arch/x86/mm/numa.c: fix boot failure when all nodes are hotpluggable

If all the nodes are marked hotpluggable, alloc node data will fail.
Because __next_mem_range_rev() will skip the hotpluggable memory
regions.  numa_clear_kernel_node_hotplug() is called after alloc node
data.

numa_init()
    ...
    ret = init_func();  // this will mark hotpluggable flag from SRAT
    ...
    memblock_set_bottom_up(false);
    ...
    ret = numa_register_memblks(&numa_meminfo);  // this will alloc node data(pglist_data)
    ...
    numa_clear_kernel_node_hotplug();  // in case all the nodes are hotpluggable
    ...

numa_register_memblks()
    setup_node_data()
        memblock_find_in_range_node()
            __memblock_find_range_top_down()
                for_each_mem_range_rev()
                    __next_mem_range_rev()

This patch moves numa_clear_kernel_node_hotplug() into
numa_register_memblks(), clear kernel node hotpluggable flag before
alloc node data, then alloc node data won't fail even all the nodes
are hotpluggable.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Xishi Qiu <qiuxishi@huawei.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Tang Chen <tangchen@cn.fujitsu.com>
Cc: Gu Zheng <guz.fnst@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
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 a32b706c401add2e47943cf1650ca63f26b8c1ae..4e1e5709fe1776dd9746341ce4745837033454f0 100644 (file)
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -478,6 +478,42 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
        return true;
 }
 
+static void __init numa_clear_kernel_node_hotplug(void)
+{
+       int i, nid;
+       nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
+       unsigned long start, end;
+       struct memblock_region *r;
+
+       /*
+        * 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.
+        */
+       for (i = 0; i < numa_meminfo.nr_blks; i++) {
+               struct numa_memblk *mb = &numa_meminfo.blk[i];
+
+               memblock_set_node(mb->start, mb->end - mb->start,
+                                 &memblock.reserved, mb->nid);
+       }
+
+       /* Mark all kernel nodes. */
+       for_each_memblock(reserved, r)
+               node_set(r->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_register_memblks(struct numa_meminfo *mi)
 {
        unsigned long uninitialized_var(pfn_align);
@@ -495,6 +531,15 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
                                  &memblock.memory, mb->nid);
        }
 
+       /*
+        * 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, alloc node data won't fail.
+        */
+       numa_clear_kernel_node_hotplug();
+
        /*
         * If sections array is gonna be used for pfn -> nid mapping, check
         * whether its granularity is fine enough.
@@ -554,41 +599,6 @@ static void __init numa_init_array(void)
        }
 }
 
-static void __init numa_clear_kernel_node_hotplug(void)
-{
-       int i, nid;
-       nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
-       unsigned long start, end;
-       struct memblock_region *r;
-
-       /*
-        * 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.
-        */
-       for (i = 0; i < numa_meminfo.nr_blks; i++) {
-               struct numa_memblk *mb = &numa_meminfo.blk[i];
-               memblock_set_node(mb->start, mb->end - mb->start,
-                                 &memblock.reserved, mb->nid);
-       }
-
-       /* Mark all kernel nodes. */
-       for_each_memblock(reserved, r)
-               node_set(r->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;
@@ -643,15 +653,6 @@ static int __init numa_init(int (*init_func)(void))
        }
        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;
 }