[PATCH] x86_64: Handle empty PXMs that only contain hotplug memory

The node setup code would try to allocate the node metadata in the node
itself, but that fails if there is no memory in there.

This can happen with memory hotplug when the hotplug area defines an so
far empty node.

Now use bootmem to try to allocate the mem_map in other nodes.

And if it fails don't panic, but just ignore the node.

To make this work I added a new __alloc_bootmem_nopanic function that
does what its name implies.

TBD should try to use nearby nodes here.  Currently we just use any.
It's hard to do it better because bootmem doesn't have proper fallback
lists yet.

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

2 files changed, 38 insertions, 9 deletions

diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index 779132af29a7..cc02573a3271 100644
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -100,11 +100,30 @@ int early_pfn_to_nid(unsigned long pfn)
 }
 #endif
 
+static void * __init
+early_node_mem(int nodeid, unsigned long start, unsigned long end,
+	      unsigned long size)
+{
+	unsigned long mem = find_e820_area(start, end, size);
+	void *ptr;
+	if (mem != -1L)
+		return __va(mem);
+	ptr = __alloc_bootmem_nopanic(size,
+				SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS));
+	if (ptr == 0) {
+		printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
+			size, nodeid);
+		return NULL;
+	}
+	return ptr;
+}
+
 /* Initialize bootmem allocator for a node */
 void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 { 
 	unsigned long start_pfn, end_pfn, bootmap_pages, bootmap_size, bootmap_start; 
 	unsigned long nodedata_phys;
+	void *bootmap;
 	const int pgdat_size = round_up(sizeof(pg_data_t), PAGE_SIZE);
 
 	start = round_up(start, ZONE_ALIGN); 
@@ -114,13 +133,11 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en
 	start_pfn = start >> PAGE_SHIFT;
 	end_pfn = end >> PAGE_SHIFT;
 
-	nodedata_phys = find_e820_area(start, end, pgdat_size); 
-	if (nodedata_phys == -1L) 
-		panic("Cannot find memory pgdat in node %d\n", nodeid);
-
-	Dprintk("nodedata_phys %lx\n", nodedata_phys); 
+	node_data[nodeid] = early_node_mem(nodeid, start, end, pgdat_size);
+	if (node_data[nodeid] == NULL)
+		return;
+	nodedata_phys = __pa(node_data[nodeid]);
 
-	node_data[nodeid] = phys_to_virt(nodedata_phys);
 	memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
 	NODE_DATA(nodeid)->bdata = &plat_node_bdata[nodeid];
 	NODE_DATA(nodeid)->node_start_pfn = start_pfn;
@@ -129,9 +146,15 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en
 	/* Find a place for the bootmem map */
 	bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn); 
 	bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
-	bootmap_start = find_e820_area(bootmap_start, end, bootmap_pages<<PAGE_SHIFT);
-	if (bootmap_start == -1L) 
-		panic("Not enough continuous space for bootmap on node %d", nodeid); 
+	bootmap = early_node_mem(nodeid, bootmap_start, end,
+					bootmap_pages<<PAGE_SHIFT);
+	if (bootmap == NULL)  {
+		if (nodedata_phys < start || nodedata_phys >= end)
+			free_bootmem((unsigned long)node_data[nodeid],pgdat_size);
+		node_data[nodeid] = NULL;
+		return;
+	}
+	bootmap_start = __pa(bootmap);
 	Dprintk("bootmap start %lu pages %lu\n", bootmap_start, bootmap_pages); 
 	
 	bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c
index 443875eb15a2..15ae9fcd65a7 100644
--- a/arch/x86_64/mm/srat.c
+++ b/arch/x86_64/mm/srat.c
@@ -415,6 +415,12 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 	/* Finally register nodes */
 	for_each_node_mask(i, nodes_parsed)
 		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
+	/* Try again in case setup_node_bootmem missed one due
+	   to missing bootmem */
+	for_each_node_mask(i, nodes_parsed)
+		if (!node_online(i))
+			setup_node_bootmem(i, nodes[i].start, nodes[i].end);
+
 	for (i = 0; i < NR_CPUS; i++) { 
 		if (cpu_to_node[i] == NUMA_NO_NODE)
 			continue;