diff --git a/mm/Kconfig b/mm/Kconfig
index 3af64646f343de2c559b20f5e65b3be5a72727df..e3490ecac839db0d9fcad94165887253ab06a570 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -747,13 +747,13 @@ config DEFERRED_STRUCT_PAGE_INIT
 	depends on SPARSEMEM
 	depends on !NEED_PER_CPU_KM
 	depends on 64BIT
+	select PADATA
 	help
 	  Ordinarily all struct pages are initialised during early boot in a
 	  single thread. On very large machines this can take a considerable
 	  amount of time. If this option is set, large machines will bring up
-	  a subset of memmap at boot and then initialise the rest in parallel
-	  by starting one-off "pgdatinitX" kernel thread for each node X. This
-	  has a potential performance impact on processes running early in the
+	  a subset of memmap at boot and then initialise the rest in parallel.
+	  This has a potential performance impact on tasks running early in the
 	  lifetime of the system until these kthreads finish the
 	  initialisation.
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 89bd57241e08e5bcb6067010358aebf419522acf..27ec5dc4db33676bb34d93ee2d97c10d100959e0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -68,6 +68,7 @@
 #include <linux/lockdep.h>
 #include <linux/nmi.h>
 #include <linux/psi.h>
+#include <linux/padata.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -1815,6 +1816,26 @@ deferred_init_maxorder(u64 *i, struct zone *zone, unsigned long *start_pfn,
 	return nr_pages;
 }
 
+static void __init
+deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
+			   void *arg)
+{
+	unsigned long spfn, epfn;
+	struct zone *zone = arg;
+	u64 i;
+
+	deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, start_pfn);
+
+	/*
+	 * Initialize and free pages in MAX_ORDER sized increments so that we
+	 * can avoid introducing any issues with the buddy allocator.
+	 */
+	while (spfn < end_pfn) {
+		deferred_init_maxorder(&i, zone, &spfn, &epfn);
+		cond_resched();
+	}
+}
+
 /* Initialise remaining memory on a node */
 static int __init deferred_init_memmap(void *data)
 {
@@ -1824,7 +1845,7 @@ static int __init deferred_init_memmap(void *data)
 	unsigned long first_init_pfn, flags;
 	unsigned long start = jiffies;
 	struct zone *zone;
-	int zid;
+	int zid, max_threads;
 	u64 i;
 
 	/* Bind memory initialisation thread to a local node if possible */
@@ -1864,13 +1885,26 @@ static int __init deferred_init_memmap(void *data)
 		goto zone_empty;
 
 	/*
-	 * Initialize and free pages in MAX_ORDER sized increments so
-	 * that we can avoid introducing any issues with the buddy
-	 * allocator.
+	 * More CPUs always led to greater speedups on tested systems, up to
+	 * all the nodes' CPUs.  Use all since the system is otherwise idle now.
 	 */
+	max_threads = max(cpumask_weight(cpumask), 1u);
+
 	while (spfn < epfn) {
-		deferred_init_maxorder(&i, zone, &spfn, &epfn);
-		cond_resched();
+		unsigned long epfn_align = ALIGN(epfn, PAGES_PER_SECTION);
+		struct padata_mt_job job = {
+			.thread_fn   = deferred_init_memmap_chunk,
+			.fn_arg      = zone,
+			.start       = spfn,
+			.size        = epfn_align - spfn,
+			.align       = PAGES_PER_SECTION,
+			.min_chunk   = PAGES_PER_SECTION,
+			.max_threads = max_threads,
+		};
+
+		padata_do_multithreaded(&job);
+		deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
+						    epfn_align);
 	}
 zone_empty:
 	/* Sanity check that the next zone really is unpopulated */