x86/NUMA: don't account hotplug regions

... except in cases where they really matter: node_memblk_range[] now
is the only place all regions get stored. nodes[] and NODE_DATA() track
present memory only. This improves the reporting when nodes have
disjoint "normal" and hotplug regions, with the hotplug region sitting
above the highest populated page. In such cases a node's spanned-pages
value (visible in both XEN_SYSCTL_numainfo and 'u' debug key output)
covered all the way up to top of populated memory, giving quite
different a picture from what an otherwise identically configured
system without and hotplug regions would report. Note, however, that
the actual hotplug case (as well as cases of nodes with multiple
disjoint present regions) is still not being handled such that the
reported values would represent how much memory a node really has (but
that can be considered intentional).

Reported-by: Jim Fehlig <jfehlig@suse.com>
This at once makes nodes_cover_memory() no longer consider E820_RAM
regions covered by SRAT hotplug regions.

Also reject self-overlaps with mismatching hotplug flags.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Tested-by: Jim Fehlig <jfehlig@suse.com>
Release-acked-by: Wei Liu <wei.liu2@citrix.com>

diff --git a/xen/arch/x86/srat.c b/xen/arch/x86/srat.c
index d6ce420d4dab7f63fa85ae1fdc203124560872e4..4242d10a3b85ba4c2d69d3a96e8d45093a5b58c8 100644 (file)
--- a/xen/arch/x86/srat.c
+++ b/xen/arch/x86/srat.c
@@ -39,6 +39,7 @@ static unsigned node_to_pxm(nodeid_t n);
 static int num_node_memblks;
 static struct node node_memblk_range[NR_NODE_MEMBLKS];
 static nodeid_t memblk_nodeid[NR_NODE_MEMBLKS];
+static __initdata DECLARE_BITMAP(memblk_hotplug, NR_NODE_MEMBLKS);
 
 static inline bool_t node_found(unsigned idx, unsigned pxm)
 {
@@ -126,9 +127,9 @@ static __init int conflicting_memblks(u64 start, u64 end)
                if (nd->start == nd->end)
                        continue;
                if (nd->end > start && nd->start < end)
-                       return memblk_nodeid[i];
+                       return i;
                if (nd->end == end && nd->start == start)
-                       return memblk_nodeid[i];
+                       return i;
        }
        return -1;
 }
@@ -269,7 +270,6 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 void __init
 acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 {
-       struct node *nd;
        u64 start, end;
        unsigned pxm;
        nodeid_t node;
@@ -304,30 +304,40 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
        }
        /* It is fine to add this area to the nodes data it will be used later*/
        i = conflicting_memblks(start, end);
-       if (i == node) {
-               printk(KERN_WARNING
-               "SRAT: Warning: PXM %d (%"PRIx64"-%"PRIx64") overlaps with itself (%"
-               PRIx64"-%"PRIx64")\n", pxm, start, end, nodes[i].start, nodes[i].end);
-       } else if (i >= 0) {
+       if (i < 0)
+               /* everything fine */;
+       else if (memblk_nodeid[i] == node) {
+               bool_t mismatch = !(ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) !=
+                                 !test_bit(i, memblk_hotplug);
+
+               printk("%sSRAT: PXM %u (%"PRIx64"-%"PRIx64") overlaps with itself (%"PRIx64"-%"PRIx64")\n",
+                      mismatch ? KERN_ERR : KERN_WARNING, pxm, start, end,
+                      node_memblk_range[i].start, node_memblk_range[i].end);
+               if (mismatch) {
+                       bad_srat();
+                       return;
+               }
+       } else {
                printk(KERN_ERR
-                      "SRAT: PXM %d (%"PRIx64"-%"PRIx64") overlaps with PXM %d (%"
-                      PRIx64"-%"PRIx64")\n", pxm, start, end, node_to_pxm(i),
-                          nodes[i].start, nodes[i].end);
+                      "SRAT: PXM %u (%"PRIx64"-%"PRIx64") overlaps with PXM %u (%"PRIx64"-%"PRIx64")\n",
+                      pxm, start, end, node_to_pxm(memblk_nodeid[i]),
+                      node_memblk_range[i].start, node_memblk_range[i].end);
                bad_srat();
                return;
        }
-       nd = &nodes[node];
-       if (!node_test_and_set(node, memory_nodes_parsed)) {
-               nd->start = start;
-               nd->end = end;
-       } else {
-               if (start < nd->start)
+       if (!(ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE)) {
+               struct node *nd = &nodes[node];
+
+               if (!node_test_and_set(node, memory_nodes_parsed)) {
                        nd->start = start;
-               if (nd->end < end)
                        nd->end = end;
+               } else {
+                       if (start < nd->start)
+                               nd->start = start;
+                       if (nd->end < end)
+                               nd->end = end;
+               }
        }
-       if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && end > mem_hotplug)
-               mem_hotplug = end;
        printk(KERN_INFO "SRAT: Node %u PXM %u %"PRIx64"-%"PRIx64"%s\n",
               node, pxm, start, end,
               ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE ? " (hotplug)" : "");
@@ -335,6 +345,11 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
        node_memblk_range[num_node_memblks].start = start;
        node_memblk_range[num_node_memblks].end = end;
        memblk_nodeid[num_node_memblks] = node;
+       if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) {
+               __set_bit(num_node_memblks, memblk_hotplug);
+               if (end > mem_hotplug)
+                       mem_hotplug = end;
+       }
        num_node_memblks++;
 }