[PATCH] x86: allow SRAT to parse empty nodes

This patch is to allow the booting of a numa srat base i386 system without
requiring memory to be in all of it's nodes.  It breaks the assumption that
all nodes have memory during bootup.
Signed-off-by: Keith Mannthey <kmannth@us.ibm.com>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

arch/i386/kernel/numaq.c

@@ -30,9 +30,7 @@
 #include <linux/module.h>
 #include <linux/nodemask.h>
 #include <asm/numaq.h>
-
-/* These are needed before the pgdat's are created */
-extern long node_start_pfn[], node_end_pfn[], node_remap_size[];
+#include <asm/topology.h>
 
 #define	MB_TO_PAGES(addr) ((addr) << (20 - PAGE_SHIFT))
 

arch/i386/kernel/srat.c

@@ -30,6 +30,7 @@
 #include <linux/acpi.h>
 #include <linux/nodemask.h>
 #include <asm/srat.h>
+#include <asm/topology.h>
 
 /*
  * proximity macros and definitions
@@ -58,8 +59,6 @@ static int num_memory_chunks;		/* total number of memory chunks */
 static int zholes_size_init;
 static unsigned long zholes_size[MAX_NUMNODES * MAX_NR_ZONES];
 
-extern unsigned long node_start_pfn[], node_end_pfn[], node_remap_size[];
-
 extern void * boot_ioremap(unsigned long, unsigned long);
 
 /* Identify CPU proximity domains */
@@ -273,6 +272,17 @@ static int __init acpi20_parse_srat(struct acpi_table_srat *sratp)
 		int been_here_before = 0;
 
 		for (j = 0; j < num_memory_chunks; j++){
+			/*
+			 * Only add present memroy to node_end/start_pfn
+			 * There is no guarantee from the srat that the memory
+			 * is present at boot time.
+			 */
+			if (node_memory_chunk[j].start_pfn >= max_pfn) {
+				printk (KERN_INFO "Ignoring chunk of memory reported in the SRAT (could be hot-add zone?)\n");
+				printk (KERN_INFO "chunk is reported from pfn %04x to %04x\n",
+					node_memory_chunk[j].start_pfn, node_memory_chunk[j].end_pfn);
+				continue;
+			}
 			if (node_memory_chunk[j].nid == nid) {
 				if (been_here_before == 0) {
 					node_start_pfn[nid] = node_memory_chunk[j].start_pfn;

arch/i386/mm/discontig.c

@@ -154,7 +154,7 @@ static void __init find_max_pfn_node(int nid)
  */
 static void __init allocate_pgdat(int nid)
 {
-	if (nid)
+	if (nid && node_has_online_mem(nid))
 		NODE_DATA(nid) = (pg_data_t *)node_remap_start_vaddr[nid];
 	else {
 		NODE_DATA(nid) = (pg_data_t *)(__va(min_low_pfn << PAGE_SHIFT));
@@ -188,6 +188,9 @@ static unsigned long calculate_numa_remap_pages(void)
 	for_each_online_node(nid) {
 		if (nid == 0)
 			continue;
+		if (!node_remap_size[nid])
+			continue;
+
 		/*
 		 * The acpi/srat node info can show hot-add memroy zones
 		 * where memory could be added but not currently present.
@@ -307,24 +310,27 @@ void __init zone_sizes_init(void)
 
 		max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
 
-		if (start > low) {
+		if (node_has_online_mem(nid)){
+			if (start > low) {
 #ifdef CONFIG_HIGHMEM
-			BUG_ON(start > high);
-			zones_size[ZONE_HIGHMEM] = high - start;
+				BUG_ON(start > high);
+				zones_size[ZONE_HIGHMEM] = high - start;
 #endif
-		} else {
-			if (low < max_dma)
-				zones_size[ZONE_DMA] = low;
-			else {
-				BUG_ON(max_dma > low);
-				BUG_ON(low > high);
-				zones_size[ZONE_DMA] = max_dma;
-				zones_size[ZONE_NORMAL] = low - max_dma;
+			} else {
+				if (low < max_dma)
+					zones_size[ZONE_DMA] = low;
+				else {
+					BUG_ON(max_dma > low);
+					BUG_ON(low > high);
+					zones_size[ZONE_DMA] = max_dma;
+					zones_size[ZONE_NORMAL] = low - max_dma;
 #ifdef CONFIG_HIGHMEM
-				zones_size[ZONE_HIGHMEM] = high - low;
+					zones_size[ZONE_HIGHMEM] = high - low;
 #endif
+				}
 			}
 		}
+
 		zholes_size = get_zholes_size(nid);
 		/*
 		 * We let the lmem_map for node 0 be allocated from the

include/asm-i386/topology.h

@@ -88,6 +88,12 @@ static inline cpumask_t pcibus_to_cpumask(int bus)
 	.nr_balance_failed	= 0,			\
 }
 
+extern unsigned long node_start_pfn[];
+extern unsigned long node_end_pfn[];
+extern unsigned long node_remap_size[];
+
+#define node_has_online_mem(nid) (node_start_pfn[nid] != node_end_pfn[nid])
+
 #else /* !CONFIG_NUMA */
 /*
  * Other i386 platforms should define their own version of the 

include/linux/topology.h

@@ -31,9 +31,12 @@
 #include <linux/bitops.h>
 #include <linux/mmzone.h>
 #include <linux/smp.h>
-
 #include <asm/topology.h>
 
+#ifndef node_has_online_mem
+#define node_has_online_mem(nid) (1)
+#endif
+
 #ifndef nr_cpus_node
 #define nr_cpus_node(node)							\
 	({									\