Merge branch 'x86/numa' into x86/devel

Conflicts:

	arch/x86/Kconfig
	arch/x86/kernel/e820.c
	arch/x86/kernel/efi_64.c
	arch/x86/kernel/mpparse.c
	arch/x86/kernel/setup.c
	arch/x86/kernel/setup_32.c
	arch/x86/mm/init_64.c
	include/asm-x86/proto.h

Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/Kconfig

@@ -121,7 +121,7 @@ config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y
 
 config HAVE_SETUP_PER_CPU_AREA
-	def_bool X86_64 || (X86_SMP && !X86_VOYAGER)
+	def_bool X86_64_SMP || (X86_SMP && !X86_VOYAGER)
 
 config HAVE_CPUMASK_OF_CPU_MAP
 	def_bool X86_64_SMP
@@ -579,7 +579,21 @@ config SWIOTLB
 
 config IOMMU_HELPER
 	def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB)
+config MAXSMP
+	bool "Configure Maximum number of SMP Processors and NUMA Nodes"
+	depends on X86_64 && SMP
+	default n
+	help
+	  Configure maximum number of CPUS and NUMA Nodes for this architecture.
+	  If unsure, say N.
 
+if MAXSMP
+config NR_CPUS
+	int
+	default "4096"
+endif
+
+if !MAXSMP
 config NR_CPUS
 	int "Maximum number of CPUs (2-4096)"
 	range 2 4096
@@ -592,7 +606,8 @@ config NR_CPUS
 	  minimum value which makes sense is 2.
 
 	  This is purely to save memory - each supported CPU adds
-	  approximately one kilobyte to the kernel image.
+	  approximately eight kilobytes to the kernel image.
+endif
 
 config SCHED_SMT
 	bool "SMT (Hyperthreading) scheduler support"
@@ -983,13 +998,25 @@ config NUMA_EMU
 	  into virtual nodes when booted with "numa=fake=N", where N is the
 	  number of nodes. This is only useful for debugging.
 
+if MAXSMP
+
+config NODES_SHIFT
+	int
+	default "9"
+endif
+
+if !MAXSMP
 config NODES_SHIFT
-	int "Max num nodes shift(1-9)"
-	range 1 9  if X86_64
+	int "Maximum NUMA Nodes (as a power of 2)"
+	range 1 9   if X86_64
 	default "6" if X86_64
 	default "4" if X86_NUMAQ
 	default "3"
 	depends on NEED_MULTIPLE_NODES
+	help
+	  Specify the maximum number of NUMA Nodes available on the target
+	  system.  Increases memory reserved to accomodate various tables.
+endif
 
 config HAVE_ARCH_BOOTMEM_NODE
 	def_bool y

arch/x86/Kconfig.debug

@@ -68,7 +68,7 @@ config DEBUG_PAGEALLOC
 config DEBUG_PER_CPU_MAPS
 	bool "Debug access to per_cpu maps"
 	depends on DEBUG_KERNEL
-	depends on X86_64_SMP
+	depends on X86_SMP
 	default n
 	help
 	  Say Y to verify that the per_cpu map being accessed has

arch/x86/kernel/apic_32.c

@@ -52,9 +52,6 @@
 
 unsigned long mp_lapic_addr;
 
-DEFINE_PER_CPU(u16, x86_bios_cpu_apicid) = BAD_APICID;
-EXPORT_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
-
 /*
  * Knob to control our willingness to enable the local APIC.
  *
@@ -1546,9 +1543,9 @@ void __cpuinit generic_processor_info(int apicid, int version)
 	}
 #ifdef CONFIG_SMP
 	/* are we being called early in kernel startup? */
-	if (x86_cpu_to_apicid_early_ptr) {
-		u16 *cpu_to_apicid = x86_cpu_to_apicid_early_ptr;
-		u16 *bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr;
+	if (early_per_cpu_ptr(x86_cpu_to_apicid)) {
+		u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
+		u16 *bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
 
 		cpu_to_apicid[cpu] = apicid;
 		bios_cpu_apicid[cpu] = apicid;

arch/x86/kernel/apic_64.c

@@ -90,9 +90,6 @@ static unsigned long apic_phys;
 
 unsigned long mp_lapic_addr;
 
-DEFINE_PER_CPU(u16, x86_bios_cpu_apicid) = BAD_APICID;
-EXPORT_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
-
 unsigned int __cpuinitdata maxcpus = NR_CPUS;
 /*
  * Get the LAPIC version
@@ -1075,9 +1072,9 @@ void __cpuinit generic_processor_info(int apicid, int version)
 		max_physical_apicid = apicid;
 
 	/* are we being called early in kernel startup? */
-	if (x86_cpu_to_apicid_early_ptr) {
-		u16 *cpu_to_apicid = x86_cpu_to_apicid_early_ptr;
-		u16 *bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr;
+	if (early_per_cpu_ptr(x86_cpu_to_apicid)) {
+		u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
+		u16 *bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
 
 		cpu_to_apicid[cpu] = apicid;
 		bios_cpu_apicid[cpu] = apicid;
@@ -1253,7 +1250,7 @@ __cpuinit int apic_is_clustered_box(void)
 	if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && !is_vsmp_box())
 		return 0;
 
-	bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr;
+	bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
 	bitmap_zero(clustermap, NUM_APIC_CLUSTERS);
 
 	for (i = 0; i < NR_CPUS; i++) {

arch/x86/kernel/head64.c

@@ -25,6 +25,20 @@
 #include <asm/e820.h>
 #include <asm/bios_ebda.h>
 
+/* boot cpu pda */
+static struct x8664_pda _boot_cpu_pda __read_mostly;
+
+#ifdef CONFIG_SMP
+/*
+ * We install an empty cpu_pda pointer table to indicate to early users
+ * (numa_set_node) that the cpu_pda pointer table for cpus other than
+ * the boot cpu is not yet setup.
+ */
+static struct x8664_pda *__cpu_pda[NR_CPUS] __initdata;
+#else
+static struct x8664_pda *__cpu_pda[NR_CPUS] __read_mostly;
+#endif
+
 static void __init zap_identity_mappings(void)
 {
 	pgd_t *pgd = pgd_offset_k(0UL);
@@ -88,10 +102,12 @@ void __init x86_64_start_kernel(char * real_mode_data)
 
 	early_printk("Kernel alive\n");
 
- 	for (i = 0; i < NR_CPUS; i++)
- 		cpu_pda(i) = &boot_cpu_pda[i];
-
+	_cpu_pda = __cpu_pda;
+	cpu_pda(0) = &_boot_cpu_pda;
 	pda_init(0);
+
+	early_printk("Kernel really alive\n");
+
 	copy_bootdata(__va(real_mode_data));
 
 	reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS");

arch/x86/kernel/nmi_64.c

@@ -90,7 +90,7 @@ int __init check_nmi_watchdog(void)
 	if (!atomic_read(&nmi_active))
 		return 0;
 
-	prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL);
+	prev_nmi_count = kmalloc(nr_cpu_ids * sizeof(int), GFP_KERNEL);
 	if (!prev_nmi_count)
 		goto error;
 
@@ -101,7 +101,7 @@ int __init check_nmi_watchdog(void)
 		smp_call_function(nmi_cpu_busy, (void *)&endflag, 0, 0);
 #endif
 
-	for (cpu = 0; cpu < NR_CPUS; cpu++)
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
 		prev_nmi_count[cpu] = cpu_pda(cpu)->__nmi_count;
 	local_irq_enable();
 	mdelay((20*1000)/nmi_hz); // wait 20 ticks