[RFC][PATCH] avoid creating empty nodes [2/2] ignore empty pxms.

[KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>]

compare SRAT information and other information to
avoid onlining nodes which doesn't have any cpus and memory.
for cpus, compare SRAT and lsapic.
for memory, compare SRAT and EFI.

Signed-Off-By: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>

Index: linux-2.6.16-mm1/arch/ia64/kernel/acpi.c
===================================================================
--- linux-2.6.16-mm1.orig/arch/ia64/kernel/acpi.c	2006-03-28 15:04:31.000000000 +0900
+++ linux-2.6.16-mm1/arch/ia64/kernel/acpi.c	2006-03-28 16:53:39.000000000 +0900
@@ -413,8 +413,11 @@
 
 static int __initdata srat_num_cpus;	/* number of cpus */
 static u32 __devinitdata pxm_flag[PXM_FLAG_LEN];
+static u32 __devinitdata pxm_online_flag[PXM_FLAG_LEN];
 #define pxm_bit_set(bit)	(set_bit(bit,(void *)pxm_flag))
 #define pxm_bit_test(bit)	(test_bit(bit,(void *)pxm_flag))
+#define pxm_online_bit_set(bit)	(set_bit(bit, (void *)pxm_online_flag))
+#define pxm_online_bit_test(bit) (test_bit(bit, (void *)pxm_online_flag))
 static struct acpi_table_slit __initdata *slit_table;
 
 /*
@@ -450,6 +453,24 @@
 	srat_num_cpus++;
 }
 
+/*
+ * compare SRAT and lsapic entries.
+ */
+void __init confirm_srat_available_cpu(void)
+{
+	int i, j;
+	unsigned long phys_id;
+	for (i = 0; i < available_cpus; i++) {
+		phys_id = smp_boot_data.cpu_phys_id[i];
+		for (j = 0; j < srat_num_cpus; j++) {
+			if (node_cpuid[j].phys_id == phys_id) {
+				pxm_online_bit_set(node_cpuid[j].nid);
+				printk("set pxm %d online\n", node_cpuid[j].nid);
+			}
+		}
+	}
+}
+
 void __init
 acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma)
 {
@@ -488,9 +509,31 @@
 	num_node_memblks++;
 }
 
+int confirm_srat_efi_memmap(unsigned long start, unsigned long end, void *arg)
+{
+	unsigned long pstart, pend;
+	struct node_memblk_s *p;
+	int i;
+	printk(KERN_INFO "print efi memamp %p %p\n", (void*)start, (void *)end);
+	pstart = __pa(start);
+	pend = __pa(end);
+	/* check intersection with SRAT's memdata */
+	for (i = 0; i < num_node_memblks; i++) {
+		p = &node_memblk[i];
+		if (((p->start_paddr <= pstart) &&
+	             (pstart < p->start_paddr + p->size)) ||
+		    ((pstart <= p->start_paddr) &&
+	             (p->start_paddr + p->size <= pend))) {
+			pxm_online_bit_set(p->nid);
+			printk(KERN_INFO "set pxm %d online\n", p->nid);
+		}
+	}
+	return 0;
+}
+
 void __init acpi_numa_arch_fixup(void)
 {
-	int i, j, node_from, node_to;
+	int i, j, node, node_from, node_to;
 
 	/* If there's no SRAT, fix the phys_id and mark node 0 online */
 	if (srat_num_cpus == 0) {
@@ -498,6 +541,8 @@
 		node_cpuid[0].phys_id = hard_smp_processor_id();
 		return;
 	}
+	confirm_srat_available_cpu();
+	efi_memmap_walk(confirm_srat_efi_memmap, NULL);
 
 	/*
 	 * MCD - This can probably be dropped now.  No need for pxm ID to node ID
@@ -507,8 +552,8 @@
 	for (i = 0; i < MAX_PXM_DOMAINS; i++) {
 		if (pxm_bit_test(i)) {
 			int nid = acpi_map_pxm_to_node(i);
-			pxm_bit_set(i);
-			node_set_online(nid);
+			if (pxm_online_bit_test(i))
+				node_set_online(nid);
 		}
 	}
 
@@ -527,8 +572,13 @@
 	}
 
 	/* set logical node id in cpu structure */
-	for (i = 0; i < srat_num_cpus; i++)
-		node_cpuid[i].nid = pxm_to_node(node_cpuid[i].nid);
+	for (i = 0; i < srat_num_cpus; i++) {
+		node = pxm_to_node(node_cpuid[i].nid);
+		if (node_online(node))
+			node_cpuid[i].nid = node;
+		else
+			node_cpuid[i].nid = 0; /* for possible cpus */
+	}
 
 	printk(KERN_INFO "Number of logical nodes in system = %d\n",
 	       num_online_nodes());
-
: send the line "unsubscribe linux-ia64" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html