acpi, numa, mem_hotplug: mark all nodes the kernel resides un-hotpluggable

At very early time, the kernel have to use some memory such as loading
the kernel image.  We cannot prevent this anyway.  So any node the
kernel resides in should be un-hotpluggable.

Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Rafael J . Wysocki" <rjw@sisk.pl>
Cc: Chen Tang <imtangchen@gmail.com>
Cc: Gong Chen <gong.chen@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Larry Woodman <lwoodman@redhat.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Liu Jiang <jiang.liu@huawei.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Taku Izumi <izumi.taku@jp.fujitsu.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Renninger <trenn@suse.de>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 78d6a9e5830e9bad6ff14acebc9c01d733bc8b4c..81b2750f3666f16d7a42e0699d8dc458530fd7b8 100644 (file)
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -493,6 +493,14 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
                struct numa_memblk *mb = &mi->blk[i];
                memblock_set_node(mb->start, mb->end - mb->start,
                                  &memblock.memory, mb->nid);
+
+               /*
+                * At this time, all memory regions reserved by memblock are
+                * used by the kernel. Set the nid in memblock.reserved will
+                * mark out all the nodes the kernel resides in.
+                */
+               memblock_set_node(mb->start, mb->end - mb->start,
+                                 &memblock.reserved, mb->nid);
        }
 
        /*
@@ -554,6 +562,30 @@ static void __init numa_init_array(void)
        }
 }
 
+static void __init numa_clear_kernel_node_hotplug(void)
+{
+       int i, nid;
+       nodemask_t numa_kernel_nodes;
+       unsigned long start, end;
+       struct memblock_type *type = &memblock.reserved;
+
+       /* Mark all kernel nodes. */
+       for (i = 0; i < type->cnt; i++)
+               node_set(type->regions[i].nid, numa_kernel_nodes);
+
+       /* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
+       for (i = 0; i < numa_meminfo.nr_blks; i++) {
+               nid = numa_meminfo.blk[i].nid;
+               if (!node_isset(nid, numa_kernel_nodes))
+                       continue;
+
+               start = numa_meminfo.blk[i].start;
+               end = numa_meminfo.blk[i].end;
+
+               memblock_clear_hotplug(start, end - start);
+       }
+}
+
 static int __init numa_init(int (*init_func)(void))
 {
        int i;
@@ -568,6 +600,8 @@ static int __init numa_init(int (*init_func)(void))
        memset(&numa_meminfo, 0, sizeof(numa_meminfo));
        WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory,
                                  MAX_NUMNODES));
+       WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved,
+                                 MAX_NUMNODES));
        /* In case that parsing SRAT failed. */
        WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX));
        numa_reset_distance();
@@ -605,6 +639,16 @@ static int __init numa_init(int (*init_func)(void))
                        numa_clear_node(i);
        }
        numa_init_array();
+
+       /*
+        * At very early time, the kernel have to use some memory such as
+        * loading the kernel image. We cannot prevent this anyway. So any
+        * node the kernel resides in should be un-hotpluggable.
+        *
+        * And when we come here, numa_init() won't fail.
+        */
+       numa_clear_kernel_node_hotplug();
+
        return 0;
 }