xen/55e43ff8-x86-NUMA-don-t-account-hotplug-regions.patch

# Commit c011f470e6e79208f5baa071b4d072b78c88e2ba
# Date 2015-08-31 13:52:24 +0200
# Author Jan Beulich <jbeulich@suse.com>
# Committer Jan Beulich <jbeulich@suse.com>
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>

--- a/xen/arch/x86/srat.c
+++ b/xen/arch/x86/srat.c
@@ -32,7 +32,7 @@ static u8 __read_mostly pxm2node[256] = 
 static int num_node_memblks;
 static struct node node_memblk_range[NR_NODE_MEMBLKS];
 static int memblk_nodeid[NR_NODE_MEMBLKS];
-
+static __initdata DECLARE_BITMAP(memblk_hotplug, NR_NODE_MEMBLKS);
 
 static int node_to_pxm(int n);
 
@@ -89,9 +89,9 @@ static __init int conflicting_memblks(u6
 		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;
 }
@@ -229,7 +229,6 @@ acpi_numa_processor_affinity_init(struct
 void __init
 acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 {
-	struct node *nd;
 	u64 start, end;
 	int node, pxm;
 	int i;
@@ -263,30 +262,40 @@ acpi_numa_memory_affinity_init(struct ac
 	}
 	/* 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)" : "");
@@ -294,6 +303,11 @@ acpi_numa_memory_affinity_init(struct ac
 	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++;
 }