powerpc: Get 64-bit configs to compile with ARCH=powerpc

This is a bunch of mostly small fixes that are needed to get
ARCH=powerpc to compile for 64-bit.  This adds setup_64.c from
arch/ppc64/kernel/setup.c and locks.c from arch/ppc64/lib/locks.c.

Signed-off-by: Paul Mackerras <paulus@samba.org>

22 files changed, 1631 insertions, 104 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index bc063edd6de0..47a8eb6e7e39 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -10,6 +10,12 @@ CFLAGS_prom_init.o      += -fPIC
 CFLAGS_btext.o		+= -fPIC
 endif
 
+obj-y				:= semaphore.o traps.o
+obj-$(CONFIG_ALTIVEC)		+= vecemu.o vector.o
+obj-$(CONFIG_POWER4)		+= idle_power4.o
+
+ifeq ($(CONFIG_PPC_MERGE),y)
+
 extra-$(CONFIG_PPC_STD_MMU)	:= head_32.o
 extra-$(CONFIG_PPC64)		:= head_64.o
 extra-$(CONFIG_40x)		:= head_4xx.o
@@ -21,15 +27,12 @@ extra-$(CONFIG_PPC64)		+= entry_64.o
 extra-$(CONFIG_PPC_FPU)		+= fpu.o
 extra-y				+= vmlinux.lds
 
-obj-y				+= traps.o prom.o semaphore.o
+obj-y				+= process.o init_task.o \
+				   prom.o systbl.o
 obj-$(CONFIG_PPC32)		+= entry_32.o setup_32.o misc_32.o
-obj-$(CONFIG_PPC64)		+= idle_power4.o
-obj-$(CONFIG_PPC64)		+= misc_64.o
-ifeq ($(CONFIG_PPC32),y)
+obj-$(CONFIG_PPC64)		+= setup_64.o misc_64.o
 obj-$(CONFIG_PPC_OF)		+= prom_init.o of_device.o
 obj-$(CONFIG_MODULES)		+= ppc_ksyms.o
-endif
-obj-$(CONFIG_ALTIVEC)		+= vecemu.o vector.o
 obj-$(CONFIG_BOOTX_TEXT)	+= btext.o
 
 ifeq ($(CONFIG_PPC_ISERIES),y)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 3a247c033e8b..ddf0c81e1958 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -111,6 +111,7 @@ int main(void)
 	DEFINE(ICACHEL1LOGLINESIZE, offsetof(struct ppc64_caches, log_iline_size));
 	DEFINE(ICACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, ilines_per_page));
 	DEFINE(PLATFORM, offsetof(struct systemcfg, platform));
+	DEFINE(PLATFORM_LPAR, PLATFORM_LPAR);
 
 	/* paca */
 	DEFINE(PACA_SIZE, sizeof(struct paca_struct));
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index 44f5d98e27c0..bdfba92b2b38 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -50,7 +50,7 @@ static unsigned char vga_font[cmapsz];
 int boot_text_mapped;
 int force_printk_to_btext = 0;
 
-
+#ifdef CONFIG_PPC32
 /* Calc BAT values for mapping the display and store them
  * in disp_BAT.  Those values are then used from head.S to map
  * the display during identify_machine() and MMU_Init()
@@ -93,6 +93,7 @@ btext_prepare_BAT(void)
 	}
 	logicalDisplayBase = (void *) (vaddr + lowbits);
 }
+#endif
 
 /* This function will enable the early boot text when doing OF booting. This
  * way, xmon output should work too
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 3fcac3c37b9b..a4ceb9ae20fc 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -746,6 +746,7 @@ bad_stack:
  * any task or sent any task a signal, you should use
  * ret_from_except or ret_from_except_lite instead of this.
  */
+	.globl	fast_exception_return
 fast_exception_return:
 	ld	r12,_MSR(r1)
 	ld	r11,_NIP(r1)
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 91a562e3257b..010554e5fe48 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -51,6 +51,7 @@
 #include <asm/commproc.h>
 #endif
 
+#ifdef CONFIG_PPC32
 extern void transfer_to_handler(void);
 extern void do_IRQ(struct pt_regs *regs);
 extern void machine_check_exception(struct pt_regs *regs);
@@ -61,14 +62,12 @@ extern int do_signal(sigset_t *, struct pt_regs *);
 extern int pmac_newworld;
 extern int sys_sigreturn(struct pt_regs *regs);
 
-long long __ashrdi3(long long, int);
-long long __ashldi3(long long, int);
-long long __lshrdi3(long long, int);
-
-extern unsigned long mm_ptov (unsigned long paddr);
-
 EXPORT_SYMBOL(clear_pages);
-EXPORT_SYMBOL(clear_user_page);
+EXPORT_SYMBOL(ISA_DMA_THRESHOLD);
+EXPORT_SYMBOL(DMA_MODE_READ);
+EXPORT_SYMBOL(DMA_MODE_WRITE);
+EXPORT_SYMBOL(__div64_32);
+
 EXPORT_SYMBOL(do_signal);
 EXPORT_SYMBOL(transfer_to_handler);
 EXPORT_SYMBOL(do_IRQ);
@@ -77,12 +76,8 @@ EXPORT_SYMBOL(alignment_exception);
 EXPORT_SYMBOL(program_check_exception);
 EXPORT_SYMBOL(single_step_exception);
 EXPORT_SYMBOL(sys_sigreturn);
-EXPORT_SYMBOL(ppc_n_lost_interrupts);
-EXPORT_SYMBOL(ppc_lost_interrupts);
+#endif
 
-EXPORT_SYMBOL(ISA_DMA_THRESHOLD);
-EXPORT_SYMBOL(DMA_MODE_READ);
-EXPORT_SYMBOL(DMA_MODE_WRITE);
 #if defined(CONFIG_PPC_PREP)
 EXPORT_SYMBOL(_prep_type);
 EXPORT_SYMBOL(ucSystemType);
@@ -110,7 +105,6 @@ EXPORT_SYMBOL(strnlen);
 EXPORT_SYMBOL(strcmp);
 EXPORT_SYMBOL(strncmp);
 EXPORT_SYMBOL(strcasecmp);
-EXPORT_SYMBOL(__div64_32);
 
 EXPORT_SYMBOL(csum_partial);
 EXPORT_SYMBOL(csum_partial_copy_generic);
@@ -132,21 +126,21 @@ EXPORT_SYMBOL(_insw_ns);
 EXPORT_SYMBOL(_outsw_ns);
 EXPORT_SYMBOL(_insl_ns);
 EXPORT_SYMBOL(_outsl_ns);
-EXPORT_SYMBOL(iopa);
-EXPORT_SYMBOL(mm_ptov);
 EXPORT_SYMBOL(ioremap);
 #ifdef CONFIG_44x
 EXPORT_SYMBOL(ioremap64);
 #endif
 EXPORT_SYMBOL(__ioremap);
 EXPORT_SYMBOL(iounmap);
+#ifdef CONFIG_PPC32
 EXPORT_SYMBOL(ioremap_bot);	/* aka VMALLOC_END */
+#endif
 
-#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_IDE_MODULE)
+#if defined(CONFIG_PPC32) && (defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_IDE_MODULE))
 EXPORT_SYMBOL(ppc_ide_md);
 #endif
 
-#ifdef CONFIG_PCI
+#if defined(CONFIG_PCI) && defined(CONFIG_PPC32)
 EXPORT_SYMBOL(isa_io_base);
 EXPORT_SYMBOL(isa_mem_base);
 EXPORT_SYMBOL(pci_dram_offset);
@@ -168,31 +162,31 @@ EXPORT_SYMBOL(flush_dcache_all);
 EXPORT_SYMBOL(start_thread);
 EXPORT_SYMBOL(kernel_thread);
 
-EXPORT_SYMBOL(flush_instruction_cache);
 EXPORT_SYMBOL(giveup_fpu);
+#ifdef CONFIG_ALTIVEC
+EXPORT_SYMBOL(giveup_altivec);
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_SPE
+EXPORT_SYMBOL(giveup_spe);
+#endif /* CONFIG_SPE */
+
 #ifdef CONFIG_PPC64
 EXPORT_SYMBOL(__flush_icache_range);
 #else
+EXPORT_SYMBOL(flush_instruction_cache);
 EXPORT_SYMBOL(flush_icache_range);
-#endif
-EXPORT_SYMBOL(flush_dcache_range);
-EXPORT_SYMBOL(flush_icache_user_range);
-EXPORT_SYMBOL(flush_dcache_page);
 EXPORT_SYMBOL(flush_tlb_kernel_range);
 EXPORT_SYMBOL(flush_tlb_page);
 EXPORT_SYMBOL(_tlbie);
-#ifdef CONFIG_ALTIVEC
-EXPORT_SYMBOL(giveup_altivec);
-#endif /* CONFIG_ALTIVEC */
-#ifdef CONFIG_SPE
-EXPORT_SYMBOL(giveup_spe);
-#endif /* CONFIG_SPE */
+#endif
+EXPORT_SYMBOL(flush_dcache_range);
+
 #ifdef CONFIG_SMP
 EXPORT_SYMBOL(smp_call_function);
+#ifdef CONFIG_PPC32
 EXPORT_SYMBOL(smp_hw_index);
 #endif
-
-EXPORT_SYMBOL(ppc_md);
+#endif
 
 #ifdef CONFIG_ADB
 EXPORT_SYMBOL(adb_request);
@@ -205,25 +199,27 @@ EXPORT_SYMBOL(adb_try_handler_change);
 EXPORT_SYMBOL(cuda_request);
 EXPORT_SYMBOL(cuda_poll);
 #endif /* CONFIG_ADB_CUDA */
-#ifdef CONFIG_PPC_MULTIPLATFORM
+#if defined(CONFIG_PPC_MULTIPLATFORM) && defined(CONFIG_PPC32)
 EXPORT_SYMBOL(_machine);
 #endif
 #ifdef CONFIG_PPC_PMAC
 EXPORT_SYMBOL(sys_ctrler);
-EXPORT_SYMBOL(pmac_newworld);
 #endif
 #ifdef CONFIG_VT
 EXPORT_SYMBOL(kd_mksound);
 #endif
 EXPORT_SYMBOL(to_tm);
 
-EXPORT_SYMBOL(pm_power_off);
-
+#ifdef CONFIG_PPC32
+long long __ashrdi3(long long, int);
+long long __ashldi3(long long, int);
+long long __lshrdi3(long long, int);
 EXPORT_SYMBOL(__ashrdi3);
 EXPORT_SYMBOL(__ashldi3);
 EXPORT_SYMBOL(__lshrdi3);
+#endif
+
 EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(cacheable_memcpy);
 EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memscan);
@@ -234,17 +230,14 @@ EXPORT_SYMBOL(memchr);
 EXPORT_SYMBOL(screen_info);
 #endif
 
+#ifdef CONFIG_PPC32
+EXPORT_SYMBOL(pm_power_off);
 EXPORT_SYMBOL(__delay);
 EXPORT_SYMBOL(timer_interrupt);
 EXPORT_SYMBOL(irq_desc);
 EXPORT_SYMBOL(tb_ticks_per_jiffy);
-EXPORT_SYMBOL(get_wchan);
 EXPORT_SYMBOL(console_drivers);
-
-#ifdef CONFIG_PPC_ISERIES
-EXPORT_SYMBOL(local_irq_disable);
-EXPORT_SYMBOL(local_irq_enable);
-EXPORT_SYMBOL(local_get_flags);
+EXPORT_SYMBOL(cacheable_memcpy);
 #endif
 
 #ifdef CONFIG_XMON
@@ -255,22 +248,6 @@ EXPORT_SYMBOL(__up);
 EXPORT_SYMBOL(__down);
 EXPORT_SYMBOL(__down_interruptible);
 
-#if defined(CONFIG_KGDB) || defined(CONFIG_XMON)
-extern void (*debugger)(struct pt_regs *regs);
-extern int (*debugger_bpt)(struct pt_regs *regs);
-extern int (*debugger_sstep)(struct pt_regs *regs);
-extern int (*debugger_iabr_match)(struct pt_regs *regs);
-extern int (*debugger_dabr_match)(struct pt_regs *regs);
-extern void (*debugger_fault_handler)(struct pt_regs *regs);
-
-EXPORT_SYMBOL(debugger);
-EXPORT_SYMBOL(debugger_bpt);
-EXPORT_SYMBOL(debugger_sstep);
-EXPORT_SYMBOL(debugger_iabr_match);
-EXPORT_SYMBOL(debugger_dabr_match);
-EXPORT_SYMBOL(debugger_fault_handler);
-#endif
-
 #ifdef  CONFIG_8xx
 EXPORT_SYMBOL(cpm_install_handler);
 EXPORT_SYMBOL(cpm_free_handler);
@@ -280,22 +257,24 @@ EXPORT_SYMBOL(cpm_free_handler);
 EXPORT_SYMBOL(__res);
 #endif
 
+#ifdef CONFIG_PPC32
 EXPORT_SYMBOL(next_mmu_context);
 EXPORT_SYMBOL(set_context);
-EXPORT_SYMBOL_GPL(__handle_mm_fault); /* For MOL */
 EXPORT_SYMBOL(disarm_decr);
-#ifdef CONFIG_PPC_STD_MMU
+#endif
+
+#ifdef CONFIG_PPC_STD_MMU_32
 extern long mol_trampoline;
 EXPORT_SYMBOL(mol_trampoline); /* For MOL */
 EXPORT_SYMBOL(flush_hash_pages); /* For MOL */
+EXPORT_SYMBOL_GPL(__handle_mm_fault); /* For MOL */
 #ifdef CONFIG_SMP
 extern int mmu_hash_lock;
 EXPORT_SYMBOL(mmu_hash_lock); /* For MOL */
 #endif /* CONFIG_SMP */
 extern long *intercept_table;
 EXPORT_SYMBOL(intercept_table);
-#endif /* CONFIG_PPC_STD_MMU */
-EXPORT_SYMBOL(cur_cpu_spec);
+#endif /* CONFIG_PPC_STD_MMU_32 */
 #ifdef CONFIG_PPC_PMAC
 extern unsigned long agp_special_page;
 EXPORT_SYMBOL(agp_special_page);
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index dc3d24ea3bff..ce0dff1caa80 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -47,6 +47,10 @@
 #include <asm/sections.h>
 #include <asm/machdep.h>
 #include <asm/pSeries_reconfig.h>
+#include <asm/pci-bridge.h>
+#ifdef CONFIG_PPC64
+#include <asm/systemcfg.h>
+#endif
 
 #ifdef DEBUG
 #define DBG(fmt...) printk(KERN_ERR fmt)
@@ -1072,7 +1076,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 	} else {
 		/* Check if it's the boot-cpu, set it's hw index in paca now */
 		if (get_flat_dt_prop(node, "linux,boot-cpu", NULL) != NULL) {
-			u32 *prop = get_flat_dt_prop(node, "reg", NULL);
+			prop = get_flat_dt_prop(node, "reg", NULL);
 			set_hard_smp_processor_id(0, prop == NULL ? 0 : *prop);
 			boot_cpuid_phys = get_hard_smp_processor_id(0);
 		}
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
new file mode 100644
index 000000000000..212b00823f82
--- /dev/null
+++ b/arch/powerpc/kernel/setup_64.c
@@ -0,0 +1,1324 @@
+/*
+ * 
+ * Common boot and setup code.
+ *
+ * Copyright (C) 2001 PPC64 Team, IBM Corp
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/reboot.h>
+#include <linux/delay.h>
+#include <linux/initrd.h>
+#include <linux/ide.h>
+#include <linux/seq_file.h>
+#include <linux/ioport.h>
+#include <linux/console.h>
+#include <linux/utsname.h>
+#include <linux/tty.h>
+#include <linux/root_dev.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/unistd.h>
+#include <linux/serial.h>
+#include <linux/serial_8250.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/processor.h>
+#include <asm/pgtable.h>
+#include <asm/bootinfo.h>
+#include <asm/smp.h>
+#include <asm/elf.h>
+#include <asm/machdep.h>
+#include <asm/paca.h>
+#include <asm/ppcdebug.h>
+#include <asm/time.h>
+#include <asm/cputable.h>
+#include <asm/sections.h>
+#include <asm/btext.h>
+#include <asm/nvram.h>
+#include <asm/setup.h>
+#include <asm/system.h>
+#include <asm/rtas.h>
+#include <asm/iommu.h>
+#include <asm/serial.h>
+#include <asm/cache.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/lmb.h>
+#include <asm/iSeries/ItLpNaca.h>
+#include <asm/firmware.h>
+#include <asm/systemcfg.h>
+
+#ifdef DEBUG
+#define DBG(fmt...) udbg_printf(fmt)
+#else
+#define DBG(fmt...)
+#endif
+
+/*
+ * Here are some early debugging facilities. You can enable one
+ * but your kernel will not boot on anything else if you do so
+ */
+
+/* This one is for use on LPAR machines that support an HVC console
+ * on vterm 0
+ */
+extern void udbg_init_debug_lpar(void);
+/* This one is for use on Apple G5 machines
+ */
+extern void udbg_init_pmac_realmode(void);
+/* That's RTAS panel debug */
+extern void call_rtas_display_status_delay(unsigned char c);
+/* Here's maple real mode debug */
+extern void udbg_init_maple_realmode(void);
+
+#define EARLY_DEBUG_INIT() do {} while(0)
+
+#if 0
+#define EARLY_DEBUG_INIT() udbg_init_debug_lpar()
+#define EARLY_DEBUG_INIT() udbg_init_maple_realmode()
+#define EARLY_DEBUG_INIT() udbg_init_pmac_realmode()
+#define EARLY_DEBUG_INIT()						\
+	do { udbg_putc = call_rtas_display_status_delay; } while(0)
+#endif
+
+/* extern void *stab; */
+extern unsigned long klimit;
+
+extern void mm_init_ppc64(void);
+extern void stab_initialize(unsigned long stab);
+extern void htab_initialize(void);
+extern void early_init_devtree(void *flat_dt);
+extern void unflatten_device_tree(void);
+
+extern void smp_release_cpus(void);
+
+int have_of = 1;
+int boot_cpuid = 0;
+int boot_cpuid_phys = 0;
+dev_t boot_dev;
+u64 ppc64_pft_size;
+
+struct ppc64_caches ppc64_caches;
+EXPORT_SYMBOL_GPL(ppc64_caches);
+
+/*
+ * These are used in binfmt_elf.c to put aux entries on the stack
+ * for each elf executable being started.
+ */
+int dcache_bsize;
+int icache_bsize;
+int ucache_bsize;
+
+/* The main machine-dep calls structure
+ */
+struct machdep_calls ppc_md;
+EXPORT_SYMBOL(ppc_md);
+
+#ifdef CONFIG_MAGIC_SYSRQ
+unsigned long SYSRQ_KEY;
+#endif /* CONFIG_MAGIC_SYSRQ */
+
+
+static int ppc64_panic_event(struct notifier_block *, unsigned long, void *);
+static struct notifier_block ppc64_panic_block = {
+	.notifier_call = ppc64_panic_event,
+	.priority = INT_MIN /* may not return; must be done last */
+};
+
+/*
+ * Perhaps we can put the pmac screen_info[] here
+ * on pmac as well so we don't need the ifdef's.
+ * Until we get multiple-console support in here
+ * that is.  -- Cort
+ * Maybe tie it to serial consoles, since this is really what
+ * these processors use on existing boards.  -- Dan
+ */ 
+struct screen_info screen_info = {
+	.orig_x = 0,
+	.orig_y = 25,
+	.orig_video_cols = 80,
+	.orig_video_lines = 25,
+	.orig_video_isVGA = 1,
+	.orig_video_points = 16
+};
+
+#ifdef CONFIG_SMP
+
+static int smt_enabled_cmdline;
+
+/* Look for ibm,smt-enabled OF option */
+static void check_smt_enabled(void)
+{
+	struct device_node *dn;
+	char *smt_option;
+
+	/* Allow the command line to overrule the OF option */
+	if (smt_enabled_cmdline)
+		return;
+
+	dn = of_find_node_by_path("/options");
+
+	if (dn) {
+		smt_option = (char *)get_property(dn, "ibm,smt-enabled", NULL);
+
+                if (smt_option) {
+			if (!strcmp(smt_option, "on"))
+				smt_enabled_at_boot = 1;
+			else if (!strcmp(smt_option, "off"))
+				smt_enabled_at_boot = 0;
+                }
+        }
+}
+
+/* Look for smt-enabled= cmdline option */
+static int __init early_smt_enabled(char *p)
+{
+	smt_enabled_cmdline = 1;
+
+	if (!p)
+		return 0;
+
+	if (!strcmp(p, "on") || !strcmp(p, "1"))
+		smt_enabled_at_boot = 1;
+	else if (!strcmp(p, "off") || !strcmp(p, "0"))
+		smt_enabled_at_boot = 0;
+
+	return 0;
+}
+early_param("smt-enabled", early_smt_enabled);
+
+/**
+ * setup_cpu_maps - initialize the following cpu maps:
+ *                  cpu_possible_map
+ *                  cpu_present_map
+ *                  cpu_sibling_map
+ *
+ * Having the possible map set up early allows us to restrict allocations
+ * of things like irqstacks to num_possible_cpus() rather than NR_CPUS.
+ *
+ * We do not initialize the online map here; cpus set their own bits in
+ * cpu_online_map as they come up.
+ *
+ * This function is valid only for Open Firmware systems.  finish_device_tree
+ * must be called before using this.
+ *
+ * While we're here, we may as well set the "physical" cpu ids in the paca.
+ */
+static void __init setup_cpu_maps(void)
+{
+	struct device_node *dn = NULL;
+	int cpu = 0;
+	int swap_cpuid = 0;
+
+	check_smt_enabled();
+
+	while ((dn = of_find_node_by_type(dn, "cpu")) && cpu < NR_CPUS) {
+		u32 *intserv;
+		int j, len = sizeof(u32), nthreads;
+
+		intserv = (u32 *)get_property(dn, "ibm,ppc-interrupt-server#s",
+					      &len);
+		if (!intserv)
+			intserv = (u32 *)get_property(dn, "reg", NULL);
+
+		nthreads = len / sizeof(u32);
+
+		for (j = 0; j < nthreads && cpu < NR_CPUS; j++) {
+			cpu_set(cpu, cpu_present_map);
+			set_hard_smp_processor_id(cpu, intserv[j]);
+
+			if (intserv[j] == boot_cpuid_phys)
+				swap_cpuid = cpu;
+			cpu_set(cpu, cpu_possible_map);
+			cpu++;
+		}
+	}
+
+	/* Swap CPU id 0 with boot_cpuid_phys, so we can always assume that
+	 * boot cpu is logical 0.
+	 */
+	if (boot_cpuid_phys != get_hard_smp_processor_id(0)) {
+		u32 tmp;
+		tmp = get_hard_smp_processor_id(0);
+		set_hard_smp_processor_id(0, boot_cpuid_phys);
+		set_hard_smp_processor_id(swap_cpuid, tmp);
+	}
+
+	/*
+	 * On pSeries LPAR, we need to know how many cpus
+	 * could possibly be added to this partition.
+	 */
+	if (systemcfg->platform == PLATFORM_PSERIES_LPAR &&
+				(dn = of_find_node_by_path("/rtas"))) {
+		int num_addr_cell, num_size_cell, maxcpus;
+		unsigned int *ireg;
+
+		num_addr_cell = prom_n_addr_cells(dn);
+		num_size_cell = prom_n_size_cells(dn);
+
+		ireg = (unsigned int *)
+			get_property(dn, "ibm,lrdr-capacity", NULL);
+
+		if (!ireg)
+			goto out;
+
+		maxcpus = ireg[num_addr_cell + num_size_cell];
+
+		/* Double maxcpus for processors which have SMT capability */
+		if (cpu_has_feature(CPU_FTR_SMT))
+			maxcpus *= 2;
+
+		if (maxcpus > NR_CPUS) {
+			printk(KERN_WARNING
+			       "Partition configured for %d cpus, "
+			       "operating system maximum is %d.\n",
+			       maxcpus, NR_CPUS);
+			maxcpus = NR_CPUS;
+		} else
+			printk(KERN_INFO "Partition configured for %d cpus.\n",
+			       maxcpus);
+
+		for (cpu = 0; cpu < maxcpus; cpu++)
+			cpu_set(cpu, cpu_possible_map);
+	out:
+		of_node_put(dn);
+	}
+
+	/*
+	 * Do the sibling map; assume only two threads per processor.
+	 */
+	for_each_cpu(cpu) {
+		cpu_set(cpu, cpu_sibling_map[cpu]);
+		if (cpu_has_feature(CPU_FTR_SMT))
+			cpu_set(cpu ^ 0x1, cpu_sibling_map[cpu]);
+	}
+
+	systemcfg->processorCount = num_present_cpus();
+}
+#endif /* CONFIG_SMP */
+
+extern struct machdep_calls pSeries_md;
+extern struct machdep_calls pmac_md;
+extern struct machdep_calls maple_md;
+extern struct machdep_calls bpa_md;
+extern struct machdep_calls iseries_md;
+
+/* Ultimately, stuff them in an elf section like initcalls... */
+static struct machdep_calls __initdata *machines[] = {
+#ifdef CONFIG_PPC_PSERIES
+	&pSeries_md,
+#endif /* CONFIG_PPC_PSERIES */
+#ifdef CONFIG_PPC_PMAC
+	&pmac_md,
+#endif /* CONFIG_PPC_PMAC */
+#ifdef CONFIG_PPC_MAPLE
+	&maple_md,
+#endif /* CONFIG_PPC_MAPLE */
+#ifdef CONFIG_PPC_BPA
+	&bpa_md,
+#endif
+#ifdef CONFIG_PPC_ISERIES
+	&iseries_md,
+#endif
+	NULL
+};
+
+/*
+ * Early initialization entry point. This is called by head.S
+ * with MMU translation disabled. We rely on the "feature" of
+ * the CPU that ignores the top 2 bits of the address in real
+ * mode so we can access kernel globals normally provided we
+ * only toy with things in the RMO region. From here, we do
+ * some early parsing of the device-tree to setup out LMB
+ * data structures, and allocate & initialize the hash table
+ * and segment tables so we can start running with translation
+ * enabled.
+ *
+ * It is this function which will call the probe() callback of
+ * the various platform types and copy the matching one to the
+ * global ppc_md structure. Your platform can eventually do
+ * some very early initializations from the probe() routine, but
+ * this is not recommended, be very careful as, for example, the
+ * device-tree is not accessible via normal means at this point.
+ */
+
+void __init early_setup(unsigned long dt_ptr)
+{
+	struct paca_struct *lpaca = get_paca();
+	static struct machdep_calls **mach;
+
+	/*
+	 * Enable early debugging if any specified (see top of
+	 * this file)
+	 */
+	EARLY_DEBUG_INIT();
+
+	DBG(" -> early_setup()\n");
+
+	/*
+	 * Fill the default DBG level (do we want to keep
+	 * that old mecanism around forever ?)
+	 */
+	ppcdbg_initialize();
+
+	/*
+	 * Do early initializations using the flattened device
+	 * tree, like retreiving the physical memory map or
+	 * calculating/retreiving the hash table size
+	 */
+	early_init_devtree(__va(dt_ptr));
+
+	/*
+	 * Iterate all ppc_md structures until we find the proper
+	 * one for the current machine type
+	 */
+	DBG("Probing machine type for platform %x...\n",
+	    systemcfg->platform);
+
+	for (mach = machines; *mach; mach++) {
+		if ((*mach)->probe(systemcfg->platform))
+			break;
+	}
+	/* What can we do if we didn't find ? */
+	if (*mach == NULL) {
+		DBG("No suitable machine found !\n");
+		for (;;);
+	}
+	ppc_md = **mach;
+
+	DBG("Found, Initializing memory management...\n");
+
+	/*
+	 * Initialize stab / SLB management
+	 */
+	if (!firmware_has_feature(FW_FEATURE_ISERIES))
+		stab_initialize(lpaca->stab_real);
+
+	/*
+	 * Initialize the MMU Hash table and create the linear mapping
+	 * of memory
+	 */
+	htab_initialize();
+
+	DBG(" <- early_setup()\n");
+}
+
+
+/*
+ * Initialize some remaining members of the ppc64_caches and systemcfg structures
+ * (at least until we get rid of them completely). This is mostly some
+ * cache informations about the CPU that will be used by cache flush
+ * routines and/or provided to userland
+ */
+static void __init initialize_cache_info(void)
+{
+	struct device_node *np;
+	unsigned long num_cpus = 0;
+
+	DBG(" -> initialize_cache_info()\n");
+
+	for (np = NULL; (np = of_find_node_by_type(np, "cpu"));) {
+		num_cpus += 1;
+
+		/* We're assuming *all* of the CPUs have the same
+		 * d-cache and i-cache sizes... -Peter
+		 */
+
+		if ( num_cpus == 1 ) {
+			u32 *sizep, *lsizep;
+			u32 size, lsize;
+			const char *dc, *ic;
+
+			/* Then read cache informations */
+			if (systemcfg->platform == PLATFORM_POWERMAC) {
+				dc = "d-cache-block-size";
+				ic = "i-cache-block-size";
+			} else {
+				dc = "d-cache-line-size";
+				ic = "i-cache-line-size";
+			}
+
+			size = 0;
+			lsize = cur_cpu_spec->dcache_bsize;
+			sizep = (u32 *)get_property(np, "d-cache-size", NULL);
+			if (sizep != NULL)
+				size = *sizep;
+			lsizep = (u32 *) get_property(np, dc, NULL);
+			if (lsizep != NULL)
+				lsize = *lsizep;
+			if (sizep == 0 || lsizep == 0)
+				DBG("Argh, can't find dcache properties ! "
+				    "sizep: %p, lsizep: %p\n", sizep, lsizep);
+
+			systemcfg->dcache_size = ppc64_caches.dsize = size;
+			systemcfg->dcache_line_size =
+				ppc64_caches.dline_size = lsize;
+			ppc64_caches.log_dline_size = __ilog2(lsize);
+			ppc64_caches.dlines_per_page = PAGE_SIZE / lsize;
+
+			size = 0;
+			lsize = cur_cpu_spec->icache_bsize;
+			sizep = (u32 *)get_property(np, "i-cache-size", NULL);
+			if (sizep != NULL)
+				size = *sizep;
+			lsizep = (u32 *)get_property(np, ic, NULL);
+			if (lsizep != NULL)
+				lsize = *lsizep;
+			if (sizep == 0 || lsizep == 0)
+				DBG("Argh, can't find icache properties ! "
+				    "sizep: %p, lsizep: %p\n", sizep, lsizep);
+
+			systemcfg->icache_size = ppc64_caches.isize = size;
+			systemcfg->icache_line_size =
+				ppc64_caches.iline_size = lsize;
+			ppc64_caches.log_iline_size = __ilog2(lsize);
+			ppc64_caches.ilines_per_page = PAGE_SIZE / lsize;
+		}
+	}
+
+	/* Add an eye catcher and the systemcfg layout version number */
+	strcpy(systemcfg->eye_catcher, "SYSTEMCFG:PPC64");
+	systemcfg->version.major = SYSTEMCFG_MAJOR;
+	systemcfg->version.minor = SYSTEMCFG_MINOR;
+	systemcfg->processor = mfspr(SPRN_PVR);
+
+	DBG(" <- initialize_cache_info()\n");
+}
+
+static void __init check_for_initrd(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+	u64 *prop;
+
+	DBG(" -> check_for_initrd()\n");
+
+	if (of_chosen) {
+		prop = (u64 *)get_property(of_chosen,
+				"linux,initrd-start", NULL);
+		if (prop != NULL) {
+			initrd_start = (unsigned long)__va(*prop);
+			prop = (u64 *)get_property(of_chosen,
+					"linux,initrd-end", NULL);
+			if (prop != NULL) {
+				initrd_end = (unsigned long)__va(*prop);
+				initrd_below_start_ok = 1;
+			} else
+				initrd_start = 0;
+		}
+	}
+
+	/* If we were passed an initrd, set the ROOT_DEV properly if the values
+	 * look sensible. If not, clear initrd reference.
+	 */
+	if (initrd_start >= KERNELBASE && initrd_end >= KERNELBASE &&
+	    initrd_end > initrd_start)
+		ROOT_DEV = Root_RAM0;
+	else
+		initrd_start = initrd_end = 0;
+
+	if (initrd_start)
+		printk("Found initrd at 0x%lx:0x%lx\n", initrd_start, initrd_end);
+
+	DBG(" <- check_for_initrd()\n");
+#endif /* CONFIG_BLK_DEV_INITRD */
+}
+
+/*
+ * Do some initial setup of the system.  The parameters are those which 
+ * were passed in from the bootloader.
+ */
+void __init setup_system(void)
+{
+	DBG(" -> setup_system()\n");
+
+	/*
+	 * Unflatten the device-tree passed by prom_init or kexec
+	 */
+	unflatten_device_tree();
+
+	/*
+	 * Fill the ppc64_caches & systemcfg structures with informations
+	 * retreived from the device-tree. Need to be called before
+	 * finish_device_tree() since the later requires some of the
+	 * informations filled up here to properly parse the interrupt
+	 * tree.
+	 * It also sets up the cache line sizes which allows to call
+	 * routines like flush_icache_range (used by the hash init
+	 * later on).
+	 */
+	initialize_cache_info();
+
+#ifdef CONFIG_PPC_RTAS
+	/*
+	 * Initialize RTAS if available
+	 */
+	rtas_initialize();
+#endif /* CONFIG_PPC_RTAS */
+	printk("%s:%d rtas.dev=%p (@ %p)\n", __FILE__, __LINE__, rtas.dev,
+	       &rtas.dev);
+
+	/*
+	 * Check if we have an initrd provided via the device-tree
+	 */
+	check_for_initrd();
+	printk("%s:%d rtas.dev=%p\n", __FILE__, __LINE__, rtas.dev);
+
+	/*
+	 * Do some platform specific early initializations, that includes
+	 * setting up the hash table pointers. It also sets up some interrupt-mapping
+	 * related options that will be used by finish_device_tree()
+	 */
+	ppc_md.init_early();
+	printk("%s:%d rtas.dev=%p\n", __FILE__, __LINE__, rtas.dev);
+
+	/*
+	 * "Finish" the device-tree, that is do the actual parsing of
+	 * some of the properties like the interrupt map
+	 */
+	finish_device_tree();
+	printk("%s:%d rtas.dev=%p\n", __FILE__, __LINE__, rtas.dev);
+
+	/*
+	 * Initialize xmon
+	 */
+#ifdef CONFIG_XMON_DEFAULT
+	xmon_init(1);
+#endif
+	printk("%s:%d rtas.dev=%p\n", __FILE__, __LINE__, rtas.dev);
+	/*
+	 * Register early console
+	 */
+	register_early_udbg_console();
+	printk("%s:%d rtas.dev=%p\n", __FILE__, __LINE__, rtas.dev);
+
+	/* Save unparsed command line copy for /proc/cmdline */
+	strlcpy(saved_command_line, cmd_line, COMMAND_LINE_SIZE);
+
+	parse_early_param();
+	printk("%s:%d rtas.dev=%p\n", __FILE__, __LINE__, rtas.dev);
+
+#ifdef CONFIG_SMP
+	/*
+	 * iSeries has already initialized the cpu maps at this point.
+	 */
+	setup_cpu_maps();
+	printk("%s:%d rtas.dev=%p\n", __FILE__, __LINE__, rtas.dev);
+
+	/* Release secondary cpus out of their spinloops at 0x60 now that
+	 * we can map physical -> logical CPU ids
+	 */
+	smp_release_cpus();
+	printk("%s:%d rtas.dev=%p\n", __FILE__, __LINE__, rtas.dev);
+#endif
+
+	printk("Starting Linux PPC64 %s\n", system_utsname.version);
+
+	printk("-----------------------------------------------------\n");
+	printk("ppc64_pft_size                = 0x%lx\n", ppc64_pft_size);
+	printk("ppc64_debug_switch            = 0x%lx\n", ppc64_debug_switch);
+	printk("ppc64_interrupt_controller    = 0x%ld\n", ppc64_interrupt_controller);
+	printk("systemcfg                     = 0x%p\n", systemcfg);
+	printk("systemcfg->platform           = 0x%x\n", systemcfg->platform);
+	printk("systemcfg->processorCount     = 0x%lx\n", systemcfg->processorCount);
+	printk("systemcfg->physicalMemorySize = 0x%lx\n", systemcfg->physicalMemorySize);
+	printk("ppc64_caches.dcache_line_size = 0x%x\n",
+			ppc64_caches.dline_size);
+	printk("ppc64_caches.icache_line_size = 0x%x\n",
+			ppc64_caches.iline_size);
+	printk("htab_address                  = 0x%p\n", htab_address);
+	printk("htab_hash_mask                = 0x%lx\n", htab_hash_mask);
+	printk("-----------------------------------------------------\n");
+	printk("%s:%d rtas.dev=%p\n", __FILE__, __LINE__, rtas.dev);
+
+	mm_init_ppc64();
+	printk("%s:%d rtas.dev=%p\n", __FILE__, __LINE__, rtas.dev);
+
+	DBG(" <- setup_system()\n");
+}
+
+/* also used by kexec */
+void machine_shutdown(void)
+{
+	if (ppc_md.nvram_sync)
+		ppc_md.nvram_sync();
+}
+
+void machine_restart(char *cmd)
+{
+	machine_shutdown();
+	ppc_md.restart(cmd);
+#ifdef CONFIG_SMP
+	smp_send_stop();
+#endif
+	printk(KERN_EMERG "System Halted, OK to turn off power\n");
+	local_irq_disable();
+	while (1) ;
+}
+
+void machine_power_off(void)
+{
+	machine_shutdown();
+	ppc_md.power_off();
+#ifdef CONFIG_SMP
+	smp_send_stop();
+#endif
+	printk(KERN_EMERG "System Halted, OK to turn off power\n");
+	local_irq_disable();
+	while (1) ;
+}
+/* Used by the G5 thermal driver */
+EXPORT_SYMBOL_GPL(machine_power_off);
+
+void machine_halt(void)
+{
+	machine_shutdown();
+	ppc_md.halt();
+#ifdef CONFIG_SMP
+	smp_send_stop();
+#endif
+	printk(KERN_EMERG "System Halted, OK to turn off power\n");
+	local_irq_disable();
+	while (1) ;
+}
+
+static int ppc64_panic_event(struct notifier_block *this,
+                             unsigned long event, void *ptr)
+{
+	ppc_md.panic((char *)ptr);  /* May not return */
+	return NOTIFY_DONE;
+}
+
+
+#ifdef CONFIG_SMP
+DEFINE_PER_CPU(unsigned int, pvr);
+#endif
+
+static int show_cpuinfo(struct seq_file *m, void *v)
+{
+	unsigned long cpu_id = (unsigned long)v - 1;
+	unsigned int pvr;
+	unsigned short maj;
+	unsigned short min;
+
+	if (cpu_id == NR_CPUS) {
+		seq_printf(m, "timebase\t: %lu\n", ppc_tb_freq);
+
+		if (ppc_md.get_cpuinfo != NULL)
+			ppc_md.get_cpuinfo(m);
+
+		return 0;
+	}
+
+	/* We only show online cpus: disable preempt (overzealous, I
+	 * knew) to prevent cpu going down. */
+	preempt_disable();
+	if (!cpu_online(cpu_id)) {
+		preempt_enable();
+		return 0;
+	}
+
+#ifdef CONFIG_SMP
+	pvr = per_cpu(pvr, cpu_id);
+#else
+	pvr = mfspr(SPRN_PVR);
+#endif
+	maj = (pvr >> 8) & 0xFF;
+	min = pvr & 0xFF;
+
+	seq_printf(m, "processor\t: %lu\n", cpu_id);
+	seq_printf(m, "cpu\t\t: ");
+
+	if (cur_cpu_spec->pvr_mask)
+		seq_printf(m, "%s", cur_cpu_spec->cpu_name);
+	else
+		seq_printf(m, "unknown (%08x)", pvr);
+
+#ifdef CONFIG_ALTIVEC
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		seq_printf(m, ", altivec supported");
+#endif /* CONFIG_ALTIVEC */
+
+	seq_printf(m, "\n");
+
+	/*
+	 * Assume here that all clock rates are the same in a
+	 * smp system.  -- Cort
+	 */
+	seq_printf(m, "clock\t\t: %lu.%06luMHz\n", ppc_proc_freq / 1000000,
+		   ppc_proc_freq % 1000000);
+
+	seq_printf(m, "revision\t: %hd.%hd\n\n", maj, min);
+
+	preempt_enable();
+	return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+	return *pos <= NR_CPUS ? (void *)((*pos)+1) : NULL;
+}
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	++*pos;
+	return c_start(m, pos);
+}
+static void c_stop(struct seq_file *m, void *v)
+{
+}
+struct seq_operations cpuinfo_op = {
+	.start =c_start,
+	.next =	c_next,
+	.stop =	c_stop,
+	.show =	show_cpuinfo,
+};
+
+/*
+ * These three variables are used to save values passed to us by prom_init()
+ * via the device tree. The TCE variables are needed because with a memory_limit
+ * in force we may need to explicitly map the TCE are at the top of RAM.
+ */
+unsigned long memory_limit;
+unsigned long tce_alloc_start;
+unsigned long tce_alloc_end;
+
+#ifdef CONFIG_PPC_ISERIES
+/*
+ * On iSeries we just parse the mem=X option from the command line.
+ * On pSeries it's a bit more complicated, see prom_init_mem()
+ */
+static int __init early_parsemem(char *p)
+{
+	if (!p)
+		return 0;
+
+	memory_limit = ALIGN(memparse(p, &p), PAGE_SIZE);
+
+	return 0;
+}
+early_param("mem", early_parsemem);
+#endif /* CONFIG_PPC_ISERIES */
+
+#ifdef CONFIG_PPC_MULTIPLATFORM
+static int __init set_preferred_console(void)
+{
+	struct device_node *prom_stdout = NULL;
+	char *name;
+	u32 *spd;
+	int offset = 0;
+
+	DBG(" -> set_preferred_console()\n");
+
+	/* The user has requested a console so this is already set up. */
+	if (strstr(saved_command_line, "console=")) {
+		DBG(" console was specified !\n");
+		return -EBUSY;
+	}
+
+	if (!of_chosen) {
+		DBG(" of_chosen is NULL !\n");
+		return -ENODEV;
+	}
+	/* We are getting a weird phandle from OF ... */
+	/* ... So use the full path instead */
+	name = (char *)get_property(of_chosen, "linux,stdout-path", NULL);
+	if (name == NULL) {
+		DBG(" no linux,stdout-path !\n");
+		return -ENODEV;
+	}
+	prom_stdout = of_find_node_by_path(name);
+	if (!prom_stdout) {
+		DBG(" can't find stdout package %s !\n", name);
+		return -ENODEV;
+	}	
+	DBG("stdout is %s\n", prom_stdout->full_name);
+
+	name = (char *)get_property(prom_stdout, "name", NULL);
+	if (!name) {
+		DBG(" stdout package has no name !\n");
+		goto not_found;
+	}
+	spd = (u32 *)get_property(prom_stdout, "current-speed", NULL);
+
+	if (0)
+		;
+#ifdef CONFIG_SERIAL_8250_CONSOLE
+	else if (strcmp(name, "serial") == 0) {
+		int i;
+		u32 *reg = (u32 *)get_property(prom_stdout, "reg", &i);
+		if (i > 8) {
+			switch (reg[1]) {
+				case 0x3f8:
+					offset = 0;
+					break;
+				case 0x2f8:
+					offset = 1;
+					break;
+				case 0x898:
+					offset = 2;
+					break;
+				case 0x890:
+					offset = 3;
+					break;
+				default:
+					/* We dont recognise the serial port */
+					goto not_found;
+			}
+		}
+	}
+#endif /* CONFIG_SERIAL_8250_CONSOLE */
+#ifdef CONFIG_PPC_PSERIES
+	else if (strcmp(name, "vty") == 0) {
+ 		u32 *reg = (u32 *)get_property(prom_stdout, "reg", NULL);
+ 		char *compat = (char *)get_property(prom_stdout, "compatible", NULL);
+
+ 		if (reg && compat && (strcmp(compat, "hvterm-protocol") == 0)) {
+ 			/* Host Virtual Serial Interface */
+ 			int offset;
+ 			switch (reg[0]) {
+ 				case 0x30000000:
+ 					offset = 0;
+ 					break;
+ 				case 0x30000001:
+ 					offset = 1;
+ 					break;
+ 				default:
+					goto not_found;
+ 			}
+			of_node_put(prom_stdout);
+			DBG("Found hvsi console at offset %d\n", offset);
+ 			return add_preferred_console("hvsi", offset, NULL);
+ 		} else {
+ 			/* pSeries LPAR virtual console */
+			of_node_put(prom_stdout);
+			DBG("Found hvc console\n");
+ 			return add_preferred_console("hvc", 0, NULL);
+ 		}
+	}
+#endif /* CONFIG_PPC_PSERIES */
+#ifdef CONFIG_SERIAL_PMACZILOG_CONSOLE
+	else if (strcmp(name, "ch-a") == 0)
+		offset = 0;
+	else if (strcmp(name, "ch-b") == 0)
+		offset = 1;
+#endif /* CONFIG_SERIAL_PMACZILOG_CONSOLE */
+	else
+		goto not_found;
+	of_node_put(prom_stdout);
+
+	DBG("Found serial console at ttyS%d\n", offset);
+
+	if (spd) {
+		static char __initdata opt[16];
+		sprintf(opt, "%d", *spd);
+		return add_preferred_console("ttyS", offset, opt);
+	} else
+		return add_preferred_console("ttyS", offset, NULL);
+
+ not_found:
+	DBG("No preferred console found !\n");
+	of_node_put(prom_stdout);
+	return -ENODEV;
+}
+console_initcall(set_preferred_console);
+#endif /* CONFIG_PPC_MULTIPLATFORM */
+
+#ifdef CONFIG_IRQSTACKS
+static void __init irqstack_early_init(void)
+{
+	unsigned int i;
+
+	/*
+	 * interrupt stacks must be under 256MB, we cannot afford to take
+	 * SLB misses on them.
+	 */
+	for_each_cpu(i) {
+		softirq_ctx[i] = (struct thread_info *)__va(lmb_alloc_base(THREAD_SIZE,
+					THREAD_SIZE, 0x10000000));
+		hardirq_ctx[i] = (struct thread_info *)__va(lmb_alloc_base(THREAD_SIZE,
+					THREAD_SIZE, 0x10000000));
+	}
+}
+#else
+#define irqstack_early_init()
+#endif
+
+/*
+ * Stack space used when we detect a bad kernel stack pointer, and
+ * early in SMP boots before relocation is enabled.
+ */
+static void __init emergency_stack_init(void)
+{
+	unsigned long limit;
+	unsigned int i;
+
+	/*
+	 * Emergency stacks must be under 256MB, we cannot afford to take
+	 * SLB misses on them. The ABI also requires them to be 128-byte
+	 * aligned.
+	 *
+	 * Since we use these as temporary stacks during secondary CPU
+	 * bringup, we need to get at them in real mode. This means they
+	 * must also be within the RMO region.
+	 */
+	limit = min(0x10000000UL, lmb.rmo_size);
+
+	for_each_cpu(i)
+		paca[i].emergency_sp = __va(lmb_alloc_base(PAGE_SIZE, 128,
+						limit)) + PAGE_SIZE;
+}
+
+/*
+ * Called from setup_arch to initialize the bitmap of available
+ * syscalls in the systemcfg page
+ */
+void __init setup_syscall_map(void)
+{
+	unsigned int i, count64 = 0, count32 = 0;
+	extern unsigned long *sys_call_table;
+	extern unsigned long sys_ni_syscall;
+
+
+	for (i = 0; i < __NR_syscalls; i++) {
+		if (sys_call_table[i*2] != sys_ni_syscall) {
+			count64++;
+			systemcfg->syscall_map_64[i >> 5] |=
+				0x80000000UL >> (i & 0x1f);
+		}
+		if (sys_call_table[i*2+1] != sys_ni_syscall) {
+			count32++;
+			systemcfg->syscall_map_32[i >> 5] |=
+				0x80000000UL >> (i & 0x1f);
+		}
+	}
+	printk(KERN_INFO "Syscall map setup, %d 32-bit and %d 64-bit syscalls\n",
+	       count32, count64);
+}
+
+/*
+ * Called into from start_kernel, after lock_kernel has been called.
+ * Initializes bootmem, which is unsed to manage page allocation until
+ * mem_init is called.
+ */
+void __init setup_arch(char **cmdline_p)
+{
+	extern void do_init_bootmem(void);
+
+	printk("%s:%d rtas.dev=%p\n", __FILE__, __LINE__, rtas.dev);
+	ppc64_boot_msg(0x12, "Setup Arch");
+
+	*cmdline_p = cmd_line;
+
+	/*
+	 * Set cache line size based on type of cpu as a default.
+	 * Systems with OF can look in the properties on the cpu node(s)
+	 * for a possibly more accurate value.
+	 */
+	dcache_bsize = ppc64_caches.dline_size;
+	icache_bsize = ppc64_caches.iline_size;
+
+	/* reboot on panic */
+	panic_timeout = 180;
+	printk("%s:%d rtas.dev=%p\n", __FILE__, __LINE__, rtas.dev);
+
+	if (ppc_md.panic)
+		notifier_chain_register(&panic_notifier_list, &ppc64_panic_block);
+
+	init_mm.start_code = PAGE_OFFSET;
+	init_mm.end_code = (unsigned long) _etext;
+	init_mm.end_data = (unsigned long) _edata;
+	init_mm.brk = klimit;
+	
+	irqstack_early_init();
+	emergency_stack_init();
+
+	printk("%s:%d rtas.dev=%p\n", __FILE__, __LINE__, rtas.dev);
+	stabs_alloc();
+
+	/* set up the bootmem stuff with available memory */
+	do_init_bootmem();
+	sparse_init();
+
+	printk("%s:%d rtas.dev=%p\n", __FILE__, __LINE__, rtas.dev);
+	/* initialize the syscall map in systemcfg */
+	setup_syscall_map();
+
+	ppc_md.setup_arch();
+
+	/* Use the default idle loop if the platform hasn't provided one. */
+	if (NULL == ppc_md.idle_loop) {
+		ppc_md.idle_loop = default_idle;
+		printk(KERN_INFO "Using default idle loop\n");
+	}
+
+	paging_init();
+	ppc64_boot_msg(0x15, "Setup Done");
+}
+
+
+/* ToDo: do something useful if ppc_md is not yet setup. */
+#define PPC64_LINUX_FUNCTION 0x0f000000
+#define PPC64_IPL_MESSAGE 0xc0000000
+#define PPC64_TERM_MESSAGE 0xb0000000
+
+static void ppc64_do_msg(unsigned int src, const char *msg)
+{
+	if (ppc_md.progress) {
+		char buf[128];
+
+		sprintf(buf, "%08X\n", src);
+		ppc_md.progress(buf, 0);
+		snprintf(buf, 128, "%s", msg);
+		ppc_md.progress(buf, 0);
+	}
+}
+
+/* Print a boot progress message. */
+void ppc64_boot_msg(unsigned int src, const char *msg)
+{
+	ppc64_do_msg(PPC64_LINUX_FUNCTION|PPC64_IPL_MESSAGE|src, msg);
+	printk("[boot]%04x %s\n", src, msg);
+}
+
+/* Print a termination message (print only -- does not stop the kernel) */
+void ppc64_terminate_msg(unsigned int src, const char *msg)
+{
+	ppc64_do_msg(PPC64_LINUX_FUNCTION|PPC64_TERM_MESSAGE|src, msg);
+	printk("[terminate]%04x %s\n", src, msg);
+}
+
+/* This should only be called on processor 0 during calibrate decr */
+void __init setup_default_decr(void)
+{
+	struct paca_struct *lpaca = get_paca();
+
+	lpaca->default_decr = tb_ticks_per_jiffy;
+	lpaca->next_jiffy_update_tb = get_tb() + tb_ticks_per_jiffy;
+}
+
+#ifndef CONFIG_PPC_ISERIES
+/*
+ * This function can be used by platforms to "find" legacy serial ports.
+ * It works for "serial" nodes under an "isa" node, and will try to
+ * respect the "ibm,aix-loc" property if any. It works with up to 8
+ * ports.
+ */
+
+#define MAX_LEGACY_SERIAL_PORTS	8
+static struct plat_serial8250_port serial_ports[MAX_LEGACY_SERIAL_PORTS+1];
+static unsigned int old_serial_count;
+
+void __init generic_find_legacy_serial_ports(u64 *physport,
+		unsigned int *default_speed)
+{
+	struct device_node *np;
+	u32 *sizeprop;
+
+	struct isa_reg_property {
+		u32 space;
+		u32 address;
+		u32 size;
+	};
+	struct pci_reg_property {
+		struct pci_address addr;
+		u32 size_hi;
+		u32 size_lo;
+	};                                                                        
+
+	DBG(" -> generic_find_legacy_serial_port()\n");
+
+	*physport = 0;
+	if (default_speed)
+		*default_speed = 0;
+
+	np = of_find_node_by_path("/");
+	if (!np)
+		return;
+
+	/* First fill our array */
+	for (np = NULL; (np = of_find_node_by_type(np, "serial"));) {
+		struct device_node *isa, *pci;
+		struct isa_reg_property *reg;
+		unsigned long phys_size, addr_size, io_base;
+		u32 *rangesp;
+		u32 *interrupts, *clk, *spd;
+		char *typep;
+		int index, rlen, rentsize;
+
+		/* Ok, first check if it's under an "isa" parent */
+		isa = of_get_parent(np);
+		if (!isa || strcmp(isa->name, "isa")) {
+			DBG("%s: no isa parent found\n", np->full_name);
+			continue;
+		}
+		
+		/* Now look for an "ibm,aix-loc" property that gives us ordering
+		 * if any...
+		 */
+	 	typep = (char *)get_property(np, "ibm,aix-loc", NULL);
+
+		/* Get the ISA port number */
+		reg = (struct isa_reg_property *)get_property(np, "reg", NULL);	
+		if (reg == NULL)
+			goto next_port;
+		/* We assume the interrupt number isn't translated ... */
+		interrupts = (u32 *)get_property(np, "interrupts", NULL);
+		/* get clock freq. if present */
+		clk = (u32 *)get_property(np, "clock-frequency", NULL);
+		/* get default speed if present */
+		spd = (u32 *)get_property(np, "current-speed", NULL);
+		/* Default to locate at end of array */
+		index = old_serial_count; /* end of the array by default */
+
+		/* If we have a location index, then use it */
+		if (typep && *typep == 'S') {
+			index = simple_strtol(typep+1, NULL, 0) - 1;
+			/* if index is out of range, use end of array instead */
+			if (index >= MAX_LEGACY_SERIAL_PORTS)
+				index = old_serial_count;
+			/* if our index is still out of range, that mean that
+			 * array is full, we could scan for a free slot but that
+			 * make little sense to bother, just skip the port
+			 */
+			if (index >= MAX_LEGACY_SERIAL_PORTS)
+				goto next_port;
+			if (index >= old_serial_count)
+				old_serial_count = index + 1;
+			/* Check if there is a port who already claimed our slot */
+			if (serial_ports[index].iobase != 0) {
+				/* if we still have some room, move it, else override */
+				if (old_serial_count < MAX_LEGACY_SERIAL_PORTS) {
+					DBG("Moved legacy port %d -> %d\n", index,
+					    old_serial_count);
+					serial_ports[old_serial_count++] =
+						serial_ports[index];
+				} else {
+					DBG("Replacing legacy port %d\n", index);
+				}
+			}
+		}
+		if (index >= MAX_LEGACY_SERIAL_PORTS)
+			goto next_port;
+		if (index >= old_serial_count)
+			old_serial_count = index + 1;
+
+		/* Now fill the entry */
+		memset(&serial_ports[index], 0, sizeof(struct plat_serial8250_port));
+		serial_ports[index].uartclk = clk ? *clk : BASE_BAUD * 16;
+		serial_ports[index].iobase = reg->address;
+		serial_ports[index].irq = interrupts ? interrupts[0] : 0;
+		serial_ports[index].flags = ASYNC_BOOT_AUTOCONF;
+
+		DBG("Added legacy port, index: %d, port: %x, irq: %d, clk: %d\n",
+		    index,
+		    serial_ports[index].iobase,
+		    serial_ports[index].irq,
+		    serial_ports[index].uartclk);
+
+		/* Get phys address of IO reg for port 1 */
+		if (index != 0)
+			goto next_port;
+
+		pci = of_get_parent(isa);
+		if (!pci) {
+			DBG("%s: no pci parent found\n", np->full_name);
+			goto next_port;
+		}
+
+		rangesp = (u32 *)get_property(pci, "ranges", &rlen);
+		if (rangesp == NULL) {
+			of_node_put(pci);
+			goto next_port;
+		}
+		rlen /= 4;
+
+		/* we need the #size-cells of the PCI bridge node itself */
+		phys_size = 1;
+		sizeprop = (u32 *)get_property(pci, "#size-cells", NULL);
+		if (sizeprop != NULL)
+			phys_size = *sizeprop;
+		/* we need the parent #addr-cells */
+		addr_size = prom_n_addr_cells(pci);
+		rentsize = 3 + addr_size + phys_size;
+		io_base = 0;
+		for (;rlen >= rentsize; rlen -= rentsize,rangesp += rentsize) {
+			if (((rangesp[0] >> 24) & 0x3) != 1)
+				continue; /* not IO space */
+			io_base = rangesp[3];
+			if (addr_size == 2)
+				io_base = (io_base << 32) | rangesp[4];
+		}
+		if (io_base != 0) {
+			*physport = io_base + reg->address;
+			if (default_speed && spd)
+				*default_speed = *spd;
+		}
+		of_node_put(pci);
+	next_port:
+		of_node_put(isa);
+	}
+
+	DBG(" <- generic_find_legacy_serial_port()\n");
+}
+
+static struct platform_device serial_device = {
+	.name	= "serial8250",
+	.id	= PLAT8250_DEV_PLATFORM,
+	.dev	= {
+		.platform_data = serial_ports,
+	},
+};
+
+static int __init serial_dev_init(void)
+{
+	return platform_device_register(&serial_device);
+}
+arch_initcall(serial_dev_init);
+
+#endif /* CONFIG_PPC_ISERIES */
+
+int check_legacy_ioport(unsigned long base_port)
+{
+	if (ppc_md.check_legacy_ioport == NULL)
+		return 0;
+	return ppc_md.check_legacy_ioport(base_port);
+}
+EXPORT_SYMBOL(check_legacy_ioport);
+
+#ifdef CONFIG_XMON
+static int __init early_xmon(char *p)
+{
+	/* ensure xmon is enabled */
+	if (p) {
+		if (strncmp(p, "on", 2) == 0)
+			xmon_init(1);
+		if (strncmp(p, "off", 3) == 0)
+			xmon_init(0);
+		if (strncmp(p, "early", 5) != 0)
+			return 0;
+	}
+	xmon_init(1);
+	debugger(NULL);
+
+	return 0;
+}
+early_param("xmon", early_xmon);
+#endif
+
+void cpu_die(void)
+{
+	if (ppc_md.cpu_die)
+		ppc_md.cpu_die();
+}
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index a8cedb96de5f..30367a0237dd 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -7,3 +7,7 @@ obj-$(CONFIG_PPC32)	+= div64.o copy_32.o checksum_32.o
 obj-$(CONFIG_PPC64)	+= copypage_64.o copyuser_64.o memcpy_64.o \
 			   usercopy_64.o sstep.o checksum_64.o mem_64.o
 obj-$(CONFIG_PPC_ISERIES) += e2a.o
+ifeq ($(CONFIG_PPC64),y)
+obj-$(CONFIG_SMP)	+= locks.o
+endif
+
diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c
new file mode 100644
index 000000000000..4b8c5ad5e7dc
--- /dev/null
+++ b/arch/powerpc/lib/locks.c
@@ -0,0 +1,95 @@
+/*
+ * Spin and read/write lock operations.
+ *
+ * Copyright (C) 2001-2004 Paul Mackerras <paulus@au.ibm.com>, IBM
+ * Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
+ * Copyright (C) 2002 Dave Engebretsen <engebret@us.ibm.com>, IBM
+ *   Rework to support virtual processors
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/stringify.h>
+
+/* waiting for a spinlock... */
+#if defined(CONFIG_PPC_SPLPAR) || defined(CONFIG_PPC_ISERIES)
+#include <asm/hvcall.h>
+#include <asm/iSeries/HvCall.h>
+
+void __spin_yield(raw_spinlock_t *lock)
+{
+	unsigned int lock_value, holder_cpu, yield_count;
+	struct paca_struct *holder_paca;
+
+	lock_value = lock->slock;
+	if (lock_value == 0)
+		return;
+	holder_cpu = lock_value & 0xffff;
+	BUG_ON(holder_cpu >= NR_CPUS);
+	holder_paca = &paca[holder_cpu];
+	yield_count = holder_paca->lppaca.yield_count;
+	if ((yield_count & 1) == 0)
+		return;		/* virtual cpu is currently running */
+	rmb();
+	if (lock->slock != lock_value)
+		return;		/* something has changed */
+#ifdef CONFIG_PPC_ISERIES
+	HvCall2(HvCallBaseYieldProcessor, HvCall_YieldToProc,
+		((u64)holder_cpu << 32) | yield_count);
+#else
+	plpar_hcall_norets(H_CONFER, get_hard_smp_processor_id(holder_cpu),
+			   yield_count);
+#endif
+}
+
+/*
+ * Waiting for a read lock or a write lock on a rwlock...
+ * This turns out to be the same for read and write locks, since
+ * we only know the holder if it is write-locked.
+ */
+void __rw_yield(raw_rwlock_t *rw)
+{
+	int lock_value;
+	unsigned int holder_cpu, yield_count;
+	struct paca_struct *holder_paca;
+
+	lock_value = rw->lock;
+	if (lock_value >= 0)
+		return;		/* no write lock at present */
+	holder_cpu = lock_value & 0xffff;
+	BUG_ON(holder_cpu >= NR_CPUS);
+	holder_paca = &paca[holder_cpu];
+	yield_count = holder_paca->lppaca.yield_count;
+	if ((yield_count & 1) == 0)
+		return;		/* virtual cpu is currently running */
+	rmb();
+	if (rw->lock != lock_value)
+		return;		/* something has changed */
+#ifdef CONFIG_PPC_ISERIES
+	HvCall2(HvCallBaseYieldProcessor, HvCall_YieldToProc,
+		((u64)holder_cpu << 32) | yield_count);
+#else
+	plpar_hcall_norets(H_CONFER, get_hard_smp_processor_id(holder_cpu),
+			   yield_count);
+#endif
+}
+#endif
+
+void __raw_spin_unlock_wait(raw_spinlock_t *lock)
+{
+	while (lock->slock) {
+		HMT_low();
+		if (SHARED_PROCESSOR)
+			__spin_yield(lock);
+	}
+	HMT_medium();
+}
+
+EXPORT_SYMBOL(__raw_spin_unlock_wait);
diff --git a/arch/ppc64/Kconfig b/arch/ppc64/Kconfig
index 246212115a48..e656e02d9dd1 100644
--- a/arch/ppc64/Kconfig
+++ b/arch/ppc64/Kconfig
@@ -186,6 +186,9 @@ config BOOTX_TEXT
 	  Say Y here to see progress messages from the boot firmware in text
 	  mode. Requires an Open Firmware compatible video card.
 
+config POWER4
+	def_bool y
+
 config POWER4_ONLY
 	bool "Optimize for POWER4"
 	default n
diff --git a/arch/ppc64/kernel/Makefile b/arch/ppc64/kernel/Makefile
index 79366e4a9e5c..5c598892f891 100644
--- a/arch/ppc64/kernel/Makefile
+++ b/arch/ppc64/kernel/Makefile
@@ -2,14 +2,14 @@
 # Makefile for the linux ppc64 kernel.
 #
 
-EXTRA_CFLAGS	+= -mno-minimal-toc
 ifneq ($(CONFIG_PPC_MERGE),y)
+
+EXTRA_CFLAGS	+= -mno-minimal-toc
 extra-y		:= head.o vmlinux.lds
-endif
 
 obj-y               :=	setup.o entry.o irq.o idle.o dma.o \
 			time.o process.o signal.o syscalls.o misc.o ptrace.o \
-			align.o semaphore.o bitops.o pacaData.o \
+			align.o bitops.o pacaData.o \
 			udbg.o binfmt_elf32.o sys_ppc32.o ioctl32.o \
 			ptrace32.o signal32.o rtc.o init_task.o \
 			cputable.o cpu_setup_power4.o \
@@ -43,7 +43,6 @@ obj-$(CONFIG_HVC_CONSOLE)	+= hvconsole.o
 obj-$(CONFIG_BOOTX_TEXT)	+= btext.o
 obj-$(CONFIG_HVCS)		+= hvcserver.o
 
-vio-obj-$(CONFIG_PPC_PSERIES)	+= pSeries_vio.o
 obj-$(CONFIG_IBMVIO)		+= vio.o $(vio-obj-y)
 obj-$(CONFIG_XICS)		+= xics.o
 obj-$(CONFIG_MPIC)		+= mpic.o
@@ -59,8 +58,6 @@ obj-$(CONFIG_U3_DART)		+= u3_iommu.o
 
 ifdef CONFIG_SMP
 obj-$(CONFIG_PPC_PMAC)		+= pmac_smp.o smp-tbsync.o
-obj-$(CONFIG_PPC_PSERIES)	+= pSeries_smp.o
-obj-$(CONFIG_PPC_BPA)		+= pSeries_smp.o
 obj-$(CONFIG_PPC_MAPLE)		+= smp-tbsync.o
 endif
 
@@ -68,9 +65,62 @@ obj-$(CONFIG_KPROBES)		+= kprobes.o
 
 CFLAGS_ioctl32.o += -Ifs/
 
-ifneq ($(CONFIG_PPC_MERGE),y)
 ifeq ($(CONFIG_PPC_ISERIES),y)
 arch/ppc64/kernel/head.o: arch/powerpc/kernel/lparmap.s
 AFLAGS_head.o += -Iarch/powerpc/kernel
 endif
+
+else
+
+# Things still needed from here by the merged ppc code
+
+obj-y               :=	irq.o idle.o dma.o \
+			time.o signal.o syscalls.o ptrace.o \
+			align.o bitops.o pacaData.o \
+			udbg.o binfmt_elf32.o sys_ppc32.o ioctl32.o \
+			ptrace32.o signal32.o rtc.o \
+			cputable.o cpu_setup_power4.o \
+			iommu.o sysfs.o vdso.o pmc.o firmware.o
+obj-y += vdso32/ vdso64/
+
+pci-obj-$(CONFIG_PPC_MULTIPLATFORM)	+= pci_dn.o pci_direct_iommu.o
+
+obj-$(CONFIG_PCI)	+= pci.o pci_iommu.o iomap.o $(pci-obj-y)
+
+obj-$(CONFIG_PPC_MULTIPLATFORM) += nvram.o i8259.o
+
+obj-$(CONFIG_PPC_PSERIES) += rtasd.o ras.o udbg_16550.o
+
+obj-$(CONFIG_PPC_BPA) += bpa_setup.o bpa_iommu.o bpa_nvram.o \
+			 bpa_iic.o spider-pic.o
+
+obj-$(CONFIG_KEXEC)		+= machine_kexec.o
+obj-$(CONFIG_EEH)		+= eeh.o
+obj-$(CONFIG_PROC_FS)		+= proc_ppc64.o
+obj-$(CONFIG_RTAS_FLASH)	+= rtas_flash.o
+obj-$(CONFIG_SMP)		+= smp.o
+obj-$(CONFIG_MODULES)		+= module.o
+obj-$(CONFIG_PPC_RTAS)		+= rtas.o rtas_pci.o
+obj-$(CONFIG_RTAS_PROC)		+= rtas-proc.o
+obj-$(CONFIG_SCANLOG)		+= scanlog.o
+obj-$(CONFIG_LPARCFG)		+= lparcfg.o
+obj-$(CONFIG_HVC_CONSOLE)	+= hvconsole.o
+obj-$(CONFIG_HVCS)		+= hvcserver.o
+
+obj-$(CONFIG_IBMVIO)		+= vio.o
+obj-$(CONFIG_XICS)		+= xics.o
+
+obj-$(CONFIG_PPC_MAPLE)		+= maple_setup.o maple_pci.o maple_time.o \
+				   udbg_16550.o
+
+obj-$(CONFIG_U3_DART)		+= u3_iommu.o
+
+ifdef CONFIG_SMP
+obj-$(CONFIG_PPC_MAPLE)		+= smp-tbsync.o
+endif
+
+obj-$(CONFIG_KPROBES)		+= kprobes.o
+
+CFLAGS_ioctl32.o += -Ifs/
+
 endif
diff --git a/arch/ppc64/kernel/asm-offsets.c b/arch/ppc64/kernel/asm-offsets.c
index 1ff4fa05a973..1378fbbe1e57 100644
--- a/arch/ppc64/kernel/asm-offsets.c
+++ b/arch/ppc64/kernel/asm-offsets.c
@@ -77,6 +77,7 @@ int main(void)
 	DEFINE(ICACHEL1LOGLINESIZE, offsetof(struct ppc64_caches, log_iline_size));
 	DEFINE(ICACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, ilines_per_page));
 	DEFINE(PLATFORM, offsetof(struct systemcfg, platform));
+	DEFINE(PLATFORM_LPAR, PLATFORM_LPAR);
 
 	/* paca */
         DEFINE(PACA_SIZE, sizeof(struct paca_struct));
diff --git a/arch/ppc64/kernel/bpa_iommu.c b/arch/ppc64/kernel/bpa_iommu.c
index 0cc463f24539..45ebe5486c40 100644
--- a/arch/ppc64/kernel/bpa_iommu.c
+++ b/arch/ppc64/kernel/bpa_iommu.c
@@ -99,7 +99,7 @@ get_iost_entry(unsigned long iopt_base, unsigned long io_address, unsigned page_
 		break;
 
 	default: /* not a known compile time constant */
-		BUILD_BUG_ON(1);
+		BUG_ON(1);
 		break;
 	}
 
diff --git a/arch/ppc64/kernel/bpa_setup.c b/arch/ppc64/kernel/bpa_setup.c
index 9f915f4222b1..017cf23e91fa 100644
--- a/arch/ppc64/kernel/bpa_setup.c
+++ b/arch/ppc64/kernel/bpa_setup.c
@@ -44,6 +44,7 @@
 #include <asm/nvram.h>
 #include <asm/cputable.h>
 #include <asm/ppc-pci.h>
+#include <asm/irq.h>
 
 #include "bpa_iic.h"
 #include "bpa_iommu.h"
diff --git a/arch/ppc64/kernel/maple_setup.c b/arch/ppc64/kernel/maple_setup.c
index 2a7fae01eee1..22987675f544 100644
--- a/arch/ppc64/kernel/maple_setup.c
+++ b/arch/ppc64/kernel/maple_setup.c
@@ -60,6 +60,7 @@
 #include <asm/of_device.h>
 #include <asm/lmb.h>
 #include <asm/mpic.h>
+#include <asm/udbg.h>
 
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
diff --git a/arch/ppc64/kernel/pmac_setup.c b/arch/ppc64/kernel/pmac_setup.c
index 497c3cd95bc3..be4c1693d149 100644
--- a/arch/ppc64/kernel/pmac_setup.c
+++ b/arch/ppc64/kernel/pmac_setup.c
@@ -73,6 +73,7 @@
 #include <asm/smu.h>
 #include <asm/pmc.h>
 #include <asm/mpic.h>
+#include <asm/udbg.h>
 
 #include "pmac.h"
 
diff --git a/include/asm-powerpc/hardirq.h b/include/asm-powerpc/hardirq.h
index 2c0a31b1008d..3b3e3b49ec12 100644
--- a/include/asm-powerpc/hardirq.h
+++ b/include/asm-powerpc/hardirq.h
@@ -1,6 +1,9 @@
 #ifndef _ASM_POWERPC_HARDIRQ_H
 #define _ASM_POWERPC_HARDIRQ_H
 
+#include <asm/irq.h>
+#include <asm/bug.h>
+
 /* The __last_jiffy_stamp field is needed to ensure that no decrementer
  * interrupt is lost on SMP machines. Since on most CPUs it is in the same
  * cache line as local_irq_count, it is cheap to access and is also used on UP
diff --git a/include/asm-powerpc/hw_irq.h b/include/asm-powerpc/hw_irq.h
index 605a65e42063..c37b31b96337 100644
--- a/include/asm-powerpc/hw_irq.h
+++ b/include/asm-powerpc/hw_irq.h
@@ -10,7 +10,6 @@
 #include <linux/errno.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
-#include <asm/irq.h>
 
 extern void timer_interrupt(struct pt_regs *);
 extern void ppc_irq_dispatch_handler(struct pt_regs *regs, int irq);
diff --git a/include/asm-powerpc/ppc_asm.h b/include/asm-powerpc/ppc_asm.h
index 6cd52c130332..e4350e406d2a 100644
--- a/include/asm-powerpc/ppc_asm.h
+++ b/include/asm-powerpc/ppc_asm.h
@@ -1,10 +1,12 @@
 /*
  * Copyright (C) 1995-1999 Gary Thomas, Paul Mackerras, Cort Dougan.
  */
-
 #ifndef _ASM_POWERPC_PPC_ASM_H
 #define _ASM_POWERPC_PPC_ASM_H
 
+#include <linux/stringify.h>
+#include <linux/config.h>
+
 #ifdef __ASSEMBLY__
 
 /*
@@ -87,6 +89,66 @@
 #define RFDI		.long 0x4c00004e	/* rfdi instruction */
 #define RFMCI		.long 0x4c00004c	/* rfmci instruction */
 
+#ifdef CONFIG_PPC64
+
+#define XGLUE(a,b) a##b
+#define GLUE(a,b) XGLUE(a,b)
+
+#define _GLOBAL(name) \
+	.section ".text"; \
+	.align 2 ; \
+	.globl name; \
+	.globl GLUE(.,name); \
+	.section ".opd","aw"; \
+name: \
+	.quad GLUE(.,name); \
+	.quad .TOC.@tocbase; \
+	.quad 0; \
+	.previous; \
+	.type GLUE(.,name),@function; \
+GLUE(.,name):
+
+#define _KPROBE(name) \
+	.section ".kprobes.text","a"; \
+	.align 2 ; \
+	.globl name; \
+	.globl GLUE(.,name); \
+	.section ".opd","aw"; \
+name: \
+	.quad GLUE(.,name); \
+	.quad .TOC.@tocbase; \
+	.quad 0; \
+	.previous; \
+	.type GLUE(.,name),@function; \
+GLUE(.,name):
+
+#define _STATIC(name) \
+	.section ".text"; \
+	.align 2 ; \
+	.section ".opd","aw"; \
+name: \
+	.quad GLUE(.,name); \
+	.quad .TOC.@tocbase; \
+	.quad 0; \
+	.previous; \
+	.type GLUE(.,name),@function; \
+GLUE(.,name):
+
+#else /* 32-bit */
+
+#define _GLOBAL(n)	\
+	.text;		\
+	.stabs __stringify(n:F-1),N_FUN,0,0,n;\
+	.globl n;	\
+n:
+
+#define _KPROBE(n)	\
+	.section ".kprobes.text","a";	\
+	.globl	n;	\
+n:
+
+#endif
+
 /* 
  * LOADADDR( rn, name )
  *   loads the address of 'name' into 'rn'
@@ -251,31 +313,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 	.previous
 #endif
 
-/*
- * On 64-bit cpus, we use the rfid instruction instead of rfi, but
- * we then have to make sure we preserve the top 32 bits except for
- * the 64-bit mode bit, which we clear.
- */
-#if defined(CONFIG_PPC64BRIDGE)
-#define	FIX_SRR1(ra, rb)	\
-	mr	rb,ra;		\
-	mfmsr	ra;		\
-	clrldi	ra,ra,1;		/* turn off 64-bit mode */ \
-	rldimi	ra,rb,0,32
-#define	RFI		.long	0x4c000024	/* rfid instruction */
-#define MTMSRD(r)	.long	(0x7c000164 + ((r) << 21))	/* mtmsrd */
-#define CLR_TOP32(r)	rlwinm	(r),(r),0,0,31	/* clear top 32 bits */
-#elif defined(CONFIG_PPC64)
-/* Insert the high 32 bits of the MSR into what will be the new
-   MSR (via SRR1 and rfid)  This preserves the MSR.SF and MSR.ISF
-   bits. */
-
-#define FIX_SRR1(ra, rb)	\
-	mr	rb,ra;		\
-	mfmsr	ra;		\
-	rldimi	ra,rb,0,32
-
-#define CLR_TOP32(r)	rlwinm	(r),(r),0,0,31	/* clear top 32 bits */
+#ifdef CONFIG_PPC64
+#define RFI		rfid
+#define MTMSRD(r)	mtmsrd	r
 
 #else
 #define FIX_SRR1(ra, rb)
diff --git a/include/asm-powerpc/prom.h b/include/asm-powerpc/prom.h
index 194b56ee1693..efc40980cb48 100644
--- a/include/asm-powerpc/prom.h
+++ b/include/asm-powerpc/prom.h
@@ -196,6 +196,7 @@ extern int prom_n_intr_cells(struct device_node* np);
 extern void prom_get_irq_senses(unsigned char *senses, int off, int max);
 extern void prom_add_property(struct device_node* np, struct property* prop);
 
+#ifdef CONFIG_PPC32
 /*
  * PCI <-> OF matching functions
  * (XXX should these be here?)
@@ -207,6 +208,8 @@ extern int pci_device_from_OF_node(struct device_node *node,
 extern struct device_node* pci_busdev_to_OF_node(struct pci_bus *, int);
 extern struct device_node* pci_device_to_OF_node(struct pci_dev *);
 extern void pci_create_OF_bus_map(void);
+#endif
+
 extern struct resource *request_OF_resource(struct device_node* node,
 				int index, const char* name_postfix);
 extern int release_OF_resource(struct device_node* node, int index);
diff --git a/include/asm-powerpc/system.h b/include/asm-powerpc/system.h
index 66866f7301a9..6463453b61a3 100644
--- a/include/asm-powerpc/system.h
+++ b/include/asm-powerpc/system.h
@@ -9,6 +9,7 @@
 
 #include <asm/hw_irq.h>
 #include <asm/ppc_asm.h>
+#include <asm/atomic.h>
 
 /*
  * Memory barrier.
@@ -127,6 +128,7 @@ extern void flush_fp_to_thread(struct task_struct *);
 extern void enable_kernel_altivec(void);
 extern void giveup_altivec(struct task_struct *);
 extern void load_up_altivec(struct task_struct *);
+extern int emulate_altivec(struct pt_regs *);
 extern void giveup_spe(struct task_struct *);
 extern void load_up_spe(struct task_struct *);
 extern int fix_alignment(struct pt_regs *);
@@ -176,6 +178,7 @@ extern struct task_struct *_switch(struct thread_struct *prev,
 				   struct thread_struct *next);
 
 extern unsigned int rtas_data;
+extern int mem_init_done;	/* set on boot once kmalloc can be called */
 
 /*
  * Atomic exchange
diff --git a/include/asm-ppc64/pci-bridge.h b/include/asm-ppc64/pci-bridge.h
index 8ca5fce626bb..c342c9eb07a4 100644
--- a/include/asm-ppc64/pci-bridge.h
+++ b/include/asm-ppc64/pci-bridge.h
@@ -106,6 +106,16 @@ static inline struct device_node *pci_device_to_OF_node(struct pci_dev *dev)
 	return fetch_dev_dn(dev);
 }
 
+static inline int pci_device_from_OF_node(struct device_node *np,
+					  u8 *bus, u8 *devfn)
+{
+	if (!PCI_DN(np))
+		return -ENODEV;
+	*bus = PCI_DN(np)->busno;
+	*devfn = PCI_DN(np)->devfn;
+	return 0;
+}
+
 static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus)
 {
 	if (bus->self)