[5/5] mm,memory_hotplug: Add kernel boot option to enable memmap_on_memory

Commit Message

Oscar Salvador Dec. 17, 2020, 1:07 p.m. UTC

Self stored memmap leads to a sparse memory situation which is unsuitable
for workloads that requires large contiguous memory chunks, so make this
an opt-in which needs to be explicitly enabled.

To control this, let memory_hotplug have its own memory space, as suggested
by David, so we can add memory_hotplug.memmap_on_memory parameter.

Signed-off-by: Oscar Salvador <[e-mail]>
---
 .../admin-guide/kernel-parameters.txt         | 14 ++++++++++++
 mm/Makefile                                   |  5 ++++-
 mm/memory_hotplug.c                           | 22 ++++++++++++++++++-
 3 files changed, 39 insertions(+), 2 deletions(-)

Patch

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index c722ec19cd00..8ff3d7c87165 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2776,6 +2776,20 @@ 
 			seconds.  Use this parameter to check at some
 			other rate.  0 disables periodic checking.
 
+	memory_hotplug.memmap_on_memory
+			[KNL,X86,ARM,PPC] Boolean flag to enable this feature.
+			Format: {on | off (default)}
+			When enabled, memory to build the pages tables for the
+			memmap array describing the hot-added range will be taken
+			from the range itself, so the memmap page tables will be
+			self-hosted.
+			Since only single memory device ranges are supported at
+			the moment, this option is disabled by default because
+			it might have an impact on workloads that needs large
+			contiguous memory chunks.
+			The state of the flag can be read in
+			/sys/module/memory_hotplug/parameters/memmap_on_memory.
+
 	memtest=	[KNL,X86,ARM,PPC] Enable memtest
 			Format: <integer>
 			default : 0 <disable>
diff --git a/mm/Makefile b/mm/Makefile
index 6b581f8337e8..0425cec6cb17 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -58,9 +58,13 @@  obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 page-alloc-y := page_alloc.o
 page-alloc-$(CONFIG_SHUFFLE_PAGE_ALLOCATOR) += shuffle.o
 
+# Give 'memory_hotplug' its own module-parameter namespace
+memory-hotplug-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
+
 obj-y += page-alloc.o
 obj-y += init-mm.o
 obj-y += memblock.o
+obj-y += $(memory-hotplug-y)
 
 ifdef CONFIG_MMU
 	obj-$(CONFIG_ADVISE_SYSCALLS)	+= madvise.o
@@ -83,7 +87,6 @@  obj-$(CONFIG_SLUB) += slub.o
 obj-$(CONFIG_KASAN)	+= kasan/
 obj-$(CONFIG_KFENCE) += kfence/
 obj-$(CONFIG_FAILSLAB) += failslab.o
-obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_MEMTEST)		+= memtest.o
 obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o khugepaged.o
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9371e7d3f583..f5f95f49b98a 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -42,7 +42,27 @@ 
 #include "internal.h"
 #include "shuffle.h"
 
-static bool memmap_on_memory_enabled;
+/*
+ * memory_hotplug.memmap_on_memory parameter
+ */
+static bool memmap_on_memory_enabled __ro_after_init;
+
+static int memmap_on_memory_show(char *buffer, const struct kernel_param *kp)
+{
+	return sprintf(buffer, "%s\n",
+		       memmap_on_memory_enabled ? "on" : "off");
+}
+
+static __meminit int memmap_on_memory_store(const char *val,
+					    const struct kernel_param *kp)
+{
+	if (!IS_ENABLED(CONFIG_ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE))
+		return -EINVAL;
+
+	return param_set_bool(val, kp);
+}
+module_param_call(memmap_on_memory, memmap_on_memory_store,
+		  memmap_on_memory_show, &memmap_on_memory_enabled, 0400);
 
 /*
  * online_page_callback contains pointer to current page onlining function.