1 files changed, 88 insertions, 119 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 38d94b703e9d..2b2b3ccbbfb5 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -33,7 +33,6 @@
 #include <linux/stop_machine.h>
 #include <linux/hugetlb.h>
 #include <linux/memblock.h>
-#include <linux/bootmem.h>
 #include <linux/compaction.h>
 
 #include <asm/tlbflush.h>
@@ -587,6 +586,7 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 	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;
@@ -687,62 +687,19 @@ static void node_states_check_changes_online(unsigned long nr_pages,
 	struct zone *zone, struct memory_notify *arg)
 {
 	int nid = zone_to_nid(zone);
-	enum zone_type zone_last = ZONE_NORMAL;
 
-	/*
-	 * If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY]
-	 * contains nodes which have zones of 0...ZONE_NORMAL,
-	 * set zone_last to ZONE_NORMAL.
-	 *
-	 * If we don't have HIGHMEM nor movable node,
-	 * node_states[N_NORMAL_MEMORY] contains nodes which have zones of
-	 * 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
-	 */
-	if (N_MEMORY == N_NORMAL_MEMORY)
-		zone_last = ZONE_MOVABLE;
+	arg->status_change_nid = -1;
+	arg->status_change_nid_normal = -1;
+	arg->status_change_nid_high = -1;
 
-	/*
-	 * if the memory to be online is in a zone of 0...zone_last, and
-	 * the zones of 0...zone_last don't have memory before online, we will
-	 * need to set the node to node_states[N_NORMAL_MEMORY] after
-	 * the memory is online.
-	 */
-	if (zone_idx(zone) <= zone_last && !node_state(nid, N_NORMAL_MEMORY))
+	if (!node_state(nid, N_MEMORY))
+		arg->status_change_nid = nid;
+	if (zone_idx(zone) <= ZONE_NORMAL && !node_state(nid, N_NORMAL_MEMORY))
 		arg->status_change_nid_normal = nid;
-	else
-		arg->status_change_nid_normal = -1;
-
 #ifdef CONFIG_HIGHMEM
-	/*
-	 * If we have movable node, node_states[N_HIGH_MEMORY]
-	 * contains nodes which have zones of 0...ZONE_HIGHMEM,
-	 * set zone_last to ZONE_HIGHMEM.
-	 *
-	 * If we don't have movable node, node_states[N_NORMAL_MEMORY]
-	 * contains nodes which have zones of 0...ZONE_MOVABLE,
-	 * set zone_last to ZONE_MOVABLE.
-	 */
-	zone_last = ZONE_HIGHMEM;
-	if (N_MEMORY == N_HIGH_MEMORY)
-		zone_last = ZONE_MOVABLE;
-
-	if (zone_idx(zone) <= zone_last && !node_state(nid, N_HIGH_MEMORY))
+	if (zone_idx(zone) <= N_HIGH_MEMORY && !node_state(nid, N_HIGH_MEMORY))
 		arg->status_change_nid_high = nid;
-	else
-		arg->status_change_nid_high = -1;
-#else
-	arg->status_change_nid_high = arg->status_change_nid_normal;
 #endif
-
-	/*
-	 * if the node don't have memory befor online, we will need to
-	 * set the node to node_states[N_MEMORY] after the memory
-	 * is online.
-	 */
-	if (!node_state(nid, N_MEMORY))
-		arg->status_change_nid = nid;
-	else
-		arg->status_change_nid = -1;
 }
 
 static void node_states_set_node(int node, struct memory_notify *arg)
@@ -753,7 +710,8 @@ static void node_states_set_node(int node, struct memory_notify *arg)
 	if (arg->status_change_nid_high >= 0)
 		node_set_state(node, N_HIGH_MEMORY);
 
-	node_set_state(node, N_MEMORY);
+	if (arg->status_change_nid >= 0)
+		node_set_state(node, N_MEMORY);
 }
 
 static void __meminit resize_zone_range(struct zone *zone, unsigned long start_pfn,
@@ -881,7 +839,6 @@ static struct zone * __meminit move_pfn_range(int online_type, int nid,
 	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;
@@ -893,6 +850,8 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	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.
@@ -957,6 +916,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 
 	if (onlined_pages)
 		memory_notify(MEM_ONLINE, &arg);
+	mem_hotplug_done();
 	return 0;
 
 failed_addition:
@@ -964,6 +924,7 @@ 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 */
@@ -1111,7 +1072,12 @@ static int online_memory_block(struct memory_block *mem, void *arg)
 	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;
@@ -1163,26 +1129,26 @@ int __ref add_memory_resource(int nid, struct resource *res, bool online)
 	/* 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;
@@ -1196,6 +1162,17 @@ int __ref add_memory(int nid, u64 start, u64 size)
 		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
@@ -1505,75 +1482,53 @@ static void node_states_check_changes_offline(unsigned long nr_pages,
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	unsigned long present_pages = 0;
-	enum zone_type zt, zone_last = ZONE_NORMAL;
+	enum zone_type zt;
 
-	/*
-	 * If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY]
-	 * contains nodes which have zones of 0...ZONE_NORMAL,
-	 * set zone_last to ZONE_NORMAL.
-	 *
-	 * If we don't have HIGHMEM nor movable node,
-	 * node_states[N_NORMAL_MEMORY] contains nodes which have zones of
-	 * 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
-	 */
-	if (N_MEMORY == N_NORMAL_MEMORY)
-		zone_last = ZONE_MOVABLE;
+	arg->status_change_nid = -1;
+	arg->status_change_nid_normal = -1;
+	arg->status_change_nid_high = -1;
 
 	/*
-	 * check whether node_states[N_NORMAL_MEMORY] will be changed.
-	 * If the memory to be offline is in a zone of 0...zone_last,
-	 * and it is the last present memory, 0...zone_last will
-	 * become empty after offline , thus we can determind we will
-	 * need to clear the node from node_states[N_NORMAL_MEMORY].
+	 * Check whether node_states[N_NORMAL_MEMORY] will be changed.
+	 * If the memory to be offline is within the range
+	 * [0..ZONE_NORMAL], and it is the last present memory there,
+	 * the zones in that range will become empty after the offlining,
+	 * thus we can determine that we need to clear the node from
+	 * node_states[N_NORMAL_MEMORY].
 	 */
-	for (zt = 0; zt <= zone_last; zt++)
+	for (zt = 0; zt <= ZONE_NORMAL; zt++)
 		present_pages += pgdat->node_zones[zt].present_pages;
-	if (zone_idx(zone) <= zone_last && nr_pages >= present_pages)
+	if (zone_idx(zone) <= ZONE_NORMAL && nr_pages >= present_pages)
 		arg->status_change_nid_normal = zone_to_nid(zone);
-	else
-		arg->status_change_nid_normal = -1;
 
 #ifdef CONFIG_HIGHMEM
 	/*
-	 * If we have movable node, node_states[N_HIGH_MEMORY]
-	 * contains nodes which have zones of 0...ZONE_HIGHMEM,
-	 * set zone_last to ZONE_HIGHMEM.
-	 *
-	 * If we don't have movable node, node_states[N_NORMAL_MEMORY]
-	 * contains nodes which have zones of 0...ZONE_MOVABLE,
-	 * set zone_last to ZONE_MOVABLE.
+	 * node_states[N_HIGH_MEMORY] contains nodes which
+	 * have normal memory or high memory.
+	 * Here we add the present_pages belonging to ZONE_HIGHMEM.
+	 * If the zone is within the range of [0..ZONE_HIGHMEM), and
+	 * we determine that the zones in that range become empty,
+	 * we need to clear the node for N_HIGH_MEMORY.
 	 */
-	zone_last = ZONE_HIGHMEM;
-	if (N_MEMORY == N_HIGH_MEMORY)
-		zone_last = ZONE_MOVABLE;
-
-	for (; zt <= zone_last; zt++)
-		present_pages += pgdat->node_zones[zt].present_pages;
-	if (zone_idx(zone) <= zone_last && nr_pages >= present_pages)
+	present_pages += pgdat->node_zones[ZONE_HIGHMEM].present_pages;
+	if (zone_idx(zone) <= ZONE_HIGHMEM && nr_pages >= present_pages)
 		arg->status_change_nid_high = zone_to_nid(zone);
-	else
-		arg->status_change_nid_high = -1;
-#else
-	arg->status_change_nid_high = arg->status_change_nid_normal;
 #endif
 
 	/*
-	 * node_states[N_HIGH_MEMORY] contains nodes which have 0...ZONE_MOVABLE
+	 * We have accounted the pages from [0..ZONE_NORMAL), and
+	 * in case of CONFIG_HIGHMEM the pages from ZONE_HIGHMEM
+	 * as well.
+	 * Here we count the possible pages from ZONE_MOVABLE.
+	 * If after having accounted all the pages, we see that the nr_pages
+	 * to be offlined is over or equal to the accounted pages,
+	 * we know that the node will become empty, and so, we can clear
+	 * it for N_MEMORY as well.
 	 */
-	zone_last = ZONE_MOVABLE;
+	present_pages += pgdat->node_zones[ZONE_MOVABLE].present_pages;
 
-	/*
-	 * check whether node_states[N_HIGH_MEMORY] will be changed
-	 * If we try to offline the last present @nr_pages from the node,
-	 * we can determind we will need to clear the node from
-	 * node_states[N_HIGH_MEMORY].
-	 */
-	for (; zt <= zone_last; zt++)
-		present_pages += pgdat->node_zones[zt].present_pages;
 	if (nr_pages >= present_pages)
 		arg->status_change_nid = zone_to_nid(zone);
-	else
-		arg->status_change_nid = -1;
 }
 
 static void node_states_clear_node(int node, struct memory_notify *arg)
@@ -1581,12 +1536,10 @@ static void node_states_clear_node(int node, struct memory_notify *arg)
 	if (arg->status_change_nid_normal >= 0)
 		node_clear_state(node, N_NORMAL_MEMORY);
 
-	if ((N_MEMORY != N_NORMAL_MEMORY) &&
-	    (arg->status_change_nid_high >= 0))
+	if (arg->status_change_nid_high >= 0)
 		node_clear_state(node, N_HIGH_MEMORY);
 
-	if ((N_MEMORY != N_HIGH_MEMORY) &&
-	    (arg->status_change_nid >= 0))
+	if (arg->status_change_nid >= 0)
 		node_clear_state(node, N_MEMORY);
 }
 
@@ -1606,10 +1559,16 @@ static int __ref __offline_pages(unsigned long start_pfn,
 		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);
@@ -1618,8 +1577,10 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	/* 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;
@@ -1690,6 +1651,7 @@ repeat:
 	writeback_set_ratelimit();
 
 	memory_notify(MEM_OFFLINE, &arg);
+	mem_hotplug_done();
 	return 0;
 
 failed_removal:
@@ -1699,10 +1661,10 @@ 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);
@@ -1873,7 +1835,7 @@ EXPORT_SYMBOL(try_offline_node);
  * 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;
 
@@ -1902,5 +1864,12 @@ void __ref remove_memory(int nid, u64 start, u64 size)
 
 	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 */