/* register memory section under specified node if it spans that node */
int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
{
int ret;
unsigned long pfn, sect_start_pfn, sect_end_pfn;
if (!mem_blk)
return -EFAULT;
if (!node_online(nid))
return 0;
sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
sect_end_pfn += PAGES_PER_SECTION - 1;
for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
int page_nid;
page_nid = get_nid_for_pfn(pfn);
if (page_nid < 0)
continue;
if (page_nid != nid)
continue;
ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
&mem_blk->dev.kobj,
kobject_name(&mem_blk->dev.kobj));
if (ret)
return ret;
return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
&node_devices[nid]->dev.kobj,
kobject_name(&node_devices[nid]->dev.kobj));
}
/* mem section does not span the specified node */
return 0;
}
/**
* alloc_bootmem_section - allocate boot memory from a specific section
* @size: size of the request in bytes
* @section_nr: sparse map section to allocate from
*
* Return NULL on failure.
*/
void * __init alloc_bootmem_section(unsigned long size,
unsigned long section_nr)
{
unsigned long pfn, goal, limit;
pfn = section_nr_to_pfn(section_nr);
goal = pfn << PAGE_SHIFT;
limit = section_nr_to_pfn(section_nr + 1) << PAGE_SHIFT;
return __alloc_memory_core_early(early_pfn_to_nid(pfn), size,
SMP_CACHE_BYTES, goal, limit);
}
/* unregister memory section under all nodes that it spans */
int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
{
nodemask_t unlinked_nodes;
unsigned long pfn, sect_start_pfn, sect_end_pfn;
if (!mem_blk)
return -EFAULT;
nodes_clear(unlinked_nodes);
sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index);
sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
int nid;
nid = get_nid_for_pfn(pfn);
if (nid < 0)
continue;
if (!node_online(nid))
continue;
if (node_test_and_set(nid, unlinked_nodes))
continue;
sysfs_remove_link(&node_devices[nid].sysdev.kobj,
kobject_name(&mem_blk->sysdev.kobj));
}
return 0;
}
static int pseries_add_memory(struct device_node *np)
{
const char *type;
const unsigned int *my_index;
const unsigned int *regs;
u64 start_pfn;
int ret = -EINVAL;
/*
* Check to see if we are actually adding memory
*/
type = of_get_property(np, "device_type", NULL);
if (type == NULL || strcmp(type, "memory") != 0)
return 0;
/*
* Find the memory index and size of the added section
*/
my_index = of_get_property(np, "ibm,my-drc-index", NULL);
if (!my_index)
return ret;
regs = of_get_property(np, "reg", NULL);
if (!regs)
return ret;
start_pfn = section_nr_to_pfn(*my_index & 0xffff);
/*
* Update memory region to represent the memory add
*/
lmb_add(start_pfn << PAGE_SHIFT, regs[3]);
return 0;
}
static ssize_t show_valid_zones(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct memory_block *mem = to_memory_block(dev);
unsigned long start_pfn, end_pfn;
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
struct page *first_page;
struct zone *zone;
start_pfn = section_nr_to_pfn(mem->start_section_nr);
end_pfn = start_pfn + nr_pages;
first_page = pfn_to_page(start_pfn);
/* The block contains more than one zone can not be offlined. */
if (!test_pages_in_a_zone(start_pfn, end_pfn))
return sprintf(buf, "none\n");
zone = page_zone(first_page);
if (zone_idx(zone) == ZONE_MOVABLE - 1) {
/*The mem block is the last memoryblock of this zone.*/
if (end_pfn == zone_end_pfn(zone))
return sprintf(buf, "%s %s\n",
zone->name, (zone + 1)->name);
}
if (zone_idx(zone) == ZONE_MOVABLE) {
/*The mem block is the first memoryblock of ZONE_MOVABLE.*/
if (start_pfn == zone->zone_start_pfn)
return sprintf(buf, "%s %s\n",
zone->name, (zone - 1)->name);
}
return sprintf(buf, "%s\n", zone->name);
}
static int init_memory_block(struct memory_block **memory,
struct mem_section *section, unsigned long state)
{
struct memory_block *mem;
unsigned long start_pfn;
int scn_nr;
int ret = 0;
mem = kzalloc(sizeof(*mem), GFP_KERNEL);
if (!mem)
return -ENOMEM;
scn_nr = __section_nr(section);
mem->start_section_nr =
base_memory_block_id(scn_nr) * sections_per_block;
mem->end_section_nr = mem->start_section_nr + sections_per_block - 1;
mem->state = state;
start_pfn = section_nr_to_pfn(mem->start_section_nr);
mem->phys_device = arch_get_memory_phys_device(start_pfn);
ret = register_memory(mem);
*memory = mem;
return ret;
}
int ehea_create_busmap( void )
{
u64 vaddr = EHEA_BUSMAP_START;
unsigned long high_section_index = 0;
int i;
/*
* Sections are not in ascending order -> Loop over all sections and
* find the highest PFN to compute the required map size.
*/
ehea_bmap.valid_sections = 0;
for (i = 0; i < NR_MEM_SECTIONS; i++)
if (valid_section_nr(i))
high_section_index = i;
ehea_bmap.entries = high_section_index + 1;
ehea_bmap.vaddr = vmalloc(ehea_bmap.entries * sizeof(*ehea_bmap.vaddr));
if (!ehea_bmap.vaddr)
return -ENOMEM;
for (i = 0 ; i < ehea_bmap.entries; i++) {
unsigned long pfn = section_nr_to_pfn(i);
if (pfn_valid(pfn)) {
ehea_bmap.vaddr[i] = vaddr;
vaddr += EHEA_SECTSIZE;
ehea_bmap.valid_sections++;
} else
ehea_bmap.vaddr[i] = 0;
}
return 0;
}
/*
* MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is
* OK to have direct references to sparsemem variables in here.
* Must already be protected by mem_hotplug_begin().
*/
static int
memory_block_action(unsigned long phys_index, unsigned long action, int online_type)
{
unsigned long start_pfn;
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
struct page *first_page;
int ret;
start_pfn = section_nr_to_pfn(phys_index);
first_page = pfn_to_page(start_pfn);
switch (action) {
case MEM_ONLINE:
if (!pages_correctly_reserved(start_pfn))
return -EBUSY;
ret = online_pages(start_pfn, nr_pages, online_type);
break;
case MEM_OFFLINE:
ret = offline_pages(start_pfn, nr_pages);
break;
default:
WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "
"%ld\n", __func__, phys_index, action, action);
ret = -EINVAL;
}
return ret;
}
/* unregister memory section under all nodes that it spans */
int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
unsigned long phys_index)
{
NODEMASK_ALLOC(nodemask_t, unlinked_nodes, GFP_KERNEL);
unsigned long pfn, sect_start_pfn, sect_end_pfn;
if (!mem_blk) {
NODEMASK_FREE(unlinked_nodes);
return -EFAULT;
}
if (!unlinked_nodes)
return -ENOMEM;
nodes_clear(*unlinked_nodes);
sect_start_pfn = section_nr_to_pfn(phys_index);
sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
int nid;
nid = get_nid_for_pfn(pfn);
if (nid < 0)
continue;
if (!node_online(nid))
continue;
if (node_test_and_set(nid, *unlinked_nodes))
continue;
sysfs_remove_link(&node_devices[nid]->dev.kobj,
kobject_name(&mem_blk->dev.kobj));
sysfs_remove_link(&mem_blk->dev.kobj,
kobject_name(&node_devices[nid]->dev.kobj));
}
NODEMASK_FREE(unlinked_nodes);
return 0;
}
/* register memory section under specified node if it spans that node */
int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
{
int ret;
unsigned long pfn, sect_start_pfn, sect_end_pfn;
if (!mem_blk)
return -EFAULT;
if (!node_online(nid))
return 0;
sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
sect_end_pfn += PAGES_PER_SECTION - 1;
for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
int page_nid;
/*
* memory block could have several absent sections from start.
* skip pfn range from absent section
*/
if (!pfn_present(pfn)) {
pfn = round_down(pfn + PAGES_PER_SECTION,
PAGES_PER_SECTION) - 1;
continue;
}
page_nid = get_nid_for_pfn(pfn);
if (page_nid < 0)
continue;
if (page_nid != nid)
continue;
ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
&mem_blk->dev.kobj,
kobject_name(&mem_blk->dev.kobj));
if (ret)
return ret;
return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
&node_devices[nid]->dev.kobj,
kobject_name(&node_devices[nid]->dev.kobj));
}
/* mem section does not span the specified node */
return 0;
}
static int pseries_remove_memory(struct device_node *np)
{
const char *type;
const unsigned int *my_index;
const unsigned int *regs;
u64 start_pfn, start;
struct zone *zone;
int ret = -EINVAL;
/*
* Check to see if we are actually removing memory
*/
type = of_get_property(np, "device_type", NULL);
if (type == NULL || strcmp(type, "memory") != 0)
return 0;
/*
* Find the memory index and size of the removing section
*/
my_index = of_get_property(np, "ibm,my-drc-index", NULL);
if (!my_index)
return ret;
regs = of_get_property(np, "reg", NULL);
if (!regs)
return ret;
start_pfn = section_nr_to_pfn(*my_index & 0xffff);
zone = page_zone(pfn_to_page(start_pfn));
/*
* Remove section mappings and sysfs entries for the
* section of the memory we are removing.
*
* NOTE: Ideally, this should be done in generic code like
* remove_memory(). But remove_memory() gets called by writing
* to sysfs "state" file and we can't remove sysfs entries
* while writing to it. So we have to defer it to here.
*/
ret = __remove_pages(zone, start_pfn, regs[3] >> PAGE_SHIFT);
if (ret)
return ret;
/*
* Update memory regions for memory remove
*/
lmb_remove(start_pfn << PAGE_SHIFT, regs[3]);
/*
* Remove htab bolted mappings for this section of memory
*/
start = (unsigned long)__va(start_pfn << PAGE_SHIFT);
ret = remove_section_mapping(start, start + regs[3]);
return ret;
}
/*
* 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)
{
unsigned long start_pfn;
int ret;
struct memory_block *mem =
container_of(dev, struct memory_block, sysdev);
start_pfn = section_nr_to_pfn(mem->phys_index);
ret = is_mem_section_removable(start_pfn, PAGES_PER_SECTION);
return sprintf(buf, "%d\n", ret);
}
/*
* 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)
{
unsigned long i, pfn;
int ret = 1;
struct memory_block *mem =
container_of(dev, struct memory_block, sysdev);
for (i = 0; i < sections_per_block; i++) {
pfn = section_nr_to_pfn(mem->start_section_nr + i);
ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
}
return sprintf(buf, "%d\n", ret);
}
/*
* Show whether the section of memory is likely to be hot-removable
*/
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 = to_memory_block(dev);
for (i = 0; i < sections_per_block; i++) {
if (!present_section_nr(mem->start_section_nr + i))
continue;
pfn = section_nr_to_pfn(mem->start_section_nr + i);
ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
}
return sprintf(buf, "%d\n", ret);
}
static struct page *sparse_early_mem_map_alloc(unsigned long pnum)
{
struct page *map;
int nid = early_pfn_to_nid(section_nr_to_pfn(pnum));
map = alloc_remap(nid, sizeof(struct page) * PAGES_PER_SECTION);
if (map)
return map;
map = alloc_bootmem_node(NODE_DATA(nid),
sizeof(struct page) * PAGES_PER_SECTION);
if (map)
return map;
printk(KERN_WARNING "%s: allocation failed\n", __FUNCTION__);
mem_section[pnum].section_mem_map = 0;
return NULL;
}
static ssize_t show_valid_zones(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct memory_block *mem = to_memory_block(dev);
unsigned long start_pfn, end_pfn;
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
struct page *first_page;
struct zone *zone;
int zone_shift = 0;
start_pfn = section_nr_to_pfn(mem->start_section_nr);
end_pfn = start_pfn + nr_pages;
first_page = pfn_to_page(start_pfn);
/* The block contains more than one zone can not be offlined. */
if (!test_pages_in_a_zone(start_pfn, end_pfn))
return sprintf(buf, "none\n");
zone = page_zone(first_page);
/* MMOP_ONLINE_KEEP */
sprintf(buf, "%s", zone->name);
/* MMOP_ONLINE_KERNEL */
zone_shift = zone_can_shift(start_pfn, nr_pages, ZONE_NORMAL);
if (zone_shift) {
strcat(buf, " ");
strcat(buf, (zone + zone_shift)->name);
}
/* MMOP_ONLINE_MOVABLE */
zone_shift = zone_can_shift(start_pfn, nr_pages, ZONE_MOVABLE);
if (zone_shift) {
strcat(buf, " ");
strcat(buf, (zone + zone_shift)->name);
}
strcat(buf, "\n");
return strlen(buf);
}
static int init_memory_block(struct memory_block **memory,
struct mem_section *section, unsigned long state)
{
struct memory_block *mem;
unsigned long start_pfn;
int scn_nr;
int ret = 0;
mem = kzalloc(sizeof(*mem), GFP_KERNEL);
if (!mem)
return -ENOMEM;
scn_nr = __section_nr(section);
mem->start_section_nr =
base_memory_block_id(scn_nr) * sections_per_block;
mem->end_section_nr = mem->start_section_nr + sections_per_block - 1;
mem->state = state;
mem->section_count++;
mutex_init(&mem->state_mutex);
start_pfn = section_nr_to_pfn(mem->start_section_nr);
mem->phys_device = arch_get_memory_phys_device(start_pfn);
ret = register_memory(mem);
if (!ret)
ret = mem_create_simple_file(mem, phys_index);
if (!ret)
ret = mem_create_simple_file(mem, end_phys_index);
if (!ret)
ret = mem_create_simple_file(mem, state);
if (!ret)
ret = mem_create_simple_file(mem, phys_device);
if (!ret)
ret = mem_create_simple_file(mem, removable);
*memory = mem;
return ret;
}
/*
* Subtle, we encode the real pfn into the mem_map such that
* the identity pfn - section_mem_map will return the actual
* physical page frame number.
*/
static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long pnum)
{
return (unsigned long)(mem_map - (section_nr_to_pfn(pnum)));
}
struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum)
{
return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
}
