int add_memory(int nid, u64 start, u64 size)
{
pg_data_t *pgdat = NULL;
int new_pgdat = 0;
struct resource *res;
int ret;
res = register_memory_resource(start, size);
if (!res)
return -EEXIST;
if (!node_online(nid)) {
pgdat = hotadd_new_pgdat(nid, start);
if (!pgdat)
return -ENOMEM;
new_pgdat = 1;
}
/* call arch's memory hotadd */
ret = arch_add_memory(nid, start, size);
if (ret < 0)
goto error;
/* we online node here. we can't roll back from here. */
node_set_online(nid);
cpuset_track_online_nodes();
if (new_pgdat) {
ret = register_one_node(nid);
/*
* If sysfs file of new node can't create, cpu on the node
* can't be hot-added. There is no rollback way now.
* So, check by BUG_ON() to catch it reluctantly..
*/
BUG_ON(ret);
}
return ret;
error:
/* rollback pgdat allocation and others */
if (new_pgdat)
rollback_node_hotadd(nid, pgdat);
if (res)
release_memory_resource(res);
return ret;
}
void *devm_memremap_pages(struct device *dev, struct resource *res)
{
int is_ram = region_intersects(res->start, resource_size(res),
"System RAM");
struct page_map *page_map;
int error, nid;
if (is_ram == REGION_MIXED) {
WARN_ONCE(1, "%s attempted on mixed region %pr\n",
__func__, res);
return ERR_PTR(-ENXIO);
}
if (is_ram == REGION_INTERSECTS)
return __va(res->start);
page_map = devres_alloc(devm_memremap_pages_release,
sizeof(*page_map), GFP_KERNEL);
if (!page_map)
return ERR_PTR(-ENOMEM);
memcpy(&page_map->res, res, sizeof(*res));
nid = dev_to_node(dev);
if (nid < 0)
nid = 0;
error = arch_add_memory(nid, res->start, resource_size(res), true);
if (error) {
devres_free(page_map);
return ERR_PTR(error);
}
devres_add(dev, page_map);
return __va(res->start);
}
/**
* devm_memremap_pages - remap and provide memmap backing for the given resource
* @dev: hosting device for @res
* @res: "host memory" address range
* @ref: a live per-cpu reference count
* @altmap: optional descriptor for allocating the memmap from @res
*
* Notes:
* 1/ @ref must be 'live' on entry and 'dead' before devm_memunmap_pages() time
* (or devm release event).
*
* 2/ @res is expected to be a host memory range that could feasibly be
* treated as a "System RAM" range, i.e. not a device mmio range, but
* this is not enforced.
*/
void *devm_memremap_pages(struct device *dev, struct resource *res,
struct percpu_ref *ref, struct vmem_altmap *altmap)
{
resource_size_t key, align_start, align_size, align_end;
pgprot_t pgprot = PAGE_KERNEL;
struct dev_pagemap *pgmap;
struct page_map *page_map;
int error, nid, is_ram;
unsigned long pfn;
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
- align_start;
is_ram = region_intersects(align_start, align_size,
IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
if (is_ram == REGION_MIXED) {
WARN_ONCE(1, "%s attempted on mixed region %pr\n",
__func__, res);
return ERR_PTR(-ENXIO);
}
if (is_ram == REGION_INTERSECTS)
return __va(res->start);
if (!ref)
return ERR_PTR(-EINVAL);
page_map = devres_alloc_node(devm_memremap_pages_release,
sizeof(*page_map), GFP_KERNEL, dev_to_node(dev));
if (!page_map)
return ERR_PTR(-ENOMEM);
pgmap = &page_map->pgmap;
memcpy(&page_map->res, res, sizeof(*res));
pgmap->dev = dev;
if (altmap) {
memcpy(&page_map->altmap, altmap, sizeof(*altmap));
pgmap->altmap = &page_map->altmap;
}
pgmap->ref = ref;
pgmap->res = &page_map->res;
mutex_lock(&pgmap_lock);
error = 0;
align_end = align_start + align_size - 1;
for (key = align_start; key <= align_end; key += SECTION_SIZE) {
struct dev_pagemap *dup;
rcu_read_lock();
dup = find_dev_pagemap(key);
rcu_read_unlock();
if (dup) {
dev_err(dev, "%s: %pr collides with mapping for %s\n",
__func__, res, dev_name(dup->dev));
error = -EBUSY;
break;
}
error = radix_tree_insert(&pgmap_radix, key >> PA_SECTION_SHIFT,
page_map);
if (error) {
dev_err(dev, "%s: failed: %d\n", __func__, error);
break;
}
}
mutex_unlock(&pgmap_lock);
if (error)
goto err_radix;
nid = dev_to_node(dev);
if (nid < 0)
nid = numa_mem_id();
error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(align_start), 0,
align_size);
if (error)
goto err_pfn_remap;
mem_hotplug_begin();
error = arch_add_memory(nid, align_start, align_size, true);
mem_hotplug_done();
if (error)
goto err_add_memory;
for_each_device_pfn(pfn, page_map) {
struct page *page = pfn_to_page(pfn);
/*
* ZONE_DEVICE pages union ->lru with a ->pgmap back
* pointer. It is a bug if a ZONE_DEVICE page is ever
* freed or placed on a driver-private list. Seed the
* storage with LIST_POISON* values.
*/
list_del(&page->lru);
page->pgmap = pgmap;
}
devres_add(dev, page_map);
return __va(res->start);
err_add_memory:
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
err_pfn_remap:
err_radix:
pgmap_radix_release(res);
devres_free(page_map);
return ERR_PTR(error);
}
/**
* devm_memremap_pages - remap and provide memmap backing for the given resource
* @dev: hosting device for @res
* @res: "host memory" address range
* @ref: a live per-cpu reference count
* @altmap: optional descriptor for allocating the memmap from @res
*
* Notes:
* 1/ @ref must be 'live' on entry and 'dead' before devm_memunmap_pages() time
* (or devm release event).
*
* 2/ @res is expected to be a host memory range that could feasibly be
* treated as a "System RAM" range, i.e. not a device mmio range, but
* this is not enforced.
*/
void *devm_memremap_pages(struct device *dev, struct resource *res,
struct percpu_ref *ref, struct vmem_altmap *altmap)
{
int is_ram = region_intersects(res->start, resource_size(res),
"System RAM");
resource_size_t key, align_start, align_size, align_end;
struct dev_pagemap *pgmap;
struct page_map *page_map;
unsigned long pfn;
int error, nid;
if (is_ram == REGION_MIXED) {
WARN_ONCE(1, "%s attempted on mixed region %pr\n",
__func__, res);
return ERR_PTR(-ENXIO);
}
if (is_ram == REGION_INTERSECTS)
return __va(res->start);
if (altmap && !IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) {
dev_err(dev, "%s: altmap requires CONFIG_SPARSEMEM_VMEMMAP=y\n",
__func__);
return ERR_PTR(-ENXIO);
}
if (!ref)
return ERR_PTR(-EINVAL);
page_map = devres_alloc_node(devm_memremap_pages_release,
sizeof(*page_map), GFP_KERNEL, dev_to_node(dev));
if (!page_map)
return ERR_PTR(-ENOMEM);
pgmap = &page_map->pgmap;
memcpy(&page_map->res, res, sizeof(*res));
pgmap->dev = dev;
if (altmap) {
memcpy(&page_map->altmap, altmap, sizeof(*altmap));
pgmap->altmap = &page_map->altmap;
}
pgmap->ref = ref;
pgmap->res = &page_map->res;
mutex_lock(&pgmap_lock);
error = 0;
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(resource_size(res), SECTION_SIZE);
align_end = align_start + align_size - 1;
for (key = align_start; key <= align_end; key += SECTION_SIZE) {
struct dev_pagemap *dup;
rcu_read_lock();
dup = find_dev_pagemap(key);
rcu_read_unlock();
if (dup) {
dev_err(dev, "%s: %pr collides with mapping for %s\n",
__func__, res, dev_name(dup->dev));
error = -EBUSY;
break;
}
error = radix_tree_insert(&pgmap_radix, key >> PA_SECTION_SHIFT,
page_map);
if (error) {
dev_err(dev, "%s: failed: %d\n", __func__, error);
break;
}
}
mutex_unlock(&pgmap_lock);
if (error)
goto err_radix;
nid = dev_to_node(dev);
if (nid < 0)
nid = numa_mem_id();
error = arch_add_memory(nid, align_start, align_size, true);
if (error)
goto err_add_memory;
for_each_device_pfn(pfn, page_map) {
struct page *page = pfn_to_page(pfn);
/* ZONE_DEVICE pages must never appear on a slab lru */
list_force_poison(&page->lru);
page->pgmap = pgmap;
}
devres_add(dev, page_map);
return __va(res->start);
err_add_memory:
err_radix:
pgmap_radix_release(res);
devres_free(page_map);
return ERR_PTR(error);
}
