/* __alloc_bootmem...() is protected by !slab_available() */
int __init_refok init_section_page_cgroup(unsigned long pfn)
{
struct mem_section *section;
struct page_cgroup *base, *pc;
unsigned long table_size;
int nid, index;
section = __pfn_to_section(pfn);
if (!section->page_cgroup) {
nid = page_to_nid(pfn_to_page(pfn));
table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
if (slab_is_available()) {
base = kmalloc_node(table_size, GFP_KERNEL, nid);
if (!base)
base = vmalloc_node(table_size, nid);
} else {
base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
table_size,
PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
}
} else {
/*
* We don't have to allocate page_cgroup again, but
* address of memmap may be changed. So, we have to initialize
* again.
*/
base = section->page_cgroup + pfn;
table_size = 0;
/* check address of memmap is changed or not. */
if (base->page == pfn_to_page(pfn))
return 0;
}
if (!base) {
printk(KERN_ERR "page cgroup allocation failure\n");
return -ENOMEM;
}
for (index = 0; index < PAGES_PER_SECTION; index++) {
pc = base + index;
__init_page_cgroup(pc, pfn + index);
}
section = __pfn_to_section(pfn);
section->page_cgroup = base - pfn;
total_usage += table_size;
return 0;
}
static int __meminit init_section_page_ext(unsigned long pfn, int nid)
{
struct mem_section *section;
struct page_ext *base;
unsigned long table_size;
section = __pfn_to_section(pfn);
if (section->page_ext)
return 0;
table_size = get_entry_size() * PAGES_PER_SECTION;
base = alloc_page_ext(table_size, nid);
/*
* The value stored in section->page_ext is (base - pfn)
* and it does not point to the memory block allocated above,
* causing kmemleak false positives.
*/
kmemleak_not_leak(base);
if (!base) {
pr_err("page ext allocation failure\n");
return -ENOMEM;
}
/*
* The passed "pfn" may not be aligned to SECTION. For the calculation
* we need to apply a mask.
*/
pfn &= PAGE_SECTION_MASK;
section->page_ext = (void *)base - get_entry_size() * pfn;
total_usage += table_size;
return 0;
}
static int __meminit init_section_page_cgroup(unsigned long pfn, int nid)
{
struct mem_section *section;
struct page_cgroup *base;
unsigned long table_size;
section = __pfn_to_section(pfn);
if (section->page_cgroup)
return 0;
table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
base = alloc_page_cgroup(table_size, nid);
kmemleak_not_leak(base);
if (!base) {
printk(KERN_ERR "page cgroup allocation failure\n");
return -ENOMEM;
}
pfn &= PAGE_SECTION_MASK;
section->page_cgroup = base - pfn;
total_usage += table_size;
return 0;
}
/*
* returns the number of sections whose mem_maps were properly
* set. If this is <=0, then that means that the passed-in
* map was not consumed and must be freed.
*/
int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
int nr_pages)
{
unsigned long section_nr = pfn_to_section_nr(start_pfn);
struct pglist_data *pgdat = zone->zone_pgdat;
struct mem_section *ms;
struct page *memmap;
unsigned long flags;
int ret;
/*
* no locking for this, because it does its own
* plus, it does a kmalloc
*/
sparse_index_init(section_nr, pgdat->node_id);
memmap = __kmalloc_section_memmap(nr_pages);
pgdat_resize_lock(pgdat, &flags);
ms = __pfn_to_section(start_pfn);
if (ms->section_mem_map & SECTION_MARKED_PRESENT) {
ret = -EEXIST;
goto out;
}
ms->section_mem_map |= SECTION_MARKED_PRESENT;
ret = sparse_init_one_section(ms, section_nr, memmap);
out:
pgdat_resize_unlock(pgdat, &flags);
if (ret <= 0)
__kfree_section_memmap(memmap, nr_pages);
return ret;
}
struct page_cgroup *lookup_page_cgroup(struct page *page)
{
unsigned long pfn = page_to_pfn(page);
struct mem_section *section = __pfn_to_section(pfn);
return section->page_cgroup + pfn;
}
struct page_cgroup *lookup_page_cgroup(struct page *page)
{
unsigned long pfn = page_to_pfn(page);
struct mem_section *section = __pfn_to_section(pfn);
#ifdef CONFIG_DEBUG_VM
if (!section->page_cgroup)
return NULL;
#endif
return section->page_cgroup + pfn;
}
/*
* returns the number of sections whose mem_maps were properly
* set. If this is <=0, then that means that the passed-in
* map was not consumed and must be freed.
*/
int sparse_add_one_section(unsigned long start_pfn, int nr_pages, struct page *map)
{
struct mem_section *ms = __pfn_to_section(start_pfn);
if (ms->section_mem_map & SECTION_MARKED_PRESENT)
return -EEXIST;
ms->section_mem_map |= SECTION_MARKED_PRESENT;
return sparse_init_one_section(ms, pfn_to_section_nr(start_pfn), map);
}
static void __free_page_ext(unsigned long pfn)
{
struct mem_section *ms;
struct page_ext *base;
ms = __pfn_to_section(pfn);
if (!ms || !ms->page_ext)
return;
base = get_entry(ms->page_ext, pfn);
free_page_ext(base);
ms->page_ext = NULL;
}
void __free_page_cgroup(unsigned long pfn)
{
struct mem_section *ms;
struct page_cgroup *base;
ms = __pfn_to_section(pfn);
if (!ms || !ms->page_cgroup)
return;
base = ms->page_cgroup + pfn;
free_page_cgroup(base);
ms->page_cgroup = NULL;
}
struct page_ext *lookup_page_ext(const struct page *page)
{
unsigned long pfn = page_to_pfn(page);
struct mem_section *section = __pfn_to_section(pfn);
/*
* The sanity checks the page allocator does upon freeing a
* page can reach here before the page_ext arrays are
* allocated when feeding a range of pages to the allocator
* for the first time during bootup or memory hotplug.
*/
if (!section->page_ext)
return NULL;
return get_entry(section->page_ext, pfn);
}
/* __alloc_bootmem...() is protected by !slab_available() */
static int __init_refok init_section_page_cgroup(unsigned long pfn)
{
struct mem_section *section = __pfn_to_section(pfn);
struct page_cgroup *base, *pc;
unsigned long table_size;
int nid, index;
if (!section->page_cgroup) {
nid = page_to_nid(pfn_to_page(pfn));
table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
VM_BUG_ON(!slab_is_available());
if (node_state(nid, N_HIGH_MEMORY)) {
base = kmalloc_node(table_size,
GFP_KERNEL | __GFP_NOWARN, nid);
if (!base)
base = vmalloc_node(table_size, nid);
} else {
base = kmalloc(table_size, GFP_KERNEL | __GFP_NOWARN);
if (!base)
base = vmalloc(table_size);
}
} else {
/*
* We don't have to allocate page_cgroup again, but
* address of memmap may be changed. So, we have to initialize
* again.
*/
base = section->page_cgroup + pfn;
table_size = 0;
/* check address of memmap is changed or not. */
if (base->page == pfn_to_page(pfn))
return 0;
}
if (!base) {
printk(KERN_ERR "page cgroup allocation failure\n");
return -ENOMEM;
}
for (index = 0; index < PAGES_PER_SECTION; index++) {
pc = base + index;
__init_page_cgroup(pc, pfn + index);
}
section->page_cgroup = base - pfn;
total_usage += table_size;
return 0;
}
struct page_cgroup *lookup_page_cgroup(struct page *page)
{
unsigned long pfn = page_to_pfn(page);
struct mem_section *section = __pfn_to_section(pfn);
#ifdef CONFIG_DEBUG_VM
/*
* The sanity checks the page allocator does upon freeing a
* page can reach here before the page_cgroup arrays are
* allocated when feeding a range of pages to the allocator
* for the first time during bootup or memory hotplug.
*/
if (!section->page_cgroup)
return NULL;
#endif
return section->page_cgroup + pfn;
}
void __init page_cgroup_init(void)
{
unsigned long pfn;
int nid;
if (mem_cgroup_disabled())
return;
for_each_node_state(nid, N_HIGH_MEMORY) {
unsigned long start_pfn, end_pfn;
start_pfn = node_start_pfn(nid);
end_pfn = node_end_pfn(nid);
/*
* start_pfn and end_pfn may not be aligned to SECTION and the
* page->flags of out of node pages are not initialized. So we
* scan [start_pfn, the biggest section's pfn < end_pfn) here.
*/
for (pfn = start_pfn;
pfn < end_pfn;
pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) {
/*
* even if the first pfn is invalid, that doesn't mean
* that the entire section is not used.
* so we should check if the section has the mem map.
* if it has the mem map then we should go ahead and
* create the page cgroup.
*/
struct mem_section *section = __pfn_to_section(pfn);
if (!section->section_mem_map)
continue;
/*
* Nodes's pfns can be overlapping.
* We know some arch can have a nodes layout such as
* -------------pfn-------------->
* N0 | N1 | N2 | N0 | N1 | N2|....
*/
if (pfn_to_nid(pfn) != nid)
continue;
if (init_section_page_cgroup(pfn, nid))
goto oom;
}
}
struct page_ext *lookup_page_ext(struct page *page)
{
unsigned long pfn = page_to_pfn(page);
struct mem_section *section = __pfn_to_section(pfn);
#if defined(CONFIG_DEBUG_VM) || defined(CONFIG_PAGE_POISONING)
/*
* The sanity checks the page allocator does upon freeing a
* page can reach here before the page_ext arrays are
* allocated when feeding a range of pages to the allocator
* for the first time during bootup or memory hotplug.
*
* This check is also necessary for ensuring page poisoning
* works as expected when enabled
*/
if (!section->page_ext)
return NULL;
#endif
return get_entry(section->page_ext, pfn);
}
void __free_page_cgroup(unsigned long pfn)
{
struct mem_section *ms;
struct page_cgroup *base;
ms = __pfn_to_section(pfn);
if (!ms || !ms->page_cgroup)
return;
base = ms->page_cgroup + pfn;
if (is_vmalloc_addr(base)) {
vfree(base);
ms->page_cgroup = NULL;
} else {
struct page *page = virt_to_page(base);
if (!PageReserved(page)) { /* Is bootmem ? */
kfree(base);
ms->page_cgroup = NULL;
}
}
}
static int __add_section(struct zone *zone, unsigned long phys_start_pfn)
{
int nr_pages = PAGES_PER_SECTION;
int ret;
if (pfn_valid(phys_start_pfn))
return -EEXIST;
ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages);
if (ret < 0)
return ret;
ret = __add_zone(zone, phys_start_pfn);
if (ret < 0)
return ret;
return register_new_memory(__pfn_to_section(phys_start_pfn));
}
static int __meminit init_section_page_cgroup(unsigned long pfn, int nid)
{
struct mem_section *section;
struct page_cgroup *base;
unsigned long table_size;
section = __pfn_to_section(pfn);
if (section->page_cgroup)
return 0;
table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
base = alloc_page_cgroup(table_size, nid);
/*
* The value stored in section->page_cgroup is (base - pfn)
* and it does not point to the memory block allocated above,
* causing kmemleak false positives.
*/
kmemleak_not_leak(base);
if (!base) {
printk(KERN_ERR "page cgroup allocation failure\n");
return -ENOMEM;
}
page_cgroup_lock_init(base, PAGES_PER_SECTION);
/*
* The passed "pfn" may not be aligned to SECTION. For the calculation
* we need to apply a mask.
*/
pfn &= PAGE_SECTION_MASK;
section->page_cgroup = base - pfn;
total_usage += table_size;
return 0;
}
