diff --git a/Documentation/ABI/testing/sysfs-devices-online b/Documentation/ABI/testing/sysfs-devices-online new file mode 100644 index 000000000000..f990026c0740 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-devices-online @@ -0,0 +1,20 @@ +What: /sys/devices/.../online +Date: April 2013 +Contact: Rafael J. Wysocki +Description: + The /sys/devices/.../online attribute is only present for + devices whose bus types provide .online() and .offline() + callbacks. The number read from it (0 or 1) reflects the value + of the device's 'offline' field. If that number is 1 and '0' + (or 'n', or 'N') is written to this file, the device bus type's + .offline() callback is executed for the device and (if + successful) its 'offline' field is updated accordingly. In + turn, if that number is 0 and '1' (or 'y', or 'Y') is written to + this file, the device bus type's .online() callback is executed + for the device and (if successful) its 'offline' field is + updated as appropriate. + + After a successful execution of the bus type's .offline() + callback the device cannot be used for any purpose until either + it is removed (i.e. device_del() is called for it), or its bus + type's .online() is exeucted successfully. diff --git a/Documentation/ABI/testing/sysfs-firmware-acpi b/Documentation/ABI/testing/sysfs-firmware-acpi index ce9bee98b43b..b4436cca97a8 100644 --- a/Documentation/ABI/testing/sysfs-firmware-acpi +++ b/Documentation/ABI/testing/sysfs-firmware-acpi @@ -44,6 +44,16 @@ Description: or 0 (unset). Attempts to write any other values to it will cause -EINVAL to be returned. +What: /sys/firmware/acpi/hotplug/force_remove +Date: May 2013 +Contact: Rafael J. Wysocki +Description: + The number in this file (0 or 1) determines whether (1) or not + (0) the ACPI subsystem will allow devices to be hot-removed even + if they cannot be put offline gracefully (from the kernel's + viewpoint). That number can be changed by writing a boolean + value to this file. + What: /sys/firmware/acpi/interrupts/ Date: February 2008 Contact: Len Brown diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index 536562c626a2..d07771bc3d8c 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -34,6 +34,7 @@ acpi-$(CONFIG_ACPI_SLEEP) += proc.o acpi-y += bus.o glue.o acpi-y += scan.o acpi-y += resource.o +acpi-y += acpi_processor.o acpi-y += processor_core.o acpi-y += ec.o acpi-$(CONFIG_ACPI_DOCK) += dock.o diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c index 5e6301e94920..c711d1144044 100644 --- a/drivers/acpi/acpi_memhotplug.c +++ b/drivers/acpi/acpi_memhotplug.c @@ -28,6 +28,7 @@ */ #include +#include #include #include "internal.h" @@ -166,13 +167,50 @@ static int acpi_memory_check_device(struct acpi_memory_device *mem_device) return 0; } +static unsigned long acpi_meminfo_start_pfn(struct acpi_memory_info *info) +{ + return PFN_DOWN(info->start_addr); +} + +static unsigned long acpi_meminfo_end_pfn(struct acpi_memory_info *info) +{ + return PFN_UP(info->start_addr + info->length-1); +} + +static int acpi_bind_memblk(struct memory_block *mem, void *arg) +{ + return acpi_bind_one(&mem->dev, (acpi_handle)arg); +} + +static int acpi_bind_memory_blocks(struct acpi_memory_info *info, + acpi_handle handle) +{ + return walk_memory_range(acpi_meminfo_start_pfn(info), + acpi_meminfo_end_pfn(info), (void *)handle, + acpi_bind_memblk); +} + +static int acpi_unbind_memblk(struct memory_block *mem, void *arg) +{ + acpi_unbind_one(&mem->dev); + return 0; +} + +static void acpi_unbind_memory_blocks(struct acpi_memory_info *info, + acpi_handle handle) +{ + walk_memory_range(acpi_meminfo_start_pfn(info), + acpi_meminfo_end_pfn(info), NULL, acpi_unbind_memblk); +} + static int acpi_memory_enable_device(struct acpi_memory_device *mem_device) { + acpi_handle handle = mem_device->device->handle; int result, num_enabled = 0; struct acpi_memory_info *info; int node; - node = acpi_get_node(mem_device->device->handle); + node = acpi_get_node(handle); /* * Tell the VM there is more memory here... * Note: Assume that this function returns zero on success @@ -203,6 +241,12 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device) if (result && result != -EEXIST) continue; + result = acpi_bind_memory_blocks(info, handle); + if (result) { + acpi_unbind_memory_blocks(info, handle); + return -ENODEV; + } + info->enabled = 1; /* @@ -227,12 +271,11 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device) return 0; } -static int acpi_memory_remove_memory(struct acpi_memory_device *mem_device) +static void acpi_memory_remove_memory(struct acpi_memory_device *mem_device) { - int result = 0, nid; + acpi_handle handle = mem_device->device->handle; struct acpi_memory_info *info, *n; - - nid = acpi_get_node(mem_device->device->handle); + int nid = acpi_get_node(handle); list_for_each_entry_safe(info, n, &mem_device->res_list, list) { if (!info->enabled) @@ -240,15 +283,12 @@ static int acpi_memory_remove_memory(struct acpi_memory_device *mem_device) if (nid < 0) nid = memory_add_physaddr_to_nid(info->start_addr); - result = remove_memory(nid, info->start_addr, info->length); - if (result) - return result; + acpi_unbind_memory_blocks(info, handle); + remove_memory(nid, info->start_addr, info->length); list_del(&info->list); kfree(info); } - - return result; } static void acpi_memory_device_free(struct acpi_memory_device *mem_device) @@ -300,7 +340,7 @@ static int acpi_memory_device_add(struct acpi_device *device, if (result) { dev_err(&device->dev, "acpi_memory_enable_device() error\n"); acpi_memory_device_free(mem_device); - return -ENODEV; + return result; } dev_dbg(&device->dev, "Memory device configured by ACPI\n"); diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c new file mode 100644 index 000000000000..e9b01e35ac37 --- /dev/null +++ b/drivers/acpi/acpi_processor.c @@ -0,0 +1,494 @@ +/* + * acpi_processor.c - ACPI processor enumeration support + * + * Copyright (C) 2001, 2002 Andy Grover + * Copyright (C) 2001, 2002 Paul Diefenbaugh + * Copyright (C) 2004 Dominik Brodowski + * Copyright (C) 2004 Anil S Keshavamurthy + * Copyright (C) 2013, Intel Corporation + * Rafael J. Wysocki + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include + +#include + +#include + +#include "internal.h" + +#define _COMPONENT ACPI_PROCESSOR_COMPONENT + +ACPI_MODULE_NAME("processor"); + +DEFINE_PER_CPU(struct acpi_processor *, processors); +EXPORT_PER_CPU_SYMBOL(processors); + +/* -------------------------------------------------------------------------- + Errata Handling + -------------------------------------------------------------------------- */ + +struct acpi_processor_errata errata __read_mostly; +EXPORT_SYMBOL_GPL(errata); + +static int acpi_processor_errata_piix4(struct pci_dev *dev) +{ + u8 value1 = 0; + u8 value2 = 0; + + + if (!dev) + return -EINVAL; + + /* + * Note that 'dev' references the PIIX4 ACPI Controller. + */ + + switch (dev->revision) { + case 0: + ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found PIIX4 A-step\n")); + break; + case 1: + ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found PIIX4 B-step\n")); + break; + case 2: + ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found PIIX4E\n")); + break; + case 3: + ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found PIIX4M\n")); + break; + default: + ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found unknown PIIX4\n")); + break; + } + + switch (dev->revision) { + + case 0: /* PIIX4 A-step */ + case 1: /* PIIX4 B-step */ + /* + * See specification changes #13 ("Manual Throttle Duty Cycle") + * and #14 ("Enabling and Disabling Manual Throttle"), plus + * erratum #5 ("STPCLK# Deassertion Time") from the January + * 2002 PIIX4 specification update. Applies to only older + * PIIX4 models. + */ + errata.piix4.throttle = 1; + + case 2: /* PIIX4E */ + case 3: /* PIIX4M */ + /* + * See erratum #18 ("C3 Power State/BMIDE and Type-F DMA + * Livelock") from the January 2002 PIIX4 specification update. + * Applies to all PIIX4 models. + */ + + /* + * BM-IDE + * ------ + * Find the PIIX4 IDE Controller and get the Bus Master IDE + * Status register address. We'll use this later to read + * each IDE controller's DMA status to make sure we catch all + * DMA activity. + */ + dev = pci_get_subsys(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_82371AB, + PCI_ANY_ID, PCI_ANY_ID, NULL); + if (dev) { + errata.piix4.bmisx = pci_resource_start(dev, 4); + pci_dev_put(dev); + } + + /* + * Type-F DMA + * ---------- + * Find the PIIX4 ISA Controller and read the Motherboard + * DMA controller's status to see if Type-F (Fast) DMA mode + * is enabled (bit 7) on either channel. Note that we'll + * disable C3 support if this is enabled, as some legacy + * devices won't operate well if fast DMA is disabled. + */ + dev = pci_get_subsys(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_82371AB_0, + PCI_ANY_ID, PCI_ANY_ID, NULL); + if (dev) { + pci_read_config_byte(dev, 0x76, &value1); + pci_read_config_byte(dev, 0x77, &value2); + if ((value1 & 0x80) || (value2 & 0x80)) + errata.piix4.fdma = 1; + pci_dev_put(dev); + } + + break; + } + + if (errata.piix4.bmisx) + ACPI_DEBUG_PRINT((ACPI_DB_INFO, + "Bus master activity detection (BM-IDE) erratum enabled\n")); + if (errata.piix4.fdma) + ACPI_DEBUG_PRINT((ACPI_DB_INFO, + "Type-F DMA livelock erratum (C3 disabled)\n")); + + return 0; +} + +static int acpi_processor_errata(struct acpi_processor *pr) +{ + int result = 0; + struct pci_dev *dev = NULL; + + + if (!pr) + return -EINVAL; + + /* + * PIIX4 + */ + dev = pci_get_subsys(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_82371AB_3, PCI_ANY_ID, + PCI_ANY_ID, NULL); + if (dev) { + result = acpi_processor_errata_piix4(dev); + pci_dev_put(dev); + } + + return result; +} + +/* -------------------------------------------------------------------------- + Initialization + -------------------------------------------------------------------------- */ + +#ifdef CONFIG_ACPI_HOTPLUG_CPU +static int acpi_processor_hotadd_init(struct acpi_processor *pr) +{ + unsigned long long sta; + acpi_status status; + int ret; + + status = acpi_evaluate_integer(pr->handle, "_STA", NULL, &sta); + if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_PRESENT)) + return -ENODEV; + + ret = acpi_map_lsapic(pr->handle, &pr->id); + if (ret) + return ret; + + ret = arch_register_cpu(pr->id); + if (ret) { + acpi_unmap_lsapic(pr->id); + return ret; + } + + /* + * CPU got hot-added, but cpu_data is not initialized yet. Set a flag + * to delay cpu_idle/throttling initialization and do it when the CPU + * gets online for the first time. + */ + pr_info("CPU%d has been hot-added\n", pr->id); + pr->flags.need_hotplug_init = 1; + return 0; +} +#else +static inline int acpi_processor_hotadd_init(struct acpi_processor *pr) +{ + return -ENODEV; +} +#endif /* CONFIG_ACPI_HOTPLUG_CPU */ + +static int acpi_processor_get_info(struct acpi_device *device) +{ + union acpi_object object = { 0 }; + struct acpi_buffer buffer = { sizeof(union acpi_object), &object }; + struct acpi_processor *pr = acpi_driver_data(device); + int cpu_index, device_declaration = 0; + acpi_status status = AE_OK; + static int cpu0_initialized; + + if (num_online_cpus() > 1) + errata.smp = TRUE; + + acpi_processor_errata(pr); + + /* + * Check to see if we have bus mastering arbitration control. This + * is required for proper C3 usage (to maintain cache coherency). + */ + if (acpi_gbl_FADT.pm2_control_block && acpi_gbl_FADT.pm2_control_length) { + pr->flags.bm_control = 1; + ACPI_DEBUG_PRINT((ACPI_DB_INFO, + "Bus mastering arbitration control present\n")); + } else + ACPI_DEBUG_PRINT((ACPI_DB_INFO, + "No bus mastering arbitration control\n")); + + if (!strcmp(acpi_device_hid(device), ACPI_PROCESSOR_OBJECT_HID)) { + /* Declared with "Processor" statement; match ProcessorID */ + status = acpi_evaluate_object(pr->handle, NULL, NULL, &buffer); + if (ACPI_FAILURE(status)) { + dev_err(&device->dev, + "Failed to evaluate processor object (0x%x)\n", + status); + return -ENODEV; + } + + /* + * TBD: Synch processor ID (via LAPIC/LSAPIC structures) on SMP. + * >>> 'acpi_get_processor_id(acpi_id, &id)' in + * arch/xxx/acpi.c + */ + pr->acpi_id = object.processor.proc_id; + } else { + /* + * Declared with "Device" statement; match _UID. + * Note that we don't handle string _UIDs yet. + */ + unsigned long long value; + status = acpi_evaluate_integer(pr->handle, METHOD_NAME__UID, + NULL, &value); + if (ACPI_FAILURE(status)) { + dev_err(&device->dev, + "Failed to evaluate processor _UID (0x%x)\n", + status); + return -ENODEV; + } + device_declaration = 1; + pr->acpi_id = value; + } + cpu_index = acpi_get_cpuid(pr->handle, device_declaration, pr->acpi_id); + + /* Handle UP system running SMP kernel, with no LAPIC in MADT */ + if (!cpu0_initialized && (cpu_index == -1) && + (num_online_cpus() == 1)) { + cpu_index = 0; + } + + cpu0_initialized = 1; + + pr->id = cpu_index; + + /* + * Extra Processor objects may be enumerated on MP systems with + * less than the max # of CPUs. They should be ignored _iff + * they are physically not present. + */ + if (pr->id == -1) { + int ret = acpi_processor_hotadd_init(pr); + if (ret) + return ret; + } + /* + * On some boxes several processors use the same processor bus id. + * But they are located in different scope. For example: + * \_SB.SCK0.CPU0 + * \_SB.SCK1.CPU0 + * Rename the processor device bus id. And the new bus id will be + * generated as the following format: + * CPU+CPU ID. + */ + sprintf(acpi_device_bid(device), "CPU%X", pr->id); + ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Processor [%d:%d]\n", pr->id, + pr->acpi_id)); + + if (!object.processor.pblk_address) + ACPI_DEBUG_PRINT((ACPI_DB_INFO, "No PBLK (NULL address)\n")); + else if (object.processor.pblk_length != 6) + dev_err(&device->dev, "Invalid PBLK length [%d]\n", + object.processor.pblk_length); + else { + pr->throttling.address = object.processor.pblk_address; + pr->throttling.duty_offset = acpi_gbl_FADT.duty_offset; + pr->throttling.duty_width = acpi_gbl_FADT.duty_width; + + pr->pblk = object.processor.pblk_address; + + /* + * We don't care about error returns - we just try to mark + * these reserved so that nobody else is confused into thinking + * that this region might be unused.. + * + * (In particular, allocating the IO range for Cardbus) + */ + request_region(pr->throttling.address, 6, "ACPI CPU throttle"); + } + + /* + * If ACPI describes a slot number for this CPU, we can use it to + * ensure we get the right value in the "physical id" field + * of /proc/cpuinfo + */ + status = acpi_evaluate_object(pr->handle, "_SUN", NULL, &buffer); + if (ACPI_SUCCESS(status)) + arch_fix_phys_package_id(pr->id, object.integer.value); + + return 0; +} + +/* + * Do not put anything in here which needs the core to be online. + * For example MSR access or setting up things which check for cpuinfo_x86 + * (cpu_data(cpu)) values, like CPU feature flags, family, model, etc. + * Such things have to be put in and set up by the processor driver's .probe(). + */ +static DEFINE_PER_CPU(void *, processor_device_array); + +static int __cpuinit acpi_processor_add(struct acpi_device *device, + const struct acpi_device_id *id) +{ + struct acpi_processor *pr; + struct device *dev; + int result = 0; + + pr = kzalloc(sizeof(struct acpi_processor), GFP_KERNEL); + if (!pr) + return -ENOMEM; + + if (!zalloc_cpumask_var(&pr->throttling.shared_cpu_map, GFP_KERNEL)) { + result = -ENOMEM; + goto err_free_pr; + } + + pr->handle = device->handle; + strcpy(acpi_device_name(device), ACPI_PROCESSOR_DEVICE_NAME); + strcpy(acpi_device_class(device), ACPI_PROCESSOR_CLASS); + device->driver_data = pr; + + result = acpi_processor_get_info(device); + if (result) /* Processor is not physically present or unavailable */ + return 0; + +#ifdef CONFIG_SMP + if (pr->id >= setup_max_cpus && pr->id != 0) + return 0; +#endif + + BUG_ON(pr->id >= nr_cpu_ids); + + /* + * Buggy BIOS check. + * ACPI id of processors can be reported wrongly by the BIOS. + * Don't trust it blindly + */ + if (per_cpu(processor_device_array, pr->id) != NULL && + per_cpu(processor_device_array, pr->id) != device) { + dev_warn(&device->dev, + "BIOS reported wrong ACPI id %d for the processor\n", + pr->id); + /* Give up, but do not abort the namespace scan. */ + goto err; + } + /* + * processor_device_array is not cleared on errors to allow buggy BIOS + * checks. + */ + per_cpu(processor_device_array, pr->id) = device; + per_cpu(processors, pr->id) = pr; + + dev = get_cpu_device(pr->id); + if (!dev) { + result = -ENODEV; + goto err; + } + + result = acpi_bind_one(dev, pr->handle); + if (result) + goto err; + + pr->dev = dev; + dev->offline = pr->flags.need_hotplug_init; + + /* Trigger the processor driver's .probe() if present. */ + if (device_attach(dev) >= 0) + return 1; + + dev_err(dev, "Processor driver could not be attached\n"); + acpi_unbind_one(dev); + + err: + free_cpumask_var(pr->throttling.shared_cpu_map); + device->driver_data = NULL; + per_cpu(processors, pr->id) = NULL; + err_free_pr: + kfree(pr); + return result; +} + +#ifdef CONFIG_ACPI_HOTPLUG_CPU +/* -------------------------------------------------------------------------- + Removal + -------------------------------------------------------------------------- */ + +static void acpi_processor_remove(struct acpi_device *device) +{ + struct acpi_processor *pr; + + if (!device || !acpi_driver_data(device)) + return; + + pr = acpi_driver_data(device); + if (pr->id >= nr_cpu_ids) + goto out; + + /* + * The only reason why we ever get here is CPU hot-removal. The CPU is + * already offline and the ACPI device removal locking prevents it from + * being put back online at this point. + * + * Unbind the driver from the processor device and detach it from the + * ACPI companion object. + */ + device_release_driver(pr->dev); + acpi_unbind_one(pr->dev); + + /* Clean up. */ + per_cpu(processor_device_array, pr->id) = NULL; + per_cpu(processors, pr->id) = NULL; + try_offline_node(cpu_to_node(pr->id)); + + /* Remove the CPU. */ + get_online_cpus(); + arch_unregister_cpu(pr->id); + acpi_unmap_lsapic(pr->id); + put_online_cpus(); + + out: + free_cpumask_var(pr->throttling.shared_cpu_map); + kfree(pr); +} +#endif /* CONFIG_ACPI_HOTPLUG_CPU */ + +/* + * The following ACPI IDs are known to be suitable for representing as + * processor devices. + */ +static const struct acpi_device_id processor_device_ids[] = { + + { ACPI_PROCESSOR_OBJECT_HID, }, + { ACPI_PROCESSOR_DEVICE_HID, }, + + { } +}; + +static struct acpi_scan_handler __refdata processor_handler = { + .ids = processor_device_ids, + .attach = acpi_processor_add, +#ifdef CONFIG_ACPI_HOTPLUG_CPU + .detach = acpi_processor_remove, +#endif + .hotplug = { + .enabled = true, + }, +}; + +void __init acpi_processor_init(void) +{ + acpi_scan_add_handler_with_hotplug(&processor_handler, "processor"); +} diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c index 40a84cc6740c..9783f400d857 100644 --- a/drivers/acpi/glue.c +++ b/drivers/acpi/glue.c @@ -105,7 +105,7 @@ acpi_handle acpi_get_child(acpi_handle parent, u64 address) } EXPORT_SYMBOL(acpi_get_child); -static int acpi_bind_one(struct device *dev, acpi_handle handle) +int acpi_bind_one(struct device *dev, acpi_handle handle) { struct acpi_device *acpi_dev; acpi_status status; @@ -188,8 +188,9 @@ static int acpi_bind_one(struct device *dev, acpi_handle handle) kfree(physical_node); goto err; } +EXPORT_SYMBOL_GPL(acpi_bind_one); -static int acpi_unbind_one(struct device *dev) +int acpi_unbind_one(struct device *dev) { struct acpi_device_physical_node *entry; struct acpi_device *acpi_dev; @@ -238,6 +239,7 @@ err: dev_err(dev, "Oops, 'acpi_handle' corrupt\n"); return -EINVAL; } +EXPORT_SYMBOL_GPL(acpi_unbind_one); static int acpi_platform_notify(struct device *dev) { diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index c610a76d92c4..520073ba36b4 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -33,6 +33,7 @@ static inline void acpi_pci_slot_init(void) { } void acpi_pci_root_init(void); void acpi_pci_link_init(void); void acpi_pci_root_hp_init(void); +void acpi_processor_init(void); void acpi_platform_init(void); int acpi_sysfs_init(void); #ifdef CONFIG_ACPI_CONTAINER @@ -51,6 +52,8 @@ void acpi_memory_hotplug_init(void); static inline void acpi_memory_hotplug_init(void) {} #endif +extern bool acpi_force_hot_remove; + void acpi_sysfs_add_hotplug_profile(struct acpi_hotplug_profile *hotplug, const char *name); int acpi_scan_add_handler_with_hotplug(struct acpi_scan_handler *handler, @@ -81,6 +84,8 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle, int type, unsigned long long sta); void acpi_device_add_finalize(struct acpi_device *device); void acpi_free_pnp_ids(struct acpi_device_pnp *pnp); +int acpi_bind_one(struct device *dev, acpi_handle handle); +int acpi_unbind_one(struct device *dev); /* -------------------------------------------------------------------------- Power Resource diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c index c266cdc11784..d93963f1e8f4 100644 --- a/drivers/acpi/processor_driver.c +++ b/drivers/acpi/processor_driver.c @@ -1,11 +1,13 @@ /* - * acpi_processor.c - ACPI Processor Driver ($Revision: 71 $) + * processor_driver.c - ACPI Processor Driver * * Copyright (C) 2001, 2002 Andy Grover * Copyright (C) 2001, 2002 Paul Diefenbaugh * Copyright (C) 2004 Dominik Brodowski * Copyright (C) 2004 Anil S Keshavamurthy * - Added processor hotplug support + * Copyright (C) 2013, Intel Corporation + * Rafael J. Wysocki * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * @@ -24,52 +26,29 @@ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA. * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * TBD: - * 1. Make # power states dynamic. - * 2. Support duty_cycle values that span bit 4. - * 3. Optimize by having scheduler determine business instead of - * having us try to calculate it here. - * 4. Need C1 timing -- must modify kernel (IRQ handler) to get this. */ #include #include #include -#include -#include -#include #include #include -#include -#include #include #include #include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include #include +#include "internal.h" + #define PREFIX "ACPI: " -#define ACPI_PROCESSOR_CLASS "processor" -#define ACPI_PROCESSOR_DEVICE_NAME "Processor" #define ACPI_PROCESSOR_FILE_INFO "info" #define ACPI_PROCESSOR_FILE_THROTTLING "throttling" #define ACPI_PROCESSOR_FILE_LIMIT "limit" #define ACPI_PROCESSOR_NOTIFY_PERFORMANCE 0x80 #define ACPI_PROCESSOR_NOTIFY_POWER 0x81 #define ACPI_PROCESSOR_NOTIFY_THROTTLING 0x82 -#define ACPI_PROCESSOR_DEVICE_HID "ACPI0007" #define ACPI_PROCESSOR_LIMIT_USER 0 #define ACPI_PROCESSOR_LIMIT_THERMAL 1 @@ -81,12 +60,8 @@ MODULE_AUTHOR("Paul Diefenbaugh"); MODULE_DESCRIPTION("ACPI Processor Driver"); MODULE_LICENSE("GPL"); -static int acpi_processor_add(struct acpi_device *device); -static int acpi_processor_remove(struct acpi_device *device); -static void acpi_processor_notify(struct acpi_device *device, u32 event); -static acpi_status acpi_processor_hotadd_init(struct acpi_processor *pr); -static int acpi_processor_handle_eject(struct acpi_processor *pr); -static int acpi_processor_start(struct acpi_processor *pr); +static int acpi_processor_start(struct device *dev); +static int acpi_processor_stop(struct device *dev); static const struct acpi_device_id processor_device_ids[] = { {ACPI_PROCESSOR_OBJECT_HID, 0}, @@ -95,295 +70,24 @@ static const struct acpi_device_id processor_device_ids[] = { }; MODULE_DEVICE_TABLE(acpi, processor_device_ids); -static struct acpi_driver acpi_processor_driver = { +static struct device_driver acpi_processor_driver = { .name = "processor", - .class = ACPI_PROCESSOR_CLASS, - .ids = processor_device_ids, - .ops = { - .add = acpi_processor_add, - .remove = acpi_processor_remove, - .notify = acpi_processor_notify, - }, + .bus = &cpu_subsys, + .acpi_match_table = processor_device_ids, + .probe = acpi_processor_start, + .remove = acpi_processor_stop, }; -#define INSTALL_NOTIFY_HANDLER 1 -#define UNINSTALL_NOTIFY_HANDLER 2 - -DEFINE_PER_CPU(struct acpi_processor *, processors); -EXPORT_PER_CPU_SYMBOL(processors); - -struct acpi_processor_errata errata __read_mostly; - -/* -------------------------------------------------------------------------- - Errata Handling - -------------------------------------------------------------------------- */ - -static int acpi_processor_errata_piix4(struct pci_dev *dev) +static void acpi_processor_notify(acpi_handle handle, u32 event, void *data) { - u8 value1 = 0; - u8 value2 = 0; - - - if (!dev) - return -EINVAL; - - /* - * Note that 'dev' references the PIIX4 ACPI Controller. - */ - - switch (dev->revision) { - case 0: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found PIIX4 A-step\n")); - break; - case 1: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found PIIX4 B-step\n")); - break; - case 2: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found PIIX4E\n")); - break; - case 3: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found PIIX4M\n")); - break; - default: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found unknown PIIX4\n")); - break; - } - - switch (dev->revision) { - - case 0: /* PIIX4 A-step */ - case 1: /* PIIX4 B-step */ - /* - * See specification changes #13 ("Manual Throttle Duty Cycle") - * and #14 ("Enabling and Disabling Manual Throttle"), plus - * erratum #5 ("STPCLK# Deassertion Time") from the January - * 2002 PIIX4 specification update. Applies to only older - * PIIX4 models. - */ - errata.piix4.throttle = 1; - - case 2: /* PIIX4E */ - case 3: /* PIIX4M */ - /* - * See erratum #18 ("C3 Power State/BMIDE and Type-F DMA - * Livelock") from the January 2002 PIIX4 specification update. - * Applies to all PIIX4 models. - */ - - /* - * BM-IDE - * ------ - * Find the PIIX4 IDE Controller and get the Bus Master IDE - * Status register address. We'll use this later to read - * each IDE controller's DMA status to make sure we catch all - * DMA activity. - */ - dev = pci_get_subsys(PCI_VENDOR_ID_INTEL, - PCI_DEVICE_ID_INTEL_82371AB, - PCI_ANY_ID, PCI_ANY_ID, NULL); - if (dev) { - errata.piix4.bmisx = pci_resource_start(dev, 4); - pci_dev_put(dev); - } - - /* - * Type-F DMA - * ---------- - * Find the PIIX4 ISA Controller and read the Motherboard - * DMA controller's status to see if Type-F (Fast) DMA mode - * is enabled (bit 7) on either channel. Note that we'll - * disable C3 support if this is enabled, as some legacy - * devices won't operate well if fast DMA is disabled. - */ - dev = pci_get_subsys(PCI_VENDOR_ID_INTEL, - PCI_DEVICE_ID_INTEL_82371AB_0, - PCI_ANY_ID, PCI_ANY_ID, NULL); - if (dev) { - pci_read_config_byte(dev, 0x76, &value1); - pci_read_config_byte(dev, 0x77, &value2); - if ((value1 & 0x80) || (value2 & 0x80)) - errata.piix4.fdma = 1; - pci_dev_put(dev); - } - - break; - } - - if (errata.piix4.bmisx) - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Bus master activity detection (BM-IDE) erratum enabled\n")); - if (errata.piix4.fdma) - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Type-F DMA livelock erratum (C3 disabled)\n")); - - return 0; -} - -static int acpi_processor_errata(struct acpi_processor *pr) -{ - int result = 0; - struct pci_dev *dev = NULL; - - - if (!pr) - return -EINVAL; - - /* - * PIIX4 - */ - dev = pci_get_subsys(PCI_VENDOR_ID_INTEL, - PCI_DEVICE_ID_INTEL_82371AB_3, PCI_ANY_ID, - PCI_ANY_ID, NULL); - if (dev) { - result = acpi_processor_errata_piix4(dev); - pci_dev_put(dev); - } - - return result; -} - -/* -------------------------------------------------------------------------- - Driver Interface - -------------------------------------------------------------------------- */ - -static int acpi_processor_get_info(struct acpi_device *device) -{ - acpi_status status = 0; - union acpi_object object = { 0 }; - struct acpi_buffer buffer = { sizeof(union acpi_object), &object }; + struct acpi_device *device = data; struct acpi_processor *pr; - int cpu_index, device_declaration = 0; - static int cpu0_initialized; - - pr = acpi_driver_data(device); - if (!pr) - return -EINVAL; - - if (num_online_cpus() > 1) - errata.smp = TRUE; - - acpi_processor_errata(pr); - - /* - * Check to see if we have bus mastering arbitration control. This - * is required for proper C3 usage (to maintain cache coherency). - */ - if (acpi_gbl_FADT.pm2_control_block && acpi_gbl_FADT.pm2_control_length) { - pr->flags.bm_control = 1; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Bus mastering arbitration control present\n")); - } else - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "No bus mastering arbitration control\n")); - - if (!strcmp(acpi_device_hid(device), ACPI_PROCESSOR_OBJECT_HID)) { - /* Declared with "Processor" statement; match ProcessorID */ - status = acpi_evaluate_object(pr->handle, NULL, NULL, &buffer); - if (ACPI_FAILURE(status)) { - dev_err(&device->dev, - "Failed to evaluate processor object (0x%x)\n", - status); - return -ENODEV; - } - - /* - * TBD: Synch processor ID (via LAPIC/LSAPIC structures) on SMP. - * >>> 'acpi_get_processor_id(acpi_id, &id)' in - * arch/xxx/acpi.c - */ - pr->acpi_id = object.processor.proc_id; - } else { - /* - * Declared with "Device" statement; match _UID. - * Note that we don't handle string _UIDs yet. - */ - unsigned long long value; - status = acpi_evaluate_integer(pr->handle, METHOD_NAME__UID, - NULL, &value); - if (ACPI_FAILURE(status)) { - dev_err(&device->dev, - "Failed to evaluate processor _UID (0x%x)\n", - status); - return -ENODEV; - } - device_declaration = 1; - pr->acpi_id = value; - } - cpu_index = acpi_get_cpuid(pr->handle, device_declaration, pr->acpi_id); - - /* Handle UP system running SMP kernel, with no LAPIC in MADT */ - if (!cpu0_initialized && (cpu_index == -1) && - (num_online_cpus() == 1)) { - cpu_index = 0; - } - - cpu0_initialized = 1; - - pr->id = cpu_index; - - /* - * Extra Processor objects may be enumerated on MP systems with - * less than the max # of CPUs. They should be ignored _iff - * they are physically not present. - */ - if (pr->id == -1) { - if (ACPI_FAILURE(acpi_processor_hotadd_init(pr))) - return -ENODEV; - } - /* - * On some boxes several processors use the same processor bus id. - * But they are located in different scope. For example: - * \_SB.SCK0.CPU0 - * \_SB.SCK1.CPU0 - * Rename the processor device bus id. And the new bus id will be - * generated as the following format: - * CPU+CPU ID. - */ - sprintf(acpi_device_bid(device), "CPU%X", pr->id); - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Processor [%d:%d]\n", pr->id, - pr->acpi_id)); - - if (!object.processor.pblk_address) - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "No PBLK (NULL address)\n")); - else if (object.processor.pblk_length != 6) - dev_err(&device->dev, "Invalid PBLK length [%d]\n", - object.processor.pblk_length); - else { - pr->throttling.address = object.processor.pblk_address; - pr->throttling.duty_offset = acpi_gbl_FADT.duty_offset; - pr->throttling.duty_width = acpi_gbl_FADT.duty_width; - - pr->pblk = object.processor.pblk_address; - - /* - * We don't care about error returns - we just try to mark - * these reserved so that nobody else is confused into thinking - * that this region might be unused.. - * - * (In particular, allocating the IO range for Cardbus) - */ - request_region(pr->throttling.address, 6, "ACPI CPU throttle"); - } - - /* - * If ACPI describes a slot number for this CPU, we can use it - * ensure we get the right value in the "physical id" field - * of /proc/cpuinfo - */ - status = acpi_evaluate_object(pr->handle, "_SUN", NULL, &buffer); - if (ACPI_SUCCESS(status)) - arch_fix_phys_package_id(pr->id, object.integer.value); - - return 0; -} - -static DEFINE_PER_CPU(void *, processor_device_array); - -static void acpi_processor_notify(struct acpi_device *device, u32 event) -{ - struct acpi_processor *pr = acpi_driver_data(device); int saved; + if (device->handle != handle) + return; + + pr = acpi_driver_data(device); if (!pr) return; @@ -420,55 +124,62 @@ static void acpi_processor_notify(struct acpi_device *device, u32 event) return; } -static int acpi_cpu_soft_notify(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static __cpuinit int __acpi_processor_start(struct acpi_device *device); + +static int __cpuinit acpi_cpu_soft_notify(struct notifier_block *nfb, + unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; struct acpi_processor *pr = per_cpu(processors, cpu); + struct acpi_device *device; - if (action == CPU_ONLINE && pr) { - /* CPU got physically hotplugged and onlined the first time: - * Initialize missing things + if (!pr || acpi_bus_get_device(pr->handle, &device)) + return NOTIFY_DONE; + + if (action == CPU_ONLINE) { + /* + * CPU got physically hotplugged and onlined for the first time: + * Initialize missing things. */ if (pr->flags.need_hotplug_init) { + int ret; + pr_info("Will online and init hotplugged CPU: %d\n", pr->id); - WARN(acpi_processor_start(pr), "Failed to start CPU:" - " %d\n", pr->id); pr->flags.need_hotplug_init = 0; - /* Normal CPU soft online event */ + ret = __acpi_processor_start(device); + WARN(ret, "Failed to start CPU: %d\n", pr->id); } else { + /* Normal CPU soft online event. */ acpi_processor_ppc_has_changed(pr, 0); acpi_processor_hotplug(pr); acpi_processor_reevaluate_tstate(pr, action); acpi_processor_tstate_has_changed(pr); } - } - if (action == CPU_DEAD && pr) { - /* invalidate the flag.throttling after one CPU is offline */ + } else if (action == CPU_DEAD) { + /* Invalidate flag.throttling after the CPU is offline. */ acpi_processor_reevaluate_tstate(pr, action); } return NOTIFY_OK; } -static struct notifier_block acpi_cpu_notifier = +static struct notifier_block __refdata acpi_cpu_notifier = { .notifier_call = acpi_cpu_soft_notify, }; -/* - * acpi_processor_start() is called by the cpu_hotplug_notifier func: - * acpi_cpu_soft_notify(). Getting it __cpuinit{data} is difficult, the - * root cause seem to be that acpi_processor_uninstall_hotplug_notify() - * is in the module_exit (__exit) func. Allowing acpi_processor_start() - * to not be in __cpuinit section, but being called from __cpuinit funcs - * via __ref looks like the right thing to do here. - */ -static __ref int acpi_processor_start(struct acpi_processor *pr) +static __cpuinit int __acpi_processor_start(struct acpi_device *device) { - struct acpi_device *device = per_cpu(processor_device_array, pr->id); + struct acpi_processor *pr = acpi_driver_data(device); + acpi_status status; int result = 0; + if (!pr) + return -ENODEV; + + if (pr->flags.need_hotplug_init) + return 0; + #ifdef CONFIG_CPU_FREQ acpi_processor_ppc_has_changed(pr, 0); acpi_processor_load_module(pr); @@ -506,462 +217,95 @@ static __ref int acpi_processor_start(struct acpi_processor *pr) goto err_remove_sysfs_thermal; } - return 0; + status = acpi_install_notify_handler(device->handle, ACPI_DEVICE_NOTIFY, + acpi_processor_notify, device); + if (ACPI_SUCCESS(status)) + return 0; -err_remove_sysfs_thermal: + sysfs_remove_link(&pr->cdev->device.kobj, "device"); + err_remove_sysfs_thermal: sysfs_remove_link(&device->dev.kobj, "thermal_cooling"); -err_thermal_unregister: + err_thermal_unregister: thermal_cooling_device_unregister(pr->cdev); -err_power_exit: + err_power_exit: acpi_processor_power_exit(pr); - return result; } -/* - * Do not put anything in here which needs the core to be online. - * For example MSR access or setting up things which check for cpuinfo_x86 - * (cpu_data(cpu)) values, like CPU feature flags, family, model, etc. - * Such things have to be put in and set up above in acpi_processor_start() - */ -static int __cpuinit acpi_processor_add(struct acpi_device *device) +static int __cpuinit acpi_processor_start(struct device *dev) { - struct acpi_processor *pr = NULL; - int result = 0; - struct device *dev; + struct acpi_device *device; - pr = kzalloc(sizeof(struct acpi_processor), GFP_KERNEL); - if (!pr) - return -ENOMEM; + if (acpi_bus_get_device(ACPI_HANDLE(dev), &device)) + return -ENODEV; - if (!zalloc_cpumask_var(&pr->throttling.shared_cpu_map, GFP_KERNEL)) { - result = -ENOMEM; - goto err_free_pr; - } - - pr->handle = device->handle; - strcpy(acpi_device_name(device), ACPI_PROCESSOR_DEVICE_NAME); - strcpy(acpi_device_class(device), ACPI_PROCESSOR_CLASS); - device->driver_data = pr; - - result = acpi_processor_get_info(device); - if (result) { - /* Processor is physically not present */ - return 0; - } - -#ifdef CONFIG_SMP - if (pr->id >= setup_max_cpus && pr->id != 0) - return 0; -#endif - - BUG_ON(pr->id >= nr_cpu_ids); - - /* - * Buggy BIOS check - * ACPI id of processors can be reported wrongly by the BIOS. - * Don't trust it blindly - */ - if (per_cpu(processor_device_array, pr->id) != NULL && - per_cpu(processor_device_array, pr->id) != device) { - dev_warn(&device->dev, - "BIOS reported wrong ACPI id %d for the processor\n", - pr->id); - result = -ENODEV; - goto err_free_cpumask; - } - per_cpu(processor_device_array, pr->id) = device; - - per_cpu(processors, pr->id) = pr; - - dev = get_cpu_device(pr->id); - if (sysfs_create_link(&device->dev.kobj, &dev->kobj, "sysdev")) { - result = -EFAULT; - goto err_clear_processor; - } - - /* - * Do not start hotplugged CPUs now, but when they - * are onlined the first time - */ - if (pr->flags.need_hotplug_init) - return 0; - - result = acpi_processor_start(pr); - if (result) - goto err_remove_sysfs; - - return 0; - -err_remove_sysfs: - sysfs_remove_link(&device->dev.kobj, "sysdev"); -err_clear_processor: - /* - * processor_device_array is not cleared to allow checks for buggy BIOS - */ - per_cpu(processors, pr->id) = NULL; -err_free_cpumask: - free_cpumask_var(pr->throttling.shared_cpu_map); -err_free_pr: - kfree(pr); - return result; + return __acpi_processor_start(device); } -static int acpi_processor_remove(struct acpi_device *device) +static int acpi_processor_stop(struct device *dev) { - struct acpi_processor *pr = NULL; + struct acpi_device *device; + struct acpi_processor *pr; + if (acpi_bus_get_device(ACPI_HANDLE(dev), &device)) + return 0; - if (!device || !acpi_driver_data(device)) - return -EINVAL; + acpi_remove_notify_handler(device->handle, ACPI_DEVICE_NOTIFY, + acpi_processor_notify); pr = acpi_driver_data(device); - - if (pr->id >= nr_cpu_ids) - goto free; - - if (device->removal_type == ACPI_BUS_REMOVAL_EJECT) { - if (acpi_processor_handle_eject(pr)) - return -EINVAL; - } + if (!pr) + return 0; acpi_processor_power_exit(pr); - sysfs_remove_link(&device->dev.kobj, "sysdev"); - if (pr->cdev) { sysfs_remove_link(&device->dev.kobj, "thermal_cooling"); sysfs_remove_link(&pr->cdev->device.kobj, "device"); thermal_cooling_device_unregister(pr->cdev); pr->cdev = NULL; } - - per_cpu(processors, pr->id) = NULL; - per_cpu(processor_device_array, pr->id) = NULL; - try_offline_node(cpu_to_node(pr->id)); - -free: - free_cpumask_var(pr->throttling.shared_cpu_map); - kfree(pr); - return 0; } -#ifdef CONFIG_ACPI_HOTPLUG_CPU -/**************************************************************************** - * Acpi processor hotplug support * - ****************************************************************************/ - -static int is_processor_present(acpi_handle handle) -{ - acpi_status status; - unsigned long long sta = 0; - - - status = acpi_evaluate_integer(handle, "_STA", NULL, &sta); - - if (ACPI_SUCCESS(status) && (sta & ACPI_STA_DEVICE_PRESENT)) - return 1; - - /* - * _STA is mandatory for a processor that supports hot plug - */ - if (status == AE_NOT_FOUND) - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Processor does not support hot plug\n")); - else - ACPI_EXCEPTION((AE_INFO, status, - "Processor Device is not present")); - return 0; -} - -static void acpi_processor_hotplug_notify(acpi_handle handle, - u32 event, void *data) -{ - struct acpi_device *device = NULL; - struct acpi_eject_event *ej_event = NULL; - u32 ost_code = ACPI_OST_SC_NON_SPECIFIC_FAILURE; /* default */ - acpi_status status; - int result; - - acpi_scan_lock_acquire(); - - switch (event) { - case ACPI_NOTIFY_BUS_CHECK: - case ACPI_NOTIFY_DEVICE_CHECK: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Processor driver received %s event\n", - (event == ACPI_NOTIFY_BUS_CHECK) ? - "ACPI_NOTIFY_BUS_CHECK" : "ACPI_NOTIFY_DEVICE_CHECK")); - - if (!is_processor_present(handle)) - break; - - if (!acpi_bus_get_device(handle, &device)) - break; - - result = acpi_bus_scan(handle); - if (result) { - acpi_handle_err(handle, "Unable to add the device\n"); - break; - } - result = acpi_bus_get_device(handle, &device); - if (result) { - acpi_handle_err(handle, "Missing device object\n"); - break; - } - ost_code = ACPI_OST_SC_SUCCESS; - break; - - case ACPI_NOTIFY_EJECT_REQUEST: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "received ACPI_NOTIFY_EJECT_REQUEST\n")); - - if (acpi_bus_get_device(handle, &device)) { - acpi_handle_err(handle, - "Device don't exist, dropping EJECT\n"); - break; - } - if (!acpi_driver_data(device)) { - acpi_handle_err(handle, - "Driver data is NULL, dropping EJECT\n"); - break; - } - - ej_event = kmalloc(sizeof(*ej_event), GFP_KERNEL); - if (!ej_event) { - acpi_handle_err(handle, "No memory, dropping EJECT\n"); - break; - } - - get_device(&device->dev); - ej_event->device = device; - ej_event->event = ACPI_NOTIFY_EJECT_REQUEST; - /* The eject is carried out asynchronously. */ - status = acpi_os_hotplug_execute(acpi_bus_hot_remove_device, - ej_event); - if (ACPI_FAILURE(status)) { - put_device(&device->dev); - kfree(ej_event); - break; - } - goto out; - - default: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Unsupported event [0x%x]\n", event)); - - /* non-hotplug event; possibly handled by other handler */ - goto out; - } - - /* Inform firmware that the hotplug operation has completed */ - (void) acpi_evaluate_hotplug_ost(handle, event, ost_code, NULL); - - out: - acpi_scan_lock_release(); -} - -static acpi_status is_processor_device(acpi_handle handle) -{ - struct acpi_device_info *info; - char *hid; - acpi_status status; - - status = acpi_get_object_info(handle, &info); - if (ACPI_FAILURE(status)) - return status; - - if (info->type == ACPI_TYPE_PROCESSOR) { - kfree(info); - return AE_OK; /* found a processor object */ - } - - if (!(info->valid & ACPI_VALID_HID)) { - kfree(info); - return AE_ERROR; - } - - hid = info->hardware_id.string; - if ((hid == NULL) || strcmp(hid, ACPI_PROCESSOR_DEVICE_HID)) { - kfree(info); - return AE_ERROR; - } - - kfree(info); - return AE_OK; /* found a processor device object */ -} - -static acpi_status -processor_walk_namespace_cb(acpi_handle handle, - u32 lvl, void *context, void **rv) -{ - acpi_status status; - int *action = context; - - status = is_processor_device(handle); - if (ACPI_FAILURE(status)) - return AE_OK; /* not a processor; continue to walk */ - - switch (*action) { - case INSTALL_NOTIFY_HANDLER: - acpi_install_notify_handler(handle, - ACPI_SYSTEM_NOTIFY, - acpi_processor_hotplug_notify, - NULL); - break; - case UNINSTALL_NOTIFY_HANDLER: - acpi_remove_notify_handler(handle, - ACPI_SYSTEM_NOTIFY, - acpi_processor_hotplug_notify); - break; - default: - break; - } - - /* found a processor; skip walking underneath */ - return AE_CTRL_DEPTH; -} - -static acpi_status acpi_processor_hotadd_init(struct acpi_processor *pr) -{ - acpi_handle handle = pr->handle; - - if (!is_processor_present(handle)) { - return AE_ERROR; - } - - if (acpi_map_lsapic(handle, &pr->id)) - return AE_ERROR; - - if (arch_register_cpu(pr->id)) { - acpi_unmap_lsapic(pr->id); - return AE_ERROR; - } - - /* CPU got hot-plugged, but cpu_data is not initialized yet - * Set flag to delay cpu_idle/throttling initialization - * in: - * acpi_processor_add() - * acpi_processor_get_info() - * and do it when the CPU gets online the first time - * TBD: Cleanup above functions and try to do this more elegant. - */ - pr_info("CPU %d got hotplugged\n", pr->id); - pr->flags.need_hotplug_init = 1; - - return AE_OK; -} - -static int acpi_processor_handle_eject(struct acpi_processor *pr) -{ - if (cpu_online(pr->id)) - cpu_down(pr->id); - - get_online_cpus(); - /* - * The cpu might become online again at this point. So we check whether - * the cpu has been onlined or not. If the cpu became online, it means - * that someone wants to use the cpu. So acpi_processor_handle_eject() - * returns -EAGAIN. - */ - if (unlikely(cpu_online(pr->id))) { - put_online_cpus(); - pr_warn("Failed to remove CPU %d, because other task " - "brought the CPU back online\n", pr->id); - return -EAGAIN; - } - arch_unregister_cpu(pr->id); - acpi_unmap_lsapic(pr->id); - put_online_cpus(); - return (0); -} -#else -static acpi_status acpi_processor_hotadd_init(struct acpi_processor *pr) -{ - return AE_ERROR; -} -static int acpi_processor_handle_eject(struct acpi_processor *pr) -{ - return (-EINVAL); -} -#endif - -static -void acpi_processor_install_hotplug_notify(void) -{ -#ifdef CONFIG_ACPI_HOTPLUG_CPU - int action = INSTALL_NOTIFY_HANDLER; - acpi_walk_namespace(ACPI_TYPE_ANY, - ACPI_ROOT_OBJECT, - ACPI_UINT32_MAX, - processor_walk_namespace_cb, NULL, &action, NULL); -#endif - register_hotcpu_notifier(&acpi_cpu_notifier); -} - -static -void acpi_processor_uninstall_hotplug_notify(void) -{ -#ifdef CONFIG_ACPI_HOTPLUG_CPU - int action = UNINSTALL_NOTIFY_HANDLER; - acpi_walk_namespace(ACPI_TYPE_ANY, - ACPI_ROOT_OBJECT, - ACPI_UINT32_MAX, - processor_walk_namespace_cb, NULL, &action, NULL); -#endif - unregister_hotcpu_notifier(&acpi_cpu_notifier); -} - /* * We keep the driver loaded even when ACPI is not running. * This is needed for the powernow-k8 driver, that works even without * ACPI, but needs symbols from this driver */ -static int __init acpi_processor_init(void) +static int __init acpi_processor_driver_init(void) { int result = 0; if (acpi_disabled) return 0; - result = acpi_bus_register_driver(&acpi_processor_driver); + result = driver_register(&acpi_processor_driver); if (result < 0) return result; acpi_processor_syscore_init(); - - acpi_processor_install_hotplug_notify(); - + register_hotcpu_notifier(&acpi_cpu_notifier); acpi_thermal_cpufreq_init(); - acpi_processor_ppc_init(); - acpi_processor_throttling_init(); - return 0; } -static void __exit acpi_processor_exit(void) +static void __exit acpi_processor_driver_exit(void) { if (acpi_disabled) return; acpi_processor_ppc_exit(); - acpi_thermal_cpufreq_exit(); - - acpi_processor_uninstall_hotplug_notify(); - + unregister_hotcpu_notifier(&acpi_cpu_notifier); acpi_processor_syscore_exit(); - - acpi_bus_unregister_driver(&acpi_processor_driver); - - return; + driver_unregister(&acpi_processor_driver); } -module_init(acpi_processor_init); -module_exit(acpi_processor_exit); +module_init(acpi_processor_driver_init); +module_exit(acpi_processor_driver_exit); MODULE_ALIAS("processor"); diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 27da63061e11..db118b1ad3e8 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -27,6 +27,12 @@ extern struct acpi_device *acpi_root; #define ACPI_IS_ROOT_DEVICE(device) (!(device)->parent) +/* + * If set, devices will be hot-removed even if they cannot be put offline + * gracefully (from the kernel's standpoint). + */ +bool acpi_force_hot_remove; + static const char *dummy_hid = "device"; static LIST_HEAD(acpi_device_list); @@ -120,12 +126,78 @@ acpi_device_modalias_show(struct device *dev, struct device_attribute *attr, cha } static DEVICE_ATTR(modalias, 0444, acpi_device_modalias_show, NULL); +static acpi_status acpi_bus_offline_companions(acpi_handle handle, u32 lvl, + void *data, void **ret_p) +{ + struct acpi_device *device = NULL; + struct acpi_device_physical_node *pn; + bool second_pass = (bool)data; + acpi_status status = AE_OK; + + if (acpi_bus_get_device(handle, &device)) + return AE_OK; + + mutex_lock(&device->physical_node_lock); + + list_for_each_entry(pn, &device->physical_node_list, node) { + int ret; + + if (second_pass) { + /* Skip devices offlined by the first pass. */ + if (pn->put_online) + continue; + } else { + pn->put_online = false; + } + ret = device_offline(pn->dev); + if (acpi_force_hot_remove) + continue; + + if (ret >= 0) { + pn->put_online = !ret; + } else { + *ret_p = pn->dev; + if (second_pass) { + status = AE_ERROR; + break; + } + } + } + + mutex_unlock(&device->physical_node_lock); + + return status; +} + +static acpi_status acpi_bus_online_companions(acpi_handle handle, u32 lvl, + void *data, void **ret_p) +{ + struct acpi_device *device = NULL; + struct acpi_device_physical_node *pn; + + if (acpi_bus_get_device(handle, &device)) + return AE_OK; + + mutex_lock(&device->physical_node_lock); + + list_for_each_entry(pn, &device->physical_node_list, node) + if (pn->put_online) { + device_online(pn->dev); + pn->put_online = false; + } + + mutex_unlock(&device->physical_node_lock); + + return AE_OK; +} + static int acpi_scan_hot_remove(struct acpi_device *device) { acpi_handle handle = device->handle; acpi_handle not_used; struct acpi_object_list arg_list; union acpi_object arg; + struct device *errdev; acpi_status status; unsigned long long sta; @@ -136,10 +208,53 @@ static int acpi_scan_hot_remove(struct acpi_device *device) return -EINVAL; } + lock_device_hotplug(); + + /* + * Carry out two passes here and ignore errors in the first pass, + * because if the devices in question are memory blocks and + * CONFIG_MEMCG is set, one of the blocks may hold data structures + * that the other blocks depend on, but it is not known in advance which + * block holds them. + * + * If the first pass is successful, the second one isn't needed, though. + */ + errdev = NULL; + acpi_walk_namespace(ACPI_TYPE_ANY, handle, ACPI_UINT32_MAX, + NULL, acpi_bus_offline_companions, + (void *)false, (void **)&errdev); + acpi_bus_offline_companions(handle, 0, (void *)false, (void **)&errdev); + if (errdev) { + errdev = NULL; + acpi_walk_namespace(ACPI_TYPE_ANY, handle, ACPI_UINT32_MAX, + NULL, acpi_bus_offline_companions, + (void *)true , (void **)&errdev); + if (!errdev || acpi_force_hot_remove) + acpi_bus_offline_companions(handle, 0, (void *)true, + (void **)&errdev); + + if (errdev && !acpi_force_hot_remove) { + dev_warn(errdev, "Offline failed.\n"); + acpi_bus_online_companions(handle, 0, NULL, NULL); + acpi_walk_namespace(ACPI_TYPE_ANY, handle, + ACPI_UINT32_MAX, + acpi_bus_online_companions, NULL, + NULL, NULL); + + unlock_device_hotplug(); + + put_device(&device->dev); + return -EBUSY; + } + } + ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Hot-removing device %s...\n", dev_name(&device->dev))); acpi_bus_trim(device); + + unlock_device_hotplug(); + /* Device node has been unregistered. */ put_device(&device->dev); device = NULL; @@ -236,6 +351,7 @@ static void acpi_scan_bus_device_check(acpi_handle handle, u32 ost_source) int error; mutex_lock(&acpi_scan_lock); + lock_device_hotplug(); acpi_bus_get_device(handle, &device); if (device) { @@ -259,6 +375,7 @@ static void acpi_scan_bus_device_check(acpi_handle handle, u32 ost_source) kobject_uevent(&device->dev.kobj, KOBJ_ONLINE); out: + unlock_device_hotplug(); acpi_evaluate_hotplug_ost(handle, ost_source, ost_code, NULL); mutex_unlock(&acpi_scan_lock); } @@ -952,7 +1069,6 @@ int acpi_device_add(struct acpi_device *device, printk(KERN_ERR PREFIX "Error creating sysfs interface for device %s\n", dev_name(&device->dev)); - device->removal_type = ACPI_BUS_REMOVAL_NORMAL; return 0; err: @@ -1939,7 +2055,6 @@ static acpi_status acpi_bus_device_detach(acpi_handle handle, u32 lvl_not_used, if (!acpi_bus_get_device(handle, &device)) { struct acpi_scan_handler *dev_handler = device->handler; - device->removal_type = ACPI_BUS_REMOVAL_EJECT; if (dev_handler) { if (dev_handler->detach) dev_handler->detach(device); @@ -2038,6 +2153,7 @@ int __init acpi_scan_init(void) acpi_pci_root_init(); acpi_pci_link_init(); + acpi_processor_init(); acpi_platform_init(); acpi_lpss_init(); acpi_container_init(); diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c index fcae5fa2e1b3..5c5d1624fa2c 100644 --- a/drivers/acpi/sysfs.c +++ b/drivers/acpi/sysfs.c @@ -780,6 +780,33 @@ void acpi_sysfs_add_hotplug_profile(struct acpi_hotplug_profile *hotplug, pr_err(PREFIX "Unable to add hotplug profile '%s'\n", name); } +static ssize_t force_remove_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", !!acpi_force_hot_remove); +} + +static ssize_t force_remove_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t size) +{ + bool val; + int ret; + + ret = strtobool(buf, &val); + if (ret < 0) + return ret; + + lock_device_hotplug(); + acpi_force_hot_remove = val; + unlock_device_hotplug(); + return size; +} + +static const struct kobj_attribute force_remove_attr = + __ATTR(force_remove, S_IRUGO | S_IWUSR, force_remove_show, + force_remove_store); + int __init acpi_sysfs_init(void) { int result; @@ -789,6 +816,10 @@ int __init acpi_sysfs_init(void) return result; hotplug_kobj = kobject_create_and_add("hotplug", acpi_kobj); + result = sysfs_create_file(hotplug_kobj, &force_remove_attr.attr); + if (result) + return result; + result = sysfs_create_file(acpi_kobj, &pm_profile_attr.attr); return result; } diff --git a/drivers/base/core.c b/drivers/base/core.c index 2499cefdcdf2..2166f34b7d84 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -403,6 +403,36 @@ static ssize_t store_uevent(struct device *dev, struct device_attribute *attr, static struct device_attribute uevent_attr = __ATTR(uevent, S_IRUGO | S_IWUSR, show_uevent, store_uevent); +static ssize_t show_online(struct device *dev, struct device_attribute *attr, + char *buf) +{ + bool val; + + lock_device_hotplug(); + val = !dev->offline; + unlock_device_hotplug(); + return sprintf(buf, "%u\n", val); +} + +static ssize_t store_online(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + bool val; + int ret; + + ret = strtobool(buf, &val); + if (ret < 0) + return ret; + + lock_device_hotplug(); + ret = val ? device_online(dev) : device_offline(dev); + unlock_device_hotplug(); + return ret < 0 ? ret : count; +} + +static struct device_attribute online_attr = + __ATTR(online, S_IRUGO | S_IWUSR, show_online, store_online); + static int device_add_attributes(struct device *dev, struct device_attribute *attrs) { @@ -516,6 +546,12 @@ static int device_add_attrs(struct device *dev) if (error) goto err_remove_type_groups; + if (device_supports_offline(dev) && !dev->offline_disabled) { + error = device_create_file(dev, &online_attr); + if (error) + goto err_remove_type_groups; + } + return 0; err_remove_type_groups: @@ -536,6 +572,7 @@ static void device_remove_attrs(struct device *dev) struct class *class = dev->class; const struct device_type *type = dev->type; + device_remove_file(dev, &online_attr); device_remove_groups(dev, dev->groups); if (type) @@ -1433,6 +1470,99 @@ EXPORT_SYMBOL_GPL(put_device); EXPORT_SYMBOL_GPL(device_create_file); EXPORT_SYMBOL_GPL(device_remove_file); +static DEFINE_MUTEX(device_hotplug_lock); + +void lock_device_hotplug(void) +{ + mutex_lock(&device_hotplug_lock); +} + +void unlock_device_hotplug(void) +{ + mutex_unlock(&device_hotplug_lock); +} + +static int device_check_offline(struct device *dev, void *not_used) +{ + int ret; + + ret = device_for_each_child(dev, NULL, device_check_offline); + if (ret) + return ret; + + return device_supports_offline(dev) && !dev->offline ? -EBUSY : 0; +} + +/** + * device_offline - Prepare the device for hot-removal. + * @dev: Device to be put offline. + * + * Execute the device bus type's .offline() callback, if present, to prepare + * the device for a subsequent hot-removal. If that succeeds, the device must + * not be used until either it is removed or its bus type's .online() callback + * is executed. + * + * Call under device_hotplug_lock. + */ +int device_offline(struct device *dev) +{ + int ret; + + if (dev->offline_disabled) + return -EPERM; + + ret = device_for_each_child(dev, NULL, device_check_offline); + if (ret) + return ret; + + device_lock(dev); + if (device_supports_offline(dev)) { + if (dev->offline) { + ret = 1; + } else { + ret = dev->bus->offline(dev); + if (!ret) { + kobject_uevent(&dev->kobj, KOBJ_OFFLINE); + dev->offline = true; + } + } + } + device_unlock(dev); + + return ret; +} + +/** + * device_online - Put the device back online after successful device_offline(). + * @dev: Device to be put back online. + * + * If device_offline() has been successfully executed for @dev, but the device + * has not been removed subsequently, execute its bus type's .online() callback + * to indicate that the device can be used again. + * + * Call under device_hotplug_lock. + */ +int device_online(struct device *dev) +{ + int ret = 0; + + device_lock(dev); + if (device_supports_offline(dev)) { + if (dev->offline) { + ret = dev->bus->online(dev); + if (!ret) { + kobject_uevent(&dev->kobj, KOBJ_ONLINE); + dev->offline = false; + } + } else { + ret = 1; + } + } + device_unlock(dev); + + return ret; +} + struct root_device { struct device dev; struct module *owner; diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 3d48fc887ef4..1d110dc6f0c1 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -13,17 +13,21 @@ #include #include #include +#include #include "base.h" -struct bus_type cpu_subsys = { - .name = "cpu", - .dev_name = "cpu", -}; -EXPORT_SYMBOL_GPL(cpu_subsys); - static DEFINE_PER_CPU(struct device *, cpu_sys_devices); +static int cpu_subsys_match(struct device *dev, struct device_driver *drv) +{ + /* ACPI style match is the only one that may succeed. */ + if (acpi_driver_match_device(dev, drv)) + return 1; + + return 0; +} + #ifdef CONFIG_HOTPLUG_CPU static void change_cpu_under_node(struct cpu *cpu, unsigned int from_nid, unsigned int to_nid) @@ -34,69 +38,45 @@ static void change_cpu_under_node(struct cpu *cpu, cpu->node_id = to_nid; } -static ssize_t show_online(struct device *dev, - struct device_attribute *attr, - char *buf) +static int __ref cpu_subsys_online(struct device *dev) { struct cpu *cpu = container_of(dev, struct cpu, dev); - - return sprintf(buf, "%u\n", !!cpu_online(cpu->dev.id)); -} - -static ssize_t __ref store_online(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct cpu *cpu = container_of(dev, struct cpu, dev); - int cpuid = cpu->dev.id; + int cpuid = dev->id; int from_nid, to_nid; - ssize_t ret; + int ret; cpu_hotplug_driver_lock(); - switch (buf[0]) { - case '0': - ret = cpu_down(cpuid); - if (!ret) - kobject_uevent(&dev->kobj, KOBJ_OFFLINE); - break; - case '1': - from_nid = cpu_to_node(cpuid); - ret = cpu_up(cpuid); - /* - * When hot adding memory to memoryless node and enabling a cpu - * on the node, node number of the cpu may internally change. - */ - to_nid = cpu_to_node(cpuid); - if (from_nid != to_nid) - change_cpu_under_node(cpu, from_nid, to_nid); + from_nid = cpu_to_node(cpuid); + ret = cpu_up(cpuid); + /* + * When hot adding memory to memoryless node and enabling a cpu + * on the node, node number of the cpu may internally change. + */ + to_nid = cpu_to_node(cpuid); + if (from_nid != to_nid) + change_cpu_under_node(cpu, from_nid, to_nid); - if (!ret) - kobject_uevent(&dev->kobj, KOBJ_ONLINE); - break; - default: - ret = -EINVAL; - } cpu_hotplug_driver_unlock(); - - if (ret >= 0) - ret = count; return ret; } -static DEVICE_ATTR(online, 0644, show_online, store_online); -static void __cpuinit register_cpu_control(struct cpu *cpu) +static int cpu_subsys_offline(struct device *dev) { - device_create_file(&cpu->dev, &dev_attr_online); + int ret; + + cpu_hotplug_driver_lock(); + ret = cpu_down(dev->id); + cpu_hotplug_driver_unlock(); + return ret; } + void unregister_cpu(struct cpu *cpu) { int logical_cpu = cpu->dev.id; unregister_cpu_under_node(logical_cpu, cpu_to_node(logical_cpu)); - device_remove_file(&cpu->dev, &dev_attr_online); - device_unregister(&cpu->dev); per_cpu(cpu_sys_devices, logical_cpu) = NULL; return; @@ -123,12 +103,19 @@ static DEVICE_ATTR(probe, S_IWUSR, NULL, cpu_probe_store); static DEVICE_ATTR(release, S_IWUSR, NULL, cpu_release_store); #endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ -#else /* ... !CONFIG_HOTPLUG_CPU */ -static inline void register_cpu_control(struct cpu *cpu) -{ -} #endif /* CONFIG_HOTPLUG_CPU */ +struct bus_type cpu_subsys = { + .name = "cpu", + .dev_name = "cpu", + .match = cpu_subsys_match, +#ifdef CONFIG_HOTPLUG_CPU + .online = cpu_subsys_online, + .offline = cpu_subsys_offline, +#endif +}; +EXPORT_SYMBOL_GPL(cpu_subsys); + #ifdef CONFIG_KEXEC #include @@ -277,12 +264,12 @@ int __cpuinit register_cpu(struct cpu *cpu, int num) cpu->dev.id = num; cpu->dev.bus = &cpu_subsys; cpu->dev.release = cpu_device_release; + cpu->dev.offline_disabled = !cpu->hotpluggable; + cpu->dev.offline = !cpu_online(num); #ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE cpu->dev.bus->uevent = arch_cpu_uevent; #endif error = device_register(&cpu->dev); - if (!error && cpu->hotpluggable) - register_cpu_control(cpu); if (!error) per_cpu(cpu_sys_devices, num) = &cpu->dev; if (!error) diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 14f8a6954da0..4ebf97f99fae 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -37,9 +37,14 @@ static inline int base_memory_block_id(int section_nr) return section_nr / sections_per_block; } +static int memory_subsys_online(struct device *dev); +static int memory_subsys_offline(struct device *dev); + static struct bus_type memory_subsys = { .name = MEMORY_CLASS_NAME, .dev_name = MEMORY_CLASS_NAME, + .online = memory_subsys_online, + .offline = memory_subsys_offline, }; static BLOCKING_NOTIFIER_HEAD(memory_chain); @@ -88,6 +93,7 @@ int register_memory(struct memory_block *memory) memory->dev.bus = &memory_subsys; memory->dev.id = memory->start_section_nr / sections_per_block; memory->dev.release = memory_block_release; + memory->dev.offline = memory->state == MEM_OFFLINE; error = device_register(&memory->dev); return error; @@ -278,33 +284,64 @@ static int __memory_block_change_state(struct memory_block *mem, { int ret = 0; - if (mem->state != from_state_req) { - ret = -EINVAL; - goto out; - } + if (mem->state != from_state_req) + return -EINVAL; if (to_state == MEM_OFFLINE) mem->state = MEM_GOING_OFFLINE; ret = memory_block_action(mem->start_section_nr, to_state, online_type); + mem->state = ret ? from_state_req : to_state; + return ret; +} - if (ret) { - mem->state = from_state_req; - goto out; - } +static int memory_subsys_online(struct device *dev) +{ + struct memory_block *mem = container_of(dev, struct memory_block, dev); + int ret; - mem->state = to_state; - switch (mem->state) { - case MEM_OFFLINE: - kobject_uevent(&mem->dev.kobj, KOBJ_OFFLINE); - break; - case MEM_ONLINE: - kobject_uevent(&mem->dev.kobj, KOBJ_ONLINE); - break; - default: - break; + mutex_lock(&mem->state_mutex); + + ret = mem->state == MEM_ONLINE ? 0 : + __memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE, + ONLINE_KEEP); + + mutex_unlock(&mem->state_mutex); + return ret; +} + +static int memory_subsys_offline(struct device *dev) +{ + struct memory_block *mem = container_of(dev, struct memory_block, dev); + int ret; + + mutex_lock(&mem->state_mutex); + + ret = mem->state == MEM_OFFLINE ? 0 : + __memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE, -1); + + mutex_unlock(&mem->state_mutex); + return ret; +} + +static int __memory_block_change_state_uevent(struct memory_block *mem, + unsigned long to_state, unsigned long from_state_req, + int online_type) +{ + int ret = __memory_block_change_state(mem, to_state, from_state_req, + online_type); + if (!ret) { + switch (mem->state) { + case MEM_OFFLINE: + kobject_uevent(&mem->dev.kobj, KOBJ_OFFLINE); + break; + case MEM_ONLINE: + kobject_uevent(&mem->dev.kobj, KOBJ_ONLINE); + break; + default: + break; + } } -out: return ret; } @@ -315,8 +352,8 @@ static int memory_block_change_state(struct memory_block *mem, int ret; mutex_lock(&mem->state_mutex); - ret = __memory_block_change_state(mem, to_state, from_state_req, - online_type); + ret = __memory_block_change_state_uevent(mem, to_state, from_state_req, + online_type); mutex_unlock(&mem->state_mutex); return ret; @@ -326,22 +363,34 @@ store_mem_state(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct memory_block *mem; + bool offline; int ret = -EINVAL; mem = container_of(dev, struct memory_block, dev); - if (!strncmp(buf, "online_kernel", min_t(int, count, 13))) + lock_device_hotplug(); + + if (!strncmp(buf, "online_kernel", min_t(int, count, 13))) { + offline = false; ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE, ONLINE_KERNEL); - else if (!strncmp(buf, "online_movable", min_t(int, count, 14))) + } else if (!strncmp(buf, "online_movable", min_t(int, count, 14))) { + offline = false; ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE, ONLINE_MOVABLE); - else if (!strncmp(buf, "online", min_t(int, count, 6))) + } else if (!strncmp(buf, "online", min_t(int, count, 6))) { + offline = false; ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE, ONLINE_KEEP); - else if(!strncmp(buf, "offline", min_t(int, count, 7))) + } else if(!strncmp(buf, "offline", min_t(int, count, 7))) { + offline = true; ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE, -1); + } + if (!ret) + dev->offline = offline; + + unlock_device_hotplug(); if (ret) return ret; @@ -679,21 +728,6 @@ int unregister_memory_section(struct mem_section *section) } #endif /* CONFIG_MEMORY_HOTREMOVE */ -/* - * offline one memory block. If the memory block has been offlined, do nothing. - */ -int offline_memory_block(struct memory_block *mem) -{ - int ret = 0; - - mutex_lock(&mem->state_mutex); - if (mem->state != MEM_OFFLINE) - ret = __memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE, -1); - mutex_unlock(&mem->state_mutex); - - return ret; -} - /* return true if the memory block is offlined, otherwise, return false */ bool is_memblock_offlined(struct memory_block *mem) { diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index edc089e9d0c4..b8efacf01d69 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -1034,4 +1034,11 @@ static const struct x86_cpu_id acpi_cpufreq_ids[] = { }; MODULE_DEVICE_TABLE(x86cpu, acpi_cpufreq_ids); +static const struct acpi_device_id processor_device_ids[] = { + {ACPI_PROCESSOR_OBJECT_HID, }, + {ACPI_PROCESSOR_DEVICE_HID, }, + {}, +}; +MODULE_DEVICE_TABLE(acpi, processor_device_ids); + MODULE_ALIAS("acpi"); diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index c13c919ab99e..cf0817a555e4 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -63,13 +63,6 @@ acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld #define ACPI_BUS_FILE_ROOT "acpi" extern struct proc_dir_entry *acpi_root_dir; -enum acpi_bus_removal_type { - ACPI_BUS_REMOVAL_NORMAL = 0, - ACPI_BUS_REMOVAL_EJECT, - ACPI_BUS_REMOVAL_SUPRISE, - ACPI_BUS_REMOVAL_TYPE_COUNT -}; - enum acpi_bus_device_type { ACPI_BUS_TYPE_DEVICE = 0, ACPI_BUS_TYPE_POWER, @@ -286,6 +279,7 @@ struct acpi_device_physical_node { u8 node_id; struct list_head node; struct device *dev; + bool put_online:1; }; /* set maximum of physical nodes to 32 for expansibility */ @@ -310,7 +304,6 @@ struct acpi_device { struct acpi_driver *driver; void *driver_data; struct device dev; - enum acpi_bus_removal_type removal_type; /* indicate for different removal type */ u8 physical_node_count; struct list_head physical_node_list; struct mutex physical_node_lock; diff --git a/include/acpi/processor.h b/include/acpi/processor.h index ea69367fdd3b..66096d06925e 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -6,6 +6,10 @@ #include #include +#define ACPI_PROCESSOR_CLASS "processor" +#define ACPI_PROCESSOR_DEVICE_NAME "Processor" +#define ACPI_PROCESSOR_DEVICE_HID "ACPI0007" + #define ACPI_PROCESSOR_BUSY_METRIC 10 #define ACPI_PROCESSOR_MAX_POWER 8 @@ -207,6 +211,7 @@ struct acpi_processor { struct acpi_processor_throttling throttling; struct acpi_processor_limit limit; struct thermal_cooling_device *cdev; + struct device *dev; /* Processor device. */ }; struct acpi_processor_errata { diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 17b5b5967641..353ba256f368 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -352,8 +352,7 @@ extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, /* Enable _OST when all relevant hotplug operations are enabled */ #if defined(CONFIG_ACPI_HOTPLUG_CPU) && \ - (defined(CONFIG_ACPI_HOTPLUG_MEMORY) || \ - defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE)) && \ + defined(CONFIG_ACPI_HOTPLUG_MEMORY) && \ defined(CONFIG_ACPI_CONTAINER) #define ACPI_HOTPLUG_OST #endif diff --git a/include/linux/device.h b/include/linux/device.h index c0a126125325..eeb33315514c 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -71,6 +71,10 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * the specific driver's probe to initial the matched device. * @remove: Called when a device removed from this bus. * @shutdown: Called at shut-down time to quiesce the device. + * + * @online: Called to put the device back online (after offlining it). + * @offline: Called to put the device offline for hot-removal. May fail. + * * @suspend: Called when a device on this bus wants to go to sleep mode. * @resume: Called to bring a device on this bus out of sleep mode. * @pm: Power management operations of this bus, callback the specific @@ -104,6 +108,9 @@ struct bus_type { int (*remove)(struct device *dev); void (*shutdown)(struct device *dev); + int (*online)(struct device *dev); + int (*offline)(struct device *dev); + int (*suspend)(struct device *dev, pm_message_t state); int (*resume)(struct device *dev); @@ -648,6 +655,8 @@ struct acpi_dev_node { * @release: Callback to free the device after all references have * gone away. This should be set by the allocator of the * device (i.e. the bus driver that discovered the device). + * @offline_disabled: If set, the device is permanently online. + * @offline: Set after successful invocation of bus type's .offline(). * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -720,6 +729,9 @@ struct device { void (*release)(struct device *dev); struct iommu_group *iommu_group; + + bool offline_disabled:1; + bool offline:1; }; static inline struct device *kobj_to_dev(struct kobject *kobj) @@ -856,6 +868,15 @@ extern const char *device_get_devnode(struct device *dev, extern void *dev_get_drvdata(const struct device *dev); extern int dev_set_drvdata(struct device *dev, void *data); +static inline bool device_supports_offline(struct device *dev) +{ + return dev->bus && dev->bus->offline && dev->bus->online; +} + +extern void lock_device_hotplug(void); +extern void unlock_device_hotplug(void); +extern int device_offline(struct device *dev); +extern int device_online(struct device *dev); /* * Root device objects for grouping under /sys/devices */ diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 3e622c610925..dd38e62b84d2 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -234,6 +234,8 @@ static inline void unlock_memory_hotplug(void) {} extern int is_mem_section_removable(unsigned long pfn, unsigned long nr_pages); extern void try_offline_node(int nid); +extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); +extern void remove_memory(int nid, u64 start, u64 size); #else static inline int is_mem_section_removable(unsigned long pfn, @@ -243,15 +245,23 @@ static inline int is_mem_section_removable(unsigned long pfn, } static inline void try_offline_node(int nid) {} + +static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages) +{ + return -EINVAL; +} + +static inline void remove_memory(int nid, u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ +extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, + void *arg, int (*func)(struct memory_block *, void *)); extern int mem_online_node(int nid); extern int add_memory(int nid, u64 start, u64 size); extern int arch_add_memory(int nid, u64 start, u64 size); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); -extern int offline_memory_block(struct memory_block *mem); extern bool is_memblock_offlined(struct memory_block *mem); -extern int remove_memory(int nid, u64 start, u64 size); +extern void remove_memory(int nid, u64 start, u64 size); extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, int nr_pages); extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 1ad92b46753e..081b4d654ed6 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1621,6 +1621,7 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages) { return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ); } +#endif /* CONFIG_MEMORY_HOTREMOVE */ /** * walk_memory_range - walks through all mem sections in [start_pfn, end_pfn) @@ -1634,7 +1635,7 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages) * * Returns the return value of func. */ -static int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, +int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)) { struct memory_block *mem = NULL; @@ -1671,24 +1672,7 @@ static int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, return 0; } -/** - * offline_memory_block_cb - callback function for offlining memory block - * @mem: the memory block to be offlined - * @arg: buffer to hold error msg - * - * Always return 0, and put the error msg in arg if any. - */ -static int offline_memory_block_cb(struct memory_block *mem, void *arg) -{ - int *ret = arg; - int error = offline_memory_block(mem); - - if (error != 0 && *ret == 0) - *ret = error; - - return 0; -} - +#ifdef CONFIG_MEMORY_HOTREMOVE static int is_memblock_offlined_cb(struct memory_block *mem, void *arg) { int ret = !is_memblock_offlined(mem); @@ -1814,54 +1798,22 @@ void try_offline_node(int nid) } EXPORT_SYMBOL(try_offline_node); -int __ref remove_memory(int nid, u64 start, u64 size) +void __ref remove_memory(int nid, u64 start, u64 size) { - unsigned long start_pfn, end_pfn; - int ret = 0; - int retry = 1; - - start_pfn = PFN_DOWN(start); - end_pfn = PFN_UP(start + size - 1); - - /* - * When CONFIG_MEMCG is on, one memory block may be used by other - * blocks to store page cgroup when onlining pages. But we don't know - * in what order pages are onlined. So we iterate twice to offline - * memory: - * 1st iterate: offline every non primary memory block. - * 2nd iterate: offline primary (i.e. first added) memory block. - */ -repeat: - walk_memory_range(start_pfn, end_pfn, &ret, - offline_memory_block_cb); - if (ret) { - if (!retry) - return ret; - - retry = 0; - ret = 0; - goto repeat; - } + int ret; lock_memory_hotplug(); /* - * we have offlined all memory blocks like this: - * 1. lock memory hotplug - * 2. offline a memory block - * 3. unlock memory hotplug - * - * repeat step1-3 to offline the memory block. All memory blocks - * must be offlined before removing memory. But we don't hold the - * lock in the whole operation. So we should check whether all - * memory blocks are offlined. + * All memory blocks must be offlined before removing memory. Check + * whether all memory blocks in question are offline and trigger a BUG() + * if this is not the case. */ - - ret = walk_memory_range(start_pfn, end_pfn, NULL, + ret = walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL, is_memblock_offlined_cb); if (ret) { unlock_memory_hotplug(); - return ret; + BUG(); } /* remove memmap entry */ @@ -1872,17 +1824,6 @@ repeat: try_offline_node(nid); unlock_memory_hotplug(); - - return 0; } -#else -int offline_pages(unsigned long start_pfn, unsigned long nr_pages) -{ - return -EINVAL; -} -int remove_memory(int nid, u64 start, u64 size) -{ - return -EINVAL; -} -#endif /* CONFIG_MEMORY_HOTREMOVE */ EXPORT_SYMBOL_GPL(remove_memory); +#endif /* CONFIG_MEMORY_HOTREMOVE */