBM_HARDWARE_ID2))) { dbg("found hardware: %s, handle: %p\n", - info->hardware_id.value, handle); + info->hardware_id.string, handle); *phandle = handle; /* returning non-zero causes the search to stop * and returns this value to the caller of diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c index a5b9f6ae507..d703e73fffa 100644 --- a/drivers/pci/hotplug/cpci_hotplug_core.c +++ b/drivers/pci/hotplug/cpci_hotplug_core.c @@ -32,7 +32,6 @@ #include <linux/pci_hotplug.h> #include <linux/init.h> #include <linux/interrupt.h> -#include <linux/smp_lock.h> #include <asm/atomic.h> #include <linux/delay.h> #include <linux/kthread.h> diff --git a/drivers/pci/hotplug/cpqphp_ctrl.c b/drivers/pci/hotplug/cpqphp_ctrl.c index 2fa47af992a..0ff689afa75 100644 --- a/drivers/pci/hotplug/cpqphp_ctrl.c +++ b/drivers/pci/hotplug/cpqphp_ctrl.c @@ -34,7 +34,6 @@ #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/wait.h> -#include <linux/smp_lock.h> #include <linux/pci.h> #include <linux/pci_hotplug.h> #include <linux/kthread.h> diff --git a/drivers/pci/hotplug/cpqphp_sysfs.c b/drivers/pci/hotplug/cpqphp_sysfs.c index 8450f4a6568..e6089bdb6e5 100644 --- a/drivers/pci/hotplug/cpqphp_sysfs.c +++ b/drivers/pci/hotplug/cpqphp_sysfs.c @@ -33,6 +33,7 @@ #include <linux/workqueue.h> #include <linux/pci.h> #include <linux/pci_hotplug.h> +#include <linux/smp_lock.h> #include <linux/debugfs.h> #include "cpqphp.h" diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c index 844580489d4..0325d989bb4 100644 --- a/drivers/pci/hotplug/pci_hotplug_core.c +++ b/drivers/pci/hotplug/pci_hotplug_core.c @@ -86,7 +86,8 @@ static char *pci_bus_speed_strings[] = { "66 MHz PCIX 533", /* 0x11 */ "100 MHz PCIX 533", /* 0x12 */ "133 MHz PCIX 533", /* 0x13 */ - "25 GBps PCI-E", /* 0x14 */ + "2.5 GT/s PCI-E", /* 0x14 */ + "5.0 GT/s PCI-E", /* 0x15 */ }; #ifdef CONFIG_HOTPLUG_PCI_CPCI @@ -555,6 +556,8 @@ static struct hotplug_slot *get_slot_from_name (const char *name) * @slot: pointer to the &struct hotplug_slot to register * @devnr: device number * @name: name registered with kobject core + * @owner: caller module owner + * @mod_name: caller module name * * Registers a hotplug slot with the pci hotplug subsystem, which will allow * userspace interaction to the slot. diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h index e6cf096498b..3070f77eb56 100644 --- a/drivers/pci/hotplug/pciehp.h +++ b/drivers/pci/hotplug/pciehp.h @@ -72,15 +72,9 @@ do { \ #define SLOT_NAME_SIZE 10 struct slot { - u8 bus; - u8 device; u8 state; - u8 hp_slot; - u32 number; struct controller *ctrl; - struct hpc_ops *hpc_ops; struct hotplug_slot *hotplug_slot; - struct list_head slot_list; struct delayed_work work; /* work for button event */ struct mutex lock; }; @@ -92,18 +86,10 @@ struct event_info { }; struct controller { - struct mutex crit_sect; /* critical section mutex */ struct mutex ctrl_lock; /* controller lock */ - int num_slots; /* Number of slots on ctlr */ - int slot_num_inc; /* 1 or -1 */ - struct pci_dev *pci_dev; struct pcie_device *pcie; /* PCI Express port service */ - struct list_head slot_list; - struct hpc_ops *hpc_ops; + struct slot *slot; wait_queue_head_t queue; /* sleep & wake process */ - u8 slot_device_offset; - u32 first_slot; /* First physical slot number */ /* PCIE only has 1 slot */ - u8 slot_bus; /* Bus where the slots handled by this controller sit */ u32 slot_cap; u8 cap_base; struct timer_list poll_timer; @@ -131,40 +117,20 @@ struct controller { #define POWERON_STATE 3 #define POWEROFF_STATE 4 -/* Error messages */ -#define INTERLOCK_OPEN 0x00000002 -#define ADD_NOT_SUPPORTED 0x00000003 -#define CARD_FUNCTIONING 0x00000005 -#define ADAPTER_NOT_SAME 0x00000006 -#define NO_ADAPTER_PRESENT 0x00000009 -#define NOT_ENOUGH_RESOURCES 0x0000000B -#define DEVICE_TYPE_NOT_SUPPORTED 0x0000000C -#define WRONG_BUS_FREQUENCY 0x0000000D -#define POWER_FAILURE 0x0000000E - -/* Field definitions in Slot Capabilities Register */ -#define ATTN_BUTTN_PRSN 0x00000001 -#define PWR_CTRL_PRSN 0x00000002 -#define MRL_SENS_PRSN 0x00000004 -#define ATTN_LED_PRSN 0x00000008 -#define PWR_LED_PRSN 0x00000010 -#define HP_SUPR_RM_SUP 0x00000020 -#define EMI_PRSN 0x00020000 -#define NO_CMD_CMPL_SUP 0x00040000 - -#define ATTN_BUTTN(ctrl) ((ctrl)->slot_cap & ATTN_BUTTN_PRSN) -#define POWER_CTRL(ctrl) ((ctrl)->slot_cap & PWR_CTRL_PRSN) -#define MRL_SENS(ctrl) ((ctrl)->slot_cap & MRL_SENS_PRSN) -#define ATTN_LED(ctrl) ((ctrl)->slot_cap & ATTN_LED_PRSN) -#define PWR_LED(ctrl) ((ctrl)->slot_cap & PWR_LED_PRSN) -#define HP_SUPR_RM(ctrl) ((ctrl)->slot_cap & HP_SUPR_RM_SUP) -#define EMI(ctrl) ((ctrl)->slot_cap & EMI_PRSN) -#define NO_CMD_CMPL(ctrl) ((ctrl)->slot_cap & NO_CMD_CMPL_SUP) +#define ATTN_BUTTN(ctrl) ((ctrl)->slot_cap & PCI_EXP_SLTCAP_ABP) +#define POWER_CTRL(ctrl) ((ctrl)->slot_cap & PCI_EXP_SLTCAP_PCP) +#define MRL_SENS(ctrl) ((ctrl)->slot_cap & PCI_EXP_SLTCAP_MRLSP) +#define ATTN_LED(ctrl) ((ctrl)->slot_cap & PCI_EXP_SLTCAP_AIP) +#define PWR_LED(ctrl) ((ctrl)->slot_cap & PCI_EXP_SLTCAP_PIP) +#define HP_SUPR_RM(ctrl) ((ctrl)->slot_cap & PCI_EXP_SLTCAP_HPS) +#define EMI(ctrl) ((ctrl)->slot_cap & PCI_EXP_SLTCAP_EIP) +#define NO_CMD_CMPL(ctrl) ((ctrl)->slot_cap & PCI_EXP_SLTCAP_NCCS) +#define PSN(ctrl) ((ctrl)->slot_cap >> 19) extern int pciehp_sysfs_enable_slot(struct slot *slot); extern int pciehp_sysfs_disable_slot(struct slot *slot); extern u8 pciehp_handle_attention_button(struct slot *p_slot); - extern u8 pciehp_handle_switch_change(struct slot *p_slot); +extern u8 pciehp_handle_switch_change(struct slot *p_slot); extern u8 pciehp_handle_presence_change(struct slot *p_slot); extern u8 pciehp_handle_power_fault(struct slot *p_slot); extern int pciehp_configure_device(struct slot *p_slot); @@ -175,45 +141,30 @@ int pcie_init_notification(struct controller *ctrl); int pciehp_enable_slot(struct slot *p_slot); int pciehp_disable_slot(struct slot *p_slot); int pcie_enable_notification(struct controller *ctrl); +int pciehp_power_on_slot(struct slot *slot); +int pciehp_power_off_slot(struct slot *slot); +int pciehp_get_power_status(struct slot *slot, u8 *status); +int pciehp_get_attention_status(struct slot *slot, u8 *status); + +int pciehp_set_attention_status(struct slot *slot, u8 status); +int pciehp_get_latch_status(struct slot *slot, u8 *status); +int pciehp_get_adapter_status(struct slot *slot, u8 *status); +int pciehp_get_max_link_speed(struct slot *slot, enum pci_bus_speed *speed); +int pciehp_get_max_link_width(struct slot *slot, enum pcie_link_width *val); +int pciehp_get_cur_link_speed(struct slot *slot, enum pci_bus_speed *speed); +int pciehp_get_cur_link_width(struct slot *slot, enum pcie_link_width *val); +int pciehp_query_power_fault(struct slot *slot); +void pciehp_green_led_on(struct slot *slot); +void pciehp_green_led_off(struct slot *slot); +void pciehp_green_led_blink(struct slot *slot); +int pciehp_check_link_status(struct controller *ctrl); +void pciehp_release_ctrl(struct controller *ctrl); static inline const char *slot_name(struct slot *slot) { return hotplug_slot_name(slot->hotplug_slot); } -static inline struct slot *pciehp_find_slot(struct controller *ctrl, u8 device) -{ - struct slot *slot; - - list_for_each_entry(slot, &ctrl->slot_list, slot_list) { - if (slot->device == device) - return slot; - } - - ctrl_err(ctrl, "Slot (device=0x%02x) not found\n", device); - return NULL; -} - -struct hpc_ops { - int (*power_on_slot)(struct slot *slot); - int (*power_off_slot)(struct slot *slot); - int (*get_power_status)(struct slot *slot, u8 *status); - int (*get_attention_status)(struct slot *slot, u8 *status); - int (*set_attention_status)(struct slot *slot, u8 status); - int (*get_latch_status)(struct slot *slot, u8 *status); - int (*get_adapter_status)(struct slot *slot, u8 *status); - int (*get_max_bus_speed)(struct slot *slot, enum pci_bus_speed *speed); - int (*get_cur_bus_speed)(struct slot *slot, enum pci_bus_speed *speed); - int (*get_max_lnk_width)(struct slot *slot, enum pcie_link_width *val); - int (*get_cur_lnk_width)(struct slot *slot, enum pcie_link_width *val); - int (*query_power_fault)(struct slot *slot); - void (*green_led_on)(struct slot *slot); - void (*green_led_off)(struct slot *slot); - void (*green_led_blink)(struct slot *slot); - void (*release_ctlr)(struct controller *ctrl); - int (*check_lnk_status)(struct controller *ctrl); -}; - #ifdef CONFIG_ACPI #include <acpi/acpi.h> #include <acpi/acpi_bus.h> @@ -237,17 +188,8 @@ static inline int pciehp_get_hp_hw_control_from_firmware(struct pci_dev *dev) return retval; return pciehp_acpi_slot_detection_check(dev); } - -static inline int pciehp_get_hp_params_from_firmware(struct pci_dev *dev, - struct hotplug_params *hpp) -{ - if (ACPI_FAILURE(acpi_get_hp_params_from_firmware(dev->bus, hpp))) - return -ENODEV; - return 0; -} #else #define pciehp_firmware_init() do {} while (0) #define pciehp_get_hp_hw_control_from_firmware(dev) 0 -#define pciehp_get_hp_params_from_firmware(dev, hpp) (-ENODEV) #endif /* CONFIG_ACPI */ #endif /* _PCIEHP_H */ diff --git a/drivers/pci/hotplug/pciehp_acpi.c b/drivers/pci/hotplug/pciehp_acpi.c index 96048010e7d..37c8d3d0323 100644 --- a/drivers/pci/hotplug/pciehp_acpi.c +++ b/drivers/pci/hotplug/pciehp_acpi.c @@ -33,6 +33,11 @@ #define PCIEHP_DETECT_AUTO (2) #define PCIEHP_DETECT_DEFAULT PCIEHP_DETECT_AUTO +struct dummy_slot { + u32 number; + struct list_head list; +}; + static int slot_detection_mode; static char *pciehp_detect_mode; module_param(pciehp_detect_mode, charp, 0444); @@ -47,7 +52,7 @@ int pciehp_acpi_slot_detection_check(struct pci_dev *dev) { if (slot_detection_mode != PCIEHP_DETECT_ACPI) return 0; - if (acpi_pci_detect_ejectable(dev->subordinate)) + if (acpi_pci_detect_ejectable(DEVICE_ACPI_HANDLE(&dev->dev))) return 0; return -ENODEV; } @@ -76,9 +81,9 @@ static int __init dummy_probe(struct pcie_device *dev) { int pos; u32 slot_cap; - struct slot *slot, *tmp; + acpi_handle handle; + struct dummy_slot *slot, *tmp; struct pci_dev *pdev = dev->port; - struct pci_bus *pbus = pdev->subordinate; /* Note: pciehp_detect_mode != PCIEHP_DETECT_ACPI here */ if (pciehp_get_hp_hw_control_from_firmware(pdev)) return -ENODEV; @@ -89,12 +94,13 @@ static int __init dummy_probe(struct pcie_device *dev) if (!slot) return -ENOMEM; slot->number = slot_cap >> 19; - list_for_each_entry(tmp, &dummy_slots, slot_list) { + list_for_each_entry(tmp, &dummy_slots, list) { if (tmp->number == slot->number) dup_slot_id++; } - list_add_tail(&slot->slot_list, &dummy_slots); - if (!acpi_slot_detected && acpi_pci_detect_ejectable(pbus)) + list_add_tail(&slot->list, &dummy_slots); + handle = DEVICE_ACPI_HANDLE(&pdev->dev); + if (!acpi_slot_detected && acpi_pci_detect_ejectable(handle)) acpi_slot_detected = 1; return -ENODEV; /* dummy driver always returns error */ } @@ -108,11 +114,11 @@ static struct pcie_port_service_driver __initdata dummy_driver = { static int __init select_detection_mode(void) { - struct slot *slot, *tmp; + struct dummy_slot *slot, *tmp; pcie_port_service_register(&dummy_driver); pcie_port_service_unregister(&dummy_driver); - list_for_each_entry_safe(slot, tmp, &dummy_slots, slot_list) { - list_del(&slot->slot_list); + list_for_each_entry_safe(slot, tmp, &dummy_slots, list) { + list_del(&slot->list); kfree(slot); } if (acpi_slot_detected && dup_slot_id) diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c index 2317557fdee..bc234719b1d 100644 --- a/drivers/pci/hotplug/pciehp_core.c +++ b/drivers/pci/hotplug/pciehp_core.c @@ -99,65 +99,55 @@ static void release_slot(struct hotplug_slot *hotplug_slot) kfree(hotplug_slot); } -static int init_slots(struct controller *ctrl) +static int init_slot(struct controller *ctrl) { - struct slot *slot; - struct hotplug_slot *hotplug_slot; - struct hotplug_slot_info *info; + struct slot *slot = ctrl->slot; + struct hotplug_slot *hotplug = NULL; + struct hotplug_slot_info *info = NULL; char name[SLOT_NAME_SIZE]; int retval = -ENOMEM; - list_for_each_entry(slot, &ctrl->slot_list, slot_list) { - hotplug_slot = kzalloc(sizeof(*hotplug_slot), GFP_KERNEL); - if (!hotplug_slot) - goto error; - - info = kzalloc(sizeof(*info), GFP_KERNEL); - if (!info) - goto error_hpslot; - - /* register this slot with the hotplug pci core */ - hotplug_slot->info = info; - hotplug_slot->private = slot; - hotplug_slot->release = &release_slot; - hotplug_slot->ops = &pciehp_hotplug_slot_ops; - slot->hotplug_slot = hotplug_slot; - snprintf(name, SLOT_NAME_SIZE, "%u", slot->number); - - ctrl_dbg(ctrl, "Registering domain:bus:dev=%04x:%02x:%02x " - "hp_slot=%x sun=%x slot_device_offset=%x\n", - pci_domain_nr(ctrl->pci_dev->subordinate), - slot->bus, slot->device, slot->hp_slot, slot->number, - ctrl->slot_device_offset); - retval = pci_hp_register(hotplug_slot, - ctrl->pci_dev->subordinate, - slot->device, - name); - if (retval) { - ctrl_err(ctrl, "pci_hp_register failed with error %d\n", - retval); - goto error_info; - } - get_power_status(hotplug_slot, &info->power_status); - get_attention_status(hotplug_slot, &info->attention_status); - get_latch_status(hotplug_slot, &info->latch_status); - get_adapter_status(hotplug_slot, &info->adapter_status); + hotplug = kzalloc(sizeof(*hotplug), GFP_KERNEL); + if (!hotplug) + goto out; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + goto out; + + /* register this slot with the hotplug pci core */ + hotplug->info = info; + hotplug->private = slot; + hotplug->release = &release_slot; + hotplug->ops = &pciehp_hotplug_slot_ops; + slot->hotplug_slot = hotplug; + snprintf(name, SLOT_NAME_SIZE, "%u", PSN(ctrl)); + + ctrl_dbg(ctrl, "Registering domain:bus:dev=%04x:%02x:00 sun=%x\n", + pci_domain_nr(ctrl->pcie->port->subordinate), + ctrl->pcie->port->subordinate->number, PSN(ctrl)); + retval = pci_hp_register(hotplug, + ctrl->pcie->port->subordinate, 0, name); + if (retval) { + ctrl_err(ctrl, + "pci_hp_register failed with error %d\n", retval); + goto out; + } + get_power_status(hotplug, &info->power_status); + get_attention_status(hotplug, &info->attention_status); + get_latch_status(hotplug, &info->latch_status); + get_adapter_status(hotplug, &info->adapter_status); +out: + if (retval) { + kfree(info); + kfree(hotplug); } - - return 0; -error_info: - kfree(info); -error_hpslot: - kfree(hotplug_slot); -error: return retval; } -static void cleanup_slots(struct controller *ctrl) +static void cleanup_slot(struct controller *ctrl) { - struct slot *slot; - list_for_each_entry(slot, &ctrl->slot_list, slot_list) - pci_hp_deregister(slot->hotplug_slot); + pci_hp_deregister(ctrl->slot->hotplug_slot); } /* @@ -173,7 +163,7 @@ static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status) hotplug_slot->info->attention_status = status; if (ATTN_LED(slot->ctrl)) - slot->hpc_ops->set_attention_status(slot, status); + pciehp_set_attention_status(slot, status); return 0; } @@ -208,7 +198,7 @@ static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n", __func__, slot_name(slot)); - retval = slot->hpc_ops->get_power_status(slot, value); + retval = pciehp_get_power_status(slot, value); if (retval < 0) *value = hotplug_slot->info->power_status; @@ -223,7 +213,7 @@ static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value) ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n", __func__, slot_name(slot)); - retval = slot->hpc_ops->get_attention_status(slot, value); + retval = pciehp_get_attention_status(slot, value); if (retval < 0) *value = hotplug_slot->info->attention_status; @@ -238,7 +228,7 @@ static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n", __func__, slot_name(slot)); - retval = slot->hpc_ops->get_latch_status(slot, value); + retval = pciehp_get_latch_status(slot, value); if (retval < 0) *value = hotplug_slot->info->latch_status; @@ -253,7 +243,7 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n", __func__, slot_name(slot)); - retval = slot->hpc_ops->get_adapter_status(slot, value); + retval = pciehp_get_adapter_status(slot, value); if (retval < 0) *value = hotplug_slot->info->adapter_status; @@ -269,7 +259,7 @@ static int get_max_bus_speed(struct hotplug_slot *hotplug_slot, ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n", __func__, slot_name(slot)); - retval = slot->hpc_ops->get_max_bus_speed(slot, value); + retval = pciehp_get_max_link_speed(slot, value); if (retval < 0) *value = PCI_SPEED_UNKNOWN; @@ -284,7 +274,7 @@ static int get_cur_bus_speed(struct hotplug_slot *hotplug_slot, enum pci_bus_spe ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n", __func__, slot_name(slot)); - retval = slot->hpc_ops->get_cur_bus_speed(slot, value); + retval = pciehp_get_cur_link_speed(slot, value); if (retval < 0) *value = PCI_SPEED_UNKNOWN; @@ -295,7 +285,7 @@ static int pciehp_probe(struct pcie_device *dev) { int rc; struct controller *ctrl; - struct slot *t_slot; + struct slot *slot; u8 value; struct pci_dev *pdev = dev->port; @@ -314,7 +304,7 @@ static int pciehp_probe(struct pcie_device *dev) set_service_data(dev, ctrl); /* Setup the slot information structures */ - rc = init_slots(ctrl); + rc = init_slot(ctrl); if (rc) { if (rc == -EBUSY) ctrl_warn(ctrl, "Slot already registered by another " @@ -332,15 +322,15 @@ static int pciehp_probe(struct pcie_device *dev) } /* Check if slot is occupied */ - t_slot = pciehp_find_slot(ctrl, ctrl->slot_device_offset); - t_slot->hpc_ops->get_adapter_status(t_slot, &value); + slot = ctrl->slot; + pciehp_get_adapter_status(slot, &value); if (value) { if (pciehp_force) - pciehp_enable_slot(t_slot); + pciehp_enable_slot(slot); } else { /* Power off slot if not occupied */ if (POWER_CTRL(ctrl)) { - rc = t_slot->hpc_ops->power_off_slot(t_slot); + rc = pciehp_power_off_slot(slot); if (rc) goto err_out_free_ctrl_slot; } @@ -349,19 +339,19 @@ static int pciehp_probe(struct pcie_device *dev) return 0; err_out_free_ctrl_slot: - cleanup_slots(ctrl); + cleanup_slot(ctrl); err_out_release_ctlr: - ctrl->hpc_ops->release_ctlr(ctrl); + pciehp_release_ctrl(ctrl); err_out_none: return -ENODEV; } -static void pciehp_remove (struct pcie_device *dev) +static void pciehp_remove(struct pcie_device *dev) { struct controller *ctrl = get_service_data(dev); - cleanup_slots(ctrl); - ctrl->hpc_ops->release_ctlr(ctrl); + cleanup_slot(ctrl); + pciehp_release_ctrl(ctrl); } #ifdef CONFIG_PM @@ -376,20 +366,20 @@ static int pciehp_resume (struct pcie_device *dev) dev_info(&dev->device, "%s ENTRY\n", __func__); if (pciehp_force) { struct controller *ctrl = get_service_data(dev); - struct slot *t_slot; + struct slot *slot; u8 status; /* reinitialize the chipset's event detection logic */ pcie_enable_notification(ctrl); - t_slot = pciehp_find_slot(ctrl, ctrl->slot_device_offset); + slot = ctrl->slot; /* Check if slot is occupied */ - t_slot->hpc_ops->get_adapter_status(t_slot, &status); + pciehp_get_adapter_status(slot, &status); if (status) - pciehp_enable_slot(t_slot); + pciehp_enable_slot(slot); else - pciehp_disable_slot(t_slot); + pciehp_disable_slot(slot); } return 0; } diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c index ff4034502d2..84487d126e4 100644 --- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -30,7 +30,6 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/types.h> -#include <linux/smp_lock.h> #include <linux/pci.h> #include <linux/workqueue.h> #include "../pci.h" @@ -83,7 +82,7 @@ u8 pciehp_handle_switch_change(struct slot *p_slot) /* Switch Change */ ctrl_dbg(ctrl, "Switch interrupt received\n"); - p_slot->hpc_ops->get_latch_status(p_slot, &getstatus); + pciehp_get_latch_status(p_slot, &getstatus); if (getstatus) { /* * Switch opened @@ -115,7 +114,7 @@ u8 pciehp_handle_presence_change(struct slot *p_slot) /* Switch is open, assume a presence change * Save the presence state */ - p_slot->hpc_ops->get_adapter_status(p_slot, &presence_save); + pciehp_get_adapter_status(p_slot, &presence_save); if (presence_save) { /* * Card Present @@ -144,7 +143,7 @@ u8 pciehp_handle_power_fault(struct slot *p_slot) /* power fault */ ctrl_dbg(ctrl, "Power fault interrupt received\n"); - if ( !(p_slot->hpc_ops->query_power_fault(p_slot))) { + if (!pciehp_query_power_fault(p_slot)) { /* * power fault Cleared */ @@ -173,7 +172,7 @@ static void set_slot_off(struct controller *ctrl, struct slot * pslot) { /* turn off slot, turn on Amber LED, turn off Green LED if supported*/ if (POWER_CTRL(ctrl)) { - if (pslot->hpc_ops->power_off_slot(pslot)) { + if (pciehp_power_off_slot(pslot)) { ctrl_err(ctrl, "Issue of Slot Power Off command failed\n"); return; @@ -187,10 +186,10 @@ static void set_slot_off(struct controller *ctrl, struct slot * pslot) } if (PWR_LED(ctrl)) - pslot->hpc_ops->green_led_off(pslot); + pciehp_green_led_off(pslot); if (ATTN_LED(ctrl)) { - if (pslot->hpc_ops->set_attention_status(pslot, 1)) { + if (pciehp_set_attention_status(pslot, 1)) { ctrl_err(ctrl, "Issue of Set Attention Led command failed\n"); return; @@ -209,24 +208,20 @@ static int board_added(struct slot *p_slot) { int retval = 0; struct controller *ctrl = p_slot->ctrl; - struct pci_bus *parent = ctrl->pci_dev->subordinate; - - ctrl_dbg(ctrl, "%s: slot device, slot offset, hp slot = %d, %d, %d\n", - __func__, p_slot->device, ctrl->slot_device_offset, - p_slot->hp_slot); + struct pci_bus *parent = ctrl->pcie->port->subordinate; if (POWER_CTRL(ctrl)) { /* Power on slot */ - retval = p_slot->hpc_ops->power_on_slot(p_slot); + retval = pciehp_power_on_slot(p_slot); if (retval) return retval; } if (PWR_LED(ctrl)) - p_slot->hpc_ops->green_led_blink(p_slot); + pciehp_green_led_blink(p_slot); /* Check link training status */ - retval = p_slot->hpc_ops->check_lnk_status(ctrl); + retval = pciehp_check_link_status(ctrl); if (retval) { ctrl_err(ctrl, "Failed to check link status\n"); set_slot_off(ctrl, p_slot); @@ -234,26 +229,21 @@ static int board_added(struct slot *p_slot) } /* Check for a power fault */ - if (p_slot->hpc_ops->query_power_fault(p_slot)) { + if (pciehp_query_power_fault(p_slot)) { ctrl_dbg(ctrl, "Power fault detected\n"); - retval = POWER_FAILURE; + retval = -EIO; goto err_exit; } retval = pciehp_configure_device(p_slot); if (retval) { - ctrl_err(ctrl, "Cannot add device at %04x:%02x:%02x\n", - pci_domain_nr(parent), p_slot->bus, p_slot->device); + ctrl_err(ctrl, "Cannot add device at %04x:%02x:00\n", + pci_domain_nr(parent), parent->number); goto err_exit; } - /* - * Some PCI Express root ports require fixup after hot-plug operation. - */ - if (pcie_mch_quirk) - pci_fixup_device(pci_fixup_final, ctrl->pci_dev); if (PWR_LED(ctrl)) - p_slot->hpc_ops->green_led_on(p_slot); + pciehp_green_led_on(p_slot); return 0; @@ -275,11 +265,9 @@ static int remove_board(struct slot *p_slot) if (retval) return retval; - ctrl_dbg(ctrl, "%s: hp_slot = %d\n", __func__, p_slot->hp_slot); - if (POWER_CTRL(ctrl)) { /* power off slot */ - retval = p_slot->hpc_ops->power_off_slot(p_slot); + retval = pciehp_power_off_slot(p_slot); if (retval) { ctrl_err(ctrl, "Issue of Slot Disable command failed\n"); @@ -293,9 +281,9 @@ static int remove_board(struct slot *p_slot) msleep(1000); } + /* turn off Green LED */ if (PWR_LED(ctrl)) - /* turn off Green LED */ - p_slot->hpc_ops->green_led_off(p_slot); + pciehp_green_led_off(p_slot); return 0; } @@ -323,18 +311,17 @@ static void pciehp_power_thread(struct work_struct *work) case POWEROFF_STATE: mutex_unlock(&p_slot->lock); ctrl_dbg(p_slot->ctrl, - "Disabling domain:bus:device=%04x:%02x:%02x\n", - pci_domain_nr(p_slot->ctrl->pci_dev->subordinate), - p_slot->bus, p_slot->device); + "Disabling domain:bus:device=%04x:%02x:00\n", + pci_domain_nr(p_slot->ctrl->pcie->port->subordinate), + p_slot->ctrl->pcie->port->subordinate->number); pciehp_disable_slot(p_slot); mutex_lock(&p_slot->lock); p_slot->state = STATIC_STATE; break; case POWERON_STATE: mutex_unlock(&p_slot->lock); - if (pciehp_enable_slot(p_slot) && - PWR_LED(p_slot->ctrl)) - p_slot->hpc_ops->green_led_off(p_slot); + if (pciehp_enable_slot(p_slot) && PWR_LED(p_slot->ctrl)) + pciehp_green_led_off(p_slot); mutex_lock(&p_slot->lock); p_slot->state = STATIC_STATE; break; @@ -385,10 +372,10 @@ static int update_slot_info(struct slot *slot) if (!info) return -ENOMEM; - slot->hpc_ops->get_power_status(slot, &(info->power_status)); - slot->hpc_ops->get_attention_status(slot, &(info->attention_status)); - slot->hpc_ops->get_latch_status(slot, &(info->latch_status)); - slot->hpc_ops->get_adapter_status(slot, &(info->adapter_status)); + pciehp_get_power_status(slot, &info->power_status); + pciehp_get_attention_status(slot, &info->attention_status); + pciehp_get_latch_status(slot, &info->latch_status); + pciehp_get_adapter_status(slot, &info->adapter_status); result = pci_hp_change_slot_info(slot->hotplug_slot, info); kfree (info); @@ -405,7 +392,7 @@ static void handle_button_press_event(struct slot *p_slot) switch (p_slot->state) { case STATIC_STATE: - p_slot->hpc_ops->get_power_status(p_slot, &getstatus); + pciehp_get_power_status(p_slot, &getstatus); if (getstatus) { p_slot->state = BLINKINGOFF_STATE; ctrl_info(ctrl, @@ -419,9 +406,9 @@ static void handle_button_press_event(struct slot *p_slot) } /* blink green LED and turn off amber */ if (PWR_LED(ctrl)) - p_slot->hpc_ops->green_led_blink(p_slot); + pciehp_green_led_blink(p_slot); if (ATTN_LED(ctrl)) - p_slot->hpc_ops->set_attention_status(p_slot, 0); + pciehp_set_attention_status(p_slot, 0); schedule_delayed_work(&p_slot->work, 5*HZ); break; @@ -436,13 +423,13 @@ static void handle_button_press_event(struct slot *p_slot) cancel_delayed_work(&p_slot->work); if (p_slot->state == BLINKINGOFF_STATE) { if (PWR_LED(ctrl)) - p_slot->hpc_ops->green_led_on(p_slot); + pciehp_green_led_on(p_slot); } else { if (PWR_LED(ctrl)) - p_slot->hpc_ops->green_led_off(p_slot); + pciehp_green_led_off(p_slot); } if (ATTN_LED(ctrl)) - p_slot->hpc_ops->set_attention_status(p_slot, 0); + pciehp_set_attention_status(p_slot, 0); ctrl_info(ctrl, "PCI slot #%s - action canceled " "due to button press\n", slot_name(p_slot)); p_slot->state = STATIC_STATE; @@ -480,7 +467,7 @@ static void handle_surprise_event(struct slot *p_slot) info->p_slot = p_slot; INIT_WORK(&info->work, pciehp_power_thread); - p_slot->hpc_ops->get_adapter_status(p_slot, &getstatus); + pciehp_get_adapter_status(p_slot, &getstatus); if (!getstatus) p_slot->state = POWEROFF_STATE; else @@ -504,9 +491,9 @@ static void interrupt_event_handler(struct work_struct *work) if (!POWER_CTRL(ctrl)) break; if (ATTN_LED(ctrl)) - p_slot->hpc_ops->set_attention_status(p_slot, 1); + pciehp_set_attention_status(p_slot, 1); if (PWR_LED(ctrl)) - p_slot->hpc_ops->green_led_off(p_slot); + pciehp_green_led_off(p_slot); break; case INT_PRESENCE_ON: case INT_PRESENCE_OFF: @@ -531,45 +518,38 @@ int pciehp_enable_slot(struct slot *p_slot) int rc; struct controller *ctrl = p_slot->ctrl; - /* Check to see if (latch closed, card present, power off) */ - mutex_lock(&p_slot->ctrl->crit_sect); - - rc = p_slot->hpc_ops->get_adapter_status(p_slot, &getstatus); + rc = pciehp_get_adapter_status(p_slot, &getstatus); if (rc || !getstatus) { ctrl_info(ctrl, "No adapter on slot(%s)\n", slot_name(p_slot)); - mutex_unlock(&p_slot->ctrl->crit_sect); return -ENODEV; } if (MRL_SENS(p_slot->ctrl)) { - rc = p_slot->hpc_ops->get_latch_status(p_slot, &getstatus); + rc = pciehp_get_latch_status(p_slot, &getstatus); if (rc || getstatus) { ctrl_info(ctrl, "Latch open on slot(%s)\n", slot_name(p_slot)); - mutex_unlock(&p_slot->ctrl->crit_sect); return -ENODEV; } } if (POWER_CTRL(p_slot->ctrl)) { - rc = p_slot->hpc_ops->get_power_status(p_slot, &getstatus); + rc = pciehp_get_power_status(p_slot, &getstatus); if (rc || getstatus) { ctrl_info(ctrl, "Already enabled on slot(%s)\n", slot_name(p_slot)); - mutex_unlock(&p_slot->ctrl->crit_sect); return -EINVAL; } } - p_slot->hpc_ops->get_latch_status(p_slot, &getstatus); + pciehp_get_latch_status(p_slot, &getstatus); rc = board_added(p_slot); if (rc) { - p_slot->hpc_ops->get_latch_status(p_slot, &getstatus); + pciehp_get_latch_status(p_slot, &getstatus); } update_slot_info(p_slot); - mutex_unlock(&p_slot->ctrl->crit_sect); return rc; } @@ -583,35 +563,29 @@ int pciehp_disable_slot(struct slot *p_slot) if (!p_slot->ctrl) return 1; - /* Check to see if (latch closed, card present, power on) */ - mutex_lock(&p_slot->ctrl->crit_sect); - if (!HP_SUPR_RM(p_slot->ctrl)) { - ret = p_slot->hpc_ops->get_adapter_status(p_slot, &getstatus); + ret = pciehp_get_adapter_status(p_slot, &getstatus); if (ret || !getstatus) { ctrl_info(ctrl, "No adapter on slot(%s)\n", slot_name(p_slot)); - mutex_unlock(&p_slot->ctrl->crit_sect); return -ENODEV; } } if (MRL_SENS(p_slot->ctrl)) { - ret = p_slot->hpc_ops->get_latch_status(p_slot, &getstatus); + ret = pciehp_get_latch_status(p_slot, &getstatus); if (ret || getstatus) { ctrl_info(ctrl, "Latch open on slot(%s)\n", slot_name(p_slot)); - mutex_unlock(&p_slot->ctrl->crit_sect); return -ENODEV; } } if (POWER_CTRL(p_slot->ctrl)) { - ret = p_slot->hpc_ops->get_power_status(p_slot, &getstatus); + ret = pciehp_get_power_status(p_slot, &getstatus); if (ret || !getstatus) { ctrl_info(ctrl, "Already disabled on slot(%s)\n", slot_name(p_slot)); - mutex_unlock(&p_slot->ctrl->crit_sect); return -EINVAL; } } @@ -619,7 +593,6 @@ int pciehp_disable_slot(struct slot *p_slot) ret = remove_board(p_slot); update_slot_info(p_slot); - mutex_unlock(&p_slot->ctrl->crit_sect); return ret; } diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 52813257e5b..9ef4605c1ef 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -44,25 +44,25 @@ static atomic_t pciehp_num_controllers = ATOMIC_INIT(0); static inline int pciehp_readw(struct controller *ctrl, int reg, u16 *value) { - struct pci_dev *dev = ctrl->pci_dev; + struct pci_dev *dev = ctrl->pcie->port; return pci_read_config_word(dev, ctrl->cap_base + reg, value); } static inline int pciehp_readl(struct controller *ctrl, int reg, u32 *value) { - struct pci_dev *dev = ctrl->pci_dev; + struct pci_dev *dev = ctrl->pcie->port; return pci_read_config_dword(dev, ctrl->cap_base + reg, value); } static inline int pciehp_writew(struct controller *ctrl, int reg, u16 value) { - struct pci_dev *dev = ctrl->pci_dev; + struct pci_dev *dev = ctrl->pcie->port; return pci_write_config_word(dev, ctrl->cap_base + reg, value); } static inline int pciehp_writel(struct controller *ctrl, int reg, u32 value) { - struct pci_dev *dev = ctrl->pci_dev; + struct pci_dev *dev = ctrl->pcie->port; return pci_write_config_dword(dev, ctrl->cap_base + reg, value); } @@ -266,7 +266,7 @@ static void pcie_wait_link_active(struct controller *ctrl) ctrl_dbg(ctrl, "Data Link Layer Link Active not set in 1000 msec\n"); } -static int hpc_check_lnk_status(struct controller *ctrl) +int pciehp_check_link_status(struct controller *ctrl) { u16 lnk_status; int retval = 0; @@ -305,7 +305,7 @@ static int hpc_check_lnk_status(struct controller *ctrl) return retval; } -static int hpc_get_attention_status(struct slot *slot, u8 *status) +int pciehp_get_attention_status(struct slot *slot, u8 *status) { struct controller *ctrl = slot->ctrl; u16 slot_ctrl; @@ -344,7 +344,7 @@ static int hpc_get_attention_status(struct slot *slot, u8 *status) return 0; } -static int hpc_get_power_status(struct slot *slot, u8 *status) +int pciehp_get_power_status(struct slot *slot, u8 *status) { struct controller *ctrl = slot->ctrl; u16 slot_ctrl; @@ -376,7 +376,7 @@ static int hpc_get_power_status(struct slot *slot, u8 *status) return retval; } -static int hpc_get_latch_status(struct slot *slot, u8 *status) +int pciehp_get_latch_status(struct slot *slot, u8 *status) { struct controller *ctrl = slot->ctrl; u16 slot_status; @@ -392,7 +392,7 @@ static int hpc_get_latch_status(struct slot *slot, u8 *status) return 0; } -static int hpc_get_adapter_status(struct slot *slot, u8 *status) +int pciehp_get_adapter_status(struct slot *slot, u8 *status) { struct controller *ctrl = slot->ctrl; u16 slot_status; @@ -408,7 +408,7 @@ static int hpc_get_adapter_status(struct slot *slot, u8 *status) return 0; } -static int hpc_query_power_fault(struct slot *slot) +int pciehp_query_power_fault(struct slot *slot) { struct controller *ctrl = slot->ctrl; u16 slot_status; @@ -422,7 +422,7 @@ static int hpc_query_power_fault(struct slot *slot) return !!(slot_status & PCI_EXP_SLTSTA_PFD); } -static int hpc_set_attention_status(struct slot *slot, u8 value) +int pciehp_set_attention_status(struct slot *slot, u8 value) { struct controller *ctrl = slot->ctrl; u16 slot_cmd; @@ -450,7 +450,7 @@ static int hpc_set_attention_status(struct slot *slot, u8 value) return rc; } -static void hpc_set_green_led_on(struct slot *slot) +void pciehp_green_led_on(struct slot *slot) { struct controller *ctrl = slot->ctrl; u16 slot_cmd; @@ -463,7 +463,7 @@ static void hpc_set_green_led_on(struct slot *slot) __func__, ctrl->cap_base + PCI_EXP_SLTCTL, slot_cmd); } -static void hpc_set_green_led_off(struct slot *slot) +void pciehp_green_led_off(struct slot *slot) { struct controller *ctrl = slot->ctrl; u16 slot_cmd; @@ -476,7 +476,7 @@ static void hpc_set_green_led_off(struct slot *slot) __func__, ctrl->cap_base + PCI_EXP_SLTCTL, slot_cmd); } -static void hpc_set_green_led_blink(struct slot *slot) +void pciehp_green_led_blink(struct slot *slot) { struct controller *ctrl = slot->ctrl; u16 slot_cmd; @@ -489,7 +489,7 @@ static void hpc_set_green_led_blink(struct slot *slot) __func__, ctrl->cap_base + PCI_EXP_SLTCTL, slot_cmd); } -static int hpc_power_on_slot(struct slot * slot) +int pciehp_power_on_slot(struct slot * slot) { struct controller *ctrl = slot->ctrl; u16 slot_cmd; @@ -497,8 +497,6 @@ static int hpc_power_on_slot(struct slot * slot) u16 slot_status; int retval = 0; - ctrl_dbg(ctrl, "%s: slot->hp_slot %x\n", __func__, slot->hp_slot); - /* Clear sticky power-fault bit from previous power failures */ retval = pciehp_readw(ctrl, PCI_EXP_SLTSTA, &slot_status); if (retval) { @@ -539,7 +537,7 @@ static int hpc_power_on_slot(struct slot * slot) static inline int pcie_mask_bad_dllp(struct controller *ctrl) { - struct pci_dev *dev = ctrl->pci_dev; + struct pci_dev *dev = ctrl->pcie->port; int pos; u32 reg; @@ -556,7 +554,7 @@ static inline int pcie_mask_bad_dllp(struct controller *ctrl) static inline void pcie_unmask_bad_dllp(struct controller *ctrl) { - struct pci_dev *dev = ctrl->pci_dev; + struct pci_dev *dev = ctrl->pcie->port; u32 reg; int pos; @@ -570,7 +568,7 @@ static inline void pcie_unmask_bad_dllp(struct controller *ctrl) pci_write_config_dword(dev, pos + PCI_ERR_COR_MASK, reg); } -static int hpc_power_off_slot(struct slot * slot) +int pciehp_power_off_slot(struct slot * slot) { struct controller *ctrl = slot->ctrl; u16 slot_cmd; @@ -578,8 +576,6 @@ static int hpc_power_off_slot(struct slot * slot) int retval = 0; int changed; - ctrl_dbg(ctrl, "%s: slot->hp_slot %x\n", __func__, slot->hp_slot); - /* * Set Bad DLLP Mask bit in Correctable Error Mask * Register. This is the workaround against Bad DLLP error @@ -614,8 +610,8 @@ static int hpc_power_off_slot(struct slot * slot) static irqreturn_t pcie_isr(int irq, void *dev_id) { struct controller *ctrl = (struct controller *)dev_id; + struct slot *slot = ctrl->slot; u16 detected, intr_loc; - struct slot *p_slot; /* * In order to guarantee that all interrupt events are @@ -656,29 +652,27 @@ static irqreturn_t pcie_isr(int irq, void *dev_id) if (!(intr_loc & ~PCI_EXP_SLTSTA_CC)) return IRQ_HANDLED; - p_slot = pciehp_find_slot(ctrl, ctrl->slot_device_offset); - /* Check MRL Sensor Changed */ if (intr_loc & PCI_EXP_SLTSTA_MRLSC) - pciehp_handle_switch_change(p_slot); + pciehp_handle_switch_change(slot); /* Check Attention Button Pressed */ if (intr_loc & PCI_EXP_SLTSTA_ABP) - pciehp_handle_attention_button(p_slot); + pciehp_handle_attention_button(slot); /* Check Presence Detect Changed */ if (intr_loc & PCI_EXP_SLTSTA_PDC) - pciehp_handle_presence_change(p_slot); + pciehp_handle_presence_change(slot); /* Check Power Fault Detected */ if ((intr_loc & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) { ctrl->power_fault_detected = 1; - pciehp_handle_power_fault(p_slot); + pciehp_handle_power_fault(slot); } return IRQ_HANDLED; } -static int hpc_get_max_lnk_speed(struct slot *slot, enum pci_bus_speed *value) +int pciehp_get_max_link_speed(struct slot *slot, enum pci_bus_speed *value) { struct controller *ctrl = slot->ctrl; enum pcie_link_speed lnk_speed; @@ -693,7 +687,10 @@ static int hpc_get_max_lnk_speed(struct slot *slot, enum pci_bus_speed *value) switch (lnk_cap & 0x000F) { case 1: - lnk_speed = PCIE_2PT5GB; + lnk_speed = PCIE_2_5GB; + break; + case 2: + lnk_speed = PCIE_5_0GB; break; default: lnk_speed = PCIE_LNK_SPEED_UNKNOWN; @@ -706,7 +703,7 @@ static int hpc_get_max_lnk_speed(struct slot *slot, enum pci_bus_speed *value) return retval; } -static int hpc_get_max_lnk_width(struct slot *slot, +int pciehp_get_max_lnk_width(struct slot *slot, enum pcie_link_width *value) { struct controller *ctrl = slot->ctrl; @@ -756,7 +753,7 @@ static int hpc_get_max_lnk_width(struct slot *slot, return retval; } -static int hpc_get_cur_lnk_speed(struct slot *slot, enum pci_bus_speed *value) +int pciehp_get_cur_link_speed(struct slot *slot, enum pci_bus_speed *value) { struct controller *ctrl = slot->ctrl; enum pcie_link_speed lnk_speed = PCI_SPEED_UNKNOWN; @@ -772,7 +769,10 @@ static int hpc_get_cur_lnk_speed(struct slot *slot, enum pci_bus_speed *value) switch (lnk_status & PCI_EXP_LNKSTA_CLS) { case 1: - lnk_speed = PCIE_2PT5GB; + lnk_speed = PCIE_2_5GB; + break; + case 2: + lnk_speed = PCIE_5_0GB; break; default: lnk_speed = PCIE_LNK_SPEED_UNKNOWN; @@ -785,7 +785,7 @@ static int hpc_get_cur_lnk_speed(struct slot *slot, enum pci_bus_speed *value) return retval; } -static int hpc_get_cur_lnk_width(struct slot *slot, +int pciehp_get_cur_lnk_width(struct slot *slot, enum pcie_link_width *value) { struct controller *ctrl = slot->ctrl; @@ -836,30 +836,6 @@ static int hpc_get_cur_lnk_width(struct slot *slot, return retval; } -static void pcie_release_ctrl(struct controller *ctrl); -static struct hpc_ops pciehp_hpc_ops = { - .power_on_slot = hpc_power_on_slot, - .power_off_slot = hpc_power_off_slot, - .set_attention_status = hpc_set_attention_status, - .get_power_status = hpc_get_power_status, - .get_attention_status = hpc_get_attention_status, - .get_latch_status = hpc_get_latch_status, - .get_adapter_status = hpc_get_adapter_status, - - .get_max_bus_speed = hpc_get_max_lnk_speed, - .get_cur_bus_speed = hpc_get_cur_lnk_speed, - .get_max_lnk_width = hpc_get_max_lnk_width, - .get_cur_lnk_width = hpc_get_cur_lnk_width, - - .query_power_fault = hpc_query_power_fault, - .green_led_on = hpc_set_green_led_on, - .green_led_off = hpc_set_green_led_off, - .green_led_blink = hpc_set_green_led_blink, - - .release_ctlr = pcie_release_ctrl, - .check_lnk_status = hpc_check_lnk_status, -}; - int pcie_enable_notification(struct controller *ctrl) { u16 cmd, mask; @@ -924,23 +900,16 @@ static int pcie_init_slot(struct controller *ctrl) if (!slot) return -ENOMEM; - slot->hp_slot = 0; slot->ctrl = ctrl; - slot->bus = ctrl->pci_dev->subordinate->number; - slot->device = ctrl->slot_device_offset + slot->hp_slot; - slot->hpc_ops = ctrl->hpc_ops; - slot->number = ctrl->first_slot; mutex_init(&slot->lock); INIT_DELAYED_WORK(&slot->work, pciehp_queue_pushbutton_work); - list_add(&slot->slot_list, &ctrl->slot_list); + ctrl->slot = slot; return 0; } static void pcie_cleanup_slot(struct controller *ctrl) { - struct slot *slot; - slot = list_first_entry(&ctrl->slot_list, struct slot, slot_list); - list_del(&slot->slot_list); + struct slot *slot = ctrl->slot; cancel_delayed_work(&slot->work); flush_scheduled_work(); flush_workqueue(pciehp_wq); @@ -951,7 +920,7 @@ static inline void dbg_ctrl(struct controller *ctrl) { int i; u16 reg16; - struct pci_dev *pdev = ctrl->pci_dev; + struct pci_dev *pdev = ctrl->pcie->port; if (!pciehp_debug) return; @@ -974,7 +943,7 @@ static inline void dbg_ctrl(struct controller *ctrl) (unsigned long long)pci_resource_start(pdev, i)); } ctrl_info(ctrl, "Slot Capabilities : 0x%08x\n", ctrl->slot_cap); - ctrl_info(ctrl, " Physical Slot Number : %d\n", ctrl->first_slot); + ctrl_info(ctrl, " Physical Slot Number : %d\n", PSN(ctrl)); ctrl_info(ctrl, " Attention Button : %3s\n", ATTN_BUTTN(ctrl) ? "yes" : "no"); ctrl_info(ctrl, " Power Controller : %3s\n", @@ -1008,10 +977,7 @@ struct controller *pcie_init(struct pcie_device *dev) dev_err(&dev->device, "%s: Out of memory\n", __func__); goto abort; } - INIT_LIST_HEAD(&ctrl->slot_list); - ctrl->pcie = dev; - ctrl->pci_dev = pdev; ctrl->cap_base = pci_find_capability(pdev, PCI_CAP_ID_EXP); if (!ctrl->cap_base) { ctrl_err(ctrl, "Cannot find PCI Express capability\n"); @@ -1023,11 +989,6 @@ struct controller *pcie_init(struct pcie_device *dev) } ctrl->slot_cap = slot_cap; - ctrl->first_slot = slot_cap >> 19; - ctrl->slot_device_offset = 0; - ctrl->num_slots = 1; - ctrl->hpc_ops = &pciehp_hpc_ops; - mutex_init(&ctrl->crit_sect); mutex_init(&ctrl->ctrl_lock); init_waitqueue_head(&ctrl->queue); dbg_ctrl(ctrl); @@ -1083,7 +1044,7 @@ abort: return NULL; } -void pcie_release_ctrl(struct controller *ctrl) +void pciehp_release_ctrl(struct controller *ctrl) { pcie_shutdown_notification(ctrl); pcie_cleanup_slot(ctrl); diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c index 10f9566ccee..21733108add 100644 --- a/drivers/pci/hotplug/pciehp_pci.c +++ b/drivers/pci/hotplug/pciehp_pci.c @@ -34,136 +34,6 @@ #include "../pci.h" #include "pciehp.h" -static void program_hpp_type0(struct pci_dev *dev, struct hpp_type0 *hpp) -{ - u16 pci_cmd, pci_bctl; - - if (hpp->revision > 1) { - warn("Rev.%d type0 record not supported\n", hpp->revision); - return; - } - - pci_write_config_byte(dev, PCI_CACHE_LINE_SIZE, hpp->cache_line_size); - pci_write_config_byte(dev, PCI_LATENCY_TIMER, hpp->latency_timer); - pci_read_config_word(dev, PCI_COMMAND, &pci_cmd); - if (hpp->enable_serr) - pci_cmd |= PCI_COMMAND_SERR; - else - pci_cmd &= ~PCI_COMMAND_SERR; - if (hpp->enable_perr) - pci_cmd |= PCI_COMMAND_PARITY; - else - pci_cmd &= ~PCI_COMMAND_PARITY; - pci_write_config_word(dev, PCI_COMMAND, pci_cmd); - - /* Program bridge control value */ - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) { - pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER, - hpp->latency_timer); - pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &pci_bctl); - if (hpp->enable_serr) - pci_bctl |= PCI_BRIDGE_CTL_SERR; - else - pci_bctl &= ~PCI_BRIDGE_CTL_SERR; - if (hpp->enable_perr) - pci_bctl |= PCI_BRIDGE_CTL_PARITY; - else - pci_bctl &= ~PCI_BRIDGE_CTL_PARITY; - pci_write_config_word(dev, PCI_BRIDGE_CONTROL, pci_bctl); - } -} - -static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp) -{ - int pos; - u16 reg16; - u32 reg32; - - if (hpp->revision > 1) { - warn("Rev.%d type2 record not supported\n", hpp->revision); - return; - } - - /* Find PCI Express capability */ - pos = pci_find_capability(dev, PCI_CAP_ID_EXP); - if (!pos) - return; - - /* Initialize Device Control Register */ - pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, ®16); - reg16 = (reg16 & hpp->pci_exp_devctl_and) | hpp->pci_exp_devctl_or; - pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, reg16); - - /* Initialize Link Control Register */ - if (dev->subordinate) { - pci_read_config_word(dev, pos + PCI_EXP_LNKCTL, ®16); - reg16 = (reg16 & hpp->pci_exp_lnkctl_and) - | hpp->pci_exp_lnkctl_or; - pci_write_config_word(dev, pos + PCI_EXP_LNKCTL, reg16); - } - - /* Find Advanced Error Reporting Enhanced Capability */ - pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); - if (!pos) - return; - - /* Initialize Uncorrectable Error Mask Register */ - pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, ®32); - reg32 = (reg32 & hpp->unc_err_mask_and) | hpp->unc_err_mask_or; - pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, reg32); - - /* Initialize Uncorrectable Error Severity Register */ - pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, ®32); - reg32 = (reg32 & hpp->unc_err_sever_and) | hpp->unc_err_sever_or; - pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, reg32); - - /* Initialize Correctable Error Mask Register */ - pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, ®32); - reg32 = (reg32 & hpp->cor_err_mask_and) | hpp->cor_err_mask_or; - pci_write_config_dword(dev, pos + PCI_ERR_COR_MASK, reg32); - - /* Initialize Advanced Error Capabilities and Control Register */ - pci_read_config_dword(dev, pos + PCI_ERR_CAP, ®32); - reg32 = (reg32 & hpp->adv_err_cap_and) | hpp->adv_err_cap_or; - pci_write_config_dword(dev, pos + PCI_ERR_CAP, reg32); - - /* - * FIXME: The following two registers are not supported yet. - * - * o Secondary Uncorrectable Error Severity Register - * o Secondary Uncorrectable Error Mask Register - */ -} - -static void program_fw_provided_values(struct pci_dev *dev) -{ - struct pci_dev *cdev; - struct hotplug_params hpp; - - /* Program hpp values for this device */ - if (!(dev->hdr_type == PCI_HEADER_TYPE_NORMAL || - (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE && - (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI))) - return; - - if (pciehp_get_hp_params_from_firmware(dev, &hpp)) { - warn("Could not get hotplug parameters\n"); - return; - } - - if (hpp.t2) - program_hpp_type2(dev, hpp.t2); - if (hpp.t0) - program_hpp_type0(dev, hpp.t0); - - /* Program child devices */ - if (dev->subordinate) { - list_for_each_entry(cdev, &dev->subordinate->devices, - bus_list) - program_fw_provided_values(cdev); - } -} - static int __ref pciehp_add_bridge(struct pci_dev *dev) { struct pci_bus *parent = dev->bus; @@ -193,27 +63,27 @@ static int __ref pciehp_add_bridge(struct pci_dev *dev) int pciehp_configure_device(struct slot *p_slot) { struct pci_dev *dev; - struct pci_bus *parent = p_slot->ctrl->pci_dev->subordinate; + struct pci_bus *parent = p_slot->ctrl->pcie->port->subordinate; int num, fn; struct controller *ctrl = p_slot->ctrl; - dev = pci_get_slot(parent, PCI_DEVFN(p_slot->device, 0)); + dev = pci_get_slot(parent, PCI_DEVFN(0, 0)); if (dev) { ctrl_err(ctrl, "Device %s already exists " - "at %04x:%02x:%02x, cannot hot-add\n", pci_name(dev), - pci_domain_nr(parent), p_slot->bus, p_slot->device); + "at %04x:%02x:00, cannot hot-add\n", pci_name(dev), + pci_domain_nr(parent), parent->number); pci_dev_put(dev); return -EINVAL; } - num = pci_scan_slot(parent, PCI_DEVFN(p_slot->device, 0)); + num = pci_scan_slot(parent, PCI_DEVFN(0, 0)); if (num == 0) { ctrl_err(ctrl, "No new device found\n"); return -ENODEV; } for (fn = 0; fn < 8; fn++) { - dev = pci_get_slot(parent, PCI_DEVFN(p_slot->device, fn)); + dev = pci_get_slot(parent, PCI_DEVFN(0, fn)); if (!dev) continue; if ((dev->class >> 16) == PCI_BASE_CLASS_DISPLAY) { @@ -226,7 +96,7 @@ int pciehp_configure_device(struct slot *p_slot) (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)) { pciehp_add_bridge(dev); } - program_fw_provided_values(dev); + pci_configure_slot(dev); pci_dev_put(dev); } @@ -241,19 +111,18 @@ int pciehp_unconfigure_device(struct slot *p_slot) int j; u8 bctl = 0; u8 presence = 0; - struct pci_bus *parent = p_slot->ctrl->pci_dev->subordinate; + struct pci_bus *parent = p_slot->ctrl->pcie->port->subordinate; u16 command; struct controller *ctrl = p_slot->ctrl; - ctrl_dbg(ctrl, "%s: domain:bus:dev = %04x:%02x:%02x\n", - __func__, pci_domain_nr(parent), p_slot->bus, p_slot->device); - ret = p_slot->hpc_ops->get_adapter_status(p_slot, &presence); + ctrl_dbg(ctrl, "%s: domain:bus:dev = %04x:%02x:00\n", + __func__, pci_domain_nr(parent), parent->number); + ret = pciehp_get_adapter_status(p_slot, &presence); if (ret) presence = 0; for (j = 0; j < 8; j++) { - struct pci_dev* temp = pci_get_slot(parent, - (p_slot->device << 3) | j); + struct pci_dev* temp = pci_get_slot(parent, PCI_DEVFN(0, j)); if (!temp) continue; if ((temp->class >> 16) == PCI_BASE_CLASS_DISPLAY) { @@ -285,11 +154,6 @@ int pciehp_unconfigure_device(struct slot *p_slot) } pci_dev_put(temp); } - /* - * Some PCI Express root ports require fixup after hot-plug operation. - */ - if (pcie_mch_quirk) - pci_fixup_device(pci_fixup_final, p_slot->ctrl->pci_dev); return rc; } diff --git a/drivers/pci/hotplug/pcihp_slot.c b/drivers/pci/hotplug/pcihp_slot.c new file mode 100644 index 00000000000..cc8ec3aa41a --- /dev/null +++ b/drivers/pci/hotplug/pcihp_slot.c @@ -0,0 +1,187 @@ +/* + * Copyright (C) 1995,2001 Compaq Computer Corporation + * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com) + * Copyright (C) 2001 IBM Corp. + * Copyright (C) 2003-2004 Intel Corporation + * (c) Copyright 2009 Hewlett-Packard Development Company, L.P. + * + * All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or (at + * your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for more + * details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#include <linux/pci.h> +#include <linux/pci_hotplug.h> + +static struct hpp_type0 pci_default_type0 = { + .revision = 1, + .cache_line_size = 8, + .latency_timer = 0x40, + .enable_serr = 0, + .enable_perr = 0, +}; + +static void program_hpp_type0(struct pci_dev *dev, struct hpp_type0 *hpp) +{ + u16 pci_cmd, pci_bctl; + + if (!hpp) { + /* + * Perhaps we *should* use default settings for PCIe, but + * pciehp didn't, so we won't either. + */ + if (dev->is_pcie) + return; + dev_info(&dev->dev, "using default PCI settings\n"); + hpp = &pci_default_type0; + } + + if (hpp->revision > 1) { + dev_warn(&dev->dev, + "PCI settings rev %d not supported; using defaults\n", + hpp->revision); + hpp = &pci_default_type0; + } + + pci_write_config_byte(dev, PCI_CACHE_LINE_SIZE, hpp->cache_line_size); + pci_write_config_byte(dev, PCI_LATENCY_TIMER, hpp->latency_timer); + pci_read_config_word(dev, PCI_COMMAND, &pci_cmd); + if (hpp->enable_serr) + pci_cmd |= PCI_COMMAND_SERR; + else + pci_cmd &= ~PCI_COMMAND_SERR; + if (hpp->enable_perr) + pci_cmd |= PCI_COMMAND_PARITY; + else + pci_cmd &= ~PCI_COMMAND_PARITY; + pci_write_config_word(dev, PCI_COMMAND, pci_cmd); + + /* Program bridge control value */ + if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) { + pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER, + hpp->latency_timer); + pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &pci_bctl); + if (hpp->enable_serr) + pci_bctl |= PCI_BRIDGE_CTL_SERR; + else + pci_bctl &= ~PCI_BRIDGE_CTL_SERR; + if (hpp->enable_perr) + pci_bctl |= PCI_BRIDGE_CTL_PARITY; + else + pci_bctl &= ~PCI_BRIDGE_CTL_PARITY; + pci_write_config_word(dev, PCI_BRIDGE_CONTROL, pci_bctl); + } +} + +static void program_hpp_type1(struct pci_dev *dev, struct hpp_type1 *hpp) +{ + if (hpp) + dev_warn(&dev->dev, "PCI-X settings not supported\n"); +} + +static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp) +{ + int pos; + u16 reg16; + u32 reg32; + + if (!hpp) + return; + + /* Find PCI Express capability */ + pos = pci_find_capability(dev, PCI_CAP_ID_EXP); + if (!pos) + return; + + if (hpp->revision > 1) { + dev_warn(&dev->dev, "PCIe settings rev %d not supported\n", + hpp->revision); + return; + } + + /* Initialize Device Control Register */ + pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, ®16); + reg16 = (reg16 & hpp->pci_exp_devctl_and) | hpp->pci_exp_devctl_or; + pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, reg16); + + /* Initialize Link Control Register */ + if (dev->subordinate) { + pci_read_config_word(dev, pos + PCI_EXP_LNKCTL, ®16); + reg16 = (reg16 & hpp->pci_exp_lnkctl_and) + | hpp->pci_exp_lnkctl_or; + pci_write_config_word(dev, pos + PCI_EXP_LNKCTL, reg16); + } + + /* Find Advanced Error Reporting Enhanced Capability */ + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); + if (!pos) + return; + + /* Initialize Uncorrectable Error Mask Register */ + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, ®32); + reg32 = (reg32 & hpp->unc_err_mask_and) | hpp->unc_err_mask_or; + pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, reg32); + + /* Initialize Uncorrectable Error Severity Register */ + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, ®32); + reg32 = (reg32 & hpp->unc_err_sever_and) | hpp->unc_err_sever_or; + pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, reg32); + + /* Initialize Correctable Error Mask Register */ + pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, ®32); + reg32 = (reg32 & hpp->cor_err_mask_and) | hpp->cor_err_mask_or; + pci_write_config_dword(dev, pos + PCI_ERR_COR_MASK, reg32); + + /* Initialize Advanced Error Capabilities and Control Register */ + pci_read_config_dword(dev, pos + PCI_ERR_CAP, ®32); + reg32 = (reg32 & hpp->adv_err_cap_and) | hpp->adv_err_cap_or; + pci_write_config_dword(dev, pos + PCI_ERR_CAP, reg32); + + /* + * FIXME: The following two registers are not supported yet. + * + * o Secondary Uncorrectable Error Severity Register + * o Secondary Uncorrectable Error Mask Register + */ +} + +void pci_configure_slot(struct pci_dev *dev) +{ + struct pci_dev *cdev; + struct hotplug_params hpp; + int ret; + + if (!(dev->hdr_type == PCI_HEADER_TYPE_NORMAL || + (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE && + (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI))) + return; + + memset(&hpp, 0, sizeof(hpp)); + ret = pci_get_hp_params(dev, &hpp); + if (ret) + dev_warn(&dev->dev, "no hotplug settings from platform\n"); + + program_hpp_type2(dev, hpp.t2); + program_hpp_type1(dev, hpp.t1); + program_hpp_type0(dev, hpp.t0); + + if (dev->subordinate) { + list_for_each_entry(cdev, &dev->subordinate->devices, + bus_list) + pci_configure_slot(cdev); + } +} +EXPORT_SYMBOL_GPL(pci_configure_slot); diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c index a4494d78e7c..8aebe1e9d3d 100644 --- a/drivers/pci/hotplug/sgi_hotplug.c +++ b/drivers/pci/hotplug/sgi_hotplug.c @@ -90,11 +90,10 @@ static struct hotplug_slot_ops sn_hotplug_slot_ops = { static DEFINE_MUTEX(sn_hotplug_mutex); -static ssize_t path_show (struct hotplug_slot *bss_hotplug_slot, - char *buf) +static ssize_t path_show(struct pci_slot *pci_slot, char *buf) { int retval = -ENOENT; - struct slot *slot = bss_hotplug_slot->private; + struct slot *slot = pci_slot->hotplug->private; if (!slot) return retval; @@ -103,7 +102,7 @@ static ssize_t path_show (struct hotplug_slot *bss_hotplug_slot, return retval; } -static struct hotplug_slot_attribute sn_slot_path_attr = __ATTR_RO(path); +static struct pci_slot_attribute sn_slot_path_attr = __ATTR_RO(path); static int sn_pci_slot_valid(struct pci_bus *pci_bus, int device) { diff --git a/drivers/pci/hotplug/shpchp.h b/drivers/pci/hotplug/shpchp.h index 974e924ca96..bd588eb8e92 100644 --- a/drivers/pci/hotplug/shpchp.h +++ b/drivers/pci/hotplug/shpchp.h @@ -188,21 +188,12 @@ static inline const char *slot_name(struct slot *slot) #ifdef CONFIG_ACPI #include <linux/pci-acpi.h> -static inline int get_hp_params_from_firmware(struct pci_dev *dev, - struct hotplug_params *hpp) -{ - if (ACPI_FAILURE(acpi_get_hp_params_from_firmware(dev->bus, hpp))) - return -ENODEV; - return 0; -} - static inline int get_hp_hw_control_from_firmware(struct pci_dev *dev) { u32 flags = OSC_SHPC_NATIVE_HP_CONTROL; return acpi_get_hp_hw_control_from_firmware(dev, flags); } #else -#define get_hp_params_from_firmware(dev, hpp) (-ENODEV) #define get_hp_hw_control_from_firmware(dev) (0) #endif diff --git a/drivers/pci/hotplug/shpchp_pci.c b/drivers/pci/hotplug/shpchp_pci.c index aa315e52529..8c3d3219f22 100644 --- a/drivers/pci/hotplug/shpchp_pci.c +++ b/drivers/pci/hotplug/shpchp_pci.c @@ -34,66 +34,6 @@ #include "../pci.h" #include "shpchp.h" -static void program_fw_provided_values(struct pci_dev *dev) -{ - u16 pci_cmd, pci_bctl; - struct pci_dev *cdev; - struct hotplug_params hpp; - - /* Program hpp values for this device */ - if (!(dev->hdr_type == PCI_HEADER_TYPE_NORMAL || - (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE && - (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI))) - return; - - /* use default values if we can't get them from firmware */ - if (get_hp_params_from_firmware(dev, &hpp) || - !hpp.t0 || (hpp.t0->revision > 1)) { - warn("Could not get hotplug parameters. Use defaults\n"); - hpp.t0 = &hpp.type0_data; - hpp.t0->revision = 0; - hpp.t0->cache_line_size = 8; - hpp.t0->latency_timer = 0x40; - hpp.t0->enable_serr = 0; - hpp.t0->enable_perr = 0; - } - - pci_write_config_byte(dev, - PCI_CACHE_LINE_SIZE, hpp.t0->cache_line_size); - pci_write_config_byte(dev, PCI_LATENCY_TIMER, hpp.t0->latency_timer); - pci_read_config_word(dev, PCI_COMMAND, &pci_cmd); - if (hpp.t0->enable_serr) - pci_cmd |= PCI_COMMAND_SERR; - else - pci_cmd &= ~PCI_COMMAND_SERR; - if (hpp.t0->enable_perr) - pci_cmd |= PCI_COMMAND_PARITY; - else - pci_cmd &= ~PCI_COMMAND_PARITY; - pci_write_config_word(dev, PCI_COMMAND, pci_cmd); - - /* Program bridge control value and child devices */ - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) { - pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER, - hpp.t0->latency_timer); - pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &pci_bctl); - if (hpp.t0->enable_serr) - pci_bctl |= PCI_BRIDGE_CTL_SERR; - else - pci_bctl &= ~PCI_BRIDGE_CTL_SERR; - if (hpp.t0->enable_perr) - pci_bctl |= PCI_BRIDGE_CTL_PARITY; - else - pci_bctl &= ~PCI_BRIDGE_CTL_PARITY; - pci_write_config_word(dev, PCI_BRIDGE_CONTROL, pci_bctl); - if (dev->subordinate) { - list_for_each_entry(cdev, &dev->subordinate->devices, - bus_list) - program_fw_provided_values(cdev); - } - } -} - int __ref shpchp_configure_device(struct slot *p_slot) { struct pci_dev *dev; @@ -153,7 +93,7 @@ int __ref shpchp_configure_device(struct slot *p_slot) child->subordinate = pci_do_scan_bus(child); pci_bus_size_bridges(child); } - program_fw_provided_values(dev); + pci_configure_slot(dev); pci_dev_put(dev); } diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index e53eacd75c8..855dd7ca47f 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -37,9 +37,10 @@ #include <linux/iommu.h> #include <linux/intel-iommu.h> #include <linux/sysdev.h> +#include <linux/tboot.h> +#include <linux/dmi.h> #include <asm/cacheflush.h> #include <asm/iommu.h> -#include <asm/e820.h> #include "pci.h" #define ROOT_SIZE VTD_PAGE_SIZE @@ -56,15 +57,39 @@ #define MAX_AGAW_WIDTH 64 -#define DOMAIN_MAX_ADDR(gaw) ((((u64)1) << gaw) - 1) +#define __DOMAIN_MAX_PFN(gaw) ((((uint64_t)1) << (gaw-VTD_PAGE_SHIFT)) - 1) +#define __DOMAIN_MAX_ADDR(gaw) ((((uint64_t)1) << gaw) - 1) + +/* We limit DOMAIN_MAX_PFN to fit in an unsigned long, and DOMAIN_MAX_ADDR + to match. That way, we can use 'unsigned long' for PFNs with impunity. */ +#define DOMAIN_MAX_PFN(gaw) ((unsigned long) min_t(uint64_t, \ + __DOMAIN_MAX_PFN(gaw), (unsigned long)-1)) +#define DOMAIN_MAX_ADDR(gaw) (((uint64_t)__DOMAIN_MAX_PFN(gaw)) << VTD_PAGE_SHIFT) #define IOVA_PFN(addr) ((addr) >> PAGE_SHIFT) #define DMA_32BIT_PFN IOVA_PFN(DMA_BIT_MASK(32)) #define DMA_64BIT_PFN IOVA_PFN(DMA_BIT_MASK(64)) -#ifndef PHYSICAL_PAGE_MASK -#define PHYSICAL_PAGE_MASK PAGE_MASK -#endif + +/* VT-d pages must always be _smaller_ than MM pages. Otherwise things + are never going to work. */ +static inline unsigned long dma_to_mm_pfn(unsigned long dma_pfn) +{ + return dma_pfn >> (PAGE_SHIFT - VTD_PAGE_SHIFT); +} + +static inline unsigned long mm_to_dma_pfn(unsigned long mm_pfn) +{ + return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT); +} +static inline unsigned long page_to_dma_pfn(struct page *pg) +{ + return mm_to_dma_pfn(page_to_pfn(pg)); +} +static inline unsigned long virt_to_dma_pfn(void *p) +{ + return page_to_dma_pfn(virt_to_page(p)); +} /* global iommu list, set NULL for ignored DMAR units */ static struct intel_iommu **g_iommus; @@ -205,12 +230,17 @@ static inline void dma_set_pte_prot(struct dma_pte *pte, unsigned long prot) static inline u64 dma_pte_addr(struct dma_pte *pte) { - return (pte->val & VTD_PAGE_MASK); +#ifdef CONFIG_64BIT + return pte->val & VTD_PAGE_MASK; +#else + /* Must have a full atomic 64-bit read */ + return __cmpxchg64(pte, 0ULL, 0ULL) & VTD_PAGE_MASK; +#endif } -static inline void dma_set_pte_addr(struct dma_pte *pte, u64 addr) +static inline void dma_set_pte_pfn(struct dma_pte *pte, unsigned long pfn) { - pte->val |= (addr & VTD_PAGE_MASK); + pte->val |= (uint64_t)pfn << VTD_PAGE_SHIFT; } static inline bool dma_pte_present(struct dma_pte *pte) @@ -218,13 +248,19 @@ static inline bool dma_pte_present(struct dma_pte *pte) return (pte->val & 3) != 0; } +static inline int first_pte_in_page(struct dma_pte *pte) +{ + return !((unsigned long)pte & ~VTD_PAGE_MASK); +} + /* * This domain is a statically identity mapping domain. * 1. This domain creats a static 1:1 mapping to all usable memory. * 2. It maps to each iommu if successful. * 3. Each iommu mapps to this domain if successful. */ -struct dmar_domain *si_domain; +static struct dmar_domain *si_domain; +static int hw_pass_through = 1; /* devices under the same p2p bridge are owned in one domain */ #define DOMAIN_FLAG_P2P_MULTIPLE_DEVICES (1 << 0) @@ -245,7 +281,6 @@ struct dmar_domain { struct iova_domain iovad; /* iova's that belong to this domain */ struct dma_pte *pgd; /* virtual address */ - spinlock_t mapping_lock; /* page table lock */ int gaw; /* max guest address width */ /* adjusted guest address width, 0 is level 2 30-bit */ @@ -649,80 +684,78 @@ static inline int width_to_agaw(int width) static inline unsigned int level_to_offset_bits(int level) { - return (12 + (level - 1) * LEVEL_STRIDE); + return (level - 1) * LEVEL_STRIDE; } -static inline int address_level_offset(u64 addr, int level) +static inline int pfn_level_offset(unsigned long pfn, int level) { - return ((addr >> level_to_offset_bits(level)) & LEVEL_MASK); + return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK; } -static inline u64 level_mask(int level) +static inline unsigned long level_mask(int level) { - return ((u64)-1 << level_to_offset_bits(level)); + return -1UL << level_to_offset_bits(level); } -static inline u64 level_size(int level) +static inline unsigned long level_size(int level) { - return ((u64)1 << level_to_offset_bits(level)); + return 1UL << level_to_offset_bits(level); } -static inline u64 align_to_level(u64 addr, int level) +static inline unsigned long align_to_level(unsigned long pfn, int level) { - return ((addr + level_size(level) - 1) & level_mask(level)); + return (pfn + level_size(level) - 1) & level_mask(level); } -static struct dma_pte * addr_to_dma_pte(struct dmar_domain *domain, u64 addr) +static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, + unsigned long pfn) { - int addr_width = agaw_to_width(domain->agaw); + int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; struct dma_pte *parent, *pte = NULL; int level = agaw_to_level(domain->agaw); int offset; - unsigned long flags; BUG_ON(!domain->pgd); - - addr &= (((u64)1) << addr_width) - 1; + BUG_ON(addr_width < BITS_PER_LONG && pfn >> addr_width); parent = domain->pgd; - spin_lock_irqsave(&domain->mapping_lock, flags); while (level > 0) { void *tmp_page; - offset = address_level_offset(addr, level); + offset = pfn_level_offset(pfn, level); pte = &parent[offset]; if (level == 1) break; if (!dma_pte_present(pte)) { + uint64_t pteval; + tmp_page = alloc_pgtable_page(); - if (!tmp_page) { - spin_unlock_irqrestore(&domain->mapping_lock, - flags); + if (!tmp_page) return NULL; + + domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE); + pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE; + if (cmpxchg64(&pte->val, 0ULL, pteval)) { + /* Someone else set it while we were thinking; use theirs. */ + free_pgtable_page(tmp_page); + } else { + dma_pte_addr(pte); + domain_flush_cache(domain, pte, sizeof(*pte)); } - domain_flush_cache(domain, tmp_page, PAGE_SIZE); - dma_set_pte_addr(pte, virt_to_phys(tmp_page)); - /* - * high level table always sets r/w, last level page - * table control read/write - */ - dma_set_pte_readable(pte); - dma_set_pte_writable(pte); - domain_flush_cache(domain, pte, sizeof(*pte)); } parent = phys_to_virt(dma_pte_addr(pte)); level--; } - spin_unlock_irqrestore(&domain->mapping_lock, flags); return pte; } /* return address's pte at specific level */ -static struct dma_pte *dma_addr_level_pte(struct dmar_domain *domain, u64 addr, - int level) +static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain, + unsigned long pfn, + int level) { struct dma_pte *parent, *pte = NULL; int total = agaw_to_level(domain->agaw); @@ -730,7 +763,7 @@ static struct dma_pte *dma_addr_level_pte(struct dmar_domain *domain, u64 addr, parent = domain->pgd; while (level <= total) { - offset = address_level_offset(addr, total); + offset = pfn_level_offset(pfn, total); pte = &parent[offset]; if (level == total) return pte; @@ -743,74 +776,85 @@ static struct dma_pte *dma_addr_level_pte(struct dmar_domain *domain, u64 addr, return NULL; } -/* clear one page's page table */ -static void dma_pte_clear_one(struct dmar_domain *domain, u64 addr) -{ - struct dma_pte *pte = NULL; - - /* get last level pte */ - pte = dma_addr_level_pte(domain, addr, 1); - - if (pte) { - dma_clear_pte(pte); - domain_flush_cache(domain, pte, sizeof(*pte)); - } -} - /* clear last level pte, a tlb flush should be followed */ -static void dma_pte_clear_range(struct dmar_domain *domain, u64 start, u64 end) -{ - int addr_width = agaw_to_width(domain->agaw); - int npages; +static void dma_pte_clear_range(struct dmar_domain *domain, + unsigned long start_pfn, + unsigned long last_pfn) +{ + int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; + struct dma_pte *first_pte, *pte; + + BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width); + BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width); + BUG_ON(start_pfn > last_pfn); + + /* we don't need lock here; nobody else touches the iova range */ + do { + first_pte = pte = dma_pfn_level_pte(domain, start_pfn, 1); + if (!pte) { + start_pfn = align_to_level(start_pfn + 1, 2); + continue; + } + do { + dma_clear_pte(pte); + start_pfn++; + pte++; + } while (start_pfn <= last_pfn && !first_pte_in_page(pte)); - start &= (((u64)1) << addr_width) - 1; - end &= (((u64)1) << addr_width) - 1; - /* in case it's partial page */ - start &= PAGE_MASK; - end = PAGE_ALIGN(end); - npages = (end - start) / VTD_PAGE_SIZE; + domain_flush_cache(domain, first_pte, + (void *)pte - (void *)first_pte); - /* we don't need lock here, nobody else touches the iova range */ - while (npages--) { - dma_pte_clear_one(domain, start); - start += VTD_PAGE_SIZE; - } + } while (start_pfn && start_pfn <= last_pfn); } /* free page table pages. last level pte should already be cleared */ static void dma_pte_free_pagetable(struct dmar_domain *domain, - u64 start, u64 end) + unsigned long start_pfn, + unsigned long last_pfn) { - int addr_width = agaw_to_width(domain->agaw); - struct dma_pte *pte; + int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; + struct dma_pte *first_pte, *pte; int total = agaw_to_level(domain->agaw); int level; - u64 tmp; + unsigned long tmp; - start &= (((u64)1) << addr_width) - 1; - end &= (((u64)1) << addr_width) - 1; + BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width); + BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width); + BUG_ON(start_pfn > last_pfn); - /* we don't need lock here, nobody else touches the iova range */ + /* We don't need lock here; nobody else touches the iova range */ level = 2; while (level <= total) { - tmp = align_to_level(start, level); - if (tmp >= end || (tmp + level_size(level) > end)) + tmp = align_to_level(start_pfn, level); + + /* If we can't even clear one PTE at this level, we're done */ + if (tmp + level_size(level) - 1 > last_pfn) return; - while (tmp < end) { - pte = dma_addr_level_pte(domain, tmp, level); - if (pte) { - free_pgtable_page( - phys_to_virt(dma_pte_addr(pte))); - dma_clear_pte(pte); - domain_flush_cache(domain, pte, sizeof(*pte)); + do { + first_pte = pte = dma_pfn_level_pte(domain, tmp, level); + if (!pte) { + tmp = align_to_level(tmp + 1, level + 1); + continue; } - tmp += level_size(level); - } + do { + if (dma_pte_present(pte)) { + free_pgtable_page(phys_to_virt(dma_pte_addr(pte))); + dma_clear_pte(pte); + } + pte++; + tmp += level_size(level); + } while (!first_pte_in_page(pte) && + tmp + level_size(level) - 1 <= last_pfn); + + domain_flush_cache(domain, first_pte, + (void *)pte - (void *)first_pte); + + } while (tmp && tmp + level_size(level) - 1 <= last_pfn); level++; } /* free pgd */ - if (start == 0 && end >= ((((u64)1) << addr_width) - 1)) { + if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) { free_pgtable_page(domain->pgd); domain->pgd = NULL; } @@ -1036,11 +1080,11 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain, } static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did, - u64 addr, unsigned int pages) + unsigned long pfn, unsigned int pages) { unsigned int mask = ilog2(__roundup_pow_of_two(pages)); + uint64_t addr = (uint64_t)pfn << VTD_PAGE_SHIFT; - BUG_ON(addr & (~VTD_PAGE_MASK)); BUG_ON(pages == 0); /* @@ -1055,7 +1099,12 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did, else iommu->flush.flush_iotlb(iommu, did, addr, mask, DMA_TLB_PSI_FLUSH); - if (did) + + /* + * In caching mode, domain ID 0 is reserved for non-present to present + * mapping flush. Device IOTLB doesn't need to be flushed in this case. + */ + if (!cap_caching_mode(iommu->cap) || did) iommu_flush_dev_iotlb(iommu->domains[did], addr, mask); } @@ -1120,6 +1169,8 @@ static int iommu_init_domains(struct intel_iommu *iommu) pr_debug("Number of Domains supportd <%ld>\n", ndomains); nlongs = BITS_TO_LONGS(ndomains); + spin_lock_init(&iommu->lock); + /* TBD: there might be 64K domains, * consider other allocation for future chip */ @@ -1132,12 +1183,9 @@ static int iommu_init_domains(struct intel_iommu *iommu) GFP_KERNEL); if (!iommu->domains) { printk(KERN_ERR "Allocating domain array failed\n"); - kfree(iommu->domain_ids); return -ENOMEM; } - spin_lock_init(&iommu->lock); - /* * if Caching mode is set, then invalid translations are tagged * with domainid 0. Hence we need to pre-allocate it. @@ -1157,22 +1205,24 @@ void free_dmar_iommu(struct intel_iommu *iommu) int i; unsigned long flags; - i = find_first_bit(iommu->domain_ids, cap_ndoms(iommu->cap)); - for (; i < cap_ndoms(iommu->cap); ) { - domain = iommu->domains[i]; - clear_bit(i, iommu->domain_ids); + if ((iommu->domains) && (iommu->domain_ids)) { + i = find_first_bit(iommu->domain_ids, cap_ndoms(iommu->cap)); + for (; i < cap_ndoms(iommu->cap); ) { + domain = iommu->domains[i]; + clear_bit(i, iommu->domain_ids); + + spin_lock_irqsave(&domain->iommu_lock, flags); + if (--domain->iommu_count == 0) { + if (domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) + vm_domain_exit(domain); + else + domain_exit(domain); + } + spin_unlock_irqrestore(&domain->iommu_lock, flags); - spin_lock_irqsave(&domain->iommu_lock, flags); - if (--domain->iommu_count == 0) { - if (domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) - vm_domain_exit(domain); - else - domain_exit(domain); + i = find_next_bit(iommu->domain_ids, + cap_ndoms(iommu->cap), i+1); } - spin_unlock_irqrestore(&domain->iommu_lock, flags); - - i = find_next_bit(iommu->domain_ids, - cap_ndoms(iommu->cap), i+1); } if (iommu->gcmd & DMA_GCMD_TE) @@ -1272,7 +1322,6 @@ static void iommu_detach_domain(struct dmar_domain *domain, } static struct iova_domain reserved_iova_list; -static struct lock_class_key reserved_alloc_key; static struct lock_class_key reserved_rbtree_key; static void dmar_init_reserved_ranges(void) @@ -1280,12 +1329,9 @@ static void dmar_init_reserved_ranges(void) struct pci_dev *pdev = NULL; struct iova *iova; int i; - u64 addr, size; init_iova_domain(&reserved_iova_list, DMA_32BIT_PFN); - lockdep_set_class(&reserved_iova_list.iova_alloc_lock, - &reserved_alloc_key); lockdep_set_class(&reserved_iova_list.iova_rbtree_lock, &reserved_rbtree_key); @@ -1303,12 +1349,9 @@ static void dmar_init_reserved_ranges(void) r = &pdev->resource[i]; if (!r->flags || !(r->flags & IORESOURCE_MEM)) continue; - addr = r->start; - addr &= PHYSICAL_PAGE_MASK; - size = r->end - addr; - size = PAGE_ALIGN(size); - iova = reserve_iova(&reserved_iova_list, IOVA_PFN(addr), - IOVA_PFN(size + addr) - 1); + iova = reserve_iova(&reserved_iova_list, + IOVA_PFN(r->start), + IOVA_PFN(r->end)); if (!iova) printk(KERN_ERR "Reserve iova failed\n"); } @@ -1342,7 +1385,6 @@ static int domain_init(struct dmar_domain *domain, int guest_width) unsigned long sagaw; init_iova_domain(&domain->iovad, DMA_32BIT_PFN); - spin_lock_init(&domain->mapping_lock); spin_lock_init(&domain->iommu_lock); domain_reserve_special_ranges(domain); @@ -1389,7 +1431,6 @@ static void domain_exit(struct dmar_domain *domain) { struct dmar_drhd_unit *drhd; struct intel_iommu *iommu; - u64 end; /* Domain 0 is reserved, so dont process it */ if (!domain) @@ -1398,14 +1439,12 @@ static void domain_exit(struct dmar_domain *domain) domain_remove_dev_info(domain); /* destroy iovas */ put_iova_domain(&domain->iovad); - end = DOMAIN_MAX_ADDR(domain->gaw); - end = end & (~PAGE_MASK); /* clear ptes */ - dma_pte_clear_range(domain, 0, end); + dma_pte_clear_range(domain, 0, DOMAIN_MAX_PFN(domain->gaw)); /* free page tables */ - dma_pte_free_pagetable(domain, 0, end); + dma_pte_free_pagetable(domain, 0, DOMAIN_MAX_PFN(domain->gaw)); for_each_active_iommu(iommu, drhd) if (test_bit(iommu->seq_id, &domain->iommu_bmp)) @@ -1476,7 +1515,6 @@ static int domain_context_mapping_one(struct dmar_domain *domain, int segment, } set_bit(num, iommu->domain_ids); - set_bit(iommu->seq_id, &domain->iommu_bmp); iommu->domains[num] = domain; id = num; } @@ -1619,42 +1657,94 @@ static int domain_context_mapped(struct pci_dev *pdev) tmp->devfn); } -static int -domain_page_mapping(struct dmar_domain *domain, dma_addr_t iova, - u64 hpa, size_t size, int prot) +/* Returns a number of VTD pages, but aligned to MM page size */ +static inline unsigned long aligned_nrpages(unsigned long host_addr, + size_t size) { - u64 start_pfn, end_pfn; - struct dma_pte *pte; - int index; - int addr_width = agaw_to_width(domain->agaw); + host_addr &= ~PAGE_MASK; + return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT; +} + +static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, + struct scatterlist *sg, unsigned long phys_pfn, + unsigned long nr_pages, int prot) +{ + struct dma_pte *first_pte = NULL, *pte = NULL; + phys_addr_t uninitialized_var(pteval); + int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; + unsigned long sg_res; - hpa &= (((u64)1) << addr_width) - 1; + BUG_ON(addr_width < BITS_PER_LONG && (iov_pfn + nr_pages - 1) >> addr_width); if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0) return -EINVAL; - iova &= PAGE_MASK; - start_pfn = ((u64)hpa) >> VTD_PAGE_SHIFT; - end_pfn = (VTD_PAGE_ALIGN(((u64)hpa) + size)) >> VTD_PAGE_SHIFT; - index = 0; - while (start_pfn < end_pfn) { - pte = addr_to_dma_pte(domain, iova + VTD_PAGE_SIZE * index); - if (!pte) - return -ENOMEM; + + prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP; + + if (sg) + sg_res = 0; + else { + sg_res = nr_pages + 1; + pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot; + } + + while (nr_pages--) { + uint64_t tmp; + + if (!sg_res) { + sg_res = aligned_nrpages(sg->offset, sg->length); + sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + sg->offset; + sg->dma_length = sg->length; + pteval = page_to_phys(sg_page(sg)) | prot; + } + if (!pte) { + first_pte = pte = pfn_to_dma_pte(domain, iov_pfn); + if (!pte) + return -ENOMEM; + } /* We don't need lock here, nobody else * touches the iova range */ - BUG_ON(dma_pte_addr(pte)); - dma_set_pte_addr(pte, start_pfn << VTD_PAGE_SHIFT); - dma_set_pte_prot(pte, prot); - if (prot & DMA_PTE_SNP) - dma_set_pte_snp(pte); - domain_flush_cache(domain, pte, sizeof(*pte)); - start_pfn++; - index++; + tmp = cmpxchg64_local(&pte->val, 0ULL, pteval); + if (tmp) { + static int dumps = 5; + printk(KERN_CRIT "ERROR: DMA PTE for vPFN 0x%lx already set (to %llx not %llx)\n", + iov_pfn, tmp, (unsigned long long)pteval); + if (dumps) { + dumps--; + debug_dma_dump_mappings(NULL); + } + WARN_ON(1); + } + pte++; + if (!nr_pages || first_pte_in_page(pte)) { + domain_flush_cache(domain, first_pte, + (void *)pte - (void *)first_pte); + pte = NULL; + } + iov_pfn++; + pteval += VTD_PAGE_SIZE; + sg_res--; + if (!sg_res) + sg = sg_next(sg); } return 0; } +static inline int domain_sg_mapping(struct dmar_domain *domain, unsigned long iov_pfn, + struct scatterlist *sg, unsigned long nr_pages, + int prot) +{ + return __domain_mapping(domain, iov_pfn, sg, 0, nr_pages, prot); +} + +static inline int domain_pfn_mapping(struct dmar_domain *domain, unsigned long iov_pfn, + unsigned long phys_pfn, unsigned long nr_pages, + int prot) +{ + return __domain_mapping(domain, iov_pfn, NULL, phys_pfn, nr_pages, prot); +} + static void iommu_detach_dev(struct intel_iommu *iommu, u8 bus, u8 devfn) { if (!iommu) @@ -1845,58 +1935,82 @@ error: static int iommu_identity_mapping; +static int iommu_domain_identity_map(struct dmar_domain *domain, + unsigned long long start, + unsigned long long end) +{ + unsigned long first_vpfn = start >> VTD_PAGE_SHIFT; + unsigned long last_vpfn = end >> VTD_PAGE_SHIFT; + + if (!reserve_iova(&domain->iovad, dma_to_mm_pfn(first_vpfn), + dma_to_mm_pfn(last_vpfn))) { + printk(KERN_ERR "IOMMU: reserve iova failed\n"); + return -ENOMEM; + } + + pr_debug("Mapping reserved region %llx-%llx for domain %d\n", + start, end, domain->id); + /* + * RMRR range might have overlap with physical memory range, + * clear it first + */ + dma_pte_clear_range(domain, first_vpfn, last_vpfn); + + return domain_pfn_mapping(domain, first_vpfn, first_vpfn, + last_vpfn - first_vpfn + 1, + DMA_PTE_READ|DMA_PTE_WRITE); +} + static int iommu_prepare_identity_map(struct pci_dev *pdev, unsigned long long start, unsigned long long end) { struct dmar_domain *domain; - unsigned long size; - unsigned long long base; int ret; - printk(KERN_INFO - "IOMMU: Setting identity map for device %s [0x%Lx - 0x%Lx]\n", - pci_name(pdev), start, end); - if (iommu_identity_mapping) - domain = si_domain; - else - /* page table init */ - domain = get_domain_for_dev(pdev, DEFAULT_DOMAIN_ADDRESS_WIDTH); + domain = get_domain_for_dev(pdev, DEFAULT_DOMAIN_ADDRESS_WIDTH); if (!domain) return -ENOMEM; - /* The address might not be aligned */ - base = start & PAGE_MASK; - size = end - base; - size = PAGE_ALIGN(size); - if (!reserve_iova(&domain->iovad, IOVA_PFN(base), - IOVA_PFN(base + size) - 1)) { - printk(KERN_ERR "IOMMU: reserve iova failed\n"); - ret = -ENOMEM; - goto error; + /* For _hardware_ passthrough, don't bother. But for software + passthrough, we do it anyway -- it may indicate a memory + range which is reserved in E820, so which didn't get set + up to start with in si_domain */ + if (domain == si_domain && hw_pass_through) { + printk("Ignoring identity map for HW passthrough device %s [0x%Lx - 0x%Lx]\n", + pci_name(pdev), start, end); + return 0; } - pr_debug("Mapping reserved region %lx@%llx for %s\n", - size, base, pci_name(pdev)); - /* - * RMRR range might have overlap with physical memory range, - * clear it first - */ - dma_pte_clear_range(domain, base, base + size); + printk(KERN_INFO + "IOMMU: Setting identity map for device %s [0x%Lx - 0x%Lx]\n", + pci_name(pdev), start, end); + + if (end >> agaw_to_width(domain->agaw)) { + WARN(1, "Your BIOS is broken; RMRR exceeds permitted address width (%d bits)\n" + "BIOS vendor: %s; Ver: %s; Product Version: %s\n", + agaw_to_width(domain->agaw), + dmi_get_system_info(DMI_BIOS_VENDOR), + dmi_get_system_info(DMI_BIOS_VERSION), + dmi_get_system_info(DMI_PRODUCT_VERSION)); + ret = -EIO; + goto error; + } - ret = domain_page_mapping(domain, base, base, size, - DMA_PTE_READ|DMA_PTE_WRITE); + ret = iommu_domain_identity_map(domain, start, end); if (ret) goto error; /* context entry init */ ret = domain_context_mapping(domain, pdev, CONTEXT_TT_MULTI_LEVEL); - if (!ret) - return 0; -error: + if (ret) + goto error; + + return 0; + + error: domain_exit(domain); return ret; - } static inline int iommu_prepare_rmrr_dev(struct dmar_rmrr_unit *rmrr, @@ -1908,64 +2022,6 @@ static inline int iommu_prepare_rmrr_dev(struct dmar_rmrr_unit *rmrr, rmrr->end_address + 1); } -#ifdef CONFIG_DMAR_GFX_WA -struct iommu_prepare_data { - struct pci_dev *pdev; - int ret; -}; - -static int __init iommu_prepare_work_fn(unsigned long start_pfn, - unsigned long end_pfn, void *datax) -{ - struct iommu_prepare_data *data; - - data = (struct iommu_prepare_data *)datax; - - data->ret = iommu_prepare_identity_map(data->pdev, - start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT); - return data->ret; - -} - -static int __init iommu_prepare_with_active_regions(struct pci_dev *pdev) -{ - int nid; - struct iommu_prepare_data data; - - data.pdev = pdev; - data.ret = 0; - - for_each_online_node(nid) { - work_with_active_regions(nid, iommu_prepare_work_fn, &data); - if (data.ret) - return data.ret; - } - return data.ret; -} - -static void __init iommu_prepare_gfx_mapping(void) -{ - struct pci_dev *pdev = NULL; - int ret; - - for_each_pci_dev(pdev) { - if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO || - !IS_GFX_DEVICE(pdev)) - continue; - printk(KERN_INFO "IOMMU: gfx device %s 1-1 mapping\n", - pci_name(pdev)); - ret = iommu_prepare_with_active_regions(pdev); - if (ret) - printk(KERN_ERR "IOMMU: mapping reserved region failed\n"); - } -} -#else /* !CONFIG_DMAR_GFX_WA */ -static inline void iommu_prepare_gfx_mapping(void) -{ - return; -} -#endif - #ifdef CONFIG_DMAR_FLOPPY_WA static inline void iommu_prepare_isa(void) { @@ -1976,12 +2032,12 @@ static inline void iommu_prepare_isa(void) if (!pdev) return; - printk(KERN_INFO "IOMMU: Prepare 0-16M unity mapping for LPC\n"); + printk(KERN_INFO "IOMMU: Prepare 0-16MiB unity mapping for LPC\n"); ret = iommu_prepare_identity_map(pdev, 0, 16*1024*1024); if (ret) - printk(KERN_ERR "IOMMU: Failed to create 0-64M identity map, " - "floppy might not work\n"); + printk(KERN_ERR "IOMMU: Failed to create 0-16MiB identity map; " + "floppy might not work\n"); } #else @@ -1991,34 +2047,31 @@ static inline void iommu_prepare_isa(void) } #endif /* !CONFIG_DMAR_FLPY_WA */ -/* Initialize each context entry as pass through.*/ -static int __init init_context_pass_through(void) +static int md_domain_init(struct dmar_domain *domain, int guest_width); + +static int __init si_domain_work_fn(unsigned long start_pfn, + unsigned long end_pfn, void *datax) { - struct pci_dev *pdev = NULL; - struct dmar_domain *domain; - int ret; + int *ret = datax; + + *ret = iommu_domain_identity_map(si_domain, + (uint64_t)start_pfn << PAGE_SHIFT, + (uint64_t)end_pfn << PAGE_SHIFT); + return *ret; - for_each_pci_dev(pdev) { - domain = get_domain_for_dev(pdev, DEFAULT_DOMAIN_ADDRESS_WIDTH); - ret = domain_context_mapping(domain, pdev, - CONTEXT_TT_PASS_THROUGH); - if (ret) - return ret; - } - return 0; } -static int md_domain_init(struct dmar_domain *domain, int guest_width); -static int si_domain_init(void) +static int __init si_domain_init(int hw) { struct dmar_drhd_unit *drhd; struct intel_iommu *iommu; - int ret = 0; + int nid, ret = 0; si_domain = alloc_domain(); if (!si_domain) return -EFAULT; + pr_debug("Identity mapping domain is domain %d\n", si_domain->id); for_each_active_iommu(iommu, drhd) { ret = iommu_attach_domain(si_domain, iommu); @@ -2035,6 +2088,15 @@ static int si_domain_init(void) si_domain->flags = DOMAIN_FLAG_STATIC_IDENTITY; + if (hw) + return 0; + + for_each_online_node(nid) { + work_with_active_regions(nid, si_domain_work_fn, &ret); + if (ret) + return ret; + } + return 0; } @@ -2055,15 +2117,23 @@ static int identity_mapping(struct pci_dev *pdev) } static int domain_add_dev_info(struct dmar_domain *domain, - struct pci_dev *pdev) + struct pci_dev *pdev, + int translation) { struct device_domain_info *info; unsigned long flags; + int ret; info = alloc_devinfo_mem(); if (!info) return -ENOMEM; + ret = domain_context_mapping(domain, pdev, translation); + if (ret) { + free_devinfo_mem(info); + return ret; + } + info->segment = pci_domain_nr(pdev->bus); info->bus = pdev->bus->number; info->devfn = pdev->devfn; @@ -2079,33 +2149,67 @@ static int domain_add_dev_info(struct dmar_domain *domain, return 0; } -static int iommu_prepare_static_identity_mapping(void) +static int iommu_should_identity_map(struct pci_dev *pdev, int startup) +{ + if (iommu_identity_mapping == 2) + return IS_GFX_DEVICE(pdev); + + /* + * We want to start off with all devices in the 1:1 domain, and + * take them out later if we find they can't access all of memory. + * + * However, we can't do this for PCI devices behind bridges, + * because all PCI devices behind the same bridge will end up + * with the same source-id on their transactions. + * + * Practically speaking, we can't change things around for these + * devices at run-time, because we can't be sure there'll be no + * DMA transactions in flight for any of their siblings. + * + * So PCI devices (unless they're on the root bus) as well as + * their parent PCI-PCI or PCIe-PCI bridges must be left _out_ of + * the 1:1 domain, just in _case_ one of their siblings turns out + * not to be able to map all of memory. + */ + if (!pdev->is_pcie) { + if (!pci_is_root_bus(pdev->bus)) + return 0; + if (pdev->class >> 8 == PCI_CLASS_BRIDGE_PCI) + return 0; + } else if (pdev->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) + return 0; + + /* + * At boot time, we don't yet know if devices will be 64-bit capable. + * Assume that they will -- if they turn out not to be, then we can + * take them out of the 1:1 domain later. + */ + if (!startup) + return pdev->dma_mask > DMA_BIT_MASK(32); + + return 1; +} + +static int __init iommu_prepare_static_identity_mapping(int hw) { - int i; struct pci_dev *pdev = NULL; int ret; - ret = si_domain_init(); + ret = si_domain_init(hw); if (ret) return -EFAULT; - printk(KERN_INFO "IOMMU: Setting identity map:\n"); for_each_pci_dev(pdev) { - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - - if (ei->type == E820_RAM) { - ret = iommu_prepare_identity_map(pdev, - ei->addr, ei->addr + ei->size); - if (ret) { - printk(KERN_INFO "1:1 mapping to one domain failed.\n"); - return -EFAULT; - } - } + if (iommu_should_identity_map(pdev, 1)) { + printk(KERN_INFO "IOMMU: %s identity mapping for device %s\n", + hw ? "hardware" : "software", pci_name(pdev)); + + ret = domain_add_dev_info(si_domain, pdev, + hw ? CONTEXT_TT_PASS_THROUGH : + CONTEXT_TT_MULTI_LEVEL); + if (ret) + return ret; } - ret = domain_add_dev_info(si_domain, pdev); - if (ret) - return ret; } return 0; @@ -2118,14 +2222,6 @@ int __init init_dmars(void) struct pci_dev *pdev; struct intel_iommu *iommu; int i, ret; - int pass_through = 1; - - /* - * In case pass through can not be enabled, iommu tries to use identity - * mapping. - */ - if (iommu_pass_through) - iommu_identity_mapping = 1; /* * for each drhd @@ -2153,7 +2249,6 @@ int __init init_dmars(void) deferred_flush = kzalloc(g_num_of_iommus * sizeof(struct deferred_flush_tables), GFP_KERNEL); if (!deferred_flush) { - kfree(g_iommus); ret = -ENOMEM; goto error; } @@ -2180,14 +2275,8 @@ int __init init_dmars(void) goto error; } if (!ecap_pass_through(iommu->ecap)) - pass_through = 0; + hw_pass_through = 0; } - if (iommu_pass_through) - if (!pass_through) { - printk(KERN_INFO - "Pass Through is not supported by hardware.\n"); - iommu_pass_through = 0; - } /* * Start from the sane iommu hardware state. @@ -2242,62 +2331,57 @@ int __init init_dmars(void) } } + if (iommu_pass_through) + iommu_identity_mapping = 1; +#ifdef CONFIG_DMAR_BROKEN_GFX_WA + else + iommu_identity_mapping = 2; +#endif /* - * If pass through is set and enabled, context entries of all pci - * devices are intialized by pass through translation type. + * If pass through is not set or not enabled, setup context entries for + * identity mappings for rmrr, gfx, and isa and may fall back to static + * identity mapping if iommu_identity_mapping is set. */ - if (iommu_pass_through) { - ret = init_context_pass_through(); + if (iommu_identity_mapping) { + ret = iommu_prepare_static_identity_mapping(hw_pass_through); if (ret) { - printk(KERN_ERR "IOMMU: Pass through init failed.\n"); - iommu_pass_through = 0; + printk(KERN_CRIT "Failed to setup IOMMU pass-through\n"); + goto error; } } - /* - * If pass through is not set or not enabled, setup context entries for - * identity mappings for rmrr, gfx, and isa and may fall back to static - * identity mapping if iommu_identity_mapping is set. + * For each rmrr + * for each dev attached to rmrr + * do + * locate drhd for dev, alloc domain for dev + * allocate free domain + * allocate page table entries for rmrr + * if context not allocated for bus + * allocate and init context + * set present in root table for this bus + * init context with domain, translation etc + * endfor + * endfor */ - if (!iommu_pass_through) { - if (iommu_identity_mapping) - iommu_prepare_static_identity_mapping(); - /* - * For each rmrr - * for each dev attached to rmrr - * do - * locate drhd for dev, alloc domain for dev - * allocate free domain - * allocate page table entries for rmrr - * if context not allocated for bus - * allocate and init context - * set present in root table for this bus - * init context with domain, translation etc - * endfor - * endfor - */ - printk(KERN_INFO "IOMMU: Setting RMRR:\n"); - for_each_rmrr_units(rmrr) { - for (i = 0; i < rmrr->devices_cnt; i++) { - pdev = rmrr->devices[i]; - /* - * some BIOS lists non-exist devices in DMAR - * table. - */ - if (!pdev) - continue; - ret = iommu_prepare_rmrr_dev(rmrr, pdev); - if (ret) - printk(KERN_ERR - "IOMMU: mapping reserved region failed\n"); - } + printk(KERN_INFO "IOMMU: Setting RMRR:\n"); + for_each_rmrr_units(rmrr) { + for (i = 0; i < rmrr->devices_cnt; i++) { + pdev = rmrr->devices[i]; + /* + * some BIOS lists non-exist devices in DMAR + * table. + */ + if (!pdev) + continue; + ret = iommu_prepare_rmrr_dev(rmrr, pdev); + if (ret) + printk(KERN_ERR + "IOMMU: mapping reserved region failed\n"); } - - iommu_prepare_gfx_mapping(); - - iommu_prepare_isa(); } + iommu_prepare_isa(); + /* * for each drhd * enable fault log @@ -2320,11 +2404,12 @@ int __init init_dmars(void) iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL); iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); - iommu_disable_protect_mem_regions(iommu); ret = iommu_enable_translation(iommu); if (ret) goto error; + + iommu_disable_protect_mem_regions(iommu); } return 0; @@ -2339,58 +2424,39 @@ error: return ret; } -static inline u64 aligned_size(u64 host_addr, size_t size) -{ - u64 addr; - addr = (host_addr & (~PAGE_MASK)) + size; - return PAGE_ALIGN(addr); -} - -struct iova * -iommu_alloc_iova(struct dmar_domain *domain, size_t size, u64 end) -{ - struct iova *piova; - - /* Make sure it's in range */ - end = min_t(u64, DOMAIN_MAX_ADDR(domain->gaw), end); - if (!size || (IOVA_START_ADDR + size > end)) - return NULL; - - piova = alloc_iova(&domain->iovad, - size >> PAGE_SHIFT, IOVA_PFN(end), 1); - return piova; -} - -static struct iova * -__intel_alloc_iova(struct device *dev, struct dmar_domain *domain, - size_t size, u64 dma_mask) +/* This takes a number of _MM_ pages, not VTD pages */ +static struct iova *intel_alloc_iova(struct device *dev, + struct dmar_domain *domain, + unsigned long nrpages, uint64_t dma_mask) { struct pci_dev *pdev = to_pci_dev(dev); struct iova *iova = NULL; - if (dma_mask <= DMA_BIT_MASK(32) || dmar_forcedac) - iova = iommu_alloc_iova(domain, size, dma_mask); - else { + /* Restrict dma_mask to the width that the iommu can handle */ + dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw), dma_mask); + + if (!dmar_forcedac && dma_mask > DMA_BIT_MASK(32)) { /* * First try to allocate an io virtual address in * DMA_BIT_MASK(32) and if that fails then try allocating * from higher range */ - iova = iommu_alloc_iova(domain, size, DMA_BIT_MASK(32)); - if (!iova) - iova = iommu_alloc_iova(domain, size, dma_mask); - } - - if (!iova) { - printk(KERN_ERR"Allocating iova for %s failed", pci_name(pdev)); + iova = alloc_iova(&domain->iovad, nrpages, + IOVA_PFN(DMA_BIT_MASK(32)), 1); + if (iova) + return iova; + } + iova = alloc_iova(&domain->iovad, nrpages, IOVA_PFN(dma_mask), 1); + if (unlikely(!iova)) { + printk(KERN_ERR "Allocating %ld-page iova for %s failed", + nrpages, pci_name(pdev)); return NULL; } return iova; } -static struct dmar_domain * -get_valid_domain_for_dev(struct pci_dev *pdev) +static struct dmar_domain *__get_valid_domain_for_dev(struct pci_dev *pdev) { struct dmar_domain *domain; int ret; @@ -2418,22 +2484,42 @@ get_valid_domain_for_dev(struct pci_dev *pdev) return domain; } +static inline struct dmar_domain *get_valid_domain_for_dev(struct pci_dev *dev) +{ + struct device_domain_info *info; + + /* No lock here, assumes no domain exit in normal case */ + info = dev->dev.archdata.iommu; + if (likely(info)) + return info->domain; + + return __get_valid_domain_for_dev(dev); +} + static int iommu_dummy(struct pci_dev *pdev) { return pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO; } /* Check if the pdev needs to go through non-identity map and unmap process.*/ -static int iommu_no_mapping(struct pci_dev *pdev) +static int iommu_no_mapping(struct device *dev) { + struct pci_dev *pdev; int found; + if (unlikely(dev->bus != &pci_bus_type)) + return 1; + + pdev = to_pci_dev(dev); + if (iommu_dummy(pdev)) + return 1; + if (!iommu_identity_mapping) - return iommu_dummy(pdev); + return 0; found = identity_mapping(pdev); if (found) { - if (pdev->dma_mask > DMA_BIT_MASK(32)) + if (iommu_should_identity_map(pdev, 0)) return 1; else { /* @@ -2450,9 +2536,12 @@ static int iommu_no_mapping(struct pci_dev *pdev) * In case of a detached 64 bit DMA device from vm, the device * is put into si_domain for identity mapping. */ - if (pdev->dma_mask > DMA_BIT_MASK(32)) { + if (iommu_should_identity_map(pdev, 0)) { int ret; - ret = domain_add_dev_info(si_domain, pdev); + ret = domain_add_dev_info(si_domain, pdev, + hw_pass_through ? + CONTEXT_TT_PASS_THROUGH : + CONTEXT_TT_MULTI_LEVEL); if (!ret) { printk(KERN_INFO "64bit %s uses identity mapping\n", pci_name(pdev)); @@ -2461,7 +2550,7 @@ static int iommu_no_mapping(struct pci_dev *pdev) } } - return iommu_dummy(pdev); + return 0; } static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr, @@ -2474,10 +2563,11 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr, int prot = 0; int ret; struct intel_iommu *iommu; + unsigned long paddr_pfn = paddr >> PAGE_SHIFT; BUG_ON(dir == DMA_NONE); - if (iommu_no_mapping(pdev)) + if (iommu_no_mapping(hwdev)) return paddr; domain = get_valid_domain_for_dev(pdev); @@ -2485,14 +2575,13 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr, return 0; iommu = domain_get_iommu(domain); - size = aligned_size((u64)paddr, size); + size = aligned_nrpages(paddr, size); - iova = __intel_alloc_iova(hwdev, domain, size, pdev->dma_mask); + iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size), + pdev->dma_mask); if (!iova) goto error; - start_paddr = (phys_addr_t)iova->pfn_lo << PAGE_SHIFT; - /* * Check if DMAR supports zero-length reads on write only * mappings.. @@ -2508,20 +2597,20 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr, * might have two guest_addr mapping to the same host paddr, but this * is not a big problem */ - ret = domain_page_mapping(domain, start_paddr, - ((u64)paddr) & PHYSICAL_PAGE_MASK, - size, prot); + ret = domain_pfn_mapping(domain, mm_to_dma_pfn(iova->pfn_lo), + mm_to_dma_pfn(paddr_pfn), size, prot); if (ret) goto error; /* it's a non-present to present mapping. Only flush if caching mode */ if (cap_caching_mode(iommu->cap)) - iommu_flush_iotlb_psi(iommu, 0, start_paddr, - size >> VTD_PAGE_SHIFT); + iommu_flush_iotlb_psi(iommu, 0, mm_to_dma_pfn(iova->pfn_lo), size); else iommu_flush_write_buffer(iommu); - return start_paddr + ((u64)paddr & (~PAGE_MASK)); + start_paddr = (phys_addr_t)iova->pfn_lo << PAGE_SHIFT; + start_paddr += paddr & ~PAGE_MASK; + return start_paddr; error: if (iova) @@ -2561,10 +2650,9 @@ static void flush_unmaps(void) unsigned long mask; struct iova *iova = deferred_flush[i].iova[j]; - mask = (iova->pfn_hi - iova->pfn_lo + 1) << PAGE_SHIFT; - mask = ilog2(mask >> VTD_PAGE_SHIFT); + mask = ilog2(mm_to_dma_pfn(iova->pfn_hi - iova->pfn_lo + 1)); iommu_flush_dev_iotlb(deferred_flush[i].domain[j], - iova->pfn_lo << PAGE_SHIFT, mask); + (uint64_t)iova->pfn_lo << PAGE_SHIFT, mask); __free_iova(&deferred_flush[i].domain[j]->iovad, iova); } deferred_flush[i].next = 0; @@ -2614,11 +2702,11 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr, { struct pci_dev *pdev = to_pci_dev(dev); struct dmar_domain *domain; - unsigned long start_addr; + unsigned long start_pfn, last_pfn; struct iova *iova; struct intel_iommu *iommu; - if (iommu_no_mapping(pdev)) + if (iommu_no_mapping(dev)) return; domain = find_domain(pdev); @@ -2627,22 +2715,25 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr, iommu = domain_get_iommu(domain); iova = find_iova(&domain->iovad, IOVA_PFN(dev_addr)); - if (!iova) + if (WARN_ONCE(!iova, "Driver unmaps unmatched page at PFN %llx\n", + (unsigned long long)dev_addr)) return; - start_addr = iova->pfn_lo << PAGE_SHIFT; - size = aligned_size((u64)dev_addr, size); + start_pfn = mm_to_dma_pfn(iova->pfn_lo); + last_pfn = mm_to_dma_pfn(iova->pfn_hi + 1) - 1; - pr_debug("Device %s unmapping: %zx@%llx\n", - pci_name(pdev), size, (unsigned long long)start_addr); + pr_debug("Device %s unmapping: pfn %lx-%lx\n", + pci_name(pdev), start_pfn, last_pfn); /* clear the whole page */ - dma_pte_clear_range(domain, start_addr, start_addr + size); + dma_pte_clear_range(domain, start_pfn, last_pfn); + /* free page tables */ - dma_pte_free_pagetable(domain, start_addr, start_addr + size); + dma_pte_free_pagetable(domain, start_pfn, last_pfn); + if (intel_iommu_strict) { - iommu_flush_iotlb_psi(iommu, domain->id, start_addr, - size >> VTD_PAGE_SHIFT); + iommu_flush_iotlb_psi(iommu, domain->id, start_pfn, + last_pfn - start_pfn + 1); /* free iova */ __free_iova(&domain->iovad, iova); } else { @@ -2654,12 +2745,6 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr, } } -static void intel_unmap_single(struct device *dev, dma_addr_t dev_addr, size_t size, - int dir) -{ - intel_unmap_page(dev, dev_addr, size, dir, NULL); -} - static void *intel_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags) { @@ -2692,7 +2777,7 @@ static void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr, size = PAGE_ALIGN(size); order = get_order(size); - intel_unmap_single(hwdev, dma_handle, size, DMA_BIDIRECTIONAL); + intel_unmap_page(hwdev, dma_handle, size, DMA_BIDIRECTIONAL, NULL); free_pages((unsigned long)vaddr, order); } @@ -2700,17 +2785,13 @@ static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist, int nelems, enum dma_data_direction dir, struct dma_attrs *attrs) { - int i; struct pci_dev *pdev = to_pci_dev(hwdev); struct dmar_domain *domain; - unsigned long start_addr; + unsigned long start_pfn, last_pfn; struct iova *iova; - size_t size = 0; - phys_addr_t addr; - struct scatterlist *sg; struct intel_iommu *iommu; - if (iommu_no_mapping(pdev)) + if (iommu_no_mapping(hwdev)) return; domain = find_domain(pdev); @@ -2719,25 +2800,31 @@ static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist, iommu = domain_get_iommu(domain); iova = find_iova(&domain->iovad, IOVA_PFN(sglist[0].dma_address)); - if (!iova) + if (WARN_ONCE(!iova, "Driver unmaps unmatched sglist at PFN %llx\n", + (unsigned long long)sglist[0].dma_address)) return; - for_each_sg(sglist, sg, nelems, i) { - addr = page_to_phys(sg_page(sg)) + sg->offset; - size += aligned_size((u64)addr, sg->length); - } - start_addr = iova->pfn_lo << PAGE_SHIFT; + start_pfn = mm_to_dma_pfn(iova->pfn_lo); + last_pfn = mm_to_dma_pfn(iova->pfn_hi + 1) - 1; /* clear the whole page */ - dma_pte_clear_range(domain, start_addr, start_addr + size); - /* free page tables */ - dma_pte_free_pagetable(domain, start_addr, start_addr + size); + dma_pte_clear_range(domain, start_pfn, last_pfn); - iommu_flush_iotlb_psi(iommu, domain->id, start_addr, - size >> VTD_PAGE_SHIFT); + /* free page tables */ + dma_pte_free_pagetable(domain, start_pfn, last_pfn); - /* free iova */ - __free_iova(&domain->iovad, iova); + if (intel_iommu_strict) { + iommu_flush_iotlb_psi(iommu, domain->id, start_pfn, + last_pfn - start_pfn + 1); + /* free iova */ + __free_iova(&domain->iovad, iova); + } else { + add_unmap(domain, iova); + /* + * queue up the release of the unmap to save the 1/6th of the + * cpu used up by the iotlb flush operation... + */ + } } static int intel_nontranslate_map_sg(struct device *hddev, @@ -2757,21 +2844,20 @@ static int intel_nontranslate_map_sg(struct device *hddev, static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int nelems, enum dma_data_direction dir, struct dma_attrs *attrs) { - phys_addr_t addr; int i; struct pci_dev *pdev = to_pci_dev(hwdev); struct dmar_domain *domain; size_t size = 0; int prot = 0; - size_t offset = 0; + size_t offset_pfn = 0; struct iova *iova = NULL; int ret; struct scatterlist *sg; - unsigned long start_addr; + unsigned long start_vpfn; struct intel_iommu *iommu; BUG_ON(dir == DMA_NONE); - if (iommu_no_mapping(pdev)) + if (iommu_no_mapping(hwdev)) return intel_nontranslate_map_sg(hwdev, sglist, nelems, dir); domain = get_valid_domain_for_dev(pdev); @@ -2780,12 +2866,11 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int ne iommu = domain_get_iommu(domain); - for_each_sg(sglist, sg, nelems, i) { - addr = page_to_phys(sg_page(sg)) + sg->offset; - size += aligned_size((u64)addr, sg->length); - } + for_each_sg(sglist, sg, nelems, i) + size += aligned_nrpages(sg->offset, sg->length); - iova = __intel_alloc_iova(hwdev, domain, size, pdev->dma_mask); + iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size), + pdev->dma_mask); if (!iova) { sglist->dma_length = 0; return 0; @@ -2801,35 +2886,24 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int ne if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) prot |= DMA_PTE_WRITE; - start_addr = iova->pfn_lo << PAGE_SHIFT; - offset = 0; - for_each_sg(sglist, sg, nelems, i) { - addr = page_to_phys(sg_page(sg)) + sg->offset; - size = aligned_size((u64)addr, sg->length); - ret = domain_page_mapping(domain, start_addr + offset, - ((u64)addr) & PHYSICAL_PAGE_MASK, - size, prot); - if (ret) { - /* clear the page */ - dma_pte_clear_range(domain, start_addr, - start_addr + offset); - /* free page tables */ - dma_pte_free_pagetable(domain, start_addr, - start_addr + offset); - /* free iova */ - __free_iova(&domain->iovad, iova); - return 0; - } - sg->dma_address = start_addr + offset + - ((u64)addr & (~PAGE_MASK)); - sg->dma_length = sg->length; - offset += size; + start_vpfn = mm_to_dma_pfn(iova->pfn_lo); + + ret = domain_sg_mapping(domain, start_vpfn, sglist, size, prot); + if (unlikely(ret)) { + /* clear the page */ + dma_pte_clear_range(domain, start_vpfn, + start_vpfn + size - 1); + /* free page tables */ + dma_pte_free_pagetable(domain, start_vpfn, + start_vpfn + size - 1); + /* free iova */ + __free_iova(&domain->iovad, iova); + return 0; } /* it's a non-present to present mapping. Only flush if caching mode */ if (cap_caching_mode(iommu->cap)) - iommu_flush_iotlb_psi(iommu, 0, start_addr, - offset >> VTD_PAGE_SHIFT); + iommu_flush_iotlb_psi(iommu, 0, start_vpfn, offset_pfn); else iommu_flush_write_buffer(iommu); @@ -2994,8 +3068,8 @@ static int init_iommu_hw(void) DMA_CCMD_GLOBAL_INVL); iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); - iommu_disable_protect_mem_regions(iommu); iommu_enable_translation(iommu); + iommu_disable_protect_mem_regions(iommu); } return 0; @@ -3122,18 +3196,28 @@ static int __init init_iommu_sysfs(void) int __init intel_iommu_init(void) { int ret = 0; + int force_on = 0; + + /* VT-d is required for a TXT/tboot launch, so enforce that */ + force_on = tboot_force_iommu(); - if (dmar_table_init()) + if (dmar_table_init()) { + if (force_on) + panic("tboot: Failed to initialize DMAR table\n"); return -ENODEV; + } - if (dmar_dev_scope_init()) + if (dmar_dev_scope_init()) { + if (force_on) + panic("tboot: Failed to initialize DMAR device scope\n"); return -ENODEV; + } /* * Check the need for DMA-remapping initialization now. * Above initialization will also be used by Interrupt-remapping. */ - if (no_iommu || (swiotlb && !iommu_pass_through) || dmar_disabled) + if (no_iommu || swiotlb || dmar_disabled) return -ENODEV; iommu_init_mempool(); @@ -3143,6 +3227,8 @@ int __init intel_iommu_init(void) ret = init_dmars(); if (ret) { + if (force_on) + panic("tboot: Failed to initialize DMARs\n"); printk(KERN_ERR "IOMMU: dmar init failed\n"); put_iova_domain(&reserved_iova_list); iommu_exit_mempool(); @@ -3153,14 +3239,7 @@ int __init intel_iommu_init(void) init_timer(&unmap_timer); force_iommu = 1; - - if (!iommu_pass_through) { - printk(KERN_INFO - "Multi-level page-table translation for DMAR.\n"); - dma_ops = &intel_dma_ops; - } else - printk(KERN_INFO - "DMAR: Pass through translation for DMAR.\n"); + dma_ops = &intel_dma_ops; init_iommu_sysfs(); @@ -3334,7 +3413,6 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width) int adjust_width; init_iova_domain(&domain->iovad, DMA_32BIT_PFN); - spin_lock_init(&domain->mapping_lock); spin_lock_init(&domain->iommu_lock); domain_reserve_special_ranges(domain); @@ -3348,6 +3426,7 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width) domain->iommu_count = 0; domain->iommu_coherency = 0; + domain->iommu_snooping = 0; domain->max_addr = 0; /* always allocate the top pgd */ @@ -3388,8 +3467,6 @@ static void iommu_free_vm_domain(struct dmar_domain *domain) static void vm_domain_exit(struct dmar_domain *domain) { - u64 end; - /* Domain 0 is reserved, so dont process it */ if (!domain) return; @@ -3397,14 +3474,12 @@ static void vm_domain_exit(struct dmar_domain *domain) vm_domain_remove_all_dev_info(domain); /* destroy iovas */ put_iova_domain(&domain->iovad); - end = DOMAIN_MAX_ADDR(domain->gaw); - end = end & (~VTD_PAGE_MASK); /* clear ptes */ - dma_pte_clear_range(domain, 0, end); + dma_pte_clear_range(domain, 0, DOMAIN_MAX_PFN(domain->gaw)); /* free page tables */ - dma_pte_free_pagetable(domain, 0, end); + dma_pte_free_pagetable(domain, 0, DOMAIN_MAX_PFN(domain->gaw)); iommu_free_vm_domain(domain); free_domain_mem(domain); @@ -3447,7 +3522,6 @@ static int intel_iommu_attach_device(struct iommu_domain *domain, struct intel_iommu *iommu; int addr_width; u64 end; - int ret; /* normally pdev is not mapped */ if (unlikely(domain_context_mapped(pdev))) { @@ -3479,12 +3553,7 @@ static int intel_iommu_attach_device(struct iommu_domain *domain, return -EFAULT; } - ret = domain_add_dev_info(dmar_domain, pdev); - if (ret) - return ret; - - ret = domain_context_mapping(dmar_domain, pdev, CONTEXT_TT_MULTI_LEVEL); - return ret; + return domain_add_dev_info(dmar_domain, pdev, CONTEXT_TT_MULTI_LEVEL); } static void intel_iommu_detach_device(struct iommu_domain *domain, @@ -3513,7 +3582,7 @@ static int intel_iommu_map_range(struct iommu_domain *domain, if ((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping) prot |= DMA_PTE_SNP; - max_addr = (iova & VTD_PAGE_MASK) + VTD_PAGE_ALIGN(size); + max_addr = iova + size; if (dmar_domain->max_addr < max_addr) { int min_agaw; u64 end; @@ -3531,8 +3600,11 @@ static int intel_iommu_map_range(struct iommu_domain *domain, } dmar_domain->max_addr = max_addr; } - - ret = domain_page_mapping(dmar_domain, iova, hpa, size, prot); + /* Round up size to next multiple of PAGE_SIZE, if it and + the low bits of hpa would take us onto the next page */ + size = aligned_nrpages(hpa, size); + ret = domain_pfn_mapping(dmar_domain, iova >> VTD_PAGE_SHIFT, + hpa >> VTD_PAGE_SHIFT, size, prot); return ret; } @@ -3540,15 +3612,15 @@ static void intel_iommu_unmap_range(struct iommu_domain *domain, unsigned long iova, size_t size) { struct dmar_domain *dmar_domain = domain->priv; - dma_addr_t base; - /* The address might not be aligned */ - base = iova & VTD_PAGE_MASK; - size = VTD_PAGE_ALIGN(size); - dma_pte_clear_range(dmar_domain, base, base + size); + if (!size) + return; + + dma_pte_clear_range(dmar_domain, iova >> VTD_PAGE_SHIFT, + (iova + size - 1) >> VTD_PAGE_SHIFT); - if (dmar_domain->max_addr == base + size) - dmar_domain->max_addr = base; + if (dmar_domain->max_addr == iova + size) + dmar_domain->max_addr = iova; } static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, @@ -3558,7 +3630,7 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, struct dma_pte *pte; u64 phys = 0; - pte = addr_to_dma_pte(dmar_domain, iova); + pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT); if (pte) phys = dma_pte_addr(pte); diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c index 4f5b8712931..0ed78a764de 100644 --- a/drivers/pci/intr_remapping.c +++ b/drivers/pci/intr_remapping.c @@ -55,15 +55,12 @@ static struct irq_2_iommu *irq_2_iommu(unsigned int irq) return desc->irq_2_iommu; } -static struct irq_2_iommu *irq_2_iommu_alloc_node(unsigned int irq, int node) +static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq) { struct irq_desc *desc; struct irq_2_iommu *irq_iommu; - /* - * alloc irq desc if not allocated already. - */ - desc = irq_to_desc_alloc_node(irq, node); + desc = irq_to_desc(irq); if (!desc) { printk(KERN_INFO "can not get irq_desc for %d\n", irq); return NULL; @@ -72,16 +69,11 @@ static struct irq_2_iommu *irq_2_iommu_alloc_node(unsigned int irq, int node) irq_iommu = desc->irq_2_iommu; if (!irq_iommu) - desc->irq_2_iommu = get_one_free_irq_2_iommu(node); + desc->irq_2_iommu = get_one_free_irq_2_iommu(irq_node(irq)); return desc->irq_2_iommu; } -static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq) -{ - return irq_2_iommu_alloc_node(irq, cpu_to_node(boot_cpu_id)); -} - #else /* !CONFIG_SPARSE_IRQ */ static struct irq_2_iommu irq_2_iommuX[NR_IRQS]; @@ -611,6 +603,9 @@ int __init intr_remapping_supported(void) if (disable_intremap) return 0; + if (!dmar_ir_support()) + return 0; + for_each_drhd_unit(drhd) { struct intel_iommu *iommu = drhd->iommu; @@ -626,6 +621,11 @@ int __init enable_intr_remapping(int eim) struct dmar_drhd_unit *drhd; int setup = 0; + if (parse_ioapics_under_ir() != 1) { + printk(KERN_INFO "Not enable interrupt remapping\n"); + return -1; + } + for_each_drhd_unit(drhd) { struct intel_iommu *iommu = drhd->iommu; diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index e3a87210e94..e03fe98f061 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -598,6 +598,29 @@ int pci_iov_resource_bar(struct pci_dev *dev, int resno, } /** + * pci_sriov_resource_alignment - get resource alignment for VF BAR + * @dev: the PCI device + * @resno: the resource number + * + * Returns the alignment of the VF BAR found in the SR-IOV capability. + * This is not the same as the resource size which is defined as + * the VF BAR size multiplied by the number of VFs. The alignment + * is just the VF BAR size. + */ +int pci_sriov_resource_alignment(struct pci_dev *dev, int resno) +{ + struct resource tmp; + enum pci_bar_type type; + int reg = pci_iov_resource_bar(dev, resno, &type); + + if (!reg) + return 0; + + __pci_read_base(dev, type, &tmp, reg); + return resource_alignment(&tmp); +} + +/** * pci_restore_iov_state - restore the state of the IOV capability * @dev: the PCI device */ diff --git a/drivers/pci/iova.c b/drivers/pci/iova.c index 2287116e982..7914951ef29 100644 --- a/drivers/pci/iova.c +++ b/drivers/pci/iova.c @@ -1,9 +1,19 @@ /* - * Copyright (c) 2006, Intel Corporation. + * Copyright © 2006-2009, Intel Corporation. * - * This file is released under the GPLv2. + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. * - * Copyright (C) 2006-2008 Intel Corporation * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> */ @@ -12,7 +22,6 @@ void init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit) { - spin_lock_init(&iovad->iova_alloc_lock); spin_lock_init(&iovad->iova_rbtree_lock); iovad->rbroot = RB_ROOT; iovad->cached32_node = NULL; @@ -123,7 +132,15 @@ move_left: /* Insert the new_iova into domain rbtree by holding writer lock */ /* Add new node and rebalance tree. */ { - struct rb_node **entry = &((prev)), *parent = NULL; + struct rb_node **entry, *parent = NULL; + + /* If we have 'prev', it's a valid place to start the + insertion. Otherwise, start from the root. */ + if (prev) + entry = &prev; + else + entry = &iovad->rbroot.rb_node; + /* Figure out where to put new node */ while (*entry) { struct iova *this = container_of(*entry, @@ -187,7 +204,6 @@ alloc_iova(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn, bool size_aligned) { - unsigned long flags; struct iova *new_iova; int ret; @@ -201,11 +217,9 @@ alloc_iova(struct iova_domain *iovad, unsigned long size, if (size_aligned) size = __roundup_pow_of_two(size); - spin_lock_irqsave(&iovad->iova_alloc_lock, flags); ret = __alloc_and_insert_iova_range(iovad, size, limit_pfn, new_iova, size_aligned); - spin_unlock_irqrestore(&iovad->iova_alloc_lock, flags); if (ret) { free_iova_mem(new_iova); return NULL; @@ -363,8 +377,7 @@ reserve_iova(struct iova_domain *iovad, struct iova *iova; unsigned int overlap = 0; - spin_lock_irqsave(&iovad->iova_alloc_lock, flags); - spin_lock(&iovad->iova_rbtree_lock); + spin_lock_irqsave(&iovad->iova_rbtree_lock, flags); for (node = rb_first(&iovad->rbroot); node; node = rb_next(node)) { if (__is_range_overlap(node, pfn_lo, pfn_hi)) { iova = container_of(node, struct iova, node); @@ -384,8 +397,7 @@ reserve_iova(struct iova_domain *iovad, iova = __insert_new_range(iovad, pfn_lo, pfn_hi); finish: - spin_unlock(&iovad->iova_rbtree_lock); - spin_unlock_irqrestore(&iovad->iova_alloc_lock, flags); + spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags); return iova; } @@ -402,8 +414,7 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to) unsigned long flags; struct rb_node *node; - spin_lock_irqsave(&from->iova_alloc_lock, flags); - spin_lock(&from->iova_rbtree_lock); + spin_lock_irqsave(&from->iova_rbtree_lock, flags); for (node = rb_first(&from->rbroot); node; node = rb_next(node)) { struct iova *iova = container_of(node, struct iova, node); struct iova *new_iova; @@ -412,6 +423,5 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to) printk(KERN_ERR "Reserve iova range %lx@%lx failed\n", iova->pfn_lo, iova->pfn_lo); } - spin_unlock(&from->iova_rbtree_lock); - spin_unlock_irqrestore(&from->iova_alloc_lock, flags); + spin_unlock_irqrestore(&from->iova_rbtree_lock, flags); } diff --git a/drivers/pci/legacy.c b/drivers/pci/legacy.c new file mode 100644 index 00000000000..871f65c1593 --- /dev/null +++ b/drivers/pci/legacy.c @@ -0,0 +1,34 @@ +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/module.h> +#include <linux/interrupt.h> +#include "pci.h" + +/** + * pci_find_device - begin or continue searching for a PCI device by vendor/device id + * @vendor: PCI vendor id to match, or %PCI_ANY_ID to match all vendor ids + * @device: PCI device id to match, or %PCI_ANY_ID to match all device ids + * @from: Previous PCI device found in search, or %NULL for new search. + * + * Iterates through the list of known PCI devices. If a PCI device is found + * with a matching @vendor and @device, a pointer to its device structure is + * returned. Otherwise, %NULL is returned. + * A new search is initiated by passing %NULL as the @from argument. + * Otherwise if @from is not %NULL, searches continue from next device + * on the global list. + * + * NOTE: Do not use this function any more; use pci_get_device() instead, as + * the PCI device returned by this function can disappear at any moment in + * time. + */ +struct pci_dev *pci_find_device(unsigned int vendor, unsigned int device, + struct pci_dev *from) +{ + struct pci_dev *pdev; + + pci_dev_get(from); + pdev = pci_get_subsys(vendor, device, PCI_ANY_ID, PCI_ANY_ID, from); + pci_dev_put(pdev); + return pdev; +} +EXPORT_SYMBOL(pci_find_device); diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index d9f06fbfa0b..f9cf3173b23 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -16,9 +16,8 @@ #include <linux/proc_fs.h> #include <linux/msi.h> #include <linux/smp.h> - -#include <asm/errno.h> -#include <asm/io.h> +#include <linux/errno.h> +#include <linux/io.h> #include "pci.h" #include "msi.h" @@ -127,17 +126,23 @@ static inline __attribute_const__ u32 msi_enabled_mask(u16 control) * reliably as devices without an INTx disable bit will then generate a * level IRQ which will never be cleared. */ -static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +static u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) { u32 mask_bits = desc->masked; if (!desc->msi_attrib.maskbit) - return; + return 0; mask_bits &= ~mask; mask_bits |= flag; pci_write_config_dword(desc->dev, desc->mask_pos, mask_bits); - desc->masked = mask_bits; + + return mask_bits; +} + +static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +{ + desc->masked = __msi_mask_irq(desc, mask, flag); } /* @@ -147,15 +152,21 @@ static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) * file. This saves a few milliseconds when initialising devices with lots * of MSI-X interrupts. */ -static void msix_mask_irq(struct msi_desc *desc, u32 flag) +static u32 __msix_mask_irq(struct msi_desc *desc, u32 flag) { u32 mask_bits = desc->masked; unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE + - PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET; + PCI_MSIX_ENTRY_VECTOR_CTRL; mask_bits &= ~1; mask_bits |= flag; writel(mask_bits, desc->mask_base + offset); - desc->masked = mask_bits; + + return mask_bits; +} + +static void msix_mask_irq(struct msi_desc *desc, u32 flag) +{ + desc->masked = __msix_mask_irq(desc, flag); } static void msi_set_mask_bit(unsigned irq, u32 flag) @@ -188,9 +199,9 @@ void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg) void __iomem *base = entry->mask_base + entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE; - msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET); - msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET); - msg->data = readl(base + PCI_MSIX_ENTRY_DATA_OFFSET); + msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR); + msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR); + msg->data = readl(base + PCI_MSIX_ENTRY_DATA); } else { struct pci_dev *dev = entry->dev; int pos = entry->msi_attrib.pos; @@ -225,11 +236,9 @@ void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg) base = entry->mask_base + entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE; - writel(msg->address_lo, - base + PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET); - writel(msg->address_hi, - base + PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET); - writel(msg->data, base + PCI_MSIX_ENTRY_DATA_OFFSET); + writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR); + writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR); + writel(msg->data, base + PCI_MSIX_ENTRY_DATA); } else { struct pci_dev *dev = entry->dev; int pos = entry->msi_attrib.pos; @@ -262,7 +271,30 @@ void write_msi_msg(unsigned int irq, struct msi_msg *msg) write_msi_msg_desc(desc, msg); } -static int msi_free_irqs(struct pci_dev* dev); +static void free_msi_irqs(struct pci_dev *dev) +{ + struct msi_desc *entry, *tmp; + + list_for_each_entry(entry, &dev->msi_list, list) { + int i, nvec; + if (!entry->irq) + continue; + nvec = 1 << entry->msi_attrib.multiple; + for (i = 0; i < nvec; i++) + BUG_ON(irq_has_action(entry->irq + i)); + } + + arch_teardown_msi_irqs(dev); + + list_for_each_entry_safe(entry, tmp, &dev->msi_list, list) { + if (entry->msi_attrib.is_msix) { + if (list_is_last(&entry->list, &dev->msi_list)) + iounmap(entry->mask_base); + } + list_del(&entry->list); + kfree(entry); + } +} static struct msi_desc *alloc_msi_entry(struct pci_dev *dev) { @@ -314,7 +346,7 @@ static void __pci_restore_msix_state(struct pci_dev *dev) if (!dev->msix_enabled) return; BUG_ON(list_empty(&dev->msi_list)); - entry = list_entry(dev->msi_list.next, struct msi_desc, list); + entry = list_first_entry(&dev->msi_list, struct msi_desc, list); pos = entry->msi_attrib.pos; pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control); @@ -357,7 +389,7 @@ static int msi_capability_init(struct pci_dev *dev, int nvec) u16 control; unsigned mask; - pos = pci_find_capability(dev, PCI_CAP_ID_MSI); + pos = pci_find_capability(dev, PCI_CAP_ID_MSI); msi_set_enable(dev, pos, 0); /* Disable MSI during set up */ pci_read_config_word(dev, msi_control_reg(pos), &control); @@ -366,12 +398,12 @@ static int msi_capability_init(struct pci_dev *dev, int nvec) if (!entry) return -ENOMEM; - entry->msi_attrib.is_msix = 0; - entry->msi_attrib.is_64 = is_64bit_address(control); - entry->msi_attrib.entry_nr = 0; - entry->msi_attrib.maskbit = is_mask_bit_support(control); - entry->msi_attrib.default_irq = dev->irq; /* Save IOAPIC IRQ */ - entry->msi_attrib.pos = pos; + entry->msi_attrib.is_msix = 0; + entry->msi_attrib.is_64 = is_64bit_address(control); + entry->msi_attrib.entry_nr = 0; + entry->msi_attrib.maskbit = is_mask_bit_support(control); + entry->msi_attrib.default_irq = dev->irq; /* Save IOAPIC IRQ */ + entry->msi_attrib.pos = pos; entry->mask_pos = msi_mask_reg(pos, entry->msi_attrib.is_64); /* All MSIs are unmasked by default, Mask them all */ @@ -385,7 +417,8 @@ static int msi_capability_init(struct pci_dev *dev, int nvec) /* Configure MSI capability structure */ ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI); if (ret) { - msi_free_irqs(dev); + msi_mask_irq(entry, mask, ~mask); + free_msi_irqs(dev); return ret; } @@ -398,6 +431,70 @@ static int msi_capability_init(struct pci_dev *dev, int nvec) return 0; } +static void __iomem *msix_map_region(struct pci_dev *dev, unsigned pos, + unsigned nr_entries) +{ + unsigned long phys_addr; + u32 table_offset; + u8 bir; + + pci_read_config_dword(dev, msix_table_offset_reg(pos), &table_offset); + bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK); + table_offset &= ~PCI_MSIX_FLAGS_BIRMASK; + phys_addr = pci_resource_start(dev, bir) + table_offset; + + return ioremap_nocache(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE); +} + +static int msix_setup_entries(struct pci_dev *dev, unsigned pos, + void __iomem *base, struct msix_entry *entries, + int nvec) +{ + struct msi_desc *entry; + int i; + + for (i = 0; i < nvec; i++) { + entry = alloc_msi_entry(dev); + if (!entry) { + if (!i) + iounmap(base); + else + free_msi_irqs(dev); + /* No enough memory. Don't try again */ + return -ENOMEM; + } + + entry->msi_attrib.is_msix = 1; + entry->msi_attrib.is_64 = 1; + entry->msi_attrib.entry_nr = entries[i].entry; + entry->msi_attrib.default_irq = dev->irq; + entry->msi_attrib.pos = pos; + entry->mask_base = base; + + list_add_tail(&entry->list, &dev->msi_list); + } + + return 0; +} + +static void msix_program_entries(struct pci_dev *dev, + struct msix_entry *entries) +{ + struct msi_desc *entry; + int i = 0; + + list_for_each_entry(entry, &dev->msi_list, list) { + int offset = entries[i].entry * PCI_MSIX_ENTRY_SIZE + + PCI_MSIX_ENTRY_VECTOR_CTRL; + + entries[i].vector = entry->irq; + set_irq_msi(entry->irq, entry); + entry->masked = readl(entry->mask_base + offset); + msix_mask_irq(entry, 1); + i++; + } +} + /** * msix_capability_init - configure device's MSI-X capability * @dev: pointer to the pci_dev data structure of MSI-X device function @@ -411,15 +508,11 @@ static int msi_capability_init(struct pci_dev *dev, int nvec) static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, int nvec) { - struct msi_desc *entry; - int pos, i, j, nr_entries, ret; - unsigned long phys_addr; - u32 table_offset; - u16 control; - u8 bir; + int pos, ret; + u16 control; void __iomem *base; - pos = pci_find_capability(dev, PCI_CAP_ID_MSIX); + pos = pci_find_capability(dev, PCI_CAP_ID_MSIX); pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control); /* Ensure MSI-X is disabled while it is set up */ @@ -427,51 +520,17 @@ static int msix_capability_init(struct pci_dev *dev, pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control); /* Request & Map MSI-X table region */ - nr_entries = multi_msix_capable(control); - - pci_read_config_dword(dev, msix_table_offset_reg(pos), &table_offset); - bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK); - table_offset &= ~PCI_MSIX_FLAGS_BIRMASK; - phys_addr = pci_resource_start (dev, bir) + table_offset; - base = ioremap_nocache(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE); - if (base == NULL) + base = msix_map_region(dev, pos, multi_msix_capable(control)); + if (!base) return -ENOMEM; - for (i = 0; i < nvec; i++) { - entry = alloc_msi_entry(dev); - if (!entry) - break; - - j = entries[i].entry; - entry->msi_attrib.is_msix = 1; - entry->msi_attrib.is_64 = 1; - entry->msi_attrib.entry_nr = j; - entry->msi_attrib.default_irq = dev->irq; - entry->msi_attrib.pos = pos; - entry->mask_base = base; - - list_add_tail(&entry->list, &dev->msi_list); - } + ret = msix_setup_entries(dev, pos, base, entries, nvec); + if (ret) + return ret; ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX); - if (ret < 0) { - /* If we had some success report the number of irqs - * we succeeded in setting up. */ - int avail = 0; - list_for_each_entry(entry, &dev->msi_list, list) { - if (entry->irq != 0) { - avail++; - } - } - - if (avail != 0) - ret = avail; - } - - if (ret) { - msi_free_irqs(dev); - return ret; - } + if (ret) + goto error; /* * Some devices require MSI-X to be enabled before we can touch the @@ -481,16 +540,7 @@ static int msix_capability_init(struct pci_dev *dev, control |= PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE; pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control); - i = 0; - list_for_each_entry(entry, &dev->msi_list, list) { - entries[i].vector = entry->irq; - set_irq_msi(entry->irq, entry); - j = entries[i].entry; - entry->masked = readl(base + j * PCI_MSIX_ENTRY_SIZE + - PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET); - msix_mask_irq(entry, 1); - i++; - } + msix_program_entries(dev, entries); /* Set MSI-X enabled bits and unmask the function */ pci_intx_for_msi(dev, 0); @@ -500,6 +550,27 @@ static int msix_capability_init(struct pci_dev *dev, pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control); return 0; + +error: + if (ret < 0) { + /* + * If we had some success, report the number of irqs + * we succeeded in setting up. + */ + struct msi_desc *entry; + int avail = 0; + + list_for_each_entry(entry, &dev->msi_list, list) { + if (entry->irq != 0) + avail++; + } + if (avail != 0) + ret = avail; + } + + free_msi_irqs(dev); + + return ret; } /** @@ -512,7 +583,7 @@ static int msix_capability_init(struct pci_dev *dev, * to determine if MSI/-X are supported for the device. If MSI/-X is * supported return 0, else return an error code. **/ -static int pci_msi_check_device(struct pci_dev* dev, int nvec, int type) +static int pci_msi_check_device(struct pci_dev *dev, int nvec, int type) { struct pci_bus *bus; int ret; @@ -529,8 +600,9 @@ static int pci_msi_check_device(struct pci_dev* dev, int nvec, int type) if (nvec < 1) return -ERANGE; - /* Any bridge which does NOT route MSI transactions from it's - * secondary bus to it's primary bus must set NO_MSI flag on + /* + * Any bridge which does NOT route MSI transactions from its + * secondary bus to its primary bus must set NO_MSI flag on * the secondary pci_bus. * We expect only arch-specific PCI host bus controller driver * or quirks for specific PCI bridges to be setting NO_MSI. @@ -611,59 +683,26 @@ void pci_msi_shutdown(struct pci_dev *dev) pci_intx_for_msi(dev, 1); dev->msi_enabled = 0; + /* Return the device with MSI unmasked as initial states */ pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &ctrl); mask = msi_capable_mask(ctrl); - msi_mask_irq(desc, mask, ~mask); + /* Keep cached state to be restored */ + __msi_mask_irq(desc, mask, ~mask); /* Restore dev->irq to its default pin-assertion irq */ dev->irq = desc->msi_attrib.default_irq; } -void pci_disable_msi(struct pci_dev* dev) +void pci_disable_msi(struct pci_dev *dev) { - struct msi_desc *entry; - if (!pci_msi_enable || !dev || !dev->msi_enabled) return; pci_msi_shutdown(dev); - - entry = list_entry(dev->msi_list.next, struct msi_desc, list); - if (entry->msi_attrib.is_msix) - return; - - msi_free_irqs(dev); + free_msi_irqs(dev); } EXPORT_SYMBOL(pci_disable_msi); -static int msi_free_irqs(struct pci_dev* dev) -{ - struct msi_desc *entry, *tmp; - - list_for_each_entry(entry, &dev->msi_list, list) { - int i, nvec; - if (!entry->irq) - continue; - nvec = 1 << entry->msi_attrib.multiple; - for (i = 0; i < nvec; i++) - BUG_ON(irq_has_action(entry->irq + i)); - } - - arch_teardown_msi_irqs(dev); - - list_for_each_entry_safe(entry, tmp, &dev->msi_list, list) { - if (entry->msi_attrib.is_msix) { - msix_mask_irq(entry, 1); - if (list_is_last(&entry->list, &dev->msi_list)) - iounmap(entry->mask_base); - } - list_del(&entry->list); - kfree(entry); - } - - return 0; -} - /** * pci_msix_table_size - return the number of device's MSI-X table entries * @dev: pointer to the pci_dev data structure of MSI-X device function @@ -696,13 +735,13 @@ int pci_msix_table_size(struct pci_dev *dev) * of irqs or MSI-X vectors available. Driver should use the returned value to * re-send its request. **/ -int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec) +int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec) { int status, nr_entries; int i, j; if (!entries) - return -EINVAL; + return -EINVAL; status = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSIX); if (status) @@ -724,7 +763,7 @@ int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec) WARN_ON(!!dev->msix_enabled); /* Check whether driver already requested for MSI irq */ - if (dev->msi_enabled) { + if (dev->msi_enabled) { dev_info(&dev->dev, "can't enable MSI-X " "(MSI IRQ already assigned)\n"); return -EINVAL; @@ -734,28 +773,31 @@ int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec) } EXPORT_SYMBOL(pci_enable_msix); -static void msix_free_all_irqs(struct pci_dev *dev) +void pci_msix_shutdown(struct pci_dev *dev) { - msi_free_irqs(dev); -} + struct msi_desc *entry; -void pci_msix_shutdown(struct pci_dev* dev) -{ if (!pci_msi_enable || !dev || !dev->msix_enabled) return; + /* Return the device with MSI-X masked as initial states */ + list_for_each_entry(entry, &dev->msi_list, list) { + /* Keep cached states to be restored */ + __msix_mask_irq(entry, 1); + } + msix_set_enable(dev, 0); pci_intx_for_msi(dev, 1); dev->msix_enabled = 0; } -void pci_disable_msix(struct pci_dev* dev) + +void pci_disable_msix(struct pci_dev *dev) { if (!pci_msi_enable || !dev || !dev->msix_enabled) return; pci_msix_shutdown(dev); - - msix_free_all_irqs(dev); + free_msi_irqs(dev); } EXPORT_SYMBOL(pci_disable_msix); @@ -768,16 +810,13 @@ EXPORT_SYMBOL(pci_disable_msix); * allocated for this device function, are reclaimed to unused state, * which may be used later on. **/ -void msi_remove_pci_irq_vectors(struct pci_dev* dev) +void msi_remove_pci_irq_vectors(struct pci_dev *dev) { if (!pci_msi_enable || !dev) - return; - - if (dev->msi_enabled) - msi_free_irqs(dev); + return; - if (dev->msix_enabled) - msix_free_all_irqs(dev); + if (dev->msi_enabled || dev->msix_enabled) + free_msi_irqs(dev); } void pci_no_msi(void) diff --git a/drivers/pci/msi.h b/drivers/pci/msi.h index a0662842550..de27c1cb5a2 100644 --- a/drivers/pci/msi.h +++ b/drivers/pci/msi.h @@ -6,11 +6,11 @@ #ifndef MSI_H #define MSI_H -#define PCI_MSIX_ENTRY_SIZE 16 -#define PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET 0 -#define PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET 4 -#define PCI_MSIX_ENTRY_DATA_OFFSET 8 -#define PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET 12 +#define PCI_MSIX_ENTRY_SIZE 16 +#define PCI_MSIX_ENTRY_LOWER_ADDR 0 +#define PCI_MSIX_ENTRY_UPPER_ADDR 4 +#define PCI_MSIX_ENTRY_DATA 8 +#define PCI_MSIX_ENTRY_VECTOR_CTRL 12 #define msi_control_reg(base) (base + PCI_MSI_FLAGS) #define msi_lower_address_reg(base) (base + PCI_MSI_ADDRESS_LO) diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index ea15b053745..33317df4769 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -109,15 +109,32 @@ static bool acpi_pci_can_wakeup(struct pci_dev *dev) return handle ? acpi_bus_can_wakeup(handle) : false; } +static void acpi_pci_propagate_wakeup_enable(struct pci_bus *bus, bool enable) +{ + while (bus->parent) { + struct pci_dev *bridge = bus->self; + int ret; + + ret = acpi_pm_device_sleep_wake(&bridge->dev, enable); + if (!ret || bridge->is_pcie) + return; + bus = bus->parent; + } + + /* We have reached the root bus. */ + if (bus->bridge) + acpi_pm_device_sleep_wake(bus->bridge, enable); +} + static int acpi_pci_sleep_wake(struct pci_dev *dev, bool enable) { - int error = acpi_pm_device_sleep_wake(&dev->dev, enable); + if (acpi_pci_can_wakeup(dev)) + return acpi_pm_device_sleep_wake(&dev->dev, enable); - if (!error) - dev_printk(KERN_INFO, &dev->dev, - "wake-up capability %s by ACPI\n", - enable ? "enabled" : "disabled"); - return error; + if (!dev->is_pcie) + acpi_pci_propagate_wakeup_enable(dev->bus, enable); + + return 0; } static struct pci_platform_pm_ops acpi_pci_platform_pm = { diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index d76c4c85367..e5d47be3c6d 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -19,37 +19,98 @@ #include <linux/cpu.h> #include "pci.h" -/* - * Dynamic device IDs are disabled for !CONFIG_HOTPLUG - */ - struct pci_dynid { struct list_head node; struct pci_device_id id; }; -#ifdef CONFIG_HOTPLUG +/** + * pci_add_dynid - add a new PCI device ID to this driver and re-probe devices + * @drv: target pci driver + * @vendor: PCI vendor ID + * @device: PCI device ID + * @subvendor: PCI subvendor ID + * @subdevice: PCI subdevice ID + * @class: PCI class + * @class_mask: PCI class mask + * @driver_data: private driver data + * + * Adds a new dynamic pci device ID to this driver and causes the + * driver to probe for all devices again. @drv must have been + * registered prior to calling this function. + * + * CONTEXT: + * Does GFP_KERNEL allocation. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int pci_add_dynid(struct pci_driver *drv, + unsigned int vendor, unsigned int device, + unsigned int subvendor, unsigned int subdevice, + unsigned int class, unsigned int class_mask, + unsigned long driver_data) +{ + struct pci_dynid *dynid; + int retval; + + dynid = kzalloc(sizeof(*dynid), GFP_KERNEL); + if (!dynid) + return -ENOMEM; + + dynid->id.vendor = vendor; + dynid->id.device = device; + dynid->id.subvendor = subvendor; + dynid->id.subdevice = subdevice; + dynid->id.class = class; + dynid->id.class_mask = class_mask; + dynid->id.driver_data = driver_data; + + spin_lock(&drv->dynids.lock); + list_add_tail(&dynid->node, &drv->dynids.list); + spin_unlock(&drv->dynids.lock); + + get_driver(&drv->driver); + retval = driver_attach(&drv->driver); + put_driver(&drv->driver); + + return retval; +} + +static void pci_free_dynids(struct pci_driver *drv) +{ + struct pci_dynid *dynid, *n; + spin_lock(&drv->dynids.lock); + list_for_each_entry_safe(dynid, n, &drv->dynids.list, node) { + list_del(&dynid->node); + kfree(dynid); + } + spin_unlock(&drv->dynids.lock); +} + +/* + * Dynamic device ID manipulation via sysfs is disabled for !CONFIG_HOTPLUG + */ +#ifdef CONFIG_HOTPLUG /** - * store_new_id - add a new PCI device ID to this driver and re-probe devices + * store_new_id - sysfs frontend to pci_add_dynid() * @driver: target device driver * @buf: buffer for scanning device ID data * @count: input size * - * Adds a new dynamic pci device ID to this driver, - * and causes the driver to probe for all devices again. + * Allow PCI IDs to be added to an existing driver via sysfs. */ static ssize_t store_new_id(struct device_driver *driver, const char *buf, size_t count) { - struct pci_dynid *dynid; struct pci_driver *pdrv = to_pci_driver(driver); const struct pci_device_id *ids = pdrv->id_table; __u32 vendor, device, subvendor=PCI_ANY_ID, subdevice=PCI_ANY_ID, class=0, class_mask=0; unsigned long driver_data=0; int fields=0; - int retval=0; + int retval; fields = sscanf(buf, "%x %x %x %x %x %x %lx", &vendor, &device, &subvendor, &subdevice, @@ -72,27 +133,8 @@ store_new_id(struct device_driver *driver, const char *buf, size_t count) return retval; } - dynid = kzalloc(sizeof(*dynid), GFP_KERNEL); - if (!dynid) - return -ENOMEM; - - dynid->id.vendor = vendor; - dynid->id.device = device; - dynid->id.subvendor = subvendor; - dynid->id.subdevice = subdevice; - dynid->id.class = class; - dynid->id.class_mask = class_mask; - dynid->id.driver_data = driver_data; - - spin_lock(&pdrv->dynids.lock); - list_add_tail(&dynid->node, &pdrv->dynids.list); - spin_unlock(&pdrv->dynids.lock); - - if (get_driver(&pdrv->driver)) { - retval = driver_attach(&pdrv->driver); - put_driver(&pdrv->driver); - } - + retval = pci_add_dynid(pdrv, vendor, device, subvendor, subdevice, + class, class_mask, driver_data); if (retval) return retval; return count; @@ -145,19 +187,6 @@ store_remove_id(struct device_driver *driver, const char *buf, size_t count) } static DRIVER_ATTR(remove_id, S_IWUSR, NULL, store_remove_id); -static void -pci_free_dynids(struct pci_driver *drv) -{ - struct pci_dynid *dynid, *n; - - spin_lock(&drv->dynids.lock); - list_for_each_entry_safe(dynid, n, &drv->dynids.list, node) { - list_del(&dynid->node); - kfree(dynid); - } - spin_unlock(&drv->dynids.lock); -} - static int pci_create_newid_file(struct pci_driver *drv) { @@ -186,7 +215,6 @@ static void pci_remove_removeid_file(struct pci_driver *drv) driver_remove_file(&drv->driver, &driver_attr_remove_id); } #else /* !CONFIG_HOTPLUG */ -static inline void pci_free_dynids(struct pci_driver *drv) {} static inline int pci_create_newid_file(struct pci_driver *drv) { return 0; @@ -417,8 +445,6 @@ static int pci_legacy_suspend(struct device *dev, pm_message_t state) struct pci_dev * pci_dev = to_pci_dev(dev); struct pci_driver * drv = pci_dev->driver; - pci_dev->state_saved = false; - if (drv && drv->suspend) { pci_power_t prev = pci_dev->current_state; int error; @@ -508,13 +534,12 @@ static int pci_restore_standard_config(struct pci_dev *pci_dev) return error; } - return pci_dev->state_saved ? pci_restore_state(pci_dev) : 0; + return pci_restore_state(pci_dev); } static void pci_pm_default_resume_noirq(struct pci_dev *pci_dev) { pci_restore_standard_config(pci_dev); - pci_dev->state_saved = false; pci_fixup_device(pci_fixup_resume_early, pci_dev); } @@ -575,13 +600,11 @@ static void pci_pm_complete(struct device *dev) static int pci_pm_suspend(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_suspend(dev, PMSG_SUSPEND); - pci_dev->state_saved = false; - if (!pm) { pci_pm_default_suspend(pci_dev); goto Fixup; @@ -613,7 +636,7 @@ static int pci_pm_suspend(struct device *dev) static int pci_pm_suspend_noirq(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_suspend_late(dev, PMSG_SUSPEND); @@ -672,7 +695,7 @@ static int pci_pm_resume_noirq(struct device *dev) static int pci_pm_resume(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; int error = 0; /* @@ -694,7 +717,7 @@ static int pci_pm_resume(struct device *dev) pci_pm_reenable_device(pci_dev); } - return 0; + return error; } #else /* !CONFIG_SUSPEND */ @@ -711,13 +734,11 @@ static int pci_pm_resume(struct device *dev) static int pci_pm_freeze(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_suspend(dev, PMSG_FREEZE); - pci_dev->state_saved = false; - if (!pm) { pci_pm_default_suspend(pci_dev); return 0; @@ -780,7 +801,7 @@ static int pci_pm_thaw_noirq(struct device *dev) static int pci_pm_thaw(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; int error = 0; if (pci_has_legacy_pm_support(pci_dev)) @@ -793,19 +814,19 @@ static int pci_pm_thaw(struct device *dev) pci_pm_reenable_device(pci_dev); } + pci_dev->state_saved = false; + return error; } static int pci_pm_poweroff(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_suspend(dev, PMSG_HIBERNATE); - pci_dev->state_saved = false; - if (!pm) { pci_pm_default_suspend(pci_dev); goto Fixup; @@ -872,7 +893,7 @@ static int pci_pm_restore_noirq(struct device *dev) static int pci_pm_restore(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; int error = 0; /* @@ -910,7 +931,7 @@ static int pci_pm_restore(struct device *dev) #endif /* !CONFIG_HIBERNATION */ -struct dev_pm_ops pci_dev_pm_ops = { +const struct dev_pm_ops pci_dev_pm_ops = { .prepare = pci_pm_prepare, .complete = pci_pm_complete, .suspend = pci_pm_suspend, @@ -1106,6 +1127,7 @@ static int __init pci_driver_init(void) postcore_initcall(pci_driver_init); +EXPORT_SYMBOL_GPL(pci_add_dynid); EXPORT_SYMBOL(pci_match_id); EXPORT_SYMBOL(__pci_register_driver); EXPORT_SYMBOL(pci_unregister_driver); diff --git a/drivers/pci/pci-stub.c b/drivers/pci/pci-stub.c index 74fbec0bf6c..f7b68ca6cc9 100644 --- a/drivers/pci/pci-stub.c +++ b/drivers/pci/pci-stub.c @@ -19,8 +19,16 @@ #include <linux/module.h> #include <linux/pci.h> +static char ids[1024] __initdata; + +module_param_string(ids, ids, sizeof(ids), 0); +MODULE_PARM_DESC(ids, "Initial PCI IDs to add to the stub driver, format is " + "\"vendor:device[:subvendor[:subdevice[:class[:class_mask]]]]\"" + " and multiple comma separated entries can be specified"); + static int pci_stub_probe(struct pci_dev *dev, const struct pci_device_id *id) { + dev_printk(KERN_INFO, &dev->dev, "claimed by stub\n"); return 0; } @@ -32,7 +40,42 @@ static struct pci_driver stub_driver = { static int __init pci_stub_init(void) { - return pci_register_driver(&stub_driver); + char *p, *id; + int rc; + + rc = pci_register_driver(&stub_driver); + if (rc) + return rc; + + /* add ids specified in the module parameter */ + p = ids; + while ((id = strsep(&p, ","))) { + unsigned int vendor, device, subvendor = PCI_ANY_ID, + subdevice = PCI_ANY_ID, class=0, class_mask=0; + int fields; + + fields = sscanf(id, "%x:%x:%x:%x:%x:%x", + &vendor, &device, &subvendor, &subdevice, + &class, &class_mask); + + if (fields < 2) { + printk(KERN_WARNING + "pci-stub: invalid id string \"%s\"\n", id); + continue; + } + + printk(KERN_INFO + "pci-stub: add %04X:%04X sub=%04X:%04X cls=%08X/%08X\n", + vendor, device, subvendor, subdevice, class, class_mask); + + rc = pci_add_dynid(&stub_driver, vendor, device, + subvendor, subdevice, class, class_mask, 0); + if (rc) + printk(KERN_WARNING + "pci-stub: failed to add dynamic id (%d)\n", rc); + } + + return 0; } static void __exit pci_stub_exit(void) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 85ebd02a64a..0f6382f090e 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -916,6 +916,24 @@ int __attribute__ ((weak)) pcibios_add_platform_entries(struct pci_dev *dev) return 0; } +static ssize_t reset_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct pci_dev *pdev = to_pci_dev(dev); + unsigned long val; + ssize_t result = strict_strtoul(buf, 0, &val); + + if (result < 0) + return result; + + if (val != 1) + return -EINVAL; + return pci_reset_function(pdev); +} + +static struct device_attribute reset_attr = __ATTR(reset, 0200, NULL, reset_store); + static int pci_create_capabilities_sysfs(struct pci_dev *dev) { int retval; @@ -943,7 +961,22 @@ static int pci_create_capabilities_sysfs(struct pci_dev *dev) /* Active State Power Management */ pcie_aspm_create_sysfs_dev_files(dev); + if (!pci_probe_reset_function(dev)) { + retval = device_create_file(&dev->dev, &reset_attr); + if (retval) + goto error; + dev->reset_fn = 1; + } return 0; + +error: + pcie_aspm_remove_sysfs_dev_files(dev); + if (dev->vpd && dev->vpd->attr) { + sysfs_remove_bin_file(&dev->dev.kobj, dev->vpd->attr); + kfree(dev->vpd->attr); + } + + return retval; } int __must_check pci_create_sysfs_dev_files (struct pci_dev *pdev) @@ -1037,6 +1070,10 @@ static void pci_remove_capabilities_sysfs(struct pci_dev *dev) } pcie_aspm_remove_sysfs_dev_files(dev); + if (dev->reset_fn) { + device_remove_file(&dev->dev, &reset_attr); + dev->reset_fn = 0; + } } /** diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 6c93af5ced1..6edecff0b41 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -41,6 +41,12 @@ int pci_domains_supported = 1; unsigned long pci_cardbus_io_size = DEFAULT_CARDBUS_IO_SIZE; unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE; +#define DEFAULT_HOTPLUG_IO_SIZE (256) +#define DEFAULT_HOTPLUG_MEM_SIZE (2*1024*1024) +/* pci=hpmemsize=nnM,hpiosize=nn can override this */ +unsigned long pci_hotplug_io_size = DEFAULT_HOTPLUG_IO_SIZE; +unsigned long pci_hotplug_mem_size = DEFAULT_HOTPLUG_MEM_SIZE; + /** * pci_bus_max_busnr - returns maximum PCI bus number of given bus' children * @bus: pointer to PCI bus structure to search @@ -846,6 +852,9 @@ pci_restore_state(struct pci_dev *dev) int i; u32 val; + if (!dev->state_saved) + return 0; + /* PCI Express register must be restored first */ pci_restore_pcie_state(dev); @@ -867,6 +876,8 @@ pci_restore_state(struct pci_dev *dev) pci_restore_msi_state(dev); pci_restore_iov_state(dev); + dev->state_saved = false; + return 0; } @@ -1212,30 +1223,40 @@ void pci_pme_active(struct pci_dev *dev, bool enable) */ int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable) { - int error = 0; - bool pme_done = false; + int ret = 0; if (enable && !device_may_wakeup(&dev->dev)) return -EINVAL; + /* Don't do the same thing twice in a row for one device. */ + if (!!enable == !!dev->wakeup_prepared) + return 0; + /* * According to "PCI System Architecture" 4th ed. by Tom Shanley & Don * Anderson we should be doing PME# wake enable followed by ACPI wake * enable. To disable wake-up we call the platform first, for symmetry. */ - if (!enable && platform_pci_can_wakeup(dev)) - error = platform_pci_sleep_wake(dev, false); - - if (!enable || pci_pme_capable(dev, state)) { - pci_pme_active(dev, enable); - pme_done = true; - } + if (enable) { + int error; - if (enable && platform_pci_can_wakeup(dev)) + if (pci_pme_capable(dev, state)) + pci_pme_active(dev, true); + else + ret = 1; error = platform_pci_sleep_wake(dev, true); + if (ret) + ret = error; + if (!ret) + dev->wakeup_prepared = true; + } else { + platform_pci_sleep_wake(dev, false); + pci_pme_active(dev, false); + dev->wakeup_prepared = false; + } - return pme_done ? 0 : error; + return ret; } /** @@ -1354,6 +1375,7 @@ void pci_pm_init(struct pci_dev *dev) int pm; u16 pmc; + dev->wakeup_prepared = false; dev->pm_cap = 0; /* find PCI PM capability in list */ @@ -1517,11 +1539,20 @@ void pci_enable_ari(struct pci_dev *dev) * * Perform INTx swizzling for a device behind one level of bridge. This is * required by section 9.1 of the PCI-to-PCI bridge specification for devices - * behind bridges on add-in cards. + * behind bridges on add-in cards. For devices with ARI enabled, the slot + * number is always 0 (see the Implementation Note in section 2.2.8.1 of + * the PCI Express Base Specification, Revision 2.1) */ u8 pci_swizzle_interrupt_pin(struct pci_dev *dev, u8 pin) { - return (((pin - 1) + PCI_SLOT(dev->devfn)) % 4) + 1; + int slot; + + if (pci_ari_enabled(dev->bus)) + slot = 0; + else + slot = PCI_SLOT(dev->devfn); + + return (((pin - 1) + slot) % 4) + 1; } int @@ -2171,7 +2202,7 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe) u16 ctrl; struct pci_dev *pdev; - if (dev->subordinate) + if (pci_is_root_bus(dev->bus) || dev->subordinate || !dev->bus->self) return -ENOTTY; list_for_each_entry(pdev, &dev->bus->devices, bus_list) @@ -2251,6 +2282,22 @@ int __pci_reset_function(struct pci_dev *dev) EXPORT_SYMBOL_GPL(__pci_reset_function); /** + * pci_probe_reset_function - check whether the device can be safely reset + * @dev: PCI device to reset + * + * Some devices allow an individual function to be reset without affecting + * other functions in the same device. The PCI device must be responsive + * to PCI config space in order to use this function. + * + * Returns 0 if the device function can be reset or negative if the + * device doesn't support resetting a single function. + */ +int pci_probe_reset_function(struct pci_dev *dev) +{ + return pci_dev_reset(dev, 1); +} + +/** * pci_reset_function - quiesce and reset a PCI device function * @dev: PCI device to reset * @@ -2493,6 +2540,50 @@ int pci_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type) return 0; } +/** + * pci_set_vga_state - set VGA decode state on device and parents if requested + * @dev the PCI device + * @decode - true = enable decoding, false = disable decoding + * @command_bits PCI_COMMAND_IO and/or PCI_COMMAND_MEMORY + * @change_bridge - traverse ancestors and change bridges + */ +int pci_set_vga_state(struct pci_dev *dev, bool decode, + unsigned int command_bits, bool change_bridge) +{ + struct pci_bus *bus; + struct pci_dev *bridge; + u16 cmd; + + WARN_ON(command_bits & ~(PCI_COMMAND_IO|PCI_COMMAND_MEMORY)); + + pci_read_config_word(dev, PCI_COMMAND, &cmd); + if (decode == true) + cmd |= command_bits; + else + cmd &= ~command_bits; + pci_write_config_word(dev, PCI_COMMAND, cmd); + + if (change_bridge == false) + return 0; + + bus = dev->bus; + while (bus) { + bridge = bus->self; + if (bridge) { + pci_read_config_word(bridge, PCI_BRIDGE_CONTROL, + &cmd); + if (decode == true) + cmd |= PCI_BRIDGE_CTL_VGA; + else + cmd &= ~PCI_BRIDGE_CTL_VGA; + pci_write_config_word(bridge, PCI_BRIDGE_CONTROL, + cmd); + } + bus = bus->parent; + } + return 0; +} + #define RESOURCE_ALIGNMENT_PARAM_SIZE COMMAND_LINE_SIZE static char resource_alignment_param[RESOURCE_ALIGNMENT_PARAM_SIZE] = {0}; spinlock_t resource_alignment_lock = SPIN_LOCK_UNLOCKED; @@ -2661,6 +2752,10 @@ static int __init pci_setup(char *str) strlen(str + 19)); } else if (!strncmp(str, "ecrc=", 5)) { pcie_ecrc_get_policy(str + 5); + } else if (!strncmp(str, "hpiosize=", 9)) { + pci_hotplug_io_size = memparse(str + 9, &str); + } else if (!strncmp(str, "hpmemsize=", 10)) { + pci_hotplug_mem_size = memparse(str + 10, &str); } else { printk(KERN_ERR "PCI: Unknown option `%s'\n", str); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index f73bcbedf37..d92d1954a2f 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -16,6 +16,7 @@ extern void pci_cleanup_rom(struct pci_dev *dev); extern int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vma); #endif +int pci_probe_reset_function(struct pci_dev *dev); /** * struct pci_platform_pm_ops - Firmware PM callbacks @@ -133,7 +134,6 @@ static inline int pci_no_d1d2(struct pci_dev *dev) return (dev->no_d1d2 || parent_dstates); } -extern int pcie_mch_quirk; extern struct device_attribute pci_dev_attrs[]; extern struct device_attribute dev_attr_cpuaffinity; extern struct device_attribute dev_attr_cpulistaffinity; @@ -243,6 +243,7 @@ extern int pci_iov_init(struct pci_dev *dev); extern void pci_iov_release(struct pci_dev *dev); extern int pci_iov_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type); +extern int pci_sriov_resource_alignment(struct pci_dev *dev, int resno); extern void pci_restore_iov_state(struct pci_dev *dev); extern int pci_iov_bus_range(struct pci_bus *bus); @@ -298,4 +299,16 @@ static inline int pci_ats_enabled(struct pci_dev *dev) } #endif /* CONFIG_PCI_IOV */ +static inline int pci_resource_alignment(struct pci_dev *dev, + struct resource *res) +{ +#ifdef CONFIG_PCI_IOV + int resno = res - dev->resource; + + if (resno >= PCI_IOV_RESOURCES && resno <= PCI_IOV_RESOURCE_END) + return pci_sriov_resource_alignment(dev, resno); +#endif + return resource_alignment(res); +} + #endif /* DRIVERS_PCI_H */ diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c index d92ae21a59d..62d15f652bb 100644 --- a/drivers/pci/pcie/aer/aer_inject.c +++ b/drivers/pci/pcie/aer/aer_inject.c @@ -22,11 +22,10 @@ #include <linux/miscdevice.h> #include <linux/pci.h> #include <linux/fs.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include "aerdrv.h" -struct aer_error_inj -{ +struct aer_error_inj { u8 bus; u8 dev; u8 fn; @@ -38,8 +37,7 @@ struct aer_error_inj u32 header_log3; }; -struct aer_error -{ +struct aer_error { struct list_head list; unsigned int bus; unsigned int devfn; @@ -55,8 +53,7 @@ struct aer_error u32 source_id; }; -struct pci_bus_ops -{ +struct pci_bus_ops { struct list_head list; struct pci_bus *bus; struct pci_ops *ops; @@ -150,7 +147,7 @@ static u32 *find_pci_config_dword(struct aer_error *err, int where, target = &err->header_log1; break; case PCI_ERR_HEADER_LOG+8: - target = &err->header_log2; + target = &err->header_log2; break; case PCI_ERR_HEADER_LOG+12: target = &err->header_log3; @@ -258,8 +255,7 @@ static int pci_bus_set_aer_ops(struct pci_bus *bus) bus_ops = NULL; out: spin_unlock_irqrestore(&inject_lock, flags); - if (bus_ops) - kfree(bus_ops); + kfree(bus_ops); return 0; } @@ -401,10 +397,8 @@ static int aer_inject(struct aer_error_inj *einj) else ret = -EINVAL; out_put: - if (err_alloc) - kfree(err_alloc); - if (rperr_alloc) - kfree(rperr_alloc); + kfree(err_alloc); + kfree(rperr_alloc); pci_dev_put(dev); return ret; } @@ -458,8 +452,7 @@ static void __exit aer_inject_exit(void) } spin_lock_irqsave(&inject_lock, flags); - list_for_each_entry_safe(err, err_next, - &pci_bus_ops_list, list) { + list_for_each_entry_safe(err, err_next, &pci_bus_ops_list, list) { list_del(&err->list); kfree(err); } diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c index 4770f13b3ca..2ce8f9ccc66 100644 --- a/drivers/pci/pcie/aer/aerdrv.c +++ b/drivers/pci/pcie/aer/aerdrv.c @@ -38,7 +38,7 @@ MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); -static int __devinit aer_probe (struct pcie_device *dev); +static int __devinit aer_probe(struct pcie_device *dev); static void aer_remove(struct pcie_device *dev); static pci_ers_result_t aer_error_detected(struct pci_dev *dev, enum pci_channel_state error); @@ -47,7 +47,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev); static struct pci_error_handlers aer_error_handlers = { .error_detected = aer_error_detected, - .resume = aer_error_resume, + .resume = aer_error_resume, }; static struct pcie_port_service_driver aerdriver = { @@ -134,12 +134,12 @@ EXPORT_SYMBOL_GPL(aer_irq); * * Invoked when Root Port's AER service is loaded. **/ -static struct aer_rpc* aer_alloc_rpc(struct pcie_device *dev) +static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev) { struct aer_rpc *rpc; - if (!(rpc = kzalloc(sizeof(struct aer_rpc), - GFP_KERNEL))) + rpc = kzalloc(sizeof(struct aer_rpc), GFP_KERNEL); + if (!rpc) return NULL; /* @@ -189,26 +189,28 @@ static void aer_remove(struct pcie_device *dev) * * Invoked when PCI Express bus loads AER service driver. **/ -static int __devinit aer_probe (struct pcie_device *dev) +static int __devinit aer_probe(struct pcie_device *dev) { int status; struct aer_rpc *rpc; struct device *device = &dev->device; /* Init */ - if ((status = aer_init(dev))) + status = aer_init(dev); + if (status) return status; /* Alloc rpc data structure */ - if (!(rpc = aer_alloc_rpc(dev))) { + rpc = aer_alloc_rpc(dev); + if (!rpc) { dev_printk(KERN_DEBUG, device, "alloc rpc failed\n"); aer_remove(dev); return -ENOMEM; } /* Request IRQ ISR */ - if ((status = request_irq(dev->irq, aer_irq, IRQF_SHARED, "aerdrv", - dev))) { + status = request_irq(dev->irq, aer_irq, IRQF_SHARED, "aerdrv", dev); + if (status) { dev_printk(KERN_DEBUG, device, "request IRQ failed\n"); aer_remove(dev); return status; @@ -316,6 +318,8 @@ static int __init aer_service_init(void) { if (pcie_aer_disable) return -ENXIO; + if (!pci_msi_enabled()) + return -ENXIO; return pcie_port_service_register(&aerdriver); } diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h index bbd7428ca2d..bd833ea3ba4 100644 --- a/drivers/pci/pcie/aer/aerdrv.h +++ b/drivers/pci/pcie/aer/aerdrv.h @@ -16,12 +16,9 @@ #define AER_NONFATAL 0 #define AER_FATAL 1 #define AER_CORRECTABLE 2 -#define AER_UNCORRECTABLE 4 -#define AER_ERROR_MASK 0x001fffff -#define AER_ERROR(d) (d & AER_ERROR_MASK) /* Root Error Status Register Bits */ -#define ROOT_ERR_STATUS_MASKS 0x0f +#define ROOT_ERR_STATUS_MASKS 0x0f #define SYSTEM_ERROR_INTR_ON_MESG_MASK (PCI_EXP_RTCTL_SECEE| \ PCI_EXP_RTCTL_SENFEE| \ @@ -32,8 +29,6 @@ #define ERR_COR_ID(d) (d & 0xffff) #define ERR_UNCOR_ID(d) (d >> 16) -#define AER_SUCCESS 0 -#define AER_UNSUCCESS 1 #define AER_ERROR_SOURCES_MAX 100 #define AER_LOG_TLP_MASKS (PCI_ERR_UNC_POISON_TLP| \ @@ -43,13 +38,6 @@ PCI_ERR_UNC_UNX_COMP| \ PCI_ERR_UNC_MALF_TLP) -/* AER Error Info Flags */ -#define AER_TLP_HEADER_VALID_FLAG 0x00000001 -#define AER_MULTI_ERROR_VALID_FLAG 0x00000002 - -#define ERR_CORRECTABLE_ERROR_MASK 0x000031c1 -#define ERR_UNCORRECTABLE_ERROR_MASK 0x001ff010 - struct header_log_regs { unsigned int dw0; unsigned int dw1; @@ -61,11 +49,20 @@ struct header_log_regs { struct aer_err_info { struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES]; int error_dev_num; - u16 id; - int severity; /* 0:NONFATAL | 1:FATAL | 2:COR */ - int flags; + + unsigned int id:16; + + unsigned int severity:2; /* 0:NONFATAL | 1:FATAL | 2:COR */ + unsigned int __pad1:5; + unsigned int multi_error_valid:1; + + unsigned int first_error:5; + unsigned int __pad2:2; + unsigned int tlp_header_valid:1; + unsigned int status; /* COR/UNCOR Error Status */ - struct header_log_regs tlp; /* TLP Header */ + unsigned int mask; /* COR/UNCOR Error Mask */ + struct header_log_regs tlp; /* TLP Header */ }; struct aer_err_source { @@ -125,6 +122,7 @@ extern void aer_delete_rootport(struct aer_rpc *rpc); extern int aer_init(struct pcie_device *dev); extern void aer_isr(struct work_struct *work); extern void aer_print_error(struct pci_dev *dev, struct aer_err_info *info); +extern void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info); extern irqreturn_t aer_irq(int irq, void *context); #ifdef CONFIG_ACPI @@ -136,4 +134,4 @@ static inline int aer_osc_setup(struct pcie_device *pciedev) } #endif -#endif //_AERDRV_H_ +#endif /* _AERDRV_H_ */ diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c index 3d8872704a5..9f5ccbeb4fa 100644 --- a/drivers/pci/pcie/aer/aerdrv_core.c +++ b/drivers/pci/pcie/aer/aerdrv_core.c @@ -49,10 +49,11 @@ int pci_enable_pcie_error_reporting(struct pci_dev *dev) PCI_EXP_DEVCTL_NFERE | PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE; - pci_write_config_word(dev, pos+PCI_EXP_DEVCTL, - reg16); + pci_write_config_word(dev, pos+PCI_EXP_DEVCTL, reg16); + return 0; } +EXPORT_SYMBOL_GPL(pci_enable_pcie_error_reporting); int pci_disable_pcie_error_reporting(struct pci_dev *dev) { @@ -68,10 +69,11 @@ int pci_disable_pcie_error_reporting(struct pci_dev *dev) PCI_EXP_DEVCTL_NFERE | PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE); - pci_write_config_word(dev, pos+PCI_EXP_DEVCTL, - reg16); + pci_write_config_word(dev, pos+PCI_EXP_DEVCTL, reg16); + return 0; } +EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting); int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) { @@ -92,6 +94,7 @@ int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) return 0; } +EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status); #if 0 int pci_cleanup_aer_correct_error_status(struct pci_dev *dev) @@ -110,7 +113,6 @@ int pci_cleanup_aer_correct_error_status(struct pci_dev *dev) } #endif /* 0 */ - static int set_device_error_reporting(struct pci_dev *dev, void *data) { bool enable = *((bool *)data); @@ -164,8 +166,9 @@ static int add_error_device(struct aer_err_info *e_info, struct pci_dev *dev) e_info->dev[e_info->error_dev_num] = dev; e_info->error_dev_num++; return 1; - } else - return 0; + } + + return 0; } @@ -193,7 +196,7 @@ static int find_device_iter(struct pci_dev *dev, void *data) * If there is no multiple error, we stop * or continue based on the id comparing. */ - if (!(e_info->flags & AER_MULTI_ERROR_VALID_FLAG)) + if (!e_info->multi_error_valid) return result; /* @@ -233,24 +236,16 @@ static int find_device_iter(struct pci_dev *dev, void *data) status = 0; mask = 0; if (e_info->severity == AER_CORRECTABLE) { - pci_read_config_dword(dev, - pos + PCI_ERR_COR_STATUS, - &status); - pci_read_config_dword(dev, - pos + PCI_ERR_COR_MASK, - &mask); - if (status & ERR_CORRECTABLE_ERROR_MASK & ~mask) { + pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS, &status); + pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, &mask); + if (status & ~mask) { add_error_device(e_info, dev); goto added; } } else { - pci_read_config_dword(dev, - pos + PCI_ERR_UNCOR_STATUS, - &status); - pci_read_config_dword(dev, - pos + PCI_ERR_UNCOR_MASK, - &mask); - if (status & ERR_UNCORRECTABLE_ERROR_MASK & ~mask) { + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status); + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, &mask); + if (status & ~mask) { add_error_device(e_info, dev); goto added; } @@ -259,7 +254,7 @@ static int find_device_iter(struct pci_dev *dev, void *data) return 0; added: - if (e_info->flags & AER_MULTI_ERROR_VALID_FLAG) + if (e_info->multi_error_valid) return 0; else return 1; @@ -411,8 +406,7 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev, pci_cleanup_aer_uncorrect_error_status(dev); dev->error_state = pci_channel_io_normal; } - } - else { + } else { /* * If the error is reported by an end point, we think this * error is related to the upstream link of the end point. @@ -473,7 +467,7 @@ static pci_ers_result_t reset_link(struct pcie_device *aerdev, if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE) udev = dev; else - udev= dev->bus->self; + udev = dev->bus->self; data.is_downstream = 0; data.aer_driver = NULL; @@ -576,7 +570,7 @@ static pci_ers_result_t do_recovery(struct pcie_device *aerdev, * * Invoked when an error being detected by Root Port. */ -static void handle_error_source(struct pcie_device * aerdev, +static void handle_error_source(struct pcie_device *aerdev, struct pci_dev *dev, struct aer_err_info *info) { @@ -682,7 +676,7 @@ static void disable_root_aer(struct aer_rpc *rpc) * * Invoked by DPC handler to consume an error. */ -static struct aer_err_source* get_e_source(struct aer_rpc *rpc) +static struct aer_err_source *get_e_source(struct aer_rpc *rpc) { struct aer_err_source *e_source; unsigned long flags; @@ -702,32 +696,50 @@ static struct aer_err_source* get_e_source(struct aer_rpc *rpc) return e_source; } +/** + * get_device_error_info - read error status from dev and store it to info + * @dev: pointer to the device expected to have a error record + * @info: pointer to structure to store the error record + * + * Return 1 on success, 0 on error. + */ static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info) { - int pos; + int pos, temp; + + info->status = 0; + info->tlp_header_valid = 0; pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); /* The device might not support AER */ if (!pos) - return AER_SUCCESS; + return 1; if (info->severity == AER_CORRECTABLE) { pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS, &info->status); - if (!(info->status & ERR_CORRECTABLE_ERROR_MASK)) - return AER_UNSUCCESS; + pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, + &info->mask); + if (!(info->status & ~info->mask)) + return 0; } else if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE || info->severity == AER_NONFATAL) { /* Link is still healthy for IO reads */ pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &info->status); - if (!(info->status & ERR_UNCORRECTABLE_ERROR_MASK)) - return AER_UNSUCCESS; + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, + &info->mask); + if (!(info->status & ~info->mask)) + return 0; + + /* Get First Error Pointer */ + pci_read_config_dword(dev, pos + PCI_ERR_CAP, &temp); + info->first_error = PCI_ERR_CAP_FEP(temp); if (info->status & AER_LOG_TLP_MASKS) { - info->flags |= AER_TLP_HEADER_VALID_FLAG; + info->tlp_header_valid = 1; pci_read_config_dword(dev, pos + PCI_ERR_HEADER_LOG, &info->tlp.dw0); pci_read_config_dword(dev, @@ -739,7 +751,7 @@ static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info) } } - return AER_SUCCESS; + return 1; } static inline void aer_process_err_devices(struct pcie_device *p_device, @@ -753,14 +765,14 @@ static inline void aer_process_err_devices(struct pcie_device *p_device, e_info->id); } + /* Report all before handle them, not to lost records by reset etc. */ for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) { - if (get_device_error_info(e_info->dev[i], e_info) == - AER_SUCCESS) { + if (get_device_error_info(e_info->dev[i], e_info)) aer_print_error(e_info->dev[i], e_info); - handle_error_source(p_device, - e_info->dev[i], - e_info); - } + } + for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) { + if (get_device_error_info(e_info->dev[i], e_info)) + handle_error_source(p_device, e_info->dev[i], e_info); } } @@ -806,7 +818,9 @@ static void aer_isr_one_error(struct pcie_device *p_device, if (e_src->status & (PCI_ERR_ROOT_MULTI_COR_RCV | PCI_ERR_ROOT_MULTI_UNCOR_RCV)) - e_info->flags |= AER_MULTI_ERROR_VALID_FLAG; + e_info->multi_error_valid = 1; + + aer_print_port_info(p_device->port, e_info); find_source_device(p_device->port, e_info); aer_process_err_devices(p_device, e_info); @@ -863,10 +877,5 @@ int aer_init(struct pcie_device *dev) if (aer_osc_setup(dev) && !forceload) return -ENXIO; - return AER_SUCCESS; + return 0; } - -EXPORT_SYMBOL_GPL(pci_enable_pcie_error_reporting); -EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting); -EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status); - diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c index 0fc29ae80df..44acde72294 100644 --- a/drivers/pci/pcie/aer/aerdrv_errprint.c +++ b/drivers/pci/pcie/aer/aerdrv_errprint.c @@ -27,69 +27,70 @@ #define AER_AGENT_COMPLETER 2 #define AER_AGENT_TRANSMITTER 3 -#define AER_AGENT_REQUESTER_MASK (PCI_ERR_UNC_COMP_TIME| \ - PCI_ERR_UNC_UNSUP) - -#define AER_AGENT_COMPLETER_MASK PCI_ERR_UNC_COMP_ABORT - -#define AER_AGENT_TRANSMITTER_MASK(t, e) (e & (PCI_ERR_COR_REP_ROLL| \ - ((t == AER_CORRECTABLE) ? PCI_ERR_COR_REP_TIMER: 0))) +#define AER_AGENT_REQUESTER_MASK(t) ((t == AER_CORRECTABLE) ? \ + 0 : (PCI_ERR_UNC_COMP_TIME|PCI_ERR_UNC_UNSUP)) +#define AER_AGENT_COMPLETER_MASK(t) ((t == AER_CORRECTABLE) ? \ + 0 : PCI_ERR_UNC_COMP_ABORT) +#define AER_AGENT_TRANSMITTER_MASK(t) ((t == AER_CORRECTABLE) ? \ + (PCI_ERR_COR_REP_ROLL|PCI_ERR_COR_REP_TIMER) : 0) #define AER_GET_AGENT(t, e) \ - ((e & AER_AGENT_COMPLETER_MASK) ? AER_AGENT_COMPLETER : \ - (e & AER_AGENT_REQUESTER_MASK) ? AER_AGENT_REQUESTER : \ - (AER_AGENT_TRANSMITTER_MASK(t, e)) ? AER_AGENT_TRANSMITTER : \ + ((e & AER_AGENT_COMPLETER_MASK(t)) ? AER_AGENT_COMPLETER : \ + (e & AER_AGENT_REQUESTER_MASK(t)) ? AER_AGENT_REQUESTER : \ + (e & AER_AGENT_TRANSMITTER_MASK(t)) ? AER_AGENT_TRANSMITTER : \ AER_AGENT_RECEIVER) -#define AER_PHYSICAL_LAYER_ERROR_MASK PCI_ERR_COR_RCVR -#define AER_DATA_LINK_LAYER_ERROR_MASK(t, e) \ - (PCI_ERR_UNC_DLP| \ - PCI_ERR_COR_BAD_TLP| \ - PCI_ERR_COR_BAD_DLLP| \ - PCI_ERR_COR_REP_ROLL| \ - ((t == AER_CORRECTABLE) ? \ - PCI_ERR_COR_REP_TIMER: 0)) - #define AER_PHYSICAL_LAYER_ERROR 0 #define AER_DATA_LINK_LAYER_ERROR 1 #define AER_TRANSACTION_LAYER_ERROR 2 -#define AER_GET_LAYER_ERROR(t, e) \ - ((e & AER_PHYSICAL_LAYER_ERROR_MASK) ? \ - AER_PHYSICAL_LAYER_ERROR : \ - (e & AER_DATA_LINK_LAYER_ERROR_MASK(t, e)) ? \ - AER_DATA_LINK_LAYER_ERROR : \ - AER_TRANSACTION_LAYER_ERROR) +#define AER_PHYSICAL_LAYER_ERROR_MASK(t) ((t == AER_CORRECTABLE) ? \ + PCI_ERR_COR_RCVR : 0) +#define AER_DATA_LINK_LAYER_ERROR_MASK(t) ((t == AER_CORRECTABLE) ? \ + (PCI_ERR_COR_BAD_TLP| \ + PCI_ERR_COR_BAD_DLLP| \ + PCI_ERR_COR_REP_ROLL| \ + PCI_ERR_COR_REP_TIMER) : PCI_ERR_UNC_DLP) + +#define AER_GET_LAYER_ERROR(t, e) \ + ((e & AER_PHYSICAL_LAYER_ERROR_MASK(t)) ? AER_PHYSICAL_LAYER_ERROR : \ + (e & AER_DATA_LINK_LAYER_ERROR_MASK(t)) ? AER_DATA_LINK_LAYER_ERROR : \ + AER_TRANSACTION_LAYER_ERROR) + +#define AER_PR(info, pdev, fmt, args...) \ + printk("%s%s %s: " fmt, (info->severity == AER_CORRECTABLE) ? \ + KERN_WARNING : KERN_ERR, dev_driver_string(&pdev->dev), \ + dev_name(&pdev->dev), ## args) /* * AER error strings */ -static char* aer_error_severity_string[] = { +static char *aer_error_severity_string[] = { "Uncorrected (Non-Fatal)", "Uncorrected (Fatal)", "Corrected" }; -static char* aer_error_layer[] = { +static char *aer_error_layer[] = { "Physical Layer", "Data Link Layer", "Transaction Layer" }; -static char* aer_correctable_error_string[] = { - "Receiver Error ", /* Bit Position 0 */ +static char *aer_correctable_error_string[] = { + "Receiver Error ", /* Bit Position 0 */ NULL, NULL, NULL, NULL, NULL, - "Bad TLP ", /* Bit Position 6 */ - "Bad DLLP ", /* Bit Position 7 */ - "RELAY_NUM Rollover ", /* Bit Position 8 */ + "Bad TLP ", /* Bit Position 6 */ + "Bad DLLP ", /* Bit Position 7 */ + "RELAY_NUM Rollover ", /* Bit Position 8 */ NULL, NULL, NULL, - "Replay Timer Timeout ", /* Bit Position 12 */ - "Advisory Non-Fatal ", /* Bit Position 13 */ + "Replay Timer Timeout ", /* Bit Position 12 */ + "Advisory Non-Fatal ", /* Bit Position 13 */ NULL, NULL, NULL, @@ -110,7 +111,7 @@ static char* aer_correctable_error_string[] = { NULL, }; -static char* aer_uncorrectable_error_string[] = { +static char *aer_uncorrectable_error_string[] = { NULL, NULL, NULL, @@ -123,10 +124,10 @@ static char* aer_uncorrectable_error_string[] = { NULL, NULL, NULL, - "Poisoned TLP ", /* Bit Position 12 */ + "Poisoned TLP ", /* Bit Position 12 */ "Flow Control Protocol ", /* Bit Position 13 */ - "Completion Timeout ", /* Bit Position 14 */ - "Completer Abort ", /* Bit Position 15 */ + "Completion Timeout ", /* Bit Position 14 */ + "Completer Abort ", /* Bit Position 15 */ "Unexpected Completion ", /* Bit Position 16 */ "Receiver Overflow ", /* Bit Position 17 */ "Malformed TLP ", /* Bit Position 18 */ @@ -145,98 +146,69 @@ static char* aer_uncorrectable_error_string[] = { NULL, }; -static char* aer_agent_string[] = { +static char *aer_agent_string[] = { "Receiver ID", "Requester ID", "Completer ID", "Transmitter ID" }; -static char * aer_get_error_source_name(int severity, - unsigned int status, - char errmsg_buff[]) +static void __aer_print_error(struct aer_err_info *info, struct pci_dev *dev) { - int i; - char * errmsg = NULL; + int i, status; + char *errmsg = NULL; + + status = (info->status & ~info->mask); for (i = 0; i < 32; i++) { if (!(status & (1 << i))) continue; - if (severity == AER_CORRECTABLE) + if (info->severity == AER_CORRECTABLE) errmsg = aer_correctable_error_string[i]; else errmsg = aer_uncorrectable_error_string[i]; - if (!errmsg) { - sprintf(errmsg_buff, "Unknown Error Bit %2d ", i); - errmsg = errmsg_buff; - } - - break; + if (errmsg) + AER_PR(info, dev, " [%2d] %s%s\n", i, errmsg, + info->first_error == i ? " (First)" : ""); + else + AER_PR(info, dev, " [%2d] Unknown Error Bit%s\n", i, + info->first_error == i ? " (First)" : ""); } - - return errmsg; } -static DEFINE_SPINLOCK(logbuf_lock); -static char errmsg_buff[100]; void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) { - char * errmsg; - int err_layer, agent; - char * loglevel; - - if (info->severity == AER_CORRECTABLE) - loglevel = KERN_WARNING; - else - loglevel = KERN_ERR; - - printk("%s+------ PCI-Express Device Error ------+\n", loglevel); - printk("%sError Severity\t\t: %s\n", loglevel, - aer_error_severity_string[info->severity]); - - if ( info->status == 0) { - printk("%sPCIE Bus Error type\t: (Unaccessible)\n", loglevel); - printk("%sUnaccessible Received\t: %s\n", loglevel, - info->flags & AER_MULTI_ERROR_VALID_FLAG ? - "Multiple" : "First"); - printk("%sUnregistered Agent ID\t: %04x\n", loglevel, - (dev->bus->number << 8) | dev->devfn); + int id = ((dev->bus->number << 8) | dev->devfn); + + if (info->status == 0) { + AER_PR(info, dev, + "PCIE Bus Error: severity=%s, type=Unaccessible, " + "id=%04x(Unregistered Agent ID)\n", + aer_error_severity_string[info->severity], id); } else { - err_layer = AER_GET_LAYER_ERROR(info->severity, info->status); - printk("%sPCIE Bus Error type\t: %s\n", loglevel, - aer_error_layer[err_layer]); - - spin_lock(&logbuf_lock); - errmsg = aer_get_error_source_name(info->severity, - info->status, - errmsg_buff); - printk("%s%s\t: %s\n", loglevel, errmsg, - info->flags & AER_MULTI_ERROR_VALID_FLAG ? - "Multiple" : "First"); - spin_unlock(&logbuf_lock); + int layer, agent; + layer = AER_GET_LAYER_ERROR(info->severity, info->status); agent = AER_GET_AGENT(info->severity, info->status); - printk("%s%s\t\t: %04x\n", loglevel, - aer_agent_string[agent], - (dev->bus->number << 8) | dev->devfn); - - printk("%sVendorID=%04xh, DeviceID=%04xh," - " Bus=%02xh, Device=%02xh, Function=%02xh\n", - loglevel, - dev->vendor, - dev->device, - dev->bus->number, - PCI_SLOT(dev->devfn), - PCI_FUNC(dev->devfn)); - - if (info->flags & AER_TLP_HEADER_VALID_FLAG) { + + AER_PR(info, dev, + "PCIE Bus Error: severity=%s, type=%s, id=%04x(%s)\n", + aer_error_severity_string[info->severity], + aer_error_layer[layer], id, aer_agent_string[agent]); + + AER_PR(info, dev, + " device [%04x:%04x] error status/mask=%08x/%08x\n", + dev->vendor, dev->device, info->status, info->mask); + + __aer_print_error(info, dev); + + if (info->tlp_header_valid) { unsigned char *tlp = (unsigned char *) &info->tlp; - printk("%sTLP Header:\n", loglevel); - printk("%s%02x%02x%02x%02x %02x%02x%02x%02x" + AER_PR(info, dev, " TLP Header:" + " %02x%02x%02x%02x %02x%02x%02x%02x" " %02x%02x%02x%02x %02x%02x%02x%02x\n", - loglevel, *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp, *(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4), *(tlp + 11), *(tlp + 10), *(tlp + 9), @@ -244,5 +216,15 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) *(tlp + 13), *(tlp + 12)); } } + + if (info->id && info->error_dev_num > 1 && info->id == id) + AER_PR(info, dev, + " Error of this Agent(%04x) is reported first\n", id); } +void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info) +{ + dev_info(&dev->dev, "AER: %s%s error received: id=%04x\n", + info->multi_error_valid ? "Multiple " : "", + aer_error_severity_string[info->severity], info->id); +} diff --git a/drivers/pci/pcie/aer/ecrc.c b/drivers/pci/pcie/aer/ecrc.c index ece97df4df6..a928d8ab6bd 100644 --- a/drivers/pci/pcie/aer/ecrc.c +++ b/drivers/pci/pcie/aer/ecrc.c @@ -106,7 +106,7 @@ void pcie_set_ecrc_checking(struct pci_dev *dev) disable_ecrc_checking(dev); break; case ECRC_POLICY_ON: - enable_ecrc_checking(dev);; + enable_ecrc_checking(dev); break; default: return; diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 3d27c97e048..745402e8e49 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -26,6 +26,13 @@ #endif #define MODULE_PARAM_PREFIX "pcie_aspm." +/* Note: those are not register definitions */ +#define ASPM_STATE_L0S_UP (1) /* Upstream direction L0s state */ +#define ASPM_STATE_L0S_DW (2) /* Downstream direction L0s state */ +#define ASPM_STATE_L1 (4) /* L1 state */ +#define ASPM_STATE_L0S (ASPM_STATE_L0S_UP | ASPM_STATE_L0S_DW) +#define ASPM_STATE_ALL (ASPM_STATE_L0S | ASPM_STATE_L1) + struct aspm_latency { u32 l0s; /* L0s latency (nsec) */ u32 l1; /* L1 latency (nsec) */ @@ -40,17 +47,20 @@ struct pcie_link_state { struct list_head link; /* node in parent's children list */ /* ASPM state */ - u32 aspm_support:2; /* Supported ASPM state */ - u32 aspm_enabled:2; /* Enabled ASPM state */ - u32 aspm_default:2; /* Default ASPM state by BIOS */ + u32 aspm_support:3; /* Supported ASPM state */ + u32 aspm_enabled:3; /* Enabled ASPM state */ + u32 aspm_capable:3; /* Capable ASPM state with latency */ + u32 aspm_default:3; /* Default ASPM state by BIOS */ + u32 aspm_disable:3; /* Disabled ASPM state */ /* Clock PM state */ u32 clkpm_capable:1; /* Clock PM capable? */ u32 clkpm_enabled:1; /* Current Clock PM state */ u32 clkpm_default:1; /* Default Clock PM state by BIOS */ - /* Latencies */ - struct aspm_latency latency; /* Exit latency */ + /* Exit latencies */ + struct aspm_latency latency_up; /* Upstream direction exit latency */ + struct aspm_latency latency_dw; /* Downstream direction exit latency */ /* * Endpoint acceptable latencies. A pcie downstream port only * has one slot under it, so at most there are 8 functions. @@ -82,7 +92,7 @@ static int policy_to_aspm_state(struct pcie_link_state *link) return 0; case POLICY_POWERSAVE: /* Enable ASPM L0s/L1 */ - return PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1; + return ASPM_STATE_ALL; case POLICY_DEFAULT: return link->aspm_default; } @@ -164,18 +174,6 @@ static void pcie_clkpm_cap_init(struct pcie_link_state *link, int blacklist) link->clkpm_capable = (blacklist) ? 0 : capable; } -static bool pcie_aspm_downstream_has_switch(struct pcie_link_state *link) -{ - struct pci_dev *child; - struct pci_bus *linkbus = link->pdev->subordinate; - - list_for_each_entry(child, &linkbus->devices, bus_list) { - if (child->pcie_type == PCI_EXP_TYPE_UPSTREAM) - return true; - } - return false; -} - /* * pcie_aspm_configure_common_clock: check if the 2 ends of a link * could use common clock. If they are, configure them to use the @@ -288,71 +286,130 @@ static u32 calc_l1_acceptable(u32 encoding) return (1000 << encoding); } -static void pcie_aspm_get_cap_device(struct pci_dev *pdev, u32 *state, - u32 *l0s, u32 *l1, u32 *enabled) +struct aspm_register_info { + u32 support:2; + u32 enabled:2; + u32 latency_encoding_l0s; + u32 latency_encoding_l1; +}; + +static void pcie_get_aspm_reg(struct pci_dev *pdev, + struct aspm_register_info *info) { int pos; u16 reg16; - u32 reg32, encoding; + u32 reg32; - *l0s = *l1 = *enabled = 0; pos = pci_find_capability(pdev, PCI_CAP_ID_EXP); pci_read_config_dword(pdev, pos + PCI_EXP_LNKCAP, ®32); - *state = (reg32 & PCI_EXP_LNKCAP_ASPMS) >> 10; - if (*state != PCIE_LINK_STATE_L0S && - *state != (PCIE_LINK_STATE_L1 | PCIE_LINK_STATE_L0S)) - *state = 0; - if (*state == 0) + info->support = (reg32 & PCI_EXP_LNKCAP_ASPMS) >> 10; + info->latency_encoding_l0s = (reg32 & PCI_EXP_LNKCAP_L0SEL) >> 12; + info->latency_encoding_l1 = (reg32 & PCI_EXP_LNKCAP_L1EL) >> 15; + pci_read_config_word(pdev, pos + PCI_EXP_LNKCTL, ®16); + info->enabled = reg16 & PCI_EXP_LNKCTL_ASPMC; +} + +static void pcie_aspm_check_latency(struct pci_dev *endpoint) +{ + u32 latency, l1_switch_latency = 0; + struct aspm_latency *acceptable; + struct pcie_link_state *link; + + /* Device not in D0 doesn't need latency check */ + if ((endpoint->current_state != PCI_D0) && + (endpoint->current_state != PCI_UNKNOWN)) return; - encoding = (reg32 & PCI_EXP_LNKCAP_L0SEL) >> 12; - *l0s = calc_l0s_latency(encoding); - if (*state & PCIE_LINK_STATE_L1) { - encoding = (reg32 & PCI_EXP_LNKCAP_L1EL) >> 15; - *l1 = calc_l1_latency(encoding); + link = endpoint->bus->self->link_state; + acceptable = &link->acceptable[PCI_FUNC(endpoint->devfn)]; + + while (link) { + /* Check upstream direction L0s latency */ + if ((link->aspm_capable & ASPM_STATE_L0S_UP) && + (link->latency_up.l0s > acceptable->l0s)) + link->aspm_capable &= ~ASPM_STATE_L0S_UP; + + /* Check downstream direction L0s latency */ + if ((link->aspm_capable & ASPM_STATE_L0S_DW) && + (link->latency_dw.l0s > acceptable->l0s)) + link->aspm_capable &= ~ASPM_STATE_L0S_DW; + /* + * Check L1 latency. + * Every switch on the path to root complex need 1 + * more microsecond for L1. Spec doesn't mention L0s. + */ + latency = max_t(u32, link->latency_up.l1, link->latency_dw.l1); + if ((link->aspm_capable & ASPM_STATE_L1) && + (latency + l1_switch_latency > acceptable->l1)) + link->aspm_capable &= ~ASPM_STATE_L1; + l1_switch_latency += 1000; + + link = link->parent; } - pci_read_config_word(pdev, pos + PCI_EXP_LNKCTL, ®16); - *enabled = reg16 & (PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1); } static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) { - u32 support, l0s, l1, enabled; struct pci_dev *child, *parent = link->pdev; struct pci_bus *linkbus = parent->subordinate; + struct aspm_register_info upreg, dwreg; if (blacklist) { - /* Set support state to 0, so we will disable ASPM later */ - link->aspm_support = 0; - link->aspm_default = 0; - link->aspm_enabled = PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1; + /* Set enabled/disable so that we will disable ASPM later */ + link->aspm_enabled = ASPM_STATE_ALL; + link->aspm_disable = ASPM_STATE_ALL; return; } /* Configure common clock before checking latencies */ pcie_aspm_configure_common_clock(link); - /* upstream component states */ - pcie_aspm_get_cap_device(parent, &support, &l0s, &l1, &enabled); - link->aspm_support = support; - link->latency.l0s = l0s; - link->latency.l1 = l1; - link->aspm_enabled = enabled; - - /* downstream component states, all functions have the same setting */ + /* Get upstream/downstream components' register state */ + pcie_get_aspm_reg(parent, &upreg); child = list_entry(linkbus->devices.next, struct pci_dev, bus_list); - pcie_aspm_get_cap_device(child, &support, &l0s, &l1, &enabled); - link->aspm_support &= support; - link->latency.l0s = max_t(u32, link->latency.l0s, l0s); - link->latency.l1 = max_t(u32, link->latency.l1, l1); + pcie_get_aspm_reg(child, &dwreg); - if (!link->aspm_support) - return; - - link->aspm_enabled &= link->aspm_support; + /* + * Setup L0s state + * + * Note that we must not enable L0s in either direction on a + * given link unless components on both sides of the link each + * support L0s. + */ + if (dwreg.support & upreg.support & PCIE_LINK_STATE_L0S) + link->aspm_support |= ASPM_STATE_L0S; + if (dwreg.enabled & PCIE_LINK_STATE_L0S) + link->aspm_enabled |= ASPM_STATE_L0S_UP; + if (upreg.enabled & PCIE_LINK_STATE_L0S) + link->aspm_enabled |= ASPM_STATE_L0S_DW; + link->latency_up.l0s = calc_l0s_latency(upreg.latency_encoding_l0s); + link->latency_dw.l0s = calc_l0s_latency(dwreg.latency_encoding_l0s); + + /* Setup L1 state */ + if (upreg.support & dwreg.support & PCIE_LINK_STATE_L1) + link->aspm_support |= ASPM_STATE_L1; + if (upreg.enabled & dwreg.enabled & PCIE_LINK_STATE_L1) + link->aspm_enabled |= ASPM_STATE_L1; + link->latency_up.l1 = calc_l1_latency(upreg.latency_encoding_l1); + link->latency_dw.l1 = calc_l1_latency(dwreg.latency_encoding_l1); + + /* Save default state */ link->aspm_default = link->aspm_enabled; - /* ENDPOINT states*/ + /* Setup initial capable state. Will be updated later */ + link->aspm_capable = link->aspm_support; + /* + * If the downstream component has pci bridge function, don't + * do ASPM for now. + */ + list_for_each_entry(child, &linkbus->devices, bus_list) { + if (child->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) { + link->aspm_disable = ASPM_STATE_ALL; + break; + } + } + + /* Get and check endpoint acceptable latencies */ list_for_each_entry(child, &linkbus->devices, bus_list) { int pos; u32 reg32, encoding; @@ -365,109 +422,46 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) pos = pci_find_capability(child, PCI_CAP_ID_EXP); pci_read_config_dword(child, pos + PCI_EXP_DEVCAP, ®32); + /* Calculate endpoint L0s acceptable latency */ encoding = (reg32 & PCI_EXP_DEVCAP_L0S) >> 6; acceptable->l0s = calc_l0s_acceptable(encoding); - if (link->aspm_support & PCIE_LINK_STATE_L1) { - encoding = (reg32 & PCI_EXP_DEVCAP_L1) >> 9; - acceptable->l1 = calc_l1_acceptable(encoding); - } - } -} - -/** - * __pcie_aspm_check_state_one - check latency for endpoint device. - * @endpoint: pointer to the struct pci_dev of endpoint device - * - * TBD: The latency from the endpoint to root complex vary per switch's - * upstream link state above the device. Here we just do a simple check - * which assumes all links above the device can be in L1 state, that - * is we just consider the worst case. If switch's upstream link can't - * be put into L0S/L1, then our check is too strictly. - */ -static u32 __pcie_aspm_check_state_one(struct pci_dev *endpoint, u32 state) -{ - u32 l1_switch_latency = 0; - struct aspm_latency *acceptable; - struct pcie_link_state *link; - - link = endpoint->bus->self->link_state; - state &= link->aspm_support; - acceptable = &link->acceptable[PCI_FUNC(endpoint->devfn)]; + /* Calculate endpoint L1 acceptable latency */ + encoding = (reg32 & PCI_EXP_DEVCAP_L1) >> 9; + acceptable->l1 = calc_l1_acceptable(encoding); - while (link && state) { - if ((state & PCIE_LINK_STATE_L0S) && - (link->latency.l0s > acceptable->l0s)) - state &= ~PCIE_LINK_STATE_L0S; - if ((state & PCIE_LINK_STATE_L1) && - (link->latency.l1 + l1_switch_latency > acceptable->l1)) - state &= ~PCIE_LINK_STATE_L1; - link = link->parent; - /* - * Every switch on the path to root complex need 1 - * more microsecond for L1. Spec doesn't mention L0s. - */ - l1_switch_latency += 1000; - } - return state; -} - -static u32 pcie_aspm_check_state(struct pcie_link_state *link, u32 state) -{ - pci_power_t power_state; - struct pci_dev *child; - struct pci_bus *linkbus = link->pdev->subordinate; - - /* If no child, ignore the link */ - if (list_empty(&linkbus->devices)) - return state; - - list_for_each_entry(child, &linkbus->devices, bus_list) { - /* - * If downstream component of a link is pci bridge, we - * disable ASPM for now for the link - */ - if (child->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) - return 0; - - if ((child->pcie_type != PCI_EXP_TYPE_ENDPOINT && - child->pcie_type != PCI_EXP_TYPE_LEG_END)) - continue; - /* Device not in D0 doesn't need check latency */ - power_state = child->current_state; - if (power_state == PCI_D1 || power_state == PCI_D2 || - power_state == PCI_D3hot || power_state == PCI_D3cold) - continue; - state = __pcie_aspm_check_state_one(child, state); + pcie_aspm_check_latency(child); } - return state; } -static void __pcie_aspm_config_one_dev(struct pci_dev *pdev, unsigned int state) +static void pcie_config_aspm_dev(struct pci_dev *pdev, u32 val) { u16 reg16; int pos = pci_find_capability(pdev, PCI_CAP_ID_EXP); pci_read_config_word(pdev, pos + PCI_EXP_LNKCTL, ®16); reg16 &= ~0x3; - reg16 |= state; + reg16 |= val; pci_write_config_word(pdev, pos + PCI_EXP_LNKCTL, reg16); } -static void __pcie_aspm_config_link(struct pcie_link_state *link, u32 state) +static void pcie_config_aspm_link(struct pcie_link_state *link, u32 state) { + u32 upstream = 0, dwstream = 0; struct pci_dev *child, *parent = link->pdev; struct pci_bus *linkbus = parent->subordinate; - /* If no child, disable the link */ - if (list_empty(&linkbus->devices)) - state = 0; - /* - * If the downstream component has pci bridge function, don't - * do ASPM now. - */ - list_for_each_entry(child, &linkbus->devices, bus_list) { - if (child->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) - return; + /* Nothing to do if the link is already in the requested state */ + state &= (link->aspm_capable & ~link->aspm_disable); + if (link->aspm_enabled == state) + return; + /* Convert ASPM state to upstream/downstream ASPM register state */ + if (state & ASPM_STATE_L0S_UP) + dwstream |= PCIE_LINK_STATE_L0S; + if (state & ASPM_STATE_L0S_DW) + upstream |= PCIE_LINK_STATE_L0S; + if (state & ASPM_STATE_L1) { + upstream |= PCIE_LINK_STATE_L1; + dwstream |= PCIE_LINK_STATE_L1; } /* * Spec 2.0 suggests all functions should be configured the @@ -475,67 +469,24 @@ static void __pcie_aspm_config_link(struct pcie_link_state *link, u32 state) * upstream component first and then downstream, and vice * versa for disabling ASPM L1. Spec doesn't mention L0S. */ - if (state & PCIE_LINK_STATE_L1) - __pcie_aspm_config_one_dev(parent, state); - + if (state & ASPM_STATE_L1) + pcie_config_aspm_dev(parent, upstream); list_for_each_entry(child, &linkbus->devices, bus_list) - __pcie_aspm_config_one_dev(child, state); - - if (!(state & PCIE_LINK_STATE_L1)) - __pcie_aspm_config_one_dev(parent, state); + pcie_config_aspm_dev(child, dwstream); + if (!(state & ASPM_STATE_L1)) + pcie_config_aspm_dev(parent, upstream); link->aspm_enabled = state; } -/* Check the whole hierarchy, and configure each link in the hierarchy */ -static void __pcie_aspm_configure_link_state(struct pcie_link_state *link, - u32 state) +static void pcie_config_aspm_path(struct pcie_link_state *link) { - struct pcie_link_state *leaf, *root = link->root; - - state &= (PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1); - - /* Check all links who have specific root port link */ - list_for_each_entry(leaf, &link_list, sibling) { - if (!list_empty(&leaf->children) || (leaf->root != root)) - continue; - state = pcie_aspm_check_state(leaf, state); - } - /* Check root port link too in case it hasn't children */ - state = pcie_aspm_check_state(root, state); - if (link->aspm_enabled == state) - return; - /* - * We must change the hierarchy. See comments in - * __pcie_aspm_config_link for the order - **/ - if (state & PCIE_LINK_STATE_L1) { - list_for_each_entry(leaf, &link_list, sibling) { - if (leaf->root == root) - __pcie_aspm_config_link(leaf, state); - } - } else { - list_for_each_entry_reverse(leaf, &link_list, sibling) { - if (leaf->root == root) - __pcie_aspm_config_link(leaf, state); - } + while (link) { + pcie_config_aspm_link(link, policy_to_aspm_state(link)); + link = link->parent; } } -/* - * pcie_aspm_configure_link_state: enable/disable PCI express link state - * @pdev: the root port or switch downstream port - */ -static void pcie_aspm_configure_link_state(struct pcie_link_state *link, - u32 state) -{ - down_read(&pci_bus_sem); - mutex_lock(&aspm_lock); - __pcie_aspm_configure_link_state(link, state); - mutex_unlock(&aspm_lock); - up_read(&pci_bus_sem); -} - static void free_link_state(struct pcie_link_state *link) { link->pdev->link_state = NULL; @@ -570,10 +521,9 @@ static int pcie_aspm_sanity_check(struct pci_dev *pdev) return 0; } -static struct pcie_link_state *pcie_aspm_setup_link_state(struct pci_dev *pdev) +static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev) { struct pcie_link_state *link; - int blacklist = !!pcie_aspm_sanity_check(pdev); link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) @@ -599,15 +549,7 @@ static struct pcie_link_state *pcie_aspm_setup_link_state(struct pci_dev *pdev) link->root = link->parent->root; list_add(&link->sibling, &link_list); - pdev->link_state = link; - - /* Check ASPM capability */ - pcie_aspm_cap_init(link, blacklist); - - /* Check Clock PM capability */ - pcie_clkpm_cap_init(link, blacklist); - return link; } @@ -618,8 +560,8 @@ static struct pcie_link_state *pcie_aspm_setup_link_state(struct pci_dev *pdev) */ void pcie_aspm_init_link_state(struct pci_dev *pdev) { - u32 state; struct pcie_link_state *link; + int blacklist = !!pcie_aspm_sanity_check(pdev); if (aspm_disabled || !pdev->is_pcie || pdev->link_state) return; @@ -637,47 +579,64 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev) goto out; mutex_lock(&aspm_lock); - link = pcie_aspm_setup_link_state(pdev); + link = alloc_pcie_link_state(pdev); if (!link) goto unlock; /* - * Setup initial ASPM state - * - * If link has switch, delay the link config. The leaf link - * initialization will config the whole hierarchy. But we must - * make sure BIOS doesn't set unsupported link state. + * Setup initial ASPM state. Note that we need to configure + * upstream links also because capable state of them can be + * update through pcie_aspm_cap_init(). */ - if (pcie_aspm_downstream_has_switch(link)) { - state = pcie_aspm_check_state(link, link->aspm_default); - __pcie_aspm_config_link(link, state); - } else { - state = policy_to_aspm_state(link); - __pcie_aspm_configure_link_state(link, state); - } + pcie_aspm_cap_init(link, blacklist); + pcie_config_aspm_path(link); /* Setup initial Clock PM state */ - state = (link->clkpm_capable) ? policy_to_clkpm_state(link) : 0; - pcie_set_clkpm(link, state); + pcie_clkpm_cap_init(link, blacklist); + pcie_set_clkpm(link, policy_to_clkpm_state(link)); unlock: mutex_unlock(&aspm_lock); out: up_read(&pci_bus_sem); } +/* Recheck latencies and update aspm_capable for links under the root */ +static void pcie_update_aspm_capable(struct pcie_link_state *root) +{ + struct pcie_link_state *link; + BUG_ON(root->parent); + list_for_each_entry(link, &link_list, sibling) { + if (link->root != root) + continue; + link->aspm_capable = link->aspm_support; + } + list_for_each_entry(link, &link_list, sibling) { + struct pci_dev *child; + struct pci_bus *linkbus = link->pdev->subordinate; + if (link->root != root) + continue; + list_for_each_entry(child, &linkbus->devices, bus_list) { + if ((child->pcie_type != PCI_EXP_TYPE_ENDPOINT) && + (child->pcie_type != PCI_EXP_TYPE_LEG_END)) + continue; + pcie_aspm_check_latency(child); + } + } +} + /* @pdev: the endpoint device */ void pcie_aspm_exit_link_state(struct pci_dev *pdev) { struct pci_dev *parent = pdev->bus->self; - struct pcie_link_state *link_state = parent->link_state; + struct pcie_link_state *link, *root, *parent_link; - if (aspm_disabled || !pdev->is_pcie || !parent || !link_state) + if (aspm_disabled || !pdev->is_pcie || !parent || !parent->link_state) return; - if (parent->pcie_type != PCI_EXP_TYPE_ROOT_PORT && - parent->pcie_type != PCI_EXP_TYPE_DOWNSTREAM) + if ((parent->pcie_type != PCI_EXP_TYPE_ROOT_PORT) && + (parent->pcie_type != PCI_EXP_TYPE_DOWNSTREAM)) return; + down_read(&pci_bus_sem); mutex_lock(&aspm_lock); - /* * All PCIe functions are in one slot, remove one function will remove * the whole slot, so just wait until we are the last function left. @@ -685,13 +644,20 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev) if (!list_is_last(&pdev->bus_list, &parent->subordinate->devices)) goto out; + link = parent->link_state; + root = link->root; + parent_link = link->parent; + /* All functions are removed, so just disable ASPM for the link */ - __pcie_aspm_config_one_dev(parent, 0); - list_del(&link_state->sibling); - list_del(&link_state->link); + pcie_config_aspm_link(link, 0); + list_del(&link->sibling); + list_del(&link->link); /* Clock PM is for endpoint device */ + free_link_state(link); - free_link_state(link_state); + /* Recheck latencies and configure upstream links */ + pcie_update_aspm_capable(root); + pcie_config_aspm_path(parent_link); out: mutex_unlock(&aspm_lock); up_read(&pci_bus_sem); @@ -700,18 +666,23 @@ out: /* @pdev: the root port or switch downstream port */ void pcie_aspm_pm_state_change(struct pci_dev *pdev) { - struct pcie_link_state *link_state = pdev->link_state; + struct pcie_link_state *link = pdev->link_state; - if (aspm_disabled || !pdev->is_pcie || !pdev->link_state) + if (aspm_disabled || !pdev->is_pcie || !link) return; - if (pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT && - pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM) + if ((pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT) && + (pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM)) return; /* - * devices changed PM state, we should recheck if latency meets all - * functions' requirement + * Devices changed PM state, we should recheck if latency + * meets all functions' requirement */ - pcie_aspm_configure_link_state(link_state, link_state->aspm_enabled); + down_read(&pci_bus_sem); + mutex_lock(&aspm_lock); + pcie_update_aspm_capable(link->root); + pcie_config_aspm_path(link); + mutex_unlock(&aspm_lock); + up_read(&pci_bus_sem); } /* @@ -721,7 +692,7 @@ void pcie_aspm_pm_state_change(struct pci_dev *pdev) void pci_disable_link_state(struct pci_dev *pdev, int state) { struct pci_dev *parent = pdev->bus->self; - struct pcie_link_state *link_state; + struct pcie_link_state *link; if (aspm_disabled || !pdev->is_pcie) return; @@ -733,12 +704,16 @@ void pci_disable_link_state(struct pci_dev *pdev, int state) down_read(&pci_bus_sem); mutex_lock(&aspm_lock); - link_state = parent->link_state; - link_state->aspm_support &= ~state; - __pcie_aspm_configure_link_state(link_state, link_state->aspm_enabled); + link = parent->link_state; + if (state & PCIE_LINK_STATE_L0S) + link->aspm_disable |= ASPM_STATE_L0S; + if (state & PCIE_LINK_STATE_L1) + link->aspm_disable |= ASPM_STATE_L1; + pcie_config_aspm_link(link, policy_to_aspm_state(link)); + if (state & PCIE_LINK_STATE_CLKPM) { - link_state->clkpm_capable = 0; - pcie_set_clkpm(link_state, 0); + link->clkpm_capable = 0; + pcie_set_clkpm(link, 0); } mutex_unlock(&aspm_lock); up_read(&pci_bus_sem); @@ -748,7 +723,7 @@ EXPORT_SYMBOL(pci_disable_link_state); static int pcie_aspm_set_policy(const char *val, struct kernel_param *kp) { int i; - struct pcie_link_state *link_state; + struct pcie_link_state *link; for (i = 0; i < ARRAY_SIZE(policy_str); i++) if (!strncmp(val, policy_str[i], strlen(policy_str[i]))) @@ -761,10 +736,9 @@ static int pcie_aspm_set_policy(const char *val, struct kernel_param *kp) down_read(&pci_bus_sem); mutex_lock(&aspm_lock); aspm_policy = i; - list_for_each_entry(link_state, &link_list, sibling) { - __pcie_aspm_configure_link_state(link_state, - policy_to_aspm_state(link_state)); - pcie_set_clkpm(link_state, policy_to_clkpm_state(link_state)); + list_for_each_entry(link, &link_list, sibling) { + pcie_config_aspm_link(link, policy_to_aspm_state(link)); + pcie_set_clkpm(link, policy_to_clkpm_state(link)); } mutex_unlock(&aspm_lock); up_read(&pci_bus_sem); @@ -802,18 +776,28 @@ static ssize_t link_state_store(struct device *dev, size_t n) { struct pci_dev *pdev = to_pci_dev(dev); - int state; + struct pcie_link_state *link, *root = pdev->link_state->root; + u32 val = buf[0] - '0', state = 0; - if (n < 1) + if (n < 1 || val > 3) return -EINVAL; - state = buf[0]-'0'; - if (state >= 0 && state <= 3) { - /* setup link aspm state */ - pcie_aspm_configure_link_state(pdev->link_state, state); - return n; - } - return -EINVAL; + /* Convert requested state to ASPM state */ + if (val & PCIE_LINK_STATE_L0S) + state |= ASPM_STATE_L0S; + if (val & PCIE_LINK_STATE_L1) + state |= ASPM_STATE_L1; + + down_read(&pci_bus_sem); + mutex_lock(&aspm_lock); + list_for_each_entry(link, &link_list, sibling) { + if (link->root != root) + continue; + pcie_config_aspm_link(link, state); + } + mutex_unlock(&aspm_lock); + up_read(&pci_bus_sem); + return n; } static ssize_t clk_ctl_show(struct device *dev, diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index 13ffdc35ea0..52f84fca9f7 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -187,14 +187,9 @@ static int pcie_port_enable_msix(struct pci_dev *dev, int *vectors, int mask) */ static int assign_interrupt_mode(struct pci_dev *dev, int *vectors, int mask) { - struct pcie_port_data *port_data = pci_get_drvdata(dev); int irq, interrupt_mode = PCIE_PORT_NO_IRQ; int i; - /* Check MSI quirk */ - if (port_data->port_type == PCIE_RC_PORT && pcie_mch_quirk) - goto Fallback; - /* Try to use MSI-X if supported */ if (!pcie_port_enable_msix(dev, vectors, mask)) return PCIE_PORT_MSIX_MODE; @@ -203,7 +198,6 @@ static int assign_interrupt_mode(struct pci_dev *dev, int *vectors, int mask) if (!pci_enable_msi(dev)) interrupt_mode = PCIE_PORT_MSI_MODE; - Fallback: if (interrupt_mode == PCIE_PORT_NO_IRQ && dev->pin) interrupt_mode = PCIE_PORT_INTx_MODE; diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c index 091ce70051e..6df5c984a79 100644 --- a/drivers/pci/pcie/portdrv_pci.c +++ b/drivers/pci/pcie/portdrv_pci.c @@ -205,6 +205,7 @@ static pci_ers_result_t pcie_portdrv_slot_reset(struct pci_dev *dev) /* If fatal, restore cfg space for possible link reset at upstream */ if (dev->error_state == pci_channel_io_frozen) { + dev->state_saved = true; pci_restore_state(dev); pcie_portdrv_restore_config(dev); pci_enable_pcie_error_reporting(dev); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 40e75f6a505..8105e32117f 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -235,7 +235,10 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, res->start = l64; res->end = l64 + sz64; dev_printk(KERN_DEBUG, &dev->dev, - "reg %x 64bit mmio: %pR\n", pos, res); + "reg %x %s: %pR\n", pos, + (res->flags & IORESOURCE_PREFETCH) ? + "64bit mmio pref" : "64bit mmio", + res); } res->flags |= IORESOURCE_MEM_64; @@ -249,7 +252,9 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, res->end = l + sz; dev_printk(KERN_DEBUG, &dev->dev, "reg %x %s: %pR\n", pos, - (res->flags & IORESOURCE_IO) ? "io port" : "32bit mmio", + (res->flags & IORESOURCE_IO) ? "io port" : + ((res->flags & IORESOURCE_PREFETCH) ? + "32bit mmio pref" : "32bit mmio"), res); } @@ -692,6 +697,23 @@ static void set_pcie_port_type(struct pci_dev *pdev) pdev->pcie_type = (reg16 & PCI_EXP_FLAGS_TYPE) >> 4; } +static void set_pcie_hotplug_bridge(struct pci_dev *pdev) +{ + int pos; + u16 reg16; + u32 reg32; + + pos = pci_find_capability(pdev, PCI_CAP_ID_EXP); + if (!pos) + return; + pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, ®16); + if (!(reg16 & PCI_EXP_FLAGS_SLOT)) + return; + pci_read_config_dword(pdev, pos + PCI_EXP_SLTCAP, ®32); + if (reg32 & PCI_EXP_SLTCAP_HPC) + pdev->is_hotplug_bridge = 1; +} + #define LEGACY_IO_RESOURCE (IORESOURCE_IO | IORESOURCE_PCI_FIXED) /** @@ -799,6 +821,7 @@ int pci_setup_device(struct pci_dev *dev) pci_read_irq(dev); dev->transparent = ((dev->class & 0xff) == 1); pci_read_bases(dev, 2, PCI_ROM_ADDRESS1); + set_pcie_hotplug_bridge(dev); break; case PCI_HEADER_TYPE_CARDBUS: /* CardBus bridge header */ @@ -1009,6 +1032,9 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) /* Fix up broken headers */ pci_fixup_device(pci_fixup_header, dev); + /* Clear the state_saved flag. */ + dev->state_saved = false; + /* Initialize various capabilities */ pci_init_capabilities(dev); @@ -1061,8 +1087,7 @@ int pci_scan_slot(struct pci_bus *bus, int devfn) if (dev && !dev->is_added) /* new device? */ nr++; - if ((dev && dev->multifunction) || - (!dev && pcibios_scan_all_fns(bus, devfn))) { + if (dev && dev->multifunction) { for (fn = 1; fn < 8; fn++) { dev = pci_scan_single_device(bus, devfn + fn); if (dev) { diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 56552d74abe..6099facecd7 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -31,8 +31,6 @@ int isa_dma_bridge_buggy; EXPORT_SYMBOL(isa_dma_bridge_buggy); int pci_pci_problems; EXPORT_SYMBOL(pci_pci_problems); -int pcie_mch_quirk; -EXPORT_SYMBOL(pcie_mch_quirk); #ifdef CONFIG_PCI_QUIRKS /* @@ -992,7 +990,7 @@ DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82454NX, static void __devinit quirk_amd_ide_mode(struct pci_dev *pdev) { - /* set sb600/sb700/sb800 sata to ahci mode */ + /* set SBX00 SATA in IDE mode to AHCI mode */ u8 tmp; pci_read_config_byte(pdev, PCI_CLASS_DEVICE, &tmp); @@ -1011,6 +1009,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP600_SATA, quirk DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP600_SATA, quirk_amd_ide_mode); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP700_SATA, quirk_amd_ide_mode); DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP700_SATA, quirk_amd_ide_mode); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_SB900_SATA_IDE, quirk_amd_ide_mode); +DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_SB900_SATA_IDE, quirk_amd_ide_mode); /* * Serverworks CSB5 IDE does not fully support native mode @@ -1058,6 +1058,11 @@ static void __devinit quirk_no_ata_d3(struct pci_dev *pdev) } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, PCI_ANY_ID, quirk_no_ata_d3); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_ATI, PCI_ANY_ID, quirk_no_ata_d3); +/* ALi loses some register settings that we cannot then restore */ +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AL, PCI_ANY_ID, quirk_no_ata_d3); +/* VIA comes back fine but we need to keep it alive or ACPI GTM failures + occur when mode detecting */ +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_VIA, PCI_ANY_ID, quirk_no_ata_d3); /* This was originally an Alpha specific thing, but it really fits here. * The i82375 PCI/EISA bridge appears as non-classified. Fix that. @@ -1196,6 +1201,7 @@ static void __init asus_hides_smbus_hostbridge(struct pci_dev *dev) switch(dev->subsystem_device) { case 0x00b8: /* Compaq Evo D510 CMT */ case 0x00b9: /* Compaq Evo D510 SFF */ + case 0x00ba: /* Compaq Evo D510 USDT */ /* Motherboard doesn't have Host bridge * subvendor/subdevice IDs and on-board VGA * controller is disabled if an AGP card is @@ -1494,7 +1500,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_EESSC, quirk_a static void __devinit quirk_pcie_mch(struct pci_dev *pdev) { - pcie_mch_quirk = 1; + pci_msi_off(pdev); + pdev->no_msi = 1; } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7520_MCH, quirk_pcie_mch); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7320_MCH, quirk_pcie_mch); @@ -1562,10 +1569,8 @@ static void quirk_reroute_to_boot_interrupts_intel(struct pci_dev *dev) return; dev->irq_reroute_variant = INTEL_IRQ_REROUTE_VARIANT; - - printk(KERN_INFO "PCI quirk: reroute interrupts for 0x%04x:0x%04x\n", - dev->vendor, dev->device); - return; + dev_info(&dev->dev, "rerouting interrupts for [%04x:%04x]\n", + dev->vendor, dev->device); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_80333_0, quirk_reroute_to_boot_interrupts_intel); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_80333_1, quirk_reroute_to_boot_interrupts_intel); @@ -1607,8 +1612,8 @@ static void quirk_disable_intel_boot_interrupt(struct pci_dev *dev) pci_config_word |= INTEL_6300_DISABLE_BOOT_IRQ; pci_write_config_word(dev, INTEL_6300_IOAPIC_ABAR, pci_config_word); - printk(KERN_INFO "disabled boot interrupt on device 0x%04x:0x%04x\n", - dev->vendor, dev->device); + dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n", + dev->vendor, dev->device); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_10, quirk_disable_intel_boot_interrupt); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_10, quirk_disable_intel_boot_interrupt); @@ -1640,8 +1645,8 @@ static void quirk_disable_broadcom_boot_interrupt(struct pci_dev *dev) pci_write_config_dword(dev, BC_HT1000_FEATURE_REG, pci_config_dword); - printk(KERN_INFO "disabled boot interrupts on PCI device" - "0x%04x:0x%04x\n", dev->vendor, dev->device); + dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n", + dev->vendor, dev->device); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_HT1000SB, quirk_disable_broadcom_boot_interrupt); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_HT1000SB, quirk_disable_broadcom_boot_interrupt); @@ -1671,8 +1676,8 @@ static void quirk_disable_amd_813x_boot_interrupt(struct pci_dev *dev) pci_config_dword &= ~AMD_813X_NOIOAMODE; pci_write_config_dword(dev, AMD_813X_MISC, pci_config_dword); - printk(KERN_INFO "disabled boot interrupts on PCI device " - "0x%04x:0x%04x\n", dev->vendor, dev->device); + dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n", + dev->vendor, dev->device); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8131_BRIDGE, quirk_disable_amd_813x_boot_interrupt); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8132_BRIDGE, quirk_disable_amd_813x_boot_interrupt); @@ -1688,14 +1693,13 @@ static void quirk_disable_amd_8111_boot_interrupt(struct pci_dev *dev) pci_read_config_word(dev, AMD_8111_PCI_IRQ_ROUTING, &pci_config_word); if (!pci_config_word) { - printk(KERN_INFO "boot interrupts on PCI device 0x%04x:0x%04x " - "already disabled\n", - dev->vendor, dev->device); + dev_info(&dev->dev, "boot interrupts on device [%04x:%04x] " + "already disabled\n", dev->vendor, dev->device); return; } pci_write_config_word(dev, AMD_8111_PCI_IRQ_ROUTING, 0); - printk(KERN_INFO "disabled boot interrupts on PCI device " - "0x%04x:0x%04x\n", dev->vendor, dev->device); + dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n", + dev->vendor, dev->device); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8111_SMBUS, quirk_disable_amd_8111_boot_interrupt); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8111_SMBUS, quirk_disable_amd_8111_boot_interrupt); @@ -2377,8 +2381,10 @@ static void __devinit nv_msi_ht_cap_quirk_leaf(struct pci_dev *dev) } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, nv_msi_ht_cap_quirk_leaf); +DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, nv_msi_ht_cap_quirk_leaf); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, PCI_ANY_ID, nv_msi_ht_cap_quirk_all); +DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_AL, PCI_ANY_ID, nv_msi_ht_cap_quirk_all); static void __devinit quirk_msi_intx_disable_bug(struct pci_dev *dev) { @@ -2487,6 +2493,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10e6, quirk_i82576_sriov); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10e7, quirk_i82576_sriov); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10e8, quirk_i82576_sriov); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x150a, quirk_i82576_sriov); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x150d, quirk_i82576_sriov); #endif /* CONFIG_PCI_IOV */ diff --git a/drivers/pci/search.c b/drivers/pci/search.c index e8cb5051c31..ec415352d9b 100644 --- a/drivers/pci/search.c +++ b/drivers/pci/search.c @@ -113,37 +113,6 @@ pci_find_next_bus(const struct pci_bus *from) return b; } -#ifdef CONFIG_PCI_LEGACY -/** - * pci_find_device - begin or continue searching for a PCI device by vendor/device id - * @vendor: PCI vendor id to match, or %PCI_ANY_ID to match all vendor ids - * @device: PCI device id to match, or %PCI_ANY_ID to match all device ids - * @from: Previous PCI device found in search, or %NULL for new search. - * - * Iterates through the list of known PCI devices. If a PCI device is found - * with a matching @vendor and @device, a pointer to its device structure is - * returned. Otherwise, %NULL is returned. - * A new search is initiated by passing %NULL as the @from argument. - * Otherwise if @from is not %NULL, searches continue from next device - * on the global list. - * - * NOTE: Do not use this function any more; use pci_get_device() instead, as - * the PCI device returned by this function can disappear at any moment in - * time. - */ -struct pci_dev *pci_find_device(unsigned int vendor, unsigned int device, - struct pci_dev *from) -{ - struct pci_dev *pdev; - - pci_dev_get(from); - pdev = pci_get_subsys(vendor, device, PCI_ANY_ID, PCI_ANY_ID, from); - pci_dev_put(pdev); - return pdev; -} -EXPORT_SYMBOL(pci_find_device); -#endif /* CONFIG_PCI_LEGACY */ - /** * pci_get_slot - locate PCI device for a given PCI slot * @bus: PCI bus on which desired PCI device resides diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index b636e245445..cb1a027eb55 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -25,7 +25,7 @@ #include <linux/ioport.h> #include <linux/cache.h> #include <linux/slab.h> - +#include "pci.h" static void pbus_assign_resources_sorted(const struct pci_bus *bus) { @@ -309,7 +309,7 @@ static struct resource *find_free_bus_resource(struct pci_bus *bus, unsigned lon since these windows have 4K granularity and the IO ranges of non-bridge PCI devices are limited to 256 bytes. We must be careful with the ISA aliasing though. */ -static void pbus_size_io(struct pci_bus *bus) +static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size) { struct pci_dev *dev; struct resource *b_res = find_free_bus_resource(bus, IORESOURCE_IO); @@ -336,6 +336,8 @@ static void pbus_size_io(struct pci_bus *bus) size1 += r_size; } } + if (size < min_size) + size = min_size; /* To be fixed in 2.5: we should have sort of HAVE_ISA flag in the struct pci_bus. */ #if defined(CONFIG_ISA) || defined(CONFIG_EISA) @@ -354,7 +356,8 @@ static void pbus_size_io(struct pci_bus *bus) /* Calculate the size of the bus and minimal alignment which guarantees that all child resources fit in this size. */ -static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, unsigned long type) +static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, + unsigned long type, resource_size_t min_size) { struct pci_dev *dev; resource_size_t min_align, align, size; @@ -384,7 +387,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, unsigned long continue; r_size = resource_size(r); /* For bridges size != alignment */ - align = resource_alignment(r); + align = pci_resource_alignment(dev, r); order = __ffs(align) - 20; if (order > 11) { dev_warn(&dev->dev, "BAR %d bad alignment %llx: " @@ -404,6 +407,8 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, unsigned long mem64_mask &= r->flags & IORESOURCE_MEM_64; } } + if (size < min_size) + size = min_size; align = 0; min_align = 0; @@ -483,6 +488,7 @@ void __ref pci_bus_size_bridges(struct pci_bus *bus) { struct pci_dev *dev; unsigned long mask, prefmask; + resource_size_t min_mem_size = 0, min_io_size = 0; list_for_each_entry(dev, &bus->devices, bus_list) { struct pci_bus *b = dev->subordinate; @@ -512,8 +518,12 @@ void __ref pci_bus_size_bridges(struct pci_bus *bus) case PCI_CLASS_BRIDGE_PCI: pci_bridge_check_ranges(bus); + if (bus->self->is_hotplug_bridge) { + min_io_size = pci_hotplug_io_size; + min_mem_size = pci_hotplug_mem_size; + } default: - pbus_size_io(bus); + pbus_size_io(bus, min_io_size); /* If the bridge supports prefetchable range, size it separately. If it doesn't, or its prefetchable window has already been allocated by arch code, try @@ -521,9 +531,11 @@ void __ref pci_bus_size_bridges(struct pci_bus *bus) resources. */ mask = IORESOURCE_MEM; prefmask = IORESOURCE_MEM | IORESOURCE_PREFETCH; - if (pbus_size_mem(bus, prefmask, prefmask)) + if (pbus_size_mem(bus, prefmask, prefmask, min_mem_size)) mask = prefmask; /* Success, size non-prefetch only. */ - pbus_size_mem(bus, mask, IORESOURCE_MEM); + else + min_mem_size += min_mem_size; + pbus_size_mem(bus, mask, IORESOURCE_MEM, min_mem_size); break; } } diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index b711fb7181e..706f82d8111 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -100,16 +100,16 @@ int pci_claim_resource(struct pci_dev *dev, int resource) { struct resource *res = &dev->resource[resource]; struct resource *root; - char *dtype = resource < PCI_BRIDGE_RESOURCES ? "device" : "bridge"; int err; root = pci_find_parent_resource(dev, res); err = -EINVAL; if (root != NULL) - err = insert_resource(root, res); + err = request_resource(root, res); if (err) { + const char *dtype = resource < PCI_BRIDGE_RESOURCES ? "device" : "bridge"; dev_err(&dev->dev, "BAR %d: %s of %s %pR\n", resource, root ? "address space collision on" : @@ -119,6 +119,7 @@ int pci_claim_resource(struct pci_dev *dev, int resource) return err; } +EXPORT_SYMBOL(pci_claim_resource); #ifdef CONFIG_PCI_QUIRKS void pci_disable_bridge_window(struct pci_dev *dev) @@ -144,7 +145,7 @@ static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev, size = resource_size(res); min = (res->flags & IORESOURCE_IO) ? PCIBIOS_MIN_IO : PCIBIOS_MIN_MEM; - align = resource_alignment(res); + align = pci_resource_alignment(dev, res); /* First, try exact prefetching match.. */ ret = pci_bus_alloc_resource(bus, res, size, align, min, @@ -178,7 +179,7 @@ int pci_assign_resource(struct pci_dev *dev, int resno) struct pci_bus *bus; int ret; - align = resource_alignment(res); + align = pci_resource_alignment(dev, res); if (!align) { dev_info(&dev->dev, "BAR %d: can't allocate resource (bogus " "alignment) %pR flags %#lx\n", @@ -259,7 +260,7 @@ void pdev_sort_resources(struct pci_dev *dev, struct resource_list *head) if (!(r->flags) || r->parent) continue; - r_align = resource_alignment(r); + r_align = pci_resource_alignment(dev, r); if (!r_align) { dev_warn(&dev->dev, "BAR %d: bogus alignment " "%pR flags %#lx\n", @@ -271,7 +272,7 @@ void pdev_sort_resources(struct pci_dev *dev, struct resource_list *head) struct resource_list *ln = list->next; if (ln) - align = resource_alignment(ln->res); + align = pci_resource_alignment(ln->dev, ln->res); if (r_align > align) { tmp = kmalloc(sizeof(*tmp), GFP_KERNEL); diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c index eddb0748b0e..8c02b6c53bd 100644 --- a/drivers/pci/slot.c +++ b/drivers/pci/slot.c @@ -311,7 +311,7 @@ EXPORT_SYMBOL_GPL(pci_destroy_slot); #include <linux/pci_hotplug.h> /** * pci_hp_create_link - create symbolic link to the hotplug driver module. - * @slot: struct pci_slot + * @pci_slot: struct pci_slot * * Helper function for pci_hotplug_core.c to create symbolic link to * the hotplug driver module. @@ -334,7 +334,7 @@ EXPORT_SYMBOL_GPL(pci_hp_create_module_link); /** * pci_hp_remove_link - remove symbolic link to the hotplug driver module. - * @slot: struct pci_slot + * @pci_slot: struct pci_slot * * Helper function for pci_hotplug_core.c to remove symbolic link to * the hotplug driver module. diff --git a/drivers/pci/syscall.c b/drivers/pci/syscall.c index ec22284eed3..e1c1ec54089 100644 --- a/drivers/pci/syscall.c +++ b/drivers/pci/syscall.c @@ -9,7 +9,6 @@ #include <linux/errno.h> #include <linux/pci.h> -#include <linux/smp_lock.h> #include <linux/syscalls.h> #include <asm/uaccess.h> #include "pci.h" |