[PATCH v3 2/3] mm: hugetlb: add hugetlb_alloc_threads cmdline option

[Thomas Prescher via B4 Relay <devnull+thomas.prescher.cyberus-technology.de@kernel.org>]

From: Thomas Prescher <thomas.prescher@cyberus-technology.de>

Add a command line option that enables control of how many
threads should be used to allocate huge pages.

Signed-off-by: Thomas Prescher <thomas.prescher@cyberus-technology.de>
---
 Documentation/admin-guide/kernel-parameters.txt |  9 +++++++
 Documentation/admin-guide/mm/hugetlbpage.rst    | 10 ++++++++
 mm/hugetlb.c                                    | 31 +++++++++++++++++++++----
 3 files changed, 46 insertions(+), 4 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index fb8752b42ec8582b8750d7e014c4d76166fa2fc1..1937ee02c1f883ecd910bab33cdb9194bddbd9b1 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1882,6 +1882,15 @@
 			Documentation/admin-guide/mm/hugetlbpage.rst.
 			Format: size[KMG]
 
+	hugepage_alloc_threads=
+			[HW] The number of threads that should be used to
+			allocate hugepages during boot. This option can be
+			used to improve system bootup time when allocating
+			a large amount of huge pages.
+			The default value is 25% of the available hardware threads.
+
+			Note that this parameter only applies to non-gigantic huge pages.
+
 	hugetlb_cma=	[HW,CMA,EARLY] The size of a CMA area used for allocation
 			of gigantic hugepages. Or using node format, the size
 			of a CMA area per node can be specified.
diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst
index f34a0d798d5b533f30add99a34f66ba4e1c496a3..67a941903fd2231e6c082cffb4c9179ee094b208 100644
--- a/Documentation/admin-guide/mm/hugetlbpage.rst
+++ b/Documentation/admin-guide/mm/hugetlbpage.rst
@@ -145,7 +145,17 @@ hugepages
 
 	It will allocate 1 2M hugepage on node0 and 2 2M hugepages on node1.
 	If the node number is invalid,  the parameter will be ignored.
+hugepage_alloc_threads
+	Specify the number of threads that should be used to allocate hugepages
+	during boot. This parameter can be used to improve system bootup time
+	when allocating a large amount of huge pages.
 
+	The default value is 25% of the available hardware threads.
+	Example to use 8 allocation threads::
+
+		hugepage_alloc_threads=8
+
+	Note that this parameter only applies to non-gigantic huge pages.
 default_hugepagesz
 	Specify the default huge page size.  This parameter can
 	only be specified once on the command line.  default_hugepagesz can
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e9b1b3e2b9d467f067d54359e1401a03f9926108..98dbfa18bee01d01b40cc7c650cd3eca5eae2457 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -70,6 +70,7 @@ static unsigned long __initdata default_hstate_max_huge_pages;
 static bool __initdata parsed_valid_hugepagesz = true;
 static bool __initdata parsed_default_hugepagesz;
 static unsigned int default_hugepages_in_node[MAX_NUMNODES] __initdata;
+static unsigned long hugepage_allocation_threads __initdata;
 
 /*
  * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages,
@@ -3429,8 +3430,6 @@ static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h)
 		.numa_aware	= true
 	};
 
-	unsigned int num_allocation_threads = max(num_online_cpus() / 4, 1);
-
 	job.thread_fn	= hugetlb_pages_alloc_boot_node;
 	job.start	= 0;
 	job.size	= h->max_huge_pages;
@@ -3451,9 +3450,13 @@ static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h)
 	 * | cascade lake 192 cpus |   39s |   20s |   11s |   10s |    9s |
 	 * +-----------------------+-------+-------+-------+-------+-------+
 	 */
+	if (hugepage_allocation_threads == 0) {
+		hugepage_allocation_threads = num_online_cpus() / 4;
+		hugepage_allocation_threads = max(hugepage_allocation_threads, 1);
+	}
 
-	job.max_threads	= num_allocation_threads;
-	job.min_chunk	= h->max_huge_pages / num_allocation_threads;
+	job.max_threads	= hugepage_allocation_threads;
+	job.min_chunk	= h->max_huge_pages / hugepage_allocation_threads;
 	padata_do_multithreaded(&job);
 
 	return h->nr_huge_pages;
@@ -4766,6 +4769,26 @@ static int __init default_hugepagesz_setup(char *s)
 }
 __setup("default_hugepagesz=", default_hugepagesz_setup);
 
+/* hugepage_alloc_threads command line parsing
+ * When set, use this specific number of threads for the boot
+ * allocation of hugepages.
+ */
+static int __init hugepage_alloc_threads_setup(char *s)
+{
+	unsigned long allocation_threads;
+
+	if (kstrtoul(s, 0, &allocation_threads) != 0)
+		return 1;
+
+	if (allocation_threads == 0)
+		return 1;
+
+	hugepage_allocation_threads = allocation_threads;
+
+	return 1;
+}
+__setup("hugepage_alloc_threads=", hugepage_alloc_threads_setup);
+
 static unsigned int allowed_mems_nr(struct hstate *h)
 {
 	int node;

-- 
2.48.1