#include <linux/device.h>
#include <linux/io.h>
#include <linux/kasan.h>
#include <linux/memory_hotplug.h>
#include <linux/memremap.h>
#include <linux/pfn_t.h>
#include <linux/swap.h>
#include <linux/mmzone.h>
#include <linux/swapops.h>
#include <linux/types.h>
#include <linux/wait_bit.h>
#include <linux/xarray.h>
#include "internal.h"
static DEFINE_XARRAY(pgmap_array);
#ifndef CONFIG_ARCH_HAS_MEMREMAP_COMPAT_ALIGN
unsigned long memremap_compat_align(void)
{
return SUBSECTION_SIZE;
}
EXPORT_SYMBOL_GPL(memremap_compat_align);
#endif
#ifdef CONFIG_FS_DAX
DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
EXPORT_SYMBOL(devmap_managed_key);
static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
{
if (pgmap->type == MEMORY_DEVICE_FS_DAX)
static_branch_dec(&devmap_managed_key);
}
static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
{
if (pgmap->type == MEMORY_DEVICE_FS_DAX)
static_branch_inc(&devmap_managed_key);
}
#else
static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
{
}
static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
{
}
#endif /* CONFIG_FS_DAX */
static void pgmap_array_delete(struct range *range)
{
xa_store_range(&pgmap_array, PHYS_PFN(range->start), PHYS_PFN(range->end),
NULL, GFP_KERNEL);
synchronize_rcu();
}
static unsigned long pfn_first(struct dev_pagemap *pgmap, int range_id)
{
struct range *range = &pgmap->ranges[range_id];
unsigned long pfn = PHYS_PFN(range->start);
if (range_id)
return pfn;
return pfn + vmem_altmap_offset(pgmap_altmap(pgmap));
}
bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn)
{
int i;
for (i = 0; i < pgmap->nr_range; i++) {
struct range *range = &pgmap->ranges[i];
if (pfn >= PHYS_PFN(range->start) &&
pfn <= PHYS_PFN(range->end))
return pfn >= pfn_first(pgmap, i);
}
return false;
}
static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id)
{
const struct range *range = &pgmap->ranges[range_id];
return (range->start + range_len(range)) >> PAGE_SHIFT;
}
static unsigned long pfn_len(struct dev_pagemap *pgmap, unsigned long range_id)
{
return (pfn_end(pgmap, range_id) -
pfn_first(pgmap, range_id)) >> pgmap->vmemmap_shift;
}
static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
{
struct range *range = &pgmap->ranges[range_id];
struct page *first_page;
first_page = pfn_to_page(pfn_first(pgmap, range_id));
mem_hotplug_begin();
remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(range->start),
PHYS_PFN(range_len(range)));
if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
__remove_pages(PHYS_PFN(range->start),
PHYS_PFN(range_len(range)), NULL);
} else {
arch_remove_memory(range->start, range_len(range),
pgmap_altmap(pgmap));
kasan_remove_zero_shadow(__va(range->start), range_len(range));
}
mem_hotplug_done();
untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range), true);
pgmap_array_delete(range);
}
void memunmap_pages(struct dev_pagemap *pgmap)
{
int i;
percpu_ref_kill(&pgmap->ref);
if (pgmap->type != MEMORY_DEVICE_PRIVATE &&
pgmap->type != MEMORY_DEVICE_COHERENT)
for (i = 0; i < pgmap->nr_range; i++)
percpu_ref_put_many(&pgmap->ref, pfn_len(pgmap, i));
wait_for_completion(&pgmap->done);
for (i = 0; i < pgmap->nr_range; i++)
pageunmap_range(pgmap, i);
percpu_ref_exit(&pgmap->ref);
WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n");
devmap_managed_enable_put(pgmap);
}
EXPORT_SYMBOL_GPL(memunmap_pages);
static void devm_memremap_pages_release(void *data)
{
memunmap_pages(data);
}
static void dev_pagemap_percpu_release(struct percpu_ref *ref)
{
struct dev_pagemap *pgmap = container_of(ref, struct dev_pagemap, ref);
complete(&pgmap->done);
}
static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
int range_id, int nid)
{
const bool is_private = pgmap->type == MEMORY_DEVICE_PRIVATE;
struct range *range = &pgmap->ranges[range_id];
struct dev_pagemap *conflict_pgmap;
int error, is_ram;
if (WARN_ONCE(pgmap_altmap(pgmap) && range_id > 0,
"altmap not supported for multiple ranges\n"))
return -EINVAL;
conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->start), NULL);
if (conflict_pgmap) {
WARN(1, "Conflicting mapping in same section\n");
put_dev_pagemap(conflict_pgmap);
return -ENOMEM;
}
conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->end), NULL);
if (conflict_pgmap) {
WARN(1, "Conflicting mapping in same section\n");
put_dev_pagemap(conflict_pgmap);
return -ENOMEM;
}
is_ram = region_intersects(range->start, range_len(range),
IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
if (is_ram != REGION_DISJOINT) {
WARN_ONCE(1, "attempted on %s region %#llx-%#llx\n",
is_ram == REGION_MIXED ? "mixed" : "ram",
range->start, range->end);
return -ENXIO;
}
error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(range->start),
PHYS_PFN(range->end), pgmap, GFP_KERNEL));
if (error)
return error;
if (nid < 0)
nid = numa_mem_id();
error = track_pfn_remap(NULL, ¶ms->pgprot, PHYS_PFN(range->start), 0,
range_len(range));
if (error)
goto err_pfn_remap;
if (!mhp_range_allowed(range->start, range_len(range), !is_private)) {
error = -EINVAL;
goto err_kasan;
}
mem_hotplug_begin();
if (is_private) {
error = add_pages(nid, PHYS_PFN(range->start),
PHYS_PFN(range_len(range)), params);
} else {
error = kasan_add_zero_shadow(__va(range->start), range_len(range));
if (error) {
mem_hotplug_done();
goto err_kasan;
}
error = arch_add_memory(nid, range->start, range_len(range),
params);
}
if (!error) {
struct zone *zone;
zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
move_pfn_range_to_zone(zone, PHYS_PFN(range->start),
PHYS_PFN(range_len(range)), params->altmap,
MIGRATE_MOVABLE);
}
mem_hotplug_done();
if (error)
goto err_add_memory;
memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
PHYS_PFN(range->start),
PHYS_PFN(range_len(range)), pgmap);
if (pgmap->type != MEMORY_DEVICE_PRIVATE &&
pgmap->type != MEMORY_DEVICE_COHERENT)
percpu_ref_get_many(&pgmap->ref, pfn_len(pgmap, range_id));
return 0;
err_add_memory:
if (!is_private)
kasan_remove_zero_shadow(__va(range->start), range_len(range));
err_kasan:
untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range), true);
err_pfn_remap:
pgmap_array_delete(range);
return error;
}
void *memremap_pages(struct dev_pagemap *pgmap, int nid)
{
struct mhp_params params = {
.altmap = pgmap_altmap(pgmap),
.pgmap = pgmap,
.pgprot = PAGE_KERNEL,
};
const int nr_range = pgmap->nr_range;
int error, i;
if (WARN_ONCE(!nr_range, "nr_range must be specified\n"))
return ERR_PTR(-EINVAL);
switch (pgmap->type) {
case MEMORY_DEVICE_PRIVATE:
if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) {
WARN(1, "Device private memory not supported\n");
return ERR_PTR(-EINVAL);
}
if (!pgmap->ops || !pgmap->ops->migrate_to_ram) {
WARN(1, "Missing migrate_to_ram method\n");
return ERR_PTR(-EINVAL);
}
if (!pgmap->ops->page_free) {
WARN(1, "Missing page_free method\n");
return ERR_PTR(-EINVAL);
}
if (!pgmap->owner) {
WARN(1, "Missing owner\n");
return ERR_PTR(-EINVAL);
}
break;
case MEMORY_DEVICE_COHERENT:
if (!pgmap->ops->page_free) {
WARN(1, "Missing page_free method\n");
return ERR_PTR(-EINVAL);
}
if (!pgmap->owner) {
WARN(1, "Missing owner\n");
return ERR_PTR(-EINVAL);
}
break;
case MEMORY_DEVICE_FS_DAX:
if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
WARN(1, "File system DAX not supported\n");
return ERR_PTR(-EINVAL);
}
params.pgprot = pgprot_decrypted(params.pgprot);
break;
case MEMORY_DEVICE_GENERIC:
break;
case MEMORY_DEVICE_PCI_P2PDMA:
params.pgprot = pgprot_noncached(params.pgprot);
break;
default:
WARN(1, "Invalid pgmap type %d\n", pgmap->type);
break;
}
init_completion(&pgmap->done);
error = percpu_ref_init(&pgmap->ref, dev_pagemap_percpu_release, 0,
GFP_KERNEL);
if (error)
return ERR_PTR(error);
devmap_managed_enable_get(pgmap);
pgmap->nr_range = 0;
error = 0;
for (i = 0; i < nr_range; i++) {
error = pagemap_range(pgmap, ¶ms, i, nid);
if (error)
break;
pgmap->nr_range++;
}
if (i < nr_range) {
memunmap_pages(pgmap);
pgmap->nr_range = nr_range;
return ERR_PTR(error);
}
return __va(pgmap->ranges[0].start);
}
EXPORT_SYMBOL_GPL(memremap_pages);
void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
{
int error;
void *ret;
ret = memremap_pages(pgmap, dev_to_node(dev));
if (IS_ERR(ret))
return ret;
error = devm_add_action_or_reset(dev, devm_memremap_pages_release,
pgmap);
if (error)
return ERR_PTR(error);
return ret;
}
EXPORT_SYMBOL_GPL(devm_memremap_pages);
void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap)
{
devm_release_action(dev, devm_memremap_pages_release, pgmap);
}
EXPORT_SYMBOL_GPL(devm_memunmap_pages);
unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
{
if (altmap)
return altmap->reserve + altmap->free;
return 0;
}
void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns)
{
altmap->alloc -= nr_pfns;
}
struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
struct dev_pagemap *pgmap)
{
resource_size_t phys = PFN_PHYS(pfn);
if (pgmap) {
if (phys >= pgmap->range.start && phys <= pgmap->range.end)
return pgmap;
put_dev_pagemap(pgmap);
}
rcu_read_lock();
pgmap = xa_load(&pgmap_array, PHYS_PFN(phys));
if (pgmap && !percpu_ref_tryget_live_rcu(&pgmap->ref))
pgmap = NULL;
rcu_read_unlock();
return pgmap;
}
EXPORT_SYMBOL_GPL(get_dev_pagemap);
void free_zone_device_page(struct page *page)
{
if (WARN_ON_ONCE(!page->pgmap->ops || !page->pgmap->ops->page_free))
return;
mem_cgroup_uncharge(page_folio(page));
VM_BUG_ON_PAGE(PageAnon(page) && PageCompound(page), page);
if (PageAnon(page))
__ClearPageAnonExclusive(page);
page->mapping = NULL;
page->pgmap->ops->page_free(page);
if (page->pgmap->type != MEMORY_DEVICE_PRIVATE &&
page->pgmap->type != MEMORY_DEVICE_COHERENT)
set_page_count(page, 1);
else
put_dev_pagemap(page->pgmap);
}
void zone_device_page_init(struct page *page)
{
WARN_ON_ONCE(!percpu_ref_tryget_live(&page->pgmap->ref));
set_page_count(page, 1);
lock_page(page);
}
EXPORT_SYMBOL_GPL(zone_device_page_init);
#ifdef CONFIG_FS_DAX
bool __put_devmap_managed_page_refs(struct page *page, int refs)
{
if (page->pgmap->type != MEMORY_DEVICE_FS_DAX)
return false;
if (page_ref_sub_return(page, refs) == 1)
wake_up_var(&page->_refcount);
return true;
}
EXPORT_SYMBOL(__put_devmap_managed_page_refs);
#endif /* CONFIG_FS_DAX */