[PATCH] x86_64: Clear more state when ignoring empty node in SRAT parsing

Fix boot failures on systems with bad PXMs.

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c
index 33340bd1e328dd903be99daecbe65ce9c5a35677..79e3e98bbf100a9e41f26763081c895aae46502e 100644 (file)
--- a/arch/x86_64/mm/srat.c
+++ b/arch/x86_64/mm/srat.c
@@ -25,6 +25,10 @@ static nodemask_t nodes_found __initdata;
 static struct node nodes[MAX_NUMNODES] __initdata;
 static __u8  pxm2node[256] = { [0 ... 255] = 0xff };
 
+/* Too small nodes confuse the VM badly. Usually they result
+   from BIOS bugs. */
+#define NODE_MIN_SIZE (4*1024*1024)
+
 static int node_to_pxm(int n);
 
 int pxm_to_node(int pxm)
@@ -168,22 +172,32 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma)
               nd->start, nd->end);
 }
 
+static void unparse_node(int node)
+{
+       int i;
+       node_clear(node, nodes_parsed);
+       for (i = 0; i < MAX_LOCAL_APIC; i++) {
+               if (apicid_to_node[i] == node)
+                       apicid_to_node[i] = NUMA_NO_NODE;
+       }
+}
+
 void __init acpi_numa_arch_fixup(void) {}
 
 /* Use the information discovered above to actually set up the nodes. */
 int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 {
        int i;
+
+       for (i = 0; i < MAX_NUMNODES; i++) {
+               cutoff_node(i, start, end);
+               if ((nodes[i].end - nodes[i].start) < NODE_MIN_SIZE)
+                       unparse_node(i);
+       }
+
        if (acpi_numa <= 0)
                return -1;
 
-       /* First clean up the node list */
-       for_each_node_mask(i, nodes_parsed) {
-               cutoff_node(i, start, end);
-               if (nodes[i].start == nodes[i].end)
-                       node_clear(i, nodes_parsed);
-       }
-
        memnode_shift = compute_hash_shift(nodes, nodes_weight(nodes_parsed));
        if (memnode_shift < 0) {
                printk(KERN_ERR