1 files changed, 55 insertions, 77 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b236069ff0d8..328878b6799d 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -39,6 +39,7 @@
 #include <asm/tlbflush.h>
 
 #include "internal.h"
+#include "shuffle.h"
 
 /*
  * online_page_callback contains pointer to current page onlining function.
@@ -273,12 +274,12 @@ static int __meminit __add_section(int nid, unsigned long phys_start_pfn,
  * add the new pages.
  */
 int __ref __add_pages(int nid, unsigned long phys_start_pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap,
-		bool want_memblock)
+		unsigned long nr_pages, struct mhp_restrictions *restrictions)
 {
 	unsigned long i;
 	int err = 0;
 	int start_sec, end_sec;
+	struct vmem_altmap *altmap = restrictions->altmap;
 
 	/* during initialize mem_map, align hot-added range to section */
 	start_sec = pfn_to_section_nr(phys_start_pfn);
@@ -299,7 +300,7 @@ int __ref __add_pages(int nid, unsigned long phys_start_pfn,
 
 	for (i = start_sec; i <= end_sec; i++) {
 		err = __add_section(nid, section_nr_to_pfn(i), altmap,
-				want_memblock);
+				restrictions->flags & MHP_MEMBLOCK_API);
 
 		/*
 		 * EEXIST is finally dealt with by ioresource collision
@@ -516,26 +517,23 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn)
 	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 }
 
-static int __remove_section(struct zone *zone, struct mem_section *ms,
-		unsigned long map_offset, struct vmem_altmap *altmap)
+static void __remove_section(struct zone *zone, struct mem_section *ms,
+			     unsigned long map_offset,
+			     struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn;
 	int scn_nr;
-	int ret = -EINVAL;
 
-	if (!valid_section(ms))
-		return ret;
+	if (WARN_ON_ONCE(!valid_section(ms)))
+		return;
 
-	ret = unregister_memory_section(ms);
-	if (ret)
-		return ret;
+	unregister_memory_section(ms);
 
 	scn_nr = __section_nr(ms);
 	start_pfn = section_nr_to_pfn((unsigned long)scn_nr);
 	__remove_zone(zone, start_pfn);
 
 	sparse_remove_one_section(zone, ms, map_offset, altmap);
-	return 0;
 }
 
 /**
@@ -550,31 +548,17 @@ static int __remove_section(struct zone *zone, struct mem_section *ms,
  * sure that pages are marked reserved and zones are adjust properly by
  * calling offline_pages().
  */
-int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
-		 unsigned long nr_pages, struct vmem_altmap *altmap)
+void __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
+		    unsigned long nr_pages, struct vmem_altmap *altmap)
 {
 	unsigned long i;
 	unsigned long map_offset = 0;
-	int sections_to_remove, ret = 0;
+	int sections_to_remove;
 
 	/* In the ZONE_DEVICE case device driver owns the memory region */
 	if (is_dev_zone(zone)) {
 		if (altmap)
 			map_offset = vmem_altmap_offset(altmap);
-	} else {
-		resource_size_t start, size;
-
-		start = phys_start_pfn << PAGE_SHIFT;
-		size = nr_pages * PAGE_SIZE;
-
-		ret = release_mem_region_adjustable(&iomem_resource, start,
-					size);
-		if (ret) {
-			resource_size_t endres = start + size - 1;
-
-			pr_warn("Unable to release resource <%pa-%pa> (%d)\n",
-					&start, &endres, ret);
-		}
 	}
 
 	clear_zone_contiguous(zone);
@@ -590,16 +574,12 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 		unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
 
 		cond_resched();
-		ret = __remove_section(zone, __pfn_to_section(pfn), map_offset,
-				altmap);
+		__remove_section(zone, __pfn_to_section(pfn), map_offset,
+				 altmap);
 		map_offset = 0;
-		if (ret)
-			break;
 	}
 
 	set_zone_contiguous(zone);
-
-	return ret;
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
@@ -714,7 +694,7 @@ static void node_states_check_changes_online(unsigned long nr_pages,
 	if (zone_idx(zone) <= ZONE_NORMAL && !node_state(nid, N_NORMAL_MEMORY))
 		arg->status_change_nid_normal = nid;
 #ifdef CONFIG_HIGHMEM
-	if (zone_idx(zone) <= N_HIGH_MEMORY && !node_state(nid, N_HIGH_MEMORY))
+	if (zone_idx(zone) <= ZONE_HIGHMEM && !node_state(nid, N_HIGH_MEMORY))
 		arg->status_change_nid_high = nid;
 #endif
 }
@@ -912,6 +892,8 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	zone->zone_pgdat->node_present_pages += onlined_pages;
 	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 
+	shuffle_zone(zone);
+
 	if (onlined_pages) {
 		node_states_set_node(nid, &arg);
 		if (need_zonelists_rebuild)
@@ -1097,6 +1079,9 @@ static int online_memory_block(struct memory_block *mem, void *arg)
  */
 int __ref add_memory_resource(int nid, struct resource *res)
 {
+	struct mhp_restrictions restrictions = {
+		.flags = MHP_MEMBLOCK_API,
+	};
 	u64 start, size;
 	bool new_node = false;
 	int ret;
@@ -1124,7 +1109,7 @@ int __ref add_memory_resource(int nid, struct resource *res)
 	new_node = ret;
 
 	/* call arch's memory hotadd */
-	ret = arch_add_memory(nid, start, size, NULL, true);
+	ret = arch_add_memory(nid, start, size, &restrictions);
 	if (ret < 0)
 		goto error;
 
@@ -1341,8 +1326,7 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
 		if (!PageHuge(page))
 			continue;
 		head = compound_head(page);
-		if (hugepage_migration_supported(page_hstate(head)) &&
-		    page_huge_active(head))
+		if (page_huge_active(head))
 			return pfn;
 		skip = (1 << compound_order(head)) - (page - head);
 		pfn += skip - 1;
@@ -1382,10 +1366,6 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 
 		if (PageHuge(page)) {
 			struct page *head = compound_head(page);
-			if (compound_order(head) > PFN_SECTION_SHIFT) {
-				ret = -EBUSY;
-				break;
-			}
 			pfn = page_to_pfn(head) + (1<<compound_order(head)) - 1;
 			isolate_huge_page(head, &source);
 			continue;
@@ -1454,15 +1434,10 @@ static int
 offline_isolated_pages_cb(unsigned long start, unsigned long nr_pages,
 			void *data)
 {
-	__offline_isolated_pages(start, start + nr_pages);
-	return 0;
-}
+	unsigned long *offlined_pages = (unsigned long *)data;
 
-static void
-offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
-{
-	walk_system_ram_range(start_pfn, end_pfn - start_pfn, NULL,
-				offline_isolated_pages_cb);
+	*offlined_pages += __offline_isolated_pages(start, start + nr_pages);
+	return 0;
 }
 
 /*
@@ -1472,26 +1447,7 @@ static int
 check_pages_isolated_cb(unsigned long start_pfn, unsigned long nr_pages,
 			void *data)
 {
-	int ret;
-	long offlined = *(long *)data;
-	ret = test_pages_isolated(start_pfn, start_pfn + nr_pages, true);
-	offlined = nr_pages;
-	if (!ret)
-		*(long *)data += offlined;
-	return ret;
-}
-
-static long
-check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
-{
-	long offlined = 0;
-	int ret;
-
-	ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn, &offlined,
-			check_pages_isolated_cb);
-	if (ret < 0)
-		offlined = (long)ret;
-	return offlined;
+	return test_pages_isolated(start_pfn, start_pfn + nr_pages, true);
 }
 
 static int __init cmdline_parse_movable_node(char *p)
@@ -1576,7 +1532,7 @@ static int __ref __offline_pages(unsigned long start_pfn,
 		  unsigned long end_pfn)
 {
 	unsigned long pfn, nr_pages;
-	long offlined_pages;
+	unsigned long offlined_pages = 0;
 	int ret, node, nr_isolate_pageblock;
 	unsigned long flags;
 	unsigned long valid_start, valid_end;
@@ -1652,14 +1608,15 @@ static int __ref __offline_pages(unsigned long start_pfn,
 			goto failed_removal_isolated;
 		}
 		/* check again */
-		offlined_pages = check_pages_isolated(start_pfn, end_pfn);
-	} while (offlined_pages < 0);
+		ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn,
+					    NULL, check_pages_isolated_cb);
+	} while (ret);
 
-	pr_info("Offlined Pages %ld\n", offlined_pages);
 	/* Ok, all of our target is isolated.
 	   We cannot do rollback at this point. */
-	offline_isolated_pages(start_pfn, end_pfn);
-
+	walk_system_ram_range(start_pfn, end_pfn - start_pfn,
+			      &offlined_pages, offline_isolated_pages_cb);
+	pr_info("Offlined Pages %ld\n", offlined_pages);
 	/*
 	 * Onlining will reset pagetype flags and makes migrate type
 	 * MOVABLE, so just need to decrease the number of isolated
@@ -1843,6 +1800,26 @@ void try_offline_node(int nid)
 }
 EXPORT_SYMBOL(try_offline_node);
 
+static void __release_memory_resource(resource_size_t start,
+				      resource_size_t size)
+{
+	int ret;
+
+	/*
+	 * When removing memory in the same granularity as it was added,
+	 * this function never fails. It might only fail if resources
+	 * have to be adjusted or split. We'll ignore the error, as
+	 * removing of memory cannot fail.
+	 */
+	ret = release_mem_region_adjustable(&iomem_resource, start, size);
+	if (ret) {
+		resource_size_t endres = start + size - 1;
+
+		pr_warn("Unable to release resource <%pa-%pa> (%d)\n",
+			&start, &endres, ret);
+	}
+}
+
 /**
  * remove_memory
  * @nid: the node ID
@@ -1877,6 +1854,7 @@ void __ref __remove_memory(int nid, u64 start, u64 size)
 	memblock_remove(start, size);
 
 	arch_remove_memory(nid, start, size, NULL);
+	__release_memory_resource(start, size);
 
 	try_offline_node(nid);