mm/memory_hotplug: mark pageblocks MIGRATE_ISOLATE while onlining memory

Currently, it can happen that pages are allocated (and freed) via the
buddy before we finished basic memory onlining.

For example, pages are exposed to the buddy and can be allocated before we
actually mark the sections online.  Allocated pages could suddenly fail
pfn_to_online_page() checks.  We had similar issues with pcp handling,
when pages are allocated+freed before we reach zone_pcp_update() in
online_pages() [1].

Instead, mark all pageblocks MIGRATE_ISOLATE, such that allocations are
impossible.  Once done with the heavy lifting, use
undo_isolate_page_range() to move the pages to the MIGRATE_MOVABLE
freelist, marking them ready for allocation.  Similar to offline_pages(),
we have to manually adjust zone->nr_isolate_pageblock.

[1] https://lkml.kernel.org/r/[email protected]

Signed-off-by: David Hildenbrand <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Reviewed-by: Oscar Salvador <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Cc: Wei Yang <[email protected]>
Cc: Baoquan He <[email protected]>
Cc: Pankaj Gupta <[email protected]>
Cc: Charan Teja Reddy <[email protected]>
Cc: Dan Williams <[email protected]>
Cc: Fenghua Yu <[email protected]>
Cc: Logan Gunthorpe <[email protected]>
Cc: "Matthew Wilcox (Oracle)" <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Michel Lespinasse <[email protected]>
Cc: Mike Rapoport <[email protected]>
Cc: Tony Luck <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Linus Torvalds <[email protected]>

Author: davidhildenbrand

mm/Kconfig

@@ -152,6 +152,7 @@ config HAVE_BOOTMEM_INFO_NODE
 # eventually, we can have this option just 'select SPARSEMEM'
 config MEMORY_HOTPLUG
 	bool "Allow for memory hot-add"
+	select MEMORY_ISOLATION
 	depends on SPARSEMEM || X86_64_ACPI_NUMA
 	depends on ARCH_ENABLE_MEMORY_HOTPLUG
 	depends on 64BIT || BROKEN
@@ -178,7 +179,6 @@ config MEMORY_HOTPLUG_DEFAULT_ONLINE
 
 config MEMORY_HOTREMOVE
 	bool "Allow for memory hot remove"
-	select MEMORY_ISOLATION
 	select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
 	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
 	depends on MIGRATION

mm/memory_hotplug.c

@@ -813,7 +813,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 
 	/* associate pfn range with the zone */
 	zone = zone_for_pfn_range(online_type, nid, pfn, nr_pages);
-	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_MOVABLE);
+	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE);
 
 	arg.start_pfn = pfn;
 	arg.nr_pages = nr_pages;
@@ -824,6 +824,14 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 	if (ret)
 		goto failed_addition;
 
+	/*
+	 * Fixup the number of isolated pageblocks before marking the sections
+	 * onlining, such that undo_isolate_page_range() works correctly.
+	 */
+	spin_lock_irqsave(&zone->lock, flags);
+	zone->nr_isolate_pageblock += nr_pages / pageblock_nr_pages;
+	spin_unlock_irqrestore(&zone->lock, flags);
+
 	/*
 	 * If this zone is not populated, then it is not in zonelist.
 	 * This means the page allocator ignores this zone.
@@ -841,21 +849,25 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 	zone->zone_pgdat->node_present_pages += nr_pages;
 	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 
+	node_states_set_node(nid, &arg);
+	if (need_zonelists_rebuild)
+		build_all_zonelists(NULL);
+	zone_pcp_update(zone);
+
+	/* Basic onlining is complete, allow allocation of onlined pages. */
+	undo_isolate_page_range(pfn, pfn + nr_pages, MIGRATE_MOVABLE);
+
 	/*
 	 * 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.
+	 * are properly distributed across the whole freelist. Make sure to
+	 * shuffle once pageblocks are no longer isolated.
 	 */
 	shuffle_zone(zone);
 
-	node_states_set_node(nid, &arg);
-	if (need_zonelists_rebuild)
-		build_all_zonelists(NULL);
-	zone_pcp_update(zone);
-
 	init_per_zone_wmark_min();
 
 	kswapd_run(nid);
@@ -1577,9 +1589,9 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages)
 	pr_info("Offlined Pages %ld\n", nr_pages);
 
 	/*
-	 * Onlining will reset pagetype flags and makes migrate type
-	 * MOVABLE, so just need to decrease the number of isolated
-	 * pageblocks zone counter here.
+	 * The memory sections are marked offline, and the pageblock flags
+	 * effectively stale; nobody should be touching them. Fixup the number
+	 * of isolated pageblocks, memory onlining will properly revert this.
 	 */
 	spin_lock_irqsave(&zone->lock, flags);
 	zone->nr_isolate_pageblock -= nr_pages / pageblock_nr_pages;