Merge branch 'x86/mpparse' into x86/devel

Conflicts:

	arch/x86/Kconfig
	arch/x86/kernel/io_apic_32.c
	arch/x86/kernel/setup_64.c
	arch/x86/mm/init_32.c
Signed-off-by: Ingo Molnar <mingo@elte.hu>

Documentation/kernel-parameters.txt

@@ -610,6 +610,29 @@ and is between 256 and 4096 characters. It is defined in the file
 			See drivers/char/README.epca and
 			Documentation/digiepca.txt.
 
+	disable_mtrr_cleanup [X86]
+	enable_mtrr_cleanup [X86]
+			The kernel tries to adjust MTRR layout from continuous
+			to discrete, to make X server driver able to add WB
+			entry later. This parameter enables/disables that.
+
+	mtrr_chunk_size=nn[KMG] [X86]
+			used for mtrr cleanup. It is largest continous chunk
+			that could hold holes aka. UC entries.
+
+	mtrr_gran_size=nn[KMG] [X86]
+			Used for mtrr cleanup. It is granularity of mtrr block.
+			Default is 1.
+			Large value could prevent small alignment from
+			using up MTRRs.
+
+	mtrr_spare_reg_nr=n [X86]
+			Format: <integer>
+			Range: 0,7 : spare reg number
+			Default : 1
+			Used for mtrr cleanup. It is spare mtrr entries number.
+			Set to 2 or more if your graphical card needs more.
+
 	disable_mtrr_trim [X86, Intel and AMD only]
 			By default the kernel will trim any uncacheable
 			memory out of your available memory pool based on

arch/x86/Kconfig

@@ -230,6 +230,27 @@ config SMP
 
 	  If you don't know what to do here, say N.
 
+config X86_FIND_SMP_CONFIG
+	def_bool y
+	depends on X86_MPPARSE || X86_VOYAGER || X86_VISWS
+	depends on X86_32
+
+if ACPI
+config X86_MPPARSE
+	def_bool y
+	bool "Enable MPS table"
+	depends on X86_LOCAL_APIC && !X86_VISWS
+	help
+	  For old smp systems that do not have proper acpi support. Newer systems
+	  (esp with 64bit cpus) with acpi support, MADT and DSDT will override it
+endif
+
+if !ACPI
+config X86_MPPARSE
+	def_bool y
+	depends on X86_LOCAL_APIC && !X86_VISWS
+endif
+
 choice
 	prompt "Subarchitecture Type"
 	default X86_PC
@@ -261,36 +282,6 @@ config X86_VOYAGER
 	  If you do not specifically know you have a Voyager based machine,
 	  say N here, otherwise the kernel you build will not be bootable.
 
-config X86_NUMAQ
-	bool "NUMAQ (IBM/Sequent)"
-	depends on SMP && X86_32 && PCI
-	select NUMA
-	help
-	  This option is used for getting Linux to run on a (IBM/Sequent) NUMA
-	  multiquad box. This changes the way that processors are bootstrapped,
-	  and uses Clustered Logical APIC addressing mode instead of Flat Logical.
-	  You will need a new lynxer.elf file to flash your firmware with - send
-	  email to <Martin.Bligh@us.ibm.com>.
-
-config X86_SUMMIT
-	bool "Summit/EXA (IBM x440)"
-	depends on X86_32 && SMP
-	help
-	  This option is needed for IBM systems that use the Summit/EXA chipset.
-	  In particular, it is needed for the x440.
-
-	  If you don't have one of these computers, you should say N here.
-	  If you want to build a NUMA kernel, you must select ACPI.
-
-config X86_BIGSMP
-	bool "Support for other sub-arch SMP systems with more than 8 CPUs"
-	depends on X86_32 && SMP
-	help
-	  This option is needed for the systems that have more than 8 CPUs
-	  and if the system is not of any sub-arch type above.
-
-	  If you don't have such a system, you should say N here.
-
 config X86_VISWS
 	bool "SGI 320/540 (Visual Workstation)"
 	depends on X86_32 && !PCI
@@ -304,12 +295,33 @@ config X86_VISWS
 	  and vice versa. See <file:Documentation/sgi-visws.txt> for details.
 
 config X86_GENERICARCH
-       bool "Generic architecture (Summit, bigsmp, ES7000, default)"
+       bool "Generic architecture"
 	depends on X86_32
        help
-          This option compiles in the Summit, bigsmp, ES7000, default subarchitectures.
-	  It is intended for a generic binary kernel.
-	  If you want a NUMA kernel, select ACPI.   We need SRAT for NUMA.
+          This option compiles in the NUMAQ, Summit, bigsmp, ES7000, default
+	  subarchitectures.  It is intended for a generic binary kernel.
+	  if you select them all, kernel will probe it one by one. and will
+	  fallback to default.
+
+if X86_GENERICARCH
+
+config X86_NUMAQ
+	bool "NUMAQ (IBM/Sequent)"
+	depends on SMP && X86_32 && PCI && X86_MPPARSE
+	select NUMA
+	help
+	  This option is used for getting Linux to run on a NUMAQ (IBM/Sequent)
+	  NUMA multiquad box. This changes the way that processors are
+	  bootstrapped, and uses Clustered Logical APIC addressing mode instead
+	  of Flat Logical.  You will need a new lynxer.elf file to flash your
+	  firmware with - send email to <Martin.Bligh@us.ibm.com>.
+
+config X86_SUMMIT
+	bool "Summit/EXA (IBM x440)"
+	depends on X86_32 && SMP
+	help
+	  This option is needed for IBM systems that use the Summit/EXA chipset.
+	  In particular, it is needed for the x440.
 
 config X86_ES7000
 	bool "Support for Unisys ES7000 IA32 series"
@@ -317,8 +329,15 @@ config X86_ES7000
 	help
 	  Support for Unisys ES7000 systems.  Say 'Y' here if this kernel is
 	  supposed to run on an IA32-based Unisys ES7000 system.
-	  Only choose this option if you have such a system, otherwise you
-	  should say N here.
+
+config X86_BIGSMP
+	bool "Support for big SMP systems with more than 8 CPUs"
+	depends on X86_32 && SMP
+	help
+	  This option is needed for the systems that have more than 8 CPUs
+	  and if the system is not of any sub-arch type above.
+
+endif
 
 config X86_RDC321X
 	bool "RDC R-321x SoC"
@@ -432,7 +451,7 @@ config MEMTEST
 
 config ACPI_SRAT
 	def_bool y
-	depends on X86_32 && ACPI && NUMA && (X86_SUMMIT || X86_GENERICARCH)
+	depends on X86_32 && ACPI && NUMA && X86_GENERICARCH
 	select ACPI_NUMA
 
 config HAVE_ARCH_PARSE_SRAT
@@ -441,11 +460,11 @@ config HAVE_ARCH_PARSE_SRAT
 
 config X86_SUMMIT_NUMA
 	def_bool y
-	depends on X86_32 && NUMA && (X86_SUMMIT || X86_GENERICARCH)
+	depends on X86_32 && NUMA && X86_GENERICARCH
 
 config X86_CYCLONE_TIMER
 	def_bool y
-	depends on X86_32 && X86_SUMMIT || X86_GENERICARCH
+	depends on X86_GENERICARCH
 
 config ES7000_CLUSTERED_APIC
 	def_bool y
@@ -910,9 +929,9 @@ config X86_PAE
 config NUMA
 	bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)"
 	depends on SMP
-	depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT || X86_GENERICARCH) && ACPI) && EXPERIMENTAL)
+	depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && EXPERIMENTAL)
 	default n if X86_PC
-	default y if (X86_NUMAQ || X86_SUMMIT)
+	default y if (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP)
 	help
 	  Enable NUMA (Non Uniform Memory Access) support.
 	  The kernel will try to allocate memory used by a CPU on the
@@ -1089,6 +1108,40 @@ config MTRR
 
 	  See <file:Documentation/mtrr.txt> for more information.
 
+config MTRR_SANITIZER
+	def_bool y
+	prompt "MTRR cleanup support"
+	depends on MTRR
+	help
+	  Convert MTRR layout from continuous to discrete, so some X driver
+	  could add WB entries.
+
+	  Say N here if you see bootup problems (boot crash, boot hang,
+	  spontaneous reboots).
+
+	  Could be disabled with disable_mtrr_cleanup. Also mtrr_chunk_size
+	  could be used to send largest mtrr entry size for continuous block
+	  to hold holes (aka. UC entries)
+
+	  If unsure, say Y.
+
+config MTRR_SANITIZER_ENABLE_DEFAULT
+	int "MTRR cleanup enable value (0-1)"
+	range 0 1
+	default "0"
+	depends on MTRR_SANITIZER
+	help
+	  Enable mtrr cleanup default value
+
+config MTRR_SANITIZER_SPARE_REG_NR_DEFAULT
+	int "MTRR cleanup spare reg num (0-7)"
+	range 0 7
+	default "1"
+	depends on MTRR_SANITIZER
+	help
+	  mtrr cleanup spare entries default, it can be changed via
+	  mtrr_spare_reg_nr=
+
 config X86_PAT
 	bool
 	prompt "x86 PAT support"

arch/x86/Kconfig.debug

@@ -137,15 +137,6 @@ config 4KSTACKS
 	  on the VM subsystem for higher order allocations. This option
 	  will also use IRQ stacks to compensate for the reduced stackspace.
 
-config X86_FIND_SMP_CONFIG
-	def_bool y
-	depends on X86_LOCAL_APIC || X86_VOYAGER
-	depends on X86_32
-
-config X86_MPPARSE
-	def_bool y
-	depends on (X86_32 && (X86_LOCAL_APIC && !X86_VISWS)) || X86_64
-
 config DOUBLEFAULT
 	default y
 	bool "Enable doublefault exception handler" if EMBEDDED

arch/x86/Makefile

@@ -117,29 +117,11 @@ mcore-$(CONFIG_X86_VOYAGER)	:= arch/x86/mach-voyager/
 mflags-$(CONFIG_X86_VISWS)	:= -Iinclude/asm-x86/mach-visws
 mcore-$(CONFIG_X86_VISWS)	:= arch/x86/mach-visws/
 
-# NUMAQ subarch support
-mflags-$(CONFIG_X86_NUMAQ)	:= -Iinclude/asm-x86/mach-numaq
-mcore-$(CONFIG_X86_NUMAQ)	:= arch/x86/mach-default/
-
-# BIGSMP subarch support
-mflags-$(CONFIG_X86_BIGSMP)	:= -Iinclude/asm-x86/mach-bigsmp
-mcore-$(CONFIG_X86_BIGSMP)	:= arch/x86/mach-default/
-
-#Summit subarch support
-mflags-$(CONFIG_X86_SUMMIT)	:= -Iinclude/asm-x86/mach-summit
-mcore-$(CONFIG_X86_SUMMIT)	:= arch/x86/mach-default/
-
 # generic subarchitecture
 mflags-$(CONFIG_X86_GENERICARCH):= -Iinclude/asm-x86/mach-generic
 fcore-$(CONFIG_X86_GENERICARCH)	+= arch/x86/mach-generic/
 mcore-$(CONFIG_X86_GENERICARCH)	:= arch/x86/mach-default/
 
-
-# ES7000 subarch support
-mflags-$(CONFIG_X86_ES7000)	:= -Iinclude/asm-x86/mach-es7000
-fcore-$(CONFIG_X86_ES7000)	:= arch/x86/mach-es7000/
-mcore-$(CONFIG_X86_ES7000)	:= arch/x86/mach-default/
-
 # RDC R-321x subarch support
 mflags-$(CONFIG_X86_RDC321X)	:= -Iinclude/asm-x86/mach-rdc321x
 mcore-$(CONFIG_X86_RDC321X)	:= arch/x86/mach-default/
@@ -160,6 +142,7 @@ KBUILD_AFLAGS += $(mflags-y)
 
 head-y := arch/x86/kernel/head_$(BITS).o
 head-y += arch/x86/kernel/head$(BITS).o
+head-y += arch/x86/kernel/head.o
 head-y += arch/x86/kernel/init_task.o
 
 libs-y  += arch/x86/lib/

arch/x86/boot/compressed/misc.c

@@ -218,10 +218,6 @@ static char *vidmem;
 static int vidport;
 static int lines, cols;
 
-#ifdef CONFIG_X86_NUMAQ
-void *xquad_portio;
-#endif
-
 #include "../../../../lib/inflate.c"
 
 static void *malloc(int size)

arch/x86/boot/memory.c

@@ -13,6 +13,7 @@
  */
 
 #include "boot.h"
+#include <linux/kernel.h>
 
 #define SMAP	0x534d4150	/* ASCII "SMAP" */
 
@@ -53,7 +54,7 @@ static int detect_memory_e820(void)
 
 		count++;
 		desc++;
-	} while (next && count < E820MAX);
+	} while (next && count < ARRAY_SIZE(boot_params.e820_map));
 
 	return boot_params.e820_entries = count;
 }

arch/x86/kernel/Makefile

@@ -2,7 +2,7 @@
 # Makefile for the linux kernel.
 #
 
-extra-y                := head_$(BITS).o head$(BITS).o init_task.o vmlinux.lds
+extra-y                := head_$(BITS).o head$(BITS).o head.o init_task.o vmlinux.lds
 
 CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
 
@@ -22,7 +22,7 @@ obj-y			+= setup_$(BITS).o i8259.o irqinit_$(BITS).o setup.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o setup64.o
-obj-y			+= bootflag.o e820_$(BITS).o
+obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o
 obj-y			+= tsc_$(BITS).o io_delay.o rtc.o

arch/x86/kernel/aperture_64.c

@@ -328,7 +328,7 @@ void __init early_gart_iommu_check(void)
 				    E820_RAM)) {
 			/* reserve it, so we can reuse it in second kernel */
 			printk(KERN_INFO "update e820 for GART\n");
-			add_memory_region(aper_base, aper_size, E820_RESERVED);
+			e820_add_region(aper_base, aper_size, E820_RESERVED);
 			update_e820();
 		}
 	}

arch/x86/kernel/apic_32.c

@@ -79,6 +79,11 @@ char system_vectors[NR_VECTORS] = { [0 ... NR_VECTORS-1] = SYS_VECTOR_FREE};
  */
 int apic_verbosity;
 
+int pic_mode;
+
+/* Have we found an MP table */
+int smp_found_config;
+
 static unsigned int calibration_result;
 
 static int lapic_next_event(unsigned long delta,
@@ -1202,7 +1207,7 @@ void __init init_apic_mappings(void)
 
 		for (i = 0; i < nr_ioapics; i++) {
 			if (smp_found_config) {
-				ioapic_phys = mp_ioapics[i].mpc_apicaddr;
+				ioapic_phys = mp_ioapics[i].mp_apicaddr;
 				if (!ioapic_phys) {
 					printk(KERN_ERR
 					       "WARNING: bogus zero IO-APIC "
@@ -1517,6 +1522,9 @@ void __cpuinit generic_processor_info(int apicid, int version)
 		 */
 		cpu = 0;
 
+	if (apicid > max_physical_apicid)
+		max_physical_apicid = apicid;
+
 	/*
 	 * Would be preferable to switch to bigsmp when CONFIG_HOTPLUG_CPU=y
 	 * but we need to work other dependencies like SMP_SUSPEND etc
@@ -1524,7 +1532,7 @@ void __cpuinit generic_processor_info(int apicid, int version)
 	 * if (CPU_HOTPLUG_ENABLED || num_processors > 8)
 	 *       - Ashok Raj <ashok.raj@intel.com>
 	 */
-	if (num_processors > 8) {
+	if (max_physical_apicid >= 8) {
 		switch (boot_cpu_data.x86_vendor) {
 		case X86_VENDOR_INTEL:
 			if (!APIC_XAPIC(version)) {

arch/x86/kernel/apic_64.c

@@ -56,6 +56,9 @@ EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
  */
 int apic_verbosity;
 
+/* Have we found an MP table */
+int smp_found_config;
+
 static struct resource lapic_resource = {
 	.name = "Local APIC",
 	.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
@@ -1068,6 +1071,9 @@ void __cpuinit generic_processor_info(int apicid, int version)
 		 */
 		cpu = 0;
 	}
+	if (apicid > max_physical_apicid)
+		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;

arch/x86/kernel/cpu/mtrr/generic.c

@@ -37,7 +37,7 @@ static struct fixed_range_block fixed_range_blocks[] = {
 static unsigned long smp_changes_mask;
 static struct mtrr_state mtrr_state = {};
 static int mtrr_state_set;
-static u64 tom2;
+u64 mtrr_tom2;
 
 #undef MODULE_PARAM_PREFIX
 #define MODULE_PARAM_PREFIX "mtrr."
@@ -139,8 +139,8 @@ u8 mtrr_type_lookup(u64 start, u64 end)
 		}
 	}
 
-	if (tom2) {
-		if (start >= (1ULL<<32) && (end < tom2))
+	if (mtrr_tom2) {
+		if (start >= (1ULL<<32) && (end < mtrr_tom2))
 			return MTRR_TYPE_WRBACK;
 	}
 
@@ -158,6 +158,20 @@ get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr)
 	rdmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi);
 }
 
+/*  fill the MSR pair relating to a var range  */
+void fill_mtrr_var_range(unsigned int index,
+		u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi)
+{
+	struct mtrr_var_range *vr;
+
+	vr = mtrr_state.var_ranges;
+
+	vr[index].base_lo = base_lo;
+	vr[index].base_hi = base_hi;
+	vr[index].mask_lo = mask_lo;
+	vr[index].mask_hi = mask_hi;
+}
+
 static void
 get_fixed_ranges(mtrr_type * frs)
 {
@@ -213,13 +227,13 @@ void __init get_mtrr_state(void)
 	mtrr_state.enabled = (lo & 0xc00) >> 10;
 
 	if (amd_special_default_mtrr()) {
-		unsigned lo, hi;
+		unsigned low, high;
 		/* TOP_MEM2 */
-		rdmsr(MSR_K8_TOP_MEM2, lo, hi);
-		tom2 = hi;
-		tom2 <<= 32;
-		tom2 |= lo;
-		tom2 &= 0xffffff8000000ULL;
+		rdmsr(MSR_K8_TOP_MEM2, low, high);
+		mtrr_tom2 = high;
+		mtrr_tom2 <<= 32;
+		mtrr_tom2 |= low;
+		mtrr_tom2 &= 0xffffff800000ULL;
 	}
 	if (mtrr_show) {
 		int high_width;
@@ -251,9 +265,9 @@ void __init get_mtrr_state(void)
 			else
 				printk(KERN_INFO "MTRR %u disabled\n", i);
 		}
-		if (tom2) {
+		if (mtrr_tom2) {
 			printk(KERN_INFO "TOM2: %016llx aka %lldM\n",
-					  tom2, tom2>>20);
+					  mtrr_tom2, mtrr_tom2>>20);
 		}
 	}
 	mtrr_state_set = 1;
@@ -328,7 +342,7 @@ static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords)
 
 	if (lo != msrwords[0] || hi != msrwords[1]) {
 		if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
-		    boot_cpu_data.x86 == 15 &&
+		    (boot_cpu_data.x86 >= 0x0f && boot_cpu_data.x86 <= 0x11) &&
 		    ((msrwords[0] | msrwords[1]) & K8_MTRR_RDMEM_WRMEM_MASK))
 			k8_enable_fixed_iorrs();
 		mtrr_wrmsr(msr, msrwords[0], msrwords[1]);

arch/x86/kernel/cpu/mtrr/mtrr.h

@@ -81,6 +81,8 @@ void set_mtrr_done(struct set_mtrr_context *ctxt);
 void set_mtrr_cache_disable(struct set_mtrr_context *ctxt);
 void set_mtrr_prepare_save(struct set_mtrr_context *ctxt);
 
+void fill_mtrr_var_range(unsigned int index,
+		u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi);
 void get_mtrr_state(void);
 
 extern void set_mtrr_ops(struct mtrr_ops * ops);
@@ -92,6 +94,7 @@ extern struct mtrr_ops * mtrr_if;
 #define use_intel()	(mtrr_if && mtrr_if->use_intel_if == 1)
 
 extern unsigned int num_var_ranges;
+extern u64 mtrr_tom2;
 
 void mtrr_state_warn(void);
 const char *mtrr_attrib_to_str(int x);

arch/x86/kernel/efi.c

@@ -213,6 +213,48 @@ unsigned long efi_get_time(void)
 		      eft.minute, eft.second);
 }
 
+/*
+ * Tell the kernel about the EFI memory map.  This might include
+ * more than the max 128 entries that can fit in the e820 legacy
+ * (zeropage) memory map.
+ */
+
+static void __init add_efi_memmap(void)
+{
+	void *p;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		efi_memory_desc_t *md = p;
+		unsigned long long start = md->phys_addr;
+		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+		int e820_type;
+
+		if (md->attribute & EFI_MEMORY_WB)
+			e820_type = E820_RAM;
+		else
+			e820_type = E820_RESERVED;
+		e820_add_region(start, size, e820_type);
+	}
+	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+}
+
+void __init efi_reserve_early(void)
+{
+	unsigned long pmap;
+
+	pmap = boot_params.efi_info.efi_memmap;
+#ifdef CONFIG_X86_64
+	pmap += (__u64)boot_params.efi_info.efi_memmap_hi << 32;
+#endif
+	memmap.phys_map = (void *)pmap;
+	memmap.nr_map = boot_params.efi_info.efi_memmap_size /
+		boot_params.efi_info.efi_memdesc_size;
+	memmap.desc_version = boot_params.efi_info.efi_memdesc_version;
+	memmap.desc_size = boot_params.efi_info.efi_memdesc_size;
+	reserve_early(pmap, pmap + memmap.nr_map * memmap.desc_size,
+		      "EFI memmap");
+}
+
 #if EFI_DEBUG
 static void __init print_efi_memmap(void)
 {
@@ -242,21 +284,11 @@ void __init efi_init(void)
 	int i = 0;
 	void *tmp;
 
-#ifdef CONFIG_X86_32
 	efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab;
-	memmap.phys_map = (void *)boot_params.efi_info.efi_memmap;
-#else
-	efi_phys.systab = (efi_system_table_t *)
-		(boot_params.efi_info.efi_systab |
-		 ((__u64)boot_params.efi_info.efi_systab_hi<<32));
-	memmap.phys_map = (void *)
-		(boot_params.efi_info.efi_memmap |
-		 ((__u64)boot_params.efi_info.efi_memmap_hi<<32));
+#ifdef CONFIG_X86_64
+	efi_phys.systab = (void *)efi_phys.systab +
+		((__u64)boot_params.efi_info.efi_systab_hi<<32);
 #endif
-	memmap.nr_map = boot_params.efi_info.efi_memmap_size /
-		boot_params.efi_info.efi_memdesc_size;
-	memmap.desc_version = boot_params.efi_info.efi_memdesc_version;
-	memmap.desc_size = boot_params.efi_info.efi_memdesc_size;
 
 	efi.systab = early_ioremap((unsigned long)efi_phys.systab,
 				   sizeof(efi_system_table_t));
@@ -370,6 +402,7 @@ void __init efi_init(void)
 	if (memmap.desc_size != sizeof(efi_memory_desc_t))
 		printk(KERN_WARNING "Kernel-defined memdesc"
 		       "doesn't match the one from EFI!\n");
+	add_efi_memmap();
 
 	/* Setup for EFI runtime service */
 	reboot_type = BOOT_EFI;

arch/x86/kernel/efi_64.c

@@ -97,13 +97,7 @@ void __init efi_call_phys_epilog(void)
 	early_runtime_code_mapping_set_exec(0);
 }
 
-void __init efi_reserve_bootmem(void)
-{
-	reserve_bootmem_generic((unsigned long)memmap.phys_map,
-				memmap.nr_map * memmap.desc_size);
-}
-
-void __iomem * __init efi_ioremap(unsigned long phys_addr, unsigned long size)
+void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size)
 {
 	static unsigned pages_mapped __initdata;
 	unsigned i, pages;

arch/x86/kernel/genapic_64.c

@@ -51,7 +51,7 @@ void __init setup_apic_routing(void)
 	else
 #endif
 
-	if (num_possible_cpus() <= 8)
+	if (max_physical_apicid < 8)
 		genapic = &apic_flat;
 	else
 		genapic = &apic_physflat;

arch/x86/kernel/head.c

+#include <linux/kernel.h>
+#include <linux/init.h>
+
+#include <asm/setup.h>
+#include <asm/bios_ebda.h>
+
+#define BIOS_LOWMEM_KILOBYTES 0x413
+
+/*
+ * The BIOS places the EBDA/XBDA at the top of conventional
+ * memory, and usually decreases the reported amount of
+ * conventional memory (int 0x12) too. This also contains a
+ * workaround for Dell systems that neglect to reserve EBDA.
+ * The same workaround also avoids a problem with the AMD768MPX
+ * chipset: reserve a page before VGA to prevent PCI prefetch
+ * into it (errata #56). Usually the page is reserved anyways,
+ * unless you have no PS/2 mouse plugged in.
+ */
+void __init reserve_ebda_region(void)
+{
+	unsigned int lowmem, ebda_addr;
+
+	/* To determine the position of the EBDA and the */
+	/* end of conventional memory, we need to look at */
+	/* the BIOS data area. In a paravirtual environment */
+	/* that area is absent. We'll just have to assume */
+	/* that the paravirt case can handle memory setup */
+	/* correctly, without our help. */
+	if (paravirt_enabled())
+		return;
+
+	/* end of low (conventional) memory */
+	lowmem = *(unsigned short *)__va(BIOS_LOWMEM_KILOBYTES);
+	lowmem <<= 10;
+
+	/* start of EBDA area */
+	ebda_addr = get_bios_ebda();
+
+	/* Fixup: bios puts an EBDA in the top 64K segment */
+	/* of conventional memory, but does not adjust lowmem. */
+	if ((lowmem - ebda_addr) <= 0x10000)
+		lowmem = ebda_addr;
+
+	/* Fixup: bios does not report an EBDA at all. */
+	/* Some old Dells seem to need 4k anyhow (bugzilla 2990) */
+	if ((ebda_addr == 0) && (lowmem >= 0x9f000))
+		lowmem = 0x9f000;
+
+	/* Paranoia: should never happen, but... */
+	if ((lowmem == 0) || (lowmem >= 0x100000))
+		lowmem = 0x9f000;
+
+	/* reserve all memory between lowmem and the 1MB mark */
+	reserve_early(lowmem, 0x100000, "BIOS reserved");
+}
+
+void __init reserve_setup_data(void)
+{
+	struct setup_data *data;
+	u64 pa_data;
+	char buf[32];
+
+	if (boot_params.hdr.version < 0x0209)
+		return;
+	pa_data = boot_params.hdr.setup_data;
+	while (pa_data) {
+		data = early_ioremap(pa_data, sizeof(*data));
+		sprintf(buf, "setup data %x", data->type);
+		reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf);
+		pa_data = data->next;
+		early_iounmap(data, sizeof(*data));
+	}
+}

arch/x86/kernel/head32.c

@@ -8,7 +8,34 @@
 #include <linux/init.h>
 #include <linux/start_kernel.h>
 
+#include <asm/setup.h>
+#include <asm/sections.h>
+#include <asm/e820.h>
+#include <asm/bios_ebda.h>
+
 void __init i386_start_kernel(void)
 {
+	reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS");
+
+#ifdef CONFIG_BLK_DEV_INITRD
+	/* Reserve INITRD */
+	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
+		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
+		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
+	}
+#endif
+	reserve_early(init_pg_tables_start, init_pg_tables_end,
+			"INIT_PG_TABLE");
+
+	reserve_ebda_region();
+
+	/*
+	 * At this point everything still needed from the boot loader
+	 * or BIOS or kernel text should be early reserved or marked not
+	 * RAM in e820. All other memory is free game.
+	 */
+
 	start_kernel();
 }

arch/x86/kernel/head64.c

@@ -51,74 +51,6 @@ static void __init copy_bootdata(char *real_mode_data)
 	}
 }
 
-#define BIOS_LOWMEM_KILOBYTES 0x413
-
-/*
- * The BIOS places the EBDA/XBDA at the top of conventional
- * memory, and usually decreases the reported amount of
- * conventional memory (int 0x12) too. This also contains a
- * workaround for Dell systems that neglect to reserve EBDA.
- * The same workaround also avoids a problem with the AMD768MPX
- * chipset: reserve a page before VGA to prevent PCI prefetch
- * into it (errata #56). Usually the page is reserved anyways,
- * unless you have no PS/2 mouse plugged in.
- */
-static void __init reserve_ebda_region(void)
-{
-	unsigned int lowmem, ebda_addr;
-
-	/* To determine the position of the EBDA and the */
-	/* end of conventional memory, we need to look at */
-	/* the BIOS data area. In a paravirtual environment */
-	/* that area is absent. We'll just have to assume */
-	/* that the paravirt case can handle memory setup */
-	/* correctly, without our help. */
-	if (paravirt_enabled())
-		return;
-
-	/* end of low (conventional) memory */
-	lowmem = *(unsigned short *)__va(BIOS_LOWMEM_KILOBYTES);
-	lowmem <<= 10;
-
-	/* start of EBDA area */
-	ebda_addr = get_bios_ebda();
-
-	/* Fixup: bios puts an EBDA in the top 64K segment */
-	/* of conventional memory, but does not adjust lowmem. */
-	if ((lowmem - ebda_addr) <= 0x10000)
-		lowmem = ebda_addr;
-
-	/* Fixup: bios does not report an EBDA at all. */
-	/* Some old Dells seem to need 4k anyhow (bugzilla 2990) */
-	if ((ebda_addr == 0) && (lowmem >= 0x9f000))
-		lowmem = 0x9f000;
-
-	/* Paranoia: should never happen, but... */
-	if ((lowmem == 0) || (lowmem >= 0x100000))
-		lowmem = 0x9f000;
-
-	/* reserve all memory between lowmem and the 1MB mark */
-	reserve_early(lowmem, 0x100000, "BIOS reserved");
-}
-
-static void __init reserve_setup_data(void)
-{
-	struct setup_data *data;
-	unsigned long pa_data;
-	char buf[32];
-
-	if (boot_params.hdr.version < 0x0209)
-		return;
-	pa_data = boot_params.hdr.setup_data;
-	while (pa_data) {
-		data = early_ioremap(pa_data, sizeof(*data));
-		sprintf(buf, "setup data %x", data->type);
-		reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf);
-		pa_data = data->next;
-		early_iounmap(data, sizeof(*data));
-	}
-}
-
 void __init x86_64_start_kernel(char * real_mode_data)
 {
 	int i;

arch/x86/kernel/head_32.S

@@ -194,6 +194,7 @@ default_entry:
 	xorl %ebx,%ebx				/* %ebx is kept at zero */
 
 	movl $pa(pg0), %edi
+	movl %edi, pa(init_pg_tables_start)
 	movl $pa(swapper_pg_pmd), %edx
 	movl $PTE_ATTR, %eax
 10:
@@ -219,6 +220,8 @@ default_entry:
 	jb 10b
 1:
 	movl %edi,pa(init_pg_tables_end)
+	shrl $12, %eax
+	movl %eax, pa(max_pfn_mapped)
 
 	/* Do early initialization of the fixmap area */
 	movl $pa(swapper_pg_fixmap)+PDE_ATTR,%eax
@@ -228,6 +231,7 @@ default_entry:
 page_pde_offset = (__PAGE_OFFSET >> 20);
 
 	movl $pa(pg0), %edi
+	movl %edi, pa(init_pg_tables_start)
 	movl $pa(swapper_pg_dir), %edx
 	movl $PTE_ATTR, %eax
 10:
@@ -249,6 +253,8 @@ page_pde_offset = (__PAGE_OFFSET >> 20);
 	cmpl %ebp,%eax
 	jb 10b
 	movl %edi,pa(init_pg_tables_end)
+	shrl $12, %eax
+	movl %eax, pa(max_pfn_mapped)
 
 	/* Do early initialization of the fixmap area */
 	movl $pa(swapper_pg_fixmap)+PDE_ATTR,%eax

arch/x86/kernel/numaq_32.c

@@ -31,6 +31,8 @@
 #include <asm/numaq.h>
 #include <asm/topology.h>
 #include <asm/processor.h>
+#include <asm/mpspec.h>
+#include <asm/e820.h>
 
 #define	MB_TO_PAGES(addr) ((addr) << (20 - PAGE_SHIFT))
 
@@ -58,6 +60,8 @@ static void __init smp_dump_qct(void)
 			node_end_pfn[node] = MB_TO_PAGES(
 				eq->hi_shrd_mem_start + eq->hi_shrd_mem_size);
 
+			e820_register_active_regions(node, node_start_pfn[node],
+							node_end_pfn[node]);
 			memory_present(node,
 				node_start_pfn[node], node_end_pfn[node]);
 			node_remap_size[node] = node_memmap_size_bytes(node,
@@ -67,13 +71,24 @@ static void __init smp_dump_qct(void)
 	}
 }
 
-/*
- * Unlike Summit, we don't really care to let the NUMA-Q
- * fall back to flat mode.  Don't compile for NUMA-Q
- * unless you really need it!
+static __init void early_check_numaq(void)
+{
+	/*
+	 * Find possible boot-time SMP configuration:
+	 */
+	early_find_smp_config();
+	/*
+	 * get boot-time SMP configuration:
 	 */
+	if (smp_found_config)
+		early_get_smp_config();
+}
+
 int __init get_memcfg_numaq(void)
 {
+	early_check_numaq();
+	if (!found_numaq)
+		return 0;
 	smp_dump_qct();
 	return 1;
 }

arch/x86/kernel/setup.c

@@ -17,6 +17,7 @@ unsigned int num_processors;
 unsigned disabled_cpus __cpuinitdata;
 /* Processor that is doing the boot up */
 unsigned int boot_cpu_physical_apicid = -1U;
+unsigned int max_physical_apicid;
 EXPORT_SYMBOL(boot_cpu_physical_apicid);
 
 DEFINE_PER_CPU(u16, x86_cpu_to_apicid) = BAD_APICID;
@@ -137,3 +138,28 @@ void __init setup_per_cpu_areas(void)
 }
 
 #endif
+
+void __init parse_setup_data(void)
+{
+	struct setup_data *data;
+	u64 pa_data;
+
+	if (boot_params.hdr.version < 0x0209)
+		return;
+	pa_data = boot_params.hdr.setup_data;
+	while (pa_data) {
+		data = early_ioremap(pa_data, PAGE_SIZE);
+		switch (data->type) {
+		case SETUP_E820_EXT:
+			parse_e820_ext(data, pa_data);
+			break;
+		default:
+			break;
+		}
+#ifndef CONFIG_DEBUG_BOOT_PARAMS
+		free_early(pa_data, pa_data+sizeof(*data)+data->len);
+#endif
+		pa_data = data->next;
+		early_iounmap(data, PAGE_SIZE);
+	}
+}

arch/x86/kernel/smpboot.c

@@ -554,23 +554,6 @@ cpumask_t cpu_coregroup_map(int cpu)
 		return c->llc_shared_map;
 }
 
-#ifdef CONFIG_X86_32
-/*
- * We are called very early to get the low memory for the
- * SMP bootup trampoline page.
- */
-void __init smp_alloc_memory(void)
-{
-	trampoline_base = alloc_bootmem_low_pages(PAGE_SIZE);
-	/*
-	 * Has to be in very low memory so we can execute
-	 * real-mode AP code.
-	 */
-	if (__pa(trampoline_base) >= 0x9F000)
-		BUG();
-}
-#endif
-
 static void impress_friends(void)
 {
 	int cpu;

arch/x86/kernel/summit_32.c

@@ -36,7 +36,9 @@ static struct rio_table_hdr *rio_table_hdr __initdata;
 static struct scal_detail   *scal_devs[MAX_NUMNODES] __initdata;
 static struct rio_detail    *rio_devs[MAX_NUMNODES*4] __initdata;
 
+#ifndef CONFIG_X86_NUMAQ
 static int mp_bus_id_to_node[MAX_MP_BUSSES] __initdata;
+#endif
 
 static int __init setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus)
 {

arch/x86/kernel/trampoline.c

@@ -2,7 +2,7 @@
 
 #include <asm/trampoline.h>
 
-/* ready for x86_64, no harm for x86, since it will overwrite after alloc */
+/* ready for x86_64 and x86 */
 unsigned char *trampoline_base = __va(TRAMPOLINE_BASE);
 
 /*

arch/x86/mach-es7000/Makefile

@@ -3,4 +3,3 @@
 #
 
 obj-$(CONFIG_X86_ES7000)	:= es7000plat.o
-obj-$(CONFIG_X86_GENERICARCH)	:= es7000plat.o

arch/x86/mach-generic/Makefile

@@ -4,5 +4,9 @@
 
 EXTRA_CFLAGS			:= -Iarch/x86/kernel
 
-obj-y		:= probe.o summit.o bigsmp.o es7000.o default.o 
-obj-y		+= ../../x86/mach-es7000/
+obj-y				:= probe.o default.o
+obj-$(CONFIG_X86_NUMAQ)		+= numaq.o
+obj-$(CONFIG_X86_SUMMIT)	+= summit.o
+obj-$(CONFIG_X86_BIGSMP)	+= bigsmp.o
+obj-$(CONFIG_X86_ES7000)	+= es7000.o
+obj-$(CONFIG_X86_ES7000)	+= ../../x86/mach-es7000/