static ssize_t
store_mem_state(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
struct memory_block *mem = to_memory_block(dev);
int ret, online_type;
ret = lock_device_hotplug_sysfs();
if (ret)
return ret;
if (sysfs_streq(buf, "online_kernel"))
online_type = MMOP_ONLINE_KERNEL;
else if (sysfs_streq(buf, "online_movable"))
online_type = MMOP_ONLINE_MOVABLE;
else if (sysfs_streq(buf, "online"))
online_type = MMOP_ONLINE_KEEP;
else if (sysfs_streq(buf, "offline"))
online_type = MMOP_OFFLINE;
else {
ret = -EINVAL;
goto err;
}
/*
* Memory hotplug needs to hold mem_hotplug_begin() for probe to find
* the correct memory block to online before doing device_online(dev),
* which will take dev->mutex. Take the lock early to prevent an
* inversion, memory_subsys_online() callbacks will be implemented by
* assuming it's already protected.
*/
mem_hotplug_begin();
switch (online_type) {
case MMOP_ONLINE_KERNEL:
case MMOP_ONLINE_MOVABLE:
case MMOP_ONLINE_KEEP:
mem->online_type = online_type;
ret = device_online(&mem->dev);
break;
case MMOP_OFFLINE:
ret = device_offline(&mem->dev);
break;
default:
ret = -EINVAL; /* should never happen */
}
mem_hotplug_done();
err:
unlock_device_hotplug();
if (ret)
return ret;
return count;
}
static void devm_memremap_pages_release(struct device *dev, void *data)
{
struct page_map *page_map = data;
struct resource *res = &page_map->res;
resource_size_t align_start, align_size;
struct dev_pagemap *pgmap = &page_map->pgmap;
if (percpu_ref_tryget_live(pgmap->ref)) {
dev_WARN(dev, "%s: page mapping is still live!\n", __func__);
percpu_ref_put(pgmap->ref);
}
/* pages are dead and unused, undo the arch mapping */
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(resource_size(res), SECTION_SIZE);
mem_hotplug_begin();
arch_remove_memory(align_start, align_size);
mem_hotplug_done();
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
pgmap_radix_release(res);
dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc,
"%s: failed to free all reserved pages\n", __func__);
}
/**
* 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);
}
