diff options
Diffstat (limited to 'drivers/base')
| -rw-r--r-- | drivers/base/Makefile | 1 | ||||
| -rw-r--r-- | drivers/base/class.c | 1 | ||||
| -rw-r--r-- | drivers/base/cpu.c | 16 | ||||
| -rw-r--r-- | drivers/base/firmware_class.c | 69 | ||||
| -rw-r--r-- | drivers/base/init.c | 2 | ||||
| -rw-r--r-- | drivers/base/memory.c | 452 | ||||
| -rw-r--r-- | drivers/base/platform.c | 1 | ||||
| -rw-r--r-- | drivers/base/sys.c | 1 |
8 files changed, 513 insertions, 30 deletions
diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 66d9c4643fc..f12898d5307 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -7,6 +7,7 @@ obj-y := core.o sys.o bus.o dd.o \ obj-y += power/ obj-$(CONFIG_FW_LOADER) += firmware_class.o obj-$(CONFIG_NUMA) += node.o +obj-$(CONFIG_MEMORY_HOTPLUG) += memory.o ifeq ($(CONFIG_DEBUG_DRIVER),y) EXTRA_CFLAGS += -DDEBUG diff --git a/drivers/base/class.c b/drivers/base/class.c index c3e569730af..db65fd0babe 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -17,6 +17,7 @@ #include <linux/string.h> #include <linux/kdev_t.h> #include <linux/err.h> +#include <linux/slab.h> #include "base.h" #define to_class_attr(_attr) container_of(_attr, struct class_attribute, attr) diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 081c927b1ed..a95844790f7 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -16,6 +16,8 @@ struct sysdev_class cpu_sysdev_class = { }; EXPORT_SYMBOL(cpu_sysdev_class); +static struct sys_device *cpu_sys_devices[NR_CPUS]; + #ifdef CONFIG_HOTPLUG_CPU int __attribute__((weak)) smp_prepare_cpu (int cpu) { @@ -64,6 +66,7 @@ static void __devinit register_cpu_control(struct cpu *cpu) } void unregister_cpu(struct cpu *cpu, struct node *root) { + int logical_cpu = cpu->sysdev.id; if (root) sysfs_remove_link(&root->sysdev.kobj, @@ -71,7 +74,7 @@ void unregister_cpu(struct cpu *cpu, struct node *root) sysdev_remove_file(&cpu->sysdev, &attr_online); sysdev_unregister(&cpu->sysdev); - + cpu_sys_devices[logical_cpu] = NULL; return; } #else /* ... !CONFIG_HOTPLUG_CPU */ @@ -103,10 +106,19 @@ int __devinit register_cpu(struct cpu *cpu, int num, struct node *root) kobject_name(&cpu->sysdev.kobj)); if (!error && !cpu->no_control) register_cpu_control(cpu); + if (!error) + cpu_sys_devices[num] = &cpu->sysdev; return error; } - +struct sys_device *get_cpu_sysdev(int cpu) +{ + if (cpu < NR_CPUS) + return cpu_sys_devices[cpu]; + else + return NULL; +} +EXPORT_SYMBOL_GPL(get_cpu_sysdev); int __init cpu_dev_init(void) { diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index 4acb2c5733c..98f6c02d679 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -62,14 +62,16 @@ firmware_timeout_show(struct class *class, char *buf) } /** - * firmware_timeout_store: - * Description: + * firmware_timeout_store - set number of seconds to wait for firmware + * @class: device class pointer + * @buf: buffer to scan for timeout value + * @count: number of bytes in @buf + * * Sets the number of seconds to wait for the firmware. Once - * this expires an error will be return to the driver and no + * this expires an error will be returned to the driver and no * firmware will be provided. * - * Note: zero means 'wait for ever' - * + * Note: zero means 'wait forever'. **/ static ssize_t firmware_timeout_store(struct class *class, const char *buf, size_t count) @@ -123,12 +125,15 @@ firmware_loading_show(struct class_device *class_dev, char *buf) } /** - * firmware_loading_store: - loading control file - * Description: + * firmware_loading_store - set value in the 'loading' control file + * @class_dev: class_device pointer + * @buf: buffer to scan for loading control value + * @count: number of bytes in @buf + * * The relevant values are: * * 1: Start a load, discarding any previous partial load. - * 0: Conclude the load and handle the data to the driver code. + * 0: Conclude the load and hand the data to the driver code. * -1: Conclude the load with an error and discard any written data. **/ static ssize_t @@ -201,6 +206,7 @@ out: up(&fw_lock); return ret_count; } + static int fw_realloc_buffer(struct firmware_priv *fw_priv, int min_size) { @@ -227,11 +233,13 @@ fw_realloc_buffer(struct firmware_priv *fw_priv, int min_size) } /** - * firmware_data_write: + * firmware_data_write - write method for firmware + * @kobj: kobject for the class_device + * @buffer: buffer being written + * @offset: buffer offset for write in total data store area + * @count: buffer size * - * Description: - * - * Data written to the 'data' attribute will be later handled to + * Data written to the 'data' attribute will be later handed to * the driver as a firmware image. **/ static ssize_t @@ -264,6 +272,7 @@ out: up(&fw_lock); return retval; } + static struct bin_attribute firmware_attr_data_tmpl = { .attr = {.name = "data", .mode = 0644, .owner = THIS_MODULE}, .size = 0, @@ -448,13 +457,16 @@ out: /** * request_firmware: - request firmware to hotplug and wait for it - * Description: - * @firmware will be used to return a firmware image by the name + * @firmware_p: pointer to firmware image + * @name: name of firmware file + * @device: device for which firmware is being loaded + * + * @firmware_p will be used to return a firmware image by the name * of @name for device @device. * * Should be called from user context where sleeping is allowed. * - * @name will be use as $FIRMWARE in the hotplug environment and + * @name will be used as $FIRMWARE in the hotplug environment and * should be distinctive enough not to be confused with any other * firmware image for this or any other device. **/ @@ -468,6 +480,7 @@ request_firmware(const struct firmware **firmware_p, const char *name, /** * release_firmware: - release the resource associated with a firmware image + * @fw: firmware resource to release **/ void release_firmware(const struct firmware *fw) @@ -480,8 +493,10 @@ release_firmware(const struct firmware *fw) /** * register_firmware: - provide a firmware image for later usage + * @name: name of firmware image file + * @data: buffer pointer for the firmware image + * @size: size of the data buffer area * - * Description: * Make sure that @data will be available by requesting firmware @name. * * Note: This will not be possible until some kind of persistence @@ -526,21 +541,19 @@ request_firmware_work_func(void *arg) } /** - * request_firmware_nowait: + * request_firmware_nowait: asynchronous version of request_firmware + * @module: module requesting the firmware + * @hotplug: invokes hotplug event to copy the firmware image if this flag + * is non-zero else the firmware copy must be done manually. + * @name: name of firmware file + * @device: device for which firmware is being loaded + * @context: will be passed over to @cont, and + * @fw may be %NULL if firmware request fails. + * @cont: function will be called asynchronously when the firmware + * request is over. * - * Description: * Asynchronous variant of request_firmware() for contexts where * it is not possible to sleep. - * - * @hotplug invokes hotplug event to copy the firmware image if this flag - * is non-zero else the firmware copy must be done manually. - * - * @cont will be called asynchronously when the firmware request is over. - * - * @context will be passed over to @cont. - * - * @fw may be %NULL if firmware request fails. - * **/ int request_firmware_nowait( diff --git a/drivers/base/init.c b/drivers/base/init.c index 84e604e25c4..c648914b9cd 100644 --- a/drivers/base/init.c +++ b/drivers/base/init.c @@ -9,6 +9,7 @@ #include <linux/device.h> #include <linux/init.h> +#include <linux/memory.h> #include "base.h" @@ -33,5 +34,6 @@ void __init driver_init(void) platform_bus_init(); system_bus_init(); cpu_dev_init(); + memory_dev_init(); attribute_container_init(); } diff --git a/drivers/base/memory.c b/drivers/base/memory.c new file mode 100644 index 00000000000..b7ddd651d66 --- /dev/null +++ b/drivers/base/memory.c @@ -0,0 +1,452 @@ +/* + * drivers/base/memory.c - basic Memory class support + * + * Written by Matt Tolentino <matthew.e.tolentino@intel.com> + * Dave Hansen <haveblue@us.ibm.com> + * + * This file provides the necessary infrastructure to represent + * a SPARSEMEM-memory-model system's physical memory in /sysfs. + * All arch-independent code that assumes MEMORY_HOTPLUG requires + * SPARSEMEM should be contained here, or in mm/memory_hotplug.c. + */ + +#include <linux/sysdev.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/sched.h> /* capable() */ +#include <linux/topology.h> +#include <linux/device.h> +#include <linux/memory.h> +#include <linux/kobject.h> +#include <linux/memory_hotplug.h> +#include <linux/mm.h> +#include <asm/atomic.h> +#include <asm/uaccess.h> + +#define MEMORY_CLASS_NAME "memory" + +static struct sysdev_class memory_sysdev_class = { + set_kset_name(MEMORY_CLASS_NAME), +}; +EXPORT_SYMBOL(memory_sysdev_class); + +static char *memory_hotplug_name(struct kset *kset, struct kobject *kobj) +{ + return MEMORY_CLASS_NAME; +} + +static int memory_hotplug(struct kset *kset, struct kobject *kobj, char **envp, + int num_envp, char *buffer, int buffer_size) +{ + int retval = 0; + + return retval; +} + +static struct kset_hotplug_ops memory_hotplug_ops = { + .name = memory_hotplug_name, + .hotplug = memory_hotplug, +}; + +static struct notifier_block *memory_chain; + +static int register_memory_notifier(struct notifier_block *nb) +{ + return notifier_chain_register(&memory_chain, nb); +} + +static void unregister_memory_notifier(struct notifier_block *nb) +{ + notifier_chain_unregister(&memory_chain, nb); +} + +/* + * register_memory - Setup a sysfs device for a memory block + */ +static int +register_memory(struct memory_block *memory, struct mem_section *section, + struct node *root) +{ + int error; + + memory->sysdev.cls = &memory_sysdev_class; + memory->sysdev.id = __section_nr(section); + + error = sysdev_register(&memory->sysdev); + + if (root && !error) + error = sysfs_create_link(&root->sysdev.kobj, + &memory->sysdev.kobj, + kobject_name(&memory->sysdev.kobj)); + + return error; +} + +static void +unregister_memory(struct memory_block *memory, struct mem_section *section, + struct node *root) +{ + BUG_ON(memory->sysdev.cls != &memory_sysdev_class); + BUG_ON(memory->sysdev.id != __section_nr(section)); + + sysdev_unregister(&memory->sysdev); + if (root) + sysfs_remove_link(&root->sysdev.kobj, + kobject_name(&memory->sysdev.kobj)); +} + +/* + * use this as the physical section index that this memsection + * uses. + */ + +static ssize_t show_mem_phys_index(struct sys_device *dev, char *buf) +{ + struct memory_block *mem = + container_of(dev, struct memory_block, sysdev); + return sprintf(buf, "%08lx\n", mem->phys_index); +} + +/* + * online, offline, going offline, etc. + */ +static ssize_t show_mem_state(struct sys_device *dev, char *buf) +{ + struct memory_block *mem = + container_of(dev, struct memory_block, sysdev); + ssize_t len = 0; + + /* + * We can probably put these states in a nice little array + * so that they're not open-coded + */ + switch (mem->state) { + case MEM_ONLINE: + len = sprintf(buf, "online\n"); + break; + case MEM_OFFLINE: + len = sprintf(buf, "offline\n"); + break; + case MEM_GOING_OFFLINE: + len = sprintf(buf, "going-offline\n"); + break; + default: + len = sprintf(buf, "ERROR-UNKNOWN-%ld\n", + mem->state); + WARN_ON(1); + break; + } + + return len; +} + +static inline int memory_notify(unsigned long val, void *v) +{ + return notifier_call_chain(&memory_chain, val, v); +} + +/* + * MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is + * OK to have direct references to sparsemem variables in here. + */ +static int +memory_block_action(struct memory_block *mem, unsigned long action) +{ + int i; + unsigned long psection; + unsigned long start_pfn, start_paddr; + struct page *first_page; + int ret; + int old_state = mem->state; + + psection = mem->phys_index; + first_page = pfn_to_page(psection << PFN_SECTION_SHIFT); + + /* + * The probe routines leave the pages reserved, just + * as the bootmem code does. Make sure they're still + * that way. + */ + if (action == MEM_ONLINE) { + for (i = 0; i < PAGES_PER_SECTION; i++) { + if (PageReserved(first_page+i)) + continue; + + printk(KERN_WARNING "section number %ld page number %d " + "not reserved, was it already online? \n", + psection, i); + return -EBUSY; + } + } + + switch (action) { + case MEM_ONLINE: + start_pfn = page_to_pfn(first_page); + ret = online_pages(start_pfn, PAGES_PER_SECTION); + break; + case MEM_OFFLINE: + mem->state = MEM_GOING_OFFLINE; + memory_notify(MEM_GOING_OFFLINE, NULL); + start_paddr = page_to_pfn(first_page) << PAGE_SHIFT; + ret = remove_memory(start_paddr, + PAGES_PER_SECTION << PAGE_SHIFT); + if (ret) { + mem->state = old_state; + break; + } + memory_notify(MEM_MAPPING_INVALID, NULL); + break; + default: + printk(KERN_WARNING "%s(%p, %ld) unknown action: %ld\n", + __FUNCTION__, mem, action, action); + WARN_ON(1); + ret = -EINVAL; + } + /* + * For now, only notify on successful memory operations + */ + if (!ret) + memory_notify(action, NULL); + + return ret; +} + +static int memory_block_change_state(struct memory_block *mem, + unsigned long to_state, unsigned long from_state_req) +{ + int ret = 0; + down(&mem->state_sem); + + if (mem->state != from_state_req) { + ret = -EINVAL; + goto out; + } + + ret = memory_block_action(mem, to_state); + if (!ret) + mem->state = to_state; + +out: + up(&mem->state_sem); + return ret; +} + +static ssize_t +store_mem_state(struct sys_device *dev, const char *buf, size_t count) +{ + struct memory_block *mem; + unsigned int phys_section_nr; + int ret = -EINVAL; + + mem = container_of(dev, struct memory_block, sysdev); + phys_section_nr = mem->phys_index; + + if (!valid_section_nr(phys_section_nr)) + goto out; + + if (!strncmp(buf, "online", min((int)count, 6))) + ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE); + else if(!strncmp(buf, "offline", min((int)count, 7))) + ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE); +out: + if (ret) + return ret; + return count; +} + +/* + * phys_device is a bad name for this. What I really want + * is a way to differentiate between memory ranges that + * are part of physical devices that constitute + * a complete removable unit or fru. + * i.e. do these ranges belong to the same physical device, + * s.t. if I offline all of these sections I can then + * remove the physical device? + */ +static ssize_t show_phys_device(struct sys_device *dev, char *buf) +{ + struct memory_block *mem = + container_of(dev, struct memory_block, sysdev); + return sprintf(buf, "%d\n", mem->phys_device); +} + +static SYSDEV_ATTR(phys_index, 0444, show_mem_phys_index, NULL); +static SYSDEV_ATTR(state, 0644, show_mem_state, store_mem_state); +static SYSDEV_ATTR(phys_device, 0444, show_phys_device, NULL); + +#define mem_create_simple_file(mem, attr_name) \ + sysdev_create_file(&mem->sysdev, &attr_##attr_name) +#define mem_remove_simple_file(mem, attr_name) \ + sysdev_remove_file(&mem->sysdev, &attr_##attr_name) + +/* + * Block size attribute stuff + */ +static ssize_t +print_block_size(struct class *class, char *buf) +{ + return sprintf(buf, "%lx\n", (unsigned long)PAGES_PER_SECTION * PAGE_SIZE); +} + +static CLASS_ATTR(block_size_bytes, 0444, print_block_size, NULL); + +static int block_size_init(void) +{ + sysfs_create_file(&memory_sysdev_class.kset.kobj, + &class_attr_block_size_bytes.attr); + return 0; +} + +/* + * Some architectures will have custom drivers to do this, and + * will not need to do it from userspace. The fake hot-add code + * as well as ppc64 will do all of their discovery in userspace + * and will require this interface. + */ +#ifdef CONFIG_ARCH_MEMORY_PROBE +static ssize_t +memory_probe_store(struct class *class, const char __user *buf, size_t count) +{ + u64 phys_addr; + int ret; + + phys_addr = simple_strtoull(buf, NULL, 0); + + ret = add_memory(phys_addr, PAGES_PER_SECTION << PAGE_SHIFT); + + if (ret) + count = ret; + + return count; +} +static CLASS_ATTR(probe, 0700, NULL, memory_probe_store); + +static int memory_probe_init(void) +{ + sysfs_create_file(&memory_sysdev_class.kset.kobj, + &class_attr_probe.attr); + return 0; +} +#else +#define memory_probe_init(...) do {} while (0) +#endif + +/* + * Note that phys_device is optional. It is here to allow for + * differentiation between which *physical* devices each + * section belongs to... + */ + +static int add_memory_block(unsigned long node_id, struct mem_section *section, + unsigned long state, int phys_device) +{ + struct memory_block *mem = kzalloc(sizeof(*mem), GFP_KERNEL); + int ret = 0; + + if (!mem) + return -ENOMEM; + + mem->phys_index = __section_nr(section); + mem->state = state; + init_MUTEX(&mem->state_sem); + mem->phys_device = phys_device; + + ret = register_memory(mem, section, NULL); + if (!ret) + ret = mem_create_simple_file(mem, phys_index); + if (!ret) + ret = mem_create_simple_file(mem, state); + if (!ret) + ret = mem_create_simple_file(mem, phys_device); + + return ret; +} + +/* + * For now, we have a linear search to go find the appropriate + * memory_block corresponding to a particular phys_index. If + * this gets to be a real problem, we can always use a radix + * tree or something here. + * + * This could be made generic for all sysdev classes. + */ +static struct memory_block *find_memory_block(struct mem_section *section) +{ + struct kobject *kobj; + struct sys_device *sysdev; + struct memory_block *mem; + char name[sizeof(MEMORY_CLASS_NAME) + 9 + 1]; + + /* + * This only works because we know that section == sysdev->id + * slightly redundant with sysdev_register() + */ + sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, __section_nr(section)); + + kobj = kset_find_obj(&memory_sysdev_class.kset, name); + if (!kobj) + return NULL; + + sysdev = container_of(kobj, struct sys_device, kobj); + mem = container_of(sysdev, struct memory_block, sysdev); + + return mem; +} + +int remove_memory_block(unsigned long node_id, struct mem_section *section, + int phys_device) +{ + struct memory_block *mem; + + mem = find_memory_block(section); + mem_remove_simple_file(mem, phys_index); + mem_remove_simple_file(mem, state); + mem_remove_simple_file(mem, phys_device); + unregister_memory(mem, section, NULL); + + return 0; +} + +/* + * need an interface for the VM to add new memory regions, + * but without onlining it. + */ +int register_new_memory(struct mem_section *section) +{ + return add_memory_block(0, section, MEM_OFFLINE, 0); +} + +int unregister_memory_section(struct mem_section *section) +{ + if (!valid_section(section)) + return -EINVAL; + + return remove_memory_block(0, section, 0); +} + +/* + * Initialize the sysfs support for memory devices... + */ +int __init memory_dev_init(void) +{ + unsigned int i; + int ret; + + memory_sysdev_class.kset.hotplug_ops = &memory_hotplug_ops; + ret = sysdev_class_register(&memory_sysdev_class); + + /* + * Create entries for memory sections that were found + * during boot and have been initialized + */ + for (i = 0; i < NR_MEM_SECTIONS; i++) { + if (!valid_section_nr(i)) + continue; + add_memory_block(0, __nr_to_section(i), MEM_ONLINE, 0); + } + + memory_probe_init(); + block_size_init(); + + return ret; +} diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 95f2af322c8..d597c922af1 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -16,6 +16,7 @@ #include <linux/dma-mapping.h> #include <linux/bootmem.h> #include <linux/err.h> +#include <linux/slab.h> #include "base.h" diff --git a/drivers/base/sys.c b/drivers/base/sys.c index 3431eb6004c..66ed8f2fece 100644 --- a/drivers/base/sys.c +++ b/drivers/base/sys.c @@ -21,6 +21,7 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/pm.h> +#include <asm/semaphore.h> extern struct subsystem devices_subsys; |