Forward to 2.6.33-rc8

Merge branch 'linus' into rt/head with a pile of conflicts.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

105 files changed, 2355 insertions, 1226 deletions

diff --git a/arch/powerpc/include/asm/agp.h b/arch/powerpc/include/asm/agp.h
index 86455c4c31ee..416e12c2d505 100644
--- a/arch/powerpc/include/asm/agp.h
+++ b/arch/powerpc/include/asm/agp.h
@@ -8,10 +8,6 @@
 #define unmap_page_from_agp(page)
 #define flush_agp_cache() mb()
 
-/* Convert a physical address to an address suitable for the GART. */
-#define phys_to_gart(x) (x)
-#define gart_to_phys(x) (x)
-
 /* GATT allocation. Returns/accepts GATT kernel virtual address. */
 #define alloc_gatt_pages(order)		\
 	((char *)__get_free_pages(GFP_KERNEL, (order)))
diff --git a/arch/powerpc/include/asm/asm-offsets.h b/arch/powerpc/include/asm/asm-offsets.h
new file mode 100644
index 000000000000..d370ee36a182
--- /dev/null
+++ b/arch/powerpc/include/asm/asm-offsets.h
@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>
diff --git a/arch/powerpc/include/asm/async_tx.h b/arch/powerpc/include/asm/async_tx.h
new file mode 100644
index 000000000000..8b2dc55d01ab
--- /dev/null
+++ b/arch/powerpc/include/asm/async_tx.h
@@ -0,0 +1,47 @@
+/*
+ * Copyright (C) 2008-2009 DENX Software Engineering.
+ *
+ * Author: Yuri Tikhonov <yur@emcraft.com>
+ *
+ * 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 program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ *
+ * The full GNU General Public License is included in this distribution in the
+ * file called COPYING.
+ */
+#ifndef _ASM_POWERPC_ASYNC_TX_H_
+#define _ASM_POWERPC_ASYNC_TX_H_
+
+#if defined(CONFIG_440SPe) || defined(CONFIG_440SP)
+extern struct dma_chan *
+ppc440spe_async_tx_find_best_channel(enum dma_transaction_type cap,
+	struct page **dst_lst, int dst_cnt, struct page **src_lst,
+	int src_cnt, size_t src_sz);
+
+#define async_tx_find_channel(dep, cap, dst_lst, dst_cnt, src_lst, \
+			      src_cnt, src_sz) \
+	ppc440spe_async_tx_find_best_channel(cap, dst_lst, dst_cnt, src_lst, \
+					     src_cnt, src_sz)
+#else
+
+#define async_tx_find_channel(dep, type, dst, dst_count, src, src_count, len) \
+	__async_tx_find_channel(dep, type)
+
+struct dma_chan *
+__async_tx_find_channel(struct async_submit_ctl *submit,
+			enum dma_transaction_type tx_type);
+
+#endif
+
+#endif
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index 897eade3afbe..56f2f2ea5631 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -56,174 +56,102 @@
 #define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
 #define BITOP_LE_SWIZZLE	((BITS_PER_LONG-1) & ~0x7)
 
+/* Macro for generating the ***_bits() functions */
+#define DEFINE_BITOP(fn, op, prefix, postfix)	\
+static __inline__ void fn(unsigned long mask,	\
+		volatile unsigned long *_p)	\
+{						\
+	unsigned long old;			\
+	unsigned long *p = (unsigned long *)_p;	\
+	__asm__ __volatile__ (			\
+	prefix					\
+"1:"	PPC_LLARX "%0,0,%3\n"			\
+	stringify_in_c(op) "%0,%0,%2\n"		\
+	PPC405_ERR77(0,%3)			\
+	PPC_STLCX "%0,0,%3\n"			\
+	"bne- 1b\n"				\
+	postfix					\
+	: "=&r" (old), "+m" (*p)		\
+	: "r" (mask), "r" (p)			\
+	: "cc", "memory");			\
+}
+
+DEFINE_BITOP(set_bits, or, "", "")
+DEFINE_BITOP(clear_bits, andc, "", "")
+DEFINE_BITOP(clear_bits_unlock, andc, LWSYNC_ON_SMP, "")
+DEFINE_BITOP(change_bits, xor, "", "")
+
 static __inline__ void set_bit(int nr, volatile unsigned long *addr)
 {
-	unsigned long old;
-	unsigned long mask = BITOP_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
-
-	__asm__ __volatile__(
-"1:"	PPC_LLARX "%0,0,%3	# set_bit\n"
-	"or	%0,%0,%2\n"
-	PPC405_ERR77(0,%3)
-	PPC_STLCX "%0,0,%3\n"
-	"bne-	1b"
-	: "=&r" (old), "+m" (*p)
-	: "r" (mask), "r" (p)
-	: "cc" );
+	set_bits(BITOP_MASK(nr), addr + BITOP_WORD(nr));
 }
 
 static __inline__ void clear_bit(int nr, volatile unsigned long *addr)
 {
-	unsigned long old;
-	unsigned long mask = BITOP_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
-
-	__asm__ __volatile__(
-"1:"	PPC_LLARX "%0,0,%3	# clear_bit\n"
-	"andc	%0,%0,%2\n"
-	PPC405_ERR77(0,%3)
-	PPC_STLCX "%0,0,%3\n"
-	"bne-	1b"
-	: "=&r" (old), "+m" (*p)
-	: "r" (mask), "r" (p)
-	: "cc" );
+	clear_bits(BITOP_MASK(nr), addr + BITOP_WORD(nr));
 }
 
 static __inline__ void clear_bit_unlock(int nr, volatile unsigned long *addr)
 {
-	unsigned long old;
-	unsigned long mask = BITOP_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
-
-	__asm__ __volatile__(
-	LWSYNC_ON_SMP
-"1:"	PPC_LLARX "%0,0,%3	# clear_bit_unlock\n"
-	"andc	%0,%0,%2\n"
-	PPC405_ERR77(0,%3)
-	PPC_STLCX "%0,0,%3\n"
-	"bne-	1b"
-	: "=&r" (old), "+m" (*p)
-	: "r" (mask), "r" (p)
-	: "cc", "memory");
+	clear_bits_unlock(BITOP_MASK(nr), addr + BITOP_WORD(nr));
 }
 
 static __inline__ void change_bit(int nr, volatile unsigned long *addr)
 {
-	unsigned long old;
-	unsigned long mask = BITOP_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
-
-	__asm__ __volatile__(
-"1:"	PPC_LLARX "%0,0,%3	# change_bit\n"
-	"xor	%0,%0,%2\n"
-	PPC405_ERR77(0,%3)
-	PPC_STLCX "%0,0,%3\n"
-	"bne-	1b"
-	: "=&r" (old), "+m" (*p)
-	: "r" (mask), "r" (p)
-	: "cc" );
+	change_bits(BITOP_MASK(nr), addr + BITOP_WORD(nr));
+}
+
+/* Like DEFINE_BITOP(), with changes to the arguments to 'op' and the output
+ * operands. */
+#define DEFINE_TESTOP(fn, op, prefix, postfix)	\
+static __inline__ unsigned long fn(		\
+		unsigned long mask,		\
+		volatile unsigned long *_p)	\
+{						\
+	unsigned long old, t;			\
+	unsigned long *p = (unsigned long *)_p;	\
+	__asm__ __volatile__ (			\
+	prefix					\
+"1:"	PPC_LLARX "%0,0,%3\n"			\
+	stringify_in_c(op) "%1,%0,%2\n"		\
+	PPC405_ERR77(0,%3)			\
+	PPC_STLCX "%1,0,%3\n"			\
+	"bne- 1b\n"				\
+	postfix					\
+	: "=&r" (old), "=&r" (t)		\
+	: "r" (mask), "r" (p)			\
+	: "cc", "memory");			\
+	return (old & mask);			\
 }
 
+DEFINE_TESTOP(test_and_set_bits, or, LWSYNC_ON_SMP, ISYNC_ON_SMP)
+DEFINE_TESTOP(test_and_set_bits_lock, or, "", ISYNC_ON_SMP)
+DEFINE_TESTOP(test_and_clear_bits, andc, LWSYNC_ON_SMP, ISYNC_ON_SMP)
+DEFINE_TESTOP(test_and_change_bits, xor, LWSYNC_ON_SMP, ISYNC_ON_SMP)
+
 static __inline__ int test_and_set_bit(unsigned long nr,
 				       volatile unsigned long *addr)
 {
-	unsigned long old, t;
-	unsigned long mask = BITOP_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
-
-	__asm__ __volatile__(
-	LWSYNC_ON_SMP
-"1:"	PPC_LLARX "%0,0,%3		# test_and_set_bit\n"
-	"or	%1,%0,%2 \n"
-	PPC405_ERR77(0,%3)
-	PPC_STLCX "%1,0,%3 \n"
-	"bne-	1b"
-	ISYNC_ON_SMP
-	: "=&r" (old), "=&r" (t)
-	: "r" (mask), "r" (p)
-	: "cc", "memory");
-
-	return (old & mask) != 0;
+	return test_and_set_bits(BITOP_MASK(nr), addr + BITOP_WORD(nr)) != 0;
 }
 
 static __inline__ int test_and_set_bit_lock(unsigned long nr,
 				       volatile unsigned long *addr)
 {
-	unsigned long old, t;
-	unsigned long mask = BITOP_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
-
-	__asm__ __volatile__(
-"1:"	PPC_LLARX "%0,0,%3		# test_and_set_bit_lock\n"
-	"or	%1,%0,%2 \n"
-	PPC405_ERR77(0,%3)
-	PPC_STLCX "%1,0,%3 \n"
-	"bne-	1b"
-	ISYNC_ON_SMP
-	: "=&r" (old), "=&r" (t)
-	: "r" (mask), "r" (p)
-	: "cc", "memory");
-
-	return (old & mask) != 0;
+	return test_and_set_bits_lock(BITOP_MASK(nr),
+				addr + BITOP_WORD(nr)) != 0;
 }
 
 static __inline__ int test_and_clear_bit(unsigned long nr,
 					 volatile unsigned long *addr)
 {
-	unsigned long old, t;
-	unsigned long mask = BITOP_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
-
-	__asm__ __volatile__(
-	LWSYNC_ON_SMP
-"1:"	PPC_LLARX "%0,0,%3		# test_and_clear_bit\n"
-	"andc	%1,%0,%2 \n"
-	PPC405_ERR77(0,%3)
-	PPC_STLCX "%1,0,%3 \n"
-	"bne-	1b"
-	ISYNC_ON_SMP
-	: "=&r" (old), "=&r" (t)
-	: "r" (mask), "r" (p)
-	: "cc", "memory");
-
-	return (old & mask) != 0;
+	return test_and_clear_bits(BITOP_MASK(nr), addr + BITOP_WORD(nr)) != 0;
 }
 
 static __inline__ int test_and_change_bit(unsigned long nr,
 					  volatile unsigned long *addr)
 {
-	unsigned long old, t;
-	unsigned long mask = BITOP_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
-
-	__asm__ __volatile__(
-	LWSYNC_ON_SMP
-"1:"	PPC_LLARX "%0,0,%3		# test_and_change_bit\n"
-	"xor	%1,%0,%2 \n"
-	PPC405_ERR77(0,%3)
-	PPC_STLCX "%1,0,%3 \n"
-	"bne-	1b"
-	ISYNC_ON_SMP
-	: "=&r" (old), "=&r" (t)
-	: "r" (mask), "r" (p)
-	: "cc", "memory");
-
-	return (old & mask) != 0;
-}
-
-static __inline__ void set_bits(unsigned long mask, unsigned long *addr)
-{
-        unsigned long old;
-
-	__asm__ __volatile__(
-"1:"	PPC_LLARX "%0,0,%3         # set_bits\n"
-	"or	%0,%0,%2\n"
-	PPC_STLCX "%0,0,%3\n"
-	"bne-	1b"
-	: "=&r" (old), "+m" (*addr)
-	: "r" (mask), "r" (addr)
-	: "cc");
+	return test_and_change_bits(BITOP_MASK(nr), addr + BITOP_WORD(nr)) != 0;
 }
 
 #include <asm-generic/bitops/non-atomic.h>
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index 64e1fdca233e..2c15212e1700 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -68,7 +68,7 @@
 		_EMIT_BUG_ENTRY					\
 		: : "i" (__FILE__), "i" (__LINE__),		\
 		    "i" (0), "i"  (sizeof(struct bug_entry)));	\
-	for(;;) ;						\
+	unreachable();						\
 } while (0)
 
 #define BUG_ON(x) do {						\
diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index ba667a383b8c..ab9e402518e8 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -25,6 +25,7 @@
 #define flush_cache_vmap(start, end)		do { } while (0)
 #define flush_cache_vunmap(start, end)		do { } while (0)
 
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *page);
 #define flush_dcache_mmap_lock(mapping)		do { } while (0)
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
diff --git a/arch/powerpc/include/asm/cell-regs.h b/arch/powerpc/include/asm/cell-regs.h
index fd6fd00434ef..fdf64fd25950 100644
--- a/arch/powerpc/include/asm/cell-regs.h
+++ b/arch/powerpc/include/asm/cell-regs.h
@@ -303,6 +303,17 @@ struct cbe_mic_tm_regs {
 extern struct cbe_mic_tm_regs __iomem *cbe_get_mic_tm_regs(struct device_node *np);
 extern struct cbe_mic_tm_regs __iomem *cbe_get_cpu_mic_tm_regs(int cpu);
 
+
+/* Cell page table entries */
+#define CBE_IOPTE_PP_W		0x8000000000000000ul /* protection: write */
+#define CBE_IOPTE_PP_R		0x4000000000000000ul /* protection: read */
+#define CBE_IOPTE_M		0x2000000000000000ul /* coherency required */
+#define CBE_IOPTE_SO_R		0x1000000000000000ul /* ordering: writes */
+#define CBE_IOPTE_SO_RW		0x1800000000000000ul /* ordering: r & w */
+#define CBE_IOPTE_RPN_Mask	0x07fffffffffff000ul /* RPN */
+#define CBE_IOPTE_H		0x0000000000000800ul /* cache hint */
+#define CBE_IOPTE_IOID_Mask	0x00000000000007fful /* ioid */
+
 /* some utility functions to deal with SMT */
 extern u32 cbe_get_hw_thread_id(int cpu);
 extern u32 cbe_cpu_to_node(int cpu);
diff --git a/arch/powerpc/include/asm/cpm.h b/arch/powerpc/include/asm/cpm.h
index 24d79e3abd8e..0835eb977ba9 100644
--- a/arch/powerpc/include/asm/cpm.h
+++ b/arch/powerpc/include/asm/cpm.h
@@ -3,8 +3,47 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
+#include <linux/errno.h>
 #include <linux/of.h>
 
+/*
+ * USB Controller pram common to QE and CPM.
+ */
+struct usb_ctlr {
+	u8	usb_usmod;
+	u8	usb_usadr;
+	u8	usb_uscom;
+	u8	res1[1];
+	__be16	usb_usep[4];
+	u8	res2[4];
+	__be16	usb_usber;
+	u8	res3[2];
+	__be16	usb_usbmr;
+	u8	res4[1];
+	u8	usb_usbs;
+	/* Fields down below are QE-only */
+	__be16	usb_ussft;
+	u8	res5[2];
+	__be16	usb_usfrn;
+	u8	res6[0x22];
+} __attribute__ ((packed));
+
+/*
+ * Function code bits, usually generic to devices.
+ */
+#ifdef CONFIG_CPM1
+#define CPMFCR_GBL	((u_char)0x00)	/* Flag doesn't exist in CPM1 */
+#define CPMFCR_TC2	((u_char)0x00)	/* Flag doesn't exist in CPM1 */
+#define CPMFCR_DTB	((u_char)0x00)	/* Flag doesn't exist in CPM1 */
+#define CPMFCR_BDB	((u_char)0x00)	/* Flag doesn't exist in CPM1 */
+#else
+#define CPMFCR_GBL	((u_char)0x20)	/* Set memory snooping */
+#define CPMFCR_TC2	((u_char)0x04)	/* Transfer code 2 value */
+#define CPMFCR_DTB	((u_char)0x02)	/* Use local bus for data when set */
+#define CPMFCR_BDB	((u_char)0x01)	/* Use local bus for BD when set */
+#endif
+#define CPMFCR_EB	((u_char)0x10)	/* Set big endian byte order */
+
 /* Opcodes common to CPM1 and CPM2
 */
 #define CPM_CR_INIT_TRX		((ushort)0x0000)
@@ -93,13 +132,56 @@ typedef struct cpm_buf_desc {
 #define BD_I2C_START		(0x0400)
 
 int cpm_muram_init(void);
+
+#if defined(CONFIG_CPM) || defined(CONFIG_QUICC_ENGINE)
 unsigned long cpm_muram_alloc(unsigned long size, unsigned long align);
 int cpm_muram_free(unsigned long offset);
 unsigned long cpm_muram_alloc_fixed(unsigned long offset, unsigned long size);
 void __iomem *cpm_muram_addr(unsigned long offset);
 unsigned long cpm_muram_offset(void __iomem *addr);
 dma_addr_t cpm_muram_dma(void __iomem *addr);
+#else
+static inline unsigned long cpm_muram_alloc(unsigned long size,
+					    unsigned long align)
+{
+	return -ENOSYS;
+}
+
+static inline int cpm_muram_free(unsigned long offset)
+{
+	return -ENOSYS;
+}
+
+static inline unsigned long cpm_muram_alloc_fixed(unsigned long offset,
+						  unsigned long size)
+{
+	return -ENOSYS;
+}
+
+static inline void __iomem *cpm_muram_addr(unsigned long offset)
+{
+	return NULL;
+}
+
+static inline unsigned long cpm_muram_offset(void __iomem *addr)
+{
+	return -ENOSYS;
+}
+
+static inline dma_addr_t cpm_muram_dma(void __iomem *addr)
+{
+	return 0;
+}
+#endif /* defined(CONFIG_CPM) || defined(CONFIG_QUICC_ENGINE) */
+
+#ifdef CONFIG_CPM
 int cpm_command(u32 command, u8 opcode);
+#else
+static inline int cpm_command(u32 command, u8 opcode)
+{
+	return -ENOSYS;
+}
+#endif /* CONFIG_CPM */
 
 int cpm2_gpiochip_add32(struct device_node *np);
 
diff --git a/arch/powerpc/include/asm/cpm1.h b/arch/powerpc/include/asm/cpm1.h
index 7685ffde8821..81b01192f440 100644
--- a/arch/powerpc/include/asm/cpm1.h
+++ b/arch/powerpc/include/asm/cpm1.h
@@ -478,51 +478,6 @@ typedef struct iic {
 	char	res2[2];	/* Reserved */
 } iic_t;
 
-/* SPI parameter RAM.
-*/
-typedef struct spi {
-	ushort	spi_rbase;	/* Rx Buffer descriptor base address */
-	ushort	spi_tbase;	/* Tx Buffer descriptor base address */
-	u_char	spi_rfcr;	/* Rx function code */
-	u_char	spi_tfcr;	/* Tx function code */
-	ushort	spi_mrblr;	/* Max receive buffer length */
-	uint	spi_rstate;	/* Internal */
-	uint	spi_rdp;	/* Internal */
-	ushort	spi_rbptr;	/* Internal */
-	ushort	spi_rbc;	/* Internal */
-	uint	spi_rxtmp;	/* Internal */
-	uint	spi_tstate;	/* Internal */
-	uint	spi_tdp;	/* Internal */
-	ushort	spi_tbptr;	/* Internal */
-	ushort	spi_tbc;	/* Internal */
-	uint	spi_txtmp;	/* Internal */
-	uint	spi_res;
-	ushort	spi_rpbase;	/* Relocation pointer */
-	ushort	spi_res2;
-} spi_t;
-
-/* SPI Mode register.
-*/
-#define SPMODE_LOOP	((ushort)0x4000)	/* Loopback */
-#define SPMODE_CI	((ushort)0x2000)	/* Clock Invert */
-#define SPMODE_CP	((ushort)0x1000)	/* Clock Phase */
-#define SPMODE_DIV16	((ushort)0x0800)	/* BRG/16 mode */
-#define SPMODE_REV	((ushort)0x0400)	/* Reversed Data */
-#define SPMODE_MSTR	((ushort)0x0200)	/* SPI Master */
-#define SPMODE_EN	((ushort)0x0100)	/* Enable */
-#define SPMODE_LENMSK	((ushort)0x00f0)	/* character length */
-#define SPMODE_LEN4	((ushort)0x0030)	/*  4 bits per char */
-#define SPMODE_LEN8	((ushort)0x0070)	/*  8 bits per char */
-#define SPMODE_LEN16	((ushort)0x00f0)	/* 16 bits per char */
-#define SPMODE_PMMSK	((ushort)0x000f)	/* prescale modulus */
-
-/* SPIE fields */
-#define SPIE_MME	0x20
-#define SPIE_TXE	0x10
-#define SPIE_BSY	0x04
-#define SPIE_TXB	0x02
-#define SPIE_RXB	0x01
-
 /*
  * RISC Controller Configuration Register definitons
  */
diff --git a/arch/powerpc/include/asm/cpm2.h b/arch/powerpc/include/asm/cpm2.h
index 990ff191da8b..f42e9baf3a4e 100644
--- a/arch/powerpc/include/asm/cpm2.h
+++ b/arch/powerpc/include/asm/cpm2.h
@@ -124,14 +124,6 @@ static inline void cpm2_fastbrg(uint brg, uint rate, int div16)
 	__cpm2_setbrg(brg, rate, CPM2_BRG_INT_CLK, div16, CPM_BRG_EXTC_INT);
 }
 
-/* Function code bits, usually generic to devices.
-*/
-#define CPMFCR_GBL	((u_char)0x20)	/* Set memory snooping */
-#define CPMFCR_EB	((u_char)0x10)	/* Set big endian byte order */
-#define CPMFCR_TC2	((u_char)0x04)	/* Transfer code 2 value */
-#define CPMFCR_DTB	((u_char)0x02)	/* Use local bus for data when set */
-#define CPMFCR_BDB	((u_char)0x01)	/* Use local bus for BD when set */
-
 /* Parameter RAM offsets from the base.
 */
 #define PROFF_SCC1		((uint)0x8000)
@@ -654,45 +646,6 @@ typedef struct iic {
 	uint	iic_txtmp;	/* Internal */
 } iic_t;
 
-/* SPI parameter RAM.
-*/
-typedef struct spi {
-	ushort	spi_rbase;	/* Rx Buffer descriptor base address */
-	ushort	spi_tbase;	/* Tx Buffer descriptor base address */
-	u_char	spi_rfcr;	/* Rx function code */
-	u_char	spi_tfcr;	/* Tx function code */
-	ushort	spi_mrblr;	/* Max receive buffer length */
-	uint	spi_rstate;	/* Internal */
-	uint	spi_rdp;	/* Internal */
-	ushort	spi_rbptr;	/* Internal */
-	ushort	spi_rbc;	/* Internal */
-	uint	spi_rxtmp;	/* Internal */
-	uint	spi_tstate;	/* Internal */
-	uint	spi_tdp;	/* Internal */
-	ushort	spi_tbptr;	/* Internal */
-	ushort	spi_tbc;	/* Internal */
-	uint	spi_txtmp;	/* Internal */
-	uint	spi_res;	/* Tx temp. */
-	uint	spi_res1[4];	/* SDMA temp. */
-} spi_t;
-
-/* SPI Mode register.
-*/
-#define SPMODE_LOOP	((ushort)0x4000)	/* Loopback */
-#define SPMODE_CI	((ushort)0x2000)	/* Clock Invert */
-#define SPMODE_CP	((ushort)0x1000)	/* Clock Phase */
-#define SPMODE_DIV16	((ushort)0x0800)	/* BRG/16 mode */
-#define SPMODE_REV	((ushort)0x0400)	/* Reversed Data */
-#define SPMODE_MSTR	((ushort)0x0200)	/* SPI Master */
-#define SPMODE_EN	((ushort)0x0100)	/* Enable */
-#define SPMODE_LENMSK	((ushort)0x00f0)	/* character length */
-#define SPMODE_PMMSK	((ushort)0x000f)	/* prescale modulus */
-
-#define SPMODE_LEN(x)	((((x)-1)&0xF)<<4)
-#define SPMODE_PM(x)	((x) &0xF)
-
-#define SPI_EB		((u_char)0x10)		/* big endian byte order */
-
 /* IDMA parameter RAM
 */
 typedef struct idma {
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index fb11b0c459b8..a8e18447c62b 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -5,6 +5,15 @@
 
 /*
  * Mapping of threads to cores
+ *
+ * Note: This implementation is limited to a power of 2 number of
+ * threads per core and the same number for each core in the system
+ * (though it would work if some processors had less threads as long
+ * as the CPU numbers are still allocated, just not brought offline).
+ *
+ * However, the API allows for a different implementation in the future
+ * if needed, as long as you only use the functions and not the variables
+ * directly.
  */
 
 #ifdef CONFIG_SMP
@@ -67,5 +76,12 @@ static inline int cpu_first_thread_in_core(int cpu)
 	return cpu & ~(threads_per_core - 1);
 }
 
+static inline int cpu_last_thread_in_core(int cpu)
+{
+	return cpu | (threads_per_core - 1);
+}
+
+
+
 #endif /* _ASM_POWERPC_CPUTHREADS_H */
 
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index f42e623030ee..fa19f3fe05ff 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -18,6 +18,9 @@
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 #include <asm-generic/cputime.h>
+#ifdef __KERNEL__
+static inline void setup_cputime_one_jiffy(void) { }
+#endif
 #else
 
 #include <linux/types.h>
@@ -49,6 +52,11 @@ typedef u64 cputime64_t;
 #ifdef __KERNEL__
 
 /*
+ * One jiffy in timebase units computed during initialization
+ */
+extern cputime_t cputime_one_jiffy;
+
+/*
  * Convert cputime <-> jiffies
  */
 extern u64 __cputime_jiffies_factor;
@@ -89,6 +97,11 @@ static inline cputime_t jiffies_to_cputime(const unsigned long jif)
 	return ct;
 }
 
+static inline void setup_cputime_one_jiffy(void)
+{
+	cputime_one_jiffy = jiffies_to_cputime(1);
+}
+
 static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
 {
 	cputime_t ct;
diff --git a/arch/powerpc/include/asm/dcr-regs.h b/arch/powerpc/include/asm/dcr-regs.h
index 828e3aa1f2fc..380274de429f 100644
--- a/arch/powerpc/include/asm/dcr-regs.h
+++ b/arch/powerpc/include/asm/dcr-regs.h
@@ -157,4 +157,27 @@
 #define  L2C_SNP_SSR_32G	0x0000f000
 #define  L2C_SNP_ESR		0x00000800
 
+/*
+ * DCR register offsets for 440SP/440SPe I2O/DMA controller.
+ * The base address is configured in the device tree.
+ */
+#define DCRN_I2O0_IBAL		0x006
+#define DCRN_I2O0_IBAH		0x007
+#define I2O_REG_ENABLE		0x00000001	/* Enable I2O/DMA access */
+
+/* 440SP/440SPe Software Reset DCR */
+#define DCRN_SDR0_SRST		0x0200
+#define DCRN_SDR0_SRST_I2ODMA	(0x80000000 >> 15)	/* Reset I2O/DMA */
+
+/* 440SP/440SPe Memory Queue DCR offsets */
+#define DCRN_MQ0_XORBA		0x04
+#define DCRN_MQ0_CF2H		0x06
+#define DCRN_MQ0_CFBHL		0x0f
+#define DCRN_MQ0_BAUH		0x10
+
+/* HB/LL Paths Configuration Register */
+#define MQ0_CFBHL_TPLM		28
+#define MQ0_CFBHL_HBCL		23
+#define MQ0_CFBHL_POLY		15
+
 #endif /* __DCR_REGS_H__ */
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 7d2277cef09a..6d94d27ed850 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -6,7 +6,7 @@
 #ifndef _ASM_POWERPC_DEVICE_H
 #define _ASM_POWERPC_DEVICE_H
 
-struct dma_mapping_ops;
+struct dma_map_ops;
 struct device_node;
 
 struct dev_archdata {
@@ -14,8 +14,20 @@ struct dev_archdata {
 	struct device_node	*of_node;
 
 	/* DMA operations on that device */
-	struct dma_mapping_ops	*dma_ops;
-	void			*dma_data;
+	struct dma_map_ops	*dma_ops;
+
+	/*
+	 * When an iommu is in use, dma_data is used as a ptr to the base of the
+	 * iommu_table.  Otherwise, it is a simple numerical offset.
+	 */
+	union {
+		dma_addr_t	dma_offset;
+		void		*iommu_table_base;
+	} dma_data;
+
+#ifdef CONFIG_SWIOTLB
+	dma_addr_t		max_direct_dma_addr;
+#endif
 };
 
 static inline void dev_archdata_set_node(struct dev_archdata *ad,
@@ -30,4 +42,7 @@ dev_archdata_get_node(const struct dev_archdata *ad)
 	return ad->of_node;
 }
 
+struct pdev_archdata {
+};
+
 #endif /* _ASM_POWERPC_DEVICE_H */
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index b44aaabdd1a6..80a973bb9e71 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -14,6 +14,7 @@
 #include <linux/mm.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-attrs.h>
+#include <linux/dma-debug.h>
 #include <asm/io.h>
 #include <asm/swiotlb.h>
 
@@ -25,7 +26,6 @@ extern void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 extern void dma_direct_free_coherent(struct device *dev, size_t size,
 				     void *vaddr, dma_addr_t dma_handle);
 
-extern unsigned long get_dma_direct_offset(struct device *dev);
 
 #ifdef CONFIG_NOT_COHERENT_CACHE
 /*
@@ -64,58 +64,14 @@ static inline unsigned long device_to_mask(struct device *dev)
 }
 
 /*
- * DMA operations are abstracted for G5 vs. i/pSeries, PCI vs. VIO
- */
-struct dma_mapping_ops {
-	void *		(*alloc_coherent)(struct device *dev, size_t size,
-				dma_addr_t *dma_handle, gfp_t flag);
-	void		(*free_coherent)(struct device *dev, size_t size,
-				void *vaddr, dma_addr_t dma_handle);
-	int		(*map_sg)(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction direction,
-				struct dma_attrs *attrs);
-	void		(*unmap_sg)(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction direction,
-				struct dma_attrs *attrs);
-	int		(*dma_supported)(struct device *dev, u64 mask);
-	int		(*set_dma_mask)(struct device *dev, u64 dma_mask);
-	dma_addr_t 	(*map_page)(struct device *dev, struct page *page,
-				unsigned long offset, size_t size,
-				enum dma_data_direction direction,
-				struct dma_attrs *attrs);
-	void		(*unmap_page)(struct device *dev,
-				dma_addr_t dma_address, size_t size,
-				enum dma_data_direction direction,
-				struct dma_attrs *attrs);
-	int		(*addr_needs_map)(struct device *dev, dma_addr_t addr,
-				size_t size);
-#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS
-	void            (*sync_single_range_for_cpu)(struct device *hwdev,
-				dma_addr_t dma_handle, unsigned long offset,
-				size_t size,
-				enum dma_data_direction direction);
-	void            (*sync_single_range_for_device)(struct device *hwdev,
-				dma_addr_t dma_handle, unsigned long offset,
-				size_t size,
-				enum dma_data_direction direction);
-	void            (*sync_sg_for_cpu)(struct device *hwdev,
-				struct scatterlist *sg, int nelems,
-				enum dma_data_direction direction);
-	void            (*sync_sg_for_device)(struct device *hwdev,
-				struct scatterlist *sg, int nelems,
-				enum dma_data_direction direction);
-#endif
-};
-
-/*
  * Available generic sets of operations
  */
 #ifdef CONFIG_PPC64
-extern struct dma_mapping_ops dma_iommu_ops;
+extern struct dma_map_ops dma_iommu_ops;
 #endif
-extern struct dma_mapping_ops dma_direct_ops;
+extern struct dma_map_ops dma_direct_ops;
 
-static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
 	/* We don't handle the NULL dev case for ISA for now. We could
 	 * do it via an out of line call but it is not needed for now. The
@@ -128,14 +84,41 @@ static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
 	return dev->archdata.dma_ops;
 }
 
-static inline void set_dma_ops(struct device *dev, struct dma_mapping_ops *ops)
+static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
 {
 	dev->archdata.dma_ops = ops;
 }
 
+/*
+ * get_dma_offset()
+ *
+ * Get the dma offset on configurations where the dma address can be determined
+ * from the physical address by looking at a simple offset.  Direct dma and
+ * swiotlb use this function, but it is typically not used by implementations
+ * with an iommu.
+ */
+static inline dma_addr_t get_dma_offset(struct device *dev)
+{
+	if (dev)
+		return dev->archdata.dma_data.dma_offset;
+
+	return PCI_DRAM_OFFSET;
+}
+
+static inline void set_dma_offset(struct device *dev, dma_addr_t off)
+{
+	if (dev)
+		dev->archdata.dma_data.dma_offset = off;
+}
+
+/* this will be removed soon */
+#define flush_write_buffers()
+
+#include <asm-generic/dma-mapping-common.h>
+
 static inline int dma_supported(struct device *dev, u64 mask)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	if (unlikely(dma_ops == NULL))
 		return 0;
@@ -149,7 +132,7 @@ static inline int dma_supported(struct device *dev, u64 mask)
 
 static inline int dma_set_mask(struct device *dev, u64 dma_mask)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	if (unlikely(dma_ops == NULL))
 		return -EIO;
@@ -161,267 +144,70 @@ static inline int dma_set_mask(struct device *dev, u64 dma_mask)
 	return 0;
 }
 
-/*
- * map_/unmap_single actually call through to map/unmap_page now that all the
- * dma_mapping_ops have been converted over. We just have to get the page and
- * offset to pass through to map_page
- */
-static inline dma_addr_t dma_map_single_attrs(struct device *dev,
-					      void *cpu_addr,
-					      size_t size,
-					      enum dma_data_direction direction,
-					      struct dma_attrs *attrs)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	return dma_ops->map_page(dev, virt_to_page(cpu_addr),
-				 (unsigned long)cpu_addr % PAGE_SIZE, size,
-				 direction, attrs);
-}
-
-static inline void dma_unmap_single_attrs(struct device *dev,
-					  dma_addr_t dma_addr,
-					  size_t size,
-					  enum dma_data_direction direction,
-					  struct dma_attrs *attrs)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	dma_ops->unmap_page(dev, dma_addr, size, direction, attrs);
-}
-
-static inline dma_addr_t dma_map_page_attrs(struct device *dev,
-					    struct page *page,
-					    unsigned long offset, size_t size,
-					    enum dma_data_direction direction,
-					    struct dma_attrs *attrs)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	return dma_ops->map_page(dev, page, offset, size, direction, attrs);
-}
-
-static inline void dma_unmap_page_attrs(struct device *dev,
-					dma_addr_t dma_address,
-					size_t size,
-					enum dma_data_direction direction,
-					struct dma_attrs *attrs)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	dma_ops->unmap_page(dev, dma_address, size, direction, attrs);
-}
-
-static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
-				   int nents, enum dma_data_direction direction,
-				   struct dma_attrs *attrs)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-	return dma_ops->map_sg(dev, sg, nents, direction, attrs);
-}
-
-static inline void dma_unmap_sg_attrs(struct device *dev,
-				      struct scatterlist *sg,
-				      int nhwentries,
-				      enum dma_data_direction direction,
-				      struct dma_attrs *attrs)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-	dma_ops->unmap_sg(dev, sg, nhwentries, direction, attrs);
-}
-
 static inline void *dma_alloc_coherent(struct device *dev, size_t size,
 				       dma_addr_t *dma_handle, gfp_t flag)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-	return dma_ops->alloc_coherent(dev, size, dma_handle, flag);
-}
-
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-	dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
-}
-
-static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
-					size_t size,
-					enum dma_data_direction direction)
-{
-	return dma_map_single_attrs(dev, cpu_addr, size, direction, NULL);
-}
-
-static inline void dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
-				    size_t size,
-				    enum dma_data_direction direction)
-{
-	dma_unmap_single_attrs(dev, dma_addr, size, direction, NULL);
-}
-
-static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
-				      unsigned long offset, size_t size,
-				      enum dma_data_direction direction)
-{
-	return dma_map_page_attrs(dev, page, offset, size, direction, NULL);
-}
-
-static inline void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
-				  size_t size,
-				  enum dma_data_direction direction)
-{
-	dma_unmap_page_attrs(dev, dma_address, size, direction, NULL);
-}
-
-static inline int dma_map_sg(struct device *dev, struct scatterlist *sg,
-			     int nents, enum dma_data_direction direction)
-{
-	return dma_map_sg_attrs(dev, sg, nents, direction, NULL);
-}
-
-static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-				int nhwentries,
-				enum dma_data_direction direction)
-{
-	dma_unmap_sg_attrs(dev, sg, nhwentries, direction, NULL);
-}
-
-#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS
-static inline void dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
+	void *cpu_addr;
 
 	BUG_ON(!dma_ops);
 
-	if (dma_ops->sync_single_range_for_cpu)
-		dma_ops->sync_single_range_for_cpu(dev, dma_handle, 0,
-					   size, direction);
-}
+	cpu_addr = dma_ops->alloc_coherent(dev, size, dma_handle, flag);
 
-static inline void dma_sync_single_for_device(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
 
-	BUG_ON(!dma_ops);
-
-	if (dma_ops->sync_single_range_for_device)
-		dma_ops->sync_single_range_for_device(dev, dma_handle,
-					      0, size, direction);
-}
-
-static inline void dma_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents,
-		enum dma_data_direction direction)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	if (dma_ops->sync_sg_for_cpu)
-		dma_ops->sync_sg_for_cpu(dev, sgl, nents, direction);
+	return cpu_addr;
 }
 
-static inline void dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nents,
-		enum dma_data_direction direction)
+static inline void dma_free_coherent(struct device *dev, size_t size,
+				     void *cpu_addr, dma_addr_t dma_handle)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
 
-	if (dma_ops->sync_sg_for_device)
-		dma_ops->sync_sg_for_device(dev, sgl, nents, direction);
-}
-
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
 
-	BUG_ON(!dma_ops);
-
-	if (dma_ops->sync_single_range_for_cpu)
-		dma_ops->sync_single_range_for_cpu(dev, dma_handle,
-					   offset, size, direction);
+	dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
 }
 
-static inline void dma_sync_single_range_for_device(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
+static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
-	BUG_ON(!dma_ops);
+	if (dma_ops->mapping_error)
+		return dma_ops->mapping_error(dev, dma_addr);
 
-	if (dma_ops->sync_single_range_for_device)
-		dma_ops->sync_single_range_for_device(dev, dma_handle, offset,
-					      size, direction);
-}
-#else /* CONFIG_PPC_NEED_DMA_SYNC_OPS */
-static inline void dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
+#ifdef CONFIG_PPC64
+	return (dma_addr == DMA_ERROR_CODE);
+#else
+	return 0;
+#endif
 }
 
-static inline void dma_sync_single_for_device(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 {
-}
+#ifdef CONFIG_SWIOTLB
+	struct dev_archdata *sd = &dev->archdata;
 
-static inline void dma_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents,
-		enum dma_data_direction direction)
-{
-}
+	if (sd->max_direct_dma_addr && addr + size > sd->max_direct_dma_addr)
+		return 0;
+#endif
 
-static inline void dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nents,
-		enum dma_data_direction direction)
-{
-}
+	if (!dev->dma_mask)
+		return 0;
 
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
-{
+	return addr + size - 1 <= *dev->dma_mask;
 }
 
-static inline void dma_sync_single_range_for_device(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
+	return paddr + get_dma_offset(dev);
 }
-#endif
 
-static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
-#ifdef CONFIG_PPC64
-	return (dma_addr == DMA_ERROR_CODE);
-#else
-	return 0;
-#endif
+	return daddr - get_dma_offset(dev);
 }
 
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 014a624f4c8e..c376eda15313 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -170,7 +170,6 @@ typedef elf_fpreg_t elf_vsrreghalf_t32[ELF_NVSRHALFREG];
 #define elf_check_arch(x) ((x)->e_machine == ELF_ARCH)
 #define compat_elf_check_arch(x)	((x)->e_machine == EM_PPC)
 
-#define USE_ELF_CORE_DUMP
 #define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	PAGE_SIZE
 
@@ -236,14 +235,10 @@ typedef elf_vrregset_t elf_fpxregset_t;
 #ifdef __powerpc64__
 # define SET_PERSONALITY(ex)					\
 do {								\
-	unsigned long new_flags = 0;				\
 	if ((ex).e_ident[EI_CLASS] == ELFCLASS32)		\
-		new_flags = _TIF_32BIT;				\
-	if ((current_thread_info()->flags & _TIF_32BIT)		\
-	    != new_flags)					\
-		set_thread_flag(TIF_ABI_PENDING);		\
+		set_thread_flag(TIF_32BIT);			\
 	else							\
-		clear_thread_flag(TIF_ABI_PENDING);		\
+		clear_thread_flag(TIF_32BIT);			\
 	if (personality(current->personality) != PER_LINUX32)	\
 		set_personality(PER_LINUX |			\
 			(current->personality & (~PER_MASK)));	\
diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h
index 9154e8526732..f0fb4fc1f6e6 100644
--- a/arch/powerpc/include/asm/emulated_ops.h
+++ b/arch/powerpc/include/asm/emulated_ops.h
@@ -19,6 +19,7 @@
 #define _ASM_POWERPC_EMULATED_OPS_H
 
 #include <asm/atomic.h>
+#include <linux/perf_event.h>
 
 
 #ifdef CONFIG_PPC_EMULATED_STATS
@@ -57,7 +58,7 @@ extern u32 ppc_warn_emulated;
 
 extern void ppc_warn_emulated_print(const char *type);
 
-#define PPC_WARN_EMULATED(type)						 \
+#define __PPC_WARN_EMULATED(type)					 \
 	do {								 \
 		atomic_inc(&ppc_emulated.type.val);			 \
 		if (ppc_warn_emulated)					 \
@@ -66,8 +67,22 @@ extern void ppc_warn_emulated_print(const char *type);
 
 #else /* !CONFIG_PPC_EMULATED_STATS */
 
-#define PPC_WARN_EMULATED(type)	do { } while (0)
+#define __PPC_WARN_EMULATED(type)	do { } while (0)
 
 #endif /* !CONFIG_PPC_EMULATED_STATS */
 
+#define PPC_WARN_EMULATED(type, regs)					\
+	do {								\
+		perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS,		\
+			1, 0, regs, 0);					\
+		__PPC_WARN_EMULATED(type);				\
+	} while (0)
+
+#define PPC_WARN_ALIGNMENT(type, regs)					\
+	do {								\
+		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS,		\
+			1, 0, regs, regs->dar);				\
+		__PPC_WARN_EMULATED(type);				\
+	} while (0)
+
 #endif /* _ASM_POWERPC_EMULATED_OPS_H */
diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h
new file mode 100644
index 000000000000..6d53f311d942
--- /dev/null
+++ b/arch/powerpc/include/asm/exception-64e.h
@@ -0,0 +1,205 @@
+/*
+ *  Definitions for use by exception code on Book3-E
+ *
+ *  Copyright (C) 2008 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+#ifndef _ASM_POWERPC_EXCEPTION_64E_H
+#define _ASM_POWERPC_EXCEPTION_64E_H
+
+/*
+ * SPRGs usage an other considerations...
+ *
+ * Since TLB miss and other standard exceptions can be interrupted by
+ * critical exceptions which can themselves be interrupted by machine
+ * checks, and since the two later can themselves cause a TLB miss when
+ * hitting the linear mapping for the kernel stacks, we need to be a bit
+ * creative on how we use SPRGs.
+ *
+ * The base idea is that we have one SRPG reserved for critical and one
+ * for machine check interrupts. Those are used to save a GPR that can
+ * then be used to get the PACA, and store as much context as we need
+ * to save in there. That includes saving the SPRGs used by the TLB miss
+ * handler for linear mapping misses and the associated SRR0/1 due to
+ * the above re-entrancy issue.
+ *
+ * So here's the current usage pattern. It's done regardless of which
+ * SPRGs are user-readable though, thus we might have to change some of
+ * this later. In order to do that more easily, we use special constants
+ * for naming them
+ *
+ * WARNING: Some of these SPRGs are user readable. We need to do something
+ * about it as some point by making sure they can't be used to leak kernel
+ * critical data
+ */
+
+
+/* We are out of SPRGs so we save some things in the PACA. The normal
+ * exception frame is smaller than the CRIT or MC one though
+ */
+#define EX_R1		(0 * 8)
+#define EX_CR		(1 * 8)
+#define EX_R10		(2 * 8)
+#define EX_R11		(3 * 8)
+#define EX_R14		(4 * 8)
+#define EX_R15		(5 * 8)
+
+/* The TLB miss exception uses different slots */
+
+#define EX_TLB_R10	( 0 * 8)
+#define EX_TLB_R11	( 1 * 8)
+#define EX_TLB_R12	( 2 * 8)
+#define EX_TLB_R13	( 3 * 8)
+#define EX_TLB_R14	( 4 * 8)
+#define EX_TLB_R15	( 5 * 8)
+#define EX_TLB_R16	( 6 * 8)
+#define EX_TLB_CR	( 7 * 8)
+#define EX_TLB_DEAR	( 8 * 8) /* Level 0 and 2 only */
+#define EX_TLB_ESR	( 9 * 8) /* Level 0 and 2 only */
+#define EX_TLB_SRR0	(10 * 8)
+#define EX_TLB_SRR1	(11 * 8)
+#define EX_TLB_MMUCR0	(12 * 8) /* Level 0 */
+#define EX_TLB_MAS1	(12 * 8) /* Level 0 */
+#define EX_TLB_MAS2	(13 * 8) /* Level 0 */
+#ifdef CONFIG_BOOK3E_MMU_TLB_STATS
+#define EX_TLB_R8	(14 * 8)
+#define EX_TLB_R9	(15 * 8)
+#define EX_TLB_LR	(16 * 8)
+#define EX_TLB_SIZE	(17 * 8)
+#else
+#define EX_TLB_SIZE	(14 * 8)
+#endif
+
+#define	START_EXCEPTION(label)						\
+	.globl exc_##label##_book3e;					\
+exc_##label##_book3e:
+
+/* TLB miss exception prolog
+ *
+ * This prolog handles re-entrancy (up to 3 levels supported in the PACA
+ * though we currently don't test for overflow). It provides you with a
+ * re-entrancy safe working space of r10...r16 and CR with r12 being used
+ * as the exception area pointer in the PACA for that level of re-entrancy
+ * and r13 containing the PACA pointer.
+ *
+ * SRR0 and SRR1 are saved, but DEAR and ESR are not, since they don't apply
+ * as-is for instruction exceptions. It's up to the actual exception code
+ * to save them as well if required.
+ */
+#define TLB_MISS_PROLOG							    \
+	mtspr	SPRN_SPRG_TLB_SCRATCH,r12;				    \
+	mfspr	r12,SPRN_SPRG_TLB_EXFRAME;				    \
+	std	r10,EX_TLB_R10(r12);					    \
+	mfcr	r10;							    \
+	std	r11,EX_TLB_R11(r12);					    \
+	mfspr	r11,SPRN_SPRG_TLB_SCRATCH;				    \
+	std	r13,EX_TLB_R13(r12);					    \
+	mfspr	r13,SPRN_SPRG_PACA;					    \
+	std	r14,EX_TLB_R14(r12);					    \
+	addi	r14,r12,EX_TLB_SIZE;					    \
+	std	r15,EX_TLB_R15(r12);					    \
+	mfspr	r15,SPRN_SRR1;						    \
+	std	r16,EX_TLB_R16(r12);					    \
+	mfspr	r16,SPRN_SRR0;						    \
+	std	r10,EX_TLB_CR(r12);					    \
+	std	r11,EX_TLB_R12(r12);					    \
+	mtspr	SPRN_SPRG_TLB_EXFRAME,r14;				    \
+	std	r15,EX_TLB_SRR1(r12);					    \
+	std	r16,EX_TLB_SRR0(r12);					    \
+	TLB_MISS_PROLOG_STATS
+
+/* And these are the matching epilogs that restores things
+ *
+ * There are 3 epilogs:
+ *
+ * - SUCCESS       : Unwinds one level
+ * - ERROR         : restore from level 0 and reset
+ * - ERROR_SPECIAL : restore from current level and reset
+ *
+ * Normal errors use ERROR, that is, they restore the initial fault context
+ * and trigger a fault. However, there is a special case for linear mapping
+ * errors. Those should basically never happen, but if they do happen, we
+ * want the error to point out the context that did that linear mapping
+ * fault, not the initial level 0 (basically, we got a bogus PGF or something
+ * like that). For userland errors on the linear mapping, there is no
+ * difference since those are always level 0 anyway
+ */
+
+#define TLB_MISS_RESTORE(freg)						    \
+	ld	r14,EX_TLB_CR(r12);					    \
+	ld	r10,EX_TLB_R10(r12);					    \
+	ld	r15,EX_TLB_SRR0(r12);					    \
+	ld	r16,EX_TLB_SRR1(r12);					    \
+	mtspr	SPRN_SPRG_TLB_EXFRAME,freg;				    \
+	ld	r11,EX_TLB_R11(r12);					    \
+	mtcr	r14;							    \
+	ld	r13,EX_TLB_R13(r12);					    \
+	ld	r14,EX_TLB_R14(r12);					    \
+	mtspr	SPRN_SRR0,r15;						    \
+	ld	r15,EX_TLB_R15(r12);					    \
+	mtspr	SPRN_SRR1,r16;						    \
+	TLB_MISS_RESTORE_STATS						    \
+	ld	r16,EX_TLB_R16(r12);					    \
+	ld	r12,EX_TLB_R12(r12);					    \
+
+#define TLB_MISS_EPILOG_SUCCESS						    \
+	TLB_MISS_RESTORE(r12)
+
+#define TLB_MISS_EPILOG_ERROR						    \
+	addi	r12,r13,PACA_EXTLB;					    \
+	TLB_MISS_RESTORE(r12)
+
+#define TLB_MISS_EPILOG_ERROR_SPECIAL					    \
+	addi	r11,r13,PACA_EXTLB;					    \
+	TLB_MISS_RESTORE(r11)
+
+#ifdef CONFIG_BOOK3E_MMU_TLB_STATS
+#define TLB_MISS_PROLOG_STATS						    \
+	mflr	r10;							    \
+	std	r8,EX_TLB_R8(r12);					    \
+	std	r9,EX_TLB_R9(r12);					    \
+	std	r10,EX_TLB_LR(r12);
+#define TLB_MISS_RESTORE_STATS					            \
+	ld	r16,EX_TLB_LR(r12);					    \
+	ld	r9,EX_TLB_R9(r12);					    \
+	ld	r8,EX_TLB_R8(r12);					    \
+	mtlr	r16;
+#define TLB_MISS_STATS_D(name)						    \
+	addi	r9,r13,MMSTAT_DSTATS+name;				    \
+	bl	.tlb_stat_inc;
+#define TLB_MISS_STATS_I(name)						    \
+	addi	r9,r13,MMSTAT_ISTATS+name;				    \
+	bl	.tlb_stat_inc;
+#define TLB_MISS_STATS_X(name)						    \
+	ld	r8,PACA_EXTLB+EX_TLB_ESR(r13);				    \
+	cmpdi	cr2,r8,-1;						    \
+	beq	cr2,61f;						    \
+	addi	r9,r13,MMSTAT_DSTATS+name;				    \
+	b	62f;							    \
+61:	addi	r9,r13,MMSTAT_ISTATS+name;				    \
+62:	bl	.tlb_stat_inc;
+#define TLB_MISS_STATS_SAVE_INFO					    \
+	std	r14,EX_TLB_ESR(r12);	/* save ESR */			    \
+
+
+#else
+#define TLB_MISS_PROLOG_STATS
+#define TLB_MISS_RESTORE_STATS
+#define TLB_MISS_STATS_D(name)
+#define TLB_MISS_STATS_I(name)
+#define TLB_MISS_STATS_X(name)
+#define TLB_MISS_STATS_Y(name)
+#define TLB_MISS_STATS_SAVE_INFO
+#endif
+
+#define SET_IVOR(vector_number, vector_offset)	\
+	li	r3,vector_offset@l; 		\
+	ori	r3,r3,interrupt_base_book3e@l;	\
+	mtspr	SPRN_IVOR##vector_number,r3;
+
+#endif /* _ASM_POWERPC_EXCEPTION_64E_H */
+
diff --git a/arch/powerpc/include/asm/exception.h b/arch/powerpc/include/asm/exception-64s.h
index d3d4534e3c74..57c400071995 100644
--- a/arch/powerpc/include/asm/exception.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -57,17 +57,16 @@
 	addi	reg,reg,(label)-_stext;	/* virt addr of handler ... */
 
 #define EXCEPTION_PROLOG_1(area)				\
-	mfspr	r13,SPRN_SPRG3;		/* get paca address into r13 */	\
+	mfspr	r13,SPRN_SPRG_PACA;	/* get paca address into r13 */	\
 	std	r9,area+EX_R9(r13);	/* save r9 - r12 */		\
 	std	r10,area+EX_R10(r13);					\
 	std	r11,area+EX_R11(r13);					\
 	std	r12,area+EX_R12(r13);					\
-	mfspr	r9,SPRN_SPRG1;						\
+	mfspr	r9,SPRN_SPRG_SCRATCH0;					\
 	std	r9,area+EX_R13(r13);					\
 	mfcr	r9
 
-#define EXCEPTION_PROLOG_PSERIES(area, label)				\
-	EXCEPTION_PROLOG_1(area);					\
+#define EXCEPTION_PROLOG_PSERIES_1(label)				\
 	ld	r12,PACAKBASE(r13);	/* get high part of &label */	\
 	ld	r10,PACAKMSR(r13);	/* get MSR value for kernel */	\
 	mfspr	r11,SPRN_SRR0;		/* save SRR0 */			\
@@ -78,6 +77,10 @@
 	rfid;								\
 	b	.	/* prevent speculative execution */
 
+#define EXCEPTION_PROLOG_PSERIES(area, label)				\
+	EXCEPTION_PROLOG_1(area);					\
+	EXCEPTION_PROLOG_PSERIES_1(label);
+
 /*
  * The common exception prolog is used for all except a few exceptions
  * such as a segment miss on a kernel address.  We have to be prepared
@@ -144,7 +147,8 @@
 	.globl label##_pSeries;				\
 label##_pSeries:					\
 	HMT_MEDIUM;					\
-	mtspr	SPRN_SPRG1,r13;		/* save r13 */	\
+	DO_KVM	n;					\
+	mtspr	SPRN_SPRG_SCRATCH0,r13;		/* save r13 */	\
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common)
 
 #define HSTD_EXCEPTION_PSERIES(n, label)		\
@@ -152,13 +156,13 @@ label##_pSeries:					\
 	.globl label##_pSeries;				\
 label##_pSeries:					\
 	HMT_MEDIUM;					\
-	mtspr	SPRN_SPRG1,r20;		/* save r20 */	\
+	mtspr	SPRN_SPRG_SCRATCH0,r20;	/* save r20 */	\
 	mfspr	r20,SPRN_HSRR0;		/* copy HSRR0 to SRR0 */ \
 	mtspr	SPRN_SRR0,r20;				\
 	mfspr	r20,SPRN_HSRR1;		/* copy HSRR0 to SRR0 */ \
 	mtspr	SPRN_SRR1,r20;				\
-	mfspr	r20,SPRN_SPRG1;		/* restore r20 */ \
-	mtspr	SPRN_SPRG1,r13;		/* save r13 */	\
+	mfspr	r20,SPRN_SPRG_SCRATCH0;	/* restore r20 */ \
+	mtspr	SPRN_SPRG_SCRATCH0,r13;		/* save r13 */	\
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common)
 
 
@@ -167,15 +171,16 @@ label##_pSeries:					\
 	.globl label##_pSeries;						\
 label##_pSeries:							\
 	HMT_MEDIUM;							\
-	mtspr	SPRN_SPRG1,r13;		/* save r13 */			\
-	mfspr	r13,SPRN_SPRG3;		/* get paca address into r13 */	\
+	DO_KVM	n;							\
+	mtspr	SPRN_SPRG_SCRATCH0,r13;	/* save r13 */			\
+	mfspr	r13,SPRN_SPRG_PACA;	/* get paca address into r13 */	\
 	std	r9,PACA_EXGEN+EX_R9(r13);	/* save r9, r10 */	\
 	std	r10,PACA_EXGEN+EX_R10(r13);				\
 	lbz	r10,PACASOFTIRQEN(r13);					\
 	mfcr	r9;							\
 	cmpwi	r10,0;							\
 	beq	masked_interrupt;					\
-	mfspr	r10,SPRN_SPRG1;						\
+	mfspr	r10,SPRN_SPRG_SCRATCH0;					\
 	std	r10,PACA_EXGEN+EX_R13(r13);				\
 	std	r11,PACA_EXGEN+EX_R11(r13);				\
 	std	r12,PACA_EXGEN+EX_R12(r13);				\
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 3a179827528d..20778a405d7a 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -37,7 +37,7 @@
 #define FW_FEATURE_VIO		ASM_CONST(0x0000000000004000)
 #define FW_FEATURE_RDMA		ASM_CONST(0x0000000000008000)
 #define FW_FEATURE_LLAN		ASM_CONST(0x0000000000010000)
-#define FW_FEATURE_BULK		ASM_CONST(0x0000000000020000)
+#define FW_FEATURE_BULK_REMOVE	ASM_CONST(0x0000000000020000)
 #define FW_FEATURE_XDABR	ASM_CONST(0x0000000000040000)
 #define FW_FEATURE_MULTITCE	ASM_CONST(0x0000000000080000)
 #define FW_FEATURE_SPLPAR	ASM_CONST(0x0000000000100000)
@@ -45,8 +45,7 @@
 #define FW_FEATURE_LPAR		ASM_CONST(0x0000000000400000)
 #define FW_FEATURE_PS3_LV1	ASM_CONST(0x0000000000800000)
 #define FW_FEATURE_BEAT		ASM_CONST(0x0000000001000000)
-#define FW_FEATURE_BULK_REMOVE	ASM_CONST(0x0000000002000000)
-#define FW_FEATURE_CMO		ASM_CONST(0x0000000004000000)
+#define FW_FEATURE_CMO		ASM_CONST(0x0000000002000000)
 
 #ifndef __ASSEMBLY__
 
@@ -58,8 +57,9 @@ enum {
 		FW_FEATURE_PERF | FW_FEATURE_DUMP | FW_FEATURE_INTERRUPT |
 		FW_FEATURE_MIGRATE | FW_FEATURE_PERFMON | FW_FEATURE_CRQ |
 		FW_FEATURE_VIO | FW_FEATURE_RDMA | FW_FEATURE_LLAN |
-		FW_FEATURE_BULK | FW_FEATURE_XDABR | FW_FEATURE_MULTITCE |
-		FW_FEATURE_SPLPAR | FW_FEATURE_LPAR | FW_FEATURE_CMO,
+		FW_FEATURE_BULK_REMOVE | FW_FEATURE_XDABR |
+		FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR |
+		FW_FEATURE_CMO,
 	FW_FEATURE_PSERIES_ALWAYS = 0,
 	FW_FEATURE_ISERIES_POSSIBLE = FW_FEATURE_ISERIES | FW_FEATURE_LPAR,
 	FW_FEATURE_ISERIES_ALWAYS = FW_FEATURE_ISERIES | FW_FEATURE_LPAR,
diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h
index f1f4e23a84e9..5c2c0233175e 100644
--- a/arch/powerpc/include/asm/fixmap.h
+++ b/arch/powerpc/include/asm/fixmap.h
@@ -44,6 +44,9 @@
  */
 enum fixed_addresses {
 	FIX_HOLE,
+	/* reserve the top 128K for early debugging purposes */
+	FIX_EARLY_DEBUG_TOP = FIX_HOLE,
+	FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+((128*1024)/PAGE_SIZE)-1,
 #ifdef CONFIG_HIGHMEM
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
 	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
diff --git a/arch/powerpc/include/asm/fsldma.h b/arch/powerpc/include/asm/fsldma.h
new file mode 100644
index 000000000000..a67aeed17d40
--- /dev/null
+++ b/arch/powerpc/include/asm/fsldma.h
@@ -0,0 +1,136 @@
+/*
+ * Freescale MPC83XX / MPC85XX DMA Controller
+ *
+ * Copyright (c) 2009 Ira W. Snyder <iws@ovro.caltech.edu>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#ifndef __ARCH_POWERPC_ASM_FSLDMA_H__
+#define __ARCH_POWERPC_ASM_FSLDMA_H__
+
+#include <linux/dmaengine.h>
+
+/*
+ * Definitions for the Freescale DMA controller's DMA_SLAVE implemention
+ *
+ * The Freescale DMA_SLAVE implementation was designed to handle many-to-many
+ * transfers. An example usage would be an accelerated copy between two
+ * scatterlists. Another example use would be an accelerated copy from
+ * multiple non-contiguous device buffers into a single scatterlist.
+ *
+ * A DMA_SLAVE transaction is defined by a struct fsl_dma_slave. This
+ * structure contains a list of hardware addresses that should be copied
+ * to/from the scatterlist passed into device_prep_slave_sg(). The structure
+ * also has some fields to enable hardware-specific features.
+ */
+
+/**
+ * struct fsl_dma_hw_addr
+ * @entry: linked list entry
+ * @address: the hardware address
+ * @length: length to transfer
+ *
+ * Holds a single physical hardware address / length pair for use
+ * with the DMAEngine DMA_SLAVE API.
+ */
+struct fsl_dma_hw_addr {
+	struct list_head entry;
+
+	dma_addr_t address;
+	size_t length;
+};
+
+/**
+ * struct fsl_dma_slave
+ * @addresses: a linked list of struct fsl_dma_hw_addr structures
+ * @request_count: value for DMA request count
+ * @src_loop_size: setup and enable constant source-address DMA transfers
+ * @dst_loop_size: setup and enable constant destination address DMA transfers
+ * @external_start: enable externally started DMA transfers
+ * @external_pause: enable externally paused DMA transfers
+ *
+ * Holds a list of address / length pairs for use with the DMAEngine
+ * DMA_SLAVE API implementation for the Freescale DMA controller.
+ */
+struct fsl_dma_slave {
+
+	/* List of hardware address/length pairs */
+	struct list_head addresses;
+
+	/* Support for extra controller features */
+	unsigned int request_count;
+	unsigned int src_loop_size;
+	unsigned int dst_loop_size;
+	bool external_start;
+	bool external_pause;
+};
+
+/**
+ * fsl_dma_slave_append - add an address/length pair to a struct fsl_dma_slave
+ * @slave: the &struct fsl_dma_slave to add to
+ * @address: the hardware address to add
+ * @length: the length of bytes to transfer from @address
+ *
+ * Add a hardware address/length pair to a struct fsl_dma_slave. Returns 0 on
+ * success, -ERRNO otherwise.
+ */
+static inline int fsl_dma_slave_append(struct fsl_dma_slave *slave,
+				       dma_addr_t address, size_t length)
+{
+	struct fsl_dma_hw_addr *addr;
+
+	addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
+	if (!addr)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&addr->entry);
+	addr->address = address;
+	addr->length = length;
+
+	list_add_tail(&addr->entry, &slave->addresses);
+	return 0;
+}
+
+/**
+ * fsl_dma_slave_free - free a struct fsl_dma_slave
+ * @slave: the struct fsl_dma_slave to free
+ *
+ * Free a struct fsl_dma_slave and all associated address/length pairs
+ */
+static inline void fsl_dma_slave_free(struct fsl_dma_slave *slave)
+{
+	struct fsl_dma_hw_addr *addr, *tmp;
+
+	if (slave) {
+		list_for_each_entry_safe(addr, tmp, &slave->addresses, entry) {
+			list_del(&addr->entry);
+			kfree(addr);
+		}
+
+		kfree(slave);
+	}
+}
+
+/**
+ * fsl_dma_slave_alloc - allocate a struct fsl_dma_slave
+ * @gfp: the flags to pass to kmalloc when allocating this structure
+ *
+ * Allocate a struct fsl_dma_slave for use by the DMA_SLAVE API. Returns a new
+ * struct fsl_dma_slave on success, or NULL on failure.
+ */
+static inline struct fsl_dma_slave *fsl_dma_slave_alloc(gfp_t gfp)
+{
+	struct fsl_dma_slave *slave;
+
+	slave = kzalloc(sizeof(*slave), gfp);
+	if (!slave)
+		return NULL;
+
+	INIT_LIST_HEAD(&slave->addresses);
+	return slave;
+}
+
+#endif /* __ARCH_POWERPC_ASM_FSLDMA_H__ */
diff --git a/arch/powerpc/include/asm/gpio.h b/arch/powerpc/include/asm/gpio.h
index ea04632399d8..38762edb5e58 100644
--- a/arch/powerpc/include/asm/gpio.h
+++ b/arch/powerpc/include/asm/gpio.h
@@ -38,12 +38,9 @@ static inline int gpio_cansleep(unsigned int gpio)
 	return __gpio_cansleep(gpio);
 }
 
-/*
- * Not implemented, yet.
- */
 static inline int gpio_to_irq(unsigned int gpio)
 {
-	return -ENOSYS;
+	return __gpio_to_irq(gpio);
 }
 
 static inline int irq_to_gpio(unsigned int irq)
diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h
index 288e14d53b7f..fb3c05a0cbbf 100644
--- a/arch/powerpc/include/asm/hardirq.h
+++ b/arch/powerpc/include/asm/hardirq.h
@@ -1,29 +1 @@
-#ifndef _ASM_POWERPC_HARDIRQ_H
-#define _ASM_POWERPC_HARDIRQ_H
-#ifdef __KERNEL__
-
-#include <asm/irq.h>
-#include <asm/bug.h>
-
-/* The __last_jiffy_stamp field is needed to ensure that no decrementer
- * interrupt is lost on SMP machines. Since on most CPUs it is in the same
- * cache line as local_irq_count, it is cheap to access and is also used on UP
- * for uniformity.
- */
-typedef struct {
-	unsigned int __softirq_pending;	/* set_bit is used on this */
-	unsigned int __last_jiffy_stamp;
-} ____cacheline_aligned irq_cpustat_t;
-
-#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
-
-#define last_jiffy_stamp(cpu) __IRQ_STAT((cpu), __last_jiffy_stamp)
-
-static inline void ack_bad_irq(int irq)
-{
-	printk(KERN_CRIT "illegal vector %d received!\n", irq);
-	BUG();
-}
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_POWERPC_HARDIRQ_H */
+#include <asm-generic/hardirq.h>
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index b1dafb6a9743..5856a66ab404 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -3,6 +3,10 @@
 
 #include <asm/page.h>
 
+pte_t *huge_pte_offset_and_shift(struct mm_struct *mm,
+				 unsigned long addr, unsigned *shift);
+
+void flush_dcache_icache_hugepage(struct page *page);
 
 int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
 			   unsigned long len);
@@ -11,12 +15,6 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 			    unsigned long end, unsigned long floor,
 			    unsigned long ceiling);
 
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-		     pte_t *ptep, pte_t pte);
-
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep);
-
 /*
  * The version of vma_mmu_pagesize() in arch/powerpc/mm/hugetlbpage.c needs
  * to override the version in mm/hugetlb.c
@@ -42,9 +40,26 @@ static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
 {
 }
 
+
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+	set_pte_at(mm, addr, ptep, pte);
+}
+
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep)
+{
+	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 1);
+	return __pte(old);
+}
+
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
+	pte_t pte;
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	flush_tlb_page(vma, addr);
 }
 
 static inline int huge_pte_none(pte_t pte)
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 6251a4b10be7..f0275818b95c 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -212,6 +212,19 @@
 #define H_QUERY_INT_STATE       0x1E4
 #define H_POLL_PENDING		0x1D8
 #define H_ILLAN_ATTRIBUTES	0x244
+#define H_MODIFY_HEA_QP		0x250
+#define H_QUERY_HEA_QP		0x254
+#define H_QUERY_HEA		0x258
+#define H_QUERY_HEA_PORT	0x25C
+#define H_MODIFY_HEA_PORT	0x260
+#define H_REG_BCMC		0x264
+#define H_DEREG_BCMC		0x268
+#define H_REGISTER_HEA_RPAGES	0x26C
+#define H_DISABLE_AND_GET_HEA	0x270
+#define H_GET_HEA_INFO		0x274
+#define H_ALLOC_HEA_RESOURCE	0x278
+#define H_ADD_CONN		0x284
+#define H_DEL_CONN		0x288
 #define H_JOIN			0x298
 #define H_VASI_STATE            0x2A4
 #define H_ENABLE_CRQ		0x2B0
@@ -274,6 +287,8 @@ struct hcall_stats {
 	unsigned long	num_calls;	/* number of calls (on this CPU) */
 	unsigned long	tb_total;	/* total wall time (mftb) of calls. */
 	unsigned long	purr_total;	/* total cpu time (PURR) of calls. */
+	unsigned long	tb_start;
+	unsigned long	purr_start;
 };
 #define HCALL_STAT_ARRAY_SIZE	((MAX_HCALL_OPCODE >> 2) + 1)
 
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 8b505eaaa38a..9f4c9d4f5803 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -49,8 +49,13 @@ extern void iseries_handle_interrupts(void);
 #define raw_irqs_disabled()		(local_get_flags() == 0)
 #define raw_irqs_disabled_flags(flags)	((flags) == 0)
 
+#ifdef CONFIG_PPC_BOOK3E
+#define __hard_irq_enable()	__asm__ __volatile__("wrteei 1": : :"memory");
+#define __hard_irq_disable()	__asm__ __volatile__("wrteei 0": : :"memory");
+#else
 #define __hard_irq_enable()	__mtmsrd(mfmsr() | MSR_EE, 1)
 #define __hard_irq_disable()	__mtmsrd(mfmsr() & ~MSR_EE, 1)
+#endif
 
 #define  hard_irq_disable()			\
 	do {					\
@@ -59,11 +64,6 @@ extern void iseries_handle_interrupts(void);
 		get_paca()->hard_enabled = 0;	\
 	} while(0)
 
-static inline int irqs_disabled_flags(unsigned long flags)
-{
-	return flags == 0;
-}
-
 #else
 
 #if defined(CONFIG_BOOKE)
@@ -130,43 +130,43 @@ static inline int irqs_disabled_flags(unsigned long flags)
  */
 struct irq_chip;
 
-#ifdef CONFIG_PERF_COUNTERS
+#ifdef CONFIG_PERF_EVENTS
 
 #ifdef CONFIG_PPC64
-static inline unsigned long test_perf_counter_pending(void)
+static inline unsigned long test_perf_event_pending(void)
 {
 	unsigned long x;
 
 	asm volatile("lbz %0,%1(13)"
 		: "=r" (x)
-		: "i" (offsetof(struct paca_struct, perf_counter_pending)));
+		: "i" (offsetof(struct paca_struct, perf_event_pending)));
 	return x;
 }
 
-static inline void set_perf_counter_pending(void)
+static inline void set_perf_event_pending(void)
 {
 	asm volatile("stb %0,%1(13)" : :
 		"r" (1),
-		"i" (offsetof(struct paca_struct, perf_counter_pending)));
+		"i" (offsetof(struct paca_struct, perf_event_pending)));
 }
 
-static inline void clear_perf_counter_pending(void)
+static inline void clear_perf_event_pending(void)
 {
 	asm volatile("stb %0,%1(13)" : :
 		"r" (0),
-		"i" (offsetof(struct paca_struct, perf_counter_pending)));
+		"i" (offsetof(struct paca_struct, perf_event_pending)));
 }
 #endif /* CONFIG_PPC64 */
 
-#else  /* CONFIG_PERF_COUNTERS */
+#else  /* CONFIG_PERF_EVENTS */
 
-static inline unsigned long test_perf_counter_pending(void)
+static inline unsigned long test_perf_event_pending(void)
 {
 	return 0;
 }
 
-static inline void clear_perf_counter_pending(void) {}
-#endif /* CONFIG_PERF_COUNTERS */
+static inline void clear_perf_event_pending(void) {}
+#endif /* CONFIG_PERF_EVENTS */
 
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_POWERPC_HW_IRQ_H */
diff --git a/arch/powerpc/include/asm/immap_cpm2.h b/arch/powerpc/include/asm/immap_cpm2.h
index d4f069bf0e57..7c64fda5357b 100644
--- a/arch/powerpc/include/asm/immap_cpm2.h
+++ b/arch/powerpc/include/asm/immap_cpm2.h
@@ -549,7 +549,7 @@ typedef struct comm_proc {
 
 /* USB Controller.
 */
-typedef struct usb_ctlr {
+typedef struct cpm_usb_ctlr {
 	u8	usb_usmod;
 	u8	usb_usadr;
 	u8	usb_uscom;
diff --git a/arch/powerpc/include/asm/immap_qe.h b/arch/powerpc/include/asm/immap_qe.h
index c346d0bcd230..4e10f508570a 100644
--- a/arch/powerpc/include/asm/immap_qe.h
+++ b/arch/powerpc/include/asm/immap_qe.h
@@ -210,7 +210,7 @@ struct sir {
 } __attribute__ ((packed));
 
 /* USB Controller */
-struct usb_ctlr {
+struct qe_usb_ctlr {
 	u8	usb_usmod;
 	u8	usb_usadr;
 	u8	usb_uscom;
@@ -229,7 +229,7 @@ struct usb_ctlr {
 } __attribute__ ((packed));
 
 /* MCC */
-struct mcc {
+struct qe_mcc {
 	__be32	mcce;		/* MCC event register */
 	__be32	mccm;		/* MCC mask register */
 	__be32	mccf;		/* MCC configuration register */
@@ -431,9 +431,9 @@ struct qe_immap {
 	struct qe_mux		qmx;		/* QE Multiplexer */
 	struct qe_timers	qet;		/* QE Timers */
 	struct spi		spi[0x2];	/* spi */
-	struct mcc		mcc;		/* mcc */
+	struct qe_mcc		mcc;		/* mcc */
 	struct qe_brg		brg;		/* brg */
-	struct usb_ctlr		usb;		/* USB */
+	struct qe_usb_ctlr	usb;		/* USB */
 	struct si1		si1;		/* SI */
 	u8			res11[0x800];
 	struct sir		sir;		/* SI Routing Tables */
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 7ead7c16fb7c..edfc9803ec91 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -35,16 +35,6 @@
 #define IOMMU_PAGE_MASK       (~((1 << IOMMU_PAGE_SHIFT) - 1))
 #define IOMMU_PAGE_ALIGN(addr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE)
 
-/* Cell page table entries */
-#define CBE_IOPTE_PP_W		0x8000000000000000ul /* protection: write */
-#define CBE_IOPTE_PP_R		0x4000000000000000ul /* protection: read */
-#define CBE_IOPTE_M		0x2000000000000000ul /* coherency required */
-#define CBE_IOPTE_SO_R		0x1000000000000000ul /* ordering: writes */
-#define CBE_IOPTE_SO_RW		0x1800000000000000ul /* ordering: r & w */
-#define CBE_IOPTE_RPN_Mask	0x07fffffffffff000ul /* RPN */
-#define CBE_IOPTE_H		0x0000000000000800ul /* cache hint */
-#define CBE_IOPTE_IOID_Mask	0x00000000000007fful /* ioid */
-
 /* Boot time flags */
 extern int iommu_is_off;
 extern int iommu_force_on;
@@ -80,6 +70,16 @@ struct iommu_table {
 
 struct scatterlist;
 
+static inline void set_iommu_table_base(struct device *dev, void *base)
+{
+	dev->archdata.dma_data.iommu_table_base = base;
+}
+
+static inline void *get_iommu_table_base(struct device *dev)
+{
+	return dev->archdata.dma_data.iommu_table_base;
+}
+
 /* Frees table for an individual device node */
 extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
 
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 0a5137676e1b..e054baef1845 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -17,8 +17,6 @@
 #include <asm/atomic.h>
 
 
-#define get_irq_desc(irq) (&irq_desc[(irq)])
-
 /* Define a way to iterate across irqs. */
 #define for_each_irq(i) \
 	for ((i) = 0; (i) < NR_IRQS; ++(i))
@@ -34,12 +32,15 @@ extern atomic_t ppc_n_lost_interrupts;
  */
 #define NO_IRQ_IGNORE		((unsigned int)-1)
 
-/* Total number of virq in the platform (make it a CONFIG_* option ? */
-#define NR_IRQS		512
+/* Total number of virq in the platform */
+#define NR_IRQS		CONFIG_NR_IRQS
 
 /* Number of irqs reserved for the legacy controller */
 #define NUM_ISA_INTERRUPTS	16
 
+/* Same thing, used by the generic IRQ code */
+#define NR_IRQS_LEGACY		NUM_ISA_INTERRUPTS
+
 /* This type is the placeholder for a hardware interrupt number. It has to
  * be big enough to enclose whatever representation is used by a given
  * platform.
@@ -99,7 +100,7 @@ struct irq_host_ops {
 	 * interrupt controller has for that line)
 	 */
 	int (*xlate)(struct irq_host *h, struct device_node *ctrler,
-		     u32 *intspec, unsigned int intsize,
+		     const u32 *intspec, unsigned int intsize,
 		     irq_hw_number_t *out_hwirq, unsigned int *out_type);
 };
 
@@ -302,7 +303,8 @@ extern void irq_free_virt(unsigned int virq, unsigned int count);
 
 /* -- OF helpers -- */
 
-/* irq_create_of_mapping - Map a hardware interrupt into linux virq space
+/**
+ * irq_create_of_mapping - Map a hardware interrupt into linux virq space
  * @controller: Device node of the interrupt controller
  * @inspec: Interrupt specifier from the device-tree
  * @intsize: Size of the interrupt specifier from the device-tree
@@ -312,10 +314,10 @@ extern void irq_free_virt(unsigned int virq, unsigned int count);
  * of the of_irq_map_*() functions.
  */
 extern unsigned int irq_create_of_mapping(struct device_node *controller,
-					  u32 *intspec, unsigned int intsize);
+					  const u32 *intspec, unsigned int intsize);
 
-
-/* irq_of_parse_and_map - Parse nad Map an interrupt into linux virq space
+/**
+ * irq_of_parse_and_map - Parse and Map an interrupt into linux virq space
  * @device: Device node of the device whose interrupt is to be mapped
  * @index: Index of the interrupt to map
  *
diff --git a/arch/powerpc/include/asm/kmap_types.h b/arch/powerpc/include/asm/kmap_types.h
index b6bac6f61c16..916369575c97 100644
--- a/arch/powerpc/include/asm/kmap_types.h
+++ b/arch/powerpc/include/asm/kmap_types.h
@@ -29,5 +29,16 @@ enum km_type {
 	KM_TYPE_NR
 };
 
+/*
+ * This is a temporary build fix that (so they say on lkml....) should no longer
+ * be required after 2.6.33, because of changes planned to the kmap code.
+ * Let's try to remove this cruft then.
+ */
+#ifdef CONFIG_DEBUG_HIGHMEM
+#define KM_NMI		(-1)
+#define KM_NMI_PTE	(-1)
+#define KM_IRQ_PTE	(-1)
+#endif
+
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_POWERPC_KMAP_TYPES_H */
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index bb2de6aa5ce0..81f3b0b5601e 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -46,6 +46,24 @@ struct kvm_regs {
 };
 
 struct kvm_sregs {
+	__u32 pvr;
+	union {
+		struct {
+			__u64 sdr1;
+			struct {
+				struct {
+					__u64 slbe;
+					__u64 slbv;
+				} slb[64];
+			} ppc64;
+			struct {
+				__u32 sr[16];
+				__u64 ibat[8]; 
+				__u64 dbat[8]; 
+			} ppc32;
+		} s;
+		__u8 pad[1020];
+	} u;
 };
 
 struct kvm_fpu {
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 56bfae59837f..af2abe74f544 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -49,6 +49,46 @@
 #define BOOKE_INTERRUPT_SPE_FP_ROUND 34
 #define BOOKE_INTERRUPT_PERFORMANCE_MONITOR 35
 
+/* book3s */
+
+#define BOOK3S_INTERRUPT_SYSTEM_RESET	0x100
+#define BOOK3S_INTERRUPT_MACHINE_CHECK	0x200
+#define BOOK3S_INTERRUPT_DATA_STORAGE	0x300
+#define BOOK3S_INTERRUPT_DATA_SEGMENT	0x380
+#define BOOK3S_INTERRUPT_INST_STORAGE	0x400
+#define BOOK3S_INTERRUPT_INST_SEGMENT	0x480
+#define BOOK3S_INTERRUPT_EXTERNAL	0x500
+#define BOOK3S_INTERRUPT_ALIGNMENT	0x600
+#define BOOK3S_INTERRUPT_PROGRAM	0x700
+#define BOOK3S_INTERRUPT_FP_UNAVAIL	0x800
+#define BOOK3S_INTERRUPT_DECREMENTER	0x900
+#define BOOK3S_INTERRUPT_SYSCALL	0xc00
+#define BOOK3S_INTERRUPT_TRACE		0xd00
+#define BOOK3S_INTERRUPT_PERFMON	0xf00
+#define BOOK3S_INTERRUPT_ALTIVEC	0xf20
+#define BOOK3S_INTERRUPT_VSX		0xf40
+
+#define BOOK3S_IRQPRIO_SYSTEM_RESET		0
+#define BOOK3S_IRQPRIO_DATA_SEGMENT		1
+#define BOOK3S_IRQPRIO_INST_SEGMENT		2
+#define BOOK3S_IRQPRIO_DATA_STORAGE		3
+#define BOOK3S_IRQPRIO_INST_STORAGE		4
+#define BOOK3S_IRQPRIO_ALIGNMENT		5
+#define BOOK3S_IRQPRIO_PROGRAM			6
+#define BOOK3S_IRQPRIO_FP_UNAVAIL		7
+#define BOOK3S_IRQPRIO_ALTIVEC			8
+#define BOOK3S_IRQPRIO_VSX			9
+#define BOOK3S_IRQPRIO_SYSCALL			10
+#define BOOK3S_IRQPRIO_MACHINE_CHECK		11
+#define BOOK3S_IRQPRIO_DEBUG			12
+#define BOOK3S_IRQPRIO_EXTERNAL			13
+#define BOOK3S_IRQPRIO_DECREMENTER		14
+#define BOOK3S_IRQPRIO_PERFORMANCE_MONITOR	15
+#define BOOK3S_IRQPRIO_MAX			16
+
+#define BOOK3S_HFLAG_DCBZ32			0x1
+#define BOOK3S_HFLAG_SLB			0x2
+
 #define RESUME_FLAG_NV          (1<<0)  /* Reload guest nonvolatile state? */
 #define RESUME_FLAG_HOST        (1<<1)  /* Resume host? */
 
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
new file mode 100644
index 000000000000..74b7369770d0
--- /dev/null
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -0,0 +1,139 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright SUSE Linux Products GmbH 2009
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#ifndef __ASM_KVM_BOOK3S_H__
+#define __ASM_KVM_BOOK3S_H__
+
+#include <linux/types.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_ppc.h>
+
+struct kvmppc_slb {
+	u64 esid;
+	u64 vsid;
+	u64 orige;
+	u64 origv;
+	bool valid;
+	bool Ks;
+	bool Kp;
+	bool nx;
+	bool large;
+	bool class;
+};
+
+struct kvmppc_sr {
+	u32 raw;
+	u32 vsid;
+	bool Ks;
+	bool Kp;
+	bool nx;
+};
+
+struct kvmppc_bat {
+	u64 raw;
+	u32 bepi;
+	u32 bepi_mask;
+	bool vs;
+	bool vp;
+	u32 brpn;
+	u8 wimg;
+	u8 pp;
+};
+
+struct kvmppc_sid_map {
+	u64 guest_vsid;
+	u64 guest_esid;
+	u64 host_vsid;
+	bool valid;
+};
+
+#define SID_MAP_BITS    9
+#define SID_MAP_NUM     (1 << SID_MAP_BITS)
+#define SID_MAP_MASK    (SID_MAP_NUM - 1)
+
+struct kvmppc_vcpu_book3s {
+	struct kvm_vcpu vcpu;
+	struct kvmppc_sid_map sid_map[SID_MAP_NUM];
+	struct kvmppc_slb slb[64];
+	struct {
+		u64 esid;
+		u64 vsid;
+	} slb_shadow[64];
+	u8 slb_shadow_max;
+	struct kvmppc_sr sr[16];
+	struct kvmppc_bat ibat[8];
+	struct kvmppc_bat dbat[8];
+	u64 hid[6];
+	int slb_nr;
+	u64 sdr1;
+	u64 dsisr;
+	u64 hior;
+	u64 msr_mask;
+	u64 vsid_first;
+	u64 vsid_next;
+	u64 vsid_max;
+	int context_id;
+};
+
+#define CONTEXT_HOST		0
+#define CONTEXT_GUEST		1
+#define CONTEXT_GUEST_END	2
+
+#define VSID_REAL	0xfffffffffff00000
+#define VSID_REAL_DR	0xffffffffffe00000
+#define VSID_REAL_IR	0xffffffffffd00000
+#define VSID_BAT	0xffffffffffc00000
+#define VSID_PR		0x8000000000000000
+
+extern void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, u64 ea, u64 ea_mask);
+extern void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 vp, u64 vp_mask);
+extern void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, u64 pa_start, u64 pa_end);
+extern void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 new_msr);
+extern void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu);
+extern void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu);
+extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte);
+extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr);
+extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu);
+extern struct kvmppc_pte *kvmppc_mmu_find_pte(struct kvm_vcpu *vcpu, u64 ea, bool data);
+extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr, bool data);
+extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr);
+extern void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec);
+extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
+			   bool upper, u32 val);
+
+extern u32 kvmppc_trampoline_lowmem;
+extern u32 kvmppc_trampoline_enter;
+
+static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
+{
+	return container_of(vcpu, struct kvmppc_vcpu_book3s, vcpu);
+}
+
+static inline ulong dsisr(void)
+{
+	ulong r;
+	asm ( "mfdsisr %0 " : "=r" (r) );
+	return r;
+}
+
+extern void kvm_return_point(void);
+
+#define INS_DCBZ			0x7c0007ec
+
+#endif /* __ASM_KVM_BOOK3S_H__ */
diff --git a/arch/powerpc/include/asm/kvm_book3s_64_asm.h b/arch/powerpc/include/asm/kvm_book3s_64_asm.h
new file mode 100644
index 000000000000..2e06ee8184ef
--- /dev/null
+++ b/arch/powerpc/include/asm/kvm_book3s_64_asm.h
@@ -0,0 +1,58 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright SUSE Linux Products GmbH 2009
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#ifndef __ASM_KVM_BOOK3S_ASM_H__
+#define __ASM_KVM_BOOK3S_ASM_H__
+
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+
+#include <asm/kvm_asm.h>
+
+.macro DO_KVM intno
+	.if (\intno == BOOK3S_INTERRUPT_SYSTEM_RESET) || \
+	    (\intno == BOOK3S_INTERRUPT_MACHINE_CHECK) || \
+	    (\intno == BOOK3S_INTERRUPT_DATA_STORAGE) || \
+	    (\intno == BOOK3S_INTERRUPT_INST_STORAGE) || \
+	    (\intno == BOOK3S_INTERRUPT_DATA_SEGMENT) || \
+	    (\intno == BOOK3S_INTERRUPT_INST_SEGMENT) || \
+	    (\intno == BOOK3S_INTERRUPT_EXTERNAL) || \
+	    (\intno == BOOK3S_INTERRUPT_ALIGNMENT) || \
+	    (\intno == BOOK3S_INTERRUPT_PROGRAM) || \
+	    (\intno == BOOK3S_INTERRUPT_FP_UNAVAIL) || \
+	    (\intno == BOOK3S_INTERRUPT_DECREMENTER) || \
+	    (\intno == BOOK3S_INTERRUPT_SYSCALL) || \
+	    (\intno == BOOK3S_INTERRUPT_TRACE) || \
+	    (\intno == BOOK3S_INTERRUPT_PERFMON) || \
+	    (\intno == BOOK3S_INTERRUPT_ALTIVEC) || \
+	    (\intno == BOOK3S_INTERRUPT_VSX)
+
+	b	kvmppc_trampoline_\intno
+kvmppc_resume_\intno:
+
+	.endif
+.endm
+
+#else
+
+.macro DO_KVM intno
+.endm
+
+#endif /* CONFIG_KVM_BOOK3S_64_HANDLER */
+
+#endif /* __ASM_KVM_BOOK3S_ASM_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index fddc3ed715fa..1201f62d0d73 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -21,7 +21,8 @@
 #define __POWERPC_KVM_HOST_H__
 
 #include <linux/mutex.h>
-#include <linux/timer.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
 #include <linux/types.h>
 #include <linux/kvm_types.h>
 #include <asm/kvm_asm.h>
@@ -34,7 +35,10 @@
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 
 /* We don't currently support large pages. */
-#define KVM_PAGES_PER_HPAGE (1UL << 31)
+#define KVM_NR_PAGE_SIZES	1
+#define KVM_PAGES_PER_HPAGE(x)	(1UL<<31)
+
+#define HPTEG_CACHE_NUM 1024
 
 struct kvm;
 struct kvm_run;
@@ -62,6 +66,17 @@ struct kvm_vcpu_stat {
 	u32 dec_exits;
 	u32 ext_intr_exits;
 	u32 halt_wakeup;
+#ifdef CONFIG_PPC64
+	u32 pf_storage;
+	u32 pf_instruc;
+	u32 sp_storage;
+	u32 sp_instruc;
+	u32 queue_intr;
+	u32 ld;
+	u32 ld_slow;
+	u32 st;
+	u32 st_slow;
+#endif
 };
 
 enum kvm_exit_types {
@@ -108,9 +123,53 @@ struct kvmppc_exit_timing {
 struct kvm_arch {
 };
 
+struct kvmppc_pte {
+	u64 eaddr;
+	u64 vpage;
+	u64 raddr;
+	bool may_read;
+	bool may_write;
+	bool may_execute;
+};
+
+struct kvmppc_mmu {
+	/* book3s_64 only */
+	void (*slbmte)(struct kvm_vcpu *vcpu, u64 rb, u64 rs);
+	u64  (*slbmfee)(struct kvm_vcpu *vcpu, u64 slb_nr);
+	u64  (*slbmfev)(struct kvm_vcpu *vcpu, u64 slb_nr);
+	void (*slbie)(struct kvm_vcpu *vcpu, u64 slb_nr);
+	void (*slbia)(struct kvm_vcpu *vcpu);
+	/* book3s */
+	void (*mtsrin)(struct kvm_vcpu *vcpu, u32 srnum, ulong value);
+	u32  (*mfsrin)(struct kvm_vcpu *vcpu, u32 srnum);
+	int  (*xlate)(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *pte, bool data);
+	void (*reset_msr)(struct kvm_vcpu *vcpu);
+	void (*tlbie)(struct kvm_vcpu *vcpu, ulong addr, bool large);
+	int  (*esid_to_vsid)(struct kvm_vcpu *vcpu, u64 esid, u64 *vsid);
+	u64  (*ea_to_vp)(struct kvm_vcpu *vcpu, gva_t eaddr, bool data);
+	bool (*is_dcbz32)(struct kvm_vcpu *vcpu);
+};
+
+struct hpte_cache {
+	u64 host_va;
+	u64 pfn;
+	ulong slot;
+	struct kvmppc_pte pte;
+};
+
 struct kvm_vcpu_arch {
-	u32 host_stack;
+	ulong host_stack;
 	u32 host_pid;
+#ifdef CONFIG_PPC64
+	ulong host_msr;
+	ulong host_r2;
+	void *host_retip;
+	ulong trampoline_lowmem;
+	ulong trampoline_enter;
+	ulong highmem_handler;
+	ulong host_paca_phys;
+	struct kvmppc_mmu mmu;
+#endif
 
 	u64 fpr[32];
 	ulong gpr[32];
@@ -122,6 +181,10 @@ struct kvm_vcpu_arch {
 	ulong xer;
 
 	ulong msr;
+#ifdef CONFIG_PPC64
+	ulong shadow_msr;
+	ulong hflags;
+#endif
 	u32 mmucr;
 	ulong sprg0;
 	ulong sprg1;
@@ -148,12 +211,12 @@ struct kvm_vcpu_arch {
 	u32 ivor[64];
 	ulong ivpr;
 	u32 pir;
+	u32 pvr;
 
 	u32 shadow_pid;
 	u32 pid;
 	u32 swap_pid;
 
-	u32 pvr;
 	u32 ccr0;
 	u32 ccr1;
 	u32 dbcr0;
@@ -174,6 +237,9 @@ struct kvm_vcpu_arch {
 #endif
 
 	u32 last_inst;
+#ifdef CONFIG_PPC64
+	ulong fault_dsisr;
+#endif
 	ulong fault_dear;
 	ulong fault_esr;
 	gpa_t paddr_accessed;
@@ -185,8 +251,15 @@ struct kvm_vcpu_arch {
 
 	u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */
 
-	struct timer_list dec_timer;
+	struct hrtimer dec_timer;
+	struct tasklet_struct tasklet;
+	u64 dec_jiffies;
 	unsigned long pending_exceptions;
+
+#ifdef CONFIG_PPC64
+	struct hpte_cache hpte_cache[HPTEG_CACHE_NUM];
+	int hpte_cache_offset;
+#endif
 };
 
 #endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 2c6ee349df5e..269ee46ab028 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -39,6 +39,7 @@ enum emulation_result {
 extern int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
 extern char kvmppc_handlers_start[];
 extern unsigned long kvmppc_handler_len;
+extern void kvmppc_handler_highmem(void);
 
 extern void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu);
 extern int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index f78f65c38f05..14b592dfb4e8 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -100,7 +100,14 @@ struct lppaca {
 	// Used to pass parms from the OS to PLIC for SetAsrAndRfid
 	u64	saved_gpr3;		// Saved GPR3                   x20-x27
 	u64	saved_gpr4;		// Saved GPR4                   x28-x2F
-	u64	saved_gpr5;		// Saved GPR5                   x30-x37
+	union {
+		u64	saved_gpr5;	/* Saved GPR5               x30-x37 */
+		struct {
+			u8	cede_latency_hint;  /*			x30 */
+			u8	reserved[7];        /*		    x31-x36 */
+		} fields;
+	} gpr5_dword;
+
 
 	u8	dtl_enable_mask;	// Dispatch Trace Log mask	x38-x38
 	u8	donate_dedicated_cpu;	// Donate dedicated CPU cycles  x39-x39
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 11d1fc3a8962..9f0fc9e6ce0d 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -209,14 +209,14 @@ struct machdep_calls {
 	/*
 	 * optional PCI "hooks"
 	 */
-	/* Called in indirect_* to avoid touching devices */
-	int (*pci_exclude_device)(struct pci_controller *, unsigned char, unsigned char);
-
 	/* Called at then very end of pcibios_init() */
 	void (*pcibios_after_init)(void);
 
 #endif /* CONFIG_PPC32 */
 
+	/* Called in indirect_* to avoid touching devices */
+	int (*pci_exclude_device)(struct pci_controller *, unsigned char, unsigned char);
+
 	/* Called after PPC generic resource fixup to perform
 	   machine specific fixups */
 	void (*pcibios_fixup_resources)(struct pci_dev *);
@@ -266,6 +266,11 @@ struct machdep_calls {
 	void (*suspend_disable_irqs)(void);
 	void (*suspend_enable_irqs)(void);
 #endif
+
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+	ssize_t (*cpu_probe)(const char *, size_t);
+	ssize_t (*cpu_release)(const char *, size_t);
+#endif
 };
 
 extern void e500_idle(void);
diff --git a/arch/powerpc/include/asm/macio.h b/arch/powerpc/include/asm/macio.h
index 079c06eae446..a062c57696d0 100644
--- a/arch/powerpc/include/asm/macio.h
+++ b/arch/powerpc/include/asm/macio.h
@@ -39,6 +39,7 @@ struct macio_dev
 	struct macio_bus	*bus;		/* macio bus this device is on */
 	struct macio_dev	*media_bay;	/* Device is part of a media bay */
 	struct of_device	ofdev;
+	struct device_dma_parameters dma_parms; /* ide needs that */
 	int			n_resources;
 	struct resource		resource[MACIO_DEV_COUNT_RESOURCES];
 	int			n_interrupts;
@@ -78,6 +79,8 @@ static inline unsigned long macio_resource_len(struct macio_dev *dev, int resour
 	return res->end - res->start + 1;
 }
 
+extern int macio_enable_devres(struct macio_dev *dev);
+
 extern int macio_request_resource(struct macio_dev *dev, int resource_no, const char *name);
 extern void macio_release_resource(struct macio_dev *dev, int resource_no);
 extern int macio_request_resources(struct macio_dev *dev, const char *name);
@@ -131,6 +134,9 @@ struct macio_driver
 	int	(*resume)(struct macio_dev* dev);
 	int	(*shutdown)(struct macio_dev* dev);
 
+#ifdef CONFIG_PMAC_MEDIABAY
+	void	(*mediabay_event)(struct macio_dev* dev, int mb_state);
+#endif
 	struct device_driver	driver;
 };
 #define	to_macio_driver(drv) container_of(drv,struct macio_driver, driver)
diff --git a/arch/powerpc/include/asm/mediabay.h b/arch/powerpc/include/asm/mediabay.h
index b2efb3325808..11037a4133ee 100644
--- a/arch/powerpc/include/asm/mediabay.h
+++ b/arch/powerpc/include/asm/mediabay.h
@@ -17,26 +17,31 @@
 #define MB_POWER	6	/* media bay contains a Power device (???) */
 #define MB_NO		7	/* media bay contains nothing */
 
-/* Number of bays in the machine or 0 */
-extern int media_bay_count;
+struct macio_dev;
 
-#ifdef CONFIG_BLK_DEV_IDE_PMAC
-#include <linux/ide.h>
+#ifdef CONFIG_PMAC_MEDIABAY
 
-int check_media_bay_by_base(unsigned long base, int what);
-/* called by IDE PMAC host driver to register IDE controller for media bay */
-int media_bay_set_ide_infos(struct device_node *which_bay, unsigned long base,
-			    int irq, ide_hwif_t *hwif);
+/* Check the content type of the bay, returns MB_NO if the bay is still
+ * transitionning
+ */
+extern int check_media_bay(struct macio_dev *bay);
 
-int check_media_bay(struct device_node *which_bay, int what);
+/* The ATA driver uses the calls below to temporarily hold on the
+ * media bay callbacks while initializing the interface
+ */
+extern void lock_media_bay(struct macio_dev *bay);
+extern void unlock_media_bay(struct macio_dev *bay);
 
 #else
 
-static inline int check_media_bay(struct device_node *which_bay, int what)
+static inline int check_media_bay(struct macio_dev *bay)
 {
-	return -ENODEV;
+	return MB_NO;
 }
 
+static inline void lock_media_bay(struct macio_dev *bay) { }
+static inline void unlock_media_bay(struct macio_dev *bay) { }
+
 #endif
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h
index 7b1c49811a24..d4a7f645c5db 100644
--- a/arch/powerpc/include/asm/mman.h
+++ b/arch/powerpc/include/asm/mman.h
@@ -25,6 +25,8 @@
 
 #define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
 #define MAP_NONBLOCK	0x10000		/* do not block on IO */
+#define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
+#define MAP_HUGETLB	0x40000		/* create a huge page mapping */
 
 #ifdef __KERNEL__
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/include/asm/mmu-40x.h b/arch/powerpc/include/asm/mmu-40x.h
index 776f415a36aa..34916865eaef 100644
--- a/arch/powerpc/include/asm/mmu-40x.h
+++ b/arch/powerpc/include/asm/mmu-40x.h
@@ -61,4 +61,7 @@ typedef struct {
 
 #endif /* !__ASSEMBLY__ */
 
+#define mmu_virtual_psize	MMU_PAGE_4K
+#define mmu_linear_psize	MMU_PAGE_256M
+
 #endif /* _ASM_POWERPC_MMU_40X_H_ */
diff --git a/arch/powerpc/include/asm/mmu-44x.h b/arch/powerpc/include/asm/mmu-44x.h
index 3c86576bfefa..0372669383a8 100644
--- a/arch/powerpc/include/asm/mmu-44x.h
+++ b/arch/powerpc/include/asm/mmu-44x.h
@@ -79,16 +79,22 @@ typedef struct {
 
 #if (PAGE_SHIFT == 12)
 #define PPC44x_TLBE_SIZE	PPC44x_TLB_4K
+#define mmu_virtual_psize	MMU_PAGE_4K
 #elif (PAGE_SHIFT == 14)
 #define PPC44x_TLBE_SIZE	PPC44x_TLB_16K
+#define mmu_virtual_psize	MMU_PAGE_16K
 #elif (PAGE_SHIFT == 16)
 #define PPC44x_TLBE_SIZE	PPC44x_TLB_64K
+#define mmu_virtual_psize	MMU_PAGE_64K
 #elif (PAGE_SHIFT == 18)
 #define PPC44x_TLBE_SIZE	PPC44x_TLB_256K
+#define mmu_virtual_psize	MMU_PAGE_256K
 #else
 #error "Unsupported PAGE_SIZE"
 #endif
 
+#define mmu_linear_psize	MMU_PAGE_256M
+
 #define PPC44x_PGD_OFF_SHIFT	(32 - PGDIR_SHIFT + PGD_T_LOG2)
 #define PPC44x_PGD_OFF_MASK_BIT	(PGDIR_SHIFT - PGD_T_LOG2)
 #define PPC44x_PTE_ADD_SHIFT	(32 - PGDIR_SHIFT + PTE_SHIFT + PTE_T_LOG2)
diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/mmu-8xx.h
index 07865a357848..3d11d3ce79ec 100644
--- a/arch/powerpc/include/asm/mmu-8xx.h
+++ b/arch/powerpc/include/asm/mmu-8xx.h
@@ -143,4 +143,7 @@ typedef struct {
 } mm_context_t;
 #endif /* !__ASSEMBLY__ */
 
+#define mmu_virtual_psize	MMU_PAGE_4K
+#define mmu_linear_psize	MMU_PAGE_8M
+
 #endif /* _ASM_POWERPC_MMU_8XX_H_ */
diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index 7e74cff81d86..74695816205c 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -38,58 +38,140 @@
 #define BOOK3E_PAGESZ_1TB	30
 #define BOOK3E_PAGESZ_2TB	31
 
-#define MAS0_TLBSEL(x)	((x << 28) & 0x30000000)
-#define MAS0_ESEL(x)	((x << 16) & 0x0FFF0000)
-#define MAS0_NV(x)	((x) & 0x00000FFF)
-
-#define MAS1_VALID 	0x80000000
-#define MAS1_IPROT	0x40000000
-#define MAS1_TID(x)	((x << 16) & 0x3FFF0000)
-#define MAS1_IND	0x00002000
-#define MAS1_TS		0x00001000
-#define MAS1_TSIZE(x)	((x << 7) & 0x00000F80)
-
-#define MAS2_EPN	0xFFFFF000
-#define MAS2_X0		0x00000040
-#define MAS2_X1		0x00000020
-#define MAS2_W		0x00000010
-#define MAS2_I		0x00000008
-#define MAS2_M		0x00000004
-#define MAS2_G		0x00000002
-#define MAS2_E		0x00000001
+/* MAS registers bit definitions */
+
+#define MAS0_TLBSEL(x)		((x << 28) & 0x30000000)
+#define MAS0_ESEL(x)		((x << 16) & 0x0FFF0000)
+#define MAS0_NV(x)		((x) & 0x00000FFF)
+#define MAS0_HES		0x00004000
+#define MAS0_WQ_ALLWAYS		0x00000000
+#define MAS0_WQ_COND		0x00001000
+#define MAS0_WQ_CLR_RSRV       	0x00002000
+
+#define MAS1_VALID		0x80000000
+#define MAS1_IPROT		0x40000000
+#define MAS1_TID(x)		((x << 16) & 0x3FFF0000)
+#define MAS1_IND		0x00002000
+#define MAS1_TS			0x00001000
+#define MAS1_TSIZE_MASK		0x00000f80
+#define MAS1_TSIZE_SHIFT	7
+#define MAS1_TSIZE(x)		((x << MAS1_TSIZE_SHIFT) & MAS1_TSIZE_MASK)
+
+#define MAS2_EPN		0xFFFFF000
+#define MAS2_X0			0x00000040
+#define MAS2_X1			0x00000020
+#define MAS2_W			0x00000010
+#define MAS2_I			0x00000008
+#define MAS2_M			0x00000004
+#define MAS2_G			0x00000002
+#define MAS2_E			0x00000001
 #define MAS2_EPN_MASK(size)		(~0 << (size + 10))
 #define MAS2_VAL(addr, size, flags)	((addr) & MAS2_EPN_MASK(size) | (flags))
 
-#define MAS3_RPN	0xFFFFF000
-#define MAS3_U0		0x00000200
-#define MAS3_U1		0x00000100
-#define MAS3_U2		0x00000080
-#define MAS3_U3		0x00000040
-#define MAS3_UX		0x00000020
-#define MAS3_SX		0x00000010
-#define MAS3_UW		0x00000008
-#define MAS3_SW		0x00000004
-#define MAS3_UR		0x00000002
-#define MAS3_SR		0x00000001
-
-#define MAS4_TLBSELD(x) MAS0_TLBSEL(x)
-#define MAS4_INDD	0x00008000
-#define MAS4_TSIZED(x)	MAS1_TSIZE(x)
-#define MAS4_X0D	0x00000040
-#define MAS4_X1D	0x00000020
-#define MAS4_WD		0x00000010
-#define MAS4_ID		0x00000008
-#define MAS4_MD		0x00000004
-#define MAS4_GD		0x00000002
-#define MAS4_ED		0x00000001
-
-#define MAS6_SPID0	0x3FFF0000
-#define MAS6_SPID1	0x00007FFE
-#define MAS6_ISIZE(x)	MAS1_TSIZE(x)
-#define MAS6_SAS	0x00000001
-#define MAS6_SPID	MAS6_SPID0
-
-#define MAS7_RPN	0xFFFFFFFF
+#define MAS3_RPN		0xFFFFF000
+#define MAS3_U0			0x00000200
+#define MAS3_U1			0x00000100
+#define MAS3_U2			0x00000080
+#define MAS3_U3			0x00000040
+#define MAS3_UX			0x00000020
+#define MAS3_SX			0x00000010
+#define MAS3_UW			0x00000008
+#define MAS3_SW			0x00000004
+#define MAS3_UR			0x00000002
+#define MAS3_SR			0x00000001
+#define MAS3_SPSIZE		0x0000003e
+#define MAS3_SPSIZE_SHIFT	1
+
+#define MAS4_TLBSELD(x) 	MAS0_TLBSEL(x)
+#define MAS4_INDD		0x00008000	/* Default IND */
+#define MAS4_TSIZED(x)		MAS1_TSIZE(x)
+#define MAS4_X0D		0x00000040
+#define MAS4_X1D		0x00000020
+#define MAS4_WD			0x00000010
+#define MAS4_ID			0x00000008
+#define MAS4_MD			0x00000004
+#define MAS4_GD			0x00000002
+#define MAS4_ED			0x00000001
+#define MAS4_WIMGED_MASK	0x0000001f	/* Default WIMGE */
+#define MAS4_WIMGED_SHIFT	0
+#define MAS4_VLED		MAS4_X1D	/* Default VLE */
+#define MAS4_ACMD		0x000000c0	/* Default ACM */
+#define MAS4_ACMD_SHIFT		6
+#define MAS4_TSIZED_MASK	0x00000f80	/* Default TSIZE */
+#define MAS4_TSIZED_SHIFT	7
+
+#define MAS6_SPID0		0x3FFF0000
+#define MAS6_SPID1		0x00007FFE
+#define MAS6_ISIZE(x)		MAS1_TSIZE(x)
+#define MAS6_SAS		0x00000001
+#define MAS6_SPID		MAS6_SPID0
+#define MAS6_SIND 		0x00000002	/* Indirect page */
+#define MAS6_SIND_SHIFT		1
+#define MAS6_SPID_MASK		0x3fff0000
+#define MAS6_SPID_SHIFT		16
+#define MAS6_ISIZE_MASK		0x00000f80
+#define MAS6_ISIZE_SHIFT	7
+
+#define MAS7_RPN		0xFFFFFFFF
+
+/* Bit definitions for MMUCSR0 */
+#define MMUCSR0_TLB1FI	0x00000002	/* TLB1 Flash invalidate */
+#define MMUCSR0_TLB0FI	0x00000004	/* TLB0 Flash invalidate */
+#define MMUCSR0_TLB2FI	0x00000040	/* TLB2 Flash invalidate */
+#define MMUCSR0_TLB3FI	0x00000020	/* TLB3 Flash invalidate */
+#define MMUCSR0_TLBFI	(MMUCSR0_TLB0FI | MMUCSR0_TLB1FI | \
+			 MMUCSR0_TLB2FI | MMUCSR0_TLB3FI)
+#define MMUCSR0_TLB0PS	0x00000780	/* TLB0 Page Size */
+#define MMUCSR0_TLB1PS	0x00007800	/* TLB1 Page Size */
+#define MMUCSR0_TLB2PS	0x00078000	/* TLB2 Page Size */
+#define MMUCSR0_TLB3PS	0x00780000	/* TLB3 Page Size */
+
+/* TLBnCFG encoding */
+#define TLBnCFG_N_ENTRY		0x00000fff	/* number of entries */
+#define TLBnCFG_HES		0x00002000	/* HW select supported */
+#define TLBnCFG_IPROT		0x00008000	/* IPROT supported */
+#define TLBnCFG_GTWE		0x00010000	/* Guest can write */
+#define TLBnCFG_IND		0x00020000	/* IND entries supported */
+#define TLBnCFG_PT		0x00040000	/* Can load from page table */
+#define TLBnCFG_ASSOC		0xff000000	/* Associativity */
+
+/* TLBnPS encoding */
+#define TLBnPS_4K		0x00000004
+#define TLBnPS_8K		0x00000008
+#define TLBnPS_16K		0x00000010
+#define TLBnPS_32K		0x00000020
+#define TLBnPS_64K		0x00000040
+#define TLBnPS_128K		0x00000080
+#define TLBnPS_256K		0x00000100
+#define TLBnPS_512K		0x00000200
+#define TLBnPS_1M 		0x00000400
+#define TLBnPS_2M 		0x00000800
+#define TLBnPS_4M 		0x00001000
+#define TLBnPS_8M 		0x00002000
+#define TLBnPS_16M		0x00004000
+#define TLBnPS_32M		0x00008000
+#define TLBnPS_64M		0x00010000
+#define TLBnPS_128M		0x00020000
+#define TLBnPS_256M		0x00040000
+#define TLBnPS_512M		0x00080000
+#define TLBnPS_1G		0x00100000
+#define TLBnPS_2G		0x00200000
+#define TLBnPS_4G		0x00400000
+#define TLBnPS_8G		0x00800000
+#define TLBnPS_16G		0x01000000
+#define TLBnPS_32G		0x02000000
+#define TLBnPS_64G		0x04000000
+#define TLBnPS_128G		0x08000000
+#define TLBnPS_256G		0x10000000
+
+/* tlbilx action encoding */
+#define TLBILX_T_ALL			0
+#define TLBILX_T_TID			1
+#define TLBILX_T_FULLMATCH		3
+#define TLBILX_T_CLASS0			4
+#define TLBILX_T_CLASS1			5
+#define TLBILX_T_CLASS2			6
+#define TLBILX_T_CLASS3			7
 
 #ifndef __ASSEMBLY__
 
@@ -100,6 +182,34 @@ typedef struct {
 	unsigned int	active;
 	unsigned long	vdso_base;
 } mm_context_t;
+
+/* Page size definitions, common between 32 and 64-bit
+ *
+ *    shift : is the "PAGE_SHIFT" value for that page size
+ *    penc  : is the pte encoding mask
+ *
+ */
+struct mmu_psize_def
+{
+	unsigned int	shift;	/* number of bits */
+	unsigned int	enc;	/* PTE encoding */
+};
+extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
+
+/* The page sizes use the same names as 64-bit hash but are
+ * constants
+ */
+#if defined(CONFIG_PPC_4K_PAGES)
+#define mmu_virtual_psize	MMU_PAGE_4K
+#elif defined(CONFIG_PPC_64K_PAGES)
+#define mmu_virtual_psize	MMU_PAGE_64K
+#else
+#error Unsupported page size
+#endif
+
+extern int mmu_linear_psize;
+extern int mmu_vmemmap_psize;
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_MMU_BOOK3E_H_ */
diff --git a/arch/powerpc/include/asm/mmu-hash32.h b/arch/powerpc/include/asm/mmu-hash32.h
index 16b1a1e77e64..16f513e5cbd7 100644
--- a/arch/powerpc/include/asm/mmu-hash32.h
+++ b/arch/powerpc/include/asm/mmu-hash32.h
@@ -55,21 +55,25 @@ struct ppc_bat {
 
 #ifndef __ASSEMBLY__
 
-/* Hardware Page Table Entry */
+/*
+ * Hardware Page Table Entry
+ * Note that the xpn and x bitfields are used only by processors that
+ * support extended addressing; otherwise, those bits are reserved.
+ */
 struct hash_pte {
 	unsigned long v:1;	/* Entry is valid */
 	unsigned long vsid:24;	/* Virtual segment identifier */
 	unsigned long h:1;	/* Hash algorithm indicator */
 	unsigned long api:6;	/* Abbreviated page index */
 	unsigned long rpn:20;	/* Real (physical) page number */
-	unsigned long    :3;	/* Unused */
+	unsigned long xpn:3;	/* Real page number bits 0-2, optional */
 	unsigned long r:1;	/* Referenced */
 	unsigned long c:1;	/* Changed */
 	unsigned long w:1;	/* Write-thru cache mode */
 	unsigned long i:1;	/* Cache inhibited */
 	unsigned long m:1;	/* Memory coherence */
 	unsigned long g:1;	/* Guarded */
-	unsigned long  :1;	/* Unused */
+	unsigned long x:1;	/* Real page number bit 3, optional */
 	unsigned long pp:2;	/* Page protection */
 };
 
@@ -80,4 +84,10 @@ typedef struct {
 
 #endif /* !__ASSEMBLY__ */
 
+/* We happily ignore the smaller BATs on 601, we don't actually use
+ * those definitions on hash32 at the moment anyway
+ */
+#define mmu_virtual_psize	MMU_PAGE_4K
+#define mmu_linear_psize	MMU_PAGE_256M
+
 #endif /* _ASM_POWERPC_MMU_HASH32_H_ */
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 98c104a09961..2102b214a87c 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -41,6 +41,7 @@ extern char initial_stab[];
 
 #define SLB_NUM_BOLTED		3
 #define SLB_CACHE_ENTRIES	8
+#define SLB_MIN_SIZE		32
 
 /* Bits in the SLB ESID word */
 #define SLB_ESID_V		ASM_CONST(0x0000000008000000) /* valid */
@@ -139,26 +140,6 @@ struct mmu_psize_def
 #endif /* __ASSEMBLY__ */
 
 /*
- * The kernel use the constants below to index in the page sizes array.
- * The use of fixed constants for this purpose is better for performances
- * of the low level hash refill handlers.
- *
- * A non supported page size has a "shift" field set to 0
- *
- * Any new page size being implemented can get a new entry in here. Whether
- * the kernel will use it or not is a different matter though. The actual page
- * size used by hugetlbfs is not defined here and may be made variable
- */
-
-#define MMU_PAGE_4K		0	/* 4K */
-#define MMU_PAGE_64K		1	/* 64K */
-#define MMU_PAGE_64K_AP		2	/* 64K Admixed (in a 4K segment) */
-#define MMU_PAGE_1M		3	/* 1M */
-#define MMU_PAGE_16M		4	/* 16M */
-#define MMU_PAGE_16G		5	/* 16G */
-#define MMU_PAGE_COUNT		6
-
-/*
  * Segment sizes.
  * These are the values used by hardware in the B field of
  * SLB entries and the first dword of MMU hashtable entries.
@@ -192,14 +173,6 @@ extern unsigned long tce_alloc_start, tce_alloc_end;
  */
 extern int mmu_ci_restrictions;
 
-#ifdef CONFIG_HUGETLB_PAGE
-/*
- * The page size indexes of the huge pages for use by hugetlbfs
- */
-extern unsigned int mmu_huge_psizes[MMU_PAGE_COUNT];
-
-#endif /* CONFIG_HUGETLB_PAGE */
-
 /*
  * This function sets the AVPN and L fields of the HPTE  appropriately
  * for the page size
@@ -272,10 +245,11 @@ extern int __hash_page_64K(unsigned long ea, unsigned long access,
 			   unsigned long vsid, pte_t *ptep, unsigned long trap,
 			   unsigned int local, int ssize);
 struct mm_struct;
+unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap);
 extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap);
-extern int hash_huge_page(struct mm_struct *mm, unsigned long access,
-			  unsigned long ea, unsigned long vsid, int local,
-			  unsigned long trap);
+int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
+		     pte_t *ptep, unsigned long trap, int local, int ssize,
+		     unsigned int shift, unsigned int mmu_psize);
 
 extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 			     unsigned long pstart, unsigned long prot,
@@ -296,6 +270,7 @@ extern void slb_flush_and_rebolt(void);
 extern void stab_initialize(unsigned long stab);
 
 extern void slb_vmalloc_update(void);
+extern void slb_set_size(u16 size);
 #endif /* __ASSEMBLY__ */
 
 /*
@@ -398,6 +373,38 @@ extern void slb_vmalloc_update(void);
 
 #ifndef __ASSEMBLY__
 
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+/*
+ * For the sub-page protection option, we extend the PGD with one of
+ * these.  Basically we have a 3-level tree, with the top level being
+ * the protptrs array.  To optimize speed and memory consumption when
+ * only addresses < 4GB are being protected, pointers to the first
+ * four pages of sub-page protection words are stored in the low_prot
+ * array.
+ * Each page of sub-page protection words protects 1GB (4 bytes
+ * protects 64k).  For the 3-level tree, each page of pointers then
+ * protects 8TB.
+ */
+struct subpage_prot_table {
+	unsigned long maxaddr;	/* only addresses < this are protected */
+	unsigned int **protptrs[2];
+	unsigned int *low_prot[4];
+};
+
+#define SBP_L1_BITS		(PAGE_SHIFT - 2)
+#define SBP_L2_BITS		(PAGE_SHIFT - 3)
+#define SBP_L1_COUNT		(1 << SBP_L1_BITS)
+#define SBP_L2_COUNT		(1 << SBP_L2_BITS)
+#define SBP_L2_SHIFT		(PAGE_SHIFT + SBP_L1_BITS)
+#define SBP_L3_SHIFT		(SBP_L2_SHIFT + SBP_L2_BITS)
+
+extern void subpage_prot_free(struct mm_struct *mm);
+extern void subpage_prot_init_new_context(struct mm_struct *mm);
+#else
+static inline void subpage_prot_free(struct mm_struct *mm) {}
+static inline void subpage_prot_init_new_context(struct mm_struct *mm) { }
+#endif /* CONFIG_PPC_SUBPAGE_PROT */
+
 typedef unsigned long mm_context_id_t;
 
 typedef struct {
@@ -411,6 +418,9 @@ typedef struct {
 	u16 sllp;		/* SLB page size encoding */
 #endif
 	unsigned long vdso_base;
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+	struct subpage_prot_table spt;
+#endif /* CONFIG_PPC_SUBPAGE_PROT */
 } mm_context_t;
 
 
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index fb57ded592f9..7ffbb65ff7a9 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -17,6 +17,7 @@
 #define MMU_FTR_TYPE_40x		ASM_CONST(0x00000004)
 #define MMU_FTR_TYPE_44x		ASM_CONST(0x00000008)
 #define MMU_FTR_TYPE_FSL_E		ASM_CONST(0x00000010)
+#define MMU_FTR_TYPE_3E			ASM_CONST(0x00000020)
 
 /*
  * This is individual features
@@ -57,6 +58,15 @@
  */
 #define MMU_FTR_TLBIE_206		ASM_CONST(0x00400000)
 
+/* Enable use of TLB reservation.  Processor should support tlbsrx.
+ * instruction and MAS0[WQ].
+ */
+#define MMU_FTR_USE_TLBRSRV		ASM_CONST(0x00800000)
+
+/* Use paired MAS registers (MAS7||MAS3, etc.)
+ */
+#define MMU_FTR_USE_PAIRED_MAS		ASM_CONST(0x01000000)
+
 #ifndef __ASSEMBLY__
 #include <asm/cputable.h>
 
@@ -73,6 +83,41 @@ extern void early_init_mmu_secondary(void);
 
 #endif /* !__ASSEMBLY__ */
 
+/* The kernel use the constants below to index in the page sizes array.
+ * The use of fixed constants for this purpose is better for performances
+ * of the low level hash refill handlers.
+ *
+ * A non supported page size has a "shift" field set to 0
+ *
+ * Any new page size being implemented can get a new entry in here. Whether
+ * the kernel will use it or not is a different matter though. The actual page
+ * size used by hugetlbfs is not defined here and may be made variable
+ *
+ * Note: This array ended up being a false good idea as it's growing to the
+ * point where I wonder if we should replace it with something different,
+ * to think about, feedback welcome. --BenH.
+ */
+
+/* There are #define as they have to be used in assembly
+ *
+ * WARNING: If you change this list, make sure to update the array of
+ * names currently in arch/powerpc/mm/hugetlbpage.c or bad things will
+ * happen
+ */
+#define MMU_PAGE_4K	0
+#define MMU_PAGE_16K	1
+#define MMU_PAGE_64K	2
+#define MMU_PAGE_64K_AP	3	/* "Admixed pages" (hash64 only) */
+#define MMU_PAGE_256K	4
+#define MMU_PAGE_1M	5
+#define MMU_PAGE_8M	6
+#define MMU_PAGE_16M	7
+#define MMU_PAGE_256M	8
+#define MMU_PAGE_1G	9
+#define MMU_PAGE_16G	10
+#define MMU_PAGE_64G	11
+#define MMU_PAGE_COUNT	12
+
 
 #if defined(CONFIG_PPC_STD_MMU_64)
 /* 64-bit classic hash table MMU */
@@ -94,5 +139,6 @@ extern void early_init_mmu_secondary(void);
 #  include <asm/mmu-8xx.h>
 #endif
 
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_MMU_H_ */
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index b7063669f972..26383e0778aa 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -14,7 +14,6 @@
 /*
  * Most if the context management is out of line
  */
-extern void mmu_context_init(void);
 extern int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 extern void destroy_context(struct mm_struct *mm);
 
@@ -23,6 +22,14 @@ extern void switch_stab(struct task_struct *tsk, struct mm_struct *mm);
 extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm);
 extern void set_context(unsigned long id, pgd_t *pgd);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+extern int __init_new_context(void);
+extern void __destroy_context(int context_id);
+static inline void mmu_context_init(void) { }
+#else
+extern void mmu_context_init(void);
+#endif
+
 /*
  * switch_mm is the entry point called from the architecture independent
  * code in kernel/sched.c
@@ -38,6 +45,10 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	tsk->thread.pgdir = next->pgd;
 #endif /* CONFIG_PPC32 */
 
+	/* 64-bit Book3E keeps track of current PGD in the PACA */
+#ifdef CONFIG_PPC_BOOK3E_64
+	get_paca()->pgd = next->pgd;
+#endif
 	/* Nothing else to do if we aren't actually switching */
 	if (prev == next)
 		return;
@@ -84,6 +95,10 @@ static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next)
 static inline void enter_lazy_tlb(struct mm_struct *mm,
 				  struct task_struct *tsk)
 {
+	/* 64-bit Book3E keeps track of current PGD in the PACA */
+#ifdef CONFIG_PPC_BOOK3E_64
+	get_paca()->pgd = NULL;
+#endif
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index 08454880a2c0..0192a4ee2bc2 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -87,5 +87,10 @@ struct exception_table_entry;
 void sort_ex_table(struct exception_table_entry *start,
 		   struct exception_table_entry *finish);
 
+#ifdef CONFIG_MODVERSIONS
+#define ARCH_RELOCATES_KCRCTAB
+
+extern const unsigned long reloc_start[];
+#endif
 #endif /* __KERNEL__ */
 #endif	/* _ASM_POWERPC_MODULE_H */
diff --git a/arch/powerpc/include/asm/mpc52xx.h b/arch/powerpc/include/asm/mpc52xx.h
index 1b4f697abbdd..b664ce79a172 100644
--- a/arch/powerpc/include/asm/mpc52xx.h
+++ b/arch/powerpc/include/asm/mpc52xx.h
@@ -276,6 +276,53 @@ extern int mpc52xx_set_psc_clkdiv(int psc_id, int clkdiv);
 extern unsigned int mpc52xx_get_xtal_freq(struct device_node *node);
 extern void mpc52xx_restart(char *cmd);
 
+/* mpc52xx_gpt.c */
+struct mpc52xx_gpt_priv;
+extern struct mpc52xx_gpt_priv *mpc52xx_gpt_from_irq(int irq);
+extern int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, u64 period,
+                            int continuous);
+extern u64 mpc52xx_gpt_timer_period(struct mpc52xx_gpt_priv *gpt);
+extern int mpc52xx_gpt_stop_timer(struct mpc52xx_gpt_priv *gpt);
+
+/* mpc52xx_lpbfifo.c */
+#define MPC52XX_LPBFIFO_FLAG_READ		(0)
+#define MPC52XX_LPBFIFO_FLAG_WRITE		(1<<0)
+#define MPC52XX_LPBFIFO_FLAG_NO_INCREMENT	(1<<1)
+#define MPC52XX_LPBFIFO_FLAG_NO_DMA		(1<<2)
+#define MPC52XX_LPBFIFO_FLAG_POLL_DMA		(1<<3)
+
+struct mpc52xx_lpbfifo_request {
+	struct list_head list;
+
+	/* localplus bus address */
+	unsigned int cs;
+	size_t offset;
+
+	/* Memory address */
+	void *data;
+	phys_addr_t data_phys;
+
+	/* Details of transfer */
+	size_t size;
+	size_t pos;	/* current position of transfer */
+	int flags;
+
+	/* What to do when finished */
+	void (*callback)(struct mpc52xx_lpbfifo_request *);
+
+	void *priv;		/* Driver private data */
+
+	/* statistics */
+	int irq_count;
+	int irq_ticks;
+	u8 last_byte;
+	int buffer_not_done_cnt;
+};
+
+extern int mpc52xx_lpbfifo_submit(struct mpc52xx_lpbfifo_request *req);
+extern void mpc52xx_lpbfifo_abort(struct mpc52xx_lpbfifo_request *req);
+extern void mpc52xx_lpbfifo_poll(void);
+
 /* mpc52xx_pic.c */
 extern void mpc52xx_init_irq(void);
 extern unsigned int mpc52xx_get_irq(void);
diff --git a/arch/powerpc/include/asm/mpic.h b/arch/powerpc/include/asm/mpic.h
index 582e47df00b6..61913d9a21a0 100644
--- a/arch/powerpc/include/asm/mpic.h
+++ b/arch/powerpc/include/asm/mpic.h
@@ -289,7 +289,7 @@ struct mpic
 #ifdef CONFIG_MPIC_U3_HT_IRQS
 	/* The fixup table */
 	struct mpic_irq_fixup	*fixups;
-	atomic_spinlock_t	fixup_lock;
+	raw_spinlock_t	fixup_lock;
 #endif
 
 	/* Register access method */
diff --git a/arch/powerpc/include/asm/nvram.h b/arch/powerpc/include/asm/nvram.h
index efde5ac82f7b..850b72f27445 100644
--- a/arch/powerpc/include/asm/nvram.h
+++ b/arch/powerpc/include/asm/nvram.h
@@ -73,7 +73,6 @@ extern int nvram_write_error_log(char * buff, int length,
 extern int nvram_read_error_log(char * buff, int length,
 					 unsigned int * err_type, unsigned int *err_seq);
 extern int nvram_clear_error_log(void);
-extern struct nvram_partition *nvram_find_partition(int sig, const char *name);
 
 extern int pSeries_nvram_init(void);
 
@@ -107,6 +106,9 @@ extern void	pmac_xpram_write(int xpaddr, u8 data);
 /* Synchronize NVRAM */
 extern void	nvram_sync(void);
 
+/* Determine NVRAM size */
+extern ssize_t nvram_get_size(void);
+
 /* Normal access to NVRAM */
 extern unsigned char nvram_read_byte(int i);
 extern void nvram_write_byte(unsigned char c, int i);
diff --git a/arch/powerpc/include/asm/pSeries_reconfig.h b/arch/powerpc/include/asm/pSeries_reconfig.h
index e482e5352e69..d4b4bfa26fb3 100644
--- a/arch/powerpc/include/asm/pSeries_reconfig.h
+++ b/arch/powerpc/include/asm/pSeries_reconfig.h
@@ -17,6 +17,7 @@
 #ifdef CONFIG_PPC_PSERIES
 extern int pSeries_reconfig_notifier_register(struct notifier_block *);
 extern void pSeries_reconfig_notifier_unregister(struct notifier_block *);
+extern struct blocking_notifier_head pSeries_reconfig_chain;
 #else /* !CONFIG_PPC_PSERIES */
 static inline int pSeries_reconfig_notifier_register(struct notifier_block *nb)
 {
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index c8a3cbfe02ff..5e9b4ef71415 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -14,9 +14,11 @@
 #define _ASM_POWERPC_PACA_H
 #ifdef __KERNEL__
 
-#include	<asm/types.h>
-#include	<asm/lppaca.h>
-#include	<asm/mmu.h>
+#include <asm/types.h>
+#include <asm/lppaca.h>
+#include <asm/mmu.h>
+#include <asm/page.h>
+#include <asm/exception-64e.h>
 
 register struct paca_struct *local_paca asm("r13");
 
@@ -91,6 +93,21 @@ struct paca_struct {
 	u16 slb_cache[SLB_CACHE_ENTRIES];
 #endif /* CONFIG_PPC_STD_MMU_64 */
 
+#ifdef CONFIG_PPC_BOOK3E
+	pgd_t *pgd;			/* Current PGD */
+	pgd_t *kernel_pgd;		/* Kernel PGD */
+	u64 exgen[8] __attribute__((aligned(0x80)));
+	u64 extlb[EX_TLB_SIZE*3] __attribute__((aligned(0x80)));
+	u64 exmc[8];		/* used for machine checks */
+	u64 excrit[8];		/* used for crit interrupts */
+	u64 exdbg[8];		/* used for debug interrupts */
+
+	/* Kernel stack pointers for use by special exceptions */
+	void *mc_kstack;
+	void *crit_kstack;
+	void *dbg_kstack;
+#endif /* CONFIG_PPC_BOOK3E */
+
 	mm_context_t context;
 
 	/*
@@ -105,13 +122,22 @@ struct paca_struct {
 	u8 soft_enabled;		/* irq soft-enable flag */
 	u8 hard_enabled;		/* set if irqs are enabled in MSR */
 	u8 io_sync;			/* writel() needs spin_unlock sync */
-	u8 perf_counter_pending;	/* PM interrupt while soft-disabled */
+	u8 perf_event_pending;		/* PM interrupt while soft-disabled */
 
 	/* Stuff for accurate time accounting */
 	u64 user_time;			/* accumulated usermode TB ticks */
 	u64 system_time;		/* accumulated system TB ticks */
 	u64 startpurr;			/* PURR/TB value snapshot */
 	u64 startspurr;			/* SPURR value snapshot */
+
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+	struct  {
+		u64     esid;
+		u64     vsid;
+	} kvm_slb[64];			/* guest SLB */
+	u8 kvm_slb_max;			/* highest used guest slb entry */
+	u8 kvm_in_guest;		/* are we inside the guest? */
+#endif
 };
 
 extern struct paca_struct paca[];
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 4940662ee87e..e96d52a516ba 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -139,7 +139,11 @@ extern phys_addr_t kernstart_addr;
  * Don't compare things with KERNELBASE or PAGE_OFFSET to test for
  * "kernelness", use is_kernel_addr() - it should do what you want.
  */
+#ifdef CONFIG_PPC_BOOK3E_64
+#define is_kernel_addr(x)	((x) >= 0x8000000000000000ul)
+#else
 #define is_kernel_addr(x)	((x) >= PAGE_OFFSET)
+#endif
 
 #ifndef __ASSEMBLY__
 
@@ -225,6 +229,20 @@ typedef unsigned long pgprot_t;
 
 #endif
 
+typedef struct { signed long pd; } hugepd_t;
+#define HUGEPD_SHIFT_MASK     0x3f
+
+#ifdef CONFIG_HUGETLB_PAGE
+static inline int hugepd_ok(hugepd_t hpd)
+{
+	return (hpd.pd > 0);
+}
+
+#define is_hugepd(pdep)               (hugepd_ok(*((hugepd_t *)(pdep))))
+#else /* CONFIG_HUGETLB_PAGE */
+#define is_hugepd(pdep)			0
+#endif /* CONFIG_HUGETLB_PAGE */
+
 struct page;
 extern void clear_user_page(void *page, unsigned long vaddr, struct page *pg);
 extern void copy_user_page(void *to, void *from, unsigned long vaddr,
diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
index 5817a3b747e5..bfc4e027e2ad 100644
--- a/arch/powerpc/include/asm/page_64.h
+++ b/arch/powerpc/include/asm/page_64.h
@@ -90,7 +90,7 @@ extern unsigned int HPAGE_SHIFT;
 #define HPAGE_SIZE		((1UL) << HPAGE_SHIFT)
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
-#define HUGE_MAX_HSTATE		3
+#define HUGE_MAX_HSTATE		(MMU_PAGE_COUNT-1)
 
 #endif /* __ASSEMBLY__ */
 
@@ -135,12 +135,22 @@ extern void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
 #endif /* __ASSEMBLY__ */
 #else
 #define slice_init()
+#ifdef CONFIG_PPC_STD_MMU_64
 #define get_slice_psize(mm, addr)	((mm)->context.user_psize)
 #define slice_set_user_psize(mm, psize)		\
 do {						\
 	(mm)->context.user_psize = (psize);	\
 	(mm)->context.sllp = SLB_VSID_USER | mmu_psize_defs[(psize)].sllp; \
 } while (0)
+#else /* CONFIG_PPC_STD_MMU_64 */
+#ifdef CONFIG_PPC_64K_PAGES
+#define get_slice_psize(mm, addr)	MMU_PAGE_64K
+#else /* CONFIG_PPC_64K_PAGES */
+#define get_slice_psize(mm, addr)	MMU_PAGE_4K
+#endif /* !CONFIG_PPC_64K_PAGES */
+#define slice_set_user_psize(mm, psize)	do { BUG(); } while(0)
+#endif /* !CONFIG_PPC_STD_MMU_64 */
+
 #define slice_set_range_psize(mm, start, len, psize)	\
 	slice_set_user_psize((mm), (psize))
 #define slice_mm_new_context(mm)	1
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 4c61fa0b8d75..76e1f313a58e 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -77,9 +77,7 @@ struct pci_controller {
 
 	int first_busno;
 	int last_busno;
-#ifndef CONFIG_PPC64
 	int self_busno;
-#endif
 
 	void __iomem *io_base_virt;
 #ifdef CONFIG_PPC64
@@ -104,7 +102,6 @@ struct pci_controller {
 	unsigned int __iomem *cfg_addr;
 	void __iomem *cfg_data;
 
-#ifndef CONFIG_PPC64
 	/*
 	 * Used for variants of PCI indirect handling and possible quirks:
 	 *  SET_CFG_TYPE - used on 4xx or any PHB that does explicit type0/1
@@ -128,7 +125,6 @@ struct pci_controller {
 #define PPC_INDIRECT_TYPE_BIG_ENDIAN		0x00000010
 #define PPC_INDIRECT_TYPE_BROKEN_MRM		0x00000020
 	u32 indirect_type;
-#endif	/* !CONFIG_PPC64 */
 	/* Currently, we limit ourselves to 1 IO range and 3 mem
 	 * ranges since the common pci_bus structure can't handle more
 	 */
@@ -146,21 +142,6 @@ struct pci_controller {
 #endif	/* CONFIG_PPC64 */
 };
 
-#ifndef CONFIG_PPC64
-
-static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus)
-{
-	return bus->sysdata;
-}
-
-static inline int isa_vaddr_is_ioport(void __iomem *address)
-{
-	/* No specific ISA handling on ppc32 at this stage, it
-	 * all goes through PCI
-	 */
-	return 0;
-}
-
 /* These are used for config access before all the PCI probing
    has been done. */
 extern int early_read_config_byte(struct pci_controller *hose, int bus,
@@ -182,6 +163,22 @@ extern int early_find_capability(struct pci_controller *hose, int bus,
 extern void setup_indirect_pci(struct pci_controller* hose,
 			       resource_size_t cfg_addr,
 			       resource_size_t cfg_data, u32 flags);
+
+#ifndef CONFIG_PPC64
+
+static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus)
+{
+	return bus->sysdata;
+}
+
+static inline int isa_vaddr_is_ioport(void __iomem *address)
+{
+	/* No specific ISA handling on ppc32 at this stage, it
+	 * all goes through PCI
+	 */
+	return 0;
+}
+
 #else	/* CONFIG_PPC64 */
 
 /*
@@ -284,11 +281,6 @@ static inline int isa_vaddr_is_ioport(void __iomem *address)
 extern int pcibios_unmap_io_space(struct pci_bus *bus);
 extern int pcibios_map_io_space(struct pci_bus *bus);
 
-/* Return values for ppc_md.pci_probe_mode function */
-#define PCI_PROBE_NONE		-1	/* Don't look at this bus at all */
-#define PCI_PROBE_NORMAL	0	/* Do normal PCI probing */
-#define PCI_PROBE_DEVTREE	1	/* Instantiate from device tree */
-
 #ifdef CONFIG_NUMA
 #define PHB_SET_NODE(PHB, NODE)		((PHB)->node = (NODE))
 #else
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index d9483c504d2d..b5ea626eea2d 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -22,6 +22,11 @@
 
 #include <asm-generic/pci-dma-compat.h>
 
+/* Return values for ppc_md.pci_probe_mode function */
+#define PCI_PROBE_NONE		-1	/* Don't look at this bus at all */
+#define PCI_PROBE_NORMAL	0	/* Do normal PCI probing */
+#define PCI_PROBE_DEVTREE	1	/* Instantiate from device tree */
+
 #define PCIBIOS_MIN_IO		0x1000
 #define PCIBIOS_MIN_MEM		0x10000000
 
@@ -40,7 +45,6 @@ struct pci_dev;
  */
 #define pcibios_assign_all_busses() \
 	(ppc_pci_has_flag(PPC_PCI_REASSIGN_ALL_BUS))
-#define pcibios_scan_all_fns(a, b)	0
 
 static inline void pcibios_set_master(struct pci_dev *dev)
 {
@@ -61,8 +65,8 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 }
 
 #ifdef CONFIG_PCI
-extern void set_pci_dma_ops(struct dma_mapping_ops *dma_ops);
-extern struct dma_mapping_ops *get_pci_dma_ops(void);
+extern void set_pci_dma_ops(struct dma_map_ops *dma_ops);
+extern struct dma_map_ops *get_pci_dma_ops(void);
 #else	/* CONFIG_PCI */
 #define set_pci_dma_ops(d)
 #define get_pci_dma_ops()	NULL
@@ -228,6 +232,8 @@ extern void pci_resource_to_user(const struct pci_dev *dev, int bar,
 
 extern void pcibios_setup_bus_devices(struct pci_bus *bus);
 extern void pcibios_setup_bus_self(struct pci_bus *bus);
+extern void pcibios_setup_phb_io_space(struct pci_controller *hose);
+extern void pcibios_scan_phb(struct pci_controller *hose, void *sysdata);
 
 #endif	/* __KERNEL__ */
 #endif /* __ASM_POWERPC_PCI_H */
diff --git a/arch/powerpc/include/asm/perf_counter.h b/arch/powerpc/include/asm/perf_event.h
index 0ea0639fcf75..3288ce3997e0 100644
--- a/arch/powerpc/include/asm/perf_counter.h
+++ b/arch/powerpc/include/asm/perf_event.h
@@ -1,5 +1,5 @@
 /*
- * Performance counter support - PowerPC-specific definitions.
+ * Performance event support - PowerPC-specific definitions.
  *
  * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
  *
@@ -12,7 +12,7 @@
 
 #include <asm/hw_irq.h>
 
-#define MAX_HWCOUNTERS		8
+#define MAX_HWEVENTS		8
 #define MAX_EVENT_ALTERNATIVES	8
 #define MAX_LIMITED_HWCOUNTERS	2
 
@@ -28,12 +28,12 @@ struct power_pmu {
 	unsigned long	test_adder;
 	int		(*compute_mmcr)(u64 events[], int n_ev,
 				unsigned int hwc[], unsigned long mmcr[]);
-	int		(*get_constraint)(u64 event, unsigned long *mskp,
+	int		(*get_constraint)(u64 event_id, unsigned long *mskp,
 				unsigned long *valp);
-	int		(*get_alternatives)(u64 event, unsigned int flags,
+	int		(*get_alternatives)(u64 event_id, unsigned int flags,
 				u64 alt[]);
 	void		(*disable_pmc)(unsigned int pmc, unsigned long mmcr[]);
-	int		(*limited_pmc_event)(u64 event);
+	int		(*limited_pmc_event)(u64 event_id);
 	u32		flags;
 	int		n_generic;
 	int		*generic_events;
@@ -61,10 +61,10 @@ struct pt_regs;
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 
-#define PERF_COUNTER_INDEX_OFFSET	1
+#define PERF_EVENT_INDEX_OFFSET	1
 
 /*
- * Only override the default definitions in include/linux/perf_counter.h
+ * Only override the default definitions in include/linux/perf_event.h
  * if we have hardware PMU support.
  */
 #ifdef CONFIG_PPC_PERF_CTRS
@@ -73,14 +73,14 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 
 /*
  * The power_pmu.get_constraint function returns a 32/64-bit value and
- * a 32/64-bit mask that express the constraints between this event and
+ * a 32/64-bit mask that express the constraints between this event_id and
  * other events.
  *
  * The value and mask are divided up into (non-overlapping) bitfields
  * of three different types:
  *
  * Select field: this expresses the constraint that some set of bits
- * in MMCR* needs to be set to a specific value for this event.  For a
+ * in MMCR* needs to be set to a specific value for this event_id.  For a
  * select field, the mask contains 1s in every bit of the field, and
  * the value contains a unique value for each possible setting of the
  * MMCR* bits.  The constraint checking code will ensure that two events
@@ -102,9 +102,9 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
  * possible.)  For N classes, the field is N+1 bits wide, and each class
  * is assigned one bit from the least-significant N bits.  The mask has
  * only the most-significant bit set, and the value has only the bit
- * for the event's class set.  The test_adder has the least significant
+ * for the event_id's class set.  The test_adder has the least significant
  * bit set in the field.
  *
- * If an event is not subject to the constraint expressed by a particular
+ * If an event_id is not subject to the constraint expressed by a particular
  * field, then it will have 0 in both the mask and value for that field.
  */
diff --git a/arch/powerpc/include/asm/pgalloc-32.h b/arch/powerpc/include/asm/pgalloc-32.h
index c9500d666a1d..580cf73b96e8 100644
--- a/arch/powerpc/include/asm/pgalloc-32.h
+++ b/arch/powerpc/include/asm/pgalloc-32.h
@@ -3,7 +3,8 @@
 
 #include <linux/threads.h>
 
-#define PTE_NONCACHE_NUM	0  /* dummy for now to share code w/ppc64 */
+/* For 32-bit, all levels of page tables are just drawn from get_free_page() */
+#define MAX_PGTABLE_INDEX_SIZE	0
 
 extern void __bad_pte(pmd_t *pmd);
 
@@ -36,11 +37,10 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
 extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr);
 
-static inline void pgtable_free(pgtable_free_t pgf)
+static inline void pgtable_free(void *table, unsigned index_size)
 {
-	void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
-
-	free_page((unsigned long)p);
+	BUG_ON(index_size); /* 32-bit doesn't use this */
+	free_page((unsigned long)table);
 }
 
 #define check_pgt_cache()	do { } while (0)
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index e6f069c4f713..605f5c5398d1 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -11,27 +11,34 @@
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
 
-#ifndef CONFIG_PPC_SUBPAGE_PROT
-static inline void subpage_prot_free(pgd_t *pgd) {}
-#endif
+/*
+ * Functions that deal with pagetables that could be at any level of
+ * the table need to be passed an "index_size" so they know how to
+ * handle allocation.  For PTE pages (which are linked to a struct
+ * page for now, and drawn from the main get_free_pages() pool), the
+ * allocation size will be (2^index_size * sizeof(pointer)) and
+ * allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
+ *
+ * The maximum index size needs to be big enough to allow any
+ * pagetable sizes we need, but small enough to fit in the low bits of
+ * any page table pointer.  In other words all pagetables, even tiny
+ * ones, must be aligned to allow at least enough low 0 bits to
+ * contain this value.  This value is also used as a mask, so it must
+ * be one less than a power of two.
+ */
+#define MAX_PGTABLE_INDEX_SIZE	0xf
 
 extern struct kmem_cache *pgtable_cache[];
-
-#define PGD_CACHE_NUM		0
-#define PUD_CACHE_NUM		1
-#define PMD_CACHE_NUM		1
-#define HUGEPTE_CACHE_NUM	2
-#define PTE_NONCACHE_NUM	7  /* from GFP rather than kmem_cache */
+#define PGT_CACHE(shift) (pgtable_cache[(shift)-1])
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return kmem_cache_alloc(pgtable_cache[PGD_CACHE_NUM], GFP_KERNEL);
+	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL);
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-	subpage_prot_free(pgd);
-	kmem_cache_free(pgtable_cache[PGD_CACHE_NUM], pgd);
+	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
 }
 
 #ifndef CONFIG_PPC_64K_PAGES
@@ -40,13 +47,13 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(pgtable_cache[PUD_CACHE_NUM],
+	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
 				GFP_KERNEL|__GFP_REPEAT);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 {
-	kmem_cache_free(pgtable_cache[PUD_CACHE_NUM], pud);
+	kmem_cache_free(PGT_CACHE(PUD_INDEX_SIZE), pud);
 }
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
@@ -78,13 +85,13 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(pgtable_cache[PMD_CACHE_NUM],
+	return kmem_cache_alloc(PGT_CACHE(PMD_INDEX_SIZE),
 				GFP_KERNEL|__GFP_REPEAT);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-	kmem_cache_free(pgtable_cache[PMD_CACHE_NUM], pmd);
+	kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
 }
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
@@ -107,24 +114,22 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 	return page;
 }
 
-static inline void pgtable_free(pgtable_free_t pgf)
+static inline void pgtable_free(void *table, unsigned index_size)
 {
-	void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
-	int cachenum = pgf.val & PGF_CACHENUM_MASK;
-
-	if (cachenum == PTE_NONCACHE_NUM)
-		free_page((unsigned long)p);
-	else
-		kmem_cache_free(pgtable_cache[cachenum], p);
+	if (!index_size)
+		free_page((unsigned long)table);
+	else {
+		BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
+		kmem_cache_free(PGT_CACHE(index_size), table);
+	}
 }
 
-#define __pmd_free_tlb(tlb, pmd,addr)		      \
-	pgtable_free_tlb(tlb, pgtable_free_cache(pmd, \
-		PMD_CACHE_NUM, PMD_TABLE_SIZE-1))
+#define __pmd_free_tlb(tlb, pmd, addr)		      \
+	pgtable_free_tlb(tlb, pmd, PMD_INDEX_SIZE)
 #ifndef CONFIG_PPC_64K_PAGES
 #define __pud_free_tlb(tlb, pud, addr)		      \
-	pgtable_free_tlb(tlb, pgtable_free_cache(pud, \
-		PUD_CACHE_NUM, PUD_TABLE_SIZE-1))
+	pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE)
+
 #endif /* CONFIG_PPC_64K_PAGES */
 
 #define check_pgt_cache()	do { } while (0)
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index 1730e5e298d6..df1b4cbb2e70 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -4,6 +4,15 @@
 
 #include <linux/mm.h>
 
+#ifdef CONFIG_PPC_BOOK3E
+extern void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address);
+#else /* CONFIG_PPC_BOOK3E */
+static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
+				     unsigned long address)
+{
+}
+#endif /* !CONFIG_PPC_BOOK3E */
+
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 {
 	free_page((unsigned long)pte);
@@ -15,39 +24,30 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 	__free_page(ptepage);
 }
 
-typedef struct pgtable_free {
-	unsigned long val;
-} pgtable_free_t;
-
-#define PGF_CACHENUM_MASK	0x7
-
-static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
-						unsigned long mask)
-{
-	BUG_ON(cachenum > PGF_CACHENUM_MASK);
-
-	return (pgtable_free_t){.val = ((unsigned long) p & ~mask) | cachenum};
-}
-
 #ifdef CONFIG_PPC64
 #include <asm/pgalloc-64.h>
 #else
 #include <asm/pgalloc-32.h>
 #endif
 
-extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
-
 #ifdef CONFIG_SMP
-#define __pte_free_tlb(tlb,ptepage,address)		\
-do { \
-	pgtable_page_dtor(ptepage); \
-	pgtable_free_tlb(tlb, pgtable_free_cache(page_address(ptepage), \
-					PTE_NONCACHE_NUM, PTE_TABLE_SIZE-1)); \
-} while (0)
-#else
-#define __pte_free_tlb(tlb, pte, address)	pte_free((tlb)->mm, (pte))
-#endif
+extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift);
+extern void pte_free_finish(struct mmu_gather *tlb);
+#else /* CONFIG_SMP */
+static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
+{
+	pgtable_free(table, shift);
+}
+static inline void pte_free_finish(struct mmu_gather *tlb) { }
+#endif /* !CONFIG_SMP */
 
+static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage,
+				  unsigned long address)
+{
+	tlb_flush_pgtable(tlb, address);
+	pgtable_page_dtor(ptepage);
+	pgtable_free_tlb(tlb, page_address(ptepage), 0);
+}
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_PGALLOC_H */
diff --git a/arch/powerpc/include/asm/pgtable-ppc32.h b/arch/powerpc/include/asm/pgtable-ppc32.h
index c9ff9d75990e..55646adfa843 100644
--- a/arch/powerpc/include/asm/pgtable-ppc32.h
+++ b/arch/powerpc/include/asm/pgtable-ppc32.h
@@ -111,6 +111,8 @@ extern int icache_44x_need_flush;
 #include <asm/pte-40x.h>
 #elif defined(CONFIG_44x)
 #include <asm/pte-44x.h>
+#elif defined(CONFIG_FSL_BOOKE) && defined(CONFIG_PTE_64BIT)
+#include <asm/pte-book3e.h>
 #elif defined(CONFIG_FSL_BOOKE)
 #include <asm/pte-fsl-booke.h>
 #elif defined(CONFIG_8xx)
@@ -186,7 +188,7 @@ static inline unsigned long pte_update(pte_t *p,
 #endif /* !PTE_ATOMIC_UPDATES */
 
 #ifdef CONFIG_44x
-	if ((old & _PAGE_USER) && (old & _PAGE_HWEXEC))
+	if ((old & _PAGE_USER) && (old & _PAGE_EXEC))
 		icache_44x_need_flush = 1;
 #endif
 	return old;
@@ -217,7 +219,7 @@ static inline unsigned long long pte_update(pte_t *p,
 #endif /* !PTE_ATOMIC_UPDATES */
 
 #ifdef CONFIG_44x
-	if ((old & _PAGE_USER) && (old & _PAGE_HWEXEC))
+	if ((old & _PAGE_USER) && (old & _PAGE_EXEC))
 		icache_44x_need_flush = 1;
 #endif
 	return old;
@@ -267,8 +269,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 {
 	unsigned long bits = pte_val(entry) &
-		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW |
-		 _PAGE_HWEXEC | _PAGE_EXEC);
+		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
 	pte_update(ptep, 0, bits);
 }
 
diff --git a/arch/powerpc/include/asm/pgtable-ppc64-64k.h b/arch/powerpc/include/asm/pgtable-ppc64-64k.h
index 6cc085b945a5..90533ddcd703 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64-64k.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64-64k.h
@@ -10,10 +10,10 @@
 #define PGD_INDEX_SIZE  4
 
 #ifndef __ASSEMBLY__
-
 #define PTE_TABLE_SIZE	(sizeof(real_pte_t) << PTE_INDEX_SIZE)
 #define PMD_TABLE_SIZE	(sizeof(pmd_t) << PMD_INDEX_SIZE)
 #define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
+#endif	/* __ASSEMBLY__ */
 
 #define PTRS_PER_PTE	(1 << PTE_INDEX_SIZE)
 #define PTRS_PER_PMD	(1 << PMD_INDEX_SIZE)
@@ -32,8 +32,6 @@
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
-#endif	/* __ASSEMBLY__ */
-
 /* Bits to mask out from a PMD to get to the PTE page */
 #define PMD_MASKED_BITS		0x1ff
 /* Bits to mask out from a PGD/PUD to get to the PMD page */
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index a1ddb07a2b90..3b29c9510b0b 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -5,11 +5,6 @@
  * the ppc64 hashed page table.
  */
 
-#ifndef __ASSEMBLY__
-#include <linux/stddef.h>
-#include <asm/tlbflush.h>
-#endif /* __ASSEMBLY__ */
-
 #ifdef CONFIG_PPC_64K_PAGES
 #include <asm/pgtable-ppc64-64k.h>
 #else
@@ -38,26 +33,47 @@
 #endif
 
 /*
- * Define the address range of the vmalloc VM area.
+ * Define the address range of the kernel non-linear virtual area
  */
-#define VMALLOC_START ASM_CONST(0xD000000000000000)
-#define VMALLOC_SIZE  (PGTABLE_RANGE >> 1)
-#define VMALLOC_END   (VMALLOC_START + VMALLOC_SIZE)
+
+#ifdef CONFIG_PPC_BOOK3E
+#define KERN_VIRT_START ASM_CONST(0x8000000000000000)
+#else
+#define KERN_VIRT_START ASM_CONST(0xD000000000000000)
+#endif
+#define KERN_VIRT_SIZE	PGTABLE_RANGE
+
+/*
+ * The vmalloc space starts at the beginning of that region, and
+ * occupies half of it on hash CPUs and a quarter of it on Book3E
+ * (we keep a quarter for the virtual memmap)
+ */
+#define VMALLOC_START	KERN_VIRT_START
+#ifdef CONFIG_PPC_BOOK3E
+#define VMALLOC_SIZE	(KERN_VIRT_SIZE >> 2)
+#else
+#define VMALLOC_SIZE	(KERN_VIRT_SIZE >> 1)
+#endif
+#define VMALLOC_END	(VMALLOC_START + VMALLOC_SIZE)
 
 /*
- * Define the address ranges for MMIO and IO space :
+ * The second half of the kernel virtual space is used for IO mappings,
+ * it's itself carved into the PIO region (ISA and PHB IO space) and
+ * the ioremap space
  *
- *  ISA_IO_BASE = VMALLOC_END, 64K reserved area
+ *  ISA_IO_BASE = KERN_IO_START, 64K reserved area
  *  PHB_IO_BASE = ISA_IO_BASE + 64K to ISA_IO_BASE + 2G, PHB IO spaces
  * IOREMAP_BASE = ISA_IO_BASE + 2G to VMALLOC_START + PGTABLE_RANGE
  */
+#define KERN_IO_START	(KERN_VIRT_START + (KERN_VIRT_SIZE >> 1))
 #define FULL_IO_SIZE	0x80000000ul
-#define  ISA_IO_BASE	(VMALLOC_END)
-#define  ISA_IO_END	(VMALLOC_END + 0x10000ul)
+#define  ISA_IO_BASE	(KERN_IO_START)
+#define  ISA_IO_END	(KERN_IO_START + 0x10000ul)
 #define  PHB_IO_BASE	(ISA_IO_END)
-#define  PHB_IO_END	(VMALLOC_END + FULL_IO_SIZE)
+#define  PHB_IO_END	(KERN_IO_START + FULL_IO_SIZE)
 #define IOREMAP_BASE	(PHB_IO_END)
-#define IOREMAP_END	(VMALLOC_START + PGTABLE_RANGE)
+#define IOREMAP_END	(KERN_VIRT_START + KERN_VIRT_SIZE)
+
 
 /*
  * Region IDs
@@ -68,23 +84,32 @@
 
 #define VMALLOC_REGION_ID	(REGION_ID(VMALLOC_START))
 #define KERNEL_REGION_ID	(REGION_ID(PAGE_OFFSET))
-#define VMEMMAP_REGION_ID	(0xfUL)
+#define VMEMMAP_REGION_ID	(0xfUL)	/* Server only */
 #define USER_REGION_ID		(0UL)
 
 /*
- * Defines the address of the vmemap area, in its own region
+ * Defines the address of the vmemap area, in its own region on
+ * hash table CPUs and after the vmalloc space on Book3E
  */
+#ifdef CONFIG_PPC_BOOK3E
+#define VMEMMAP_BASE		VMALLOC_END
+#define VMEMMAP_END		KERN_IO_START
+#else
 #define VMEMMAP_BASE		(VMEMMAP_REGION_ID << REGION_SHIFT)
+#endif
 #define vmemmap			((struct page *)VMEMMAP_BASE)
 
 
 /*
  * Include the PTE bits definitions
  */
+#ifdef CONFIG_PPC_BOOK3S
 #include <asm/pte-hash64.h>
+#else
+#include <asm/pte-book3e.h>
+#endif
 #include <asm/pte-common.h>
 
-
 #ifdef CONFIG_PPC_MM_SLICES
 #define HAVE_ARCH_UNMAPPED_AREA
 #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
@@ -92,6 +117,9 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/stddef.h>
+#include <asm/tlbflush.h>
+
 /*
  * This is the default implementation of various PTE accessors, it's
  * used in all cases except Book3S with 64K pages where we have a
@@ -292,8 +320,7 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
 static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 {
 	unsigned long bits = pte_val(entry) &
-		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW |
-		 _PAGE_EXEC | _PAGE_HWEXEC);
+		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
 
 #ifdef PTE_ATOMIC_UPDATES
 	unsigned long old, tmp;
@@ -334,6 +361,7 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 #define pgoff_to_pte(off)	((pte_t) {((off) << PTE_RPN_SHIFT)|_PAGE_FILE})
 #define PTE_FILE_MAX_BITS	(BITS_PER_LONG - PTE_RPN_SHIFT)
 
+void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
 void pgtable_cache_init(void);
 
 /*
@@ -358,7 +386,18 @@ void pgtable_cache_init(void);
 	return pt;
 }
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long address);
+#ifdef CONFIG_HUGETLB_PAGE
+pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
+				 unsigned *shift);
+#else
+static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
+					       unsigned *shift)
+{
+	if (shift)
+		*shift = 0;
+	return find_linux_pte(pgdir, ea);
+}
+#endif /* !CONFIG_HUGETLB_PAGE */
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index eb17da781128..21207e54825b 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -104,8 +104,8 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	else
 		pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte));
 
-#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) && defined(CONFIG_SMP)
-	/* Second case is 32-bit with 64-bit PTE in SMP mode. In this case, we
+#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT)
+	/* Second case is 32-bit with 64-bit PTE.  In this case, we
 	 * can just store as long as we do the two halves in the right order
 	 * with a barrier in between. This is possible because we take care,
 	 * in the hash code, to pre-invalidate if the PTE was already hashed,
@@ -140,7 +140,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #else
 	/* Anything else just stores the PTE normally. That covers all 64-bit
-	 * cases, and 32-bit non-hash with 64-bit PTEs in UP mode
+	 * cases, and 32-bit non-hash with 32-bit PTEs.
 	 */
 	*ptep = pte;
 #endif
@@ -211,6 +211,9 @@ extern void paging_init(void);
  */
 extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t);
 
+extern int gup_hugepd(hugepd_t *hugepd, unsigned pdshift, unsigned long addr,
+		      unsigned long end, int write, struct page **pages, int *nr);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/pmac_feature.h b/arch/powerpc/include/asm/pmac_feature.h
index ba117238bb07..00eedc5a4e61 100644
--- a/arch/powerpc/include/asm/pmac_feature.h
+++ b/arch/powerpc/include/asm/pmac_feature.h
@@ -378,7 +378,7 @@ extern struct macio_chip* macio_find(struct device_node* child, int type);
  * Those are exported by pmac feature for internal use by arch code
  * only like the platform function callbacks, do not use directly in drivers
  */
-extern atomic_spinlock_t feature_lock;
+extern raw_spinlock_t feature_lock;
 extern struct device_node *uninorth_node;
 extern u32 __iomem *uninorth_base;
 
diff --git a/arch/powerpc/include/asm/pmac_low_i2c.h b/arch/powerpc/include/asm/pmac_low_i2c.h
index 131011bd7e76..01d71826d92f 100644
--- a/arch/powerpc/include/asm/pmac_low_i2c.h
+++ b/arch/powerpc/include/asm/pmac_low_i2c.h
@@ -72,11 +72,7 @@ extern int pmac_i2c_get_type(struct pmac_i2c_bus *bus);
 extern int pmac_i2c_get_flags(struct pmac_i2c_bus *bus);
 extern int pmac_i2c_get_channel(struct pmac_i2c_bus *bus);
 
-/* i2c layer adapter attach/detach */
-extern void pmac_i2c_attach_adapter(struct pmac_i2c_bus *bus,
-				    struct i2c_adapter *adapter);
-extern void pmac_i2c_detach_adapter(struct pmac_i2c_bus *bus,
-				    struct i2c_adapter *adapter);
+/* i2c layer adapter helpers */
 extern struct i2c_adapter *pmac_i2c_get_adapter(struct pmac_i2c_bus *bus);
 extern struct pmac_i2c_bus *pmac_i2c_adapter_to_bus(struct i2c_adapter *adapter);
 
diff --git a/arch/powerpc/include/asm/pmc.h b/arch/powerpc/include/asm/pmc.h
index d6a616a1b3ea..5a9ede4962cb 100644
--- a/arch/powerpc/include/asm/pmc.h
+++ b/arch/powerpc/include/asm/pmc.h
@@ -27,10 +27,22 @@ extern perf_irq_t perf_irq;
 
 int reserve_pmc_hardware(perf_irq_t new_perf_irq);
 void release_pmc_hardware(void);
+void ppc_enable_pmcs(void);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+#include <asm/lppaca.h>
+
+static inline void ppc_set_pmu_inuse(int inuse)
+{
+	get_lppaca()->pmcregs_in_use = inuse;
+}
+
+extern void power4_enable_pmcs(void);
+
+#else /* CONFIG_PPC64 */
+
+static inline void ppc_set_pmu_inuse(int inuse) { }
 
-#ifdef CONFIG_PPC64
-void power4_enable_pmcs(void);
-void pasemi_enable_pmcs(void);
 #endif
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index b74f16d45cb4..ef9aa84cac5a 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -48,6 +48,8 @@
 #define PPC_INST_TLBIE			0x7c000264
 #define PPC_INST_TLBILX			0x7c000024
 #define PPC_INST_WAIT			0x7c00007c
+#define PPC_INST_TLBIVAX		0x7c000624
+#define PPC_INST_TLBSRX_DOT		0x7c0006a5
 
 /* macros to insert fields into opcodes */
 #define __PPC_RA(a)	(((a) & 0x1f) << 16)
@@ -76,6 +78,10 @@
 					__PPC_WC(w))
 #define PPC_TLBIE(lp,a) 	stringify_in_c(.long PPC_INST_TLBIE | \
 					       __PPC_RB(a) | __PPC_RS(lp))
+#define PPC_TLBSRX_DOT(a,b)	stringify_in_c(.long PPC_INST_TLBSRX_DOT | \
+					__PPC_RA(a) | __PPC_RB(b))
+#define PPC_TLBIVAX(a,b)	stringify_in_c(.long PPC_INST_TLBIVAX | \
+					__PPC_RA(a) | __PPC_RB(b))
 
 /*
  * Define what the VSX XX1 form instructions will look like, then add
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index 854ab713f56c..2828f9d0f66d 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -39,7 +39,6 @@ void *traverse_pci_devices(struct device_node *start, traverse_func pre,
 
 extern void pci_devs_phb_init(void);
 extern void pci_devs_phb_init_dynamic(struct pci_controller *phb);
-extern void scan_phb(struct pci_controller *hose);
 
 /* From rtas_pci.h */
 extern void init_pci_config_tokens (void);
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index f9729529c20d..498fe09263d3 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -98,13 +98,13 @@ END_FTR_SECTION_IFCLR(CPU_FTR_PURR);					\
 #define REST_16FPRS(n, base)	REST_8FPRS(n, base); REST_8FPRS(n+8, base)
 #define REST_32FPRS(n, base)	REST_16FPRS(n, base); REST_16FPRS(n+16, base)
 
-#define SAVE_VR(n,b,base)	li b,THREAD_VR0+(16*(n));  stvx n,b,base
+#define SAVE_VR(n,b,base)	li b,THREAD_VR0+(16*(n));  stvx n,base,b
 #define SAVE_2VRS(n,b,base)	SAVE_VR(n,b,base); SAVE_VR(n+1,b,base)
 #define SAVE_4VRS(n,b,base)	SAVE_2VRS(n,b,base); SAVE_2VRS(n+2,b,base)
 #define SAVE_8VRS(n,b,base)	SAVE_4VRS(n,b,base); SAVE_4VRS(n+4,b,base)
 #define SAVE_16VRS(n,b,base)	SAVE_8VRS(n,b,base); SAVE_8VRS(n+8,b,base)
 #define SAVE_32VRS(n,b,base)	SAVE_16VRS(n,b,base); SAVE_16VRS(n+16,b,base)
-#define REST_VR(n,b,base)	li b,THREAD_VR0+(16*(n)); lvx n,b,base
+#define REST_VR(n,b,base)	li b,THREAD_VR0+(16*(n)); lvx n,base,b
 #define REST_2VRS(n,b,base)	REST_VR(n,b,base); REST_VR(n+1,b,base)
 #define REST_4VRS(n,b,base)	REST_2VRS(n,b,base); REST_2VRS(n+2,b,base)
 #define REST_8VRS(n,b,base)	REST_4VRS(n,b,base); REST_4VRS(n+4,b,base)
@@ -112,26 +112,26 @@ END_FTR_SECTION_IFCLR(CPU_FTR_PURR);					\
 #define REST_32VRS(n,b,base)	REST_16VRS(n,b,base); REST_16VRS(n+16,b,base)
 
 /* Save the lower 32 VSRs in the thread VSR region */
-#define SAVE_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n));  STXVD2X(n,b,base)
+#define SAVE_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n));  STXVD2X(n,base,b)
 #define SAVE_2VSRS(n,b,base)	SAVE_VSR(n,b,base); SAVE_VSR(n+1,b,base)
 #define SAVE_4VSRS(n,b,base)	SAVE_2VSRS(n,b,base); SAVE_2VSRS(n+2,b,base)
 #define SAVE_8VSRS(n,b,base)	SAVE_4VSRS(n,b,base); SAVE_4VSRS(n+4,b,base)
 #define SAVE_16VSRS(n,b,base)	SAVE_8VSRS(n,b,base); SAVE_8VSRS(n+8,b,base)
 #define SAVE_32VSRS(n,b,base)	SAVE_16VSRS(n,b,base); SAVE_16VSRS(n+16,b,base)
-#define REST_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n)); LXVD2X(n,b,base)
+#define REST_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n)); LXVD2X(n,base,b)
 #define REST_2VSRS(n,b,base)	REST_VSR(n,b,base); REST_VSR(n+1,b,base)
 #define REST_4VSRS(n,b,base)	REST_2VSRS(n,b,base); REST_2VSRS(n+2,b,base)
 #define REST_8VSRS(n,b,base)	REST_4VSRS(n,b,base); REST_4VSRS(n+4,b,base)
 #define REST_16VSRS(n,b,base)	REST_8VSRS(n,b,base); REST_8VSRS(n+8,b,base)
 #define REST_32VSRS(n,b,base)	REST_16VSRS(n,b,base); REST_16VSRS(n+16,b,base)
 /* Save the upper 32 VSRs (32-63) in the thread VSX region (0-31) */
-#define SAVE_VSRU(n,b,base)	li b,THREAD_VR0+(16*(n));  STXVD2X(n+32,b,base)
+#define SAVE_VSRU(n,b,base)	li b,THREAD_VR0+(16*(n));  STXVD2X(n+32,base,b)
 #define SAVE_2VSRSU(n,b,base)	SAVE_VSRU(n,b,base); SAVE_VSRU(n+1,b,base)
 #define SAVE_4VSRSU(n,b,base)	SAVE_2VSRSU(n,b,base); SAVE_2VSRSU(n+2,b,base)
 #define SAVE_8VSRSU(n,b,base)	SAVE_4VSRSU(n,b,base); SAVE_4VSRSU(n+4,b,base)
 #define SAVE_16VSRSU(n,b,base)	SAVE_8VSRSU(n,b,base); SAVE_8VSRSU(n+8,b,base)
 #define SAVE_32VSRSU(n,b,base)	SAVE_16VSRSU(n,b,base); SAVE_16VSRSU(n+16,b,base)
-#define REST_VSRU(n,b,base)	li b,THREAD_VR0+(16*(n)); LXVD2X(n+32,b,base)
+#define REST_VSRU(n,b,base)	li b,THREAD_VR0+(16*(n)); LXVD2X(n+32,base,b)
 #define REST_2VSRSU(n,b,base)	REST_VSRU(n,b,base); REST_VSRU(n+1,b,base)
 #define REST_4VSRSU(n,b,base)	REST_2VSRSU(n,b,base); REST_2VSRSU(n+2,b,base)
 #define REST_8VSRSU(n,b,base)	REST_4VSRSU(n,b,base); REST_4VSRSU(n+4,b,base)
@@ -375,8 +375,15 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 #define PPC440EP_ERR42
 #endif
 
-
-#if defined(CONFIG_BOOKE)
+/*
+ * toreal/fromreal/tophys/tovirt macros. 32-bit BookE makes them
+ * keep the address intact to be compatible with code shared with
+ * 32-bit classic.
+ *
+ * On the other hand, I find it useful to have them behave as expected
+ * by their name (ie always do the addition) on 64-bit BookE
+ */
+#if defined(CONFIG_BOOKE) && !defined(CONFIG_PPC64)
 #define toreal(rd)
 #define fromreal(rd)
 
@@ -426,10 +433,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 	.previous
 #endif
 
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S_64
 #define RFI		rfid
 #define MTMSRD(r)	mtmsrd	r
-
 #else
 #define FIX_SRR1(ra, rb)
 #ifndef CONFIG_40x
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 6ff04185d2aa..2ab9cbd98826 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -1,3 +1,4 @@
+#include <linux/of.h>	/* linux/of.h gets to determine #include ordering */
 #ifndef _POWERPC_PROM_H
 #define _POWERPC_PROM_H
 #ifdef __KERNEL__
@@ -16,6 +17,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 #include <linux/types.h>
+#include <linux/of_fdt.h>
 #include <linux/proc_fs.h>
 #include <linux/platform_device.h>
 #include <asm/irq.h>
@@ -28,133 +30,14 @@
 #define of_prop_cmp(s1, s2)		strcmp((s1), (s2))
 #define of_node_cmp(s1, s2)		strcasecmp((s1), (s2))
 
-/* Definitions used by the flattened device tree */
-#define OF_DT_HEADER		0xd00dfeed	/* marker */
-#define OF_DT_BEGIN_NODE	0x1		/* Start of node, full name */
-#define OF_DT_END_NODE		0x2		/* End node */
-#define OF_DT_PROP		0x3		/* Property: name off, size,
-						 * content */
-#define OF_DT_NOP		0x4		/* nop */
-#define OF_DT_END		0x9
-
-#define OF_DT_VERSION		0x10
-
-/*
- * This is what gets passed to the kernel by prom_init or kexec
- *
- * The dt struct contains the device tree structure, full pathes and
- * property contents. The dt strings contain a separate block with just
- * the strings for the property names, and is fully page aligned and
- * self contained in a page, so that it can be kept around by the kernel,
- * each property name appears only once in this page (cheap compression)
- *
- * the mem_rsvmap contains a map of reserved ranges of physical memory,
- * passing it here instead of in the device-tree itself greatly simplifies
- * the job of everybody. It's just a list of u64 pairs (base/size) that
- * ends when size is 0
- */
-struct boot_param_header
-{
-	u32	magic;			/* magic word OF_DT_HEADER */
-	u32	totalsize;		/* total size of DT block */
-	u32	off_dt_struct;		/* offset to structure */
-	u32	off_dt_strings;		/* offset to strings */
-	u32	off_mem_rsvmap;		/* offset to memory reserve map */
-	u32	version;		/* format version */
-	u32	last_comp_version;	/* last compatible version */
-	/* version 2 fields below */
-	u32	boot_cpuid_phys;	/* Physical CPU id we're booting on */
-	/* version 3 fields below */
-	u32	dt_strings_size;	/* size of the DT strings block */
-	/* version 17 fields below */
-	u32	dt_struct_size;		/* size of the DT structure block */
-};
-
-
-
-typedef u32 phandle;
-typedef u32 ihandle;
-
-struct property {
-	char	*name;
-	int	length;
-	void	*value;
-	struct property *next;
-};
-
-struct device_node {
-	const char *name;
-	const char *type;
-	phandle	node;
-	phandle linux_phandle;
-	char	*full_name;
-
-	struct	property *properties;
-	struct  property *deadprops; /* removed properties */
-	struct	device_node *parent;
-	struct	device_node *child;
-	struct	device_node *sibling;
-	struct	device_node *next;	/* next device of same type */
-	struct	device_node *allnext;	/* next in list of all nodes */
-	struct  proc_dir_entry *pde;	/* this node's proc directory */
-	struct  kref kref;
-	unsigned long _flags;
-	void	*data;
-};
-
 extern struct device_node *of_chosen;
 
-static inline int of_node_check_flag(struct device_node *n, unsigned long flag)
-{
-	return test_bit(flag, &n->_flags);
-}
-
-static inline void of_node_set_flag(struct device_node *n, unsigned long flag)
-{
-	set_bit(flag, &n->_flags);
-}
-
-
 #define HAVE_ARCH_DEVTREE_FIXUPS
 
-static inline void set_node_proc_entry(struct device_node *dn, struct proc_dir_entry *de)
-{
-	dn->pde = de;
-}
-
-
-extern struct device_node *of_find_all_nodes(struct device_node *prev);
-extern struct device_node *of_node_get(struct device_node *node);
-extern void of_node_put(struct device_node *node);
-
-/* For scanning the flat device-tree at boot time */
-extern int __init of_scan_flat_dt(int (*it)(unsigned long node,
-					    const char *uname, int depth,
-					    void *data),
-				  void *data);
-extern void* __init of_get_flat_dt_prop(unsigned long node, const char *name,
-					unsigned long *size);
-extern int __init of_flat_dt_is_compatible(unsigned long node, const char *name);
-extern unsigned long __init of_get_flat_dt_root(void);
-
 /* For updating the device tree at runtime */
 extern void of_attach_node(struct device_node *);
 extern void of_detach_node(struct device_node *);
 
-/* Other Prototypes */
-extern void finish_device_tree(void);
-extern void unflatten_device_tree(void);
-extern void early_init_devtree(void *);
-extern int machine_is_compatible(const char *compat);
-extern void print_properties(struct device_node *node);
-extern int prom_n_intr_cells(struct device_node* np);
-extern void prom_get_irq_senses(unsigned char *senses, int off, int max);
-extern int prom_add_property(struct device_node* np, struct property* prop);
-extern int prom_remove_property(struct device_node *np, struct property *prop);
-extern int prom_update_property(struct device_node *np,
-				struct property *newprop,
-				struct property *oldprop);
-
 #ifdef CONFIG_PPC32
 /*
  * PCI <-> OF matching functions
@@ -178,26 +61,6 @@ extern int release_OF_resource(struct device_node* node, int index);
  * OF address retreival & translation
  */
 
-
-/* Helper to read a big number; size is in cells (not bytes) */
-static inline u64 of_read_number(const u32 *cell, int size)
-{
-	u64 r = 0;
-	while (size--)
-		r = (r << 32) | *(cell++);
-	return r;
-}
-
-/* Like of_read_number, but we want an unsigned long result */
-#ifdef CONFIG_PPC32
-static inline unsigned long of_read_ulong(const u32 *cell, int size)
-{
-	return cell[size-1];
-}
-#else
-#define of_read_ulong(cell, size)	of_read_number(cell, size)
-#endif
-
 /* Translate an OF address block into a CPU physical address
  */
 extern u64 of_translate_address(struct device_node *np, const u32 *addr);
@@ -349,11 +212,5 @@ extern int of_irq_to_resource(struct device_node *dev, int index,
  */
 extern void __iomem *of_iomap(struct device_node *device, int index);
 
-/*
- * NB:  This is here while we transition from using asm/prom.h
- * to linux/of.h
- */
-#include <linux/of.h>
-
 #endif /* __KERNEL__ */
 #endif /* _POWERPC_PROM_H */
diff --git a/arch/powerpc/include/asm/pte-40x.h b/arch/powerpc/include/asm/pte-40x.h
index 07630faae029..ec0b0b0d1df9 100644
--- a/arch/powerpc/include/asm/pte-40x.h
+++ b/arch/powerpc/include/asm/pte-40x.h
@@ -43,10 +43,11 @@
 #define	_PAGE_NO_CACHE	0x004	/* I: caching is inhibited */
 #define	_PAGE_WRITETHRU	0x008	/* W: caching is write-through */
 #define	_PAGE_USER	0x010	/* matches one of the zone permission bits */
+#define	_PAGE_SPECIAL	0x020	/* software: Special page */
 #define	_PAGE_RW	0x040	/* software: Writes permitted */
 #define	_PAGE_DIRTY	0x080	/* software: dirty page */
 #define _PAGE_HWWRITE	0x100	/* hardware: Dirty & RW, set in exception */
-#define _PAGE_HWEXEC	0x200	/* hardware: EX permission */
+#define _PAGE_EXEC	0x200	/* hardware: EX permission */
 #define _PAGE_ACCESSED	0x400	/* software: R: page referenced */
 
 #define _PMD_PRESENT	0x400	/* PMD points to page of PTEs */
diff --git a/arch/powerpc/include/asm/pte-44x.h b/arch/powerpc/include/asm/pte-44x.h
index 37e98bcf83e0..4192b9bad901 100644
--- a/arch/powerpc/include/asm/pte-44x.h
+++ b/arch/powerpc/include/asm/pte-44x.h
@@ -78,7 +78,7 @@
 #define _PAGE_PRESENT	0x00000001		/* S: PTE valid */
 #define _PAGE_RW	0x00000002		/* S: Write permission */
 #define _PAGE_FILE	0x00000004		/* S: nonlinear file mapping */
-#define _PAGE_HWEXEC	0x00000004		/* H: Execute permission */
+#define _PAGE_EXEC	0x00000004		/* H: Execute permission */
 #define _PAGE_ACCESSED	0x00000008		/* S: Page referenced */
 #define _PAGE_DIRTY	0x00000010		/* S: Page dirty */
 #define _PAGE_SPECIAL	0x00000020		/* S: Special page */
diff --git a/arch/powerpc/include/asm/pte-8xx.h b/arch/powerpc/include/asm/pte-8xx.h
index 8c6e31251034..d44826e4ff97 100644
--- a/arch/powerpc/include/asm/pte-8xx.h
+++ b/arch/powerpc/include/asm/pte-8xx.h
@@ -32,22 +32,22 @@
 #define _PAGE_FILE	0x0002	/* when !present: nonlinear file mapping */
 #define _PAGE_NO_CACHE	0x0002	/* I: cache inhibit */
 #define _PAGE_SHARED	0x0004	/* No ASID (context) compare */
+#define _PAGE_SPECIAL	0x0008	/* SW entry, forced to 0 by the TLB miss */
+#define _PAGE_DIRTY	0x0100	/* C: page changed */
 
-/* These five software bits must be masked out when the entry is loaded
- * into the TLB.
+/* These 4 software bits must be masked out when the entry is loaded
+ * into the TLB, 1 SW bit left(0x0080).
  */
-#define _PAGE_EXEC	0x0008	/* software: i-cache coherency required */
 #define _PAGE_GUARDED	0x0010	/* software: guarded access */
-#define _PAGE_DIRTY	0x0020	/* software: page changed */
-#define _PAGE_RW	0x0040	/* software: user write access allowed */
-#define _PAGE_ACCESSED	0x0080	/* software: page referenced */
+#define _PAGE_ACCESSED	0x0020	/* software: page referenced */
+#define _PAGE_WRITETHRU	0x0040	/* software: caching is write through */
 
 /* Setting any bits in the nibble with the follow two controls will
  * require a TLB exception handler change.  It is assumed unused bits
  * are always zero.
  */
-#define _PAGE_HWWRITE	0x0100	/* h/w write enable: never set in Linux PTE */
-#define _PAGE_USER	0x0800	/* One of the PP bits, the other is USER&~RW */
+#define _PAGE_RW	0x0400	/* lsb PP bits, inverted in HW */
+#define _PAGE_USER	0x0800	/* msb PP bits */
 
 #define _PMD_PRESENT	0x0001
 #define _PMD_BAD	0x0ff0
diff --git a/arch/powerpc/include/asm/pte-book3e.h b/arch/powerpc/include/asm/pte-book3e.h
new file mode 100644
index 000000000000..082d515930a2
--- /dev/null
+++ b/arch/powerpc/include/asm/pte-book3e.h
@@ -0,0 +1,84 @@
+#ifndef _ASM_POWERPC_PTE_BOOK3E_H
+#define _ASM_POWERPC_PTE_BOOK3E_H
+#ifdef __KERNEL__
+
+/* PTE bit definitions for processors compliant to the Book3E
+ * architecture 2.06 or later. The position of the PTE bits
+ * matches the HW definition of the optional Embedded Page Table
+ * category.
+ */
+
+/* Architected bits */
+#define _PAGE_PRESENT	0x000001 /* software: pte contains a translation */
+#define _PAGE_FILE	0x000002 /* (!present only) software: pte holds file offset */
+#define _PAGE_SW1	0x000002
+#define _PAGE_BAP_SR	0x000004
+#define _PAGE_BAP_UR	0x000008
+#define _PAGE_BAP_SW	0x000010
+#define _PAGE_BAP_UW	0x000020
+#define _PAGE_BAP_SX	0x000040
+#define _PAGE_BAP_UX	0x000080
+#define _PAGE_PSIZE_MSK	0x000f00
+#define _PAGE_PSIZE_4K	0x000200
+#define _PAGE_PSIZE_8K	0x000300
+#define _PAGE_PSIZE_16K	0x000400
+#define _PAGE_PSIZE_32K	0x000500
+#define _PAGE_PSIZE_64K	0x000600
+#define _PAGE_PSIZE_128K	0x000700
+#define _PAGE_PSIZE_256K	0x000800
+#define _PAGE_PSIZE_512K	0x000900
+#define _PAGE_PSIZE_1M	0x000a00
+#define _PAGE_PSIZE_2M	0x000b00
+#define _PAGE_PSIZE_4M	0x000c00
+#define _PAGE_PSIZE_8M	0x000d00
+#define _PAGE_PSIZE_16M	0x000e00
+#define _PAGE_PSIZE_32M	0x000f00
+#define _PAGE_DIRTY	0x001000 /* C: page changed */
+#define _PAGE_SW0	0x002000
+#define _PAGE_U3	0x004000
+#define _PAGE_U2	0x008000
+#define _PAGE_U1	0x010000
+#define _PAGE_U0	0x020000
+#define _PAGE_ACCESSED	0x040000
+#define _PAGE_LENDIAN	0x080000
+#define _PAGE_GUARDED	0x100000
+#define _PAGE_COHERENT	0x200000 /* M: enforce memory coherence */
+#define _PAGE_NO_CACHE	0x400000 /* I: cache inhibit */
+#define _PAGE_WRITETHRU	0x800000 /* W: cache write-through */
+
+/* "Higher level" linux bit combinations */
+#define _PAGE_EXEC		_PAGE_BAP_UX /* .. and was cache cleaned */
+#define _PAGE_RW		(_PAGE_BAP_SW | _PAGE_BAP_UW) /* User write permission */
+#define _PAGE_KERNEL_RW		(_PAGE_BAP_SW | _PAGE_BAP_SR | _PAGE_DIRTY)
+#define _PAGE_KERNEL_RO		(_PAGE_BAP_SR)
+#define _PAGE_KERNEL_RWX	(_PAGE_BAP_SW | _PAGE_BAP_SR | _PAGE_DIRTY | _PAGE_BAP_SX)
+#define _PAGE_KERNEL_ROX	(_PAGE_BAP_SR | _PAGE_BAP_SX)
+#define _PAGE_USER		(_PAGE_BAP_UR | _PAGE_BAP_SR) /* Can be read */
+
+#define _PAGE_HASHPTE	0
+#define _PAGE_BUSY	0
+
+#define _PAGE_SPECIAL	_PAGE_SW0
+
+/* Flags to be preserved on PTE modifications */
+#define _PAGE_HPTEFLAGS	_PAGE_BUSY
+
+/* Base page size */
+#ifdef CONFIG_PPC_64K_PAGES
+#define _PAGE_PSIZE	_PAGE_PSIZE_64K
+#define PTE_RPN_SHIFT	(28)
+#else
+#define _PAGE_PSIZE	_PAGE_PSIZE_4K
+#define	PTE_RPN_SHIFT	(24)
+#endif
+
+/* On 32-bit, we never clear the top part of the PTE */
+#ifdef CONFIG_PPC32
+#define _PTE_NONE_MASK	0xffffffff00000000ULL
+#define _PMD_PRESENT	0
+#define _PMD_PRESENT_MASK (PAGE_MASK)
+#define _PMD_BAD	(~PAGE_MASK)
+#endif
+
+#endif /* __KERNEL__ */
+#endif /*  _ASM_POWERPC_PTE_FSL_BOOKE_H */
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
index a7e210b6b48c..f2b370180a09 100644
--- a/arch/powerpc/include/asm/pte-common.h
+++ b/arch/powerpc/include/asm/pte-common.h
@@ -13,9 +13,6 @@
 #ifndef _PAGE_HWWRITE
 #define _PAGE_HWWRITE	0
 #endif
-#ifndef _PAGE_HWEXEC
-#define _PAGE_HWEXEC	0
-#endif
 #ifndef _PAGE_EXEC
 #define _PAGE_EXEC	0
 #endif
@@ -28,12 +25,12 @@
 #ifndef _PAGE_WRITETHRU
 #define _PAGE_WRITETHRU	0
 #endif
-#ifndef _PAGE_SPECIAL
-#define _PAGE_SPECIAL	0
-#endif
 #ifndef _PAGE_4K_PFN
 #define _PAGE_4K_PFN		0
 #endif
+#ifndef _PAGE_SAO
+#define _PAGE_SAO	0
+#endif
 #ifndef _PAGE_PSIZE
 #define _PAGE_PSIZE		0
 #endif
@@ -45,10 +42,16 @@
 #define PMD_PAGE_SIZE(pmd)	bad_call_to_PMD_PAGE_SIZE()
 #endif
 #ifndef _PAGE_KERNEL_RO
-#define _PAGE_KERNEL_RO	0
+#define _PAGE_KERNEL_RO		0
+#endif
+#ifndef _PAGE_KERNEL_ROX
+#define _PAGE_KERNEL_ROX	(_PAGE_EXEC)
 #endif
 #ifndef _PAGE_KERNEL_RW
-#define _PAGE_KERNEL_RW	(_PAGE_DIRTY | _PAGE_RW | _PAGE_HWWRITE)
+#define _PAGE_KERNEL_RW		(_PAGE_DIRTY | _PAGE_RW | _PAGE_HWWRITE)
+#endif
+#ifndef _PAGE_KERNEL_RWX
+#define _PAGE_KERNEL_RWX	(_PAGE_DIRTY | _PAGE_RW | _PAGE_HWWRITE | _PAGE_EXEC)
 #endif
 #ifndef _PAGE_HPTEFLAGS
 #define _PAGE_HPTEFLAGS _PAGE_HASHPTE
@@ -93,8 +96,7 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
 #define PAGE_PROT_BITS	(_PAGE_GUARDED | _PAGE_COHERENT | _PAGE_NO_CACHE | \
 			 _PAGE_WRITETHRU | _PAGE_ENDIAN | _PAGE_4K_PFN | \
 			 _PAGE_USER | _PAGE_ACCESSED | \
-			 _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | \
-			 _PAGE_EXEC | _PAGE_HWEXEC)
+			 _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | _PAGE_EXEC)
 
 /*
  * We define 2 sets of base prot bits, one for basic pages (ie,
@@ -151,11 +153,9 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
 				 _PAGE_NO_CACHE)
 #define PAGE_KERNEL_NCG	__pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \
 				 _PAGE_NO_CACHE | _PAGE_GUARDED)
-#define PAGE_KERNEL_X	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RW | _PAGE_EXEC | \
-				 _PAGE_HWEXEC)
+#define PAGE_KERNEL_X	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX)
 #define PAGE_KERNEL_RO	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RO)
-#define PAGE_KERNEL_ROX	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RO | _PAGE_EXEC | \
-				 _PAGE_HWEXEC)
+#define PAGE_KERNEL_ROX	__pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX)
 
 /* Protection used for kernel text. We want the debuggers to be able to
  * set breakpoints anywhere, so don't write protect the kernel text
@@ -176,7 +176,5 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
 #define HAVE_PAGE_AGP
 
 /* Advertise support for _PAGE_SPECIAL */
-#ifdef _PAGE_SPECIAL
 #define __HAVE_ARCH_PTE_SPECIAL
-#endif
 
diff --git a/arch/powerpc/include/asm/pte-fsl-booke.h b/arch/powerpc/include/asm/pte-fsl-booke.h
index 10820f58acf5..2c12be5f677a 100644
--- a/arch/powerpc/include/asm/pte-fsl-booke.h
+++ b/arch/powerpc/include/asm/pte-fsl-booke.h
@@ -23,7 +23,7 @@
 #define _PAGE_FILE	0x00002	/* S: when !present: nonlinear file mapping */
 #define _PAGE_RW	0x00004	/* S: Write permission (SW) */
 #define _PAGE_DIRTY	0x00008	/* S: Page dirty */
-#define _PAGE_HWEXEC	0x00010	/* H: SX permission */
+#define _PAGE_EXEC	0x00010	/* H: SX permission */
 #define _PAGE_ACCESSED	0x00020	/* S: Page referenced */
 
 #define _PAGE_ENDIAN	0x00040	/* H: E bit */
@@ -33,13 +33,6 @@
 #define _PAGE_WRITETHRU	0x00400	/* H: W bit */
 #define _PAGE_SPECIAL	0x00800 /* S: Special page */
 
-#ifdef CONFIG_PTE_64BIT
-/* ERPN in a PTE never gets cleared, ignore it */
-#define _PTE_NONE_MASK	0xffffffffffff0000ULL
-/* We extend the size of the PTE flags area when using 64-bit PTEs */
-#define PTE_RPN_SHIFT	(PAGE_SHIFT + 8)
-#endif
-
 #define _PMD_PRESENT	0
 #define _PMD_PRESENT_MASK (PAGE_MASK)
 #define _PMD_BAD	(~PAGE_MASK)
diff --git a/arch/powerpc/include/asm/pte-hash32.h b/arch/powerpc/include/asm/pte-hash32.h
index 16e571c7f9ef..4aad4132d0a8 100644
--- a/arch/powerpc/include/asm/pte-hash32.h
+++ b/arch/powerpc/include/asm/pte-hash32.h
@@ -26,7 +26,6 @@
 #define _PAGE_WRITETHRU	0x040	/* W: cache write-through */
 #define _PAGE_DIRTY	0x080	/* C: page changed */
 #define _PAGE_ACCESSED	0x100	/* R: page referenced */
-#define _PAGE_EXEC	0x200	/* software: i-cache coherency required */
 #define _PAGE_RW	0x400	/* software: user write access allowed */
 #define _PAGE_SPECIAL	0x800	/* software: Special page */
 
diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h
index 82b72207c51c..c4490f9c67c4 100644
--- a/arch/powerpc/include/asm/pte-hash64-64k.h
+++ b/arch/powerpc/include/asm/pte-hash64-64k.h
@@ -76,41 +76,4 @@
 	remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE,		\
 			__pgprot(pgprot_val((prot)) | _PAGE_4K_PFN))
 
-
-#ifdef CONFIG_PPC_SUBPAGE_PROT
-/*
- * For the sub-page protection option, we extend the PGD with one of
- * these.  Basically we have a 3-level tree, with the top level being
- * the protptrs array.  To optimize speed and memory consumption when
- * only addresses < 4GB are being protected, pointers to the first
- * four pages of sub-page protection words are stored in the low_prot
- * array.
- * Each page of sub-page protection words protects 1GB (4 bytes
- * protects 64k).  For the 3-level tree, each page of pointers then
- * protects 8TB.
- */
-struct subpage_prot_table {
-	unsigned long maxaddr;	/* only addresses < this are protected */
-	unsigned int **protptrs[2];
-	unsigned int *low_prot[4];
-};
-
-#undef PGD_TABLE_SIZE
-#define PGD_TABLE_SIZE		((sizeof(pgd_t) << PGD_INDEX_SIZE) + \
-				 sizeof(struct subpage_prot_table))
-
-#define SBP_L1_BITS		(PAGE_SHIFT - 2)
-#define SBP_L2_BITS		(PAGE_SHIFT - 3)
-#define SBP_L1_COUNT		(1 << SBP_L1_BITS)
-#define SBP_L2_COUNT		(1 << SBP_L2_BITS)
-#define SBP_L2_SHIFT		(PAGE_SHIFT + SBP_L1_BITS)
-#define SBP_L3_SHIFT		(SBP_L2_SHIFT + SBP_L2_BITS)
-
-extern void subpage_prot_free(pgd_t *pgd);
-
-static inline struct subpage_prot_table *pgd_subpage_prot(pgd_t *pgd)
-{
-	return (struct subpage_prot_table *)(pgd + PTRS_PER_PGD);
-}
-#endif /* CONFIG_PPC_SUBPAGE_PROT */
 #endif	/* __ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 8c341490cfc5..cbd759e3cd78 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -140,6 +140,8 @@ extern void user_enable_single_step(struct task_struct *);
 extern void user_enable_block_step(struct task_struct *);
 extern void user_disable_single_step(struct task_struct *);
 
+#define ARCH_HAS_USER_SINGLE_STEP_INFO
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/qe.h b/arch/powerpc/include/asm/qe.h
index 157c5ca581c8..0947b36e534c 100644
--- a/arch/powerpc/include/asm/qe.h
+++ b/arch/powerpc/include/asm/qe.h
@@ -87,7 +87,7 @@ extern spinlock_t cmxgcr_lock;
 
 /* Export QE common operations */
 #ifdef CONFIG_QUICC_ENGINE
-extern void __init qe_reset(void);
+extern void qe_reset(void);
 #else
 static inline void qe_reset(void) {}
 #endif
@@ -145,8 +145,17 @@ static inline void qe_pin_set_gpio(struct qe_pin *qe_pin) {}
 static inline void qe_pin_set_dedicated(struct qe_pin *pin) {}
 #endif /* CONFIG_QE_GPIO */
 
-/* QE internal API */
+#ifdef CONFIG_QUICC_ENGINE
 int qe_issue_cmd(u32 cmd, u32 device, u8 mcn_protocol, u32 cmd_input);
+#else
+static inline int qe_issue_cmd(u32 cmd, u32 device, u8 mcn_protocol,
+			       u32 cmd_input)
+{
+	return -ENOSYS;
+}
+#endif /* CONFIG_QUICC_ENGINE */
+
+/* QE internal API */
 enum qe_clock qe_clock_source(const char *source);
 unsigned int qe_get_brg_clk(void);
 int qe_setbrg(enum qe_clock brg, unsigned int rate, unsigned int multiplier);
@@ -155,6 +164,28 @@ void qe_put_snum(u8 snum);
 unsigned int qe_get_num_of_risc(void);
 unsigned int qe_get_num_of_snums(void);
 
+static inline int qe_alive_during_sleep(void)
+{
+	/*
+	 * MPC8568E reference manual says:
+	 *
+	 * "...power down sequence waits for all I/O interfaces to become idle.
+	 *  In some applications this may happen eventually without actively
+	 *  shutting down interfaces, but most likely, software will have to
+	 *  take steps to shut down the eTSEC, QUICC Engine Block, and PCI
+	 *  interfaces before issuing the command (either the write to the core
+	 *  MSR[WE] as described above or writing to POWMGTCSR) to put the
+	 *  device into sleep state."
+	 *
+	 * MPC8569E reference manual has a similar paragraph.
+	 */
+#ifdef CONFIG_PPC_85xx
+	return 0;
+#else
+	return 1;
+#endif
+}
+
 /* we actually use cpm_muram implementation, define this for convenience */
 #define qe_muram_init cpm_muram_init
 #define qe_muram_alloc cpm_muram_alloc
@@ -209,8 +240,15 @@ struct qe_firmware_info {
 	u64 extended_modes;	/* Extended modes */
 };
 
+#ifdef CONFIG_QUICC_ENGINE
 /* Upload a firmware to the QE */
 int qe_upload_firmware(const struct qe_firmware *firmware);
+#else
+static inline int qe_upload_firmware(const struct qe_firmware *firmware)
+{
+	return -ENOSYS;
+}
+#endif /* CONFIG_QUICC_ENGINE */
 
 /* Obtain information on the uploaded firmware */
 struct qe_firmware_info *qe_get_firmware_info(void);
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 1170267736d3..bc8dd53f718a 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -98,19 +98,15 @@
 #define MSR_RI		__MASK(MSR_RI_LG)	/* Recoverable Exception */
 #define MSR_LE		__MASK(MSR_LE_LG)	/* Little Endian */
 
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC_BOOK3S_64)
+/* Server variant */
 #define MSR_		MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV
 #define MSR_KERNEL      MSR_ | MSR_SF
-
 #define MSR_USER32	MSR_ | MSR_PR | MSR_EE
 #define MSR_USER64	MSR_USER32 | MSR_SF
-
-#else /* 32-bit */
+#elif defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_8xx)
 /* Default MSR for kernel mode. */
-#ifndef MSR_KERNEL	/* reg_booke.h also defines this */
 #define MSR_KERNEL	(MSR_ME|MSR_RI|MSR_IR|MSR_DR)
-#endif
-
 #define MSR_USER	(MSR_KERNEL|MSR_PR|MSR_EE)
 #endif
 
@@ -493,6 +489,8 @@
 #define SPRN_MMCR1	798
 #define SPRN_MMCRA	0x312
 #define   MMCRA_SDSYNC	0x80000000UL /* SDAR synced with SIAR */
+#define   MMCRA_SDAR_DCACHE_MISS 0x40000000UL
+#define   MMCRA_SDAR_ERAT_MISS   0x20000000UL
 #define   MMCRA_SIHV	0x10000000UL /* state of MSR HV when SIAR set */
 #define   MMCRA_SIPR	0x08000000UL /* state of MSR PR when SIAR set */
 #define   MMCRA_SLOT	0x07000000UL /* SLOT bits (37-39) */
@@ -646,6 +644,137 @@
 #endif
 
 /*
+ * SPRG usage:
+ *
+ * All 64-bit:
+ *	- SPRG1 stores PACA pointer
+ *
+ * 64-bit server:
+ *	- SPRG0 unused (reserved for HV on Power4)
+ *	- SPRG2 scratch for exception vectors
+ *	- SPRG3 unused (user visible)
+ *
+ * 64-bit embedded
+ *	- SPRG0 generic exception scratch
+ *	- SPRG2 TLB exception stack
+ *	- SPRG3 unused (user visible)
+ *	- SPRG4 unused (user visible)
+ *	- SPRG6 TLB miss scratch (user visible, sorry !)
+ *	- SPRG7 critical exception scratch
+ *	- SPRG8 machine check exception scratch
+ *	- SPRG9 debug exception scratch
+ *
+ * All 32-bit:
+ *	- SPRG3 current thread_info pointer
+ *        (virtual on BookE, physical on others)
+ *
+ * 32-bit classic:
+ *	- SPRG0 scratch for exception vectors
+ *	- SPRG1 scratch for exception vectors
+ *	- SPRG2 indicator that we are in RTAS
+ *	- SPRG4 (603 only) pseudo TLB LRU data
+ *
+ * 32-bit 40x:
+ *	- SPRG0 scratch for exception vectors
+ *	- SPRG1 scratch for exception vectors
+ *	- SPRG2 scratch for exception vectors
+ *	- SPRG4 scratch for exception vectors (not 403)
+ *	- SPRG5 scratch for exception vectors (not 403)
+ *	- SPRG6 scratch for exception vectors (not 403)
+ *	- SPRG7 scratch for exception vectors (not 403)
+ *
+ * 32-bit 440 and FSL BookE:
+ *	- SPRG0 scratch for exception vectors
+ *	- SPRG1 scratch for exception vectors (*)
+ *	- SPRG2 scratch for crit interrupts handler
+ *	- SPRG4 scratch for exception vectors
+ *	- SPRG5 scratch for exception vectors
+ *	- SPRG6 scratch for machine check handler
+ *	- SPRG7 scratch for exception vectors
+ *	- SPRG9 scratch for debug vectors (e500 only)
+ *
+ *      Additionally, BookE separates "read" and "write"
+ *      of those registers. That allows to use the userspace
+ *      readable variant for reads, which can avoid a fault
+ *      with KVM type virtualization.
+ *
+ *      (*) Under KVM, the host SPRG1 is used to point to
+ *      the current VCPU data structure
+ *
+ * 32-bit 8xx:
+ *	- SPRG0 scratch for exception vectors
+ *	- SPRG1 scratch for exception vectors
+ *	- SPRG2 apparently unused but initialized
+ *
+ */
+#ifdef CONFIG_PPC64
+#define SPRN_SPRG_PACA 		SPRN_SPRG1
+#else
+#define SPRN_SPRG_THREAD 	SPRN_SPRG3
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+#define SPRN_SPRG_SCRATCH0	SPRN_SPRG2
+#endif
+
+#ifdef CONFIG_PPC_BOOK3E_64
+#define SPRN_SPRG_MC_SCRATCH	SPRN_SPRG8
+#define SPRN_SPRG_CRIT_SCRATCH	SPRN_SPRG7
+#define SPRN_SPRG_DBG_SCRATCH	SPRN_SPRG9
+#define SPRN_SPRG_TLB_EXFRAME	SPRN_SPRG2
+#define SPRN_SPRG_TLB_SCRATCH	SPRN_SPRG6
+#define SPRN_SPRG_GEN_SCRATCH	SPRN_SPRG0
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_32
+#define SPRN_SPRG_SCRATCH0	SPRN_SPRG0
+#define SPRN_SPRG_SCRATCH1	SPRN_SPRG1
+#define SPRN_SPRG_RTAS		SPRN_SPRG2
+#define SPRN_SPRG_603_LRU	SPRN_SPRG4
+#endif
+
+#ifdef CONFIG_40x
+#define SPRN_SPRG_SCRATCH0	SPRN_SPRG0
+#define SPRN_SPRG_SCRATCH1	SPRN_SPRG1
+#define SPRN_SPRG_SCRATCH2	SPRN_SPRG2
+#define SPRN_SPRG_SCRATCH3	SPRN_SPRG4
+#define SPRN_SPRG_SCRATCH4	SPRN_SPRG5
+#define SPRN_SPRG_SCRATCH5	SPRN_SPRG6
+#define SPRN_SPRG_SCRATCH6	SPRN_SPRG7
+#endif
+
+#ifdef CONFIG_BOOKE
+#define SPRN_SPRG_RSCRATCH0	SPRN_SPRG0
+#define SPRN_SPRG_WSCRATCH0	SPRN_SPRG0
+#define SPRN_SPRG_RSCRATCH1	SPRN_SPRG1
+#define SPRN_SPRG_WSCRATCH1	SPRN_SPRG1
+#define SPRN_SPRG_RSCRATCH_CRIT	SPRN_SPRG2
+#define SPRN_SPRG_WSCRATCH_CRIT	SPRN_SPRG2
+#define SPRN_SPRG_RSCRATCH2	SPRN_SPRG4R
+#define SPRN_SPRG_WSCRATCH2	SPRN_SPRG4W
+#define SPRN_SPRG_RSCRATCH3	SPRN_SPRG5R
+#define SPRN_SPRG_WSCRATCH3	SPRN_SPRG5W
+#define SPRN_SPRG_RSCRATCH_MC	SPRN_SPRG6R
+#define SPRN_SPRG_WSCRATCH_MC	SPRN_SPRG6W
+#define SPRN_SPRG_RSCRATCH4	SPRN_SPRG7R
+#define SPRN_SPRG_WSCRATCH4	SPRN_SPRG7W
+#ifdef CONFIG_E200
+#define SPRN_SPRG_RSCRATCH_DBG	SPRN_SPRG6R
+#define SPRN_SPRG_WSCRATCH_DBG	SPRN_SPRG6W
+#else
+#define SPRN_SPRG_RSCRATCH_DBG	SPRN_SPRG9
+#define SPRN_SPRG_WSCRATCH_DBG	SPRN_SPRG9
+#endif
+#define SPRN_SPRG_RVCPU		SPRN_SPRG1
+#define SPRN_SPRG_WVCPU		SPRN_SPRG1
+#endif
+
+#ifdef CONFIG_8xx
+#define SPRN_SPRG_SCRATCH0	SPRN_SPRG0
+#define SPRN_SPRG_SCRATCH1	SPRN_SPRG1
+#endif
+
+/*
  * An mtfsf instruction with the L bit set. On CPUs that support this a
  * full 64bits of FPSCR is restored and on other CPUs the L bit is ignored.
  *
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index 6bcf364cbb2f..3bf783505528 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -18,18 +18,26 @@
 #define MSR_IS		MSR_IR	/* Instruction Space */
 #define MSR_DS		MSR_DR	/* Data Space */
 #define MSR_PMM		(1<<2)	/* Performance monitor mark bit */
+#define MSR_CM		(1<<31) /* Computation Mode (0=32-bit, 1=64-bit) */
 
-/* Default MSR for kernel mode. */
-#if defined (CONFIG_40x)
+#if defined(CONFIG_PPC_BOOK3E_64)
+#define MSR_		MSR_ME | MSR_CE
+#define MSR_KERNEL      MSR_ | MSR_CM
+#define MSR_USER32	MSR_ | MSR_PR | MSR_EE
+#define MSR_USER64	MSR_USER32 | MSR_CM
+#elif defined (CONFIG_40x)
 #define MSR_KERNEL	(MSR_ME|MSR_RI|MSR_IR|MSR_DR|MSR_CE)
-#elif defined(CONFIG_BOOKE)
+#define MSR_USER	(MSR_KERNEL|MSR_PR|MSR_EE)
+#else
 #define MSR_KERNEL	(MSR_ME|MSR_RI|MSR_CE)
+#define MSR_USER	(MSR_KERNEL|MSR_PR|MSR_EE)
 #endif
 
 /* Special Purpose Registers (SPRNs)*/
 #define SPRN_DECAR	0x036	/* Decrementer Auto Reload Register */
 #define SPRN_IVPR	0x03F	/* Interrupt Vector Prefix Register */
 #define SPRN_USPRG0	0x100	/* User Special Purpose Register General 0 */
+#define SPRN_SPRG3R	0x103	/* Special Purpose Register General 3 Read */
 #define SPRN_SPRG4R	0x104	/* Special Purpose Register General 4 Read */
 #define SPRN_SPRG5R	0x105	/* Special Purpose Register General 5 Read */
 #define SPRN_SPRG6R	0x106	/* Special Purpose Register General 6 Read */
@@ -38,11 +46,18 @@
 #define SPRN_SPRG5W	0x115	/* Special Purpose Register General 5 Write */
 #define SPRN_SPRG6W	0x116	/* Special Purpose Register General 6 Write */
 #define SPRN_SPRG7W	0x117	/* Special Purpose Register General 7 Write */
+#define SPRN_EPCR	0x133	/* Embedded Processor Control Register */
 #define SPRN_DBCR2	0x136	/* Debug Control Register 2 */
 #define SPRN_IAC3	0x13A	/* Instruction Address Compare 3 */
 #define SPRN_IAC4	0x13B	/* Instruction Address Compare 4 */
 #define SPRN_DVC1	0x13E	/* Data Value Compare Register 1 */
 #define SPRN_DVC2	0x13F	/* Data Value Compare Register 2 */
+#define SPRN_MAS8	0x155	/* MMU Assist Register 8 */
+#define SPRN_TLB0PS	0x158	/* TLB 0 Page Size Register */
+#define SPRN_MAS5_MAS6	0x15c	/* MMU Assist Register 5 || 6 */
+#define SPRN_MAS8_MAS1	0x15d	/* MMU Assist Register 8 || 1 */
+#define SPRN_MAS7_MAS3	0x174	/* MMU Assist Register 7 || 3 */
+#define SPRN_MAS0_MAS1	0x175	/* MMU Assist Register 0 || 1 */
 #define SPRN_IVOR0	0x190	/* Interrupt Vector Offset Register 0 */
 #define SPRN_IVOR1	0x191	/* Interrupt Vector Offset Register 1 */
 #define SPRN_IVOR2	0x192	/* Interrupt Vector Offset Register 2 */
@@ -93,6 +108,8 @@
 #define SPRN_PID2	0x27A	/* Process ID Register 2 */
 #define SPRN_TLB0CFG	0x2B0	/* TLB 0 Config Register */
 #define SPRN_TLB1CFG	0x2B1	/* TLB 1 Config Register */
+#define SPRN_TLB2CFG	0x2B2	/* TLB 2 Config Register */
+#define SPRN_TLB3CFG	0x2B3	/* TLB 3 Config Register */
 #define SPRN_EPR	0x2BE	/* External Proxy Register */
 #define SPRN_CCR1	0x378	/* Core Configuration Register 1 */
 #define SPRN_ZPR	0x3B0	/* Zone Protection Register (40x) */
@@ -415,16 +432,31 @@
 #define L2CSR0_L2LOA	0x00000080	/* L2 Cache Lock Overflow Allocate */
 #define L2CSR0_L2LO	0x00000020	/* L2 Cache Lock Overflow */
 
-/* Bit definitions for MMUCSR0 */
-#define MMUCSR0_TLB1FI	0x00000002	/* TLB1 Flash invalidate */
-#define MMUCSR0_TLB0FI	0x00000004	/* TLB0 Flash invalidate */
-#define MMUCSR0_TLB2FI	0x00000040	/* TLB2 Flash invalidate */
-#define MMUCSR0_TLB3FI	0x00000020	/* TLB3 Flash invalidate */
-
 /* Bit definitions for SGR. */
 #define SGR_NORMAL	0		/* Speculative fetching allowed. */
 #define SGR_GUARDED	1		/* Speculative fetching disallowed. */
 
+/* Bit definitions for EPCR */
+#define SPRN_EPCR_EXTGS		0x80000000	/* External Input interrupt
+						 * directed to Guest state */
+#define SPRN_EPCR_DTLBGS	0x40000000	/* Data TLB Error interrupt
+						 * directed to guest state */
+#define SPRN_EPCR_ITLBGS	0x20000000	/* Instr. TLB error interrupt
+						 * directed to guest state */
+#define SPRN_EPCR_DSIGS		0x10000000	/* Data Storage interrupt
+						 * directed to guest state */
+#define SPRN_EPCR_ISIGS		0x08000000	/* Instr. Storage interrupt
+						 * directed to guest state */
+#define SPRN_EPCR_DUVD		0x04000000	/* Disable Hypervisor Debug */
+#define SPRN_EPCR_ICM		0x02000000	/* Interrupt computation mode
+						 * (copied to MSR:CM on intr) */
+#define SPRN_EPCR_GICM		0x01000000	/* Guest Interrupt Comp. mode */
+#define SPRN_EPCR_DGTMI		0x00800000	/* Disable TLB Guest Management
+						 * instructions */
+#define SPRN_EPCR_DMIUH		0x00400000	/* Disable MAS Interrupt updates
+						 * for hypervisor */
+
+
 /*
  * The IBM-403 is an even more odd special case, as it is much
  * older than the IBM-405 series.  We put these down here incase someone
diff --git a/arch/powerpc/include/asm/reg_fsl_emb.h b/arch/powerpc/include/asm/reg_fsl_emb.h
index 1e180a594589..0de404dfee8b 100644
--- a/arch/powerpc/include/asm/reg_fsl_emb.h
+++ b/arch/powerpc/include/asm/reg_fsl_emb.h
@@ -39,7 +39,7 @@
 #define PMRN_PMLCB2	0x112	/* PM Local Control B2 */
 #define PMRN_PMLCB3	0x113	/* PM Local Control B3 */
 
-#define PMLCB_THRESHMUL_MASK	0x0700	/* Threshhold Multiple Field */
+#define PMLCB_THRESHMUL_MASK	0x0700	/* Threshold Multiple Field */
 #define PMLCB_THRESHMUL_SHIFT	8
 
 #define PMLCB_THRESHOLD_MASK	0x003f	/* Threshold Field */
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 168fce726201..20de73c36682 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -58,7 +58,7 @@ struct rtas_t {
 	unsigned long entry;		/* physical address pointer */
 	unsigned long base;		/* physical address pointer */
 	unsigned long size;
-	raw_spinlock_t lock;
+	arch_spinlock_t lock;
 	struct rtas_args args;
 	struct device_node *dev;	/* virtual address pointer */
 };
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 817fac0a0714..dae19342f0b9 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -1,6 +1,6 @@
 #ifndef _ASM_POWERPC_SETUP_H
 #define _ASM_POWERPC_SETUP_H
 
-#define COMMAND_LINE_SIZE	512
+#include <asm-generic/setup.h>
 
 #endif	/* _ASM_POWERPC_SETUP_H */
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index c25f73d1d842..1d3b270d3083 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -37,7 +37,7 @@ extern void cpu_die(void);
 extern void smp_send_debugger_break(int cpu);
 extern void smp_message_recv(int);
 
-DECLARE_PER_CPU(unsigned int, pvr);
+DECLARE_PER_CPU(unsigned int, cpu_pvr);
 
 #ifdef CONFIG_HOTPLUG_CPU
 extern void fixup_irqs(cpumask_t map);
@@ -146,7 +146,17 @@ extern void smp_generic_take_timebase(void);
 extern struct smp_ops_t *smp_ops;
 
 extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi(cpumask_t mask);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+
+/* Definitions relative to the secondary CPU spin loop
+ * and entry point. Not all of them exist on both 32 and
+ * 64-bit but defining them all here doesn't harm
+ */
+extern void generic_secondary_smp_init(void);
+extern void generic_secondary_thread_init(void);
+extern unsigned long __secondary_hold_spinloop;
+extern unsigned long __secondary_hold_acknowledge;
+extern char __secondary_hold;
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/powerpc/include/asm/socket.h b/arch/powerpc/include/asm/socket.h
index 1e5cfad0e3f7..866f7606da68 100644
--- a/arch/powerpc/include/asm/socket.h
+++ b/arch/powerpc/include/asm/socket.h
@@ -64,4 +64,9 @@
 #define SO_TIMESTAMPING		37
 #define SCM_TIMESTAMPING	SO_TIMESTAMPING
 
+#define SO_PROTOCOL		38
+#define SO_DOMAIN		39
+
+#define SO_RXQ_OVFL             40
+
 #endif	/* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index c3b193121f81..764094cff681 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -28,7 +28,7 @@
 #include <asm/asm-compat.h>
 #include <asm/synch.h>
 
-#define __raw_spin_is_locked(x)		((x)->slock != 0)
+#define arch_spin_is_locked(x)		((x)->slock != 0)
 
 #ifdef CONFIG_PPC64
 /* use 0x800000yy when locked, where yy == CPU number */
@@ -54,7 +54,7 @@
  * This returns the old value in the lock, so we succeeded
  * in getting the lock if the return value is 0.
  */
-static inline unsigned long __spin_trylock(raw_spinlock_t *lock)
+static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock)
 {
 	unsigned long tmp, token;
 
@@ -73,10 +73,10 @@ static inline unsigned long __spin_trylock(raw_spinlock_t *lock)
 	return tmp;
 }
 
-static inline int __raw_spin_trylock(raw_spinlock_t *lock)
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	CLEAR_IO_SYNC;
-	return __spin_trylock(lock) == 0;
+	return __arch_spin_trylock(lock) == 0;
 }
 
 /*
@@ -96,19 +96,19 @@ static inline int __raw_spin_trylock(raw_spinlock_t *lock)
 #if defined(CONFIG_PPC_SPLPAR) || defined(CONFIG_PPC_ISERIES)
 /* We only yield to the hypervisor if we are in shared processor mode */
 #define SHARED_PROCESSOR (get_lppaca()->shared_proc)
-extern void __spin_yield(raw_spinlock_t *lock);
-extern void __rw_yield(raw_rwlock_t *lock);
+extern void __spin_yield(arch_spinlock_t *lock);
+extern void __rw_yield(arch_rwlock_t *lock);
 #else /* SPLPAR || ISERIES */
 #define __spin_yield(x)	barrier()
 #define __rw_yield(x)	barrier()
 #define SHARED_PROCESSOR	0
 #endif
 
-static inline void __raw_spin_lock(raw_spinlock_t *lock)
+static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	CLEAR_IO_SYNC;
 	while (1) {
-		if (likely(__spin_trylock(lock) == 0))
+		if (likely(__arch_spin_trylock(lock) == 0))
 			break;
 		do {
 			HMT_low();
@@ -120,13 +120,13 @@ static inline void __raw_spin_lock(raw_spinlock_t *lock)
 }
 
 static inline
-void __raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long flags)
+void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
 {
 	unsigned long flags_dis;
 
 	CLEAR_IO_SYNC;
 	while (1) {
-		if (likely(__spin_trylock(lock) == 0))
+		if (likely(__arch_spin_trylock(lock) == 0))
 			break;
 		local_save_flags(flags_dis);
 		local_irq_restore(flags);
@@ -140,19 +140,19 @@ void __raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long flags)
 	}
 }
 
-static inline void __raw_spin_unlock(raw_spinlock_t *lock)
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	SYNC_IO;
-	__asm__ __volatile__("# __raw_spin_unlock\n\t"
+	__asm__ __volatile__("# arch_spin_unlock\n\t"
 				LWSYNC_ON_SMP: : :"memory");
 	lock->slock = 0;
 }
 
 #ifdef CONFIG_PPC64
-extern void __raw_spin_unlock_wait(raw_spinlock_t *lock);
+extern void arch_spin_unlock_wait(arch_spinlock_t *lock);
 #else
-#define __raw_spin_unlock_wait(lock) \
-	do { while (__raw_spin_is_locked(lock)) cpu_relax(); } while (0)
+#define arch_spin_unlock_wait(lock) \
+	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
 #endif
 
 /*
@@ -166,8 +166,8 @@ extern void __raw_spin_unlock_wait(raw_spinlock_t *lock);
  * read-locks.
  */
 
-#define __raw_read_can_lock(rw)		((rw)->lock >= 0)
-#define __raw_write_can_lock(rw)	(!(rw)->lock)
+#define arch_read_can_lock(rw)		((rw)->lock >= 0)
+#define arch_write_can_lock(rw)	(!(rw)->lock)
 
 #ifdef CONFIG_PPC64
 #define __DO_SIGN_EXTEND	"extsw	%0,%0\n"
@@ -181,7 +181,7 @@ extern void __raw_spin_unlock_wait(raw_spinlock_t *lock);
  * This returns the old value in the lock + 1,
  * so we got a read lock if the return value is > 0.
  */
-static inline long __read_trylock(raw_rwlock_t *rw)
+static inline long __arch_read_trylock(arch_rwlock_t *rw)
 {
 	long tmp;
 
@@ -205,7 +205,7 @@ static inline long __read_trylock(raw_rwlock_t *rw)
  * This returns the old value in the lock,
  * so we got the write lock if the return value is 0.
  */
-static inline long __write_trylock(raw_rwlock_t *rw)
+static inline long __arch_write_trylock(arch_rwlock_t *rw)
 {
 	long tmp, token;
 
@@ -225,10 +225,10 @@ static inline long __write_trylock(raw_rwlock_t *rw)
 	return tmp;
 }
 
-static inline void __raw_read_lock(raw_rwlock_t *rw)
+static inline void arch_read_lock(arch_rwlock_t *rw)
 {
 	while (1) {
-		if (likely(__read_trylock(rw) > 0))
+		if (likely(__arch_read_trylock(rw) > 0))
 			break;
 		do {
 			HMT_low();
@@ -239,10 +239,10 @@ static inline void __raw_read_lock(raw_rwlock_t *rw)
 	}
 }
 
-static inline void __raw_write_lock(raw_rwlock_t *rw)
+static inline void arch_write_lock(arch_rwlock_t *rw)
 {
 	while (1) {
-		if (likely(__write_trylock(rw) == 0))
+		if (likely(__arch_write_trylock(rw) == 0))
 			break;
 		do {
 			HMT_low();
@@ -253,17 +253,17 @@ static inline void __raw_write_lock(raw_rwlock_t *rw)
 	}
 }
 
-static inline int __raw_read_trylock(raw_rwlock_t *rw)
+static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
-	return __read_trylock(rw) > 0;
+	return __arch_read_trylock(rw) > 0;
 }
 
-static inline int __raw_write_trylock(raw_rwlock_t *rw)
+static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
-	return __write_trylock(rw) == 0;
+	return __arch_write_trylock(rw) == 0;
 }
 
-static inline void __raw_read_unlock(raw_rwlock_t *rw)
+static inline void arch_read_unlock(arch_rwlock_t *rw)
 {
 	long tmp;
 
@@ -280,19 +280,19 @@ static inline void __raw_read_unlock(raw_rwlock_t *rw)
 	: "cr0", "xer", "memory");
 }
 
-static inline void __raw_write_unlock(raw_rwlock_t *rw)
+static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
 	__asm__ __volatile__("# write_unlock\n\t"
 				LWSYNC_ON_SMP: : :"memory");
 	rw->lock = 0;
 }
 
-#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock)
-#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock)
+#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
 
-#define _raw_spin_relax(lock)	__spin_yield(lock)
-#define _raw_read_relax(lock)	__rw_yield(lock)
-#define _raw_write_relax(lock)	__rw_yield(lock)
+#define arch_spin_relax(lock)	__spin_yield(lock)
+#define arch_read_relax(lock)	__rw_yield(lock)
+#define arch_write_relax(lock)	__rw_yield(lock)
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_SPINLOCK_H */
diff --git a/arch/powerpc/include/asm/spinlock_types.h b/arch/powerpc/include/asm/spinlock_types.h
index 74236c9f05b1..2351adc4fdc4 100644
--- a/arch/powerpc/include/asm/spinlock_types.h
+++ b/arch/powerpc/include/asm/spinlock_types.h
@@ -7,14 +7,14 @@
 
 typedef struct {
 	volatile unsigned int slock;
-} raw_spinlock_t;
+} arch_spinlock_t;
 
-#define __RAW_SPIN_LOCK_UNLOCKED	{ 0 }
+#define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 }
 
 typedef struct {
 	volatile signed int lock;
-} raw_rwlock_t;
+} arch_rwlock_t;
 
-#define __RAW_RW_LOCK_UNLOCKED		{ 0 }
+#define __ARCH_RW_LOCK_UNLOCKED		{ 0 }
 
 #endif
diff --git a/arch/powerpc/include/asm/swiotlb.h b/arch/powerpc/include/asm/swiotlb.h
index 30891d6e2bc1..8979d4cd3d70 100644
--- a/arch/powerpc/include/asm/swiotlb.h
+++ b/arch/powerpc/include/asm/swiotlb.h
@@ -13,15 +13,13 @@
 
 #include <linux/swiotlb.h>
 
-extern struct dma_mapping_ops swiotlb_dma_ops;
-extern struct dma_mapping_ops swiotlb_pci_dma_ops;
-
-int swiotlb_arch_address_needs_mapping(struct device *, dma_addr_t,
-				       size_t size);
+extern struct dma_map_ops swiotlb_dma_ops;
 
 static inline void dma_mark_clean(void *addr, size_t size) {}
 
 extern unsigned int ppc_swiotlb_enable;
 int __init swiotlb_setup_bus_notifier(void);
 
+extern void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev);
+
 #endif /* __ASM_SWIOTLB_H */
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 370600ca2765..07d2d19ab5e9 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -95,8 +95,8 @@ SYSCALL(reboot)
 SYSX(sys_ni_syscall,compat_sys_old_readdir,sys_old_readdir)
 SYSCALL_SPU(mmap)
 SYSCALL_SPU(munmap)
-SYSCALL_SPU(truncate)
-SYSCALL_SPU(ftruncate)
+COMPAT_SYS_SPU(truncate)
+COMPAT_SYS_SPU(ftruncate)
 SYSCALL_SPU(fchmod)
 SYSCALL_SPU(fchown)
 COMPAT_SYS_SPU(getpriority)
@@ -145,7 +145,7 @@ SYSCALL_SPU(setfsuid)
 SYSCALL_SPU(setfsgid)
 SYSCALL_SPU(llseek)
 COMPAT_SYS_SPU(getdents)
-SYSX_SPU(sys_select,ppc32_select,ppc_select)
+SYSX_SPU(sys_select,ppc32_select,sys_select)
 SYSCALL_SPU(flock)
 SYSCALL_SPU(msync)
 COMPAT_SYS_SPU(readv)
@@ -322,7 +322,7 @@ SYSCALL_SPU(epoll_create1)
 SYSCALL_SPU(dup3)
 SYSCALL_SPU(pipe2)
 SYSCALL(inotify_init1)
-SYSCALL_SPU(perf_counter_open)
+SYSCALL_SPU(perf_event_open)
 COMPAT_SYS_SPU(preadv)
 COMPAT_SYS_SPU(pwritev)
 COMPAT_SYS(rt_tgsigqueueinfo)
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index c8b329255678..aa9d383a1c09 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -111,7 +111,6 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_NOTIFY_RESUME	13	/* callback before returning to user */
 #define TIF_FREEZE		14	/* Freezing for suspend */
 #define TIF_RUNLATCH		15	/* Is the runlatch enabled? */
-#define TIF_ABI_PENDING		16	/* 32/64 bit switch needed */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
@@ -129,7 +128,6 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
 #define _TIF_FREEZE		(1<<TIF_FREEZE)
 #define _TIF_RUNLATCH		(1<<TIF_RUNLATCH)
-#define _TIF_ABI_PENDING	(1<<TIF_ABI_PENDING)
 #define _TIF_SYSCALL_T_OR_A	(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP)
 
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index 3ddc8f6986dd..8f0ed7adcd12 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -25,8 +25,6 @@
 
 #include <linux/pagemap.h>
 
-struct mmu_gather;
-
 #define tlb_start_vma(tlb, vma)	do { } while (0)
 #define tlb_end_vma(tlb, vma)	do { } while (0)
 
@@ -40,54 +38,22 @@ struct arch_mmu_gather {
 
 #define ARCH_MMU_GATHER_INIT (struct arch_mmu_gather){ .batch = NULL, }
 
-#if !defined(CONFIG_PPC_STD_MMU)
-
-#define tlb_flush(tlb)			flush_tlb_mm((tlb)->mm)
-
-#elif defined(__powerpc64__)
-
-extern void pte_free_finish(struct mmu_gather *tlb);
-
-static inline void tlb_flush(struct mmu_gather *tlb)
-{
-	struct ppc64_tlb_batch *tlbbatch = &get_cpu_var(ppc64_tlb_batch);
-
-	/* If there's a TLB batch pending, then we must flush it because the
-	 * pages are going to be freed and we really don't want to have a CPU
-	 * access a freed page because it has a stale TLB
-	 */
-	if (tlbbatch->index) {
-		__flush_tlb_pending(tlbbatch);
-	}
-
-	put_cpu_var(ppc64_tlb_batch);
-	pte_free_finish(tlb);
-}
-
-#else
-
 extern void tlb_flush(struct mmu_gather *tlb);
 
-#endif
-
 /* Get the generic bits... */
 #include <asm-generic/tlb.h>
 
-#if !defined(CONFIG_PPC_STD_MMU) || defined(__powerpc64__)
-
-#define __tlb_remove_tlb_entry(tlb, pte, address) do { } while (0)
-
-#else
 extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep,
 			     unsigned long address);
 
 static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
-					unsigned long address)
+					  unsigned long address)
 {
+#ifdef CONFIG_PPC_STD_MMU_32
 	if (pte_val(*ptep) & _PAGE_HASHPTE)
 		flush_hash_entry(tlb->mm, ptep, address);
+#endif
 }
 
-#endif
 #endif /* __KERNEL__ */
 #endif /* __ASM_POWERPC_TLB_H */
diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h
index 3f675968de70..b594942e5312 100644
--- a/arch/powerpc/include/asm/tlbflush.h
+++ b/arch/powerpc/include/asm/tlbflush.h
@@ -6,7 +6,7 @@
  *
  *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
  *  - flush_tlb_page(vma, vmaddr) flushes one page
- *  - local_flush_tlb_mm(mm) flushes the specified mm context on
+ *  - local_flush_tlb_mm(mm, full) flushes the specified mm context on
  *                           the local processor
  *  - local_flush_tlb_page(vma, vmaddr) flushes one page on the local processor
  *  - flush_tlb_page_nohash(vma, vmaddr) flushes one page if SW loaded TLB
@@ -29,7 +29,8 @@
  * specific tlbie's
  */
 
-#include <linux/mm.h>
+struct vm_area_struct;
+struct mm_struct;
 
 #define MMU_NO_CONTEXT      	((unsigned int)-1)
 
@@ -40,12 +41,18 @@ extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 extern void local_flush_tlb_mm(struct mm_struct *mm);
 extern void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 
+extern void __local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
+				   int tsize, int ind);
+
 #ifdef CONFIG_SMP
 extern void flush_tlb_mm(struct mm_struct *mm);
 extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
+extern void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
+			     int tsize, int ind);
 #else
 #define flush_tlb_mm(mm)		local_flush_tlb_mm(mm)
 #define flush_tlb_page(vma,addr)	local_flush_tlb_page(vma,addr)
+#define __flush_tlb_page(mm,addr,p,i)	__local_flush_tlb_page(mm,addr,p,i)
 #endif
 #define flush_tlb_page_nohash(vma,addr)	flush_tlb_page(vma,addr)
 
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 054a16d68082..bbf89701d7a4 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -17,12 +17,9 @@ static inline int cpu_to_node(int cpu)
 
 #define parent_node(node)	(node)
 
-static inline cpumask_t node_to_cpumask(int node)
-{
-	return numa_cpumask_lookup_table[node];
-}
-
-#define cpumask_of_node(node) (&numa_cpumask_lookup_table[node])
+#define cpumask_of_node(node) ((node) == -1 ?				\
+			       cpu_all_mask :				\
+			       &numa_cpumask_lookup_table[node])
 
 int of_node_to_nid(struct device_node *device);
 
@@ -36,11 +33,6 @@ static inline int pcibus_to_node(struct pci_bus *bus)
 }
 #endif
 
-#define pcibus_to_cpumask(bus)	(pcibus_to_node(bus) == -1 ? \
-					CPU_MASK_ALL : \
-					node_to_cpumask(pcibus_to_node(bus)) \
-				)
-
 #define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ?		\
 				 cpu_all_mask :				\
 				 cpumask_of_node(pcibus_to_node(bus)))
@@ -57,14 +49,13 @@ static inline int pcibus_to_node(struct pci_bus *bus)
 	.cache_nice_tries	= 1,			\
 	.busy_idx		= 3,			\
 	.idle_idx		= 1,			\
-	.newidle_idx		= 2,			\
-	.wake_idx		= 1,			\
+	.newidle_idx		= 0,			\
+	.wake_idx		= 0,			\
 	.flags			= SD_LOAD_BALANCE	\
 				| SD_BALANCE_EXEC	\
+				| SD_BALANCE_FORK	\
 				| SD_BALANCE_NEWIDLE	\
-				| SD_WAKE_IDLE		\
-				| SD_SERIALIZE		\
-				| SD_WAKE_BALANCE,	\
+				| SD_SERIALIZE,		\
 	.last_balance		= jiffies,		\
 	.balance_interval	= 1,			\
 	.nr_balance_failed	= 0,			\
@@ -105,8 +96,6 @@ static inline void sysfs_remove_device_from_node(struct sys_device *dev,
 #ifdef CONFIG_PPC64
 #include <asm/smp.h>
 
-#define topology_thread_siblings(cpu)	(per_cpu(cpu_sibling_map, cpu))
-#define topology_core_siblings(cpu)	(per_cpu(cpu_core_map, cpu))
 #define topology_thread_cpumask(cpu)	(&per_cpu(cpu_sibling_map, cpu))
 #define topology_core_cpumask(cpu)	(&per_cpu(cpu_core_map, cpu))
 #define topology_core_id(cpu)		(cpu_to_core_id(cpu))
diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h
new file mode 100644
index 000000000000..cbe2297d68b6
--- /dev/null
+++ b/arch/powerpc/include/asm/trace.h
@@ -0,0 +1,133 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM powerpc
+
+#if !defined(_TRACE_POWERPC_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_POWERPC_H
+
+#include <linux/tracepoint.h>
+
+struct pt_regs;
+
+TRACE_EVENT(irq_entry,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+TRACE_EVENT(irq_exit,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+TRACE_EVENT(timer_interrupt_entry,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+TRACE_EVENT(timer_interrupt_exit,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+#ifdef CONFIG_PPC_PSERIES
+extern void hcall_tracepoint_regfunc(void);
+extern void hcall_tracepoint_unregfunc(void);
+
+TRACE_EVENT_FN(hcall_entry,
+
+	TP_PROTO(unsigned long opcode, unsigned long *args),
+
+	TP_ARGS(opcode, args),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, opcode)
+	),
+
+	TP_fast_assign(
+		__entry->opcode = opcode;
+	),
+
+	TP_printk("opcode=%lu", __entry->opcode),
+
+	hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc
+);
+
+TRACE_EVENT_FN(hcall_exit,
+
+	TP_PROTO(unsigned long opcode, unsigned long retval,
+		unsigned long *retbuf),
+
+	TP_ARGS(opcode, retval, retbuf),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, opcode)
+		__field(unsigned long, retval)
+	),
+
+	TP_fast_assign(
+		__entry->opcode = opcode;
+		__entry->retval = retval;
+	),
+
+	TP_printk("opcode=%lu retval=%lu", __entry->opcode, __entry->retval),
+
+	hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc
+);
+#endif
+
+#endif /* _TRACE_POWERPC_H */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+
+#define TRACE_INCLUDE_PATH asm
+#define TRACE_INCLUDE_FILE trace
+
+#include <trace/define_trace.h>
diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h
index cd21e5e6b04f..11ae699135ba 100644
--- a/arch/powerpc/include/asm/udbg.h
+++ b/arch/powerpc/include/asm/udbg.h
@@ -51,6 +51,7 @@ extern void __init udbg_init_btext(void);
 extern void __init udbg_init_44x_as1(void);
 extern void __init udbg_init_40x_realmode(void);
 extern void __init udbg_init_cpm(void);
+extern void __init udbg_init_usbgecko(void);
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_UDBG_H */
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index cef080bfc607..f6ca76176766 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -341,7 +341,7 @@
 #define __NR_dup3		316
 #define __NR_pipe2		317
 #define __NR_inotify_init1	318
-#define __NR_perf_counter_open	319
+#define __NR_perf_event_open	319
 #define __NR_preadv		320
 #define __NR_pwritev		321
 #define __NR_rt_tgsigqueueinfo	322
diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h
index 26fc449bd989..dc0419b66f17 100644
--- a/arch/powerpc/include/asm/vdso.h
+++ b/arch/powerpc/include/asm/vdso.h
@@ -7,9 +7,8 @@
 #define VDSO32_LBASE	0x100000
 #define VDSO64_LBASE	0x100000
 
-/* Default map addresses */
+/* Default map addresses for 32bit vDSO */
 #define VDSO32_MBASE	VDSO32_LBASE
-#define VDSO64_MBASE	VDSO64_LBASE
 
 #define VDSO_VERSION_STRING	LINUX_2.6.15