u64 max_mem_size = U64_MAX;
/* add this memory to iomem resource */
-static struct resource *register_memory_resource(u64 start, u64 size)
+static struct resource *register_memory_resource(u64 start, u64 size,
+ const char *resource_name)
{
struct resource *res;
unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
- char *resource_name = "System RAM";
+
+ if (strcmp(resource_name, "System RAM"))
+ flags |= IORESOURCE_MEM_DRIVER_MANAGED;
/*
* Make sure value parsed from 'mem=' only restricts memory adding
unsigned long start_pfn,
unsigned long nr_pages)
{
+ const unsigned long end_pfn = start_pfn + nr_pages;
struct pglist_data *pgdat = zone->zone_pgdat;
- unsigned long flags;
+ unsigned long pfn, cur_nr_pages, flags;
/* Poison struct pages because they are now uninitialized again. */
- page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages);
+ for (pfn = start_pfn; pfn < end_pfn; pfn += cur_nr_pages) {
+ cond_resched();
+
+ /* Select all remaining pages up to the next section boundary */
+ cur_nr_pages =
+ min(end_pfn - pfn, SECTION_ALIGN_UP(pfn + 1) - pfn);
+ page_init_poison(pfn_to_page(pfn),
+ sizeof(struct page) * cur_nr_pages);
+ }
#ifdef CONFIG_ZONE_DEVICE
/*
zone->zone_pgdat->node_present_pages += onlined_pages;
pgdat_resize_unlock(zone->zone_pgdat, &flags);
+ /*
+ * When exposing larger, physically contiguous memory areas to the
+ * buddy, shuffling in the buddy (when freeing onlined pages, putting
+ * them either to the head or the tail of the freelist) is only helpful
+ * for maintaining the shuffle, but not for creating the initial
+ * shuffle. Shuffle the whole zone to make sure the just onlined pages
+ * are properly distributed across the whole freelist.
+ */
shuffle_zone(zone);
node_states_set_node(nid, &arg);
kswapd_run(nid);
kcompactd_run(nid);
- vm_total_pages = nr_free_pagecache_pages();
-
writeback_set_ratelimit();
memory_notify(MEM_ONLINE, &arg);
}
/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
-static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
+static pg_data_t __ref *hotadd_new_pgdat(int nid)
{
struct pglist_data *pgdat;
- unsigned long start_pfn = PFN_DOWN(start);
pgdat = NODE_DATA(nid);
if (!pgdat) {
} else {
int cpu;
/*
- * Reset the nr_zones, order and classzone_idx before reuse.
- * Note that kswapd will init kswapd_classzone_idx properly
+ * Reset the nr_zones, order and highest_zoneidx before reuse.
+ * Note that kswapd will init kswapd_highest_zoneidx properly
* when it starts in the near future.
*/
pgdat->nr_zones = 0;
pgdat->kswapd_order = 0;
- pgdat->kswapd_classzone_idx = 0;
+ pgdat->kswapd_highest_zoneidx = 0;
for_each_online_cpu(cpu) {
struct per_cpu_nodestat *p;
}
/* we can use NODE_DATA(nid) from here */
-
pgdat->node_id = nid;
- pgdat->node_start_pfn = start_pfn;
+ pgdat->node_start_pfn = 0;
/* init node's zones as empty zones, we don't have any present pages.*/
free_area_init_core_hotplug(nid);
/**
* try_online_node - online a node if offlined
* @nid: the node ID
- * @start: start addr of the node
* @set_node_online: Whether we want to online the node
* called by cpu_up() to online a node without onlined memory.
*
* 0 -> the node is already online
* -ENOMEM -> the node could not be allocated
*/
-static int __try_online_node(int nid, u64 start, bool set_node_online)
+static int __try_online_node(int nid, bool set_node_online)
{
pg_data_t *pgdat;
int ret = 1;
if (node_online(nid))
return 0;
- pgdat = hotadd_new_pgdat(nid, start);
+ pgdat = hotadd_new_pgdat(nid);
if (!pgdat) {
pr_err("Cannot online node %d due to NULL pgdat\n", nid);
ret = -ENOMEM;
int ret;
mem_hotplug_begin();
- ret = __try_online_node(nid, 0, true);
+ ret = __try_online_node(nid, true);
mem_hotplug_done();
return ret;
}
if (ret)
return ret;
+ if (!node_possible(nid)) {
+ WARN(1, "node %d was absent from the node_possible_map\n", nid);
+ return -EINVAL;
+ }
+
mem_hotplug_begin();
- /*
- * Add new range to memblock so that when hotadd_new_pgdat() is called
- * to allocate new pgdat, get_pfn_range_for_nid() will be able to find
- * this new range and calculate total pages correctly. The range will
- * be removed at hot-remove time.
- */
- memblock_add_node(start, size, nid);
+ if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
+ memblock_add_node(start, size, nid);
- ret = __try_online_node(nid, start, false);
+ ret = __try_online_node(nid, false);
if (ret < 0)
goto error;
new_node = ret;
BUG_ON(ret);
/* create new memmap entry */
- firmware_map_add_hotplug(start, start + size, "System RAM");
+ if (!strcmp(res->name, "System RAM"))
+ firmware_map_add_hotplug(start, start + size, "System RAM");
/* device_online() will take the lock when calling online_pages() */
mem_hotplug_done();
/* rollback pgdat allocation and others */
if (new_node)
rollback_node_hotadd(nid);
- memblock_remove(start, size);
+ if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
+ memblock_remove(start, size);
mem_hotplug_done();
return ret;
}
struct resource *res;
int ret;
- res = register_memory_resource(start, size);
+ res = register_memory_resource(start, size, "System RAM");
if (IS_ERR(res))
return PTR_ERR(res);
}
EXPORT_SYMBOL_GPL(add_memory);
-#ifdef CONFIG_MEMORY_HOTREMOVE
/*
- * A free page on the buddy free lists (not the per-cpu lists) has PageBuddy
- * set and the size of the free page is given by page_order(). Using this,
- * the function determines if the pageblock contains only free pages.
- * Due to buddy contraints, a free page at least the size of a pageblock will
- * be located at the start of the pageblock
+ * Add special, driver-managed memory to the system as system RAM. Such
+ * memory is not exposed via the raw firmware-provided memmap as system
+ * RAM, instead, it is detected and added by a driver - during cold boot,
+ * after a reboot, and after kexec.
+ *
+ * Reasons why this memory should not be used for the initial memmap of a
+ * kexec kernel or for placing kexec images:
+ * - The booting kernel is in charge of determining how this memory will be
+ * used (e.g., use persistent memory as system RAM)
+ * - Coordination with a hypervisor is required before this memory
+ * can be used (e.g., inaccessible parts).
+ *
+ * For this memory, no entries in /sys/firmware/memmap ("raw firmware-provided
+ * memory map") are created. Also, the created memory resource is flagged
+ * with IORESOURCE_MEM_DRIVER_MANAGED, so in-kernel users can special-case
+ * this memory as well (esp., not place kexec images onto it).
+ *
+ * The resource_name (visible via /proc/iomem) has to have the format
+ * "System RAM ($DRIVER)".
*/
-static inline int pageblock_free(struct page *page)
+int add_memory_driver_managed(int nid, u64 start, u64 size,
+ const char *resource_name)
{
- return PageBuddy(page) && page_order(page) >= pageblock_order;
-}
+ struct resource *res;
+ int rc;
-/* 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);
+ if (!resource_name ||
+ strstr(resource_name, "System RAM (") != resource_name ||
+ resource_name[strlen(resource_name) - 1] != ')')
+ return -EINVAL;
- /* Ensure the starting page is pageblock-aligned */
- BUG_ON(pfn & (pageblock_nr_pages - 1));
+ lock_device_hotplug();
- /* If the entire pageblock is free, move to the end of free page */
- if (pageblock_free(page)) {
- int order;
- /* be careful. we don't have locks, page_order can be changed.*/
- order = page_order(page);
- if ((order < MAX_ORDER) && (order >= pageblock_order))
- return pfn + (1 << order);
+ res = register_memory_resource(start, size, resource_name);
+ if (IS_ERR(res)) {
+ rc = PTR_ERR(res);
+ goto out_unlock;
}
- return pfn + pageblock_nr_pages;
-}
-
-static bool is_pageblock_removable_nolock(unsigned long pfn)
-{
- struct page *page = pfn_to_page(pfn);
- struct zone *zone;
-
- /*
- * We have to be careful here because we are iterating over memory
- * sections which are not zone aware so we might end up outside of
- * the zone but still within the section.
- * We have to take care about the node as well. If the node is offline
- * its NODE_DATA will be NULL - see page_zone.
- */
- if (!node_online(page_to_nid(page)))
- return false;
-
- zone = page_zone(page);
- pfn = page_to_pfn(page);
- if (!zone_spans_pfn(zone, pfn))
- return false;
-
- return !has_unmovable_pages(zone, page, MIGRATE_MOVABLE,
- MEMORY_OFFLINE);
-}
-
-/* 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)
-{
- 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 (pfn = start_pfn; pfn < end_pfn; pfn = next_active_pageblock(pfn)) {
- if (!is_pageblock_removable_nolock(pfn))
- return false;
- cond_resched();
- }
+ rc = add_memory_resource(nid, res);
+ if (rc < 0)
+ release_memory_resource(res);
- /* All pageblocks in the memory block are likely to be hot-removable */
- return true;
+out_unlock:
+ unlock_device_hotplug();
+ return rc;
}
+EXPORT_SYMBOL_GPL(add_memory_driver_managed);
+#ifdef CONFIG_MEMORY_HOTREMOVE
/*
* Confirm all pages in a range [start, end) belong to the same zone (skipping
* memory holes). When true, return the zone.
/*
* Scan pfn range [start,end) to find movable/migratable pages (LRU pages,
- * non-lru movable pages and hugepages). We scan pfn because it's much
- * easier than scanning over linked list. This function returns the pfn
- * of the first found movable page if it's found, otherwise 0.
+ * non-lru movable pages and hugepages). Will skip over most unmovable
+ * pages (esp., pages that can be skipped when offlining), but bail out on
+ * definitely unmovable pages.
+ *
+ * Returns:
+ * 0 in case a movable page is found and movable_pfn was updated.
+ * -ENOENT in case no movable page was found.
+ * -EBUSY in case a definitely unmovable page was found.
*/
-static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
+static int scan_movable_pages(unsigned long start, unsigned long end,
+ unsigned long *movable_pfn)
{
unsigned long pfn;
continue;
page = pfn_to_page(pfn);
if (PageLRU(page))
- return pfn;
+ goto found;
if (__PageMovable(page))
- return pfn;
+ goto found;
+
+ /*
+ * PageOffline() pages that are not marked __PageMovable() and
+ * have a reference count > 0 (after MEM_GOING_OFFLINE) are
+ * definitely unmovable. If their reference count would be 0,
+ * they could at least be skipped when offlining memory.
+ */
+ if (PageOffline(page) && page_count(page))
+ return -EBUSY;
if (!PageHuge(page))
continue;
head = compound_head(page);
if (page_huge_active(head))
- return pfn;
+ goto found;
skip = compound_nr(head) - (page - head);
pfn += skip - 1;
}
+ return -ENOENT;
+found:
+ *movable_pfn = pfn;
return 0;
}
}
/*
- * Check all pages in range, recoreded as memory resource, are isolated.
+ * Check all pages in range, recorded as memory resource, are isolated.
*/
static int
check_pages_isolated_cb(unsigned long start_pfn, unsigned long nr_pages,
static int __init cmdline_parse_movable_node(char *p)
{
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
movable_node_enabled = true;
-#else
- pr_warn("movable_node parameter depends on CONFIG_HAVE_MEMBLOCK_NODE_MAP to work properly\n");
-#endif
return 0;
}
early_param("movable_node", cmdline_parse_movable_node);
}
do {
- for (pfn = start_pfn; pfn;) {
+ pfn = start_pfn;
+ do {
if (signal_pending(current)) {
ret = -EINTR;
reason = "signal backoff";
cond_resched();
lru_add_drain_all();
- pfn = scan_movable_pages(pfn, end_pfn);
- if (pfn) {
+ ret = scan_movable_pages(pfn, end_pfn, &pfn);
+ if (!ret) {
/*
* TODO: fatal migration failures should bail
* out
*/
do_migrate_range(pfn, end_pfn);
}
+ } while (!ret);
+
+ if (ret != -ENOENT) {
+ reason = "unmovable page";
+ goto failed_removal_isolated;
}
/*
kcompactd_stop(node);
}
- vm_total_pages = nr_free_pagecache_pages();
writeback_set_ratelimit();
memory_notify(MEM_OFFLINE, &arg);
mem_hotplug_begin();
arch_remove_memory(nid, start, size, NULL);
- memblock_free(start, size);
- memblock_remove(start, size);
+
+ if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) {
+ memblock_free(start, size);
+ memblock_remove(start, size);
+ }
+
__release_memory_resource(start, size);
try_offline_node(nid);
return rc;
}
EXPORT_SYMBOL_GPL(remove_memory);
+
+/*
+ * Try to offline and remove a memory block. Might take a long time to
+ * finish in case memory is still in use. Primarily useful for memory devices
+ * that logically unplugged all memory (so it's no longer in use) and want to
+ * offline + remove the memory block.
+ */
+int offline_and_remove_memory(int nid, u64 start, u64 size)
+{
+ struct memory_block *mem;
+ int rc = -EINVAL;
+
+ if (!IS_ALIGNED(start, memory_block_size_bytes()) ||
+ size != memory_block_size_bytes())
+ return rc;
+
+ lock_device_hotplug();
+ mem = find_memory_block(__pfn_to_section(PFN_DOWN(start)));
+ if (mem)
+ rc = device_offline(&mem->dev);
+ /* Ignore if the device is already offline. */
+ if (rc > 0)
+ rc = 0;
+
+ /*
+ * In case we succeeded to offline the memory block, remove it.
+ * This cannot fail as it cannot get onlined in the meantime.
+ */
+ if (!rc) {
+ rc = try_remove_memory(nid, start, size);
+ WARN_ON_ONCE(rc);
+ }
+ unlock_device_hotplug();
+
+ return rc;
+}
+EXPORT_SYMBOL_GPL(offline_and_remove_memory);
#endif /* CONFIG_MEMORY_HOTREMOVE */