/*
- * drivers/base/memory.c - basic Memory class support
+ * Memory subsystem support
*
* Written by Matt Tolentino <matthew.e.tolentino@intel.com>
* Dave Hansen <haveblue@us.ibm.com>
* 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/topology.h>
#include <linux/stat.h>
#include <linux/slab.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
#include <asm/uaccess.h>
static DEFINE_MUTEX(mem_sysfs_mutex);
#define MEMORY_CLASS_NAME "memory"
-#define MIN_MEMORY_BLOCK_SIZE (1 << SECTION_SIZE_BITS)
static int sections_per_block;
return section_nr / sections_per_block;
}
-static struct sysdev_class memory_sysdev_class = {
+static struct bus_type memory_subsys = {
.name = MEMORY_CLASS_NAME,
-};
-
-static const char *memory_uevent_name(struct kset *kset, struct kobject *kobj)
-{
- return MEMORY_CLASS_NAME;
-}
-
-static int memory_uevent(struct kset *kset, struct kobject *obj,
- struct kobj_uevent_env *env)
-{
- int retval = 0;
-
- return retval;
-}
-
-static const struct kset_uevent_ops memory_uevent_ops = {
- .name = memory_uevent_name,
- .uevent = memory_uevent,
+ .dev_name = MEMORY_CLASS_NAME,
};
static BLOCKING_NOTIFIER_HEAD(memory_chain);
{
int error;
- memory->sysdev.cls = &memory_sysdev_class;
- memory->sysdev.id = memory->start_section_nr / sections_per_block;
+ memory->dev.bus = &memory_subsys;
+ memory->dev.id = memory->start_section_nr / sections_per_block;
- error = sysdev_register(&memory->sysdev);
+ error = device_register(&memory->dev);
return error;
}
static void
unregister_memory(struct memory_block *memory)
{
- BUG_ON(memory->sysdev.cls != &memory_sysdev_class);
+ BUG_ON(memory->dev.bus != &memory_subsys);
/* drop the ref. we got in remove_memory_block() */
- kobject_put(&memory->sysdev.kobj);
- sysdev_unregister(&memory->sysdev);
+ kobject_put(&memory->dev.kobj);
+ device_unregister(&memory->dev);
}
unsigned long __weak memory_block_size_bytes(void)
* uses.
*/
-static ssize_t show_mem_start_phys_index(struct sys_device *dev,
- struct sysdev_attribute *attr, char *buf)
+static ssize_t show_mem_start_phys_index(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct memory_block *mem =
- container_of(dev, struct memory_block, sysdev);
+ container_of(dev, struct memory_block, dev);
unsigned long phys_index;
phys_index = mem->start_section_nr / sections_per_block;
return sprintf(buf, "%08lx\n", phys_index);
}
-static ssize_t show_mem_end_phys_index(struct sys_device *dev,
- struct sysdev_attribute *attr, char *buf)
+static ssize_t show_mem_end_phys_index(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct memory_block *mem =
- container_of(dev, struct memory_block, sysdev);
+ container_of(dev, struct memory_block, dev);
unsigned long phys_index;
phys_index = mem->end_section_nr / sections_per_block;
/*
* Show whether the section of memory is likely to be hot-removable
*/
-static ssize_t show_mem_removable(struct sys_device *dev,
- struct sysdev_attribute *attr, char *buf)
+static ssize_t show_mem_removable(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
unsigned long i, pfn;
int ret = 1;
struct memory_block *mem =
- container_of(dev, struct memory_block, sysdev);
+ container_of(dev, struct memory_block, dev);
for (i = 0; i < sections_per_block; i++) {
pfn = section_nr_to_pfn(mem->start_section_nr + i);
/*
* online, offline, going offline, etc.
*/
-static ssize_t show_mem_state(struct sys_device *dev,
- struct sysdev_attribute *attr, char *buf)
+static ssize_t show_mem_state(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct memory_block *mem =
- container_of(dev, struct memory_block, sysdev);
+ container_of(dev, struct memory_block, dev);
ssize_t len = 0;
/*
return atomic_notifier_call_chain(&memory_isolate_chain, val, v);
}
+/*
+ * The probe routines leave the pages reserved, just as the bootmem code does.
+ * Make sure they're still that way.
+ */
+static bool pages_correctly_reserved(unsigned long start_pfn,
+ unsigned long nr_pages)
+{
+ int i, j;
+ struct page *page;
+ unsigned long pfn = start_pfn;
+
+ /*
+ * memmap between sections is not contiguous except with
+ * SPARSEMEM_VMEMMAP. We lookup the page once per section
+ * and assume memmap is contiguous within each section
+ */
+ for (i = 0; i < sections_per_block; i++, pfn += PAGES_PER_SECTION) {
+ if (WARN_ON_ONCE(!pfn_valid(pfn)))
+ return false;
+ page = pfn_to_page(pfn);
+
+ for (j = 0; j < PAGES_PER_SECTION; j++) {
+ if (PageReserved(page + j))
+ continue;
+
+ printk(KERN_WARNING "section number %ld page number %d "
+ "not reserved, was it already online?\n",
+ pfn_to_section_nr(pfn), j);
+
+ return false;
+ }
+ }
+
+ return true;
+}
+
/*
* 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(unsigned long phys_index, unsigned long action)
{
- int i;
unsigned long start_pfn, start_paddr;
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
struct page *first_page;
first_page = pfn_to_page(phys_index << 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 < nr_pages; i++) {
- if (PageReserved(first_page+i))
- continue;
-
- printk(KERN_WARNING "section number %ld page number %d "
- "not reserved, was it already online?\n",
- phys_index, i);
- return -EBUSY;
- }
- }
-
switch (action) {
case MEM_ONLINE:
start_pfn = page_to_pfn(first_page);
+
+ if (!pages_correctly_reserved(start_pfn, nr_pages))
+ return -EBUSY;
+
ret = online_pages(start_pfn, nr_pages);
break;
case MEM_OFFLINE:
static int memory_block_change_state(struct memory_block *mem,
unsigned long to_state, unsigned long from_state_req)
{
- int i, ret = 0;
+ int ret = 0;
mutex_lock(&mem->state_mutex);
ret = memory_block_action(mem->start_section_nr, to_state);
- if (ret)
+ if (ret) {
mem->state = from_state_req;
- else
- mem->state = to_state;
+ goto out;
+ }
+ 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;
+ }
out:
mutex_unlock(&mem->state_mutex);
return ret;
}
static ssize_t
-store_mem_state(struct sys_device *dev,
- struct sysdev_attribute *attr, const char *buf, size_t count)
+store_mem_state(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t count)
{
struct memory_block *mem;
int ret = -EINVAL;
- mem = container_of(dev, struct memory_block, sysdev);
+ mem = container_of(dev, struct memory_block, dev);
if (!strncmp(buf, "online", min((int)count, 6)))
ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
* 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,
- struct sysdev_attribute *attr, char *buf)
+static ssize_t show_phys_device(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct memory_block *mem =
- container_of(dev, struct memory_block, sysdev);
+ container_of(dev, struct memory_block, dev);
return sprintf(buf, "%d\n", mem->phys_device);
}
-static SYSDEV_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL);
-static SYSDEV_ATTR(end_phys_index, 0444, show_mem_end_phys_index, NULL);
-static SYSDEV_ATTR(state, 0644, show_mem_state, store_mem_state);
-static SYSDEV_ATTR(phys_device, 0444, show_phys_device, NULL);
-static SYSDEV_ATTR(removable, 0444, show_mem_removable, NULL);
+static DEVICE_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL);
+static DEVICE_ATTR(end_phys_index, 0444, show_mem_end_phys_index, NULL);
+static DEVICE_ATTR(state, 0644, show_mem_state, store_mem_state);
+static DEVICE_ATTR(phys_device, 0444, show_phys_device, NULL);
+static DEVICE_ATTR(removable, 0444, show_mem_removable, NULL);
#define mem_create_simple_file(mem, attr_name) \
- sysdev_create_file(&mem->sysdev, &attr_##attr_name)
+ device_create_file(&mem->dev, &dev_attr_##attr_name)
#define mem_remove_simple_file(mem, attr_name) \
- sysdev_remove_file(&mem->sysdev, &attr_##attr_name)
+ device_remove_file(&mem->dev, &dev_attr_##attr_name)
/*
* Block size attribute stuff
*/
static ssize_t
-print_block_size(struct sysdev_class *class, struct sysdev_class_attribute *attr,
+print_block_size(struct device *dev, struct device_attribute *attr,
char *buf)
{
return sprintf(buf, "%lx\n", get_memory_block_size());
}
-static SYSDEV_CLASS_ATTR(block_size_bytes, 0444, print_block_size, NULL);
+static DEVICE_ATTR(block_size_bytes, 0444, print_block_size, NULL);
static int block_size_init(void)
{
- return sysfs_create_file(&memory_sysdev_class.kset.kobj,
- &attr_block_size_bytes.attr);
+ return device_create_file(memory_subsys.dev_root,
+ &dev_attr_block_size_bytes);
}
/*
*/
#ifdef CONFIG_ARCH_MEMORY_PROBE
static ssize_t
-memory_probe_store(struct class *class, struct class_attribute *attr,
+memory_probe_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
u64 phys_addr;
int nid;
int i, ret;
+ unsigned long pages_per_block = PAGES_PER_SECTION * sections_per_block;
phys_addr = simple_strtoull(buf, NULL, 0);
+ if (phys_addr & ((pages_per_block << PAGE_SHIFT) - 1))
+ return -EINVAL;
+
for (i = 0; i < sections_per_block; i++) {
nid = memory_add_physaddr_to_nid(phys_addr);
ret = add_memory(nid, phys_addr,
PAGES_PER_SECTION << PAGE_SHIFT);
if (ret)
- break;
+ goto out;
phys_addr += MIN_MEMORY_BLOCK_SIZE;
}
- if (ret)
- count = ret;
-
- return count;
+ ret = count;
+out:
+ return ret;
}
-static CLASS_ATTR(probe, S_IWUSR, NULL, memory_probe_store);
+static DEVICE_ATTR(probe, S_IWUSR, NULL, memory_probe_store);
static int memory_probe_init(void)
{
- return sysfs_create_file(&memory_sysdev_class.kset.kobj,
- &class_attr_probe.attr);
+ return device_create_file(memory_subsys.dev_root, &dev_attr_probe);
}
#else
static inline int memory_probe_init(void)
/* Soft offline a page */
static ssize_t
-store_soft_offline_page(struct class *class,
- struct class_attribute *attr,
+store_soft_offline_page(struct device *dev,
+ struct device_attribute *attr,
const char *buf, size_t count)
{
int ret;
/* Forcibly offline a page, including killing processes. */
static ssize_t
-store_hard_offline_page(struct class *class,
- struct class_attribute *attr,
+store_hard_offline_page(struct device *dev,
+ struct device_attribute *attr,
const char *buf, size_t count)
{
int ret;
if (strict_strtoull(buf, 0, &pfn) < 0)
return -EINVAL;
pfn >>= PAGE_SHIFT;
- ret = __memory_failure(pfn, 0, 0);
+ ret = memory_failure(pfn, 0, 0);
return ret ? ret : count;
}
-static CLASS_ATTR(soft_offline_page, 0644, NULL, store_soft_offline_page);
-static CLASS_ATTR(hard_offline_page, 0644, NULL, store_hard_offline_page);
+static DEVICE_ATTR(soft_offline_page, 0644, NULL, store_soft_offline_page);
+static DEVICE_ATTR(hard_offline_page, 0644, NULL, store_hard_offline_page);
static __init int memory_fail_init(void)
{
int err;
- err = sysfs_create_file(&memory_sysdev_class.kset.kobj,
- &class_attr_soft_offline_page.attr);
+ err = device_create_file(memory_subsys.dev_root,
+ &dev_attr_soft_offline_page);
if (!err)
- err = sysfs_create_file(&memory_sysdev_class.kset.kobj,
- &class_attr_hard_offline_page.attr);
+ err = device_create_file(memory_subsys.dev_root,
+ &dev_attr_hard_offline_page);
return err;
}
#else
return 0;
}
+/*
+ * A reference for the returned object is held and the reference for the
+ * hinted object is released.
+ */
struct memory_block *find_memory_block_hinted(struct mem_section *section,
struct memory_block *hint)
{
- struct kobject *kobj;
- struct sys_device *sysdev;
- struct memory_block *mem;
- char name[sizeof(MEMORY_CLASS_NAME) + 9 + 1];
int block_id = base_memory_block_id(__section_nr(section));
+ struct device *hintdev = hint ? &hint->dev : NULL;
+ struct device *dev;
- kobj = hint ? &hint->sysdev.kobj : NULL;
-
- /*
- * This only works because we know that section == sysdev->id
- * slightly redundant with sysdev_register()
- */
- sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, block_id);
-
- kobj = kset_find_obj_hinted(&memory_sysdev_class.kset, name, kobj);
- if (!kobj)
+ dev = subsys_find_device_by_id(&memory_subsys, block_id, hintdev);
+ if (hint)
+ put_device(&hint->dev);
+ if (!dev)
return NULL;
-
- sysdev = container_of(kobj, struct sys_device, kobj);
- mem = container_of(sysdev, struct memory_block, sysdev);
-
- return mem;
+ return container_of(dev, struct memory_block, dev);
}
/*
* 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.
+ * This could be made generic for all device subsystems.
*/
struct memory_block *find_memory_block(struct mem_section *section)
{
}
static int add_memory_section(int nid, struct mem_section *section,
+ struct memory_block **mem_p,
unsigned long state, enum mem_add_context context)
{
- struct memory_block *mem;
+ struct memory_block *mem = NULL;
+ int scn_nr = __section_nr(section);
int ret = 0;
mutex_lock(&mem_sysfs_mutex);
- mem = find_memory_block(section);
+ if (context == BOOT) {
+ /* same memory block ? */
+ if (mem_p && *mem_p)
+ if (scn_nr >= (*mem_p)->start_section_nr &&
+ scn_nr <= (*mem_p)->end_section_nr) {
+ mem = *mem_p;
+ kobject_get(&mem->dev.kobj);
+ }
+ } else
+ mem = find_memory_block(section);
+
if (mem) {
mem->section_count++;
- kobject_put(&mem->sysdev.kobj);
- } else
+ kobject_put(&mem->dev.kobj);
+ } else {
ret = init_memory_block(&mem, section, state);
+ /* store memory_block pointer for next loop */
+ if (!ret && context == BOOT)
+ if (mem_p)
+ *mem_p = mem;
+ }
if (!ret) {
if (context == HOTPLUG &&
unregister_memory(mem);
kfree(mem);
} else
- kobject_put(&mem->sysdev.kobj);
+ kobject_put(&mem->dev.kobj);
mutex_unlock(&mem_sysfs_mutex);
return 0;
*/
int register_new_memory(int nid, struct mem_section *section)
{
- return add_memory_section(nid, section, MEM_OFFLINE, HOTPLUG);
+ return add_memory_section(nid, section, NULL, MEM_OFFLINE, HOTPLUG);
}
int unregister_memory_section(struct mem_section *section)
int ret;
int err;
unsigned long block_sz;
+ struct memory_block *mem = NULL;
- memory_sysdev_class.kset.uevent_ops = &memory_uevent_ops;
- ret = sysdev_class_register(&memory_sysdev_class);
+ ret = subsys_system_register(&memory_subsys, NULL);
if (ret)
goto out;
for (i = 0; i < NR_MEM_SECTIONS; i++) {
if (!present_section_nr(i))
continue;
- err = add_memory_section(0, __nr_to_section(i), MEM_ONLINE,
+ /* don't need to reuse memory_block if only one per block */
+ err = add_memory_section(0, __nr_to_section(i),
+ (sections_per_block == 1) ? NULL : &mem,
+ MEM_ONLINE,
BOOT);
if (!ret)
ret = err;
Code Review / linux-2.6.git / blobdiff