x86/NUMA: improve memnode_shift calculation for multi node system

SRAT may describe individual nodes using multiple ranges. When they're
adjacent (with or without a gap in between), only the start of the first
such range actually needs accounting for. Furthermore the very first
range doesn't need considering of its start address at all, as it's fine
to associate all lower addresses (with no memory) with that same node.
For this to work, the array of ranges needs to be sorted by address -
adjust logic accordingly in acpi_numa_memory_affinity_init().

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>

diff --git a/xen/arch/x86/numa.c b/xen/arch/x86/numa.c
index 4f742414b093321d8b64fcdf8fec2fd58ba977bc..2c3c1c15fe8b4499f2e12259ddbdc45d3ec30920 100644 (file)
--- a/xen/arch/x86/numa.c
+++ b/xen/arch/x86/numa.c
@@ -127,7 +127,8 @@ static int __init extract_lsb_from_nodes(const struct node *nodes,
         epdx = paddr_to_pdx(nodes[i].end - 1) + 1;
         if ( spdx >= epdx )
             continue;
-        bitfield |= spdx;
+        if ( i && (!nodeids || nodeids[i - 1] != nodeids[i]) )
+            bitfield |= spdx;
         if ( !i || !nodeids || nodeids[i - 1] != nodeids[i] )
             nodes_used++;
         if ( epdx > memtop )

diff --git a/xen/arch/x86/srat.c b/xen/arch/x86/srat.c
index b62a1529111f293b88f085810d3a04e25c493fbe..fbcd8749c4fa43cf983c74aea6f1b7d8a6d1c2e2 100644 (file)
--- a/xen/arch/x86/srat.c
+++ b/xen/arch/x86/srat.c
@@ -312,6 +312,7 @@ acpi_numa_memory_affinity_init(const struct acpi_srat_mem_affinity *ma)
        unsigned pxm;
        nodeid_t node;
        unsigned int i;
+       bool next = false;
 
        if (srat_disabled())
                return;
@@ -413,14 +414,37 @@ acpi_numa_memory_affinity_init(const struct acpi_srat_mem_affinity *ma)
               node, pxm, start, end - 1,
               ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE ? " (hotplug)" : "");
 
-       node_memblk_range[num_node_memblks].start = start;
-       node_memblk_range[num_node_memblks].end = end;
-       memblk_nodeid[num_node_memblks] = node;
+       /* Keep node_memblk_range[] sorted by address. */
+       for (i = 0; i < num_node_memblks; ++i)
+               if (node_memblk_range[i].start > start ||
+                   (node_memblk_range[i].start == start &&
+                    node_memblk_range[i].end > end))
+                       break;
+
+       memmove(&node_memblk_range[i + 1], &node_memblk_range[i],
+               (num_node_memblks - i) * sizeof(*node_memblk_range));
+       node_memblk_range[i].start = start;
+       node_memblk_range[i].end = end;
+
+       memmove(&memblk_nodeid[i + 1], &memblk_nodeid[i],
+               (num_node_memblks - i) * sizeof(*memblk_nodeid));
+       memblk_nodeid[i] = node;
+
        if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) {
-               __set_bit(num_node_memblks, memblk_hotplug);
+               next = true;
                if (end > mem_hotplug)
                        mem_hotplug = end;
        }
+       for (; i <= num_node_memblks; ++i) {
+               bool prev = next;
+
+               next = test_bit(i, memblk_hotplug);
+               if (prev)
+                       __set_bit(i, memblk_hotplug);
+               else
+                       __clear_bit(i, memblk_hotplug);
+       }
+
        num_node_memblks++;
 }