[PATCH] x86_64: Reject SRAT tables that don't cover all memory

Broken BIOS on Iwill 8way systems reports these and it causes the bootmem
allocator to crash. Add a sanity check if all the PXMs in the
SRAT table cover all memory as reported by e820. If the sanity
check fails the SRAT is rejected and the code will fall back
to discover the NUMA topology using the K8 northbridge registers
when applicable.

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c
index d96c701..8b7f856 100644 (file)
--- a/arch/x86_64/mm/srat.c
+++ b/arch/x86_64/mm/srat.c
@@ -17,6 +17,7 @@
 #include <linux/topology.h>
 #include <asm/proto.h>
 #include <asm/numa.h>
+#include <asm/e820.h>
 
 static struct acpi_table_slit *acpi_slit;
 
@@ -196,12 +197,39 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma)
               nd->start, nd->end);
 }
 
+/* Sanity check to catch more bad SRATs (they are amazingly common).
+   Make sure the PXMs cover all memory. */
+static int nodes_cover_memory(void)
+{
+       int i;
+       unsigned long pxmram, e820ram;
+
+       pxmram = 0;
+       for_each_node_mask(i, nodes_parsed) {
+               unsigned long s = nodes[i].start >> PAGE_SHIFT;
+               unsigned long e = nodes[i].end >> PAGE_SHIFT;
+               pxmram += e - s;
+               pxmram -= e820_hole_size(s, e);
+       }
+
+       e820ram = end_pfn - e820_hole_size(0, end_pfn);
+       if (pxmram < e820ram) {
+               printk(KERN_ERR
+       "SRAT: PXMs only cover %luMB of your %luMB e820 RAM. Not used.\n",
+                       (pxmram << PAGE_SHIFT) >> 20,
+                       (e820ram << PAGE_SHIFT) >> 20);
+               return 0;
+       }
+       return 1;
+}
+
 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;
+
        if (acpi_numa <= 0)
                return -1;
 
@@ -212,6 +240,11 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
                        node_clear(i, nodes_parsed);
        }
 
+       if (!nodes_cover_memory()) {
+               bad_srat();
+               return -1;
+       }
+
        memnode_shift = compute_hash_shift(nodes, nodes_weight(nodes_parsed));
        if (memnode_shift < 0) {
                printk(KERN_ERR