mm,memory_hotplug: add kernel boot option to enable memmap_on_memory

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.

Link: https://lkml.kernel.org/r/20210421102701.25051-7-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 1c0a3cf..d93fbc1 100644 (file)
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2801,6 +2801,23 @@
                        seconds.  Use this parameter to check at some
                        other rate.  0 disables periodic checking.
 
+       memory_hotplug.memmap_on_memory
+                       [KNL,X86,ARM] Boolean flag to enable this feature.
+                       Format: {on | off (default)}
+                       When enabled, runtime hotplugged memory will
+                       allocate its internal metadata (struct pages)
+                       from the hotadded memory which will allow to
+                       hotadd a lot of memory without requiring
+                       additional memory to do so.
+                       This feature is disabled by default because it
+                       has some implication on large (e.g. GB)
+                       allocations in some configurations (e.g. small
+                       memory blocks).
+                       The state of the flag can be read in
+                       /sys/module/memory_hotplug/parameters/memmap_on_memory.
+                       Note that even when enabled, there are a few cases where
+                       the feature is not effective.
+
        memtest=        [KNL,X86,ARM,PPC] Enable memtest
                        Format: <integer>
                        default : 0 <disable>

diff --git a/mm/Makefile b/mm/Makefile
index 809033d..bf71e29 100644 (file)
--- 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 0b31578..f7e46f5 100644 (file)
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -42,7 +42,15 @@
 #include "internal.h"
 #include "shuffle.h"
 
-static bool memmap_on_memory;
+
+/*
+ * memory_hotplug.memmap_on_memory parameter
+ */
+static bool memmap_on_memory __ro_after_init;
+#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
+module_param(memmap_on_memory, bool, 0444);
+MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug");
+#endif
 
 /*
  * online_page_callback contains pointer to current page onlining function.