Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc updates from Ben Herrenschmidt:
 "Here's the powerpc batch for this merge window.  Some of the
  highlights are:

   - A bunch of endian fixes ! We don't have full LE support yet in that
     release but this contains a lot of fixes all over arch/powerpc to
     use the proper accessors, call the firmware with the right endian
     mode, etc...

   - A few updates to our "powernv" platform (non-virtualized, the one
     to run KVM on), among other, support for bridging the P8 LPC bus
     for UARTs, support and some EEH fixes.

   - Some mpc51xx clock API cleanups in preparation for a clock API
     overhaul

   - A pile of cleanups of our old math emulation code, including better
     support for using it to emulate optional FP instructions on
     embedded chips that otherwise have a HW FPU.

   - Some infrastructure in selftest, for powerpc now, but could be
     generalized, initially used by some tests for our perf instruction
     counting code.

   - A pile of fixes for hotplug on pseries (that was seriously
     bitrotting)

   - The usual slew of freescale embedded updates, new boards, 64-bit
     hiberation support, e6500 core PMU support, etc..."

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (146 commits)
  powerpc: Correct FSCR bit definitions
  powerpc/xmon: Fix printing of set of CPUs in xmon
  powerpc/pseries: Move lparcfg.c to platforms/pseries
  powerpc/powernv: Return secondary CPUs to firmware on kexec
  powerpc/btext: Fix CONFIG_PPC_EARLY_DEBUG_BOOTX on ppc32
  powerpc: Cleanup handling of the DSCR bit in the FSCR register
  powerpc/pseries: Child nodes are not detached by dlpar_detach_node
  powerpc/pseries: Add mising of_node_put in delete_dt_node
  powerpc/pseries: Make dlpar_configure_connector parent node aware
  powerpc/pseries: Do all node initialization in dlpar_parse_cc_node
  powerpc/pseries: Fix parsing of initial node path in update_dt_node
  powerpc/pseries: Pack update_props_workarea to map correctly to rtas buffer header
  powerpc/pseries: Fix over writing of rtas return code in update_dt_node
  powerpc/pseries: Fix creation of loop in device node property list
  powerpc: Skip emulating & leave interrupts off for kernel program checks
  powerpc: Add more exception trampolines for hypervisor exceptions
  powerpc: Fix location and rename exception trampolines
  powerpc: Add more trap names to xmon
  powerpc/pseries: Add a warning in the case of cross-cpu VPA registration
  powerpc: Update the 00-Index in Documentation/powerpc
  ...

48 files changed, 1093 insertions, 1733 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index a8619bfe879e..445cb6e39d5b 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -55,7 +55,6 @@ obj-$(CONFIG_PPC_RTAS)		+= rtas.o rtas-rtc.o $(rtaspci-y-y)
 obj-$(CONFIG_PPC_RTAS_DAEMON)	+= rtasd.o
 obj-$(CONFIG_RTAS_FLASH)	+= rtas_flash.o
 obj-$(CONFIG_RTAS_PROC)		+= rtas-proc.o
-obj-$(CONFIG_LPARCFG)		+= lparcfg.o
 obj-$(CONFIG_IBMVIO)		+= vio.o
 obj-$(CONFIG_IBMEBUS)           += ibmebus.o
 obj-$(CONFIG_EEH)              += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \
@@ -117,9 +116,7 @@ obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 
-obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o
-
-ifneq ($(CONFIG_PPC_INDIRECT_IO),y)
+ifneq ($(CONFIG_PPC_INDIRECT_PIO),y)
 obj-y				+= iomap.o
 endif
 
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index ee5b690a0bed..a27ccd5dc6b9 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -651,6 +651,10 @@ static int emulate_vsx(unsigned char __user *addr, unsigned int reg,
 	int sw = 0;
 	int i, j;
 
+	/* userland only */
+	if (unlikely(!user_mode(regs)))
+		return 0;
+
 	flush_vsx_to_thread(current);
 
 	if (reg < 32)
@@ -764,6 +768,16 @@ int fix_alignment(struct pt_regs *regs)
 	nb = aligninfo[instr].len;
 	flags = aligninfo[instr].flags;
 
+	/* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */
+	if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) {
+		nb = 8;
+		flags = LD+SW;
+	} else if (IS_XFORM(instruction) &&
+		   ((instruction >> 1) & 0x3ff) == 660) {
+		nb = 8;
+		flags = ST+SW;
+	}
+
 	/* Byteswap little endian loads and stores */
 	swiz = 0;
 	if (regs->msr & MSR_LE) {
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index ac8f52732fde..41c011cb6070 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -25,11 +25,6 @@
 static void scrollscreen(void);
 #endif
 
-static void draw_byte(unsigned char c, long locX, long locY);
-static void draw_byte_32(unsigned char *bits, unsigned int *base, int rb);
-static void draw_byte_16(unsigned char *bits, unsigned int *base, int rb);
-static void draw_byte_8(unsigned char *bits, unsigned int *base, int rb);
-
 #define __force_data __attribute__((__section__(".data")))
 
 static int g_loc_X __force_data;
@@ -52,6 +47,26 @@ static unsigned char vga_font[cmapsz];
 int boot_text_mapped __force_data = 0;
 int force_printk_to_btext = 0;
 
+extern void rmci_on(void);
+extern void rmci_off(void);
+
+static inline void rmci_maybe_on(void)
+{
+#if defined(CONFIG_PPC_EARLY_DEBUG_BOOTX) && defined(CONFIG_PPC64)
+	if (!(mfmsr() & MSR_DR))
+		rmci_on();
+#endif
+}
+
+static inline void rmci_maybe_off(void)
+{
+#if defined(CONFIG_PPC_EARLY_DEBUG_BOOTX) && defined(CONFIG_PPC64)
+	if (!(mfmsr() & MSR_DR))
+		rmci_off();
+#endif
+}
+
+
 #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
@@ -134,7 +149,7 @@ void __init btext_unmap(void)
  *    changes.
  */
 
-static void map_boot_text(void)
+void btext_map(void)
 {
 	unsigned long base, offset, size;
 	unsigned char *vbase;
@@ -209,7 +224,7 @@ int btext_initialize(struct device_node *np)
 	dispDeviceRect[2] = width;
 	dispDeviceRect[3] = height;
 
-	map_boot_text();
+	btext_map();
 
 	return 0;
 }
@@ -283,7 +298,7 @@ void btext_update_display(unsigned long phys, int width, int height,
 		iounmap(logicalDisplayBase);
 		boot_text_mapped = 0;
 	}
-	map_boot_text();
+	btext_map();
 	g_loc_X = 0;
 	g_loc_Y = 0;
 	g_max_loc_X = width / 8;
@@ -298,6 +313,7 @@ void btext_clearscreen(void)
 					(dispDeviceDepth >> 3)) >> 2;
 	int i,j;
 
+	rmci_maybe_on();
 	for (i=0; i<(dispDeviceRect[3] - dispDeviceRect[1]); i++)
 	{
 		unsigned int *ptr = base;
@@ -305,6 +321,7 @@ void btext_clearscreen(void)
 			*(ptr++) = 0;
 		base += (dispDeviceRowBytes >> 2);
 	}
+	rmci_maybe_off();
 }
 
 void btext_flushscreen(void)
@@ -355,6 +372,8 @@ static void scrollscreen(void)
 				   (dispDeviceDepth >> 3)) >> 2;
 	int i,j;
 
+	rmci_maybe_on();
+
 	for (i=0; i<(dispDeviceRect[3] - dispDeviceRect[1] - 16); i++)
 	{
 		unsigned int *src_ptr = src;
@@ -371,9 +390,116 @@ static void scrollscreen(void)
 			*(dst_ptr++) = 0;
 		dst += (dispDeviceRowBytes >> 2);
 	}
+
+	rmci_maybe_off();
 }
 #endif /* ndef NO_SCROLL */
 
+static unsigned int expand_bits_8[16] = {
+	0x00000000,
+	0x000000ff,
+	0x0000ff00,
+	0x0000ffff,
+	0x00ff0000,
+	0x00ff00ff,
+	0x00ffff00,
+	0x00ffffff,
+	0xff000000,
+	0xff0000ff,
+	0xff00ff00,
+	0xff00ffff,
+	0xffff0000,
+	0xffff00ff,
+	0xffffff00,
+	0xffffffff
+};
+
+static unsigned int expand_bits_16[4] = {
+	0x00000000,
+	0x0000ffff,
+	0xffff0000,
+	0xffffffff
+};
+
+
+static void draw_byte_32(unsigned char *font, unsigned int *base, int rb)
+{
+	int l, bits;
+	int fg = 0xFFFFFFFFUL;
+	int bg = 0x00000000UL;
+
+	for (l = 0; l < 16; ++l)
+	{
+		bits = *font++;
+		base[0] = (-(bits >> 7) & fg) ^ bg;
+		base[1] = (-((bits >> 6) & 1) & fg) ^ bg;
+		base[2] = (-((bits >> 5) & 1) & fg) ^ bg;
+		base[3] = (-((bits >> 4) & 1) & fg) ^ bg;
+		base[4] = (-((bits >> 3) & 1) & fg) ^ bg;
+		base[5] = (-((bits >> 2) & 1) & fg) ^ bg;
+		base[6] = (-((bits >> 1) & 1) & fg) ^ bg;
+		base[7] = (-(bits & 1) & fg) ^ bg;
+		base = (unsigned int *) ((char *)base + rb);
+	}
+}
+
+static inline void draw_byte_16(unsigned char *font, unsigned int *base, int rb)
+{
+	int l, bits;
+	int fg = 0xFFFFFFFFUL;
+	int bg = 0x00000000UL;
+	unsigned int *eb = (int *)expand_bits_16;
+
+	for (l = 0; l < 16; ++l)
+	{
+		bits = *font++;
+		base[0] = (eb[bits >> 6] & fg) ^ bg;
+		base[1] = (eb[(bits >> 4) & 3] & fg) ^ bg;
+		base[2] = (eb[(bits >> 2) & 3] & fg) ^ bg;
+		base[3] = (eb[bits & 3] & fg) ^ bg;
+		base = (unsigned int *) ((char *)base + rb);
+	}
+}
+
+static inline void draw_byte_8(unsigned char *font, unsigned int *base, int rb)
+{
+	int l, bits;
+	int fg = 0x0F0F0F0FUL;
+	int bg = 0x00000000UL;
+	unsigned int *eb = (int *)expand_bits_8;
+
+	for (l = 0; l < 16; ++l)
+	{
+		bits = *font++;
+		base[0] = (eb[bits >> 4] & fg) ^ bg;
+		base[1] = (eb[bits & 0xf] & fg) ^ bg;
+		base = (unsigned int *) ((char *)base + rb);
+	}
+}
+
+static noinline void draw_byte(unsigned char c, long locX, long locY)
+{
+	unsigned char *base	= calc_base(locX << 3, locY << 4);
+	unsigned char *font	= &vga_font[((unsigned int)c) * 16];
+	int rb			= dispDeviceRowBytes;
+
+	rmci_maybe_on();
+	switch(dispDeviceDepth) {
+	case 24:
+	case 32:
+		draw_byte_32(font, (unsigned int *)base, rb);
+		break;
+	case 15:
+	case 16:
+		draw_byte_16(font, (unsigned int *)base, rb);
+		break;
+	case 8:
+		draw_byte_8(font, (unsigned int *)base, rb);
+		break;
+	}
+	rmci_maybe_off();
+}
+
 void btext_drawchar(char c)
 {
 	int cline = 0;
@@ -465,107 +591,12 @@ void btext_drawhex(unsigned long v)
 	btext_drawchar(' ');
 }
 
-static void draw_byte(unsigned char c, long locX, long locY)
-{
-	unsigned char *base	= calc_base(locX << 3, locY << 4);
-	unsigned char *font	= &vga_font[((unsigned int)c) * 16];
-	int rb			= dispDeviceRowBytes;
-
-	switch(dispDeviceDepth) {
-	case 24:
-	case 32:
-		draw_byte_32(font, (unsigned int *)base, rb);
-		break;
-	case 15:
-	case 16:
-		draw_byte_16(font, (unsigned int *)base, rb);
-		break;
-	case 8:
-		draw_byte_8(font, (unsigned int *)base, rb);
-		break;
-	}
-}
-
-static unsigned int expand_bits_8[16] = {
-	0x00000000,
-	0x000000ff,
-	0x0000ff00,
-	0x0000ffff,
-	0x00ff0000,
-	0x00ff00ff,
-	0x00ffff00,
-	0x00ffffff,
-	0xff000000,
-	0xff0000ff,
-	0xff00ff00,
-	0xff00ffff,
-	0xffff0000,
-	0xffff00ff,
-	0xffffff00,
-	0xffffffff
-};
-
-static unsigned int expand_bits_16[4] = {
-	0x00000000,
-	0x0000ffff,
-	0xffff0000,
-	0xffffffff
-};
-
-
-static void draw_byte_32(unsigned char *font, unsigned int *base, int rb)
-{
-	int l, bits;
-	int fg = 0xFFFFFFFFUL;
-	int bg = 0x00000000UL;
-
-	for (l = 0; l < 16; ++l)
-	{
-		bits = *font++;
-		base[0] = (-(bits >> 7) & fg) ^ bg;
-		base[1] = (-((bits >> 6) & 1) & fg) ^ bg;
-		base[2] = (-((bits >> 5) & 1) & fg) ^ bg;
-		base[3] = (-((bits >> 4) & 1) & fg) ^ bg;
-		base[4] = (-((bits >> 3) & 1) & fg) ^ bg;
-		base[5] = (-((bits >> 2) & 1) & fg) ^ bg;
-		base[6] = (-((bits >> 1) & 1) & fg) ^ bg;
-		base[7] = (-(bits & 1) & fg) ^ bg;
-		base = (unsigned int *) ((char *)base + rb);
-	}
-}
-
-static void draw_byte_16(unsigned char *font, unsigned int *base, int rb)
-{
-	int l, bits;
-	int fg = 0xFFFFFFFFUL;
-	int bg = 0x00000000UL;
-	unsigned int *eb = (int *)expand_bits_16;
-
-	for (l = 0; l < 16; ++l)
-	{
-		bits = *font++;
-		base[0] = (eb[bits >> 6] & fg) ^ bg;
-		base[1] = (eb[(bits >> 4) & 3] & fg) ^ bg;
-		base[2] = (eb[(bits >> 2) & 3] & fg) ^ bg;
-		base[3] = (eb[bits & 3] & fg) ^ bg;
-		base = (unsigned int *) ((char *)base + rb);
-	}
-}
-
-static void draw_byte_8(unsigned char *font, unsigned int *base, int rb)
+void __init udbg_init_btext(void)
 {
-	int l, bits;
-	int fg = 0x0F0F0F0FUL;
-	int bg = 0x00000000UL;
-	unsigned int *eb = (int *)expand_bits_8;
-
-	for (l = 0; l < 16; ++l)
-	{
-		bits = *font++;
-		base[0] = (eb[bits >> 4] & fg) ^ bg;
-		base[1] = (eb[bits & 0xf] & fg) ^ bg;
-		base = (unsigned int *) ((char *)base + rb);
-	}
+	/* If btext is enabled, we might have a BAT setup for early display,
+	 * thus we do enable some very basic udbg output
+	 */
+	udbg_putc = btext_drawchar;
 }
 
 static unsigned char vga_font[cmapsz] = {
@@ -913,10 +944,3 @@ static unsigned char vga_font[cmapsz] = {
 0x00, 0x00, 0x00, 0x00,
 };
 
-void __init udbg_init_btext(void)
-{
-	/* If btext is enabled, we might have a BAT setup for early display,
-	 * thus we do enable some very basic udbg output
-	 */
-	udbg_putc = btext_drawchar;
-}
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 9262cf2bec4b..654932727873 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -196,7 +196,7 @@ static void cache_cpu_set(struct cache *cache, int cpu)
 static int cache_size(const struct cache *cache, unsigned int *ret)
 {
 	const char *propname;
-	const u32 *cache_size;
+	const __be32 *cache_size;
 
 	propname = cache_type_info[cache->type].size_prop;
 
@@ -204,7 +204,7 @@ static int cache_size(const struct cache *cache, unsigned int *ret)
 	if (!cache_size)
 		return -ENODEV;
 
-	*ret = *cache_size;
+	*ret = of_read_number(cache_size, 1);
 	return 0;
 }
 
@@ -222,7 +222,7 @@ static int cache_size_kb(const struct cache *cache, unsigned int *ret)
 /* not cache_line_size() because that's a macro in include/linux/cache.h */
 static int cache_get_line_size(const struct cache *cache, unsigned int *ret)
 {
-	const u32 *line_size;
+	const __be32 *line_size;
 	int i, lim;
 
 	lim = ARRAY_SIZE(cache_type_info[cache->type].line_size_props);
@@ -239,14 +239,14 @@ static int cache_get_line_size(const struct cache *cache, unsigned int *ret)
 	if (!line_size)
 		return -ENODEV;
 
-	*ret = *line_size;
+	*ret = of_read_number(line_size, 1);
 	return 0;
 }
 
 static int cache_nr_sets(const struct cache *cache, unsigned int *ret)
 {
 	const char *propname;
-	const u32 *nr_sets;
+	const __be32 *nr_sets;
 
 	propname = cache_type_info[cache->type].nr_sets_prop;
 
@@ -254,7 +254,7 @@ static int cache_nr_sets(const struct cache *cache, unsigned int *ret)
 	if (!nr_sets)
 		return -ENODEV;
 
-	*ret = *nr_sets;
+	*ret = of_read_number(nr_sets, 1);
 	return 0;
 }
 
diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index 0b9af015bedc..bfb18c7290b7 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -75,7 +75,7 @@ _GLOBAL(__setup_cpu_e500v2)
 	bl	__e500_icache_setup
 	bl	__e500_dcache_setup
 	bl	__setup_e500_ivors
-#ifdef CONFIG_FSL_RIO
+#if defined(CONFIG_FSL_RIO) || defined(CONFIG_FSL_PCI)
 	/* Ensure that RFXE is set */
 	mfspr	r3,SPRN_HID1
 	oris	r3,r3,HID1_RFXE@h
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 22973a74df73..597d954e5860 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -2105,7 +2105,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 			MMU_FTR_USE_TLBILX,
 		.icache_bsize		= 64,
 		.dcache_bsize		= 64,
-		.num_pmcs		= 4,
+		.num_pmcs		= 6,
 		.oprofile_cpu_type	= "ppc/e6500",
 		.oprofile_type		= PPC_OPROFILE_FSL_EMB,
 		.cpu_setup		= __setup_cpu_e6500,
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 2bd0b885b0fe..c04cdf70d487 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -102,7 +102,8 @@ BEGIN_FW_FTR_SECTION
 	/* if from user, see if there are any DTL entries to process */
 	ld	r10,PACALPPACAPTR(r13)	/* get ptr to VPA */
 	ld	r11,PACA_DTL_RIDX(r13)	/* get log read index */
-	ld	r10,LPPACA_DTLIDX(r10)	/* get log write index */
+	addi	r10,r10,LPPACA_DTLIDX
+	LDX_BE	r10,0,r10		/* get log write index */
 	cmpd	cr1,r11,r10
 	beq+	cr1,33f
 	bl	.accumulate_stolen_time
@@ -522,9 +523,11 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	 */
 	ld	r9,PACA_SLBSHADOWPTR(r13)
 	li	r12,0
-	std	r12,SLBSHADOW_STACKESID(r9) /* Clear ESID */
-	std	r7,SLBSHADOW_STACKVSID(r9)  /* Save VSID */
-	std	r0,SLBSHADOW_STACKESID(r9)  /* Save ESID */
+	std	r12,SLBSHADOW_STACKESID(r9)	/* Clear ESID */
+	li	r12,SLBSHADOW_STACKVSID
+	STDX_BE	r7,r12,r9			/* Save VSID */
+	li	r12,SLBSHADOW_STACKESID
+	STDX_BE	r0,r12,r9			/* Save ESID */
 
 	/* No need to check for MMU_FTR_NO_SLBIE_B here, since when
 	 * we have 1TB segments, the only CPUs known to have the errata
@@ -575,34 +578,15 @@ BEGIN_FTR_SECTION
 	ld	r7,DSCR_DEFAULT@toc(2)
 	ld	r0,THREAD_DSCR(r4)
 	cmpwi	r6,0
-	li	r8, FSCR_DSCR
 	bne	1f
 	ld	r0,0(r7)
-	b	3f
 1:
-  BEGIN_FTR_SECTION_NESTED(70)
-	mfspr	r6, SPRN_FSCR
-	or	r6, r6, r8
-	mtspr	SPRN_FSCR, r6
-    BEGIN_FTR_SECTION_NESTED(69)
-	mfspr	r6, SPRN_HFSCR
-	or	r6, r6, r8
-	mtspr	SPRN_HFSCR, r6
-    END_FTR_SECTION_NESTED(CPU_FTR_HVMODE, CPU_FTR_HVMODE, 69)
-	b	4f
-  END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
-3:
-  BEGIN_FTR_SECTION_NESTED(70)
-	mfspr	r6, SPRN_FSCR
-	andc	r6, r6, r8
-	mtspr	SPRN_FSCR, r6
-    BEGIN_FTR_SECTION_NESTED(69)
-	mfspr	r6, SPRN_HFSCR
-	andc	r6, r6, r8
-	mtspr	SPRN_HFSCR, r6
-    END_FTR_SECTION_NESTED(CPU_FTR_HVMODE, CPU_FTR_HVMODE, 69)
-  END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
-4:	cmpd	r0,r25
+BEGIN_FTR_SECTION_NESTED(70)
+	mfspr	r8, SPRN_FSCR
+	rldimi	r8, r6, FSCR_DSCR_LG, (63 - FSCR_DSCR_LG)
+	mtspr	SPRN_FSCR, r8
+END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
+	cmpd	r0,r25
 	beq	2f
 	mtspr	SPRN_DSCR,r0
 2:
@@ -737,9 +721,9 @@ resume_kernel:
 
 	/*
 	 * Here we are preempting the current task. We want to make
-	 * sure we are soft-disabled first
+	 * sure we are soft-disabled first and reconcile irq state.
 	 */
-	SOFT_DISABLE_INTS(r3,r4)
+	RECONCILE_IRQ_STATE(r3,r4)
 1:	bl	.preempt_schedule_irq
 
 	/* Re-test flags and eventually loop */
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
index d44a571e45a7..6300c13bbde4 100644
--- a/arch/powerpc/kernel/epapr_paravirt.c
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -30,22 +30,20 @@ extern u32 epapr_ev_idle_start[];
 
 bool epapr_paravirt_enabled;
 
-static int __init epapr_paravirt_init(void)
+static int __init early_init_dt_scan_epapr(unsigned long node,
+					   const char *uname,
+					   int depth, void *data)
 {
-	struct device_node *hyper_node;
 	const u32 *insts;
-	int len, i;
+	unsigned long len;
+	int i;
 
-	hyper_node = of_find_node_by_path("/hypervisor");
-	if (!hyper_node)
-		return -ENODEV;
-
-	insts = of_get_property(hyper_node, "hcall-instructions", &len);
+	insts = of_get_flat_dt_prop(node, "hcall-instructions", &len);
 	if (!insts)
-		return -ENODEV;
+		return 0;
 
 	if (len % 4 || len > (4 * 4))
-		return -ENODEV;
+		return -1;
 
 	for (i = 0; i < (len / 4); i++) {
 		patch_instruction(epapr_hypercall_start + i, insts[i]);
@@ -55,13 +53,19 @@ static int __init epapr_paravirt_init(void)
 	}
 
 #if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
-	if (of_get_property(hyper_node, "has-idle", NULL))
+	if (of_get_flat_dt_prop(node, "has-idle", NULL))
 		ppc_md.power_save = epapr_ev_idle;
 #endif
 
 	epapr_paravirt_enabled = true;
 
+	return 1;
+}
+
+int __init epapr_paravirt_early_init(void)
+{
+	of_scan_flat_dt(early_init_dt_scan_epapr, NULL);
+
 	return 0;
 }
 
-early_initcall(epapr_paravirt_init);
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 645170a07ada..2d067049db27 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -198,9 +198,9 @@ exc_##n##_common:							    \
 /* This second version is meant for exceptions that don't immediately
  * hard-enable. We set a bit in paca->irq_happened to ensure that
  * a subsequent call to arch_local_irq_restore() will properly
- * hard-enable and avoid the fast-path
+ * hard-enable and avoid the fast-path, and then reconcile irq state.
  */
-#define INTS_DISABLE	SOFT_DISABLE_INTS(r3,r4)
+#define INTS_DISABLE	RECONCILE_IRQ_STATE(r3,r4)
 
 /* This is called by exceptions that used INTS_KEEP (that did not touch
  * irq indicators in the PACA). This will restore MSR:EE to it's previous
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 902ca3c6b4b6..3a9ed6ac224b 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -293,27 +293,31 @@ system_call_pSeries:
 	 * out of line to handle them
 	 */
 	. = 0xe00
-hv_exception_trampoline:
+hv_data_storage_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	h_data_storage_hv
 
 	. = 0xe20
+hv_instr_storage_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	h_instr_storage_hv
 
 	. = 0xe40
+emulation_assist_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	emulation_assist_hv
 
 	. = 0xe60
+hv_exception_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	hmi_exception_hv
 
 	. = 0xe80
+hv_doorbell_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	h_doorbell_hv
@@ -323,32 +327,32 @@ hv_exception_trampoline:
 	 * prolog code of the PerformanceMonitor one. A little
 	 * trickery is thus necessary
 	 */
-performance_monitor_pSeries_1:
 	. = 0xf00
+performance_monitor_pseries_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	performance_monitor_pSeries
 
-altivec_unavailable_pSeries_1:
 	. = 0xf20
+altivec_unavailable_pseries_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	altivec_unavailable_pSeries
 
-vsx_unavailable_pSeries_1:
 	. = 0xf40
+vsx_unavailable_pseries_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	vsx_unavailable_pSeries
 
-facility_unavailable_trampoline:
 	. = 0xf60
+facility_unavailable_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	facility_unavailable_pSeries
 
-hv_facility_unavailable_trampoline:
 	. = 0xf80
+hv_facility_unavailable_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	facility_unavailable_hv
@@ -367,11 +371,7 @@ denorm_exception_hv:
 	HMT_MEDIUM_PPR_DISCARD
 	mtspr	SPRN_SPRG_HSCRATCH0,r13
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	std	r11,PACA_EXGEN+EX_R11(r13)
-	std	r12,PACA_EXGEN+EX_R12(r13)
-	mfspr	r9,SPRN_SPRG_HSCRATCH0
-	std	r9,PACA_EXGEN+EX_R13(r13)
-	mfcr	r9
+	EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x1500)
 
 #ifdef CONFIG_PPC_DENORMALISATION
 	mfspr	r10,SPRN_HSRR1
@@ -381,6 +381,7 @@ denorm_exception_hv:
 	bne+	denorm_assist
 #endif
 
+	KVMTEST(0x1500)
 	EXCEPTION_PROLOG_PSERIES_1(denorm_common, EXC_HV)
 	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x1500)
 
@@ -501,6 +502,10 @@ denorm_done:
 	mtcrf	0x80,r9
 	ld	r9,PACA_EXGEN+EX_R9(r13)
 	RESTORE_PPR_PACA(PACA_EXGEN, r10)
+BEGIN_FTR_SECTION
+	ld	r10,PACA_EXGEN+EX_CFAR(r13)
+	mtspr	SPRN_CFAR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	ld	r10,PACA_EXGEN+EX_R10(r13)
 	ld	r11,PACA_EXGEN+EX_R11(r13)
 	ld	r12,PACA_EXGEN+EX_R12(r13)
@@ -808,6 +813,7 @@ system_call_relon_pSeries:
 	b	.	/* Can't happen, see v2.07 Book III-S section 6.5 */
 
 	. = 0x4e40
+emulation_assist_relon_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	emulation_assist_relon_hv
@@ -816,36 +822,37 @@ system_call_relon_pSeries:
 	b	.	/* Can't happen, see v2.07 Book III-S section 6.5 */
 
 	. = 0x4e80
+h_doorbell_relon_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	h_doorbell_relon_hv
 
-performance_monitor_relon_pSeries_1:
 	. = 0x4f00
+performance_monitor_relon_pseries_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	performance_monitor_relon_pSeries
 
-altivec_unavailable_relon_pSeries_1:
 	. = 0x4f20
+altivec_unavailable_relon_pseries_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	altivec_unavailable_relon_pSeries
 
-vsx_unavailable_relon_pSeries_1:
 	. = 0x4f40
+vsx_unavailable_relon_pseries_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	vsx_unavailable_relon_pSeries
 
-facility_unavailable_relon_trampoline:
 	. = 0x4f60
+facility_unavailable_relon_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	facility_unavailable_relon_pSeries
 
-hv_facility_unavailable_relon_trampoline:
 	. = 0x4f80
+hv_facility_unavailable_relon_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	hv_facility_unavailable_relon_hv
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index 8a9b6f59822d..67ee0d6c1070 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -822,14 +822,6 @@ finish_tlb_load:
 	rfi			/* Should sync shadow TLBs */
 	b	.		/* prevent prefetch past rfi */
 
-/* extern void giveup_fpu(struct task_struct *prev)
- *
- * The PowerPC 4xx family of processors do not have an FPU, so this just
- * returns.
- */
-_ENTRY(giveup_fpu)
-	blr
-
 /* This is where the main kernel code starts.
  */
 start_here:
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 97e2671cde7f..c334f53453f7 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -784,16 +784,6 @@ _GLOBAL(__fixup_440A_mcheck)
 	sync
 	blr
 
-/*
- * extern void giveup_fpu(struct task_struct *prev)
- *
- * The 44x core does not have an FPU.
- */
-#ifndef CONFIG_PPC_FPU
-_GLOBAL(giveup_fpu)
-	blr
-#endif
-
 _GLOBAL(set_context)
 
 #ifdef CONFIG_BDI_SWITCH
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index b61363d557b5..3d11d8038dee 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -703,6 +703,7 @@ _GLOBAL(relative_toc)
 	mtlr	r0
 	blr
 
+.balign 8
 p_toc:	.llong	__toc_start + 0x8000 - 0b
 
 /*
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index b2a5860accfb..1b92a97b1b04 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -691,10 +691,6 @@ modified_instr:
 	b	151b
 #endif
 
-	.globl	giveup_fpu
-giveup_fpu:
-	blr
-
 /*
  * This is where the main kernel code starts.
  */
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index d10a7cacccd2..289afaffbbb5 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -948,16 +948,6 @@ _GLOBAL(giveup_spe)
 #endif /* CONFIG_SPE */
 
 /*
- * extern void giveup_fpu(struct task_struct *prev)
- *
- * Not all FSL Book-E cores have an FPU
- */
-#ifndef CONFIG_PPC_FPU
-_GLOBAL(giveup_fpu)
-	blr
-#endif
-
-/*
  * extern void abort(void)
  *
  * At present, this routine just applies a system reset.
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
index fa0b54b2a362..24b968f8e4d8 100644
--- a/arch/powerpc/kernel/io-workarounds.c
+++ b/arch/powerpc/kernel/io-workarounds.c
@@ -53,6 +53,7 @@ static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr)
 	return NULL;
 }
 
+#ifdef CONFIG_PPC_INDIRECT_MMIO
 struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
 {
 	unsigned hugepage_shift;
@@ -90,13 +91,25 @@ struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
 
 	return bus;
 }
+#else /* CONFIG_PPC_INDIRECT_MMIO */
+struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
+{
+	return NULL;
+}
+#endif /* !CONFIG_PPC_INDIRECT_MMIO */
 
+#ifdef CONFIG_PPC_INDIRECT_PIO
 struct iowa_bus *iowa_pio_find_bus(unsigned long port)
 {
 	unsigned long vaddr = (unsigned long)pci_io_base + port;
 	return iowa_pci_find(vaddr, 0);
 }
-
+#else
+struct iowa_bus *iowa_pio_find_bus(unsigned long port)
+{
+	return NULL;
+}
+#endif
 
 #define DEF_PCI_AC_RET(name, ret, at, al, space, aa)		\
 static ret iowa_##name at					\
@@ -137,6 +150,7 @@ static const struct ppc_pci_io iowa_pci_io = {
 
 };
 
+#ifdef CONFIG_PPC_INDIRECT_MMIO
 static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
 				  unsigned long flags, void *caller)
 {
@@ -151,6 +165,9 @@ static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
 	}
 	return res;
 }
+#else /* CONFIG_PPC_INDIRECT_MMIO */
+#define iowa_ioremap NULL
+#endif /* !CONFIG_PPC_INDIRECT_MMIO */
 
 /* Enable IO workaround */
 static void io_workaround_init(void)
diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c
index 886381f32c3d..2a2b4aeab80f 100644
--- a/arch/powerpc/kernel/io.c
+++ b/arch/powerpc/kernel/io.c
@@ -25,6 +25,9 @@
 #include <asm/firmware.h>
 #include <asm/bug.h>
 
+/* See definition in io.h */
+bool isa_io_special;
+
 void _insb(const volatile u8 __iomem *port, void *buf, long count)
 {
 	u8 *tbuf = buf;
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 0733b05eb856..22e88dd2f34a 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -99,7 +99,7 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
 		legacy_serial_count = index + 1;
 
 	/* Check if there is a port who already claimed our slot */
-	if (legacy_serial_infos[index].np != 0) {
+	if (legacy_serial_infos[index].np != NULL) {
 		/* if we still have some room, move it, else override */
 		if (legacy_serial_count < MAX_LEGACY_SERIAL_PORTS) {
 			printk(KERN_DEBUG "Moved legacy port %d -> %d\n",
@@ -152,7 +152,7 @@ static int __init add_legacy_soc_port(struct device_node *np,
 				      struct device_node *soc_dev)
 {
 	u64 addr;
-	const u32 *addrp;
+	const __be32 *addrp;
 	upf_t flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_SHARE_IRQ
 		| UPF_FIXED_PORT;
 	struct device_node *tsi = of_get_parent(np);
@@ -221,14 +221,19 @@ static int __init add_legacy_isa_port(struct device_node *np,
 	/* Translate ISA address. If it fails, we still register the port
 	 * with no translated address so that it can be picked up as an IO
 	 * port later by the serial driver
+	 *
+	 * Note: Don't even try on P8 lpc, we know it's not directly mapped
 	 */
-	taddr = of_translate_address(np, reg);
-	if (taddr == OF_BAD_ADDR)
+	if (!of_device_is_compatible(isa_brg, "ibm,power8-lpc")) {
+		taddr = of_translate_address(np, reg);
+		if (taddr == OF_BAD_ADDR)
+			taddr = 0;
+	} else
 		taddr = 0;
 
 	/* Add port, irq will be dealt with later */
-	return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]), taddr,
-			       NO_IRQ, UPF_BOOT_AUTOCONF, 0);
+	return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]),
+			       taddr, NO_IRQ, UPF_BOOT_AUTOCONF, 0);
 
 }
 
@@ -237,7 +242,7 @@ static int __init add_legacy_pci_port(struct device_node *np,
 				      struct device_node *pci_dev)
 {
 	u64 addr, base;
-	const u32 *addrp;
+	const __be32 *addrp;
 	unsigned int flags;
 	int iotype, index = -1, lindex = 0;
 
@@ -270,7 +275,7 @@ static int __init add_legacy_pci_port(struct device_node *np,
 	if (iotype == UPIO_MEM)
 		base = addr;
 	else
-		base = addrp[2];
+		base = of_read_number(&addrp[2], 1);
 
 	/* Try to guess an index... If we have subdevices of the pci dev,
 	 * we get to their "reg" property
@@ -307,19 +312,31 @@ static int __init add_legacy_pci_port(struct device_node *np,
 
 static void __init setup_legacy_serial_console(int console)
 {
-	struct legacy_serial_info *info =
-		&legacy_serial_infos[console];
+	struct legacy_serial_info *info = &legacy_serial_infos[console];
+	struct plat_serial8250_port *port = &legacy_serial_ports[console];
 	void __iomem *addr;
 
-	if (info->taddr == 0)
-		return;
-	addr = ioremap(info->taddr, 0x1000);
-	if (addr == NULL)
-		return;
+	/* Check if a translated MMIO address has been found */
+	if (info->taddr) {
+		addr = ioremap(info->taddr, 0x1000);
+		if (addr == NULL)
+			return;
+		udbg_uart_init_mmio(addr, 1);
+	} else {
+		/* Check if it's PIO and we support untranslated PIO */
+		if (port->iotype == UPIO_PORT && isa_io_special)
+			udbg_uart_init_pio(port->iobase, 1);
+		else
+			return;
+	}
+
+	/* Try to query the current speed */
 	if (info->speed == 0)
-		info->speed = udbg_probe_uart_speed(addr, info->clock);
+		info->speed = udbg_probe_uart_speed(info->clock);
+
+	/* Set it up */
 	DBG("default console speed = %d\n", info->speed);
-	udbg_init_uart(addr, info->speed, info->clock);
+	udbg_uart_setup(info->speed, info->clock);
 }
 
 /*
@@ -367,10 +384,13 @@ void __init find_legacy_serial_ports(void)
 	/* Next, fill our array with ISA ports */
 	for_each_node_by_type(np, "serial") {
 		struct device_node *isa = of_get_parent(np);
-		if (isa && !strcmp(isa->name, "isa")) {
-			index = add_legacy_isa_port(np, isa);
-			if (index >= 0 && np == stdout)
-				legacy_serial_console = index;
+		if (isa && (!strcmp(isa->name, "isa") ||
+			    !strcmp(isa->name, "lpc"))) {
+			if (of_device_is_available(np)) {
+				index = add_legacy_isa_port(np, isa);
+				if (index >= 0 && np == stdout)
+					legacy_serial_console = index;
+			}
 		}
 		of_node_put(isa);
 	}
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
deleted file mode 100644
index e2a0a162299b..000000000000
--- a/arch/powerpc/kernel/lparcfg.c
+++ /dev/null
@@ -1,708 +0,0 @@
-/*
- * PowerPC64 LPAR Configuration Information Driver
- *
- * Dave Engebretsen engebret@us.ibm.com
- *    Copyright (c) 2003 Dave Engebretsen
- * Will Schmidt willschm@us.ibm.com
- *    SPLPAR updates, Copyright (c) 2003 Will Schmidt IBM Corporation.
- *    seq_file updates, Copyright (c) 2004 Will Schmidt IBM Corporation.
- * Nathan Lynch nathanl@austin.ibm.com
- *    Added lparcfg_write, Copyright (C) 2004 Nathan Lynch IBM Corporation.
- *
- *      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.
- *
- * This driver creates a proc file at /proc/ppc64/lparcfg which contains
- * keyword - value pairs that specify the configuration of the partition.
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/errno.h>
-#include <linux/proc_fs.h>
-#include <linux/init.h>
-#include <linux/seq_file.h>
-#include <linux/slab.h>
-#include <asm/uaccess.h>
-#include <asm/lppaca.h>
-#include <asm/hvcall.h>
-#include <asm/firmware.h>
-#include <asm/rtas.h>
-#include <asm/time.h>
-#include <asm/prom.h>
-#include <asm/vdso_datapage.h>
-#include <asm/vio.h>
-#include <asm/mmu.h>
-#include <asm/machdep.h>
-
-
-/*
- * This isn't a module but we expose that to userspace
- * via /proc so leave the definitions here
- */
-#define MODULE_VERS "1.9"
-#define MODULE_NAME "lparcfg"
-
-/* #define LPARCFG_DEBUG */
-
-/*
- * Track sum of all purrs across all processors. This is used to further
- * calculate usage values by different applications
- */
-static unsigned long get_purr(void)
-{
-	unsigned long sum_purr = 0;
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct cpu_usage *cu;
-
-		cu = &per_cpu(cpu_usage_array, cpu);
-		sum_purr += cu->current_tb;
-	}
-	return sum_purr;
-}
-
-/*
- * Methods used to fetch LPAR data when running on a pSeries platform.
- */
-
-struct hvcall_ppp_data {
-	u64	entitlement;
-	u64	unallocated_entitlement;
-	u16	group_num;
-	u16	pool_num;
-	u8	capped;
-	u8	weight;
-	u8	unallocated_weight;
-	u16	active_procs_in_pool;
-	u16	active_system_procs;
-	u16	phys_platform_procs;
-	u32	max_proc_cap_avail;
-	u32	entitled_proc_cap_avail;
-};
-
-/*
- * H_GET_PPP hcall returns info in 4 parms.
- *  entitled_capacity,unallocated_capacity,
- *  aggregation, resource_capability).
- *
- *  R4 = Entitled Processor Capacity Percentage.
- *  R5 = Unallocated Processor Capacity Percentage.
- *  R6 (AABBCCDDEEFFGGHH).
- *      XXXX - reserved (0)
- *          XXXX - reserved (0)
- *              XXXX - Group Number
- *                  XXXX - Pool Number.
- *  R7 (IIJJKKLLMMNNOOPP).
- *      XX - reserved. (0)
- *        XX - bit 0-6 reserved (0).   bit 7 is Capped indicator.
- *          XX - variable processor Capacity Weight
- *            XX - Unallocated Variable Processor Capacity Weight.
- *              XXXX - Active processors in Physical Processor Pool.
- *                  XXXX  - Processors active on platform.
- *  R8 (QQQQRRRRRRSSSSSS). if ibm,partition-performance-parameters-level >= 1
- *	XXXX - Physical platform procs allocated to virtualization.
- *	    XXXXXX - Max procs capacity % available to the partitions pool.
- *	          XXXXXX - Entitled procs capacity % available to the
- *			   partitions pool.
- */
-static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data)
-{
-	unsigned long rc;
-	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
-
-	rc = plpar_hcall9(H_GET_PPP, retbuf);
-
-	ppp_data->entitlement = retbuf[0];
-	ppp_data->unallocated_entitlement = retbuf[1];
-
-	ppp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff;
-	ppp_data->pool_num = retbuf[2] & 0xffff;
-
-	ppp_data->capped = (retbuf[3] >> 6 * 8) & 0x01;
-	ppp_data->weight = (retbuf[3] >> 5 * 8) & 0xff;
-	ppp_data->unallocated_weight = (retbuf[3] >> 4 * 8) & 0xff;
-	ppp_data->active_procs_in_pool = (retbuf[3] >> 2 * 8) & 0xffff;
-	ppp_data->active_system_procs = retbuf[3] & 0xffff;
-
-	ppp_data->phys_platform_procs = retbuf[4] >> 6 * 8;
-	ppp_data->max_proc_cap_avail = (retbuf[4] >> 3 * 8) & 0xffffff;
-	ppp_data->entitled_proc_cap_avail = retbuf[4] & 0xffffff;
-
-	return rc;
-}
-
-static unsigned h_pic(unsigned long *pool_idle_time,
-		      unsigned long *num_procs)
-{
-	unsigned long rc;
-	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
-	rc = plpar_hcall(H_PIC, retbuf);
-
-	*pool_idle_time = retbuf[0];
-	*num_procs = retbuf[1];
-
-	return rc;
-}
-
-/*
- * parse_ppp_data
- * Parse out the data returned from h_get_ppp and h_pic
- */
-static void parse_ppp_data(struct seq_file *m)
-{
-	struct hvcall_ppp_data ppp_data;
-	struct device_node *root;
-	const int *perf_level;
-	int rc;
-
-	rc = h_get_ppp(&ppp_data);
-	if (rc)
-		return;
-
-	seq_printf(m, "partition_entitled_capacity=%lld\n",
-	           ppp_data.entitlement);
-	seq_printf(m, "group=%d\n", ppp_data.group_num);
-	seq_printf(m, "system_active_processors=%d\n",
-	           ppp_data.active_system_procs);
-
-	/* pool related entries are appropriate for shared configs */
-	if (lppaca_of(0).shared_proc) {
-		unsigned long pool_idle_time, pool_procs;
-
-		seq_printf(m, "pool=%d\n", ppp_data.pool_num);
-
-		/* report pool_capacity in percentage */
-		seq_printf(m, "pool_capacity=%d\n",
-			   ppp_data.active_procs_in_pool * 100);
-
-		h_pic(&pool_idle_time, &pool_procs);
-		seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time);
-		seq_printf(m, "pool_num_procs=%ld\n", pool_procs);
-	}
-
-	seq_printf(m, "unallocated_capacity_weight=%d\n",
-		   ppp_data.unallocated_weight);
-	seq_printf(m, "capacity_weight=%d\n", ppp_data.weight);
-	seq_printf(m, "capped=%d\n", ppp_data.capped);
-	seq_printf(m, "unallocated_capacity=%lld\n",
-		   ppp_data.unallocated_entitlement);
-
-	/* The last bits of information returned from h_get_ppp are only
-	 * valid if the ibm,partition-performance-parameters-level
-	 * property is >= 1.
-	 */
-	root = of_find_node_by_path("/");
-	if (root) {
-		perf_level = of_get_property(root,
-				"ibm,partition-performance-parameters-level",
-					     NULL);
-		if (perf_level && (*perf_level >= 1)) {
-			seq_printf(m,
-			    "physical_procs_allocated_to_virtualization=%d\n",
-				   ppp_data.phys_platform_procs);
-			seq_printf(m, "max_proc_capacity_available=%d\n",
-				   ppp_data.max_proc_cap_avail);
-			seq_printf(m, "entitled_proc_capacity_available=%d\n",
-				   ppp_data.entitled_proc_cap_avail);
-		}
-
-		of_node_put(root);
-	}
-}
-
-/**
- * parse_mpp_data
- * Parse out data returned from h_get_mpp
- */
-static void parse_mpp_data(struct seq_file *m)
-{
-	struct hvcall_mpp_data mpp_data;
-	int rc;
-
-	rc = h_get_mpp(&mpp_data);
-	if (rc)
-		return;
-
-	seq_printf(m, "entitled_memory=%ld\n", mpp_data.entitled_mem);
-
-	if (mpp_data.mapped_mem != -1)
-		seq_printf(m, "mapped_entitled_memory=%ld\n",
-		           mpp_data.mapped_mem);
-
-	seq_printf(m, "entitled_memory_group_number=%d\n", mpp_data.group_num);
-	seq_printf(m, "entitled_memory_pool_number=%d\n", mpp_data.pool_num);
-
-	seq_printf(m, "entitled_memory_weight=%d\n", mpp_data.mem_weight);
-	seq_printf(m, "unallocated_entitled_memory_weight=%d\n",
-	           mpp_data.unallocated_mem_weight);
-	seq_printf(m, "unallocated_io_mapping_entitlement=%ld\n",
-	           mpp_data.unallocated_entitlement);
-
-	if (mpp_data.pool_size != -1)
-		seq_printf(m, "entitled_memory_pool_size=%ld bytes\n",
-		           mpp_data.pool_size);
-
-	seq_printf(m, "entitled_memory_loan_request=%ld\n",
-	           mpp_data.loan_request);
-
-	seq_printf(m, "backing_memory=%ld bytes\n", mpp_data.backing_mem);
-}
-
-/**
- * parse_mpp_x_data
- * Parse out data returned from h_get_mpp_x
- */
-static void parse_mpp_x_data(struct seq_file *m)
-{
-	struct hvcall_mpp_x_data mpp_x_data;
-
-	if (!firmware_has_feature(FW_FEATURE_XCMO))
-		return;
-	if (h_get_mpp_x(&mpp_x_data))
-		return;
-
-	seq_printf(m, "coalesced_bytes=%ld\n", mpp_x_data.coalesced_bytes);
-
-	if (mpp_x_data.pool_coalesced_bytes)
-		seq_printf(m, "pool_coalesced_bytes=%ld\n",
-			   mpp_x_data.pool_coalesced_bytes);
-	if (mpp_x_data.pool_purr_cycles)
-		seq_printf(m, "coalesce_pool_purr=%ld\n", mpp_x_data.pool_purr_cycles);
-	if (mpp_x_data.pool_spurr_cycles)
-		seq_printf(m, "coalesce_pool_spurr=%ld\n", mpp_x_data.pool_spurr_cycles);
-}
-
-#define SPLPAR_CHARACTERISTICS_TOKEN 20
-#define SPLPAR_MAXLENGTH 1026*(sizeof(char))
-
-/*
- * parse_system_parameter_string()
- * Retrieve the potential_processors, max_entitled_capacity and friends
- * through the get-system-parameter rtas call.  Replace keyword strings as
- * necessary.
- */
-static void parse_system_parameter_string(struct seq_file *m)
-{
-	int call_status;
-
-	unsigned char *local_buffer = kmalloc(SPLPAR_MAXLENGTH, GFP_KERNEL);
-	if (!local_buffer) {
-		printk(KERN_ERR "%s %s kmalloc failure at line %d\n",
-		       __FILE__, __func__, __LINE__);
-		return;
-	}
-
-	spin_lock(&rtas_data_buf_lock);
-	memset(rtas_data_buf, 0, SPLPAR_MAXLENGTH);
-	call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
-				NULL,
-				SPLPAR_CHARACTERISTICS_TOKEN,
-				__pa(rtas_data_buf),
-				RTAS_DATA_BUF_SIZE);
-	memcpy(local_buffer, rtas_data_buf, SPLPAR_MAXLENGTH);
-	local_buffer[SPLPAR_MAXLENGTH - 1] = '\0';
-	spin_unlock(&rtas_data_buf_lock);
-
-	if (call_status != 0) {
-		printk(KERN_INFO
-		       "%s %s Error calling get-system-parameter (0x%x)\n",
-		       __FILE__, __func__, call_status);
-	} else {
-		int splpar_strlen;
-		int idx, w_idx;
-		char *workbuffer = kzalloc(SPLPAR_MAXLENGTH, GFP_KERNEL);
-		if (!workbuffer) {
-			printk(KERN_ERR "%s %s kmalloc failure at line %d\n",
-			       __FILE__, __func__, __LINE__);
-			kfree(local_buffer);
-			return;
-		}
-#ifdef LPARCFG_DEBUG
-		printk(KERN_INFO "success calling get-system-parameter\n");
-#endif
-		splpar_strlen = local_buffer[0] * 256 + local_buffer[1];
-		local_buffer += 2;	/* step over strlen value */
-
-		w_idx = 0;
-		idx = 0;
-		while ((*local_buffer) && (idx < splpar_strlen)) {
-			workbuffer[w_idx++] = local_buffer[idx++];
-			if ((local_buffer[idx] == ',')
-			    || (local_buffer[idx] == '\0')) {
-				workbuffer[w_idx] = '\0';
-				if (w_idx) {
-					/* avoid the empty string */
-					seq_printf(m, "%s\n", workbuffer);
-				}
-				memset(workbuffer, 0, SPLPAR_MAXLENGTH);
-				idx++;	/* skip the comma */
-				w_idx = 0;
-			} else if (local_buffer[idx] == '=') {
-				/* code here to replace workbuffer contents
-				   with different keyword strings */
-				if (0 == strcmp(workbuffer, "MaxEntCap")) {
-					strcpy(workbuffer,
-					       "partition_max_entitled_capacity");
-					w_idx = strlen(workbuffer);
-				}
-				if (0 == strcmp(workbuffer, "MaxPlatProcs")) {
-					strcpy(workbuffer,
-					       "system_potential_processors");
-					w_idx = strlen(workbuffer);
-				}
-			}
-		}
-		kfree(workbuffer);
-		local_buffer -= 2;	/* back up over strlen value */
-	}
-	kfree(local_buffer);
-}
-
-/* Return the number of processors in the system.
- * This function reads through the device tree and counts
- * the virtual processors, this does not include threads.
- */
-static int lparcfg_count_active_processors(void)
-{
-	struct device_node *cpus_dn = NULL;
-	int count = 0;
-
-	while ((cpus_dn = of_find_node_by_type(cpus_dn, "cpu"))) {
-#ifdef LPARCFG_DEBUG
-		printk(KERN_ERR "cpus_dn %p\n", cpus_dn);
-#endif
-		count++;
-	}
-	return count;
-}
-
-static void pseries_cmo_data(struct seq_file *m)
-{
-	int cpu;
-	unsigned long cmo_faults = 0;
-	unsigned long cmo_fault_time = 0;
-
-	seq_printf(m, "cmo_enabled=%d\n", firmware_has_feature(FW_FEATURE_CMO));
-
-	if (!firmware_has_feature(FW_FEATURE_CMO))
-		return;
-
-	for_each_possible_cpu(cpu) {
-		cmo_faults += lppaca_of(cpu).cmo_faults;
-		cmo_fault_time += lppaca_of(cpu).cmo_fault_time;
-	}
-
-	seq_printf(m, "cmo_faults=%lu\n", cmo_faults);
-	seq_printf(m, "cmo_fault_time_usec=%lu\n",
-		   cmo_fault_time / tb_ticks_per_usec);
-	seq_printf(m, "cmo_primary_psp=%d\n", cmo_get_primary_psp());
-	seq_printf(m, "cmo_secondary_psp=%d\n", cmo_get_secondary_psp());
-	seq_printf(m, "cmo_page_size=%lu\n", cmo_get_page_size());
-}
-
-static void splpar_dispatch_data(struct seq_file *m)
-{
-	int cpu;
-	unsigned long dispatches = 0;
-	unsigned long dispatch_dispersions = 0;
-
-	for_each_possible_cpu(cpu) {
-		dispatches += lppaca_of(cpu).yield_count;
-		dispatch_dispersions += lppaca_of(cpu).dispersion_count;
-	}
-
-	seq_printf(m, "dispatches=%lu\n", dispatches);
-	seq_printf(m, "dispatch_dispersions=%lu\n", dispatch_dispersions);
-}
-
-static void parse_em_data(struct seq_file *m)
-{
-	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
-	if (firmware_has_feature(FW_FEATURE_LPAR) &&
-	    plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS)
-		seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]);
-}
-
-static int pseries_lparcfg_data(struct seq_file *m, void *v)
-{
-	int partition_potential_processors;
-	int partition_active_processors;
-	struct device_node *rtas_node;
-	const int *lrdrp = NULL;
-
-	rtas_node = of_find_node_by_path("/rtas");
-	if (rtas_node)
-		lrdrp = of_get_property(rtas_node, "ibm,lrdr-capacity", NULL);
-
-	if (lrdrp == NULL) {
-		partition_potential_processors = vdso_data->processorCount;
-	} else {
-		partition_potential_processors = *(lrdrp + 4);
-	}
-	of_node_put(rtas_node);
-
-	partition_active_processors = lparcfg_count_active_processors();
-
-	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
-		/* this call handles the ibm,get-system-parameter contents */
-		parse_system_parameter_string(m);
-		parse_ppp_data(m);
-		parse_mpp_data(m);
-		parse_mpp_x_data(m);
-		pseries_cmo_data(m);
-		splpar_dispatch_data(m);
-
-		seq_printf(m, "purr=%ld\n", get_purr());
-	} else {		/* non SPLPAR case */
-
-		seq_printf(m, "system_active_processors=%d\n",
-			   partition_potential_processors);
-
-		seq_printf(m, "system_potential_processors=%d\n",
-			   partition_potential_processors);
-
-		seq_printf(m, "partition_max_entitled_capacity=%d\n",
-			   partition_potential_processors * 100);
-
-		seq_printf(m, "partition_entitled_capacity=%d\n",
-			   partition_active_processors * 100);
-	}
-
-	seq_printf(m, "partition_active_processors=%d\n",
-		   partition_active_processors);
-
-	seq_printf(m, "partition_potential_processors=%d\n",
-		   partition_potential_processors);
-
-	seq_printf(m, "shared_processor_mode=%d\n", lppaca_of(0).shared_proc);
-
-	seq_printf(m, "slb_size=%d\n", mmu_slb_size);
-
-	parse_em_data(m);
-
-	return 0;
-}
-
-static ssize_t update_ppp(u64 *entitlement, u8 *weight)
-{
-	struct hvcall_ppp_data ppp_data;
-	u8 new_weight;
-	u64 new_entitled;
-	ssize_t retval;
-
-	/* Get our current parameters */
-	retval = h_get_ppp(&ppp_data);
-	if (retval)
-		return retval;
-
-	if (entitlement) {
-		new_weight = ppp_data.weight;
-		new_entitled = *entitlement;
-	} else if (weight) {
-		new_weight = *weight;
-		new_entitled = ppp_data.entitlement;
-	} else
-		return -EINVAL;
-
-	pr_debug("%s: current_entitled = %llu, current_weight = %u\n",
-		 __func__, ppp_data.entitlement, ppp_data.weight);
-
-	pr_debug("%s: new_entitled = %llu, new_weight = %u\n",
-		 __func__, new_entitled, new_weight);
-
-	retval = plpar_hcall_norets(H_SET_PPP, new_entitled, new_weight);
-	return retval;
-}
-
-/**
- * update_mpp
- *
- * Update the memory entitlement and weight for the partition.  Caller must
- * specify either a new entitlement or weight, not both, to be updated
- * since the h_set_mpp call takes both entitlement and weight as parameters.
- */
-static ssize_t update_mpp(u64 *entitlement, u8 *weight)
-{
-	struct hvcall_mpp_data mpp_data;
-	u64 new_entitled;
-	u8 new_weight;
-	ssize_t rc;
-
-	if (entitlement) {
-		/* Check with vio to ensure the new memory entitlement
-		 * can be handled.
-		 */
-		rc = vio_cmo_entitlement_update(*entitlement);
-		if (rc)
-			return rc;
-	}
-
-	rc = h_get_mpp(&mpp_data);
-	if (rc)
-		return rc;
-
-	if (entitlement) {
-		new_weight = mpp_data.mem_weight;
-		new_entitled = *entitlement;
-	} else if (weight) {
-		new_weight = *weight;
-		new_entitled = mpp_data.entitled_mem;
-	} else
-		return -EINVAL;
-
-	pr_debug("%s: current_entitled = %lu, current_weight = %u\n",
-	         __func__, mpp_data.entitled_mem, mpp_data.mem_weight);
-
-	pr_debug("%s: new_entitled = %llu, new_weight = %u\n",
-		 __func__, new_entitled, new_weight);
-
-	rc = plpar_hcall_norets(H_SET_MPP, new_entitled, new_weight);
-	return rc;
-}
-
-/*
- * Interface for changing system parameters (variable capacity weight
- * and entitled capacity).  Format of input is "param_name=value";
- * anything after value is ignored.  Valid parameters at this time are
- * "partition_entitled_capacity" and "capacity_weight".  We use
- * H_SET_PPP to alter parameters.
- *
- * This function should be invoked only on systems with
- * FW_FEATURE_SPLPAR.
- */
-static ssize_t lparcfg_write(struct file *file, const char __user * buf,
-			     size_t count, loff_t * off)
-{
-	int kbuf_sz = 64;
-	char kbuf[kbuf_sz];
-	char *tmp;
-	u64 new_entitled, *new_entitled_ptr = &new_entitled;
-	u8 new_weight, *new_weight_ptr = &new_weight;
-	ssize_t retval;
-
-	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
-		return -EINVAL;
-
-	if (count > kbuf_sz)
-		return -EINVAL;
-
-	if (copy_from_user(kbuf, buf, count))
-		return -EFAULT;
-
-	kbuf[count - 1] = '\0';
-	tmp = strchr(kbuf, '=');
-	if (!tmp)
-		return -EINVAL;
-
-	*tmp++ = '\0';
-
-	if (!strcmp(kbuf, "partition_entitled_capacity")) {
-		char *endp;
-		*new_entitled_ptr = (u64) simple_strtoul(tmp, &endp, 10);
-		if (endp == tmp)
-			return -EINVAL;
-
-		retval = update_ppp(new_entitled_ptr, NULL);
-	} else if (!strcmp(kbuf, "capacity_weight")) {
-		char *endp;
-		*new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10);
-		if (endp == tmp)
-			return -EINVAL;
-
-		retval = update_ppp(NULL, new_weight_ptr);
-	} else if (!strcmp(kbuf, "entitled_memory")) {
-		char *endp;
-		*new_entitled_ptr = (u64) simple_strtoul(tmp, &endp, 10);
-		if (endp == tmp)
-			return -EINVAL;
-
-		retval = update_mpp(new_entitled_ptr, NULL);
-	} else if (!strcmp(kbuf, "entitled_memory_weight")) {
-		char *endp;
-		*new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10);
-		if (endp == tmp)
-			return -EINVAL;
-
-		retval = update_mpp(NULL, new_weight_ptr);
-	} else
-		return -EINVAL;
-
-	if (retval == H_SUCCESS || retval == H_CONSTRAINED) {
-		retval = count;
-	} else if (retval == H_BUSY) {
-		retval = -EBUSY;
-	} else if (retval == H_HARDWARE) {
-		retval = -EIO;
-	} else if (retval == H_PARAMETER) {
-		retval = -EINVAL;
-	}
-
-	return retval;
-}
-
-static int lparcfg_data(struct seq_file *m, void *v)
-{
-	struct device_node *rootdn;
-	const char *model = "";
-	const char *system_id = "";
-	const char *tmp;
-	const unsigned int *lp_index_ptr;
-	unsigned int lp_index = 0;
-
-	seq_printf(m, "%s %s\n", MODULE_NAME, MODULE_VERS);
-
-	rootdn = of_find_node_by_path("/");
-	if (rootdn) {
-		tmp = of_get_property(rootdn, "model", NULL);
-		if (tmp)
-			model = tmp;
-		tmp = of_get_property(rootdn, "system-id", NULL);
-		if (tmp)
-			system_id = tmp;
-		lp_index_ptr = of_get_property(rootdn, "ibm,partition-no",
-					NULL);
-		if (lp_index_ptr)
-			lp_index = *lp_index_ptr;
-		of_node_put(rootdn);
-	}
-	seq_printf(m, "serial_number=%s\n", system_id);
-	seq_printf(m, "system_type=%s\n", model);
-	seq_printf(m, "partition_id=%d\n", (int)lp_index);
-
-	return pseries_lparcfg_data(m, v);
-}
-
-static int lparcfg_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, lparcfg_data, NULL);
-}
-
-static const struct file_operations lparcfg_fops = {
-	.read		= seq_read,
-	.write		= lparcfg_write,
-	.open		= lparcfg_open,
-	.release	= single_release,
-	.llseek		= seq_lseek,
-};
-
-static int __init lparcfg_init(void)
-{
-	umode_t mode = S_IRUSR | S_IRGRP | S_IROTH;
-
-	/* Allow writing if we have FW_FEATURE_SPLPAR */
-	if (firmware_has_feature(FW_FEATURE_SPLPAR))
-		mode |= S_IWUSR;
-
-	if (!proc_create("powerpc/lparcfg", mode, NULL, &lparcfg_fops)) {
-		printk(KERN_ERR "Failed to create powerpc/lparcfg\n");
-		return -EIO;
-	}
-	return 0;
-}
-machine_device_initcall(pseries, lparcfg_init);
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index e469f30e6eeb..777d999f563b 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -327,8 +327,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_UNIFIED_ID_CACHE)
  *
  * flush_icache_range(unsigned long start, unsigned long stop)
  */
-_KPROBE(__flush_icache_range)
+_KPROBE(flush_icache_range)
 BEGIN_FTR_SECTION
+	isync
 	blr				/* for 601, do nothing */
 END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 	li	r5,L1_CACHE_BYTES-1
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 6820e45f557b..971d7e78aff2 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -67,8 +67,10 @@ PPC64_CACHES:
  *   flush all bytes from start through stop-1 inclusive
  */
 
-_KPROBE(__flush_icache_range)
-
+_KPROBE(flush_icache_range)
+BEGIN_FTR_SECTION
+	blr
+END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 /*
  * Flush the data cache to memory 
  * 
@@ -247,6 +249,37 @@ _GLOBAL(__bswapdi2)
 	blr
 
 #if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE)
+
+_GLOBAL(rmci_on)
+	sync
+	isync
+	li	r3,0x100
+	rldicl	r3,r3,32,0
+	mfspr	r5,SPRN_HID4
+	or	r5,r5,r3
+	sync
+	mtspr	SPRN_HID4,r5
+	isync
+	slbia
+	isync
+	sync
+	blr
+
+_GLOBAL(rmci_off)
+	sync
+	isync
+	li	r3,0x100
+	rldicl	r3,r3,32,0
+	mfspr	r5,SPRN_HID4
+	andc	r5,r5,r3
+	sync
+	mtspr	SPRN_HID4,r5
+	isync
+	slbia
+	isync
+	sync
+	blr
+
 /*
  * Do an IO access in real mode
  */
@@ -416,19 +449,6 @@ _GLOBAL(scom970_write)
 	blr
 #endif /* CONFIG_CPU_FREQ_PMAC64 || CONFIG_CPU_FREQ_MAPLE */
 
-
-/*
- * disable_kernel_fp()
- * Disable the FPU.
- */
-_GLOBAL(disable_kernel_fp)
-	mfmsr	r3
-	rldicl	r0,r3,(63-MSR_FP_LG),1
-	rldicl	r3,r0,(MSR_FP_LG+1),0
-	mtmsrd	r3			/* disable use of fpu now */
-	isync
-	blr
-
 /* kexec_wait(phys_cpu)
  *
  * wait for the flag to change, indicating this kernel is going away but
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index f8f24685f10a..3fc16e3beb9f 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -34,10 +34,10 @@ extern unsigned long __toc_start;
  */
 struct lppaca lppaca[] = {
 	[0 ... (NR_LPPACAS-1)] = {
-		.desc = 0xd397d781,	/* "LpPa" */
-		.size = sizeof(struct lppaca),
+		.desc = cpu_to_be32(0xd397d781),	/* "LpPa" */
+		.size = cpu_to_be16(sizeof(struct lppaca)),
 		.fpregs_in_use = 1,
-		.slb_count = 64,
+		.slb_count = cpu_to_be16(64),
 		.vmxregs_in_use = 0,
 		.page_ins = 0,
 	},
@@ -101,8 +101,8 @@ static inline void free_lppacas(void) { }
  */
 struct slb_shadow slb_shadow[] __cacheline_aligned = {
 	[0 ... (NR_CPUS-1)] = {
-		.persistent = SLB_NUM_BOLTED,
-		.buffer_length = sizeof(struct slb_shadow),
+		.persistent = cpu_to_be32(SLB_NUM_BOLTED),
+		.buffer_length = cpu_to_be32(sizeof(struct slb_shadow)),
 	},
 };
 
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 2b4a9a4db7d9..905a24bb7acc 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -306,7 +306,7 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
 	unsigned long io_offset = 0;
 	int i, res_bit;
 
-	if (hose == 0)
+	if (hose == NULL)
 		return NULL;		/* should never happen */
 
 	/* If memory, add on the PCI bridge address offset */
@@ -667,7 +667,7 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
 void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 				  struct device_node *dev, int primary)
 {
-	const u32 *ranges;
+	const __be32 *ranges;
 	int rlen;
 	int pna = of_n_addr_cells(dev);
 	int np = pna + 5;
@@ -687,7 +687,7 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 	/* Parse it */
 	while ((rlen -= np * 4) >= 0) {
 		/* Read next ranges element */
-		pci_space = ranges[0];
+		pci_space = of_read_number(ranges, 1);
 		pci_addr = of_read_number(ranges + 1, 2);
 		cpu_addr = of_translate_address(dev, ranges + 3);
 		size = of_read_number(ranges + pna + 3, 2);
@@ -704,7 +704,7 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 		/* Now consume following elements while they are contiguous */
 		for (; rlen >= np * sizeof(u32);
 		     ranges += np, rlen -= np * 4) {
-			if (ranges[0] != pci_space)
+			if (of_read_number(ranges, 1) != pci_space)
 				break;
 			pci_next = of_read_number(ranges + 1, 2);
 			cpu_next = of_translate_address(dev, ranges + 3);
@@ -1055,8 +1055,7 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 	 * bases. This is -not- called when generating the PCI tree from
 	 * the OF device-tree.
 	 */
-	if (bus->self != NULL)
-		pci_read_bridge_bases(bus);
+	pci_read_bridge_bases(bus);
 
 	/* Now fixup the bus bus */
 	pcibios_setup_bus_self(bus);
@@ -1578,7 +1577,7 @@ fake_pci_bus(struct pci_controller *hose, int busnr)
 {
 	static struct pci_bus bus;
 
-	if (hose == 0) {
+	if (hose == NULL) {
 		printk(KERN_ERR "Can't find hose for PCI bus %d!\n", busnr);
 	}
 	bus.number = busnr;
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 2e8629654ca8..a9e311f7a9dd 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -109,7 +109,7 @@ int pcibios_unmap_io_space(struct pci_bus *bus)
 	hose = pci_bus_to_host(bus);
 
 	/* Check if we have IOs allocated */
-	if (hose->io_base_alloc == 0)
+	if (hose->io_base_alloc == NULL)
 		return 0;
 
 	pr_debug("IO unmapping for PHB %s\n", hose->dn->full_name);
@@ -272,7 +272,7 @@ static void quirk_radeon_32bit_msi(struct pci_dev *dev)
 	struct pci_dn *pdn = pci_get_pdn(dev);
 
 	if (pdn)
-		pdn->force_32bit_msi = 1;
+		pdn->force_32bit_msi = true;
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x68f2, quirk_radeon_32bit_msi);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0xaa68, quirk_radeon_32bit_msi);
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index df038442548a..1f61fab59d9b 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -47,9 +47,8 @@ struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
 void *update_dn_pci_info(struct device_node *dn, void *data)
 {
 	struct pci_controller *phb = data;
-	const int *type =
-		of_get_property(dn, "ibm,pci-config-space-type", NULL);
-	const u32 *regs;
+	const __be32 *type = of_get_property(dn, "ibm,pci-config-space-type", NULL);
+	const __be32 *regs;
 	struct pci_dn *pdn;
 
 	pdn = zalloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL);
@@ -63,12 +62,14 @@ void *update_dn_pci_info(struct device_node *dn, void *data)
 #endif
 	regs = of_get_property(dn, "reg", NULL);
 	if (regs) {
+		u32 addr = of_read_number(regs, 1);
+
 		/* First register entry is addr (00BBSS00)  */
-		pdn->busno = (regs[0] >> 16) & 0xff;
-		pdn->devfn = (regs[0] >> 8) & 0xff;
+		pdn->busno = (addr >> 16) & 0xff;
+		pdn->devfn = (addr >> 8) & 0xff;
 	}
 
-	pdn->pci_ext_config_space = (type && *type == 1);
+	pdn->pci_ext_config_space = (type && of_read_number(type, 1) == 1);
 	return NULL;
 }
 
@@ -98,12 +99,13 @@ void *traverse_pci_devices(struct device_node *start, traverse_func pre,
 
 	/* We started with a phb, iterate all childs */
 	for (dn = start->child; dn; dn = nextdn) {
-		const u32 *classp;
-		u32 class;
+		const __be32 *classp;
+		u32 class = 0;
 
 		nextdn = NULL;
 		classp = of_get_property(dn, "class-code", NULL);
-		class = classp ? *classp : 0;
+		if (classp)
+			class = of_read_number(classp, 1);
 
 		if (pre && ((ret = pre(dn, data)) != NULL))
 			return ret;
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 15d9105323bf..4368ec6fdc8c 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -24,12 +24,12 @@
  */
 static u32 get_int_prop(struct device_node *np, const char *name, u32 def)
 {
-	const u32 *prop;
+	const __be32 *prop;
 	int len;
 
 	prop = of_get_property(np, name, &len);
 	if (prop && len >= 4)
-		return *prop;
+		return of_read_number(prop, 1);
 	return def;
 }
 
@@ -77,7 +77,7 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev)
 	unsigned int flags;
 	struct pci_bus_region region;
 	struct resource *res;
-	const u32 *addrs;
+	const __be32 *addrs;
 	u32 i;
 	int proplen;
 
@@ -86,14 +86,14 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev)
 		return;
 	pr_debug("    parse addresses (%d bytes) @ %p\n", proplen, addrs);
 	for (; proplen >= 20; proplen -= 20, addrs += 5) {
-		flags = pci_parse_of_flags(addrs[0], 0);
+		flags = pci_parse_of_flags(of_read_number(addrs, 1), 0);
 		if (!flags)
 			continue;
 		base = of_read_number(&addrs[1], 2);
 		size = of_read_number(&addrs[3], 2);
 		if (!size)
 			continue;
-		i = addrs[0] & 0xff;
+		i = of_read_number(addrs, 1) & 0xff;
 		pr_debug("  base: %llx, size: %llx, i: %x\n",
 			 (unsigned long long)base,
 			 (unsigned long long)size, i);
@@ -207,7 +207,7 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 {
 	struct device_node *node = dev->dev.of_node;
 	struct pci_bus *bus;
-	const u32 *busrange, *ranges;
+	const __be32 *busrange, *ranges;
 	int len, i, mode;
 	struct pci_bus_region region;
 	struct resource *res;
@@ -230,9 +230,11 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 		return;
 	}
 
-	bus = pci_find_bus(pci_domain_nr(dev->bus), busrange[0]);
+	bus = pci_find_bus(pci_domain_nr(dev->bus),
+			   of_read_number(busrange, 1));
 	if (!bus) {
-		bus = pci_add_new_bus(dev->bus, dev, busrange[0]);
+		bus = pci_add_new_bus(dev->bus, dev,
+				      of_read_number(busrange, 1));
 		if (!bus) {
 			printk(KERN_ERR "Failed to create pci bus for %s\n",
 			       node->full_name);
@@ -241,7 +243,8 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 	}
 
 	bus->primary = dev->bus->number;
-	pci_bus_insert_busn_res(bus, busrange[0], busrange[1]);
+	pci_bus_insert_busn_res(bus, of_read_number(busrange, 1),
+				of_read_number(busrange+1, 1));
 	bus->bridge_ctl = 0;
 
 	/* parse ranges property */
@@ -254,7 +257,7 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 	}
 	i = 1;
 	for (; len >= 32; len -= 32, ranges += 8) {
-		flags = pci_parse_of_flags(ranges[0], 1);
+		flags = pci_parse_of_flags(of_read_number(ranges, 1), 1);
 		size = of_read_number(&ranges[6], 2);
 		if (flags == 0 || size == 0)
 			continue;
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index c29666586998..21646dbe1bb3 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -96,7 +96,9 @@ EXPORT_SYMBOL(pci_dram_offset);
 
 EXPORT_SYMBOL(start_thread);
 
+#ifdef CONFIG_PPC_FPU
 EXPORT_SYMBOL(giveup_fpu);
+#endif
 #ifdef CONFIG_ALTIVEC
 EXPORT_SYMBOL(giveup_altivec);
 #endif /* CONFIG_ALTIVEC */
@@ -111,7 +113,6 @@ EXPORT_SYMBOL(giveup_spe);
 #ifndef CONFIG_PPC64
 EXPORT_SYMBOL(flush_instruction_cache);
 #endif
-EXPORT_SYMBOL(__flush_icache_range);
 EXPORT_SYMBOL(flush_dcache_range);
 
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 8083be20fe5e..6f428da53e20 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -74,6 +74,7 @@ struct task_struct *last_task_used_vsx = NULL;
 struct task_struct *last_task_used_spe = NULL;
 #endif
 
+#ifdef CONFIG_PPC_FPU
 /*
  * Make sure the floating-point register state in the
  * the thread_struct is up to date for task tsk.
@@ -107,6 +108,7 @@ void flush_fp_to_thread(struct task_struct *tsk)
 	}
 }
 EXPORT_SYMBOL_GPL(flush_fp_to_thread);
+#endif
 
 void enable_kernel_fp(void)
 {
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 1c14cd4a5e05..6bfcab97c981 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -215,16 +215,16 @@ static void __init check_cpu_pa_features(unsigned long node)
 #ifdef CONFIG_PPC_STD_MMU_64
 static void __init check_cpu_slb_size(unsigned long node)
 {
-	u32 *slb_size_ptr;
+	__be32 *slb_size_ptr;
 
 	slb_size_ptr = of_get_flat_dt_prop(node, "slb-size", NULL);
 	if (slb_size_ptr != NULL) {
-		mmu_slb_size = *slb_size_ptr;
+		mmu_slb_size = be32_to_cpup(slb_size_ptr);
 		return;
 	}
 	slb_size_ptr = of_get_flat_dt_prop(node, "ibm,slb-size", NULL);
 	if (slb_size_ptr != NULL) {
-		mmu_slb_size = *slb_size_ptr;
+		mmu_slb_size = be32_to_cpup(slb_size_ptr);
 	}
 }
 #else
@@ -279,11 +279,11 @@ static void __init check_cpu_feature_properties(unsigned long node)
 {
 	unsigned long i;
 	struct feature_property *fp = feature_properties;
-	const u32 *prop;
+	const __be32 *prop;
 
 	for (i = 0; i < ARRAY_SIZE(feature_properties); ++i, ++fp) {
 		prop = of_get_flat_dt_prop(node, fp->name, NULL);
-		if (prop && *prop >= fp->min_value) {
+		if (prop && be32_to_cpup(prop) >= fp->min_value) {
 			cur_cpu_spec->cpu_features |= fp->cpu_feature;
 			cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftr;
 		}
@@ -295,8 +295,8 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 					  void *data)
 {
 	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	const u32 *prop;
-	const u32 *intserv;
+	const __be32 *prop;
+	const __be32 *intserv;
 	int i, nthreads;
 	unsigned long len;
 	int found = -1;
@@ -324,8 +324,9 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 		 * version 2 of the kexec param format adds the phys cpuid of
 		 * booted proc.
 		 */
-		if (initial_boot_params->version >= 2) {
-			if (intserv[i] == initial_boot_params->boot_cpuid_phys) {
+		if (be32_to_cpu(initial_boot_params->version) >= 2) {
+			if (be32_to_cpu(intserv[i]) ==
+			    be32_to_cpu(initial_boot_params->boot_cpuid_phys)) {
 				found = boot_cpu_count;
 				found_thread = i;
 			}
@@ -347,9 +348,10 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 
 	if (found >= 0) {
 		DBG("boot cpu: logical %d physical %d\n", found,
-			intserv[found_thread]);
+			be32_to_cpu(intserv[found_thread]));
 		boot_cpuid = found;
-		set_hard_smp_processor_id(found, intserv[found_thread]);
+		set_hard_smp_processor_id(found,
+			be32_to_cpu(intserv[found_thread]));
 
 		/*
 		 * PAPR defines "logical" PVR values for cpus that
@@ -366,8 +368,8 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 		 * it uses 0x0f000001.
 		 */
 		prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
-		if (prop && (*prop & 0xff000000) == 0x0f000000)
-			identify_cpu(0, *prop);
+		if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000)
+			identify_cpu(0, be32_to_cpup(prop));
 
 		identical_pvr_fixup(node);
 	}
@@ -389,7 +391,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 int __init early_init_dt_scan_chosen_ppc(unsigned long node, const char *uname,
 					 int depth, void *data)
 {
-	unsigned long *lprop;
+	unsigned long *lprop; /* All these set by kernel, so no need to convert endian */
 
 	/* Use common scan routine to determine if this is the chosen node */
 	if (early_init_dt_scan_chosen(node, uname, depth, data) == 0)
@@ -454,7 +456,7 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 	if (dm == NULL || l < sizeof(__be32))
 		return 0;
 
-	n = *dm++;	/* number of entries */
+	n = of_read_number(dm++, 1);	/* number of entries */
 	if (l < (n * (dt_root_addr_cells + 4) + 1) * sizeof(__be32))
 		return 0;
 
@@ -466,7 +468,7 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 
 	for (; n != 0; --n) {
 		base = dt_mem_next_cell(dt_root_addr_cells, &dm);
-		flags = dm[3];
+		flags = of_read_number(&dm[3], 1);
 		/* skip DRC index, pad, assoc. list index, flags */
 		dm += 4;
 		/* skip this block if the reserved bit is set in flags (0x80)
@@ -591,16 +593,16 @@ static void __init early_reserve_mem_dt(void)
 static void __init early_reserve_mem(void)
 {
 	u64 base, size;
-	u64 *reserve_map;
+	__be64 *reserve_map;
 	unsigned long self_base;
 	unsigned long self_size;
 
-	reserve_map = (u64 *)(((unsigned long)initial_boot_params) +
-					initial_boot_params->off_mem_rsvmap);
+	reserve_map = (__be64 *)(((unsigned long)initial_boot_params) +
+			be32_to_cpu(initial_boot_params->off_mem_rsvmap));
 
 	/* before we do anything, lets reserve the dt blob */
 	self_base = __pa((unsigned long)initial_boot_params);
-	self_size = initial_boot_params->totalsize;
+	self_size = be32_to_cpu(initial_boot_params->totalsize);
 	memblock_reserve(self_base, self_size);
 
 	/* Look for the new "reserved-regions" property in the DT */
@@ -620,15 +622,15 @@ static void __init early_reserve_mem(void)
 	 * Handle the case where we might be booting from an old kexec
 	 * image that setup the mem_rsvmap as pairs of 32-bit values
 	 */
-	if (*reserve_map > 0xffffffffull) {
+	if (be64_to_cpup(reserve_map) > 0xffffffffull) {
 		u32 base_32, size_32;
-		u32 *reserve_map_32 = (u32 *)reserve_map;
+		__be32 *reserve_map_32 = (__be32 *)reserve_map;
 
 		DBG("Found old 32-bit reserve map\n");
 
 		while (1) {
-			base_32 = *(reserve_map_32++);
-			size_32 = *(reserve_map_32++);
+			base_32 = be32_to_cpup(reserve_map_32++);
+			size_32 = be32_to_cpup(reserve_map_32++);
 			if (size_32 == 0)
 				break;
 			/* skip if the reservation is for the blob */
@@ -644,8 +646,8 @@ static void __init early_reserve_mem(void)
 
 	/* Handle the reserve map in the fdt blob if it exists */
 	while (1) {
-		base = *(reserve_map++);
-		size = *(reserve_map++);
+		base = be64_to_cpup(reserve_map++);
+		size = be64_to_cpup(reserve_map++);
 		if (size == 0)
 			break;
 		DBG("reserving: %llx -> %llx\n", base, size);
@@ -795,6 +797,32 @@ struct device_node *of_find_next_cache_node(struct device_node *np)
 	return NULL;
 }
 
+/**
+ * of_get_ibm_chip_id - Returns the IBM "chip-id" of a device
+ * @np: device node of the device
+ *
+ * This looks for a property "ibm,chip-id" in the node or any
+ * of its parents and returns its content, or -1 if it cannot
+ * be found.
+ */
+int of_get_ibm_chip_id(struct device_node *np)
+{
+	of_node_get(np);
+	while(np) {
+		struct device_node *old = np;
+		const __be32 *prop;
+
+		prop = of_get_property(np, "ibm,chip-id", NULL);
+		if (prop) {
+			of_node_put(np);
+			return be32_to_cpup(prop);
+		}
+		np = of_get_parent(np);
+		of_node_put(old);
+	}
+	return -1;
+}
+
 #ifdef CONFIG_PPC_PSERIES
 /*
  * Fix up the uninitialized fields in a new device node:
@@ -878,7 +906,7 @@ static int __init export_flat_device_tree(void)
 	struct dentry *d;
 
 	flat_dt_blob.data = initial_boot_params;
-	flat_dt_blob.size = initial_boot_params->totalsize;
+	flat_dt_blob.size = be32_to_cpu(initial_boot_params->totalsize);
 
 	d = debugfs_create_blob("flat-device-tree", S_IFREG | S_IRUSR,
 				powerpc_debugfs_root, &flat_dt_blob);
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 607902424e73..7b6391b68fb8 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -107,10 +107,10 @@ int of_workarounds;
 typedef u32 prom_arg_t;
 
 struct prom_args {
-        u32 service;
-        u32 nargs;
-        u32 nret;
-        prom_arg_t args[10];
+        __be32 service;
+        __be32 nargs;
+        __be32 nret;
+        __be32 args[10];
 };
 
 struct prom_t {
@@ -123,11 +123,11 @@ struct prom_t {
 };
 
 struct mem_map_entry {
-	u64	base;
-	u64	size;
+	__be64	base;
+	__be64	size;
 };
 
-typedef u32 cell_t;
+typedef __be32 cell_t;
 
 extern void __start(unsigned long r3, unsigned long r4, unsigned long r5,
 		    unsigned long r6, unsigned long r7, unsigned long r8,
@@ -219,13 +219,13 @@ static int __init call_prom(const char *service, int nargs, int nret, ...)
 	struct prom_args args;
 	va_list list;
 
-	args.service = ADDR(service);
-	args.nargs = nargs;
-	args.nret = nret;
+	args.service = cpu_to_be32(ADDR(service));
+	args.nargs = cpu_to_be32(nargs);
+	args.nret = cpu_to_be32(nret);
 
 	va_start(list, nret);
 	for (i = 0; i < nargs; i++)
-		args.args[i] = va_arg(list, prom_arg_t);
+		args.args[i] = cpu_to_be32(va_arg(list, prom_arg_t));
 	va_end(list);
 
 	for (i = 0; i < nret; i++)
@@ -234,7 +234,7 @@ static int __init call_prom(const char *service, int nargs, int nret, ...)
 	if (enter_prom(&args, prom_entry) < 0)
 		return PROM_ERROR;
 
-	return (nret > 0) ? args.args[nargs] : 0;
+	return (nret > 0) ? be32_to_cpu(args.args[nargs]) : 0;
 }
 
 static int __init call_prom_ret(const char *service, int nargs, int nret,
@@ -244,13 +244,13 @@ static int __init call_prom_ret(const char *service, int nargs, int nret,
 	struct prom_args args;
 	va_list list;
 
-	args.service = ADDR(service);
-	args.nargs = nargs;
-	args.nret = nret;
+	args.service = cpu_to_be32(ADDR(service));
+	args.nargs = cpu_to_be32(nargs);
+	args.nret = cpu_to_be32(nret);
 
 	va_start(list, rets);
 	for (i = 0; i < nargs; i++)
-		args.args[i] = va_arg(list, prom_arg_t);
+		args.args[i] = cpu_to_be32(va_arg(list, prom_arg_t));
 	va_end(list);
 
 	for (i = 0; i < nret; i++)
@@ -261,9 +261,9 @@ static int __init call_prom_ret(const char *service, int nargs, int nret,
 
 	if (rets != NULL)
 		for (i = 1; i < nret; ++i)
-			rets[i-1] = args.args[nargs+i];
+			rets[i-1] = be32_to_cpu(args.args[nargs+i]);
 
-	return (nret > 0) ? args.args[nargs] : 0;
+	return (nret > 0) ? be32_to_cpu(args.args[nargs]) : 0;
 }
 
 
@@ -527,7 +527,7 @@ static int __init prom_setprop(phandle node, const char *nodename,
 #define islower(c)	('a' <= (c) && (c) <= 'z')
 #define toupper(c)	(islower(c) ? ((c) - 'a' + 'A') : (c))
 
-unsigned long prom_strtoul(const char *cp, const char **endp)
+static unsigned long prom_strtoul(const char *cp, const char **endp)
 {
 	unsigned long result = 0, base = 10, value;
 
@@ -552,7 +552,7 @@ unsigned long prom_strtoul(const char *cp, const char **endp)
 	return result;
 }
 
-unsigned long prom_memparse(const char *ptr, const char **retptr)
+static unsigned long prom_memparse(const char *ptr, const char **retptr)
 {
 	unsigned long ret = prom_strtoul(ptr, retptr);
 	int shift = 0;
@@ -724,7 +724,8 @@ unsigned char ibm_architecture_vec[] = {
 
 };
 
-/* Old method - ELF header with PT_NOTE sections */
+/* Old method - ELF header with PT_NOTE sections only works on BE */
+#ifdef __BIG_ENDIAN__
 static struct fake_elf {
 	Elf32_Ehdr	elfhdr;
 	Elf32_Phdr	phdr[2];
@@ -810,6 +811,7 @@ static struct fake_elf {
 		}
 	}
 };
+#endif /* __BIG_ENDIAN__ */
 
 static int __init prom_count_smt_threads(void)
 {
@@ -852,9 +854,9 @@ static int __init prom_count_smt_threads(void)
 
 static void __init prom_send_capabilities(void)
 {
-	ihandle elfloader, root;
+	ihandle root;
 	prom_arg_t ret;
-	u32 *cores;
+	__be32 *cores;
 
 	root = call_prom("open", 1, 1, ADDR("/"));
 	if (root != 0) {
@@ -864,15 +866,15 @@ static void __init prom_send_capabilities(void)
 		 * (we assume this is the same for all cores) and use it to
 		 * divide NR_CPUS.
 		 */
-		cores = (u32 *)&ibm_architecture_vec[IBM_ARCH_VEC_NRCORES_OFFSET];
-		if (*cores != NR_CPUS) {
+		cores = (__be32 *)&ibm_architecture_vec[IBM_ARCH_VEC_NRCORES_OFFSET];
+		if (be32_to_cpup(cores) != NR_CPUS) {
 			prom_printf("WARNING ! "
 				    "ibm_architecture_vec structure inconsistent: %lu!\n",
-				    *cores);
+				    be32_to_cpup(cores));
 		} else {
-			*cores = DIV_ROUND_UP(NR_CPUS, prom_count_smt_threads());
+			*cores = cpu_to_be32(DIV_ROUND_UP(NR_CPUS, prom_count_smt_threads()));
 			prom_printf("Max number of cores passed to firmware: %lu (NR_CPUS = %lu)\n",
-				    *cores, NR_CPUS);
+				    be32_to_cpup(cores), NR_CPUS);
 		}
 
 		/* try calling the ibm,client-architecture-support method */
@@ -893,17 +895,24 @@ static void __init prom_send_capabilities(void)
 		prom_printf(" not implemented\n");
 	}
 
-	/* no ibm,client-architecture-support call, try the old way */
-	elfloader = call_prom("open", 1, 1, ADDR("/packages/elf-loader"));
-	if (elfloader == 0) {
-		prom_printf("couldn't open /packages/elf-loader\n");
-		return;
+#ifdef __BIG_ENDIAN__
+	{
+		ihandle elfloader;
+
+		/* no ibm,client-architecture-support call, try the old way */
+		elfloader = call_prom("open", 1, 1,
+				      ADDR("/packages/elf-loader"));
+		if (elfloader == 0) {
+			prom_printf("couldn't open /packages/elf-loader\n");
+			return;
+		}
+		call_prom("call-method", 3, 1, ADDR("process-elf-header"),
+			  elfloader, ADDR(&fake_elf));
+		call_prom("close", 1, 0, elfloader);
 	}
-	call_prom("call-method", 3, 1, ADDR("process-elf-header"),
-			elfloader, ADDR(&fake_elf));
-	call_prom("close", 1, 0, elfloader);
+#endif /* __BIG_ENDIAN__ */
 }
-#endif
+#endif /* #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */
 
 /*
  * Memory allocation strategy... our layout is normally:
@@ -1050,11 +1059,11 @@ static unsigned long __init prom_next_cell(int s, cell_t **cellp)
 		p++;
 		s--;
 	}
-	r = *p++;
+	r = be32_to_cpu(*p++);
 #ifdef CONFIG_PPC64
 	if (s > 1) {
 		r <<= 32;
-		r |= *(p++);
+		r |= be32_to_cpu(*(p++));
 	}
 #endif
 	*cellp = p;
@@ -1087,8 +1096,8 @@ static void __init reserve_mem(u64 base, u64 size)
 
 	if (cnt >= (MEM_RESERVE_MAP_SIZE - 1))
 		prom_panic("Memory reserve map exhausted !\n");
-	mem_reserve_map[cnt].base = base;
-	mem_reserve_map[cnt].size = size;
+	mem_reserve_map[cnt].base = cpu_to_be64(base);
+	mem_reserve_map[cnt].size = cpu_to_be64(size);
 	mem_reserve_cnt = cnt + 1;
 }
 
@@ -1102,6 +1111,7 @@ static void __init prom_init_mem(void)
 	char *path, type[64];
 	unsigned int plen;
 	cell_t *p, *endp;
+	__be32 val;
 	u32 rac, rsc;
 
 	/*
@@ -1109,12 +1119,14 @@ static void __init prom_init_mem(void)
 	 * 1) top of RMO (first node)
 	 * 2) top of memory
 	 */
-	rac = 2;
-	prom_getprop(prom.root, "#address-cells", &rac, sizeof(rac));
-	rsc = 1;
-	prom_getprop(prom.root, "#size-cells", &rsc, sizeof(rsc));
-	prom_debug("root_addr_cells: %x\n", (unsigned long) rac);
-	prom_debug("root_size_cells: %x\n", (unsigned long) rsc);
+	val = cpu_to_be32(2);
+	prom_getprop(prom.root, "#address-cells", &val, sizeof(val));
+	rac = be32_to_cpu(val);
+	val = cpu_to_be32(1);
+	prom_getprop(prom.root, "#size-cells", &val, sizeof(rsc));
+	rsc = be32_to_cpu(val);
+	prom_debug("root_addr_cells: %x\n", rac);
+	prom_debug("root_size_cells: %x\n", rsc);
 
 	prom_debug("scanning memory:\n");
 	path = prom_scratch;
@@ -1222,25 +1234,23 @@ static void __init prom_init_mem(void)
 
 static void __init prom_close_stdin(void)
 {
-	ihandle val;
+	__be32 val;
+	ihandle stdin;
 
-	if (prom_getprop(prom.chosen, "stdin", &val, sizeof(val)) > 0)
-		call_prom("close", 1, 0, val);
+	if (prom_getprop(prom.chosen, "stdin", &val, sizeof(val)) > 0) {
+		stdin = be32_to_cpu(val);
+		call_prom("close", 1, 0, stdin);
+	}
 }
 
 #ifdef CONFIG_PPC_POWERNV
 
-static u64 __initdata prom_opal_size;
-static u64 __initdata prom_opal_align;
-static int __initdata prom_rtas_start_cpu;
-static u64 __initdata prom_rtas_data;
-static u64 __initdata prom_rtas_entry;
-
 #ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
 static u64 __initdata prom_opal_base;
 static u64 __initdata prom_opal_entry;
 #endif
 
+#ifdef __BIG_ENDIAN__
 /* XXX Don't change this structure without updating opal-takeover.S */
 static struct opal_secondary_data {
 	s64				ack;	/*  0 */
@@ -1248,6 +1258,12 @@ static struct opal_secondary_data {
 	struct opal_takeover_args	args;	/* 16 */
 } opal_secondary_data;
 
+static u64 __initdata prom_opal_align;
+static u64 __initdata prom_opal_size;
+static int __initdata prom_rtas_start_cpu;
+static u64 __initdata prom_rtas_data;
+static u64 __initdata prom_rtas_entry;
+
 extern char opal_secondary_entry;
 
 static void __init prom_query_opal(void)
@@ -1265,6 +1281,7 @@ static void __init prom_query_opal(void)
 	}
 
 	prom_printf("Querying for OPAL presence... ");
+
 	rc = opal_query_takeover(&prom_opal_size,
 				 &prom_opal_align);
 	prom_debug("(rc = %ld) ", rc);
@@ -1425,6 +1442,7 @@ static void __init prom_opal_takeover(void)
 	for (;;)
 		opal_do_takeover(args);
 }
+#endif /* __BIG_ENDIAN__ */
 
 /*
  * Allocate room for and instantiate OPAL
@@ -1435,6 +1453,7 @@ static void __init prom_instantiate_opal(void)
 	ihandle opal_inst;
 	u64 base, entry;
 	u64 size = 0, align = 0x10000;
+	__be64 val64;
 	u32 rets[2];
 
 	prom_debug("prom_instantiate_opal: start...\n");
@@ -1444,11 +1463,14 @@ static void __init prom_instantiate_opal(void)
 	if (!PHANDLE_VALID(opal_node))
 		return;
 
-	prom_getprop(opal_node, "opal-runtime-size", &size, sizeof(size));
+	val64 = 0;
+	prom_getprop(opal_node, "opal-runtime-size", &val64, sizeof(val64));
+	size = be64_to_cpu(val64);
 	if (size == 0)
 		return;
-	prom_getprop(opal_node, "opal-runtime-alignment", &align,
-		     sizeof(align));
+	val64 = 0;
+	prom_getprop(opal_node, "opal-runtime-alignment", &val64,sizeof(val64));
+	align = be64_to_cpu(val64);
 
 	base = alloc_down(size, align, 0);
 	if (base == 0) {
@@ -1505,6 +1527,7 @@ static void __init prom_instantiate_rtas(void)
 	phandle rtas_node;
 	ihandle rtas_inst;
 	u32 base, entry = 0;
+	__be32 val;
 	u32 size = 0;
 
 	prom_debug("prom_instantiate_rtas: start...\n");
@@ -1514,7 +1537,9 @@ static void __init prom_instantiate_rtas(void)
 	if (!PHANDLE_VALID(rtas_node))
 		return;
 
-	prom_getprop(rtas_node, "rtas-size", &size, sizeof(size));
+	val = 0;
+	prom_getprop(rtas_node, "rtas-size", &val, sizeof(size));
+	size = be32_to_cpu(val);
 	if (size == 0)
 		return;
 
@@ -1541,12 +1566,14 @@ static void __init prom_instantiate_rtas(void)
 
 	reserve_mem(base, size);
 
+	val = cpu_to_be32(base);
 	prom_setprop(rtas_node, "/rtas", "linux,rtas-base",
-		     &base, sizeof(base));
+		     &val, sizeof(val));
+	val = cpu_to_be32(entry);
 	prom_setprop(rtas_node, "/rtas", "linux,rtas-entry",
-		     &entry, sizeof(entry));
+		     &val, sizeof(val));
 
-#ifdef CONFIG_PPC_POWERNV
+#if defined(CONFIG_PPC_POWERNV) && defined(__BIG_ENDIAN__)
 	/* PowerVN takeover hack */
 	prom_rtas_data = base;
 	prom_rtas_entry = entry;
@@ -1620,6 +1647,7 @@ static void __init prom_instantiate_sml(void)
 /*
  * Allocate room for and initialize TCE tables
  */
+#ifdef __BIG_ENDIAN__
 static void __init prom_initialize_tce_table(void)
 {
 	phandle node;
@@ -1748,7 +1776,8 @@ static void __init prom_initialize_tce_table(void)
 	/* Flag the first invalid entry */
 	prom_debug("ending prom_initialize_tce_table\n");
 }
-#endif
+#endif /* __BIG_ENDIAN__ */
+#endif /* CONFIG_PPC64 */
 
 /*
  * With CHRP SMP we need to use the OF to start the other processors.
@@ -1777,7 +1806,6 @@ static void __init prom_initialize_tce_table(void)
 static void __init prom_hold_cpus(void)
 {
 	unsigned long i;
-	unsigned int reg;
 	phandle node;
 	char type[64];
 	unsigned long *spinloop
@@ -1803,6 +1831,9 @@ static void __init prom_hold_cpus(void)
 
 	/* look for cpus */
 	for (node = 0; prom_next_node(&node); ) {
+		unsigned int cpu_no;
+		__be32 reg;
+
 		type[0] = 0;
 		prom_getprop(node, "device_type", type, sizeof(type));
 		if (strcmp(type, "cpu") != 0)
@@ -1813,10 +1844,11 @@ static void __init prom_hold_cpus(void)
 			if (strcmp(type, "okay") != 0)
 				continue;
 
-		reg = -1;
+		reg = cpu_to_be32(-1); /* make sparse happy */
 		prom_getprop(node, "reg", &reg, sizeof(reg));
+		cpu_no = be32_to_cpu(reg);
 
-		prom_debug("cpu hw idx   = %lu\n", reg);
+		prom_debug("cpu hw idx   = %lu\n", cpu_no);
 
 		/* Init the acknowledge var which will be reset by
 		 * the secondary cpu when it awakens from its OF
@@ -1824,24 +1856,24 @@ static void __init prom_hold_cpus(void)
 		 */
 		*acknowledge = (unsigned long)-1;
 
-		if (reg != prom.cpu) {
+		if (cpu_no != prom.cpu) {
 			/* Primary Thread of non-boot cpu or any thread */
-			prom_printf("starting cpu hw idx %lu... ", reg);
+			prom_printf("starting cpu hw idx %lu... ", cpu_no);
 			call_prom("start-cpu", 3, 0, node,
-				  secondary_hold, reg);
+				  secondary_hold, cpu_no);
 
 			for (i = 0; (i < 100000000) && 
 			     (*acknowledge == ((unsigned long)-1)); i++ )
 				mb();
 
-			if (*acknowledge == reg)
+			if (*acknowledge == cpu_no)
 				prom_printf("done\n");
 			else
 				prom_printf("failed: %x\n", *acknowledge);
 		}
 #ifdef CONFIG_SMP
 		else
-			prom_printf("boot cpu hw idx %lu\n", reg);
+			prom_printf("boot cpu hw idx %lu\n", cpu_no);
 #endif /* CONFIG_SMP */
 	}
 
@@ -1895,6 +1927,7 @@ static void __init prom_find_mmu(void)
 	prom.memory = call_prom("open", 1, 1, ADDR("/memory"));
 	prom_getprop(prom.chosen, "mmu", &prom.mmumap,
 		     sizeof(prom.mmumap));
+	prom.mmumap = be32_to_cpu(prom.mmumap);
 	if (!IHANDLE_VALID(prom.memory) || !IHANDLE_VALID(prom.mmumap))
 		of_workarounds &= ~OF_WA_CLAIM;		/* hmmm */
 }
@@ -1906,17 +1939,19 @@ static void __init prom_init_stdout(void)
 {
 	char *path = of_stdout_device;
 	char type[16];
-	u32 val;
+	phandle stdout_node;
+	__be32 val;
 
 	if (prom_getprop(prom.chosen, "stdout", &val, sizeof(val)) <= 0)
 		prom_panic("cannot find stdout");
 
-	prom.stdout = val;
+	prom.stdout = be32_to_cpu(val);
 
 	/* Get the full OF pathname of the stdout device */
 	memset(path, 0, 256);
 	call_prom("instance-to-path", 3, 1, prom.stdout, path, 255);
-	val = call_prom("instance-to-package", 1, 1, prom.stdout);
+	stdout_node = call_prom("instance-to-package", 1, 1, prom.stdout);
+	val = cpu_to_be32(stdout_node);
 	prom_setprop(prom.chosen, "/chosen", "linux,stdout-package",
 		     &val, sizeof(val));
 	prom_printf("OF stdout device is: %s\n", of_stdout_device);
@@ -1925,9 +1960,9 @@ static void __init prom_init_stdout(void)
 
 	/* If it's a display, note it */
 	memset(type, 0, sizeof(type));
-	prom_getprop(val, "device_type", type, sizeof(type));
+	prom_getprop(stdout_node, "device_type", type, sizeof(type));
 	if (strcmp(type, "display") == 0)
-		prom_setprop(val, path, "linux,boot-display", NULL, 0);
+		prom_setprop(stdout_node, path, "linux,boot-display", NULL, 0);
 }
 
 static int __init prom_find_machine_type(void)
@@ -2082,6 +2117,22 @@ static void __init prom_check_displays(void)
 					   clut[2]) != 0)
 				break;
 #endif /* CONFIG_LOGO_LINUX_CLUT224 */
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX
+		if (prom_getprop(node, "linux,boot-display", NULL, 0) !=
+		    PROM_ERROR) {
+			u32 width, height, pitch, addr;
+
+			prom_printf("Setting btext !\n");
+			prom_getprop(node, "width", &width, 4);
+			prom_getprop(node, "height", &height, 4);
+			prom_getprop(node, "linebytes", &pitch, 4);
+			prom_getprop(node, "address", &addr, 4);
+			prom_printf("W=%d H=%d LB=%d addr=0x%x\n",
+				    width, height, pitch, addr);
+			btext_setup_display(width, height, 8, pitch, addr);
+		}
+#endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */
 	}
 }
 
@@ -2117,8 +2168,10 @@ static void __init *make_room(unsigned long *mem_start, unsigned long *mem_end,
 	return ret;
 }
 
-#define dt_push_token(token, mem_start, mem_end) \
-	do { *((u32 *)make_room(mem_start, mem_end, 4, 4)) = token; } while(0)
+#define dt_push_token(token, mem_start, mem_end) do { 			\
+		void *room = make_room(mem_start, mem_end, 4, 4);	\
+		*(__be32 *)room = cpu_to_be32(token);			\
+	} while(0)
 
 static unsigned long __init dt_find_string(char *str)
 {
@@ -2291,7 +2344,7 @@ static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start,
 			dt_push_token(4, mem_start, mem_end);
 			dt_push_token(soff, mem_start, mem_end);
 			valp = make_room(mem_start, mem_end, 4, 4);
-			*(u32 *)valp = node;
+			*(__be32 *)valp = cpu_to_be32(node);
 		}
 	}
 
@@ -2364,16 +2417,16 @@ static void __init flatten_device_tree(void)
 	dt_struct_end = PAGE_ALIGN(mem_start);
 
 	/* Finish header */
-	hdr->boot_cpuid_phys = prom.cpu;
-	hdr->magic = OF_DT_HEADER;
-	hdr->totalsize = dt_struct_end - dt_header_start;
-	hdr->off_dt_struct = dt_struct_start - dt_header_start;
-	hdr->off_dt_strings = dt_string_start - dt_header_start;
-	hdr->dt_strings_size = dt_string_end - dt_string_start;
-	hdr->off_mem_rsvmap = ((unsigned long)rsvmap) - dt_header_start;
-	hdr->version = OF_DT_VERSION;
+	hdr->boot_cpuid_phys = cpu_to_be32(prom.cpu);
+	hdr->magic = cpu_to_be32(OF_DT_HEADER);
+	hdr->totalsize = cpu_to_be32(dt_struct_end - dt_header_start);
+	hdr->off_dt_struct = cpu_to_be32(dt_struct_start - dt_header_start);
+	hdr->off_dt_strings = cpu_to_be32(dt_string_start - dt_header_start);
+	hdr->dt_strings_size = cpu_to_be32(dt_string_end - dt_string_start);
+	hdr->off_mem_rsvmap = cpu_to_be32(((unsigned long)rsvmap) - dt_header_start);
+	hdr->version = cpu_to_be32(OF_DT_VERSION);
 	/* Version 16 is not backward compatible */
-	hdr->last_comp_version = 0x10;
+	hdr->last_comp_version = cpu_to_be32(0x10);
 
 	/* Copy the reserve map in */
 	memcpy(rsvmap, mem_reserve_map, sizeof(mem_reserve_map));
@@ -2384,8 +2437,8 @@ static void __init flatten_device_tree(void)
 		prom_printf("reserved memory map:\n");
 		for (i = 0; i < mem_reserve_cnt; i++)
 			prom_printf("  %x - %x\n",
-				    mem_reserve_map[i].base,
-				    mem_reserve_map[i].size);
+				    be64_to_cpu(mem_reserve_map[i].base),
+				    be64_to_cpu(mem_reserve_map[i].size));
 	}
 #endif
 	/* Bump mem_reserve_cnt to cause further reservations to fail
@@ -2397,7 +2450,6 @@ static void __init flatten_device_tree(void)
 		    dt_string_start, dt_string_end);
 	prom_printf("Device tree struct  0x%x -> 0x%x\n",
 		    dt_struct_start, dt_struct_end);
-
 }
 
 #ifdef CONFIG_PPC_MAPLE
@@ -2730,18 +2782,19 @@ static void __init fixup_device_tree(void)
 
 static void __init prom_find_boot_cpu(void)
 {
-	u32 getprop_rval;
+	__be32 rval;
 	ihandle prom_cpu;
 	phandle cpu_pkg;
 
-	prom.cpu = 0;
-	if (prom_getprop(prom.chosen, "cpu", &prom_cpu, sizeof(prom_cpu)) <= 0)
+	rval = 0;
+	if (prom_getprop(prom.chosen, "cpu", &rval, sizeof(rval)) <= 0)
 		return;
+	prom_cpu = be32_to_cpu(rval);
 
 	cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu);
 
-	prom_getprop(cpu_pkg, "reg", &getprop_rval, sizeof(getprop_rval));
-	prom.cpu = getprop_rval;
+	prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval));
+	prom.cpu = be32_to_cpu(rval);
 
 	prom_debug("Booting CPU hw index = %lu\n", prom.cpu);
 }
@@ -2750,15 +2803,15 @@ static void __init prom_check_initrd(unsigned long r3, unsigned long r4)
 {
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (r3 && r4 && r4 != 0xdeadbeef) {
-		unsigned long val;
+		__be64 val;
 
 		prom_initrd_start = is_kernel_addr(r3) ? __pa(r3) : r3;
 		prom_initrd_end = prom_initrd_start + r4;
 
-		val = prom_initrd_start;
+		val = cpu_to_be64(prom_initrd_start);
 		prom_setprop(prom.chosen, "/chosen", "linux,initrd-start",
 			     &val, sizeof(val));
-		val = prom_initrd_end;
+		val = cpu_to_be64(prom_initrd_end);
 		prom_setprop(prom.chosen, "/chosen", "linux,initrd-end",
 			     &val, sizeof(val));
 
@@ -2915,7 +2968,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 */
 	prom_check_displays();
 
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC64) && defined(__BIG_ENDIAN__)
 	/*
 	 * Initialize IOMMU (TCE tables) on pSeries. Do that before anything else
 	 * that uses the allocator, we need to make sure we get the top of memory
@@ -2934,6 +2987,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 		prom_instantiate_rtas();
 
 #ifdef CONFIG_PPC_POWERNV
+#ifdef __BIG_ENDIAN__
 	/* Detect HAL and try instanciating it & doing takeover */
 	if (of_platform == PLATFORM_PSERIES_LPAR) {
 		prom_query_opal();
@@ -2941,9 +2995,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 			prom_opal_hold_cpus();
 			prom_opal_takeover();
 		}
-	} else if (of_platform == PLATFORM_OPAL)
+	} else
+#endif /* __BIG_ENDIAN__ */
+	if (of_platform == PLATFORM_OPAL)
 		prom_instantiate_opal();
-#endif
+#endif /* CONFIG_PPC_POWERNV */
 
 #ifdef CONFIG_PPC64
 	/* instantiate sml */
@@ -2962,10 +3018,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	/*
 	 * Fill in some infos for use by the kernel later on
 	 */
-	if (prom_memory_limit)
+	if (prom_memory_limit) {
+		__be64 val = cpu_to_be64(prom_memory_limit);
 		prom_setprop(prom.chosen, "/chosen", "linux,memory-limit",
-			     &prom_memory_limit,
-			     sizeof(prom_memory_limit));
+			     &val, sizeof(val));
+	}
 #ifdef CONFIG_PPC64
 	if (prom_iommu_off)
 		prom_setprop(prom.chosen, "/chosen", "linux,iommu-off",
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index 3765da6be4f2..b0c263da219a 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -22,7 +22,8 @@ __secondary_hold_acknowledge __secondary_hold_spinloop __start
 strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224
 reloc_got2 kernstart_addr memstart_addr linux_banner _stext
 opal_query_takeover opal_do_takeover opal_enter_rtas opal_secondary_entry
-boot_command_line __prom_init_toc_start __prom_init_toc_end"
+boot_command_line __prom_init_toc_start __prom_init_toc_end
+btext_setup_display"
 
 NM="$1"
 OBJ="$2"
diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c
index 4e1331b8eb33..6295e646f78c 100644
--- a/arch/powerpc/kernel/prom_parse.c
+++ b/arch/powerpc/kernel/prom_parse.c
@@ -7,28 +7,27 @@
 #include <linux/of_address.h>
 #include <asm/prom.h>
 
-void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
-		unsigned long *busno, unsigned long *phys, unsigned long *size)
+void of_parse_dma_window(struct device_node *dn, const __be32 *dma_window,
+			 unsigned long *busno, unsigned long *phys,
+			 unsigned long *size)
 {
-	const u32 *dma_window;
 	u32 cells;
-	const unsigned char *prop;
-
-	dma_window = dma_window_prop;
+	const __be32 *prop;
 
 	/* busno is always one cell */
-	*busno = *(dma_window++);
+	*busno = of_read_number(dma_window, 1);
+	dma_window++;
 
 	prop = of_get_property(dn, "ibm,#dma-address-cells", NULL);
 	if (!prop)
 		prop = of_get_property(dn, "#address-cells", NULL);
 
-	cells = prop ? *(u32 *)prop : of_n_addr_cells(dn);
+	cells = prop ? of_read_number(prop, 1) : of_n_addr_cells(dn);
 	*phys = of_read_number(dma_window, cells);
 
 	dma_window += cells;
 
 	prop = of_get_property(dn, "ibm,#dma-size-cells", NULL);
-	cells = prop ? *(u32 *)prop : of_n_size_cells(dn);
+	cells = prop ? of_read_number(prop, 1) : of_n_size_cells(dn);
 	*size = of_read_number(dma_window, cells);
 }
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 80b5ef403f68..4cf674d7d5ae 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -91,7 +91,7 @@ static void unlock_rtas(unsigned long flags)
  * are designed only for very early low-level debugging, which
  * is why the token is hard-coded to 10.
  */
-static void call_rtas_display_status(char c)
+static void call_rtas_display_status(unsigned char c)
 {
 	struct rtas_args *args = &rtas.args;
 	unsigned long s;
@@ -100,11 +100,11 @@ static void call_rtas_display_status(char c)
 		return;
 	s = lock_rtas();
 
-	args->token = 10;
-	args->nargs = 1;
-	args->nret  = 1;
-	args->rets  = (rtas_arg_t *)&(args->args[1]);
-	args->args[0] = (unsigned char)c;
+	args->token = cpu_to_be32(10);
+	args->nargs = cpu_to_be32(1);
+	args->nret  = cpu_to_be32(1);
+	args->rets  = &(args->args[1]);
+	args->args[0] = cpu_to_be32(c);
 
 	enter_rtas(__pa(args));
 
@@ -204,7 +204,7 @@ void rtas_progress(char *s, unsigned short hex)
 {
 	struct device_node *root;
 	int width;
-	const int *p;
+	const __be32 *p;
 	char *os;
 	static int display_character, set_indicator;
 	static int display_width, display_lines, form_feed;
@@ -221,13 +221,13 @@ void rtas_progress(char *s, unsigned short hex)
 		if ((root = of_find_node_by_path("/rtas"))) {
 			if ((p = of_get_property(root,
 					"ibm,display-line-length", NULL)))
-				display_width = *p;
+				display_width = be32_to_cpu(*p);
 			if ((p = of_get_property(root,
 					"ibm,form-feed", NULL)))
-				form_feed = *p;
+				form_feed = be32_to_cpu(*p);
 			if ((p = of_get_property(root,
 					"ibm,display-number-of-lines", NULL)))
-				display_lines = *p;
+				display_lines = be32_to_cpu(*p);
 			row_width = of_get_property(root,
 					"ibm,display-truncation-length", NULL);
 			of_node_put(root);
@@ -322,11 +322,11 @@ EXPORT_SYMBOL(rtas_progress);		/* needed by rtas_flash module */
 
 int rtas_token(const char *service)
 {
-	const int *tokp;
+	const __be32 *tokp;
 	if (rtas.dev == NULL)
 		return RTAS_UNKNOWN_SERVICE;
 	tokp = of_get_property(rtas.dev, service, NULL);
-	return tokp ? *tokp : RTAS_UNKNOWN_SERVICE;
+	return tokp ? be32_to_cpu(*tokp) : RTAS_UNKNOWN_SERVICE;
 }
 EXPORT_SYMBOL(rtas_token);
 
@@ -380,11 +380,11 @@ static char *__fetch_rtas_last_error(char *altbuf)
 
 	bufsz = rtas_get_error_log_max();
 
-	err_args.token = rtas_last_error_token;
-	err_args.nargs = 2;
-	err_args.nret = 1;
-	err_args.args[0] = (rtas_arg_t)__pa(rtas_err_buf);
-	err_args.args[1] = bufsz;
+	err_args.token = cpu_to_be32(rtas_last_error_token);
+	err_args.nargs = cpu_to_be32(2);
+	err_args.nret = cpu_to_be32(1);
+	err_args.args[0] = cpu_to_be32(__pa(rtas_err_buf));
+	err_args.args[1] = cpu_to_be32(bufsz);
 	err_args.args[2] = 0;
 
 	save_args = rtas.args;
@@ -433,13 +433,13 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 	s = lock_rtas();
 	rtas_args = &rtas.args;
 
-	rtas_args->token = token;
-	rtas_args->nargs = nargs;
-	rtas_args->nret  = nret;
-	rtas_args->rets  = (rtas_arg_t *)&(rtas_args->args[nargs]);
+	rtas_args->token = cpu_to_be32(token);
+	rtas_args->nargs = cpu_to_be32(nargs);
+	rtas_args->nret  = cpu_to_be32(nret);
+	rtas_args->rets  = &(rtas_args->args[nargs]);
 	va_start(list, outputs);
 	for (i = 0; i < nargs; ++i)
-		rtas_args->args[i] = va_arg(list, rtas_arg_t);
+		rtas_args->args[i] = cpu_to_be32(va_arg(list, __u32));
 	va_end(list);
 
 	for (i = 0; i < nret; ++i)
@@ -449,13 +449,13 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 
 	/* A -1 return code indicates that the last command couldn't
 	   be completed due to a hardware error. */
-	if (rtas_args->rets[0] == -1)
+	if (be32_to_cpu(rtas_args->rets[0]) == -1)
 		buff_copy = __fetch_rtas_last_error(NULL);
 
 	if (nret > 1 && outputs != NULL)
 		for (i = 0; i < nret-1; ++i)
-			outputs[i] = rtas_args->rets[i+1];
-	ret = (nret > 0)? rtas_args->rets[0]: 0;
+			outputs[i] = be32_to_cpu(rtas_args->rets[i+1]);
+	ret = (nret > 0)? be32_to_cpu(rtas_args->rets[0]): 0;
 
 	unlock_rtas(s);
 
@@ -588,8 +588,8 @@ bool rtas_indicator_present(int token, int *maxindex)
 {
 	int proplen, count, i;
 	const struct indicator_elem {
-		u32 token;
-		u32 maxindex;
+		__be32 token;
+		__be32 maxindex;
 	} *indicators;
 
 	indicators = of_get_property(rtas.dev, "rtas-indicators", &proplen);
@@ -599,10 +599,10 @@ bool rtas_indicator_present(int token, int *maxindex)
 	count = proplen / sizeof(struct indicator_elem);
 
 	for (i = 0; i < count; i++) {
-		if (indicators[i].token != token)
+		if (__be32_to_cpu(indicators[i].token) != token)
 			continue;
 		if (maxindex)
-			*maxindex = indicators[i].maxindex;
+			*maxindex = __be32_to_cpu(indicators[i].maxindex);
 		return true;
 	}
 
@@ -1097,19 +1097,19 @@ void __init rtas_initialize(void)
 	 */
 	rtas.dev = of_find_node_by_name(NULL, "rtas");
 	if (rtas.dev) {
-		const u32 *basep, *entryp, *sizep;
+		const __be32 *basep, *entryp, *sizep;
 
 		basep = of_get_property(rtas.dev, "linux,rtas-base", NULL);
 		sizep = of_get_property(rtas.dev, "rtas-size", NULL);
 		if (basep != NULL && sizep != NULL) {
-			rtas.base = *basep;
-			rtas.size = *sizep;
+			rtas.base = __be32_to_cpu(*basep);
+			rtas.size = __be32_to_cpu(*sizep);
 			entryp = of_get_property(rtas.dev,
 					"linux,rtas-entry", NULL);
 			if (entryp == NULL) /* Ugh */
 				rtas.entry = rtas.base;
 			else
-				rtas.entry = *entryp;
+				rtas.entry = __be32_to_cpu(*entryp);
 		} else
 			rtas.dev = NULL;
 	}
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 63d051f5b7a5..3d261c071fc8 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -436,7 +436,8 @@ void __init smp_setup_cpu_maps(void)
 	DBG("smp_setup_cpu_maps()\n");
 
 	while ((dn = of_find_node_by_type(dn, "cpu")) && cpu < nr_cpu_ids) {
-		const int *intserv;
+		const __be32 *intserv;
+		__be32 cpu_be;
 		int j, len;
 
 		DBG("  * %s...\n", dn->full_name);
@@ -450,15 +451,17 @@ void __init smp_setup_cpu_maps(void)
 		} else {
 			DBG("    no ibm,ppc-interrupt-server#s -> 1 thread\n");
 			intserv = of_get_property(dn, "reg", NULL);
-			if (!intserv)
-				intserv = &cpu;	/* assume logical == phys */
+			if (!intserv) {
+				cpu_be = cpu_to_be32(cpu);
+				intserv = &cpu_be;	/* assume logical == phys */
+			}
 		}
 
 		for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) {
 			DBG("    thread %d -> cpu %d (hard id %d)\n",
-			    j, cpu, intserv[j]);
+			    j, cpu, be32_to_cpu(intserv[j]));
 			set_cpu_present(cpu, true);
-			set_hard_smp_processor_id(cpu, intserv[j]);
+			set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j]));
 			set_cpu_possible(cpu, true);
 			cpu++;
 		}
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index a8f54ecb091f..a4bbcae72578 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -38,6 +38,7 @@
 #include <asm/serial.h>
 #include <asm/udbg.h>
 #include <asm/mmu_context.h>
+#include <asm/epapr_hcalls.h>
 
 #include "setup.h"
 
@@ -128,6 +129,8 @@ notrace void __init machine_init(u64 dt_ptr)
 	/* Do some early initialization based on the flat device tree */
 	early_init_devtree(__va(dt_ptr));
 
+	epapr_paravirt_early_init();
+
 	early_init_mmu();
 
 	probe_machine();
@@ -326,5 +329,4 @@ void __init setup_arch(char **cmdline_p)
 
 	/* Initialize the MMU context management stuff */
 	mmu_context_init();
-
 }
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index fe6a58c9f0b7..278ca93e1f28 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -10,7 +10,7 @@
  *      2 of the License, or (at your option) any later version.
  */
 
-#undef DEBUG
+#define DEBUG
 
 #include <linux/export.h>
 #include <linux/string.h>
@@ -66,6 +66,7 @@
 #include <asm/code-patching.h>
 #include <asm/kvm_ppc.h>
 #include <asm/hugetlb.h>
+#include <asm/epapr_hcalls.h>
 
 #include "setup.h"
 
@@ -215,6 +216,8 @@ void __init early_setup(unsigned long dt_ptr)
 	 */
 	early_init_devtree(__va(dt_ptr));
 
+	epapr_paravirt_early_init();
+
 	/* Now we know the logical id of our boot cpu, setup the paca. */
 	setup_paca(&paca[boot_cpuid]);
 	fixup_boot_paca();
@@ -239,6 +242,18 @@ void __init early_setup(unsigned long dt_ptr)
 	reserve_hugetlb_gpages();
 
 	DBG(" <- early_setup()\n");
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX
+	/*
+	 * This needs to be done *last* (after the above DBG() even)
+	 *
+	 * Right after we return from this function, we turn on the MMU
+	 * which means the real-mode access trick that btext does will
+	 * no longer work, it needs to switch to using a real MMU
+	 * mapping. This call will ensure that it does
+	 */
+	btext_map();
+#endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */
 }
 
 #ifdef CONFIG_SMP
@@ -307,14 +322,14 @@ static void __init initialize_cache_info(void)
 		 * d-cache and i-cache sizes... -Peter
 		 */
 		if (num_cpus == 1) {
-			const u32 *sizep, *lsizep;
+			const __be32 *sizep, *lsizep;
 			u32 size, lsize;
 
 			size = 0;
 			lsize = cur_cpu_spec->dcache_bsize;
 			sizep = of_get_property(np, "d-cache-size", NULL);
 			if (sizep != NULL)
-				size = *sizep;
+				size = be32_to_cpu(*sizep);
 			lsizep = of_get_property(np, "d-cache-block-size",
 						 NULL);
 			/* fallback if block size missing */
@@ -323,8 +338,8 @@ static void __init initialize_cache_info(void)
 							 "d-cache-line-size",
 							 NULL);
 			if (lsizep != NULL)
-				lsize = *lsizep;
-			if (sizep == 0 || lsizep == 0)
+				lsize = be32_to_cpu(*lsizep);
+			if (sizep == NULL || lsizep == NULL)
 				DBG("Argh, can't find dcache properties ! "
 				    "sizep: %p, lsizep: %p\n", sizep, lsizep);
 
@@ -337,7 +352,7 @@ static void __init initialize_cache_info(void)
 			lsize = cur_cpu_spec->icache_bsize;
 			sizep = of_get_property(np, "i-cache-size", NULL);
 			if (sizep != NULL)
-				size = *sizep;
+				size = be32_to_cpu(*sizep);
 			lsizep = of_get_property(np, "i-cache-block-size",
 						 NULL);
 			if (lsizep == NULL)
@@ -345,8 +360,8 @@ static void __init initialize_cache_info(void)
 							 "i-cache-line-size",
 							 NULL);
 			if (lsizep != NULL)
-				lsize = *lsizep;
-			if (sizep == 0 || lsizep == 0)
+				lsize = be32_to_cpu(*lsizep);
+			if (sizep == NULL || lsizep == NULL)
 				DBG("Argh, can't find icache properties ! "
 				    "sizep: %p, lsizep: %p\n", sizep, lsizep);
 
@@ -701,8 +716,7 @@ void __init setup_per_cpu_areas(void)
 #endif
 
 
-#ifdef CONFIG_PPC_INDIRECT_IO
+#if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO)
 struct ppc_pci_io ppc_pci_io;
 EXPORT_SYMBOL(ppc_pci_io);
-#endif /* CONFIG_PPC_INDIRECT_IO */
-
+#endif
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 0f83122e6676..bebdf1a1a540 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -436,7 +436,10 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
 	 * use altivec. Since VSCR only contains 32 bits saved in the least
 	 * significant bits of a vector, we "cheat" and stuff VRSAVE in the
 	 * most significant bits of that same vector. --BenH
+	 * Note that the current VRSAVE value is in the SPR at this point.
 	 */
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		current->thread.vrsave = mfspr(SPRN_VRSAVE);
 	if (__put_user(current->thread.vrsave, (u32 __user *)&frame->mc_vregs[32]))
 		return 1;
 #endif /* CONFIG_ALTIVEC */
@@ -557,6 +560,8 @@ static int save_tm_user_regs(struct pt_regs *regs,
 	 * significant bits of a vector, we "cheat" and stuff VRSAVE in the
 	 * most significant bits of that same vector. --BenH
 	 */
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		current->thread.vrsave = mfspr(SPRN_VRSAVE);
 	if (__put_user(current->thread.vrsave,
 		       (u32 __user *)&frame->mc_vregs[32]))
 		return 1;
@@ -696,6 +701,8 @@ static long restore_user_regs(struct pt_regs *regs,
 	/* Always get VRSAVE back */
 	if (__get_user(current->thread.vrsave, (u32 __user *)&sr->mc_vregs[32]))
 		return 1;
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		mtspr(SPRN_VRSAVE, current->thread.vrsave);
 #endif /* CONFIG_ALTIVEC */
 	if (copy_fpr_from_user(current, &sr->mc_fregs))
 		return 1;
@@ -809,6 +816,8 @@ static long restore_tm_user_regs(struct pt_regs *regs,
 	    __get_user(current->thread.transact_vrsave,
 		       (u32 __user *)&tm_sr->mc_vregs[32]))
 		return 1;
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		mtspr(SPRN_VRSAVE, current->thread.vrsave);
 #endif /* CONFIG_ALTIVEC */
 
 	regs->msr &= ~(MSR_FP | MSR_FE0 | MSR_FE1);
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 887e99d85bc2..f93ec2835a13 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -96,8 +96,6 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 	unsigned long msr = regs->msr;
 	long err = 0;
 
-	flush_fp_to_thread(current);
-
 #ifdef CONFIG_ALTIVEC
 	err |= __put_user(v_regs, &sc->v_regs);
 
@@ -114,6 +112,8 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 	/* We always copy to/from vrsave, it's 0 if we don't have or don't
 	 * use altivec.
 	 */
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		current->thread.vrsave = mfspr(SPRN_VRSAVE);
 	err |= __put_user(current->thread.vrsave, (u32 __user *)&v_regs[33]);
 #else /* CONFIG_ALTIVEC */
 	err |= __put_user(0, &sc->v_regs);
@@ -217,6 +217,8 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 	/* We always copy to/from vrsave, it's 0 if we don't have or don't
 	 * use altivec.
 	 */
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		current->thread.vrsave = mfspr(SPRN_VRSAVE);
 	err |= __put_user(current->thread.vrsave, (u32 __user *)&v_regs[33]);
 	if (msr & MSR_VEC)
 		err |= __put_user(current->thread.transact_vrsave,
@@ -346,16 +348,18 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig,
 	if (v_regs && !access_ok(VERIFY_READ, v_regs, 34 * sizeof(vector128)))
 		return -EFAULT;
 	/* Copy 33 vec registers (vr0..31 and vscr) from the stack */
-	if (v_regs != 0 && (msr & MSR_VEC) != 0)
+	if (v_regs != NULL && (msr & MSR_VEC) != 0)
 		err |= __copy_from_user(current->thread.vr, v_regs,
 					33 * sizeof(vector128));
 	else if (current->thread.used_vr)
 		memset(current->thread.vr, 0, 33 * sizeof(vector128));
 	/* Always get VRSAVE back */
-	if (v_regs != 0)
+	if (v_regs != NULL)
 		err |= __get_user(current->thread.vrsave, (u32 __user *)&v_regs[33]);
 	else
 		current->thread.vrsave = 0;
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		mtspr(SPRN_VRSAVE, current->thread.vrsave);
 #endif /* CONFIG_ALTIVEC */
 	/* restore floating point */
 	err |= copy_fpr_from_user(current, &sc->fp_regs);
@@ -463,7 +467,7 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
 				    tm_v_regs, 34 * sizeof(vector128)))
 		return -EFAULT;
 	/* Copy 33 vec registers (vr0..31 and vscr) from the stack */
-	if (v_regs != 0 && tm_v_regs != 0 && (msr & MSR_VEC) != 0) {
+	if (v_regs != NULL && tm_v_regs != NULL && (msr & MSR_VEC) != 0) {
 		err |= __copy_from_user(current->thread.vr, v_regs,
 					33 * sizeof(vector128));
 		err |= __copy_from_user(current->thread.transact_vr, tm_v_regs,
@@ -474,7 +478,7 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
 		memset(current->thread.transact_vr, 0, 33 * sizeof(vector128));
 	}
 	/* Always get VRSAVE back */
-	if (v_regs != 0 && tm_v_regs != 0) {
+	if (v_regs != NULL && tm_v_regs != NULL) {
 		err |= __get_user(current->thread.vrsave,
 				  (u32 __user *)&v_regs[33]);
 		err |= __get_user(current->thread.transact_vrsave,
@@ -484,6 +488,8 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
 		current->thread.vrsave = 0;
 		current->thread.transact_vrsave = 0;
 	}
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		mtspr(SPRN_VRSAVE, current->thread.vrsave);
 #endif /* CONFIG_ALTIVEC */
 	/* restore floating point */
 	err |= copy_fpr_from_user(current, &sc->fp_regs);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 38b0ba65a735..442d8e23f8f4 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -81,6 +81,28 @@ int smt_enabled_at_boot = 1;
 
 static void (*crash_ipi_function_ptr)(struct pt_regs *) = NULL;
 
+/*
+ * Returns 1 if the specified cpu should be brought up during boot.
+ * Used to inhibit booting threads if they've been disabled or
+ * limited on the command line
+ */
+int smp_generic_cpu_bootable(unsigned int nr)
+{
+	/* Special case - we inhibit secondary thread startup
+	 * during boot if the user requests it.
+	 */
+	if (system_state == SYSTEM_BOOTING && cpu_has_feature(CPU_FTR_SMT)) {
+		if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
+			return 0;
+		if (smt_enabled_at_boot
+		    && cpu_thread_in_core(nr) >= smt_enabled_at_boot)
+			return 0;
+	}
+
+	return 1;
+}
+
+
 #ifdef CONFIG_PPC64
 int smp_generic_kick_cpu(int nr)
 {
@@ -172,7 +194,7 @@ int smp_request_message_ipi(int virq, int msg)
 #endif
 	err = request_irq(virq, smp_ipi_action[msg],
 			  IRQF_PERCPU | IRQF_NO_THREAD | IRQF_NO_SUSPEND,
-			  smp_ipi_name[msg], 0);
+			  smp_ipi_name[msg], NULL);
 	WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n",
 		virq, smp_ipi_name[msg], err);
 
@@ -210,6 +232,12 @@ void smp_muxed_ipi_message_pass(int cpu, int msg)
 	smp_ops->cause_ipi(cpu, info->data);
 }
 
+#ifdef __BIG_ENDIAN__
+#define IPI_MESSAGE(A) (1 << (24 - 8 * (A)))
+#else
+#define IPI_MESSAGE(A) (1 << (8 * (A)))
+#endif
+
 irqreturn_t smp_ipi_demux(void)
 {
 	struct cpu_messages *info = &__get_cpu_var(ipi_message);
@@ -219,19 +247,14 @@ irqreturn_t smp_ipi_demux(void)
 
 	do {
 		all = xchg(&info->messages, 0);
-
-#ifdef __BIG_ENDIAN
-		if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION)))
+		if (all & IPI_MESSAGE(PPC_MSG_CALL_FUNCTION))
 			generic_smp_call_function_interrupt();
-		if (all & (1 << (24 - 8 * PPC_MSG_RESCHEDULE)))
+		if (all & IPI_MESSAGE(PPC_MSG_RESCHEDULE))
 			scheduler_ipi();
-		if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNC_SINGLE)))
+		if (all & IPI_MESSAGE(PPC_MSG_CALL_FUNC_SINGLE))
 			generic_smp_call_function_single_interrupt();
-		if (all & (1 << (24 - 8 * PPC_MSG_DEBUGGER_BREAK)))
+		if (all & IPI_MESSAGE(PPC_MSG_DEBUGGER_BREAK))
 			debug_ipi_action(0, NULL);
-#else
-#error Unsupported ENDIAN
-#endif
 	} while (info->messages);
 
 	return IRQ_HANDLED;
@@ -574,6 +597,21 @@ out:
 	return id;
 }
 
+/* Return the value of the chip-id property corresponding
+ * to the given logical cpu.
+ */
+int cpu_to_chip_id(int cpu)
+{
+	struct device_node *np;
+
+	np = of_get_cpu_node(cpu, NULL);
+	if (!np)
+		return -1;
+
+	of_node_put(np);
+	return of_get_ibm_chip_id(np);
+}
+
 /* Helper routines for cpu to core mapping */
 int cpu_core_index_of_thread(int cpu)
 {
@@ -587,6 +625,33 @@ int cpu_first_thread_of_core(int core)
 }
 EXPORT_SYMBOL_GPL(cpu_first_thread_of_core);
 
+static void traverse_siblings_chip_id(int cpu, bool add, int chipid)
+{
+	const struct cpumask *mask;
+	struct device_node *np;
+	int i, plen;
+	const __be32 *prop;
+
+	mask = add ? cpu_online_mask : cpu_present_mask;
+	for_each_cpu(i, mask) {
+		np = of_get_cpu_node(i, NULL);
+		if (!np)
+			continue;
+		prop = of_get_property(np, "ibm,chip-id", &plen);
+		if (prop && plen == sizeof(int) &&
+		    of_read_number(prop, 1) == chipid) {
+			if (add) {
+				cpumask_set_cpu(cpu, cpu_core_mask(i));
+				cpumask_set_cpu(i, cpu_core_mask(cpu));
+			} else {
+				cpumask_clear_cpu(cpu, cpu_core_mask(i));
+				cpumask_clear_cpu(i, cpu_core_mask(cpu));
+			}
+		}
+		of_node_put(np);
+	}
+}
+
 /* Must be called when no change can occur to cpu_present_mask,
  * i.e. during cpu online or offline.
  */
@@ -609,11 +674,51 @@ static struct device_node *cpu_to_l2cache(int cpu)
 	return cache;
 }
 
+static void traverse_core_siblings(int cpu, bool add)
+{
+	struct device_node *l2_cache, *np;
+	const struct cpumask *mask;
+	int i, chip, plen;
+	const __be32 *prop;
+
+	/* First see if we have ibm,chip-id properties in cpu nodes */
+	np = of_get_cpu_node(cpu, NULL);
+	if (np) {
+		chip = -1;
+		prop = of_get_property(np, "ibm,chip-id", &plen);
+		if (prop && plen == sizeof(int))
+			chip = of_read_number(prop, 1);
+		of_node_put(np);
+		if (chip >= 0) {
+			traverse_siblings_chip_id(cpu, add, chip);
+			return;
+		}
+	}
+
+	l2_cache = cpu_to_l2cache(cpu);
+	mask = add ? cpu_online_mask : cpu_present_mask;
+	for_each_cpu(i, mask) {
+		np = cpu_to_l2cache(i);
+		if (!np)
+			continue;
+		if (np == l2_cache) {
+			if (add) {
+				cpumask_set_cpu(cpu, cpu_core_mask(i));
+				cpumask_set_cpu(i, cpu_core_mask(cpu));
+			} else {
+				cpumask_clear_cpu(cpu, cpu_core_mask(i));
+				cpumask_clear_cpu(i, cpu_core_mask(cpu));
+			}
+		}
+		of_node_put(np);
+	}
+	of_node_put(l2_cache);
+}
+
 /* Activate a secondary processor. */
 void start_secondary(void *unused)
 {
 	unsigned int cpu = smp_processor_id();
-	struct device_node *l2_cache;
 	int i, base;
 
 	atomic_inc(&init_mm.mm_count);
@@ -652,18 +757,7 @@ void start_secondary(void *unused)
 		cpumask_set_cpu(cpu, cpu_core_mask(base + i));
 		cpumask_set_cpu(base + i, cpu_core_mask(cpu));
 	}
-	l2_cache = cpu_to_l2cache(cpu);
-	for_each_online_cpu(i) {
-		struct device_node *np = cpu_to_l2cache(i);
-		if (!np)
-			continue;
-		if (np == l2_cache) {
-			cpumask_set_cpu(cpu, cpu_core_mask(i));
-			cpumask_set_cpu(i, cpu_core_mask(cpu));
-		}
-		of_node_put(np);
-	}
-	of_node_put(l2_cache);
+	traverse_core_siblings(cpu, true);
 
 	smp_wmb();
 	notify_cpu_starting(cpu);
@@ -719,7 +813,6 @@ int arch_sd_sibling_asym_packing(void)
 #ifdef CONFIG_HOTPLUG_CPU
 int __cpu_disable(void)
 {
-	struct device_node *l2_cache;
 	int cpu = smp_processor_id();
 	int base, i;
 	int err;
@@ -739,20 +832,7 @@ int __cpu_disable(void)
 		cpumask_clear_cpu(cpu, cpu_core_mask(base + i));
 		cpumask_clear_cpu(base + i, cpu_core_mask(cpu));
 	}
-
-	l2_cache = cpu_to_l2cache(cpu);
-	for_each_present_cpu(i) {
-		struct device_node *np = cpu_to_l2cache(i);
-		if (!np)
-			continue;
-		if (np == l2_cache) {
-			cpumask_clear_cpu(cpu, cpu_core_mask(i));
-			cpumask_clear_cpu(i, cpu_core_mask(cpu));
-		}
-		of_node_put(np);
-	}
-	of_node_put(l2_cache);
-
+	traverse_core_siblings(cpu, false);
 
 	return 0;
 }
diff --git a/arch/powerpc/kernel/softemu8xx.c b/arch/powerpc/kernel/softemu8xx.c
deleted file mode 100644
index 29b2f81dd709..000000000000
--- a/arch/powerpc/kernel/softemu8xx.c
+++ /dev/null
@@ -1,199 +0,0 @@
-/*
- * Software emulation of some PPC instructions for the 8xx core.
- *
- * Copyright (C) 1998 Dan Malek (dmalek@jlc.net)
- *
- * Software floating emuation for the MPC8xx processor.  I did this mostly
- * because it was easier than trying to get the libraries compiled for
- * software floating point.  The goal is still to get the libraries done,
- * but I lost patience and needed some hacks to at least get init and
- * shells running.  The first problem is the setjmp/longjmp that save
- * and restore the floating point registers.
- *
- * For this emulation, our working registers are found on the register
- * save area.
- */
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
-#include <linux/ptrace.h>
-#include <linux/user.h>
-#include <linux/interrupt.h>
-
-#include <asm/pgtable.h>
-#include <asm/uaccess.h>
-#include <asm/io.h>
-
-/* Eventually we may need a look-up table, but this works for now.
-*/
-#define LFS	48
-#define LFD	50
-#define LFDU	51
-#define STFD	54
-#define STFDU	55
-#define FMR	63
-
-void print_8xx_pte(struct mm_struct *mm, unsigned long addr)
-{
-	pgd_t *pgd;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	printk(" pte @ 0x%8lx: ", addr);
-	pgd = pgd_offset(mm, addr & PAGE_MASK);
-	if (pgd) {
-		pmd = pmd_offset(pud_offset(pgd, addr & PAGE_MASK),
-		                 addr & PAGE_MASK);
-		if (pmd && pmd_present(*pmd)) {
-			pte = pte_offset_kernel(pmd, addr & PAGE_MASK);
-			if (pte) {
-				printk(" (0x%08lx)->(0x%08lx)->0x%08lx\n",
-				        (long)pgd, (long)pte, (long)pte_val(*pte));
-#define pp ((long)pte_val(*pte))
-				printk(" RPN: %05lx PP: %lx SPS: %lx SH: %lx "
-				       "CI: %lx v: %lx\n",
-				       pp>>12,    /* rpn */
-				       (pp>>10)&3, /* pp */
-				       (pp>>3)&1, /* small */
-				       (pp>>2)&1, /* shared */
-				       (pp>>1)&1, /* cache inhibit */
-				       pp&1       /* valid */
-				       );
-#undef pp
-			}
-			else {
-				printk("no pte\n");
-			}
-		}
-		else {
-			printk("no pmd\n");
-		}
-	}
-	else {
-		printk("no pgd\n");
-	}
-}
-
-int get_8xx_pte(struct mm_struct *mm, unsigned long addr)
-{
-	pgd_t *pgd;
-	pmd_t *pmd;
-	pte_t *pte;
-	int retval = 0;
-
-	pgd = pgd_offset(mm, addr & PAGE_MASK);
-	if (pgd) {
-		pmd = pmd_offset(pud_offset(pgd, addr & PAGE_MASK),
-		                 addr & PAGE_MASK);
-		if (pmd && pmd_present(*pmd)) {
-			pte = pte_offset_kernel(pmd, addr & PAGE_MASK);
-			if (pte) {
-				retval = (int)pte_val(*pte);
-			}
-		}
-	}
-	return retval;
-}
-
-/*
- * We return 0 on success, 1 on unimplemented instruction, and EFAULT
- * if a load/store faulted.
- */
-int Soft_emulate_8xx(struct pt_regs *regs)
-{
-	u32 inst, instword;
-	u32 flreg, idxreg, disp;
-	int retval;
-	s16 sdisp;
-	u32 *ea, *ip;
-
-	retval = 0;
-
-	instword = *((u32 *)regs->nip);
-	inst = instword >> 26;
-
-	flreg = (instword >> 21) & 0x1f;
-	idxreg = (instword >> 16) & 0x1f;
-	disp = instword & 0xffff;
-
-	ea = (u32 *)(regs->gpr[idxreg] + disp);
-	ip = (u32 *)&current->thread.TS_FPR(flreg);
-
-	switch ( inst )
-	{
-	case LFD:
-		/* this is a 16 bit quantity that is sign extended
-		 * so use a signed short here -- Cort
-		 */
-		sdisp = (instword & 0xffff);
-		ea = (u32 *)(regs->gpr[idxreg] + sdisp);
-		if (copy_from_user(ip, ea, sizeof(double)))
-			retval = -EFAULT;
-		break;
-
-	case LFDU:
-		if (copy_from_user(ip, ea, sizeof(double)))
-			retval = -EFAULT;
-		else
-			regs->gpr[idxreg] = (u32)ea;
-		break;
-	case LFS:
-		sdisp = (instword & 0xffff);
-		ea = (u32 *)(regs->gpr[idxreg] + sdisp);
-		if (copy_from_user(ip, ea, sizeof(float)))
-			retval = -EFAULT;
-		break;
-	case STFD:
-		/* this is a 16 bit quantity that is sign extended
-		 * so use a signed short here -- Cort
-		 */
-		sdisp = (instword & 0xffff);
-		ea = (u32 *)(regs->gpr[idxreg] + sdisp);
-		if (copy_to_user(ea, ip, sizeof(double)))
-			retval = -EFAULT;
-		break;
-
-	case STFDU:
-		if (copy_to_user(ea, ip, sizeof(double)))
-			retval = -EFAULT;
-		else
-			regs->gpr[idxreg] = (u32)ea;
-		break;
-	case FMR:
-		/* assume this is a fp move -- Cort */
-		memcpy(ip, &current->thread.TS_FPR((instword>>11)&0x1f),
-		       sizeof(double));
-		break;
-	default:
-		retval = 1;
-		printk("Bad emulation %s/%d\n"
-		       " NIP: %08lx instruction: %08x opcode: %x "
-		       "A: %x B: %x C: %x code: %x rc: %x\n",
-		       current->comm,current->pid,
-		       regs->nip,
-		       instword,inst,
-		       (instword>>16)&0x1f,
-		       (instword>>11)&0x1f,
-		       (instword>>6)&0x1f,
-		       (instword>>1)&0x3ff,
-		       instword&1);
-		{
-			int pa;
-			print_8xx_pte(current->mm,regs->nip);
-			pa = get_8xx_pte(current->mm,regs->nip) & PAGE_MASK;
-			pa |= (regs->nip & ~PAGE_MASK);
-			pa = (unsigned long)__va(pa);
-			printk("Kernel VA for NIP %x ", pa);
-			print_8xx_pte(current->mm,pa);
-		}
-	}
-
-	if (retval == 0)
-		regs->nip += 4;
-
-	return retval;
-}
diff --git a/arch/powerpc/kernel/swsusp_asm64.S b/arch/powerpc/kernel/swsusp_asm64.S
index 86ac1d90d02b..22045984835f 100644
--- a/arch/powerpc/kernel/swsusp_asm64.S
+++ b/arch/powerpc/kernel/swsusp_asm64.S
@@ -46,10 +46,19 @@
 #define SL_r29		0xe8
 #define SL_r30		0xf0
 #define SL_r31		0xf8
-#define SL_SIZE		SL_r31+8
+#define SL_SPRG1	0x100
+#define SL_TCR		0x108
+#define SL_SIZE		SL_TCR+8
 
 /* these macros rely on the save area being
  * pointed to by r11 */
+
+#define SAVE_SPR(register)		\
+	mfspr	r0, SPRN_##register	;\
+	std	r0, SL_##register(r11)
+#define RESTORE_SPR(register)		\
+	ld	r0, SL_##register(r11)	;\
+	mtspr	SPRN_##register, r0
 #define SAVE_SPECIAL(special)		\
 	mf##special	r0		;\
 	std	r0, SL_##special(r11)
@@ -103,8 +112,15 @@ _GLOBAL(swsusp_arch_suspend)
 	SAVE_REGISTER(r30)
 	SAVE_REGISTER(r31)
 	SAVE_SPECIAL(MSR)
-	SAVE_SPECIAL(SDR1)
 	SAVE_SPECIAL(XER)
+#ifdef CONFIG_PPC_BOOK3S_64
+	SAVE_SPECIAL(SDR1)
+#else
+	SAVE_SPR(TCR)
+
+	/* Save SPRG1, SPRG1 be used save paca */
+	SAVE_SPR(SPRG1)
+#endif
 
 	/* we push the stack up 128 bytes but don't store the
 	 * stack pointer on the stack like a real stackframe */
@@ -151,6 +167,7 @@ copy_page_loop:
 	bne+	copyloop
 nothing_to_copy:
 
+#ifdef CONFIG_PPC_BOOK3S_64
 	/* flush caches */
 	lis	r3, 0x10
 	mtctr	r3
@@ -167,6 +184,7 @@ nothing_to_copy:
 	sync
 
 	tlbia
+#endif
 
 	ld	r11,swsusp_save_area_ptr@toc(r2)
 
@@ -208,16 +226,39 @@ nothing_to_copy:
 	RESTORE_REGISTER(r29)
 	RESTORE_REGISTER(r30)
 	RESTORE_REGISTER(r31)
+
+#ifdef CONFIG_PPC_BOOK3S_64
 	/* can't use RESTORE_SPECIAL(MSR) */
 	ld	r0, SL_MSR(r11)
 	mtmsrd	r0, 0
 	RESTORE_SPECIAL(SDR1)
+#else
+	/* Restore SPRG1, be used to save paca */
+	ld	r0, SL_SPRG1(r11)
+	mtsprg	1, r0
+
+	RESTORE_SPECIAL(MSR)
+
+	/* Restore TCR and clear any pending bits in TSR. */
+	RESTORE_SPR(TCR)
+	lis	r0, (TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS)@h
+	mtspr	SPRN_TSR, r0
+
+	/* Kick decrementer */
+	li	r0, 1
+	mtdec	r0
+
+	/* Invalidate all tlbs */
+	bl	_tlbil_all
+#endif
 	RESTORE_SPECIAL(XER)
 
 	sync
 
 	addi	r1,r1,-128
+#ifdef CONFIG_PPC_BOOK3S_64
 	bl	slb_flush_and_rebolt
+#endif
 	bl	do_after_copyback
 	addi	r1,r1,128
 
diff --git a/arch/powerpc/kernel/swsusp_booke.S b/arch/powerpc/kernel/swsusp_booke.S
index 11a39307dd71..0f204053e5b5 100644
--- a/arch/powerpc/kernel/swsusp_booke.S
+++ b/arch/powerpc/kernel/swsusp_booke.S
@@ -141,6 +141,14 @@ _GLOBAL(swsusp_arch_resume)
 	lis	r11,swsusp_save_area@h
 	ori	r11,r11,swsusp_save_area@l
 
+	/*
+	 * Mappings from virtual addresses to physical addresses may be
+	 * different than they were prior to restoring hibernation state. 
+	 * Invalidate the TLB so that the boot CPU is using the new
+	 * mappings.
+	 */
+	bl	_tlbil_all
+
 	lwz	r4,SL_SPRG0(r11)
 	mtsprg	0,r4
 	lwz	r4,SL_SPRG1(r11)
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index cdcc156865ef..192b051df97e 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -210,18 +210,18 @@ static u64 scan_dispatch_log(u64 stop_tb)
 	if (!dtl)
 		return 0;
 
-	if (i == vpa->dtl_idx)
+	if (i == be64_to_cpu(vpa->dtl_idx))
 		return 0;
-	while (i < vpa->dtl_idx) {
+	while (i < be64_to_cpu(vpa->dtl_idx)) {
 		if (dtl_consumer)
 			dtl_consumer(dtl, i);
-		dtb = dtl->timebase;
-		tb_delta = dtl->enqueue_to_dispatch_time +
-			dtl->ready_to_enqueue_time;
+		dtb = be64_to_cpu(dtl->timebase);
+		tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) +
+			be32_to_cpu(dtl->ready_to_enqueue_time);
 		barrier();
-		if (i + N_DISPATCH_LOG < vpa->dtl_idx) {
+		if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) {
 			/* buffer has overflowed */
-			i = vpa->dtl_idx - N_DISPATCH_LOG;
+			i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG;
 			dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG);
 			continue;
 		}
@@ -269,7 +269,7 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
 {
 	u64 stolen = 0;
 
-	if (get_paca()->dtl_ridx != get_paca()->lppaca_ptr->dtl_idx) {
+	if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) {
 		stolen = scan_dispatch_log(stop_tb);
 		get_paca()->system_time -= stolen;
 	}
@@ -612,7 +612,7 @@ unsigned long long sched_clock(void)
 static int __init get_freq(char *name, int cells, unsigned long *val)
 {
 	struct device_node *cpu;
-	const unsigned int *fp;
+	const __be32 *fp;
 	int found = 0;
 
 	/* The cpu node should have timebase and clock frequency properties */
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 0554d1f6d70d..7b60b9851469 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -155,10 +155,10 @@ _GLOBAL(tm_reclaim)
 	mfvscr	vr0
 	li	r6, THREAD_TRANSACT_VSCR
 	stvx	vr0, r3, r6
+dont_backup_vec:
 	mfspr	r0, SPRN_VRSAVE
 	std	r0, THREAD_TRANSACT_VRSAVE(r3)
 
-dont_backup_vec:
 	andi.	r0, r4, MSR_FP
 	beq	dont_backup_fp
 
@@ -341,11 +341,11 @@ _GLOBAL(tm_recheckpoint)
 	lvx	vr0, r3, r5
 	mtvscr	vr0
 	REST_32VRS(0, r5, r3)			/* r5 scratch, r3 THREAD ptr */
+dont_restore_vec:
 	ld	r5, THREAD_VRSAVE(r3)
 	mtspr	SPRN_VRSAVE, r5
 #endif
 
-dont_restore_vec:
 	andi.	r0, r4, MSR_FP
 	beq	dont_restore_fp
 
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index e435bc089ea3..f783c932faeb 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -60,6 +60,7 @@
 #include <asm/switch_to.h>
 #include <asm/tm.h>
 #include <asm/debug.h>
+#include <sysdev/fsl_pci.h>
 
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
 int (*__debugger)(struct pt_regs *regs) __read_mostly;
@@ -565,6 +566,8 @@ int machine_check_e500(struct pt_regs *regs)
 	if (reason & MCSR_BUS_RBERR) {
 		if (fsl_rio_mcheck_exception(regs))
 			return 1;
+		if (fsl_pci_mcheck_exception(regs))
+			return 1;
 	}
 
 	printk("Machine check in kernel mode.\n");
@@ -962,7 +965,7 @@ static int emulate_instruction(struct pt_regs *regs)
 	u32 instword;
 	u32 rd;
 
-	if (!user_mode(regs) || (regs->msr & MSR_LE))
+	if (!user_mode(regs))
 		return -EINVAL;
 	CHECK_FULL_REGS(regs);
 
@@ -1050,11 +1053,41 @@ int is_valid_bugaddr(unsigned long addr)
 	return is_kernel_addr(addr);
 }
 
+#ifdef CONFIG_MATH_EMULATION
+static int emulate_math(struct pt_regs *regs)
+{
+	int ret;
+	extern int do_mathemu(struct pt_regs *regs);
+
+	ret = do_mathemu(regs);
+	if (ret >= 0)
+		PPC_WARN_EMULATED(math, regs);
+
+	switch (ret) {
+	case 0:
+		emulate_single_step(regs);
+		return 0;
+	case 1: {
+			int code = 0;
+			code = __parse_fpscr(current->thread.fpscr.val);
+			_exception(SIGFPE, regs, code, regs->nip);
+			return 0;
+		}
+	case -EFAULT:
+		_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
+		return 0;
+	}
+
+	return -1;
+}
+#else
+static inline int emulate_math(struct pt_regs *regs) { return -1; }
+#endif
+
 void __kprobes program_check_exception(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
 	unsigned int reason = get_reason(regs);
-	extern int do_mathemu(struct pt_regs *regs);
 
 	/* We can now get here via a FP Unavailable exception if the core
 	 * has no FPU, in that case the reason flags will be 0 */
@@ -1116,11 +1149,20 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 	}
 #endif
 
+	/*
+	 * If we took the program check in the kernel skip down to sending a
+	 * SIGILL. The subsequent cases all relate to emulating instructions
+	 * which we should only do for userspace. We also do not want to enable
+	 * interrupts for kernel faults because that might lead to further
+	 * faults, and loose the context of the original exception.
+	 */
+	if (!user_mode(regs))
+		goto sigill;
+
 	/* We restore the interrupt state now */
 	if (!arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
-#ifdef CONFIG_MATH_EMULATION
 	/* (reason & REASON_ILLEGAL) would be the obvious thing here,
 	 * but there seems to be a hardware bug on the 405GP (RevD)
 	 * that means ESR is sometimes set incorrectly - either to
@@ -1129,31 +1171,8 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 	 * instruction or only on FP instructions, whether there is a
 	 * pattern to occurrences etc. -dgibson 31/Mar/2003
 	 */
-
-	/*
-	 * If we support a HW FPU, we need to ensure the FP state
-	 * if flushed into the thread_struct before attempting
-	 * emulation
-	 */
-#ifdef CONFIG_PPC_FPU
-	flush_fp_to_thread(current);
-#endif
-	switch (do_mathemu(regs)) {
-	case 0:
-		emulate_single_step(regs);
-		goto bail;
-	case 1: {
-			int code = 0;
-			code = __parse_fpscr(current->thread.fpscr.val);
-			_exception(SIGFPE, regs, code, regs->nip);
-			goto bail;
-		}
-	case -EFAULT:
-		_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
+	if (!emulate_math(regs))
 		goto bail;
-	}
-	/* fall through on any other errors */
-#endif /* CONFIG_MATH_EMULATION */
 
 	/* Try to emulate it if we should. */
 	if (reason & (REASON_ILLEGAL | REASON_PRIVILEGED)) {
@@ -1168,6 +1187,7 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 		}
 	}
 
+sigill:
 	if (reason & REASON_PRIVILEGED)
 		_exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
 	else
@@ -1322,13 +1342,10 @@ void facility_unavailable_exception(struct pt_regs *regs)
 	if (status == FSCR_DSCR_LG) {
 		/* User is acessing the DSCR.  Set the inherit bit and allow
 		 * the user to set it directly in future by setting via the
-		 * H/FSCR DSCR bit.
+		 * FSCR DSCR bit.  We always leave HFSCR DSCR set.
 		 */
 		current->thread.dscr_inherit = 1;
-		if (hv)
-			mtspr(SPRN_HFSCR, value | HFSCR_DSCR);
-		else
-			mtspr(SPRN_FSCR,  value | FSCR_DSCR);
+		mtspr(SPRN_FSCR, value | FSCR_DSCR);
 		return;
 	}
 
@@ -1444,11 +1461,6 @@ void performance_monitor_exception(struct pt_regs *regs)
 #ifdef CONFIG_8xx
 void SoftwareEmulation(struct pt_regs *regs)
 {
-	extern int do_mathemu(struct pt_regs *);
-#if defined(CONFIG_MATH_EMULATION)
-	int errcode;
-#endif
-
 	CHECK_FULL_REGS(regs);
 
 	if (!user_mode(regs)) {
@@ -1456,31 +1468,10 @@ void SoftwareEmulation(struct pt_regs *regs)
 		die("Kernel Mode Software FPU Emulation", regs, SIGFPE);
 	}
 
-#ifdef CONFIG_MATH_EMULATION
-	errcode = do_mathemu(regs);
-	if (errcode >= 0)
-		PPC_WARN_EMULATED(math, regs);
-
-	switch (errcode) {
-	case 0:
-		emulate_single_step(regs);
+	if (!emulate_math(regs))
 		return;
-	case 1: {
-			int code = 0;
-			code = __parse_fpscr(current->thread.fpscr.val);
-			_exception(SIGFPE, regs, code, regs->nip);
-			return;
-		}
-	case -EFAULT:
-		_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
-		return;
-	default:
-		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-		return;
-	}
-#else
+
 	_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-#endif
 }
 #endif /* CONFIG_8xx */
 
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 6837f839ab78..75702e207b29 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -18,23 +18,19 @@ extern void real_writeb(u8 data, volatile u8 __iomem *addr);
 extern u8 real_205_readb(volatile u8 __iomem  *addr);
 extern void real_205_writeb(u8 data, volatile u8 __iomem *addr);
 
-struct NS16550 {
-	/* this struct must be packed */
-	unsigned char rbr;  /* 0 */
-	unsigned char ier;  /* 1 */
-	unsigned char fcr;  /* 2 */
-	unsigned char lcr;  /* 3 */
-	unsigned char mcr;  /* 4 */
-	unsigned char lsr;  /* 5 */
-	unsigned char msr;  /* 6 */
-	unsigned char scr;  /* 7 */
-};
-
-#define thr rbr
-#define iir fcr
-#define dll rbr
-#define dlm ier
-#define dlab lcr
+#define UART_RBR	0
+#define UART_IER	1
+#define UART_FCR	2
+#define UART_LCR	3
+#define UART_MCR	4
+#define UART_LSR	5
+#define UART_MSR	6
+#define UART_SCR	7
+#define UART_THR	UART_RBR
+#define UART_IIR	UART_FCR
+#define UART_DLL	UART_RBR
+#define UART_DLM	UART_IER
+#define UART_DLAB	UART_LCR
 
 #define LSR_DR   0x01  /* Data ready */
 #define LSR_OE   0x02  /* Overrun */
@@ -47,52 +43,62 @@ struct NS16550 {
 
 #define LCR_DLAB 0x80
 
-static struct NS16550 __iomem *udbg_comport;
+static u8 (*udbg_uart_in)(unsigned int reg);
+static void (*udbg_uart_out)(unsigned int reg, u8 data);
 
-static void udbg_550_flush(void)
+static void udbg_uart_flush(void)
 {
-	if (udbg_comport) {
-		while ((in_8(&udbg_comport->lsr) & LSR_THRE) == 0)
-			/* wait for idle */;
-	}
+	if (!udbg_uart_in)
+		return;
+
+	/* wait for idle */
+	while ((udbg_uart_in(UART_LSR) & LSR_THRE) == 0)
+		cpu_relax();
 }
 
-static void udbg_550_putc(char c)
+static void udbg_uart_putc(char c)
 {
-	if (udbg_comport) {
-		if (c == '\n')
-			udbg_550_putc('\r');
-		udbg_550_flush();
-		out_8(&udbg_comport->thr, c);
-	}
+	if (!udbg_uart_out)
+		return;
+
+	if (c == '\n')
+		udbg_uart_putc('\r');
+	udbg_uart_flush();
+	udbg_uart_out(UART_THR, c);
 }
 
-static int udbg_550_getc_poll(void)
+static int udbg_uart_getc_poll(void)
 {
-	if (udbg_comport) {
-		if ((in_8(&udbg_comport->lsr) & LSR_DR) != 0)
-			return in_8(&udbg_comport->rbr);
-		else
-			return -1;
-	}
+	if (!udbg_uart_in || !(udbg_uart_in(UART_LSR) & LSR_DR))
+		return udbg_uart_in(UART_RBR);
 	return -1;
 }
 
-static int udbg_550_getc(void)
+static int udbg_uart_getc(void)
 {
-	if (udbg_comport) {
-		while ((in_8(&udbg_comport->lsr) & LSR_DR) == 0)
-			/* wait for char */;
-		return in_8(&udbg_comport->rbr);
-	}
-	return -1;
+	if (!udbg_uart_in)
+		return -1;
+	/* wait for char */
+	while (!(udbg_uart_in(UART_LSR) & LSR_DR))
+		cpu_relax();
+	return udbg_uart_in(UART_RBR);
+}
+
+static void udbg_use_uart(void)
+{
+	udbg_putc = udbg_uart_putc;
+	udbg_flush = udbg_uart_flush;
+	udbg_getc = udbg_uart_getc;
+	udbg_getc_poll = udbg_uart_getc_poll;
 }
 
-void udbg_init_uart(void __iomem *comport, unsigned int speed,
-		    unsigned int clock)
+void udbg_uart_setup(unsigned int speed, unsigned int clock)
 {
 	unsigned int dll, base_bauds;
 
+	if (!udbg_uart_out)
+		return;
+
 	if (clock == 0)
 		clock = 1843200;
 	if (speed == 0)
@@ -101,51 +107,43 @@ void udbg_init_uart(void __iomem *comport, unsigned int speed,
 	base_bauds = clock / 16;
 	dll = base_bauds / speed;
 
-	if (comport) {
-		udbg_comport = (struct NS16550 __iomem *)comport;
-		out_8(&udbg_comport->lcr, 0x00);
-		out_8(&udbg_comport->ier, 0xff);
-		out_8(&udbg_comport->ier, 0x00);
-		out_8(&udbg_comport->lcr, LCR_DLAB);
-		out_8(&udbg_comport->dll, dll & 0xff);
-		out_8(&udbg_comport->dlm, dll >> 8);
-		/* 8 data, 1 stop, no parity */
-		out_8(&udbg_comport->lcr, 0x03);
-		/* RTS/DTR */
-		out_8(&udbg_comport->mcr, 0x03);
-		/* Clear & enable FIFOs */
-		out_8(&udbg_comport->fcr ,0x07);
-		udbg_putc = udbg_550_putc;
-		udbg_flush = udbg_550_flush;
-		udbg_getc = udbg_550_getc;
-		udbg_getc_poll = udbg_550_getc_poll;
-	}
+	udbg_uart_out(UART_LCR, 0x00);
+	udbg_uart_out(UART_IER, 0xff);
+	udbg_uart_out(UART_IER, 0x00);
+	udbg_uart_out(UART_LCR, LCR_DLAB);
+	udbg_uart_out(UART_DLL, dll & 0xff);
+	udbg_uart_out(UART_DLM, dll >> 8);
+	/* 8 data, 1 stop, no parity */
+	udbg_uart_out(UART_LCR, 0x3);
+	/* RTS/DTR */
+	udbg_uart_out(UART_MCR, 0x3);
+	/* Clear & enable FIFOs */
+	udbg_uart_out(UART_FCR, 0x7);
 }
 
-unsigned int udbg_probe_uart_speed(void __iomem *comport, unsigned int clock)
+unsigned int udbg_probe_uart_speed(unsigned int clock)
 {
 	unsigned int dll, dlm, divisor, prescaler, speed;
 	u8 old_lcr;
-	struct NS16550 __iomem *port = comport;
 
-	old_lcr = in_8(&port->lcr);
+	old_lcr = udbg_uart_in(UART_LCR);
 
 	/* select divisor latch registers.  */
-	out_8(&port->lcr, LCR_DLAB);
+	udbg_uart_out(UART_LCR, old_lcr | LCR_DLAB);
 
 	/* now, read the divisor */
-	dll = in_8(&port->dll);
-	dlm = in_8(&port->dlm);
+	dll = udbg_uart_in(UART_DLL);
+	dlm = udbg_uart_in(UART_DLM);
 	divisor = dlm << 8 | dll;
 
 	/* check prescaling */
-	if (in_8(&port->mcr) & 0x80)
+	if (udbg_uart_in(UART_MCR) & 0x80)
 		prescaler = 4;
 	else
 		prescaler = 1;
 
 	/* restore the LCR */
-	out_8(&port->lcr, old_lcr);
+	udbg_uart_out(UART_LCR, old_lcr);
 
 	/* calculate speed */
 	speed = (clock / prescaler) / (divisor * 16);
@@ -157,195 +155,155 @@ unsigned int udbg_probe_uart_speed(void __iomem *comport, unsigned int clock)
 	return speed;
 }
 
-#ifdef CONFIG_PPC_MAPLE
-void udbg_maple_real_flush(void)
+static union {
+	unsigned char __iomem *mmio_base;
+	unsigned long pio_base;
+} udbg_uart;
+
+static unsigned int udbg_uart_stride = 1;
+
+static u8 udbg_uart_in_pio(unsigned int reg)
 {
-	if (udbg_comport) {
-		while ((real_readb(&udbg_comport->lsr) & LSR_THRE) == 0)
-			/* wait for idle */;
-	}
+	return inb(udbg_uart.pio_base + (reg * udbg_uart_stride));
 }
 
-void udbg_maple_real_putc(char c)
+static void udbg_uart_out_pio(unsigned int reg, u8 data)
 {
-	if (udbg_comport) {
-		if (c == '\n')
-			udbg_maple_real_putc('\r');
-		udbg_maple_real_flush();
-		real_writeb(c, &udbg_comport->thr); eieio();
-	}
+	outb(data, udbg_uart.pio_base + (reg * udbg_uart_stride));
 }
 
-void __init udbg_init_maple_realmode(void)
+void udbg_uart_init_pio(unsigned long port, unsigned int stride)
 {
-	udbg_comport = (struct NS16550 __iomem *)0xf40003f8;
-
-	udbg_putc = udbg_maple_real_putc;
-	udbg_flush = udbg_maple_real_flush;
-	udbg_getc = NULL;
-	udbg_getc_poll = NULL;
+	if (!port)
+		return;
+	udbg_uart.pio_base = port;
+	udbg_uart_stride = stride;
+	udbg_uart_in = udbg_uart_in_pio;
+	udbg_uart_out = udbg_uart_out_pio;
+	udbg_use_uart();
 }
-#endif /* CONFIG_PPC_MAPLE */
 
-#ifdef CONFIG_PPC_PASEMI
-void udbg_pas_real_flush(void)
+static u8 udbg_uart_in_mmio(unsigned int reg)
 {
-	if (udbg_comport) {
-		while ((real_205_readb(&udbg_comport->lsr) & LSR_THRE) == 0)
-			/* wait for idle */;
-	}
+	return in_8(udbg_uart.mmio_base + (reg * udbg_uart_stride));
 }
 
-void udbg_pas_real_putc(char c)
+static void udbg_uart_out_mmio(unsigned int reg, u8 data)
 {
-	if (udbg_comport) {
-		if (c == '\n')
-			udbg_pas_real_putc('\r');
-		udbg_pas_real_flush();
-		real_205_writeb(c, &udbg_comport->thr); eieio();
-	}
+	out_8(udbg_uart.mmio_base + (reg * udbg_uart_stride), data);
 }
 
-void udbg_init_pas_realmode(void)
-{
-	udbg_comport = (struct NS16550 __iomem *)0xfcff03f8UL;
 
-	udbg_putc = udbg_pas_real_putc;
-	udbg_flush = udbg_pas_real_flush;
-	udbg_getc = NULL;
-	udbg_getc_poll = NULL;
+void udbg_uart_init_mmio(void __iomem *addr, unsigned int stride)
+{
+	if (!addr)
+		return;
+	udbg_uart.mmio_base = addr;
+	udbg_uart_stride = stride;
+	udbg_uart_in = udbg_uart_in_mmio;
+	udbg_uart_out = udbg_uart_out_mmio;
+	udbg_use_uart();
 }
-#endif /* CONFIG_PPC_MAPLE */
 
-#ifdef CONFIG_PPC_EARLY_DEBUG_44x
-#include <platforms/44x/44x.h>
+#ifdef CONFIG_PPC_MAPLE
+
+#define UDBG_UART_MAPLE_ADDR	((void __iomem *)0xf40003f8)
 
-static void udbg_44x_as1_flush(void)
+static u8 udbg_uart_in_maple(unsigned int reg)
 {
-	if (udbg_comport) {
-		while ((as1_readb(&udbg_comport->lsr) & LSR_THRE) == 0)
-			/* wait for idle */;
-	}
+	return real_readb(UDBG_UART_MAPLE_ADDR + reg);
 }
 
-static void udbg_44x_as1_putc(char c)
+static void udbg_uart_out_maple(unsigned int reg, u8 val)
 {
-	if (udbg_comport) {
-		if (c == '\n')
-			udbg_44x_as1_putc('\r');
-		udbg_44x_as1_flush();
-		as1_writeb(c, &udbg_comport->thr); eieio();
-	}
+	real_writeb(val, UDBG_UART_MAPLE_ADDR + reg);
 }
 
-static int udbg_44x_as1_getc(void)
+void __init udbg_init_maple_realmode(void)
 {
-	if (udbg_comport) {
-		while ((as1_readb(&udbg_comport->lsr) & LSR_DR) == 0)
-			; /* wait for char */
-		return as1_readb(&udbg_comport->rbr);
-	}
-	return -1;
+	udbg_uart_in = udbg_uart_in_maple;
+	udbg_uart_out = udbg_uart_out_maple;
+	udbg_use_uart();
 }
 
-void __init udbg_init_44x_as1(void)
-{
-	udbg_comport =
-		(struct NS16550 __iomem *)PPC44x_EARLY_DEBUG_VIRTADDR;
+#endif /* CONFIG_PPC_MAPLE */
 
-	udbg_putc = udbg_44x_as1_putc;
-	udbg_flush = udbg_44x_as1_flush;
-	udbg_getc = udbg_44x_as1_getc;
-}
-#endif /* CONFIG_PPC_EARLY_DEBUG_44x */
+#ifdef CONFIG_PPC_PASEMI
 
-#ifdef CONFIG_PPC_EARLY_DEBUG_40x
-static void udbg_40x_real_flush(void)
+#define UDBG_UART_PAS_ADDR	((void __iomem *)0xfcff03f8UL)
+
+static u8 udbg_uart_in_pas(unsigned int reg)
 {
-	if (udbg_comport) {
-		while ((real_readb(&udbg_comport->lsr) & LSR_THRE) == 0)
-			/* wait for idle */;
-	}
+	return real_205_readb(UDBG_UART_PAS_ADDR + reg);
 }
 
-static void udbg_40x_real_putc(char c)
+static void udbg_uart_out_pas(unsigned int reg, u8 val)
 {
-	if (udbg_comport) {
-		if (c == '\n')
-			udbg_40x_real_putc('\r');
-		udbg_40x_real_flush();
-		real_writeb(c, &udbg_comport->thr); eieio();
-	}
+	real_205_writeb(val, UDBG_UART_PAS_ADDR + reg);
 }
 
-static int udbg_40x_real_getc(void)
+void __init udbg_init_pas_realmode(void)
 {
-	if (udbg_comport) {
-		while ((real_readb(&udbg_comport->lsr) & LSR_DR) == 0)
-			; /* wait for char */
-		return real_readb(&udbg_comport->rbr);
-	}
-	return -1;
+	udbg_uart_in = udbg_uart_in_pas;
+	udbg_uart_out = udbg_uart_out_pas;
+	udbg_use_uart();
 }
 
-void __init udbg_init_40x_realmode(void)
-{
-	udbg_comport = (struct NS16550 __iomem *)
-		CONFIG_PPC_EARLY_DEBUG_40x_PHYSADDR;
+#endif /* CONFIG_PPC_PASEMI */
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_44x
 
-	udbg_putc = udbg_40x_real_putc;
-	udbg_flush = udbg_40x_real_flush;
-	udbg_getc = udbg_40x_real_getc;
-	udbg_getc_poll = NULL;
+#include <platforms/44x/44x.h>
+
+static u8 udbg_uart_in_44x_as1(unsigned int reg)
+{
+	return as1_readb((void __iomem *)PPC44x_EARLY_DEBUG_VIRTADDR + reg);
 }
-#endif /* CONFIG_PPC_EARLY_DEBUG_40x */
 
-#ifdef CONFIG_PPC_EARLY_DEBUG_WSP
-static void udbg_wsp_flush(void)
+static void udbg_uart_out_44x_as1(unsigned int reg, u8 val)
 {
-	if (udbg_comport) {
-		while ((readb(&udbg_comport->lsr) & LSR_THRE) == 0)
-			/* wait for idle */;
-	}
+	as1_writeb(val, (void __iomem *)PPC44x_EARLY_DEBUG_VIRTADDR + reg);
 }
 
-static void udbg_wsp_putc(char c)
+void __init udbg_init_44x_as1(void)
 {
-	if (udbg_comport) {
-		if (c == '\n')
-			udbg_wsp_putc('\r');
-		udbg_wsp_flush();
-		writeb(c, &udbg_comport->thr); eieio();
-	}
+	udbg_uart_in = udbg_uart_in_44x_as1;
+	udbg_uart_out = udbg_uart_out_44x_as1;
+	udbg_use_uart();
 }
 
-static int udbg_wsp_getc(void)
+#endif /* CONFIG_PPC_EARLY_DEBUG_44x */
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_40x
+
+static u8 udbg_uart_in_40x(unsigned int reg)
 {
-	if (udbg_comport) {
-		while ((readb(&udbg_comport->lsr) & LSR_DR) == 0)
-			; /* wait for char */
-		return readb(&udbg_comport->rbr);
-	}
-	return -1;
+	return real_readb((void __iomem *)CONFIG_PPC_EARLY_DEBUG_40x_PHYSADDR
+			  + reg);
 }
 
-static int udbg_wsp_getc_poll(void)
+static void udbg_uart_out_40x(unsigned int reg, u8 val)
 {
-	if (udbg_comport)
-		if (readb(&udbg_comport->lsr) & LSR_DR)
-			return readb(&udbg_comport->rbr);
-	return -1;
+	real_writeb(val, (void __iomem *)CONFIG_PPC_EARLY_DEBUG_40x_PHYSADDR
+		    + reg);
 }
 
-void __init udbg_init_wsp(void)
+void __init udbg_init_40x_realmode(void)
 {
-	udbg_comport = (struct NS16550 __iomem *)WSP_UART_VIRT;
+	udbg_uart_in = udbg_uart_in_40x;
+	udbg_uart_out = udbg_uart_out_40x;
+	udbg_use_uart();
+}
 
-	udbg_init_uart(udbg_comport, 57600, 50000000);
+#endif /* CONFIG_PPC_EARLY_DEBUG_40x */
+
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_WSP
 
-	udbg_putc = udbg_wsp_putc;
-	udbg_flush = udbg_wsp_flush;
-	udbg_getc = udbg_wsp_getc;
-	udbg_getc_poll = udbg_wsp_getc_poll;
+void __init udbg_init_wsp(void)
+{
+	udbg_uart_init_mmio((void *)WSP_UART_VIRT, 1);
+	udbg_uart_setup(57600, 50000000);
 }
+
 #endif /* CONFIG_PPC_EARLY_DEBUG_WSP */
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index 27e2f623210b..6b1f2a6d5517 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -232,9 +232,9 @@ __do_get_tspec:
 	lwz	r6,(CFG_TB_ORIG_STAMP+4)(r9)
 
 	/* Get a stable TB value */
-2:	mftbu	r3
-	mftbl	r4
-	mftbu	r0
+2:	mfspr	r3, SPRN_TBRU
+	mfspr	r4, SPRN_TBRL
+	mfspr	r0, SPRN_TBRU
 	cmplw	cr0,r3,r0
 	bne-	2b
 
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 536016d792ba..78a350670de3 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -1153,7 +1153,7 @@ EXPORT_SYMBOL(vio_h_cop_sync);
 
 static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
 {
-	const unsigned char *dma_window;
+	const __be32 *dma_window;
 	struct iommu_table *tbl;
 	unsigned long offset, size;
 
@@ -1312,8 +1312,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 {
 	struct vio_dev *viodev;
 	struct device_node *parent_node;
-	const unsigned int *unit_address;
-	const unsigned int *pfo_resid = NULL;
+	const __be32 *prop;
 	enum vio_dev_family family;
 	const char *of_node_name = of_node->name ? of_node->name : "<unknown>";
 
@@ -1360,6 +1359,8 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 	/* we need the 'device_type' property, in order to match with drivers */
 	viodev->family = family;
 	if (viodev->family == VDEVICE) {
+		unsigned int unit_address;
+
 		if (of_node->type != NULL)
 			viodev->type = of_node->type;
 		else {
@@ -1368,24 +1369,24 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 			goto out;
 		}
 
-		unit_address = of_get_property(of_node, "reg", NULL);
-		if (unit_address == NULL) {
+		prop = of_get_property(of_node, "reg", NULL);
+		if (prop == NULL) {
 			pr_warn("%s: node %s missing 'reg'\n",
 					__func__, of_node_name);
 			goto out;
 		}
-		dev_set_name(&viodev->dev, "%x", *unit_address);
+		unit_address = of_read_number(prop, 1);
+		dev_set_name(&viodev->dev, "%x", unit_address);
 		viodev->irq = irq_of_parse_and_map(of_node, 0);
-		viodev->unit_address = *unit_address;
+		viodev->unit_address = unit_address;
 	} else {
 		/* PFO devices need their resource_id for submitting COP_OPs
 		 * This is an optional field for devices, but is required when
 		 * performing synchronous ops */
-		pfo_resid = of_get_property(of_node, "ibm,resource-id", NULL);
-		if (pfo_resid != NULL)
-			viodev->resource_id = *pfo_resid;
+		prop = of_get_property(of_node, "ibm,resource-id", NULL);
+		if (prop != NULL)
+			viodev->resource_id = of_read_number(prop, 1);
 
-		unit_address = NULL;
 		dev_set_name(&viodev->dev, "%s", of_node_name);
 		viodev->type = of_node_name;
 		viodev->irq = 0;
@@ -1622,7 +1623,6 @@ static struct vio_dev *vio_find_name(const char *name)
  */
 struct vio_dev *vio_find_node(struct device_node *vnode)
 {
-	const uint32_t *unit_address;
 	char kobj_name[20];
 	struct device_node *vnode_parent;
 	const char *dev_type;
@@ -1638,10 +1638,13 @@ struct vio_dev *vio_find_node(struct device_node *vnode)
 
 	/* construct the kobject name from the device node */
 	if (!strcmp(dev_type, "vdevice")) {
-		unit_address = of_get_property(vnode, "reg", NULL);
-		if (!unit_address)
+		const __be32 *prop;
+		
+		prop = of_get_property(vnode, "reg", NULL);
+		if (!prop)
 			return NULL;
-		snprintf(kobj_name, sizeof(kobj_name), "%x", *unit_address);
+		snprintf(kobj_name, sizeof(kobj_name), "%x",
+			 (uint32_t)of_read_number(prop, 1));
 	} else if (!strcmp(dev_type, "ibm,platform-facilities"))
 		snprintf(kobj_name, sizeof(kobj_name), "%s", vnode->name);
 	else