#include <linux/memblock.h>
#include <linux/bootmem.h>
#include <linux/compaction.h>
+#include <linux/rmap.h>
#include <asm/tlbflush.h>
if (pfn_valid(phys_start_pfn))
return -EEXIST;
- ret = sparse_add_one_section(NODE_DATA(nid), phys_start_pfn, altmap);
+ ret = sparse_add_one_section(nid, phys_start_pfn, altmap);
if (ret < 0)
return ret;
unsigned long start_pfn,
unsigned long end_pfn)
{
- struct mem_section *ms;
-
for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SECTION) {
- ms = __pfn_to_section(start_pfn);
-
- if (unlikely(!valid_section(ms)))
+ if (unlikely(!pfn_to_online_page(start_pfn)))
continue;
if (unlikely(pfn_to_nid(start_pfn) != nid))
unsigned long start_pfn,
unsigned long end_pfn)
{
- struct mem_section *ms;
unsigned long pfn;
/* pfn is the end pfn of a memory section. */
pfn = end_pfn - 1;
for (; pfn >= start_pfn; pfn -= PAGES_PER_SECTION) {
- ms = __pfn_to_section(pfn);
-
- if (unlikely(!valid_section(ms)))
+ if (unlikely(!pfn_to_online_page(pfn)))
continue;
if (unlikely(pfn_to_nid(pfn) != nid))
unsigned long z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */
unsigned long zone_end_pfn = z;
unsigned long pfn;
- struct mem_section *ms;
int nid = zone_to_nid(zone);
zone_span_writelock(zone);
*/
pfn = zone_start_pfn;
for (; pfn < zone_end_pfn; pfn += PAGES_PER_SECTION) {
- ms = __pfn_to_section(pfn);
-
- if (unlikely(!valid_section(ms)))
+ if (unlikely(!pfn_to_online_page(pfn)))
continue;
if (page_zone(pfn_to_page(pfn)) != zone)
zone_span_writeunlock(zone);
}
-static void shrink_pgdat_span(struct pglist_data *pgdat,
- unsigned long start_pfn, unsigned long end_pfn)
+static void update_pgdat_span(struct pglist_data *pgdat)
{
- unsigned long pgdat_start_pfn = pgdat->node_start_pfn;
- unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */
- unsigned long pgdat_end_pfn = p;
- unsigned long pfn;
- struct mem_section *ms;
- int nid = pgdat->node_id;
-
- if (pgdat_start_pfn == start_pfn) {
- /*
- * If the section is smallest section in the pgdat, it need
- * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages.
- * In this case, we find second smallest valid mem_section
- * for shrinking zone.
- */
- pfn = find_smallest_section_pfn(nid, NULL, end_pfn,
- pgdat_end_pfn);
- if (pfn) {
- pgdat->node_start_pfn = pfn;
- pgdat->node_spanned_pages = pgdat_end_pfn - pfn;
- }
- } else if (pgdat_end_pfn == end_pfn) {
- /*
- * If the section is biggest section in the pgdat, it need
- * shrink pgdat->node_spanned_pages.
- * In this case, we find second biggest valid mem_section for
- * shrinking zone.
- */
- pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn,
- start_pfn);
- if (pfn)
- pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1;
- }
-
- /*
- * If the section is not biggest or smallest mem_section in the pgdat,
- * it only creates a hole in the pgdat. So in this case, we need not
- * change the pgdat.
- * But perhaps, the pgdat has only hole data. Thus it check the pgdat
- * has only hole or not.
- */
- pfn = pgdat_start_pfn;
- for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SECTION) {
- ms = __pfn_to_section(pfn);
+ unsigned long node_start_pfn = 0, node_end_pfn = 0;
+ struct zone *zone;
- if (unlikely(!valid_section(ms)))
- continue;
+ for (zone = pgdat->node_zones;
+ zone < pgdat->node_zones + MAX_NR_ZONES; zone++) {
+ unsigned long zone_end_pfn = zone->zone_start_pfn +
+ zone->spanned_pages;
- if (pfn_to_nid(pfn) != nid)
+ /* No need to lock the zones, they can't change. */
+ if (!zone->spanned_pages)
continue;
-
- /* If the section is current section, it continues the loop */
- if (start_pfn == pfn)
+ if (!node_end_pfn) {
+ node_start_pfn = zone->zone_start_pfn;
+ node_end_pfn = zone_end_pfn;
continue;
+ }
- /* If we find valid section, we have nothing to do */
- return;
+ if (zone_end_pfn > node_end_pfn)
+ node_end_pfn = zone_end_pfn;
+ if (zone->zone_start_pfn < node_start_pfn)
+ node_start_pfn = zone->zone_start_pfn;
}
- /* The pgdat has no valid section */
- pgdat->node_start_pfn = 0;
- pgdat->node_spanned_pages = 0;
+ pgdat->node_start_pfn = node_start_pfn;
+ pgdat->node_spanned_pages = node_end_pfn - node_start_pfn;
}
static void __remove_zone(struct zone *zone, unsigned long start_pfn)
int nr_pages = PAGES_PER_SECTION;
unsigned long flags;
+#ifdef CONFIG_ZONE_DEVICE
+ /*
+ * Zone shrinking code cannot properly deal with ZONE_DEVICE. So
+ * we will not try to shrink the zones - which is okay as
+ * set_zone_contiguous() cannot deal with ZONE_DEVICE either way.
+ */
+ if (zone_idx(zone) == ZONE_DEVICE)
+ return;
+#endif
+
pgdat_resize_lock(zone->zone_pgdat, &flags);
shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
- shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages);
+ update_pgdat_span(pgdat);
pgdat_resize_unlock(zone->zone_pgdat, &flags);
}
for (i = 0; i < sections_to_remove; i++) {
unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
+ cond_resched();
ret = __remove_section(zone, __pfn_to_section(pfn), map_offset,
altmap);
map_offset = 0;
return zone;
}
-/* Must be protected by mem_hotplug_begin() or a device_lock */
int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type)
{
unsigned long flags;
struct memory_notify arg;
struct memory_block *mem;
+ mem_hotplug_begin();
+
/*
* We can't use pfn_to_nid() because nid might be stored in struct page
* which is not yet initialized. Instead, we find nid from memory block.
*/
mem = find_memory_block(__pfn_to_section(pfn));
nid = mem->nid;
+ put_device(&mem->dev);
/* associate pfn range with the zone */
zone = move_pfn_range(online_type, nid, pfn, nr_pages);
if (onlined_pages)
memory_notify(MEM_ONLINE, &arg);
+ mem_hotplug_done();
return 0;
failed_addition:
(unsigned long long) pfn << PAGE_SHIFT,
(((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1);
memory_notify(MEM_CANCEL_ONLINE, &arg);
+ mem_hotplug_done();
return ret;
}
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
return device_online(&mem->dev);
}
-/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
+/*
+ * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
+ * and online/offline operations (triggered e.g. by sysfs).
+ *
+ * we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG
+ */
int __ref add_memory_resource(int nid, struct resource *res, bool online)
{
u64 start, size;
/* create new memmap entry */
firmware_map_add_hotplug(start, start + size, "System RAM");
+ /* device_online() will take the lock when calling online_pages() */
+ mem_hotplug_done();
+
/* online pages if requested */
if (online)
walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1),
NULL, online_memory_block);
- goto out;
-
+ return ret;
error:
/* rollback pgdat allocation and others */
if (new_node)
rollback_node_hotadd(nid);
memblock_remove(start, size);
-
-out:
mem_hotplug_done();
return ret;
}
-EXPORT_SYMBOL_GPL(add_memory_resource);
-int __ref add_memory(int nid, u64 start, u64 size)
+/* requires device_hotplug_lock, see add_memory_resource() */
+int __ref __add_memory(int nid, u64 start, u64 size)
{
struct resource *res;
int ret;
release_memory_resource(res);
return ret;
}
+
+int add_memory(int nid, u64 start, u64 size)
+{
+ int rc;
+
+ lock_device_hotplug();
+ rc = __add_memory(nid, start, size);
+ unlock_device_hotplug();
+
+ return rc;
+}
EXPORT_SYMBOL_GPL(add_memory);
#ifdef CONFIG_MEMORY_HOTREMOVE
return PageBuddy(page) && page_order(page) >= pageblock_order;
}
-/* Return the start of the next active pageblock after a given page */
-static struct page *next_active_pageblock(struct page *page)
+/* Return the pfn of the start of the next active pageblock after a given pfn */
+static unsigned long next_active_pageblock(unsigned long pfn)
{
+ struct page *page = pfn_to_page(pfn);
+
/* Ensure the starting page is pageblock-aligned */
- BUG_ON(page_to_pfn(page) & (pageblock_nr_pages - 1));
+ BUG_ON(pfn & (pageblock_nr_pages - 1));
/* If the entire pageblock is free, move to the end of free page */
if (pageblock_free(page)) {
/* be careful. we don't have locks, page_order can be changed.*/
order = page_order(page);
if ((order < MAX_ORDER) && (order >= pageblock_order))
- return page + (1 << order);
+ return pfn + (1 << order);
}
- return page + pageblock_nr_pages;
+ return pfn + pageblock_nr_pages;
}
-static bool is_pageblock_removable_nolock(struct page *page)
+static bool is_pageblock_removable_nolock(unsigned long pfn)
{
+ struct page *page = pfn_to_page(pfn);
struct zone *zone;
- unsigned long pfn;
/*
* We have to be careful here because we are iterating over memory
/* Checks if this range of memory is likely to be hot-removable. */
bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
{
- struct page *page = pfn_to_page(start_pfn);
- struct page *end_page = page + nr_pages;
+ unsigned long end_pfn, pfn;
+
+ end_pfn = min(start_pfn + nr_pages,
+ zone_end_pfn(page_zone(pfn_to_page(start_pfn))));
/* Check the starting page of each pageblock within the range */
- for (; page < end_page; page = next_active_pageblock(page)) {
- if (!is_pageblock_removable_nolock(page))
+ for (pfn = start_pfn; pfn < end_pfn; pfn = next_active_pageblock(pfn)) {
+ if (!is_pageblock_removable_nolock(pfn))
return false;
cond_resched();
}
i++;
if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn)
continue;
+ /* Check if we got outside of the zone */
+ if (zone && !zone_spans_pfn(zone, pfn + i))
+ return 0;
page = pfn_to_page(pfn + i);
if (zone && page_zone(page) != zone)
return 0;
static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
{
unsigned long pfn;
- struct page *page;
+
for (pfn = start; pfn < end; pfn++) {
- if (pfn_valid(pfn)) {
- page = pfn_to_page(pfn);
- if (PageLRU(page))
- return pfn;
- if (__PageMovable(page))
- return pfn;
- if (PageHuge(page)) {
- if (hugepage_migration_supported(page_hstate(page)) &&
- page_huge_active(page))
- return pfn;
- else
- pfn = round_up(pfn + 1,
- 1 << compound_order(page)) - 1;
- }
- }
+ struct page *page, *head;
+ unsigned long skip;
+
+ if (!pfn_valid(pfn))
+ continue;
+ page = pfn_to_page(pfn);
+ if (PageLRU(page))
+ return pfn;
+ if (__PageMovable(page))
+ return pfn;
+
+ if (!PageHuge(page))
+ continue;
+ head = compound_head(page);
+ if (hugepage_migration_supported(page_hstate(head)) &&
+ page_huge_active(head))
+ return pfn;
+ skip = (1 << compound_order(head)) - (page - head);
+ pfn += skip - 1;
}
return 0;
}
pfn = page_to_pfn(compound_head(page))
+ hpage_nr_pages(page) - 1;
+ /*
+ * HWPoison pages have elevated reference counts so the migration would
+ * fail on them. It also doesn't make any sense to migrate them in the
+ * first place. Still try to unmap such a page in case it is still mapped
+ * (e.g. current hwpoison implementation doesn't unmap KSM pages but keep
+ * the unmap as the catch all safety net).
+ */
+ if (PageHWPoison(page)) {
+ if (WARN_ON(PageLRU(page)))
+ isolate_lru_page(page);
+ if (page_mapped(page))
+ try_to_unmap(page, TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS);
+ continue;
+ }
+
if (!get_page_unless_zero(page))
continue;
/*
return -EINVAL;
if (!IS_ALIGNED(end_pfn, pageblock_nr_pages))
return -EINVAL;
+
+ mem_hotplug_begin();
+
/* This makes hotplug much easier...and readable.
we assume this for now. .*/
- if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
+ if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start,
+ &valid_end)) {
+ mem_hotplug_done();
return -EINVAL;
+ }
zone = page_zone(pfn_to_page(valid_start));
node = zone_to_nid(zone);
/* set above range as isolated */
ret = start_isolate_page_range(start_pfn, end_pfn,
MIGRATE_MOVABLE, true);
- if (ret)
+ if (ret) {
+ mem_hotplug_done();
return ret;
+ }
arg.start_pfn = start_pfn;
arg.nr_pages = nr_pages;
writeback_set_ratelimit();
memory_notify(MEM_OFFLINE, &arg);
+ mem_hotplug_done();
return 0;
failed_removal:
memory_notify(MEM_CANCEL_OFFLINE, &arg);
/* pushback to free area */
undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
+ mem_hotplug_done();
return ret;
}
-/* Must be protected by mem_hotplug_begin() or a device_lock */
int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
{
return __offline_pages(start_pfn, start_pfn + nr_pages);
* and online/offline operations before this call, as required by
* try_offline_node().
*/
-void __ref remove_memory(int nid, u64 start, u64 size)
+void __ref __remove_memory(int nid, u64 start, u64 size)
{
int ret;
memblock_free(start, size);
memblock_remove(start, size);
- arch_remove_memory(start, size, NULL);
+ arch_remove_memory(nid, start, size, NULL);
try_offline_node(nid);
mem_hotplug_done();
}
+
+void remove_memory(int nid, u64 start, u64 size)
+{
+ lock_device_hotplug();
+ __remove_memory(nid, start, size);
+ unlock_device_hotplug();
+}
EXPORT_SYMBOL_GPL(remove_memory);
#endif /* CONFIG_MEMORY_HOTREMOVE */