summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/kernel-parameters.txt3
-rw-r--r--arch/x86/mm/numa.c11
-rw-r--r--mm/Kconfig17
-rw-r--r--mm/memory_hotplug.c31
4 files changed, 57 insertions, 5 deletions
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index fd3ecedc084d..882a40d405c8 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1775,6 +1775,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
that the amount of memory usable for all allocations
is not too small.
+ movable_node [KNL,X86] Boot-time switch to enable the effects
+ of CONFIG_MOVABLE_NODE=y. See mm/Kconfig for details.
+
MTD_Partition= [MTD]
Format: <name>,<region-number>,<size>,<offset>
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 8bf93bae1f13..24aec58d6afd 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -567,6 +567,17 @@ static int __init numa_init(int (*init_func)(void))
ret = init_func();
if (ret < 0)
return ret;
+
+ /*
+ * We reset memblock back to the top-down direction
+ * here because if we configured ACPI_NUMA, we have
+ * parsed SRAT in init_func(). It is ok to have the
+ * reset here even if we did't configure ACPI_NUMA
+ * or acpi numa init fails and fallbacks to dummy
+ * numa init.
+ */
+ memblock_set_bottom_up(false);
+
ret = numa_cleanup_meminfo(&numa_meminfo);
if (ret < 0)
return ret;
diff --git a/mm/Kconfig b/mm/Kconfig
index 394838f489eb..3f4ffda152bb 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -153,11 +153,18 @@ config MOVABLE_NODE
help
Allow a node to have only movable memory. Pages used by the kernel,
such as direct mapping pages cannot be migrated. So the corresponding
- memory device cannot be hotplugged. This option allows users to
- online all the memory of a node as movable memory so that the whole
- node can be hotplugged. Users who don't use the memory hotplug
- feature are fine with this option on since they don't online memory
- as movable.
+ memory device cannot be hotplugged. This option allows the following
+ two things:
+ - When the system is booting, node full of hotpluggable memory can
+ be arranged to have only movable memory so that the whole node can
+ be hot-removed. (need movable_node boot option specified).
+ - After the system is up, the option allows users to online all the
+ memory of a node as movable memory so that the whole node can be
+ hot-removed.
+
+ Users who don't use the memory hotplug feature are fine with this
+ option on since they don't specify movable_node boot option or they
+ don't online memory as movable.
Say Y here if you want to hotplug a whole node.
Say N here if you want kernel to use memory on all nodes evenly.
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1b6fe8ca71e6..489f235502db 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -31,6 +31,7 @@
#include <linux/firmware-map.h>
#include <linux/stop_machine.h>
#include <linux/hugetlb.h>
+#include <linux/memblock.h>
#include <asm/tlbflush.h>
@@ -1422,6 +1423,36 @@ static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
}
#endif /* CONFIG_MOVABLE_NODE */
+static int __init cmdline_parse_movable_node(char *p)
+{
+#ifdef CONFIG_MOVABLE_NODE
+ /*
+ * Memory used by the kernel cannot be hot-removed because Linux
+ * cannot migrate the kernel pages. When memory hotplug is
+ * enabled, we should prevent memblock from allocating memory
+ * for the kernel.
+ *
+ * ACPI SRAT records all hotpluggable memory ranges. But before
+ * SRAT is parsed, we don't know about it.
+ *
+ * The kernel image is loaded into memory at very early time. We
+ * cannot prevent this anyway. So on NUMA system, we set any
+ * node the kernel resides in as un-hotpluggable.
+ *
+ * Since on modern servers, one node could have double-digit
+ * gigabytes memory, we can assume the memory around the kernel
+ * image is also un-hotpluggable. So before SRAT is parsed, just
+ * allocate memory near the kernel image to try the best to keep
+ * the kernel away from hotpluggable memory.
+ */
+ memblock_set_bottom_up(true);
+#else
+ pr_warn("movable_node option not supported\n");
+#endif
+ return 0;
+}
+early_param("movable_node", cmdline_parse_movable_node);
+
/* check which state of node_states will be changed when offline memory */
static void node_states_check_changes_offline(unsigned long nr_pages,
struct zone *zone, struct memory_notify *arg)