1 files changed, 10 insertions, 0 deletions
diff --git a/crypto/tcrypt.h b/crypto/tcrypt.h
index ecdeeb1a7b0..6c7e21a09f7 100644
--- a/crypto/tcrypt.h
+++ b/crypto/tcrypt.h
@@ -22,6 +22,11 @@ struct cipher_speed_template {
 	unsigned int klen;
 };
 
+struct aead_speed_template {
+	const char *key;
+	unsigned int klen;
+};
+
 struct hash_speed {
 	unsigned int blen;	/* buffer length */
 	unsigned int plen;	/* per-update length */
@@ -58,6 +63,11 @@ static u8 speed_template_32_48_64[] = {32, 48, 64, 0};
 static u8 speed_template_32_64[] = {32, 64, 0};
 
 /*
+ * AEAD speed tests
+ */
+static u8 aead_speed_template_20[] = {20, 0};
+
+/*
  * Digest speed tests
  */
 static struct hash_speed generic_hash_speed_template[] = {
diff --git a/arch/powerpc/include/asm/8253pit.h b/arch/powerpc/include/asm/8253pit.h
deleted file mode 100644
index a71c9c1455a..00000000000
--- a/arch/powerpc/include/asm/8253pit.h
+++ /dev/null
@@ -1,3 +0,0 @@
-/*
- * 8253/8254 Programmable Interval Timer
- */
diff --git a/arch/powerpc/include/asm/8xx_immap.h b/arch/powerpc/include/asm/8xx_immap.h
index 4b0e1520600..bdf0563ba42 100644
--- a/arch/powerpc/include/asm/8xx_immap.h
+++ b/arch/powerpc/include/asm/8xx_immap.h
@@ -93,7 +93,7 @@ typedef struct	mem_ctlr {
 } memctl8xx_t;
 
 /*-----------------------------------------------------------------------
- * BR - Memory Controler: Base Register					16-9
+ * BR - Memory Controller: Base Register					16-9
  */
 #define BR_BA_MSK	0xffff8000	/* Base Address Mask			*/
 #define BR_AT_MSK	0x00007000	/* Address Type Mask			*/
@@ -110,7 +110,7 @@ typedef struct	mem_ctlr {
 #define BR_V		0x00000001	/* Bank Valid				*/
 
 /*-----------------------------------------------------------------------
- * OR - Memory Controler: Option Register				16-11
+ * OR - Memory Controller: Option Register				16-11
  */
 #define OR_AM_MSK	0xffff8000	/* Address Mask Mask			*/
 #define OR_ATM_MSK	0x00007000	/* Address Type Mask Mask		*/
@@ -393,8 +393,8 @@ typedef struct fec {
 	uint	fec_addr_low;		/* lower 32 bits of station address	*/
 	ushort	fec_addr_high;		/* upper 16 bits of station address	*/
 	ushort	res1;			/* reserved				*/
-	uint	fec_hash_table_high;	/* upper 32-bits of hash table		*/
-	uint	fec_hash_table_low;	/* lower 32-bits of hash table		*/
+	uint	fec_grp_hash_table_high;	/* upper 32-bits of hash table		*/
+	uint	fec_grp_hash_table_low;	/* lower 32-bits of hash table		*/
 	uint	fec_r_des_start;	/* beginning of Rx descriptor ring	*/
 	uint	fec_x_des_start;	/* beginning of Tx descriptor ring	*/
 	uint	fec_r_buff_size;	/* Rx buffer size			*/
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index d51df17c7e6..3fb1bc432f4 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -1,36 +1,8 @@
-include include/asm-generic/Kbuild.asm
 
-header-y += auxvec.h
-header-y += bootx.h
-header-y += byteorder.h
-header-y += cputable.h
-header-y += elf.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += linkage.h
-header-y += msgbuf.h
-header-y += nvram.h
-header-y += param.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ps3fb.h
-header-y += resource.h
-header-y += seccomp.h
-header-y += sembuf.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += spu_info.h
-header-y += stat.h
-header-y += statfs.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += ucontext.h
-header-y += unistd.h
+generic-y += clkdev.h
+generic-y += hash.h
+generic-y += mcs_spinlock.h
+generic-y += preempt.h
+generic-y += rwsem.h
+generic-y += trace_clock.h
+generic-y += vtime.h
diff --git a/arch/powerpc/include/asm/abs_addr.h b/arch/powerpc/include/asm/abs_addr.h
deleted file mode 100644
index 5ab0b71531b..00000000000
--- a/arch/powerpc/include/asm/abs_addr.h
+++ /dev/null
@@ -1,75 +0,0 @@
-#ifndef _ASM_POWERPC_ABS_ADDR_H
-#define _ASM_POWERPC_ABS_ADDR_H
-#ifdef __KERNEL__
-
-
-/*
- * c 2001 PPC 64 Team, IBM Corp
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/memblock.h>
-
-#include <asm/types.h>
-#include <asm/page.h>
-#include <asm/prom.h>
-#include <asm/firmware.h>
-
-struct mschunks_map {
-        unsigned long num_chunks;
-        unsigned long chunk_size;
-        unsigned long chunk_shift;
-        unsigned long chunk_mask;
-        u32 *mapping;
-};
-
-extern struct mschunks_map mschunks_map;
-
-/* Chunks are 256 KB */
-#define MSCHUNKS_CHUNK_SHIFT	(18)
-#define MSCHUNKS_CHUNK_SIZE	(1UL << MSCHUNKS_CHUNK_SHIFT)
-#define MSCHUNKS_OFFSET_MASK	(MSCHUNKS_CHUNK_SIZE - 1)
-
-static inline unsigned long chunk_to_addr(unsigned long chunk)
-{
-	return chunk << MSCHUNKS_CHUNK_SHIFT;
-}
-
-static inline unsigned long addr_to_chunk(unsigned long addr)
-{
-	return addr >> MSCHUNKS_CHUNK_SHIFT;
-}
-
-static inline unsigned long phys_to_abs(unsigned long pa)
-{
-	unsigned long chunk;
-
-	/* This is a no-op on non-iSeries */
-	if (!firmware_has_feature(FW_FEATURE_ISERIES))
-		return pa;
-
-	chunk = addr_to_chunk(pa);
-
-	if (chunk < mschunks_map.num_chunks)
-		chunk = mschunks_map.mapping[chunk];
-
-	return chunk_to_addr(chunk) + (pa & MSCHUNKS_OFFSET_MASK);
-}
-
-/* Convenience macros */
-#define virt_to_abs(va) phys_to_abs(__pa(va))
-#define abs_to_virt(aa) __va(aa)
-
-/*
- * Converts Virtual Address to Real Address for
- * Legacy iSeries Hypervisor calls
- */
-#define iseries_hv_addr(virtaddr)	\
-	(0x8000000000000000UL | virt_to_abs(virtaddr))
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_POWERPC_ABS_ADDR_H */
diff --git a/arch/powerpc/include/asm/apm82181-adma.h b/arch/powerpc/include/asm/apm82181-adma.h
new file mode 100644
index 00000000000..8d36b517fbf
--- /dev/null
+++ b/arch/powerpc/include/asm/apm82181-adma.h
@@ -0,0 +1,311 @@
+/*
+ * 2009-2010 (C) Applied Micro Circuits Corporation.
+ *
+ * Author: Tai Tri Nguyen<ttnguyen@appliedmicro.com>
+ *
+ * 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 APM82181_ADMA_H
+#define APM82181_ADMA_H
+
+
+#include <linux/types.h>
+
+
+#define to_apm82181_adma_chan(chan) container_of(chan,apm82181_ch_t,common)
+#define to_apm82181_adma_device(dev) container_of(dev,apm82181_dev_t,common)
+#define tx_to_apm82181_adma_slot(tx) container_of(tx,apm82181_desc_t,async_tx)
+
+#define APM82181_DMA_PROC_ROOT "driver/apm82181_adma"
+
+/* Number of operands supported in the h/w */
+#define XOR_MAX_OPS             16
+/* this is the XOR_CBBCR width */
+#define APM82181_ADMA_XOR_MAX_BYTE_COUNT       (1 << 31)
+#define APM82181_ADMA_DMA_MAX_BYTE_COUNT 1024 * 1024
+#define MAX_APM82181_DMA_CHANNELS 5
+#define APM82181_ADMA_THRESHOLD 1
+
+#define APM82181_PDMA0_ID 0
+#define APM82181_PDMA1_ID 1
+#define APM82181_PDMA2_ID 2
+#define APM82181_PDMA3_ID 3
+#define APM82181_XOR_ID	  4 
+
+/* DMA 0/1/2/3 registers */
+#define DCR_DMAx_BASE(x)	(0x200 + x*0x8)			/* DMA DCR base */
+#define DCR_DMA2P40_CRx(x)     	(DCR_DMAx_BASE(x) + 0x0)   /* DMA Channel Control */
+#define DMA_CR_CE		(1 << 31)
+#define DMA_CR_CIE		(1 << 30)
+#define DMA_CR_PL		(1 << 28)
+#define DMA_CR_PW_128		0x08000000
+#define DMA_CR_DAI		0x01000000
+#define DMA_CR_SAI		0x00800000
+#define DMA_CR_BEN		0x00400000
+#define DMA_CR_TM_S_MM		0x00300000
+#define DMA_CR_ETD		0x00000100
+#define DMA_CR_TCE		0x00000080
+#define DMA_CR_CP(x)		(x<<5)& 0x00000060
+#define DMA_CR_DEC		(1 << 2)
+#define DMA_CR_SL		(1 << 1)
+#define DCR_DMA2P40_CTCx(x)    	(DCR_DMAx_BASE(x) + 0x1) /* DMA Count 0 */
+#define DMA_CTC_ETIE		(1 << 28)
+#define DMA_CTC_EIE		(1 << 27)
+#define DMA_CTC_PCE		(1 << 20)
+#define DMA_CTC_TC_MASK		0x000fffff
+#define DCR_DMA2P40_SAHx(x)    	(DCR_DMAx_BASE(x) + 0x2) /* DMA Src Addr High 0 */
+#define DCR_DMA2P40_SALx(x)    	(DCR_DMAx_BASE(x) + 0x3) /* DMA Src Addr Low 0 */
+#define DCR_DMA2P40_DAHx(x)    	(DCR_DMAx_BASE(x) + 0x4) /* DMA Dest Addr High 0 */
+#define DCR_DMA2P40_DALx(x)    	(DCR_DMAx_BASE(x) + 0x5) /* DMA Dest Addr Low 0 */
+#define DCR_DMA2P40_SGHx(x)    	(DCR_DMAx_BASE(x) + 0x6) /* DMA SG Desc Addr High 0 */
+#define DCR_DMA2P40_SGLx(x)    	(DCR_DMAx_BASE(x) + 0x7) /* DMA SG Desc Addr Low 0 */
+/* DMA Status Register */
+#define DCR_DMA2P40_SR      	0x220 
+#define DMA_SR_CS(x)		(1 << (31 -x))
+#define DMA_SR_TS(x)		(1 << (27 -x))
+#define DMA_SR_RI(x)		(1 << (23 -x))
+#define DMA_SR_IR(x)		(1 << (19 -x))
+#define DMA_SR_ER(x)		(1 << (15 -x))
+#define DMA_SR_CB(x)		(1 << (11 -x))
+#define DMA_SR_SG(x)		(1 << (7 -x))
+/* S/G registers */
+#define DCR_DMA2P40_SGC		0x223
+#define DMA_SGC_SSG(x)		( 1 << (31 - x))
+#define DMA_SGC_SGL(x,y)	( y << (27 - x)) /* x: channel; y: 0 PLB, 1 OPB*/
+#define DMA_SGC_EM(x)		( 1 << (15 - x))
+#define DMA_SGC_EM_ALL		0x0000F000
+
+/*
+ * XOR Command Block Control Register bits
+ */
+#define XOR_CBCR_LNK_BIT        (1<<31) /* link present */
+#define XOR_CBCR_TGT_BIT        (1<<30) /* target present */
+#define XOR_CBCR_CBCE_BIT       (1<<29) /* command block compete enable */
+#define XOR_CBCR_RNZE_BIT       (1<<28) /* result not zero enable */
+#define XOR_CBCR_XNOR_BIT       (1<<15) /* XOR/XNOR */
+#define XOR_CDCR_OAC_MSK        (0x7F)  /* operand address count */
+
+/*
+ * XORCore Status Register bits
+ */
+#define XOR_SR_XCP_BIT          (1<<31) /* core processing */
+#define XOR_SR_ICB_BIT          (1<<17) /* invalid CB */
+#define XOR_SR_IC_BIT           (1<<16) /* invalid command */
+#define XOR_SR_IPE_BIT          (1<<15) /* internal parity error */
+#define XOR_SR_RNZ_BIT          (1<<2)  /* result not Zero */
+#define XOR_SR_CBC_BIT          (1<<1)  /* CB complete */
+#define XOR_SR_CBLC_BIT         (1<<0)  /* CB list complete */
+
+/*
+ * XORCore Control Set and Reset Register bits
+ */
+#define XOR_CRSR_XASR_BIT       (1<<31) /* soft reset */
+#define XOR_CRSR_XAE_BIT        (1<<30) /* enable */
+#define XOR_CRSR_RCBE_BIT       (1<<29) /* refetch CB enable */
+#define XOR_CRSR_PAUS_BIT       (1<<28) /* pause */
+#define XOR_CRSR_64BA_BIT       (1<<27) /* 64/32 CB format */
+#define XOR_CRSR_CLP_BIT        (1<<25) /* continue list processing */
+
+/*
+ * XORCore Interrupt Enable Register
+ */
+#define XOR_IE_ICBIE_BIT        (1<<17) /* Invalid Command Block Interrupt Enable */
+#define XOR_IE_ICIE_BIT         (1<<16) /* Invalid Command Interrupt Enable */
+#define XOR_IE_RPTIE_BIT        (1<<14) /* Read PLB Timeout Error Interrupt Enable */
+#define XOR_IE_CBCIE_BIT        (1<<1)  /* CB complete interrupt enable */
+#define XOR_IE_CBLCI_BIT        (1<<0)  /* CB list complete interrupt enable */
+
+typedef struct apm82181_plb_dma4_device {
+        struct resource reg;    /* Resource for register */
+        void __iomem *reg_base;
+        struct platform_device *ofdev;
+        struct device *dev;
+} apm82181_plb_dma_t;
+
+/**
+ * struct apm82181_dma_device - internal representation of an DMA device
+ * @id: HW DMA Device selector
+ * @ofdev: OF device
+ * @dcr_base: dcr base of HW PLB DMA channels
+ * @reg_base: base of ADMA XOR channel
+ * @dma_desc_pool: base of DMA descriptor region (DMA address)
+ * @dma_desc_pool_virt: base of DMA descriptor region (CPU address)
+ * @pool_size: memory pool size for the channel device
+ * @common: embedded struct dma_device
+ * @cap_mask: capabilities of ADMA channels
+ */
+typedef struct apm82181_plb_dma_device {
+	int id;
+	struct platform_device *ofdev;
+	u32 dcr_base;
+	void __iomem *xor_base;
+	struct device *dev;
+	struct dma_device common;
+	struct apm82181_plb_dma4_device *pdma;
+	void *dma_desc_pool_virt;
+	u32 pool_size;
+	dma_addr_t dma_desc_pool;
+	dma_cap_mask_t cap_mask;
+} apm82181_dev_t;
+
+/**
+ * struct apm82181_dma_chan - internal representation of an ADMA channel
+ * @lock: serializes enqueue/dequeue operations to the slot pool
+ * @device: parent device
+ * @chain: device chain view of the descriptors
+ * @common: common dmaengine channel object members
+ * @all_slots: complete domain of slots usable by the channel
+ * @reg: Resource for register 
+ * @pending: allows batching of hardware operations
+ * @completed_cookie: identifier for the most recently completed operation
+ * @slots_allocated: records the actual size of the descriptor slot pool
+ * @hw_chain_inited: h/w descriptor chain initialization flag
+ * @irq_tasklet: bottom half where apm82181_adma_slot_cleanup runs
+ * @needs_unmap: if buffers should not be unmapped upon final processing
+ */
+typedef struct apm82181_plb_dma_chan {
+	spinlock_t lock;
+	struct apm82181_plb_dma_device *device;
+	struct timer_list cleanup_watchdog;
+	struct list_head chain;
+	struct dma_chan common;
+	struct list_head all_slots;
+	struct apm82181_adma_plb_desc_slot *last_used;
+	int pending;
+	dma_cookie_t completed_cookie;
+	int slots_allocated;
+	int hw_chain_inited;
+        struct tasklet_struct irq_tasklet;
+	u8 needs_unmap;
+	phys_addr_t current_cdb_addr;	
+} apm82181_ch_t;
+
+typedef struct apm82181_adma_plb_desc_slot {
+	dma_addr_t phys;
+	struct apm82181_adma_plb_desc_slot *group_head;
+	struct apm82181_adma_plb_desc_slot *hw_next;
+	struct dma_async_tx_descriptor async_tx;
+	struct list_head slot_node;
+	struct list_head chain_node;
+	struct list_head group_list;
+	unsigned int unmap_len;
+	void *hw_desc;
+	u16 stride;
+	u16 idx;
+	u16 slot_cnt;
+	u8 src_cnt;
+	u8 dst_cnt;
+	u8 slots_per_op;
+	u8 descs_per_op;
+	unsigned long flags;
+	unsigned long reverse_flags[8];
+#define APM82181_DESC_INT       0       /* generate interrupt on complete */
+#define APM82181_DESC_FENCE     1       /* Other tx will use its result */
+					/* This tx needs to be polled to complete */
+
+}apm82181_desc_t;
+
+typedef struct {
+	u32 ce:1;
+	u32 cie:1;
+	u32 td:1;
+	u32 pl:1;
+	u32 pw:3;
+	u32 dai:1;
+	u32 sai:1;
+	u32 ben:1;
+	u32 tm:2;
+	u32 psc:2;
+	u32 pwc:6;
+	u32 phc:3;
+	u32 etd:1;
+	u32 tce:1;
+	u32 cp:2;
+	u32 pf:2;
+	u32 dec:1;
+	u32 sl:1;
+	u32 reserved:1;
+} __attribute__((packed)) dma_cdb_ctrl_t;
+
+typedef struct {
+	u32 link:1;
+	u32 sgl:1;
+	u32 tcie:1;
+	u32 etie:1;
+	u32 eie:1;
+	u32 sid:3;
+	u32 bten:1;
+	u32 bsiz:2;
+	u32 pce:1;
+	u32 tc:20;
+} __attribute__((packed)) dma_cdb_count_t;
+/* scatter/gather descriptor struct */
+typedef struct dma_cdb {
+	dma_cdb_ctrl_t ctrl;
+	dma_cdb_count_t cnt;
+	u32 src_hi;
+	u32 src_lo;
+	u32 dest_hi;
+	u32 dest_lo;
+	u32 sg_hi;
+	u32 sg_lo;
+}dma_cdb_t;
+
+typedef struct {
+        uint32_t control;
+        phys_addr_t src_addr;
+        phys_addr_t dst_addr;
+        uint32_t control_count;
+        uint32_t next;
+} ppc_sgl_t;
+
+/*
+ * XOR Accelerator engine Command Block Type
+ */
+typedef struct {
+        /*
+         * Basic 64-bit format XOR CB
+         */
+        u32     cbc;            /* control */
+        u32     cbbc;           /* byte count */
+        u32     cbs;            /* status */
+        u8      pad0[4];        /* reserved */
+        u32     cbtah;          /* target address high */
+        u32     cbtal;          /* target address low */
+        u32     cblah;          /* link address high */
+        u32     cblal;          /* link address low */
+        struct {
+                u32 h;
+                u32 l;
+        } __attribute__ ((packed)) ops [16];
+} __attribute__ ((packed)) xor_cb_t;
+
+/*
+ * XOR hardware registers
+ */
+typedef struct {
+        u32     op_ar[16][2];   /* operand address[0]-high,[1]-low registers */
+        u8      pad0[352];      /* reserved */
+        u32     cbcr;           /* CB control register */
+        u32     cbbcr;          /* CB byte count register */
+        u32     cbsr;           /* CB status register */
+        u8      pad1[4];        /* reserved */
+        u32     cbtahr;         /* operand target address high register */
+        u32     cbtalr;         /* operand target address low register */
+        u32     cblahr;         /* CB link address high register */
+        u32     cblalr;         /* CB link address low register */
+        u32     crsr;           /* control set register */
+        u32     crrr;           /* control reset register */
+        u32     ccbahr;         /* current CB address high register */
+        u32     ccbalr;         /* current CB address low register */
+        u32     plbr;           /* PLB configuration register */
+        u32     ier;            /* interrupt enable register */
+        u32     pecr;           /* parity error count register */
+        u32     sr;             /* status register */
+        u32     revidr;         /* revision ID register */
+} xor_regs_t;
+
+#endif
diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h
new file mode 100644
index 00000000000..bde53110363
--- /dev/null
+++ b/arch/powerpc/include/asm/archrandom.h
@@ -0,0 +1,50 @@
+#ifndef _ASM_POWERPC_ARCHRANDOM_H
+#define _ASM_POWERPC_ARCHRANDOM_H
+
+#ifdef CONFIG_ARCH_RANDOM
+
+#include <asm/machdep.h>
+
+static inline int arch_get_random_long(unsigned long *v)
+{
+	if (ppc_md.get_random_long)
+		return ppc_md.get_random_long(v);
+
+	return 0;
+}
+
+static inline int arch_get_random_int(unsigned int *v)
+{
+	unsigned long val;
+	int rc;
+
+	rc = arch_get_random_long(&val);
+	if (rc)
+		*v = val;
+
+	return rc;
+}
+
+static inline int arch_has_random(void)
+{
+	return !!ppc_md.get_random_long;
+}
+
+int powernv_get_random_long(unsigned long *v);
+
+static inline int arch_get_random_seed_long(unsigned long *v)
+{
+	return 0;
+}
+static inline int arch_get_random_seed_int(unsigned int *v)
+{
+	return 0;
+}
+static inline int arch_has_random_seed(void)
+{
+	return 0;
+}
+
+#endif /* CONFIG_ARCH_RANDOM */
+
+#endif /* _ASM_POWERPC_ARCHRANDOM_H */
diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h
index decad950f11..4b237aa3566 100644
--- a/arch/powerpc/include/asm/asm-compat.h
+++ b/arch/powerpc/include/asm/asm-compat.h
@@ -29,16 +29,16 @@
 #define PPC_LLARX(t, a, b, eh)	PPC_LDARX(t, a, b, eh)
 #define PPC_STLCX	stringify_in_c(stdcx.)
 #define PPC_CNTLZL	stringify_in_c(cntlzd)
+#define PPC_MTOCRF(FXM, RS) MTOCRF((FXM), RS)
 #define PPC_LR_STKOFF	16
 #define PPC_MIN_STKFRM	112
 
-/* Move to CR, single-entry optimized version. Only available
- * on POWER4 and later.
- */
-#ifdef CONFIG_POWER4_ONLY
-#define PPC_MTOCRF	stringify_in_c(mtocrf)
+#ifdef __BIG_ENDIAN__
+#define LDX_BE	stringify_in_c(ldx)
+#define STDX_BE	stringify_in_c(stdx)
 #else
-#define PPC_MTOCRF	stringify_in_c(mtcrf)
+#define LDX_BE	stringify_in_c(ldbrx)
+#define STDX_BE	stringify_in_c(stdbrx)
 #endif
 
 #else /* 32-bit */
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index b8f152ece02..28992d01292 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -5,13 +5,10 @@
  * PowerPC atomic operations
  */
 
-#include <linux/types.h>
-
 #ifdef __KERNEL__
-#include <linux/compiler.h>
-#include <asm/synch.h>
-#include <asm/asm-compat.h>
-#include <asm/system.h>
+#include <linux/types.h>
+#include <asm/cmpxchg.h>
+#include <asm/barrier.h>
 
 #define ATOMIC_INIT(i)		{ (i) }
 
@@ -49,13 +46,13 @@ static __inline__ int atomic_add_return(int a, atomic_t *v)
 	int t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%2		# atomic_add_return\n\
 	add	%0,%1,%0\n"
 	PPC405_ERR77(0,%2)
 "	stwcx.	%0,0,%2 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (a), "r" (&v->counter)
 	: "cc", "memory");
@@ -85,13 +82,13 @@ static __inline__ int atomic_sub_return(int a, atomic_t *v)
 	int t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%2		# atomic_sub_return\n\
 	subf	%0,%1,%0\n"
 	PPC405_ERR77(0,%2)
 "	stwcx.	%0,0,%2 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (a), "r" (&v->counter)
 	: "cc", "memory");
@@ -119,13 +116,13 @@ static __inline__ int atomic_inc_return(atomic_t *v)
 	int t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%1		# atomic_inc_return\n\
 	addic	%0,%0,1\n"
 	PPC405_ERR77(0,%1)
 "	stwcx.	%0,0,%1 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (&v->counter)
 	: "cc", "xer", "memory");
@@ -163,13 +160,13 @@ static __inline__ int atomic_dec_return(atomic_t *v)
 	int t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%1		# atomic_dec_return\n\
 	addic	%0,%0,-1\n"
 	PPC405_ERR77(0,%1)
 "	stwcx.	%0,0,%1\n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (&v->counter)
 	: "cc", "xer", "memory");
@@ -181,38 +178,67 @@ static __inline__ int atomic_dec_return(atomic_t *v)
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
 /**
- * atomic_add_unless - add unless the number is a given value
+ * __atomic_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
  *
  * Atomically adds @a to @v, so long as it was not @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
+ * Returns the old value of @v.
  */
-static __inline__ int atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 {
 	int t;
 
 	__asm__ __volatile__ (
-	PPC_RELEASE_BARRIER
-"1:	lwarx	%0,0,%1		# atomic_add_unless\n\
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	lwarx	%0,0,%1		# __atomic_add_unless\n\
 	cmpw	0,%0,%3 \n\
 	beq-	2f \n\
 	add	%0,%2,%0 \n"
 	PPC405_ERR77(0,%2)
 "	stwcx.	%0,0,%1 \n\
 	bne-	1b \n"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 "	subf	%0,%2,%0 \n\
 2:"
 	: "=&r" (t)
 	: "r" (&v->counter), "r" (a), "r" (u)
 	: "cc", "memory");
 
-	return t != u;
+	return t;
 }
 
-#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
+/**
+ * atomic_inc_not_zero - increment unless the number is zero
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1, so long as @v is non-zero.
+ * Returns non-zero if @v was non-zero, and zero otherwise.
+ */
+static __inline__ int atomic_inc_not_zero(atomic_t *v)
+{
+	int t1, t2;
+
+	__asm__ __volatile__ (
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	lwarx	%0,0,%2		# atomic_inc_not_zero\n\
+	cmpwi	0,%0,0\n\
+	beq-	2f\n\
+	addic	%1,%0,1\n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%1,0,%2\n\
+	bne-	1b\n"
+	PPC_ATOMIC_EXIT_BARRIER
+	"\n\
+2:"
+	: "=&r" (t1), "=&r" (t2)
+	: "r" (&v->counter)
+	: "cc", "xer", "memory");
+
+	return t1;
+}
+#define atomic_inc_not_zero(v) atomic_inc_not_zero((v))
 
 #define atomic_sub_and_test(a, v)	(atomic_sub_return((a), (v)) == 0)
 #define atomic_dec_and_test(v)		(atomic_dec_return((v)) == 0)
@@ -227,7 +253,7 @@ static __inline__ int atomic_dec_if_positive(atomic_t *v)
 	int t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%1		# atomic_dec_if_positive\n\
 	cmpwi	%0,1\n\
 	addi	%0,%0,-1\n\
@@ -235,7 +261,7 @@ static __inline__ int atomic_dec_if_positive(atomic_t *v)
 	PPC405_ERR77(0,%1)
 "	stwcx.	%0,0,%1\n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	"\n\
 2:"	: "=&b" (t)
 	: "r" (&v->counter)
@@ -243,11 +269,7 @@ static __inline__ int atomic_dec_if_positive(atomic_t *v)
 
 	return t;
 }
-
-#define smp_mb__before_atomic_dec()     smp_mb()
-#define smp_mb__after_atomic_dec()      smp_mb()
-#define smp_mb__before_atomic_inc()     smp_mb()
-#define smp_mb__after_atomic_inc()      smp_mb()
+#define atomic_dec_if_positive atomic_dec_if_positive
 
 #ifdef __powerpc64__
 
@@ -286,12 +308,12 @@ static __inline__ long atomic64_add_return(long a, atomic64_t *v)
 	long t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%2		# atomic64_add_return\n\
 	add	%0,%1,%0\n\
 	stdcx.	%0,0,%2 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (a), "r" (&v->counter)
 	: "cc", "memory");
@@ -320,12 +342,12 @@ static __inline__ long atomic64_sub_return(long a, atomic64_t *v)
 	long t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%2		# atomic64_sub_return\n\
 	subf	%0,%1,%0\n\
 	stdcx.	%0,0,%2 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (a), "r" (&v->counter)
 	: "cc", "memory");
@@ -352,12 +374,12 @@ static __inline__ long atomic64_inc_return(atomic64_t *v)
 	long t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%1		# atomic64_inc_return\n\
 	addic	%0,%0,1\n\
 	stdcx.	%0,0,%1 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (&v->counter)
 	: "cc", "xer", "memory");
@@ -394,12 +416,12 @@ static __inline__ long atomic64_dec_return(atomic64_t *v)
 	long t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%1		# atomic64_dec_return\n\
 	addic	%0,%0,-1\n\
 	stdcx.	%0,0,%1\n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (&v->counter)
 	: "cc", "xer", "memory");
@@ -419,13 +441,13 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 	long t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%1		# atomic64_dec_if_positive\n\
 	addic.	%0,%0,-1\n\
 	blt-	2f\n\
 	stdcx.	%0,0,%1\n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	"\n\
 2:"	: "=&r" (t)
 	: "r" (&v->counter)
@@ -444,21 +466,21 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
  * @u: ...unless v is equal to u.
  *
  * Atomically adds @a to @v, so long as it was not @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
+ * Returns the old value of @v.
  */
 static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
 {
 	long t;
 
 	__asm__ __volatile__ (
-	PPC_RELEASE_BARRIER
-"1:	ldarx	%0,0,%1		# atomic_add_unless\n\
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	ldarx	%0,0,%1		# __atomic_add_unless\n\
 	cmpd	0,%0,%3 \n\
 	beq-	2f \n\
 	add	%0,%2,%0 \n"
 "	stdcx.	%0,0,%1 \n\
 	bne-	1b \n"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 "	subf	%0,%2,%0 \n\
 2:"
 	: "=&r" (t)
@@ -468,13 +490,36 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
 	return t != u;
 }
 
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
+/**
+ * atomic_inc64_not_zero - increment unless the number is zero
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically increments @v by 1, so long as @v is non-zero.
+ * Returns non-zero if @v was non-zero, and zero otherwise.
+ */
+static __inline__ long atomic64_inc_not_zero(atomic64_t *v)
+{
+	long t1, t2;
+
+	__asm__ __volatile__ (
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	ldarx	%0,0,%2		# atomic64_inc_not_zero\n\
+	cmpdi	0,%0,0\n\
+	beq-	2f\n\
+	addic	%1,%0,1\n\
+	stdcx.	%1,0,%2\n\
+	bne-	1b\n"
+	PPC_ATOMIC_EXIT_BARRIER
+	"\n\
+2:"
+	: "=&r" (t1), "=&r" (t2)
+	: "r" (&v->counter)
+	: "cc", "xer", "memory");
 
-#else  /* __powerpc64__ */
-#include <asm-generic/atomic64.h>
+	return t1;
+}
 
 #endif /* __powerpc64__ */
 
-#include <asm-generic/atomic-long.h>
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_ATOMIC_H_ */
diff --git a/arch/powerpc/include/asm/auxvec.h b/arch/powerpc/include/asm/auxvec.h
deleted file mode 100644
index 19a099b62cd..00000000000
--- a/arch/powerpc/include/asm/auxvec.h
+++ /dev/null
@@ -1,19 +0,0 @@
-#ifndef _ASM_POWERPC_AUXVEC_H
-#define _ASM_POWERPC_AUXVEC_H
-
-/*
- * We need to put in some extra aux table entries to tell glibc what
- * the cache block size is, so it can use the dcbz instruction safely.
- */
-#define AT_DCACHEBSIZE		19
-#define AT_ICACHEBSIZE		20
-#define AT_UCACHEBSIZE		21
-/* A special ignored type value for PPC, for glibc compatibility.  */
-#define AT_IGNOREPPC		22
-
-/* The vDSO location. We have to use the same value as x86 for glibc's
- * sake :-)
- */
-#define AT_SYSINFO_EHDR		33
-
-#endif
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
new file mode 100644
index 00000000000..bab79a110c7
--- /dev/null
+++ b/arch/powerpc/include/asm/barrier.h
@@ -0,0 +1,90 @@
+/*
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ */
+#ifndef _ASM_POWERPC_BARRIER_H
+#define _ASM_POWERPC_BARRIER_H
+
+/*
+ * Memory barrier.
+ * The sync instruction guarantees that all memory accesses initiated
+ * by this processor have been performed (with respect to all other
+ * mechanisms that access memory).  The eieio instruction is a barrier
+ * providing an ordering (separately) for (a) cacheable stores and (b)
+ * loads and stores to non-cacheable memory (e.g. I/O devices).
+ *
+ * mb() prevents loads and stores being reordered across this point.
+ * rmb() prevents loads being reordered across this point.
+ * wmb() prevents stores being reordered across this point.
+ * read_barrier_depends() prevents data-dependent loads being reordered
+ *	across this point (nop on PPC).
+ *
+ * *mb() variants without smp_ prefix must order all types of memory
+ * operations with one another. sync is the only instruction sufficient
+ * to do this.
+ *
+ * For the smp_ barriers, ordering is for cacheable memory operations
+ * only. We have to use the sync instruction for smp_mb(), since lwsync
+ * doesn't order loads with respect to previous stores.  Lwsync can be
+ * used for smp_rmb() and smp_wmb().
+ *
+ * However, on CPUs that don't support lwsync, lwsync actually maps to a
+ * heavy-weight sync, so smp_wmb() can be a lighter-weight eieio.
+ */
+#define mb()   __asm__ __volatile__ ("sync" : : : "memory")
+#define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
+#define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
+#define read_barrier_depends()  do { } while(0)
+
+#define set_mb(var, value)	do { var = value; mb(); } while (0)
+
+#ifdef CONFIG_SMP
+
+#ifdef __SUBARCH_HAS_LWSYNC
+#    define SMPWMB      LWSYNC
+#else
+#    define SMPWMB      eieio
+#endif
+
+#define __lwsync()	__asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+
+#define smp_mb()	mb()
+#define smp_rmb()	__lwsync()
+#define smp_wmb()	__asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
+#define smp_read_barrier_depends()	read_barrier_depends()
+#else
+#define __lwsync()	barrier()
+
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	do { } while(0)
+#endif /* CONFIG_SMP */
+
+/*
+ * This is a barrier which prevents following instructions from being
+ * started until the value of the argument x is known.  For example, if
+ * x is a variable loaded from memory, this prevents following
+ * instructions from being executed until the load has been performed.
+ */
+#define data_barrier(x)	\
+	asm volatile("twi 0,%0,0; isync" : : "r" (x) : "memory");
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	__lwsync();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	__lwsync();							\
+	___p1;								\
+})
+
+#define smp_mb__before_atomic()     smp_mb()
+#define smp_mb__after_atomic()      smp_mb()
+
+#endif /* _ASM_POWERPC_BARRIER_H */
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index 30964ae2d09..bd3bd573d0a 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -46,18 +46,15 @@
 #include <asm/asm-compat.h>
 #include <asm/synch.h>
 
-/*
- * clear_bit doesn't imply a memory barrier
- */
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	smp_mb()
+/* PPC bit number conversion */
+#define PPC_BITLSHIFT(be)	(BITS_PER_LONG - 1 - (be))
+#define PPC_BIT(bit)		(1UL << PPC_BITLSHIFT(bit))
+#define PPC_BITMASK(bs, be)	((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs))
 
-#define BITOP_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
-#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
-#define BITOP_LE_SWIZZLE	((BITS_PER_LONG-1) & ~0x7)
+#include <asm/barrier.h>
 
 /* Macro for generating the ***_bits() functions */
-#define DEFINE_BITOP(fn, op, prefix, postfix)	\
+#define DEFINE_BITOP(fn, op, prefix)		\
 static __inline__ void fn(unsigned long mask,	\
 		volatile unsigned long *_p)	\
 {						\
@@ -70,35 +67,34 @@ static __inline__ void fn(unsigned long mask,	\
 	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, PPC_RELEASE_BARRIER, "")
-DEFINE_BITOP(change_bits, xor, "", "")
+DEFINE_BITOP(set_bits, or, "")
+DEFINE_BITOP(clear_bits, andc, "")
+DEFINE_BITOP(clear_bits_unlock, andc, PPC_RELEASE_BARRIER)
+DEFINE_BITOP(change_bits, xor, "")
 
 static __inline__ void set_bit(int nr, volatile unsigned long *addr)
 {
-	set_bits(BITOP_MASK(nr), addr + BITOP_WORD(nr));
+	set_bits(BIT_MASK(nr), addr + BIT_WORD(nr));
 }
 
 static __inline__ void clear_bit(int nr, volatile unsigned long *addr)
 {
-	clear_bits(BITOP_MASK(nr), addr + BITOP_WORD(nr));
+	clear_bits(BIT_MASK(nr), addr + BIT_WORD(nr));
 }
 
 static __inline__ void clear_bit_unlock(int nr, volatile unsigned long *addr)
 {
-	clear_bits_unlock(BITOP_MASK(nr), addr + BITOP_WORD(nr));
+	clear_bits_unlock(BIT_MASK(nr), addr + BIT_WORD(nr));
 }
 
 static __inline__ void change_bit(int nr, volatile unsigned long *addr)
 {
-	change_bits(BITOP_MASK(nr), addr + BITOP_WORD(nr));
+	change_bits(BIT_MASK(nr), addr + BIT_WORD(nr));
 }
 
 /* Like DEFINE_BITOP(), with changes to the arguments to 'op' and the output
@@ -124,38 +120,38 @@ static __inline__ unsigned long fn(			\
 	return (old & mask);				\
 }
 
-DEFINE_TESTOP(test_and_set_bits, or, PPC_RELEASE_BARRIER,
-	      PPC_ACQUIRE_BARRIER, 0)
+DEFINE_TESTOP(test_and_set_bits, or, PPC_ATOMIC_ENTRY_BARRIER,
+	      PPC_ATOMIC_EXIT_BARRIER, 0)
 DEFINE_TESTOP(test_and_set_bits_lock, or, "",
 	      PPC_ACQUIRE_BARRIER, 1)
-DEFINE_TESTOP(test_and_clear_bits, andc, PPC_RELEASE_BARRIER,
-	      PPC_ACQUIRE_BARRIER, 0)
-DEFINE_TESTOP(test_and_change_bits, xor, PPC_RELEASE_BARRIER,
-	      PPC_ACQUIRE_BARRIER, 0)
+DEFINE_TESTOP(test_and_clear_bits, andc, PPC_ATOMIC_ENTRY_BARRIER,
+	      PPC_ATOMIC_EXIT_BARRIER, 0)
+DEFINE_TESTOP(test_and_change_bits, xor, PPC_ATOMIC_ENTRY_BARRIER,
+	      PPC_ATOMIC_EXIT_BARRIER, 0)
 
 static __inline__ int test_and_set_bit(unsigned long nr,
 				       volatile unsigned long *addr)
 {
-	return test_and_set_bits(BITOP_MASK(nr), addr + BITOP_WORD(nr)) != 0;
+	return test_and_set_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0;
 }
 
 static __inline__ int test_and_set_bit_lock(unsigned long nr,
 				       volatile unsigned long *addr)
 {
-	return test_and_set_bits_lock(BITOP_MASK(nr),
-				addr + BITOP_WORD(nr)) != 0;
+	return test_and_set_bits_lock(BIT_MASK(nr),
+				addr + BIT_WORD(nr)) != 0;
 }
 
 static __inline__ int test_and_clear_bit(unsigned long nr,
 					 volatile unsigned long *addr)
 {
-	return test_and_clear_bits(BITOP_MASK(nr), addr + BITOP_WORD(nr)) != 0;
+	return test_and_clear_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0;
 }
 
 static __inline__ int test_and_change_bit(unsigned long nr,
 					  volatile unsigned long *addr)
 {
-	return test_and_change_bits(BITOP_MASK(nr), addr + BITOP_WORD(nr)) != 0;
+	return test_and_change_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0;
 }
 
 #include <asm-generic/bitops/non-atomic.h>
@@ -209,8 +205,8 @@ static __inline__ unsigned long ffz(unsigned long x)
 		return BITS_PER_LONG;
 
 	/*
-	 * Calculate the bit position of the least signficant '1' bit in x
-	 * (since x has been changed this will actually be the least signficant
+	 * Calculate the bit position of the least significant '1' bit in x
+	 * (since x has been changed this will actually be the least significant
 	 * '0' bit in * the original x).  Note: (x & -x) gives us a mask that
 	 * is the least significant * (RIGHT-most) 1-bit of the value in x.
 	 */
@@ -267,73 +263,24 @@ static __inline__ int fls64(__u64 x)
 #include <asm-generic/bitops/fls64.h>
 #endif /* __powerpc64__ */
 
+#ifdef CONFIG_PPC64
+unsigned int __arch_hweight8(unsigned int w);
+unsigned int __arch_hweight16(unsigned int w);
+unsigned int __arch_hweight32(unsigned int w);
+unsigned long __arch_hweight64(__u64 w);
+#include <asm-generic/bitops/const_hweight.h>
+#else
 #include <asm-generic/bitops/hweight.h>
+#endif
+
 #include <asm-generic/bitops/find.h>
 
 /* Little-endian versions */
+#include <asm-generic/bitops/le.h>
 
-static __inline__ int test_le_bit(unsigned long nr,
-				  __const__ unsigned long *addr)
-{
-	__const__ unsigned char	*tmp = (__const__ unsigned char *) addr;
-	return (tmp[nr >> 3] >> (nr & 7)) & 1;
-}
-
-#define __set_le_bit(nr, addr) \
-	__set_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
-#define __clear_le_bit(nr, addr) \
-	__clear_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
-
-#define test_and_set_le_bit(nr, addr) \
-	test_and_set_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
-#define test_and_clear_le_bit(nr, addr) \
-	test_and_clear_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
-
-#define __test_and_set_le_bit(nr, addr) \
-	__test_and_set_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
-#define __test_and_clear_le_bit(nr, addr) \
-	__test_and_clear_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
-
-#define find_first_zero_le_bit(addr, size) generic_find_next_zero_le_bit((addr), (size), 0)
-unsigned long generic_find_next_zero_le_bit(const unsigned long *addr,
-				    unsigned long size, unsigned long offset);
-
-unsigned long generic_find_next_le_bit(const unsigned long *addr,
-				    unsigned long size, unsigned long offset);
 /* Bitmap functions for the ext2 filesystem */
 
-#define ext2_set_bit(nr,addr) \
-	__test_and_set_le_bit((nr), (unsigned long*)addr)
-#define ext2_clear_bit(nr, addr) \
-	__test_and_clear_le_bit((nr), (unsigned long*)addr)
-
-#define ext2_set_bit_atomic(lock, nr, addr) \
-	test_and_set_le_bit((nr), (unsigned long*)addr)
-#define ext2_clear_bit_atomic(lock, nr, addr) \
-	test_and_clear_le_bit((nr), (unsigned long*)addr)
-
-#define ext2_test_bit(nr, addr)      test_le_bit((nr),(unsigned long*)addr)
-
-#define ext2_find_first_zero_bit(addr, size) \
-	find_first_zero_le_bit((unsigned long*)addr, size)
-#define ext2_find_next_zero_bit(addr, size, off) \
-	generic_find_next_zero_le_bit((unsigned long*)addr, size, off)
-
-#define ext2_find_next_bit(addr, size, off) \
-	generic_find_next_le_bit((unsigned long *)addr, size, off)
-/* Bitmap functions for the minix filesystem.  */
-
-#define minix_test_and_set_bit(nr,addr) \
-	__test_and_set_le_bit(nr, (unsigned long *)addr)
-#define minix_set_bit(nr,addr) \
-	__set_le_bit(nr, (unsigned long *)addr)
-#define minix_test_and_clear_bit(nr,addr) \
-	__test_and_clear_le_bit(nr, (unsigned long *)addr)
-#define minix_test_bit(nr,addr) \
-	test_le_bit(nr, (unsigned long *)addr)
-
-#define minix_find_first_zero_bit(addr,size) \
-	find_first_zero_le_bit((unsigned long *)addr, size)
+#include <asm-generic/bitops/ext2-atomic-setbit.h>
 
 #include <asm-generic/bitops/sched.h>
 
diff --git a/arch/powerpc/include/asm/bitsperlong.h b/arch/powerpc/include/asm/bitsperlong.h
deleted file mode 100644
index 5f1659032c4..00000000000
--- a/arch/powerpc/include/asm/bitsperlong.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef __ASM_POWERPC_BITSPERLONG_H
-#define __ASM_POWERPC_BITSPERLONG_H
-
-#if defined(__powerpc64__)
-# define __BITS_PER_LONG 64
-#else
-# define __BITS_PER_LONG 32
-#endif
-
-#include <asm-generic/bitsperlong.h>
-
-#endif /* __ASM_POWERPC_BITSPERLONG_H */
diff --git a/arch/powerpc/include/asm/bootx.h b/arch/powerpc/include/asm/bootx.h
index 60a3c9ef301..dd9461003df 100644
--- a/arch/powerpc/include/asm/bootx.h
+++ b/arch/powerpc/include/asm/bootx.h
@@ -5,126 +5,11 @@
  * Written by Benjamin Herrenschmidt.
  */
 
-
 #ifndef __ASM_BOOTX_H__
 #define __ASM_BOOTX_H__
 
-#include <linux/types.h>
-
-#ifdef macintosh
-#include <Types.h>
-#include "linux_type_defs.h"
-#endif
-
-#ifdef macintosh
-/* All this requires PowerPC alignment */
-#pragma options align=power
-#endif
-
-/* On kernel entry:
- *
- * r3 = 0x426f6f58    ('BooX')
- * r4 = pointer to boot_infos
- * r5 = NULL
- *
- * Data and instruction translation disabled, interrupts
- * disabled, kernel loaded at physical 0x00000000 on PCI
- * machines (will be different on NuBus).
- */
-
-#define BOOT_INFO_VERSION               5
-#define BOOT_INFO_COMPATIBLE_VERSION    1
-
-/* Bit in the architecture flag mask. More to be defined in
-   future versions. Note that either BOOT_ARCH_PCI or
-   BOOT_ARCH_NUBUS is set. The other BOOT_ARCH_NUBUS_xxx are
-   set additionally when BOOT_ARCH_NUBUS is set.
- */
-#define BOOT_ARCH_PCI                   0x00000001UL
-#define BOOT_ARCH_NUBUS                 0x00000002UL
-#define BOOT_ARCH_NUBUS_PDM             0x00000010UL
-#define BOOT_ARCH_NUBUS_PERFORMA        0x00000020UL
-#define BOOT_ARCH_NUBUS_POWERBOOK       0x00000040UL
-
-/*  Maximum number of ranges in phys memory map */
-#define MAX_MEM_MAP_SIZE				26
-
-/* This is the format of an element in the physical memory map. Note that
-   the map is optional and current BootX will only build it for pre-PCI
-   machines */
-typedef struct boot_info_map_entry
-{
-    __u32       physAddr;                /* Physical starting address */
-    __u32       size;                    /* Size in bytes */
-} boot_info_map_entry_t;
-
-
-/* Here are the boot informations that are passed to the bootstrap
- * Note that the kernel arguments and the device tree are appended
- * at the end of this structure. */
-typedef struct boot_infos
-{
-    /* Version of this structure */
-    __u32       version;
-    /* backward compatible down to version: */
-    __u32       compatible_version;
-
-    /* NEW (vers. 2) this holds the current _logical_ base addr of
-       the frame buffer (for use by early boot message) */
-    __u8*       logicalDisplayBase;
+#include <uapi/asm/bootx.h>
 
-    /* NEW (vers. 4) Apple's machine identification */
-    __u32       machineID;
-
-    /* NEW (vers. 4) Detected hw architecture */
-    __u32       architecture;
-
-    /* The device tree (internal addresses relative to the beginning of the tree,
-     * device tree offset relative to the beginning of this structure).
-     * On pre-PCI macintosh (BOOT_ARCH_PCI bit set to 0 in architecture), this
-     * field is 0.
-     */
-    __u32       deviceTreeOffset;        /* Device tree offset */
-    __u32       deviceTreeSize;          /* Size of the device tree */
-
-    /* Some infos about the current MacOS display */
-    __u32       dispDeviceRect[4];       /* left,top,right,bottom */
-    __u32       dispDeviceDepth;         /* (8, 16 or 32) */
-    __u8*       dispDeviceBase;          /* base address (physical) */
-    __u32       dispDeviceRowBytes;      /* rowbytes (in bytes) */
-    __u32       dispDeviceColorsOffset;  /* Colormap (8 bits only) or 0 (*) */
-    /* Optional offset in the registry to the current
-     * MacOS display. (Can be 0 when not detected) */
-     __u32      dispDeviceRegEntryOffset;
-
-    /* Optional pointer to boot ramdisk (offset from this structure) */
-    __u32       ramDisk;
-    __u32       ramDiskSize;             /* size of ramdisk image */
-
-    /* Kernel command line arguments (offset from this structure) */
-    __u32       kernelParamsOffset;
-
-    /* ALL BELOW NEW (vers. 4) */
-
-    /* This defines the physical memory. Valid with BOOT_ARCH_NUBUS flag
-       (non-PCI) only. On PCI, memory is contiguous and it's size is in the
-       device-tree. */
-    boot_info_map_entry_t
-    	        physMemoryMap[MAX_MEM_MAP_SIZE]; /* Where the phys memory is */
-    __u32       physMemoryMapSize;               /* How many entries in map */
-
-
-    /* The framebuffer size (optional, currently 0) */
-    __u32       frameBufferSize;         /* Represents a max size, can be 0. */
-
-    /* NEW (vers. 5) */
-
-    /* Total params size (args + colormap + device tree + ramdisk) */
-    __u32       totalParamsSize;
-
-} boot_infos_t;
-
-#ifdef __KERNEL__
 /* (*) The format of the colormap is 256 * 3 * 2 bytes. Each color index
  * is represented by 3 short words containing a 16 bits (unsigned) color
  * component. Later versions may contain the gamma table for direct-color
@@ -162,10 +47,4 @@ struct bootx_dt_node {
 
 extern void bootx_init(unsigned long r4, unsigned long phys);
 
-#endif /* __KERNEL__ */
-
-#ifdef macintosh
-#pragma options align=reset
-#endif
-
 #endif
diff --git a/arch/powerpc/include/asm/btext.h b/arch/powerpc/include/asm/btext.h
index 906f46e3100..89fc382648b 100644
--- a/arch/powerpc/include/asm/btext.h
+++ b/arch/powerpc/include/asm/btext.h
@@ -13,6 +13,7 @@ extern void btext_update_display(unsigned long phys, int width, int height,
 extern void btext_setup_display(int width, int height, int depth, int pitch,
 				unsigned long address);
 extern void btext_prepare_BAT(void);
+extern void btext_map(void);
 extern void btext_unmap(void);
 
 extern void btext_drawchar(char c);
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index 065c590c991..3eb53d74107 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -126,5 +126,16 @@
 
 #include <asm-generic/bug.h>
 
+#ifndef __ASSEMBLY__
+
+struct pt_regs;
+extern int do_page_fault(struct pt_regs *, unsigned long, unsigned long);
+extern void bad_page_fault(struct pt_regs *, unsigned long, int);
+extern void _exception(int, struct pt_regs *, int, unsigned long);
+extern void die(const char *, struct pt_regs *, long);
+extern void print_backtrace(unsigned long *);
+
+#endif /* !__ASSEMBLY__ */
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_BUG_H */
diff --git a/arch/powerpc/include/asm/byteorder.h b/arch/powerpc/include/asm/byteorder.h
deleted file mode 100644
index aa6cc4fac96..00000000000
--- a/arch/powerpc/include/asm/byteorder.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_POWERPC_BYTEORDER_H
-#define _ASM_POWERPC_BYTEORDER_H
-
-/*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-#include <linux/byteorder/big_endian.h>
-
-#endif /* _ASM_POWERPC_BYTEORDER_H */
diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h
index 4b509411ad8..ed0afc1e44a 100644
--- a/arch/powerpc/include/asm/cache.h
+++ b/arch/powerpc/include/asm/cache.h
@@ -41,9 +41,37 @@ struct ppc64_caches {
 extern struct ppc64_caches ppc64_caches;
 #endif /* __powerpc64__ && ! __ASSEMBLY__ */
 
-#if !defined(__ASSEMBLY__)
+#if defined(__ASSEMBLY__)
+/*
+ * For a snooping icache, we still need a dummy icbi to purge all the
+ * prefetched instructions from the ifetch buffers. We also need a sync
+ * before the icbi to order the the actual stores to memory that might
+ * have modified instructions with the icbi.
+ */
+#define PURGE_PREFETCHED_INS	\
+	sync;			\
+	icbi	0,r3;		\
+	sync;			\
+	isync
+
+#else
 #define __read_mostly __attribute__((__section__(".data..read_mostly")))
+
+#ifdef CONFIG_6xx
+extern long _get_L2CR(void);
+extern long _get_L3CR(void);
+extern void _set_L2CR(unsigned long);
+extern void _set_L3CR(unsigned long);
+#else
+#define _get_L2CR()	0L
+#define _get_L3CR()	0L
+#define _set_L2CR(val)	do { } while(0)
+#define _set_L3CR(val)	do { } while(0)
 #endif
 
+extern void cacheable_memzero(void *p, unsigned int nb);
+extern void *cacheable_memcpy(void *, const void *, unsigned int);
+
+#endif /* !__ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_CACHE_H */
diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index ab9e402518e..5b9312220e8 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -30,13 +30,9 @@ 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)
 
-extern void __flush_icache_range(unsigned long, unsigned long);
-static inline void flush_icache_range(unsigned long start, unsigned long stop)
-{
-	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
-		__flush_icache_range(start, stop);
-}
+extern void __flush_disable_L1(void);
 
+extern void flush_icache_range(unsigned long, unsigned long);
 extern void flush_icache_user_range(struct vm_area_struct *vma,
 				    struct page *page, unsigned long addr,
 				    int len);
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index ce0c28495f9..8251a3ba870 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -14,6 +14,9 @@
  * which always checksum on 4 octet boundaries.  ihl is the number
  * of 32-bit words and is always >= 5.
  */
+#ifdef CONFIG_GENERIC_CSUM
+#include <asm-generic/checksum.h>
+#else
 extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
 
 /*
@@ -123,5 +126,7 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 	return sum;
 #endif
 }
+
+#endif
 #endif /* __KERNEL__ */
 #endif
diff --git a/arch/powerpc/include/asm/clk_interface.h b/arch/powerpc/include/asm/clk_interface.h
deleted file mode 100644
index ab1882c1e17..00000000000
--- a/arch/powerpc/include/asm/clk_interface.h
+++ /dev/null
@@ -1,20 +0,0 @@
-#ifndef __ASM_POWERPC_CLK_INTERFACE_H
-#define __ASM_POWERPC_CLK_INTERFACE_H
-
-#include <linux/clk.h>
-
-struct clk_interface {
-	struct clk*	(*clk_get)	(struct device *dev, const char *id);
-	int		(*clk_enable)	(struct clk *clk);
-	void		(*clk_disable)	(struct clk *clk);
-	unsigned long	(*clk_get_rate)	(struct clk *clk);
-	void		(*clk_put)	(struct clk *clk);
-	long		(*clk_round_rate) (struct clk *clk, unsigned long rate);
-	int 		(*clk_set_rate)	(struct clk *clk, unsigned long rate);
-	int		(*clk_set_parent) (struct clk *clk, struct clk *parent);
-	struct clk*	(*clk_get_parent) (struct clk *clk);
-};
-
-extern struct clk_interface clk_functions;
-
-#endif /* __ASM_POWERPC_CLK_INTERFACE_H */
diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h
new file mode 100644
index 00000000000..d463c68fe7f
--- /dev/null
+++ b/arch/powerpc/include/asm/cmpxchg.h
@@ -0,0 +1,310 @@
+#ifndef _ASM_POWERPC_CMPXCHG_H_
+#define _ASM_POWERPC_CMPXCHG_H_
+
+#ifdef __KERNEL__
+#include <linux/compiler.h>
+#include <asm/synch.h>
+#include <asm/asm-compat.h>
+
+/*
+ * Atomic exchange
+ *
+ * Changes the memory location '*ptr' to be val and returns
+ * the previous value stored there.
+ */
+static __always_inline unsigned long
+__xchg_u32(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+	PPC_RELEASE_BARRIER
+"1:	lwarx	%0,0,%2 \n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%3,0,%2 \n\
+	bne-	1b"
+	PPC_ACQUIRE_BARRIER
+	: "=&r" (prev), "+m" (*(volatile unsigned int *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+
+/*
+ * Atomic exchange
+ *
+ * Changes the memory location '*ptr' to be val and returns
+ * the previous value stored there.
+ */
+static __always_inline unsigned long
+__xchg_u32_local(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%2 \n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%3,0,%2 \n\
+	bne-	1b"
+	: "=&r" (prev), "+m" (*(volatile unsigned int *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+
+#ifdef CONFIG_PPC64
+static __always_inline unsigned long
+__xchg_u64(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+	PPC_RELEASE_BARRIER
+"1:	ldarx	%0,0,%2 \n"
+	PPC405_ERR77(0,%2)
+"	stdcx.	%3,0,%2 \n\
+	bne-	1b"
+	PPC_ACQUIRE_BARRIER
+	: "=&r" (prev), "+m" (*(volatile unsigned long *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__xchg_u64_local(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%2 \n"
+	PPC405_ERR77(0,%2)
+"	stdcx.	%3,0,%2 \n\
+	bne-	1b"
+	: "=&r" (prev), "+m" (*(volatile unsigned long *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+#endif
+
+/*
+ * This function doesn't exist, so you'll get a linker error
+ * if something tries to do an invalid xchg().
+ */
+extern void __xchg_called_with_bad_pointer(void);
+
+static __always_inline unsigned long
+__xchg(volatile void *ptr, unsigned long x, unsigned int size)
+{
+	switch (size) {
+	case 4:
+		return __xchg_u32(ptr, x);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __xchg_u64(ptr, x);
+#endif
+	}
+	__xchg_called_with_bad_pointer();
+	return x;
+}
+
+static __always_inline unsigned long
+__xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
+{
+	switch (size) {
+	case 4:
+		return __xchg_u32_local(ptr, x);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __xchg_u64_local(ptr, x);
+#endif
+	}
+	__xchg_called_with_bad_pointer();
+	return x;
+}
+#define xchg(ptr,x)							     \
+  ({									     \
+     __typeof__(*(ptr)) _x_ = (x);					     \
+     (__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_, sizeof(*(ptr))); \
+  })
+
+#define xchg_local(ptr,x)						     \
+  ({									     \
+     __typeof__(*(ptr)) _x_ = (x);					     \
+     (__typeof__(*(ptr))) __xchg_local((ptr),				     \
+     		(unsigned long)_x_, sizeof(*(ptr))); 			     \
+  })
+
+/*
+ * Compare and exchange - if *p == old, set it to new,
+ * and return the old value of *p.
+ */
+#define __HAVE_ARCH_CMPXCHG	1
+
+static __always_inline unsigned long
+__cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+	PPC_RELEASE_BARRIER
+"1:	lwarx	%0,0,%2		# __cmpxchg_u32\n\
+	cmpw	0,%0,%3\n\
+	bne-	2f\n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%4,0,%2\n\
+	bne-	1b"
+	PPC_ACQUIRE_BARRIER
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u32_local(volatile unsigned int *p, unsigned long old,
+			unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+"1:	lwarx	%0,0,%2		# __cmpxchg_u32\n\
+	cmpw	0,%0,%3\n\
+	bne-	2f\n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%4,0,%2\n\
+	bne-	1b"
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+#ifdef CONFIG_PPC64
+static __always_inline unsigned long
+__cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+	PPC_RELEASE_BARRIER
+"1:	ldarx	%0,0,%2		# __cmpxchg_u64\n\
+	cmpd	0,%0,%3\n\
+	bne-	2f\n\
+	stdcx.	%4,0,%2\n\
+	bne-	1b"
+	PPC_ACQUIRE_BARRIER
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u64_local(volatile unsigned long *p, unsigned long old,
+			unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	ldarx	%0,0,%2		# __cmpxchg_u64\n\
+	cmpd	0,%0,%3\n\
+	bne-	2f\n\
+	stdcx.	%4,0,%2\n\
+	bne-	1b"
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+#endif
+
+/* This function doesn't exist, so you'll get a linker error
+   if something tries to do an invalid cmpxchg().  */
+extern void __cmpxchg_called_with_bad_pointer(void);
+
+static __always_inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new,
+	  unsigned int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32(ptr, old, new);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __cmpxchg_u64(ptr, old, new);
+#endif
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
+static __always_inline unsigned long
+__cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new,
+	  unsigned int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32_local(ptr, old, new);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __cmpxchg_u64_local(ptr, old, new);
+#endif
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
+#define cmpxchg(ptr, o, n)						 \
+  ({									 \
+     __typeof__(*(ptr)) _o_ = (o);					 \
+     __typeof__(*(ptr)) _n_ = (n);					 \
+     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		 \
+				    (unsigned long)_n_, sizeof(*(ptr))); \
+  })
+
+
+#define cmpxchg_local(ptr, o, n)					 \
+  ({									 \
+     __typeof__(*(ptr)) _o_ = (o);					 \
+     __typeof__(*(ptr)) _n_ = (n);					 \
+     (__typeof__(*(ptr))) __cmpxchg_local((ptr), (unsigned long)_o_,	 \
+				    (unsigned long)_n_, sizeof(*(ptr))); \
+  })
+
+#ifdef CONFIG_PPC64
+#define cmpxchg64(ptr, o, n)						\
+  ({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg((ptr), (o), (n));					\
+  })
+#define cmpxchg64_local(ptr, o, n)					\
+  ({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg_local((ptr), (o), (n));					\
+  })
+#define cmpxchg64_relaxed	cmpxchg64_local
+#else
+#include <asm-generic/cmpxchg-local.h>
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_CMPXCHG_H_ */
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index 37c32aba79b..840a5509b3f 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -26,27 +26,77 @@ unsigned int create_branch(const unsigned int *addr,
 			   unsigned long target, int flags);
 unsigned int create_cond_branch(const unsigned int *addr,
 				unsigned long target, int flags);
-void patch_branch(unsigned int *addr, unsigned long target, int flags);
-void patch_instruction(unsigned int *addr, unsigned int instr);
+int patch_branch(unsigned int *addr, unsigned long target, int flags);
+int patch_instruction(unsigned int *addr, unsigned int instr);
 
 int instr_is_relative_branch(unsigned int instr);
 int instr_is_branch_to_addr(const unsigned int *instr, unsigned long addr);
 unsigned long branch_target(const unsigned int *instr);
 unsigned int translate_branch(const unsigned int *dest,
 			      const unsigned int *src);
+#ifdef CONFIG_PPC_BOOK3E_64
+void __patch_exception(int exc, unsigned long addr);
+#define patch_exception(exc, name) do { \
+	extern unsigned int name; \
+	__patch_exception((exc), (unsigned long)&name); \
+} while (0)
+#endif
+
+#define OP_RT_RA_MASK	0xffff0000UL
+#define LIS_R2		0x3c020000UL
+#define ADDIS_R2_R12	0x3c4c0000UL
+#define ADDI_R2_R2	0x38420000UL
 
 static inline unsigned long ppc_function_entry(void *func)
 {
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC64)
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+	u32 *insn = func;
+
 	/*
-	 * On PPC64 the function pointer actually points to the function's
-	 * descriptor. The first entry in the descriptor is the address
-	 * of the function text.
+	 * A PPC64 ABIv2 function may have a local and a global entry
+	 * point. We need to use the local entry point when patching
+	 * functions, so identify and step over the global entry point
+	 * sequence.
+	 *
+	 * The global entry point sequence is always of the form:
+	 *
+	 * addis r2,r12,XXXX
+	 * addi  r2,r2,XXXX
+	 *
+	 * A linker optimisation may convert the addis to lis:
+	 *
+	 * lis   r2,XXXX
+	 * addi  r2,r2,XXXX
+	 */
+	if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) ||
+	     ((*insn & OP_RT_RA_MASK) == LIS_R2)) &&
+	    ((*(insn+1) & OP_RT_RA_MASK) == ADDI_R2_R2))
+		return (unsigned long)(insn + 2);
+	else
+		return (unsigned long)func;
+#else
+	/*
+	 * On PPC64 ABIv1 the function pointer actually points to the
+	 * function's descriptor. The first entry in the descriptor is the
+	 * address of the function text.
 	 */
 	return ((func_descr_t *)func)->entry;
+#endif
 #else
 	return (unsigned long)func;
 #endif
 }
 
+static inline unsigned long ppc_global_function_entry(void *func)
+{
+#if defined(CONFIG_PPC64) && defined(_CALL_ELF) && _CALL_ELF == 2
+	/* PPC64 ABIv2 the global entry point is at the address */
+	return (unsigned long)func;
+#else
+	/* All other cases there is no change vs ppc_function_entry() */
+	return ppc_function_entry(func);
+#endif
+}
+
 #endif /* _ASM_POWERPC_CODE_PATCHING_H */
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 2296112e247..b142b8e0ed9 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -8,7 +8,11 @@
 #include <linux/sched.h>
 
 #define COMPAT_USER_HZ		100
+#ifdef __BIG_ENDIAN__
 #define COMPAT_UTS_MACHINE	"ppc\0\0"
+#else
+#define COMPAT_UTS_MACHINE	"ppcle\0\0"
+#endif
 
 typedef u32		compat_size_t;
 typedef s32		compat_ssize_t;
@@ -38,6 +42,7 @@ typedef s64		compat_s64;
 typedef u32		compat_uint_t;
 typedef u32		compat_ulong_t;
 typedef u64		compat_u64;
+typedef u32		compat_uptr_t;
 
 struct compat_timespec {
 	compat_time_t	tv_sec;
@@ -100,7 +105,8 @@ struct compat_statfs {
 	compat_fsid_t	f_fsid;
 	int		f_namelen;	/* SunOS ignores this field. */
 	int		f_frsize;
-	int		f_spare[5];
+	int		f_flags;
+	int		f_spare[4];
 };
 
 #define COMPAT_RLIM_OLD_INFINITY	0x7fffffff
@@ -113,6 +119,64 @@ typedef u32		compat_old_sigset_t;
 
 typedef u32		compat_sigset_word;
 
+typedef union compat_sigval {
+	compat_int_t	sival_int;
+	compat_uptr_t	sival_ptr;
+} compat_sigval_t;
+
+#define SI_PAD_SIZE32	(128/sizeof(int) - 3)
+
+typedef struct compat_siginfo {
+	int si_signo;
+	int si_errno;
+	int si_code;
+
+	union {
+		int _pad[SI_PAD_SIZE32];
+
+		/* kill() */
+		struct {
+			compat_pid_t _pid;		/* sender's pid */
+			__compat_uid_t _uid;		/* sender's uid */
+		} _kill;
+
+		/* POSIX.1b timers */
+		struct {
+			compat_timer_t _tid;		/* timer id */
+			int _overrun;			/* overrun count */
+			compat_sigval_t _sigval;	/* same as below */
+			int _sys_private;	/* not to be passed to user */
+		} _timer;
+
+		/* POSIX.1b signals */
+		struct {
+			compat_pid_t _pid;		/* sender's pid */
+			__compat_uid_t _uid;		/* sender's uid */
+			compat_sigval_t _sigval;
+		} _rt;
+
+		/* SIGCHLD */
+		struct {
+			compat_pid_t _pid;		/* which child */
+			__compat_uid_t _uid;		/* sender's uid */
+			int _status;			/* exit code */
+			compat_clock_t _utime;
+			compat_clock_t _stime;
+		} _sigchld;
+
+		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */
+		struct {
+			unsigned int _addr; /* faulting insn/memory ref. */
+		} _sigfault;
+
+		/* SIGPOLL */
+		struct {
+			int _band;	/* POLL_IN, POLL_OUT, POLL_MSG */
+			int _fd;
+		} _sigpoll;
+	} _sifields;
+} compat_siginfo_t;
+
 #define COMPAT_OFF_T_MAX	0x7fffffff
 #define COMPAT_LOFF_T_MAX	0x7fffffffffffffffL
 
@@ -122,7 +186,6 @@ typedef u32		compat_sigset_word;
  * as pointers because the syscall entry code will have
  * appropriately converted them already.
  */
-typedef	u32		compat_uptr_t;
 
 static inline void __user *compat_ptr(compat_uptr_t uptr)
 {
@@ -140,11 +203,12 @@ static inline void __user *arch_compat_alloc_user_space(long len)
 	unsigned long usp = regs->gpr[1];
 
 	/*
-	 * We cant access below the stack pointer in the 32bit ABI and
-	 * can access 288 bytes in the 64bit ABI
+	 * We can't access below the stack pointer in the 32bit ABI and
+	 * can access 288 bytes in the 64bit big-endian ABI,
+	 * or 512 bytes with the new ELFv2 little-endian ABI.
 	 */
 	if (!is_32bit_task())
-		usp -= 288;
+		usp -= USER_REDZONE_SIZE;
 
 	return (void __user *) (usp - len);
 }
diff --git a/arch/powerpc/include/asm/context_tracking.h b/arch/powerpc/include/asm/context_tracking.h
new file mode 100644
index 00000000000..40014921fff
--- /dev/null
+++ b/arch/powerpc/include/asm/context_tracking.h
@@ -0,0 +1,10 @@
+#ifndef _ASM_POWERPC_CONTEXT_TRACKING_H
+#define _ASM_POWERPC_CONTEXT_TRACKING_H
+
+#ifdef CONFIG_CONTEXT_TRACKING
+#define SCHEDULE_USER bl	schedule_user
+#else
+#define SCHEDULE_USER bl	schedule
+#endif
+
+#endif
diff --git a/arch/powerpc/include/asm/cpm.h b/arch/powerpc/include/asm/cpm.h
index e50323fe941..4398a6cdcf5 100644
--- a/arch/powerpc/include/asm/cpm.h
+++ b/arch/powerpc/include/asm/cpm.h
@@ -98,7 +98,7 @@ typedef struct cpm_buf_desc {
 #define BD_SC_INTRPT	(0x1000)	/* Interrupt on change */
 #define BD_SC_LAST	(0x0800)	/* Last buffer in frame */
 #define BD_SC_TC	(0x0400)	/* Transmit CRC */
-#define BD_SC_CM	(0x0200)	/* Continous mode */
+#define BD_SC_CM	(0x0200)	/* Continuous mode */
 #define BD_SC_ID	(0x0100)	/* Rec'd too many idles */
 #define BD_SC_P		(0x0100)	/* xmt preamble */
 #define BD_SC_BR	(0x0020)	/* Break received */
diff --git a/arch/powerpc/include/asm/cpm1.h b/arch/powerpc/include/asm/cpm1.h
index bd07650dca5..8ee4211ca0c 100644
--- a/arch/powerpc/include/asm/cpm1.h
+++ b/arch/powerpc/include/asm/cpm1.h
@@ -4,7 +4,7 @@
  *
  * This file contains structures and information for the communication
  * processor channels.  Some CPM control and status is available
- * throught the MPC8xx internal memory map.  See immap.h for details.
+ * through the MPC8xx internal memory map.  See immap.h for details.
  * This file only contains what I need for the moment, not the total
  * CPM capabilities.  I (or someone else) will add definitions as they
  * are needed.  -- Dan
diff --git a/arch/powerpc/include/asm/cpm2.h b/arch/powerpc/include/asm/cpm2.h
index f42e9baf3a4..7c8608b0969 100644
--- a/arch/powerpc/include/asm/cpm2.h
+++ b/arch/powerpc/include/asm/cpm2.h
@@ -489,7 +489,6 @@ typedef struct scc_trans {
 #define FCC_GFMR_TCI		((uint)0x20000000)
 #define FCC_GFMR_TRX		((uint)0x10000000)
 #define FCC_GFMR_TTX		((uint)0x08000000)
-#define FCC_GFMR_TTX		((uint)0x08000000)
 #define FCC_GFMR_CDP		((uint)0x04000000)
 #define FCC_GFMR_CTSP		((uint)0x02000000)
 #define FCC_GFMR_CDS		((uint)0x01000000)
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index f3a1fdd9cf0..0fdd7eece6d 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -1,42 +1,10 @@
 #ifndef __ASM_POWERPC_CPUTABLE_H
 #define __ASM_POWERPC_CPUTABLE_H
 
-#define PPC_FEATURE_32			0x80000000
-#define PPC_FEATURE_64			0x40000000
-#define PPC_FEATURE_601_INSTR		0x20000000
-#define PPC_FEATURE_HAS_ALTIVEC		0x10000000
-#define PPC_FEATURE_HAS_FPU		0x08000000
-#define PPC_FEATURE_HAS_MMU		0x04000000
-#define PPC_FEATURE_HAS_4xxMAC		0x02000000
-#define PPC_FEATURE_UNIFIED_CACHE	0x01000000
-#define PPC_FEATURE_HAS_SPE		0x00800000
-#define PPC_FEATURE_HAS_EFP_SINGLE	0x00400000
-#define PPC_FEATURE_HAS_EFP_DOUBLE	0x00200000
-#define PPC_FEATURE_NO_TB		0x00100000
-#define PPC_FEATURE_POWER4		0x00080000
-#define PPC_FEATURE_POWER5		0x00040000
-#define PPC_FEATURE_POWER5_PLUS		0x00020000
-#define PPC_FEATURE_CELL		0x00010000
-#define PPC_FEATURE_BOOKE		0x00008000
-#define PPC_FEATURE_SMT			0x00004000
-#define PPC_FEATURE_ICACHE_SNOOP	0x00002000
-#define PPC_FEATURE_ARCH_2_05		0x00001000
-#define PPC_FEATURE_PA6T		0x00000800
-#define PPC_FEATURE_HAS_DFP		0x00000400
-#define PPC_FEATURE_POWER6_EXT		0x00000200
-#define PPC_FEATURE_ARCH_2_06		0x00000100
-#define PPC_FEATURE_HAS_VSX		0x00000080
-
-#define PPC_FEATURE_PSERIES_PERFMON_COMPAT \
-					0x00000040
-
-#define PPC_FEATURE_TRUE_LE		0x00000002
-#define PPC_FEATURE_PPC_LE		0x00000001
-
-#ifdef __KERNEL__
 
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
+#include <uapi/asm/cputable.h>
 
 #ifndef __ASSEMBLY__
 
@@ -84,6 +52,7 @@ struct cpu_spec {
 	char		*cpu_name;
 	unsigned long	cpu_features;		/* Kernel features */
 	unsigned int	cpu_user_features;	/* Userland features */
+	unsigned int	cpu_user_features2;	/* Userland features v2 */
 	unsigned int	mmu_features;		/* MMU features */
 
 	/* cache line sizes */
@@ -121,6 +90,18 @@ struct cpu_spec {
 	 * if the error is fatal, 1 if it was fully recovered and 0 to
 	 * pass up (not CPU originated) */
 	int		(*machine_check)(struct pt_regs *regs);
+
+	/*
+	 * Processor specific early machine check handler which is
+	 * called in real mode to handle SLB and TLB errors.
+	 */
+	long		(*machine_check_early)(struct pt_regs *regs);
+
+	/*
+	 * Processor specific routine to flush tlbs.
+	 */
+	void		(*flush_tlb)(unsigned long inval_selector);
+
 };
 
 extern struct cpu_spec		*cur_cpu_spec;
@@ -138,34 +119,37 @@ extern const char *powerpc_base_platform;
 /* CPU kernel features */
 
 /* Retain the 32b definitions all use bottom half of word */
-#define CPU_FTR_COHERENT_ICACHE		ASM_CONST(0x0000000000000001)
-#define CPU_FTR_L2CR			ASM_CONST(0x0000000000000002)
-#define CPU_FTR_SPEC7450		ASM_CONST(0x0000000000000004)
-#define CPU_FTR_ALTIVEC			ASM_CONST(0x0000000000000008)
-#define CPU_FTR_TAU			ASM_CONST(0x0000000000000010)
-#define CPU_FTR_CAN_DOZE		ASM_CONST(0x0000000000000020)
-#define CPU_FTR_USE_TB			ASM_CONST(0x0000000000000040)
-#define CPU_FTR_L2CSR			ASM_CONST(0x0000000000000080)
-#define CPU_FTR_601			ASM_CONST(0x0000000000000100)
-#define CPU_FTR_DBELL			ASM_CONST(0x0000000000000200)
-#define CPU_FTR_CAN_NAP			ASM_CONST(0x0000000000000400)
-#define CPU_FTR_L3CR			ASM_CONST(0x0000000000000800)
-#define CPU_FTR_L3_DISABLE_NAP		ASM_CONST(0x0000000000001000)
-#define CPU_FTR_NAP_DISABLE_L2_PR	ASM_CONST(0x0000000000002000)
-#define CPU_FTR_DUAL_PLL_750FX		ASM_CONST(0x0000000000004000)
-#define CPU_FTR_NO_DPM			ASM_CONST(0x0000000000008000)
-#define CPU_FTR_NEED_COHERENT		ASM_CONST(0x0000000000020000)
-#define CPU_FTR_NO_BTIC			ASM_CONST(0x0000000000040000)
-#define CPU_FTR_NODSISRALIGN		ASM_CONST(0x0000000000100000)
-#define CPU_FTR_PPC_LE			ASM_CONST(0x0000000000200000)
-#define CPU_FTR_REAL_LE			ASM_CONST(0x0000000000400000)
-#define CPU_FTR_FPU_UNAVAILABLE		ASM_CONST(0x0000000000800000)
-#define CPU_FTR_UNIFIED_ID_CACHE	ASM_CONST(0x0000000001000000)
-#define CPU_FTR_SPE			ASM_CONST(0x0000000002000000)
-#define CPU_FTR_NEED_PAIRED_STWCX	ASM_CONST(0x0000000004000000)
-#define CPU_FTR_LWSYNC			ASM_CONST(0x0000000008000000)
-#define CPU_FTR_NOEXECUTE		ASM_CONST(0x0000000010000000)
-#define CPU_FTR_INDEXED_DCR		ASM_CONST(0x0000000020000000)
+#define CPU_FTR_COHERENT_ICACHE		ASM_CONST(0x00000001)
+#define CPU_FTR_L2CR			ASM_CONST(0x00000002)
+#define CPU_FTR_SPEC7450		ASM_CONST(0x00000004)
+#define CPU_FTR_ALTIVEC			ASM_CONST(0x00000008)
+#define CPU_FTR_TAU			ASM_CONST(0x00000010)
+#define CPU_FTR_CAN_DOZE		ASM_CONST(0x00000020)
+#define CPU_FTR_USE_TB			ASM_CONST(0x00000040)
+#define CPU_FTR_L2CSR			ASM_CONST(0x00000080)
+#define CPU_FTR_601			ASM_CONST(0x00000100)
+#define CPU_FTR_DBELL			ASM_CONST(0x00000200)
+#define CPU_FTR_CAN_NAP			ASM_CONST(0x00000400)
+#define CPU_FTR_L3CR			ASM_CONST(0x00000800)
+#define CPU_FTR_L3_DISABLE_NAP		ASM_CONST(0x00001000)
+#define CPU_FTR_NAP_DISABLE_L2_PR	ASM_CONST(0x00002000)
+#define CPU_FTR_DUAL_PLL_750FX		ASM_CONST(0x00004000)
+#define CPU_FTR_NO_DPM			ASM_CONST(0x00008000)
+#define CPU_FTR_476_DD2			ASM_CONST(0x00010000)
+#define CPU_FTR_NEED_COHERENT		ASM_CONST(0x00020000)
+#define CPU_FTR_NO_BTIC			ASM_CONST(0x00040000)
+#define CPU_FTR_DEBUG_LVL_EXC		ASM_CONST(0x00080000)
+#define CPU_FTR_NODSISRALIGN		ASM_CONST(0x00100000)
+#define CPU_FTR_PPC_LE			ASM_CONST(0x00200000)
+#define CPU_FTR_REAL_LE			ASM_CONST(0x00400000)
+#define CPU_FTR_FPU_UNAVAILABLE		ASM_CONST(0x00800000)
+#define CPU_FTR_UNIFIED_ID_CACHE	ASM_CONST(0x01000000)
+#define CPU_FTR_SPE			ASM_CONST(0x02000000)
+#define CPU_FTR_NEED_PAIRED_STWCX	ASM_CONST(0x04000000)
+#define CPU_FTR_LWSYNC			ASM_CONST(0x08000000)
+#define CPU_FTR_NOEXECUTE		ASM_CONST(0x10000000)
+#define CPU_FTR_INDEXED_DCR		ASM_CONST(0x20000000)
+#define CPU_FTR_EMB_HV			ASM_CONST(0x40000000)
 
 /*
  * Add the 64-bit processor unique features in the top half of the word;
@@ -177,34 +161,42 @@ extern const char *powerpc_base_platform;
 #define LONG_ASM_CONST(x)		0
 #endif
 
-#define CPU_FTR_SLB			LONG_ASM_CONST(0x0000000100000000)
-#define CPU_FTR_16M_PAGE		LONG_ASM_CONST(0x0000000200000000)
-#define CPU_FTR_TLBIEL			LONG_ASM_CONST(0x0000000400000000)
-#define CPU_FTR_IABR			LONG_ASM_CONST(0x0000002000000000)
-#define CPU_FTR_MMCRA			LONG_ASM_CONST(0x0000004000000000)
-#define CPU_FTR_CTRL			LONG_ASM_CONST(0x0000008000000000)
-#define CPU_FTR_SMT			LONG_ASM_CONST(0x0000010000000000)
-#define CPU_FTR_LOCKLESS_TLBIE		LONG_ASM_CONST(0x0000040000000000)
-#define CPU_FTR_CI_LARGE_PAGE		LONG_ASM_CONST(0x0000100000000000)
-#define CPU_FTR_PAUSE_ZERO		LONG_ASM_CONST(0x0000200000000000)
-#define CPU_FTR_PURR			LONG_ASM_CONST(0x0000400000000000)
-#define CPU_FTR_CELL_TB_BUG		LONG_ASM_CONST(0x0000800000000000)
-#define CPU_FTR_SPURR			LONG_ASM_CONST(0x0001000000000000)
-#define CPU_FTR_DSCR			LONG_ASM_CONST(0x0002000000000000)
-#define CPU_FTR_1T_SEGMENT		LONG_ASM_CONST(0x0004000000000000)
-#define CPU_FTR_NO_SLBIE_B		LONG_ASM_CONST(0x0008000000000000)
-#define CPU_FTR_VSX			LONG_ASM_CONST(0x0010000000000000)
-#define CPU_FTR_SAO			LONG_ASM_CONST(0x0020000000000000)
-#define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0040000000000000)
-#define CPU_FTR_UNALIGNED_LD_STD	LONG_ASM_CONST(0x0080000000000000)
-#define CPU_FTR_ASYM_SMT		LONG_ASM_CONST(0x0100000000000000)
-#define CPU_FTR_STCX_CHECKS_ADDRESS	LONG_ASM_CONST(0x0200000000000000)
+#define CPU_FTR_HVMODE			LONG_ASM_CONST(0x0000000100000000)
+#define CPU_FTR_ARCH_201		LONG_ASM_CONST(0x0000000200000000)
+#define CPU_FTR_ARCH_206		LONG_ASM_CONST(0x0000000400000000)
+#define CPU_FTR_ARCH_207S		LONG_ASM_CONST(0x0000000800000000)
+#define CPU_FTR_IABR			LONG_ASM_CONST(0x0000001000000000)
+#define CPU_FTR_MMCRA			LONG_ASM_CONST(0x0000002000000000)
+#define CPU_FTR_CTRL			LONG_ASM_CONST(0x0000004000000000)
+#define CPU_FTR_SMT			LONG_ASM_CONST(0x0000008000000000)
+#define CPU_FTR_PAUSE_ZERO		LONG_ASM_CONST(0x0000010000000000)
+#define CPU_FTR_PURR			LONG_ASM_CONST(0x0000020000000000)
+#define CPU_FTR_CELL_TB_BUG		LONG_ASM_CONST(0x0000040000000000)
+#define CPU_FTR_SPURR			LONG_ASM_CONST(0x0000080000000000)
+#define CPU_FTR_DSCR			LONG_ASM_CONST(0x0000100000000000)
+#define CPU_FTR_VSX			LONG_ASM_CONST(0x0000200000000000)
+#define CPU_FTR_SAO			LONG_ASM_CONST(0x0000400000000000)
+#define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0000800000000000)
+#define CPU_FTR_UNALIGNED_LD_STD	LONG_ASM_CONST(0x0001000000000000)
+#define CPU_FTR_ASYM_SMT		LONG_ASM_CONST(0x0002000000000000)
+#define CPU_FTR_STCX_CHECKS_ADDRESS	LONG_ASM_CONST(0x0004000000000000)
+#define CPU_FTR_POPCNTB			LONG_ASM_CONST(0x0008000000000000)
+#define CPU_FTR_POPCNTD			LONG_ASM_CONST(0x0010000000000000)
+#define CPU_FTR_ICSWX			LONG_ASM_CONST(0x0020000000000000)
+#define CPU_FTR_VMX_COPY		LONG_ASM_CONST(0x0040000000000000)
+#define CPU_FTR_TM			LONG_ASM_CONST(0x0080000000000000)
+#define CPU_FTR_CFAR			LONG_ASM_CONST(0x0100000000000000)
+#define	CPU_FTR_HAS_PPR			LONG_ASM_CONST(0x0200000000000000)
+#define CPU_FTR_DAWR			LONG_ASM_CONST(0x0400000000000000)
+#define CPU_FTR_DABRX			LONG_ASM_CONST(0x0800000000000000)
+#define CPU_FTR_PMAO_BUG		LONG_ASM_CONST(0x1000000000000000)
 
 #ifndef __ASSEMBLY__
 
-#define CPU_FTR_PPCAS_ARCH_V2	(CPU_FTR_SLB | \
-				 CPU_FTR_TLBIEL | CPU_FTR_NOEXECUTE | \
-				 CPU_FTR_NODSISRALIGN | CPU_FTR_16M_PAGE)
+#define CPU_FTR_PPCAS_ARCH_V2	(CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN)
+
+#define MMU_FTR_PPCAS_ARCH_V2 	(MMU_FTR_SLB | MMU_FTR_TLBIEL | \
+				 MMU_FTR_16M_PAGE)
 
 /* We only set the altivec features if the kernel was compiled with altivec
  * support
@@ -243,6 +235,15 @@ extern const char *powerpc_base_platform;
 #define PPC_FEATURE_HAS_EFP_DOUBLE_COMP 0
 #endif
 
+/* We only set the TM feature if the kernel was compiled with TM supprt */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+#define CPU_FTR_TM_COMP		CPU_FTR_TM
+#define PPC_FEATURE2_HTM_COMP	PPC_FEATURE2_HTM
+#else
+#define CPU_FTR_TM_COMP		0
+#define PPC_FEATURE2_HTM_COMP	0
+#endif
+
 /* We need to mark all pages as being coherent if we're SMP or we have a
  * 74[45]x and an MPC107 host bridge. Also 83xx and PowerQUICC II
  * require it for PCI "streaming/prefetch" to work properly.
@@ -372,17 +373,30 @@ extern const char *powerpc_base_platform;
 #define CPU_FTRS_47X	(CPU_FTRS_440x6)
 #define CPU_FTRS_E200	(CPU_FTR_USE_TB | CPU_FTR_SPE_COMP | \
 	    CPU_FTR_NODSISRALIGN | CPU_FTR_COHERENT_ICACHE | \
-	    CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_NOEXECUTE)
+	    CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_NOEXECUTE | \
+	    CPU_FTR_DEBUG_LVL_EXC)
 #define CPU_FTRS_E500	(CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
 	    CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \
 	    CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_E500_2	(CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
 	    CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | \
 	    CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
-#define CPU_FTRS_E500MC	(CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
-	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \
+#define CPU_FTRS_E500MC	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
+	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
+	    CPU_FTR_DBELL | CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV)
+/*
+ * e5500/e6500 erratum A-006958 is a timebase bug that can use the
+ * same workaround as CPU_FTR_CELL_TB_BUG.
+ */
+#define CPU_FTRS_E5500	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
+	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
+	    CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_CELL_TB_BUG)
+#define CPU_FTRS_E6500	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
 	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
-	    CPU_FTR_DBELL)
+	    CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_CELL_TB_BUG)
 #define CPU_FTRS_GENERIC_32	(CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN)
 
 /* 64-bit CPUs */
@@ -396,46 +410,68 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_MMCRA | CPU_FTR_CP_USE_DCBTZ | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS)
 #define CPU_FTRS_PPC970	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_201 | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_CAN_NAP | CPU_FTR_MMCRA | \
-	    CPU_FTR_CP_USE_DCBTZ | CPU_FTR_STCX_CHECKS_ADDRESS)
+	    CPU_FTR_CP_USE_DCBTZ | CPU_FTR_STCX_CHECKS_ADDRESS | \
+	    CPU_FTR_HVMODE | CPU_FTR_DABRX)
 #define CPU_FTRS_POWER5	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
-	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
-	    CPU_FTR_PURR | CPU_FTR_STCX_CHECKS_ADDRESS)
+	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_PURR | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_DABRX)
 #define CPU_FTRS_POWER6 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
-	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
+	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
 	    CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD | \
-	    CPU_FTR_STCX_CHECKS_ADDRESS)
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_CFAR | \
+	    CPU_FTR_DABRX)
 #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
-	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
+	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
 	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT | \
-	    CPU_FTR_STCX_CHECKS_ADDRESS)
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | \
+	    CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX)
+#define CPU_FTRS_POWER8 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
+	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
+	    CPU_FTR_COHERENT_ICACHE | \
+	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
+	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
+	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP)
+#define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG)
+#define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL)
 #define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
-	    CPU_FTR_PAUSE_ZERO | CPU_FTR_CI_LARGE_PAGE | \
-	    CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \
-	    CPU_FTR_UNALIGNED_LD_STD)
+	    CPU_FTR_PAUSE_ZERO  | CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \
+	    CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_DABRX)
 #define CPU_FTRS_PA6T (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-	    CPU_FTR_PPCAS_ARCH_V2 | \
-	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_CI_LARGE_PAGE | \
-	    CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_NO_SLBIE_B)
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_DABRX)
 #define CPU_FTRS_COMPATIBLE	(CPU_FTR_USE_TB | CPU_FTR_PPCAS_ARCH_V2)
 
+#define CPU_FTRS_A2 (CPU_FTR_USE_TB | CPU_FTR_SMT | CPU_FTR_DBELL | \
+		     CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN | \
+		     CPU_FTR_ICSWX | CPU_FTR_DABRX )
+
 #ifdef __powerpc64__
+#ifdef CONFIG_PPC_BOOK3E
+#define CPU_FTRS_POSSIBLE	(CPU_FTRS_E6500 | CPU_FTRS_E5500 | CPU_FTRS_A2)
+#else
 #define CPU_FTRS_POSSIBLE	\
 	    (CPU_FTRS_POWER3 | CPU_FTRS_RS64 | CPU_FTRS_POWER4 |	\
 	    CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | CPU_FTRS_POWER6 |	\
-	    CPU_FTRS_POWER7 | CPU_FTRS_CELL | CPU_FTRS_PA6T |		\
-	    CPU_FTR_1T_SEGMENT | CPU_FTR_VSX)
+	    CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | CPU_FTRS_POWER8 |	\
+	    CPU_FTRS_CELL | CPU_FTRS_PA6T | CPU_FTR_VSX)
+#endif
 #else
 enum {
 	CPU_FTRS_POSSIBLE =
@@ -462,23 +498,30 @@ enum {
 	    CPU_FTRS_44X | CPU_FTRS_440x6 |
 #endif
 #ifdef CONFIG_PPC_47x
-	    CPU_FTRS_47X |
+	    CPU_FTRS_47X | CPU_FTR_476_DD2 |
 #endif
 #ifdef CONFIG_E200
 	    CPU_FTRS_E200 |
 #endif
 #ifdef CONFIG_E500
-	    CPU_FTRS_E500 | CPU_FTRS_E500_2 | CPU_FTRS_E500MC |
+	    CPU_FTRS_E500 | CPU_FTRS_E500_2 |
+#endif
+#ifdef CONFIG_PPC_E500MC
+	    CPU_FTRS_E500MC | CPU_FTRS_E5500 | CPU_FTRS_E6500 |
 #endif
 	    0,
 };
 #endif /* __powerpc64__ */
 
 #ifdef __powerpc64__
+#ifdef CONFIG_PPC_BOOK3E
+#define CPU_FTRS_ALWAYS		(CPU_FTRS_E6500 & CPU_FTRS_E5500 & CPU_FTRS_A2)
+#else
 #define CPU_FTRS_ALWAYS		\
 	    (CPU_FTRS_POWER3 & CPU_FTRS_RS64 & CPU_FTRS_POWER4 &	\
 	    CPU_FTRS_PPC970 & CPU_FTRS_POWER5 & CPU_FTRS_POWER6 &	\
 	    CPU_FTRS_POWER7 & CPU_FTRS_CELL & CPU_FTRS_PA6T & CPU_FTRS_POSSIBLE)
+#endif
 #else
 enum {
 	CPU_FTRS_ALWAYS =
@@ -508,8 +551,12 @@ enum {
 	    CPU_FTRS_E200 &
 #endif
 #ifdef CONFIG_E500
-	    CPU_FTRS_E500 & CPU_FTRS_E500_2 & CPU_FTRS_E500MC &
+	    CPU_FTRS_E500 & CPU_FTRS_E500_2 &
+#endif
+#ifdef CONFIG_PPC_E500MC
+	    CPU_FTRS_E500MC & CPU_FTRS_E5500 & CPU_FTRS_E6500 &
 #endif
+	    ~CPU_FTR_EMB_HV &	/* can be removed at runtime */
 	    CPU_FTRS_POSSIBLE,
 };
 #endif /* __powerpc64__ */
@@ -522,11 +569,8 @@ static inline int cpu_has_feature(unsigned long feature)
 		& feature);
 }
 
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
 #define HBP_NUM 1
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
 
 #endif /* !__ASSEMBLY__ */
 
-#endif /* __KERNEL__ */
 #endif /* __ASM_POWERPC_CPUTABLE_H */
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index a8e18447c62..2bf8e9307be 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -9,7 +9,7 @@
  * 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).
+ * as the CPU numbers are still allocated, just not brought online).
  *
  * 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
@@ -18,10 +18,12 @@
 
 #ifdef CONFIG_SMP
 extern int threads_per_core;
+extern int threads_per_subcore;
 extern int threads_shift;
 extern cpumask_t threads_core_mask;
 #else
 #define threads_per_core	1
+#define threads_per_subcore	1
 #define threads_shift		0
 #define threads_core_mask	(CPU_MASK_CPU0)
 #endif
@@ -37,16 +39,16 @@ extern cpumask_t threads_core_mask;
  * This can typically be used for things like IPI for tlb invalidations
  * since those need to be done only once per core/TLB
  */
-static inline cpumask_t cpu_thread_mask_to_cores(cpumask_t threads)
+static inline cpumask_t cpu_thread_mask_to_cores(const struct cpumask *threads)
 {
 	cpumask_t	tmp, res;
 	int		i;
 
-	res = CPU_MASK_NONE;
+	cpumask_clear(&res);
 	for (i = 0; i < NR_CPUS; i += threads_per_core) {
-		cpus_shift_left(tmp, threads_core_mask, i);
-		if (cpus_intersects(threads, tmp))
-			cpu_set(i, res);
+		cpumask_shift_left(&tmp, &threads_core_mask, i);
+		if (cpumask_intersects(threads, &tmp))
+			cpumask_set_cpu(i, &res);
 	}
 	return res;
 }
@@ -58,25 +60,33 @@ static inline int cpu_nr_cores(void)
 
 static inline cpumask_t cpu_online_cores_map(void)
 {
-	return cpu_thread_mask_to_cores(cpu_online_map);
+	return cpu_thread_mask_to_cores(cpu_online_mask);
 }
 
-static inline int cpu_thread_to_core(int cpu)
-{
-	return cpu >> threads_shift;
-}
+#ifdef CONFIG_SMP
+int cpu_core_index_of_thread(int cpu);
+int cpu_first_thread_of_core(int core);
+#else
+static inline int cpu_core_index_of_thread(int cpu) { return cpu; }
+static inline int cpu_first_thread_of_core(int core) { return core; }
+#endif
 
 static inline int cpu_thread_in_core(int cpu)
 {
 	return cpu & (threads_per_core - 1);
 }
 
-static inline int cpu_first_thread_in_core(int cpu)
+static inline int cpu_thread_in_subcore(int cpu)
+{
+	return cpu & (threads_per_subcore - 1);
+}
+
+static inline int cpu_first_thread_sibling(int cpu)
 {
 	return cpu & ~(threads_per_core - 1);
 }
 
-static inline int cpu_last_thread_in_core(int cpu)
+static inline int cpu_last_thread_sibling(int cpu)
 {
 	return cpu | (threads_per_core - 1);
 }
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index 1cf20bdfbec..607559ab271 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -8,7 +8,7 @@
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  *
- * If we have CONFIG_VIRT_CPU_ACCOUNTING, we measure cpu time in
+ * If we have CONFIG_VIRT_CPU_ACCOUNTING_NATIVE, we measure cpu time in
  * the same units as the timebase.  Otherwise we measure cpu time
  * in jiffies using the generic definitions.
  */
@@ -16,7 +16,7 @@
 #ifndef __POWERPC_CPUTIME_H
 #define __POWERPC_CPUTIME_H
 
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 #include <asm-generic/cputime.h>
 #ifdef __KERNEL__
 static inline void setup_cputime_one_jiffy(void) { }
@@ -29,25 +29,8 @@ static inline void setup_cputime_one_jiffy(void) { }
 #include <asm/time.h>
 #include <asm/param.h>
 
-typedef u64 cputime_t;
-typedef u64 cputime64_t;
-
-#define cputime_zero			((cputime_t)0)
-#define cputime_max			((~((cputime_t)0) >> 1) - 1)
-#define cputime_add(__a, __b)		((__a) +  (__b))
-#define cputime_sub(__a, __b)		((__a) -  (__b))
-#define cputime_div(__a, __n)		((__a) /  (__n))
-#define cputime_halve(__a)		((__a) >> 1)
-#define cputime_eq(__a, __b)		((__a) == (__b))
-#define cputime_gt(__a, __b)		((__a) >  (__b))
-#define cputime_ge(__a, __b)		((__a) >= (__b))
-#define cputime_lt(__a, __b)		((__a) <  (__b))
-#define cputime_le(__a, __b)		((__a) <= (__b))
-
-#define cputime64_zero			((cputime64_t)0)
-#define cputime64_add(__a, __b)		((__a) + (__b))
-#define cputime64_sub(__a, __b)		((__a) - (__b))
-#define cputime_to_cputime64(__ct)	(__ct)
+typedef u64 __nocast cputime_t;
+typedef u64 __nocast cputime64_t;
 
 #ifdef __KERNEL__
 
@@ -65,7 +48,7 @@ DECLARE_PER_CPU(unsigned long, cputime_scaled_last_delta);
 
 static inline unsigned long cputime_to_jiffies(const cputime_t ct)
 {
-	return mulhdu(ct, __cputime_jiffies_factor);
+	return mulhdu((__force u64) ct, __cputime_jiffies_factor);
 }
 
 /* Estimate the scaled cputime by scaling the real cputime based on
@@ -74,14 +57,15 @@ static inline cputime_t cputime_to_scaled(const cputime_t ct)
 {
 	if (cpu_has_feature(CPU_FTR_SPURR) &&
 	    __get_cpu_var(cputime_last_delta))
-		return ct * __get_cpu_var(cputime_scaled_last_delta) /
-			    __get_cpu_var(cputime_last_delta);
+		return (__force u64) ct *
+			__get_cpu_var(cputime_scaled_last_delta) /
+			__get_cpu_var(cputime_last_delta);
 	return ct;
 }
 
 static inline cputime_t jiffies_to_cputime(const unsigned long jif)
 {
-	cputime_t ct;
+	u64 ct;
 	unsigned long sec;
 
 	/* have to be a little careful about overflow */
@@ -93,7 +77,7 @@ static inline cputime_t jiffies_to_cputime(const unsigned long jif)
 	}
 	if (sec)
 		ct += (cputime_t) sec * tb_ticks_per_sec;
-	return ct;
+	return (__force cputime_t) ct;
 }
 
 static inline void setup_cputime_one_jiffy(void)
@@ -103,7 +87,7 @@ static inline void setup_cputime_one_jiffy(void)
 
 static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
 {
-	cputime_t ct;
+	u64 ct;
 	u64 sec;
 
 	/* have to be a little careful about overflow */
@@ -114,28 +98,28 @@ static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
 		do_div(ct, HZ);
 	}
 	if (sec)
-		ct += (cputime_t) sec * tb_ticks_per_sec;
-	return ct;
+		ct += (u64) sec * tb_ticks_per_sec;
+	return (__force cputime64_t) ct;
 }
 
 static inline u64 cputime64_to_jiffies64(const cputime_t ct)
 {
-	return mulhdu(ct, __cputime_jiffies_factor);
+	return mulhdu((__force u64) ct, __cputime_jiffies_factor);
 }
 
 /*
  * Convert cputime <-> microseconds
  */
-extern u64 __cputime_msec_factor;
+extern u64 __cputime_usec_factor;
 
 static inline unsigned long cputime_to_usecs(const cputime_t ct)
 {
-	return mulhdu(ct, __cputime_msec_factor) * USEC_PER_MSEC;
+	return mulhdu((__force u64) ct, __cputime_usec_factor);
 }
 
 static inline cputime_t usecs_to_cputime(const unsigned long us)
 {
-	cputime_t ct;
+	u64 ct;
 	unsigned long sec;
 
 	/* have to be a little careful about overflow */
@@ -143,13 +127,15 @@ static inline cputime_t usecs_to_cputime(const unsigned long us)
 	sec = us / 1000000;
 	if (ct) {
 		ct *= tb_ticks_per_sec;
-		do_div(ct, 1000);
+		do_div(ct, 1000000);
 	}
 	if (sec)
 		ct += (cputime_t) sec * tb_ticks_per_sec;
-	return ct;
+	return (__force cputime_t) ct;
 }
 
+#define usecs_to_cputime64(us)		usecs_to_cputime(us)
+
 /*
  * Convert cputime <-> seconds
  */
@@ -157,12 +143,12 @@ extern u64 __cputime_sec_factor;
 
 static inline unsigned long cputime_to_secs(const cputime_t ct)
 {
-	return mulhdu(ct, __cputime_sec_factor);
+	return mulhdu((__force u64) ct, __cputime_sec_factor);
 }
 
 static inline cputime_t secs_to_cputime(const unsigned long sec)
 {
-	return (cputime_t) sec * tb_ticks_per_sec;
+	return (__force cputime_t)((u64) sec * tb_ticks_per_sec);
 }
 
 /*
@@ -170,7 +156,7 @@ static inline cputime_t secs_to_cputime(const unsigned long sec)
  */
 static inline void cputime_to_timespec(const cputime_t ct, struct timespec *p)
 {
-	u64 x = ct;
+	u64 x = (__force u64) ct;
 	unsigned int frac;
 
 	frac = do_div(x, tb_ticks_per_sec);
@@ -182,11 +168,11 @@ static inline void cputime_to_timespec(const cputime_t ct, struct timespec *p)
 
 static inline cputime_t timespec_to_cputime(const struct timespec *p)
 {
-	cputime_t ct;
+	u64 ct;
 
 	ct = (u64) p->tv_nsec * tb_ticks_per_sec;
 	do_div(ct, 1000000000);
-	return ct + (u64) p->tv_sec * tb_ticks_per_sec;
+	return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec);
 }
 
 /*
@@ -194,7 +180,7 @@ static inline cputime_t timespec_to_cputime(const struct timespec *p)
  */
 static inline void cputime_to_timeval(const cputime_t ct, struct timeval *p)
 {
-	u64 x = ct;
+	u64 x = (__force u64) ct;
 	unsigned int frac;
 
 	frac = do_div(x, tb_ticks_per_sec);
@@ -206,11 +192,11 @@ static inline void cputime_to_timeval(const cputime_t ct, struct timeval *p)
 
 static inline cputime_t timeval_to_cputime(const struct timeval *p)
 {
-	cputime_t ct;
+	u64 ct;
 
 	ct = (u64) p->tv_usec * tb_ticks_per_sec;
 	do_div(ct, 1000000);
-	return ct + (u64) p->tv_sec * tb_ticks_per_sec;
+	return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec);
 }
 
 /*
@@ -220,12 +206,12 @@ extern u64 __cputime_clockt_factor;
 
 static inline unsigned long cputime_to_clock_t(const cputime_t ct)
 {
-	return mulhdu(ct, __cputime_clockt_factor);
+	return mulhdu((__force u64) ct, __cputime_clockt_factor);
 }
 
 static inline cputime_t clock_t_to_cputime(const unsigned long clk)
 {
-	cputime_t ct;
+	u64 ct;
 	unsigned long sec;
 
 	/* have to be a little careful about overflow */
@@ -236,12 +222,14 @@ static inline cputime_t clock_t_to_cputime(const unsigned long clk)
 		do_div(ct, USER_HZ);
 	}
 	if (sec)
-		ct += (cputime_t) sec * tb_ticks_per_sec;
-	return ct;
+		ct += (u64) sec * tb_ticks_per_sec;
+	return (__force cputime_t) ct;
 }
 
 #define cputime64_to_clock_t(ct)	cputime_to_clock_t((cputime_t)(ct))
 
+static inline void arch_vtime_task_switch(struct task_struct *tsk) { }
+
 #endif /* __KERNEL__ */
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 #endif /* __POWERPC_CPUTIME_H */
diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h
index 0893ab9343a..5fa6b20eba1 100644
--- a/arch/powerpc/include/asm/dbell.h
+++ b/arch/powerpc/include/asm/dbell.h
@@ -1,5 +1,5 @@
 /*
- * Copyright 2009 Freescale Semicondutor, Inc.
+ * Copyright 2009 Freescale Semiconductor, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -18,18 +18,48 @@
 #include <asm/ppc-opcode.h>
 
 #define PPC_DBELL_MSG_BRDCAST	(0x04000000)
-#define PPC_DBELL_TYPE(x)	(((x) & 0xf) << 28)
+#define PPC_DBELL_TYPE(x)	(((x) & 0xf) << (63-36))
+#define PPC_DBELL_TYPE_MASK	PPC_DBELL_TYPE(0xf)
+#define PPC_DBELL_LPID(x)	((x) << (63 - 49))
+#define PPC_DBELL_PIR_MASK	0x3fff
 enum ppc_dbell {
 	PPC_DBELL = 0,		/* doorbell */
 	PPC_DBELL_CRIT = 1,	/* critical doorbell */
 	PPC_G_DBELL = 2,	/* guest doorbell */
 	PPC_G_DBELL_CRIT = 3,	/* guest critical doorbell */
 	PPC_G_DBELL_MC = 4,	/* guest mcheck doorbell */
+	PPC_DBELL_SERVER = 5,	/* doorbell on server */
 };
 
-extern void doorbell_message_pass(int target, int msg);
+#ifdef CONFIG_PPC_BOOK3S
+
+#define PPC_DBELL_MSGTYPE		PPC_DBELL_SERVER
+#define SPRN_DOORBELL_CPUTAG		SPRN_TIR
+#define PPC_DBELL_TAG_MASK		0x7f
+
+static inline void _ppc_msgsnd(u32 msg)
+{
+	if (cpu_has_feature(CPU_FTR_HVMODE))
+		__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+	else
+		__asm__ __volatile__ (PPC_MSGSNDP(%0) : : "r" (msg));
+}
+
+#else /* CONFIG_PPC_BOOK3S */
+
+#define PPC_DBELL_MSGTYPE		PPC_DBELL
+#define SPRN_DOORBELL_CPUTAG		SPRN_PIR
+#define PPC_DBELL_TAG_MASK		0x3fff
+
+static inline void _ppc_msgsnd(u32 msg)
+{
+	__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+}
+
+#endif /* CONFIG_PPC_BOOK3S */
+
+extern void doorbell_cause_ipi(int cpu, unsigned long data);
 extern void doorbell_exception(struct pt_regs *regs);
-extern void doorbell_check_self(void);
 extern void doorbell_setup_this_cpu(void);
 
 static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag)
@@ -37,7 +67,7 @@ static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag)
 	u32 msg = PPC_DBELL_TYPE(type) | (flags & PPC_DBELL_MSG_BRDCAST) |
 			(tag & 0x07ffffff);
 
-	__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+	_ppc_msgsnd(msg);
 }
 
 #endif /* _ASM_POWERPC_DBELL_H */
diff --git a/arch/powerpc/include/asm/dcr-mmio.h b/arch/powerpc/include/asm/dcr-mmio.h
index acd491dbd45..93a68b28e69 100644
--- a/arch/powerpc/include/asm/dcr-mmio.h
+++ b/arch/powerpc/include/asm/dcr-mmio.h
@@ -51,10 +51,6 @@ static inline void dcr_write_mmio(dcr_host_mmio_t host,
 	out_be32(host.token + ((host.base + dcr_n) * host.stride), value);
 }
 
-extern u64 of_translate_dcr_address(struct device_node *dev,
-				    unsigned int dcr_n,
-				    unsigned int *stride);
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_DCR_MMIO_H */
 
diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h
new file mode 100644
index 00000000000..a954e497504
--- /dev/null
+++ b/arch/powerpc/include/asm/debug.h
@@ -0,0 +1,60 @@
+/*
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ */
+#ifndef _ASM_POWERPC_DEBUG_H
+#define _ASM_POWERPC_DEBUG_H
+
+#include <asm/hw_breakpoint.h>
+
+struct pt_regs;
+
+extern struct dentry *powerpc_debugfs_root;
+
+#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
+
+extern int (*__debugger)(struct pt_regs *regs);
+extern int (*__debugger_ipi)(struct pt_regs *regs);
+extern int (*__debugger_bpt)(struct pt_regs *regs);
+extern int (*__debugger_sstep)(struct pt_regs *regs);
+extern int (*__debugger_iabr_match)(struct pt_regs *regs);
+extern int (*__debugger_break_match)(struct pt_regs *regs);
+extern int (*__debugger_fault_handler)(struct pt_regs *regs);
+
+#define DEBUGGER_BOILERPLATE(__NAME) \
+static inline int __NAME(struct pt_regs *regs) \
+{ \
+	if (unlikely(__ ## __NAME)) \
+		return __ ## __NAME(regs); \
+	return 0; \
+}
+
+DEBUGGER_BOILERPLATE(debugger)
+DEBUGGER_BOILERPLATE(debugger_ipi)
+DEBUGGER_BOILERPLATE(debugger_bpt)
+DEBUGGER_BOILERPLATE(debugger_sstep)
+DEBUGGER_BOILERPLATE(debugger_iabr_match)
+DEBUGGER_BOILERPLATE(debugger_break_match)
+DEBUGGER_BOILERPLATE(debugger_fault_handler)
+
+#else
+static inline int debugger(struct pt_regs *regs) { return 0; }
+static inline int debugger_ipi(struct pt_regs *regs) { return 0; }
+static inline int debugger_bpt(struct pt_regs *regs) { return 0; }
+static inline int debugger_sstep(struct pt_regs *regs) { return 0; }
+static inline int debugger_iabr_match(struct pt_regs *regs) { return 0; }
+static inline int debugger_break_match(struct pt_regs *regs) { return 0; }
+static inline int debugger_fault_handler(struct pt_regs *regs) { return 0; }
+#endif
+
+void set_breakpoint(struct arch_hw_breakpoint *brk);
+void __set_breakpoint(struct arch_hw_breakpoint *brk);
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+extern void do_send_trap(struct pt_regs *regs, unsigned long address,
+			 unsigned long error_code, int signal_code, int brkpt);
+#else
+
+extern void do_break(struct pt_regs *regs, unsigned long address,
+		     unsigned long error_code);
+#endif
+
+#endif /* _ASM_POWERPC_DEBUG_H */
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index a3954e4fcbe..38faeded7d5 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -9,6 +9,12 @@
 struct dma_map_ops;
 struct device_node;
 
+/*
+ * Arch extensions to struct device.
+ *
+ * When adding fields, consider macio_add_one_device in
+ * drivers/macintosh/macio_asic.c
+ */
 struct dev_archdata {
 	/* DMA operations on that device */
 	struct dma_map_ops	*dma_ops;
@@ -22,13 +28,24 @@ struct dev_archdata {
 		void		*iommu_table_base;
 	} dma_data;
 
+#ifdef CONFIG_IOMMU_API
+	void			*iommu_domain;
+#endif
 #ifdef CONFIG_SWIOTLB
 	dma_addr_t		max_direct_dma_addr;
 #endif
+#ifdef CONFIG_EEH
+	struct eeh_dev		*edev;
+#endif
+#ifdef CONFIG_FAIL_IOMMU
+	int fail_iommu;
+#endif
 };
 
 struct pdev_archdata {
 	u64 dma_mask;
 };
 
+#define ARCH_HAS_DMA_GET_REQUIRED_MASK
+
 #endif /* _ASM_POWERPC_DEVICE_H */
diff --git a/arch/powerpc/include/asm/disassemble.h b/arch/powerpc/include/asm/disassemble.h
index 9b198d1b3b2..6330a61b875 100644
--- a/arch/powerpc/include/asm/disassemble.h
+++ b/arch/powerpc/include/asm/disassemble.h
@@ -77,4 +77,42 @@ static inline unsigned int get_d(u32 inst)
 	return inst & 0xffff;
 }
 
+static inline unsigned int get_oc(u32 inst)
+{
+	return (inst >> 11) & 0x7fff;
+}
+
+#define IS_XFORM(inst)	(get_op(inst)  == 31)
+#define IS_DSFORM(inst)	(get_op(inst) >= 56)
+
+/*
+ * Create a DSISR value from the instruction
+ */
+static inline unsigned make_dsisr(unsigned instr)
+{
+	unsigned dsisr;
+
+
+	/* bits  6:15 --> 22:31 */
+	dsisr = (instr & 0x03ff0000) >> 16;
+
+	if (IS_XFORM(instr)) {
+		/* bits 29:30 --> 15:16 */
+		dsisr |= (instr & 0x00000006) << 14;
+		/* bit     25 -->    17 */
+		dsisr |= (instr & 0x00000040) << 8;
+		/* bits 21:24 --> 18:21 */
+		dsisr |= (instr & 0x00000780) << 3;
+	} else {
+		/* bit      5 -->    17 */
+		dsisr |= (instr & 0x04000000) >> 12;
+		/* bits  1: 4 --> 18:21 */
+		dsisr |= (instr & 0x78000000) >> 17;
+		/* bits 30:31 --> 12:13 */
+		if (IS_DSFORM(instr))
+			dsisr |= (instr & 0x00000003) << 18;
+	}
+
+	return dsisr;
+}
 #endif /* __ASM_PPC_DISASSEMBLE_H__ */
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 6d2416a8570..150866b2a3f 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -22,10 +22,15 @@
 
 /* Some dma direct funcs must be visible for use in other dma_ops */
 extern void *dma_direct_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag);
+				       dma_addr_t *dma_handle, gfp_t flag,
+				       struct dma_attrs *attrs);
 extern void dma_direct_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t dma_handle);
-
+				     void *vaddr, dma_addr_t dma_handle,
+				     struct dma_attrs *attrs);
+extern int dma_direct_mmap_coherent(struct device *dev,
+				    struct vm_area_struct *vma,
+				    void *cpu_addr, dma_addr_t handle,
+				    size_t size, struct dma_attrs *attrs);
 
 #ifdef CONFIG_NOT_COHERENT_CACHE
 /*
@@ -42,6 +47,7 @@ extern void __dma_free_coherent(size_t size, void *vaddr);
 extern void __dma_sync(void *vaddr, size_t size, int direction);
 extern void __dma_sync_page(struct page *page, unsigned long offset,
 				 size_t size, int direction);
+extern unsigned long __dma_get_coherent_pfn(unsigned long cpu_addr);
 
 #else /* ! CONFIG_NOT_COHERENT_CACHE */
 /*
@@ -128,24 +134,31 @@ static inline int dma_supported(struct device *dev, u64 mask)
 }
 
 extern int dma_set_mask(struct device *dev, u64 dma_mask);
+extern int __dma_set_mask(struct device *dev, u64 dma_mask);
+
+#define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
 
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag)
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t flag,
+				    struct dma_attrs *attrs)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 	void *cpu_addr;
 
 	BUG_ON(!dma_ops);
 
-	cpu_addr = dma_ops->alloc_coherent(dev, size, dma_handle, flag);
+	cpu_addr = dma_ops->alloc(dev, size, dma_handle, flag, attrs);
 
 	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
 
 	return cpu_addr;
 }
 
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle)
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *cpu_addr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
@@ -153,13 +166,14 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
 
 	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
 
-	dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
+	dma_ops->free(dev, size, cpu_addr, dma_handle, attrs);
 }
 
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
+	debug_dma_mapping_error(dev, dma_addr);
 	if (dma_ops->mapping_error)
 		return dma_ops->mapping_error(dev, dma_addr);
 
@@ -198,6 +212,8 @@ static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
 
+#define ARCH_HAS_DMA_MMAP_COHERENT
+
 static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		enum dma_data_direction direction)
 {
diff --git a/arch/powerpc/include/asm/dma.h b/arch/powerpc/include/asm/dma.h
index a7e06e25c70..a5c6d83b5f6 100644
--- a/arch/powerpc/include/asm/dma.h
+++ b/arch/powerpc/include/asm/dma.h
@@ -16,15 +16,10 @@
  *
  * None of this really applies for Power Macintoshes.  There is
  * basically just enough here to get kernel/dma.c to compile.
- *
- * There may be some comments or restrictions made here which are
- * not valid for the PReP platform.  Take what you read
- * with a grain of salt.
  */
 
 #include <asm/io.h>
 #include <linux/spinlock.h>
-#include <asm/system.h>
 
 #ifndef MAX_DMA_CHANNELS
 #define MAX_DMA_CHANNELS	8
@@ -34,8 +29,6 @@
 /* Doesn't really apply... */
 #define MAX_DMA_ADDRESS		(~0UL)
 
-#if !defined(CONFIG_PPC_ISERIES) || defined(CONFIG_PCI)
-
 #ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
 #define dma_outb	outb_p
 #else
@@ -60,7 +53,6 @@
  *  - page registers for 5-7 don't use data bit 0, represent 128K pages
  *  - page registers for 0-3 use bit 0, represent 64K pages
  *
- * On PReP, DMA transfers are limited to the lower 16MB of _physical_ memory.
  * On CHRP, the W83C553F (and VLSI Tollgate?) support full 32 bit addressing.
  * Note that addresses loaded into registers must be _physical_ addresses,
  * not logical addresses (which may differ if paging is active).
@@ -354,7 +346,5 @@ extern int isa_dma_bridge_buggy;
 #define isa_dma_bridge_buggy	(0)
 #endif
 
-#endif	/* !defined(CONFIG_PPC_ISERIES) || defined(CONFIG_PCI) */
-
 #endif /* __KERNEL__ */
 #endif	/* _ASM_POWERPC_DMA_H */
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 66ea9b8b95c..fab7743c264 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -1,6 +1,6 @@
 /*
- * eeh.h
  * Copyright (C) 2001  Dave Engebretsen & Todd Inglett IBM Corporation.
+ * Copyright 2001-2012 IBM Corporation.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -24,6 +24,7 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/string.h>
+#include <linux/time.h>
 
 struct pci_dev;
 struct pci_bus;
@@ -31,45 +32,246 @@ struct device_node;
 
 #ifdef CONFIG_EEH
 
-extern int eeh_subsystem_enabled;
+/* EEH subsystem flags */
+#define EEH_ENABLED		0x1	/* EEH enabled		*/
+#define EEH_FORCE_DISABLED	0x2	/* EEH disabled		*/
+#define EEH_PROBE_MODE_DEV	0x4	/* From PCI device	*/
+#define EEH_PROBE_MODE_DEVTREE	0x8	/* From device tree	*/
 
-/* Values for eeh_mode bits in device_node */
-#define EEH_MODE_SUPPORTED     (1<<0)
-#define EEH_MODE_NOCHECK       (1<<1)
-#define EEH_MODE_ISOLATED      (1<<2)
-#define EEH_MODE_RECOVERING    (1<<3)
-#define EEH_MODE_IRQ_DISABLED  (1<<4)
+/*
+ * Delay for PE reset, all in ms
+ *
+ * PCI specification has reset hold time of 100 milliseconds.
+ * We have 250 milliseconds here. The PCI bus settlement time
+ * is specified as 1.5 seconds and we have 1.8 seconds.
+ */
+#define EEH_PE_RST_HOLD_TIME		250
+#define EEH_PE_RST_SETTLE_TIME		1800
+
+/*
+ * The struct is used to trace PE related EEH functionality.
+ * In theory, there will have one instance of the struct to
+ * be created against particular PE. In nature, PEs corelate
+ * to each other. the struct has to reflect that hierarchy in
+ * order to easily pick up those affected PEs when one particular
+ * PE has EEH errors.
+ *
+ * Also, one particular PE might be composed of PCI device, PCI
+ * bus and its subordinate components. The struct also need ship
+ * the information. Further more, one particular PE is only meaingful
+ * in the corresponding PHB. Therefore, the root PEs should be created
+ * against existing PHBs in on-to-one fashion.
+ */
+#define EEH_PE_INVALID	(1 << 0)	/* Invalid   */
+#define EEH_PE_PHB	(1 << 1)	/* PHB PE    */
+#define EEH_PE_DEVICE 	(1 << 2)	/* Device PE */
+#define EEH_PE_BUS	(1 << 3)	/* Bus PE    */
+
+#define EEH_PE_ISOLATED		(1 << 0)	/* Isolated PE		*/
+#define EEH_PE_RECOVERING	(1 << 1)	/* Recovering PE	*/
+#define EEH_PE_RESET		(1 << 2)	/* PE reset in progress	*/
+
+#define EEH_PE_KEEP		(1 << 8)	/* Keep PE on hotplug	*/
+
+struct eeh_pe {
+	int type;			/* PE type: PHB/Bus/Device	*/
+	int state;			/* PE EEH dependent mode	*/
+	int config_addr;		/* Traditional PCI address	*/
+	int addr;			/* PE configuration address	*/
+	struct pci_controller *phb;	/* Associated PHB		*/
+	struct pci_bus *bus;		/* Top PCI bus for bus PE	*/
+	int check_count;		/* Times of ignored error	*/
+	int freeze_count;		/* Times of froze up		*/
+	struct timeval tstamp;		/* Time on first-time freeze	*/
+	int false_positives;		/* Times of reported #ff's	*/
+	struct eeh_pe *parent;		/* Parent PE			*/
+	struct list_head child_list;	/* Link PE to the child list	*/
+	struct list_head edevs;		/* Link list of EEH devices	*/
+	struct list_head child;		/* Child PEs			*/
+};
+
+#define eeh_pe_for_each_dev(pe, edev, tmp) \
+		list_for_each_entry_safe(edev, tmp, &pe->edevs, list)
+
+/*
+ * The struct is used to trace EEH state for the associated
+ * PCI device node or PCI device. In future, it might
+ * represent PE as well so that the EEH device to form
+ * another tree except the currently existing tree of PCI
+ * buses and PCI devices
+ */
+#define EEH_DEV_BRIDGE		(1 << 0)	/* PCI bridge		*/
+#define EEH_DEV_ROOT_PORT	(1 << 1)	/* PCIe root port	*/
+#define EEH_DEV_DS_PORT		(1 << 2)	/* Downstream port	*/
+#define EEH_DEV_IRQ_DISABLED	(1 << 3)	/* Interrupt disabled	*/
+#define EEH_DEV_DISCONNECTED	(1 << 4)	/* Removing from PE	*/
+
+#define EEH_DEV_NO_HANDLER	(1 << 8)	/* No error handler	*/
+#define EEH_DEV_SYSFS		(1 << 9)	/* Sysfs created	*/
+#define EEH_DEV_REMOVED		(1 << 10)	/* Removed permanently	*/
+
+struct eeh_dev {
+	int mode;			/* EEH mode			*/
+	int class_code;			/* Class code of the device	*/
+	int config_addr;		/* Config address		*/
+	int pe_config_addr;		/* PE config address		*/
+	u32 config_space[16];		/* Saved PCI config space	*/
+	int pcix_cap;			/* Saved PCIx capability	*/
+	int pcie_cap;			/* Saved PCIe capability	*/
+	int aer_cap;			/* Saved AER capability		*/
+	struct eeh_pe *pe;		/* Associated PE		*/
+	struct list_head list;		/* Form link list in the PE	*/
+	struct pci_controller *phb;	/* Associated PHB		*/
+	struct device_node *dn;		/* Associated device node	*/
+	struct pci_dev *pdev;		/* Associated PCI device	*/
+	struct pci_bus *bus;		/* PCI bus for partial hotplug	*/
+};
+
+static inline struct device_node *eeh_dev_to_of_node(struct eeh_dev *edev)
+{
+	return edev ? edev->dn : NULL;
+}
+
+static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev)
+{
+	return edev ? edev->pdev : NULL;
+}
+
+/* Return values from eeh_ops::next_error */
+enum {
+	EEH_NEXT_ERR_NONE = 0,
+	EEH_NEXT_ERR_INF,
+	EEH_NEXT_ERR_FROZEN_PE,
+	EEH_NEXT_ERR_FENCED_PHB,
+	EEH_NEXT_ERR_DEAD_PHB,
+	EEH_NEXT_ERR_DEAD_IOC
+};
+
+/*
+ * The struct is used to trace the registered EEH operation
+ * callback functions. Actually, those operation callback
+ * functions are heavily platform dependent. That means the
+ * platform should register its own EEH operation callback
+ * functions before any EEH further operations.
+ */
+#define EEH_OPT_DISABLE		0	/* EEH disable	*/
+#define EEH_OPT_ENABLE		1	/* EEH enable	*/
+#define EEH_OPT_THAW_MMIO	2	/* MMIO enable	*/
+#define EEH_OPT_THAW_DMA	3	/* DMA enable	*/
+#define EEH_STATE_UNAVAILABLE	(1 << 0)	/* State unavailable	*/
+#define EEH_STATE_NOT_SUPPORT	(1 << 1)	/* EEH not supported	*/
+#define EEH_STATE_RESET_ACTIVE	(1 << 2)	/* Active reset		*/
+#define EEH_STATE_MMIO_ACTIVE	(1 << 3)	/* Active MMIO		*/
+#define EEH_STATE_DMA_ACTIVE	(1 << 4)	/* Active DMA		*/
+#define EEH_STATE_MMIO_ENABLED	(1 << 5)	/* MMIO enabled		*/
+#define EEH_STATE_DMA_ENABLED	(1 << 6)	/* DMA enabled		*/
+#define EEH_RESET_DEACTIVATE	0	/* Deactivate the PE reset	*/
+#define EEH_RESET_HOT		1	/* Hot reset			*/
+#define EEH_RESET_FUNDAMENTAL	3	/* Fundamental reset		*/
+#define EEH_LOG_TEMP		1	/* EEH temporary error log	*/
+#define EEH_LOG_PERM		2	/* EEH permanent error log	*/
+
+struct eeh_ops {
+	char *name;
+	int (*init)(void);
+	int (*post_init)(void);
+	void* (*of_probe)(struct device_node *dn, void *flag);
+	int (*dev_probe)(struct pci_dev *dev, void *flag);
+	int (*set_option)(struct eeh_pe *pe, int option);
+	int (*get_pe_addr)(struct eeh_pe *pe);
+	int (*get_state)(struct eeh_pe *pe, int *state);
+	int (*reset)(struct eeh_pe *pe, int option);
+	int (*wait_state)(struct eeh_pe *pe, int max_wait);
+	int (*get_log)(struct eeh_pe *pe, int severity, char *drv_log, unsigned long len);
+	int (*configure_bridge)(struct eeh_pe *pe);
+	int (*read_config)(struct device_node *dn, int where, int size, u32 *val);
+	int (*write_config)(struct device_node *dn, int where, int size, u32 val);
+	int (*next_error)(struct eeh_pe **pe);
+	int (*restore_config)(struct device_node *dn);
+};
+
+extern int eeh_subsystem_flags;
+extern struct eeh_ops *eeh_ops;
+extern raw_spinlock_t confirm_error_lock;
+
+static inline bool eeh_enabled(void)
+{
+	if ((eeh_subsystem_flags & EEH_FORCE_DISABLED) ||
+	    !(eeh_subsystem_flags & EEH_ENABLED))
+		return false;
+
+	return true;
+}
+
+static inline void eeh_set_enable(bool mode)
+{
+	if (mode)
+		eeh_subsystem_flags |= EEH_ENABLED;
+	else
+		eeh_subsystem_flags &= ~EEH_ENABLED;
+}
+
+static inline void eeh_probe_mode_set(int flag)
+{
+	eeh_subsystem_flags |= flag;
+}
+
+static inline int eeh_probe_mode_devtree(void)
+{
+	return (eeh_subsystem_flags & EEH_PROBE_MODE_DEVTREE);
+}
+
+static inline int eeh_probe_mode_dev(void)
+{
+	return (eeh_subsystem_flags & EEH_PROBE_MODE_DEV);
+}
 
-/* Max number of EEH freezes allowed before we consider the device
- * to be permanently disabled. */
+static inline void eeh_serialize_lock(unsigned long *flags)
+{
+	raw_spin_lock_irqsave(&confirm_error_lock, *flags);
+}
+
+static inline void eeh_serialize_unlock(unsigned long flags)
+{
+	raw_spin_unlock_irqrestore(&confirm_error_lock, flags);
+}
+
+/*
+ * Max number of EEH freezes allowed before we consider the device
+ * to be permanently disabled.
+ */
 #define EEH_MAX_ALLOWED_FREEZES 5
 
-void __init eeh_init(void);
+typedef void *(*eeh_traverse_func)(void *data, void *flag);
+int eeh_phb_pe_create(struct pci_controller *phb);
+struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb);
+struct eeh_pe *eeh_pe_get(struct eeh_dev *edev);
+int eeh_add_to_parent_pe(struct eeh_dev *edev);
+int eeh_rmv_from_parent_pe(struct eeh_dev *edev);
+void eeh_pe_update_time_stamp(struct eeh_pe *pe);
+void *eeh_pe_traverse(struct eeh_pe *root,
+		eeh_traverse_func fn, void *flag);
+void *eeh_pe_dev_traverse(struct eeh_pe *root,
+		eeh_traverse_func fn, void *flag);
+void eeh_pe_restore_bars(struct eeh_pe *pe);
+const char *eeh_pe_loc_get(struct eeh_pe *pe);
+struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe);
+
+void *eeh_dev_init(struct device_node *dn, void *data);
+void eeh_dev_phb_init_dynamic(struct pci_controller *phb);
+int eeh_init(void);
+int __init eeh_ops_register(struct eeh_ops *ops);
+int __exit eeh_ops_unregister(const char *name);
 unsigned long eeh_check_failure(const volatile void __iomem *token,
 				unsigned long val);
-int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev);
-void __init pci_addr_cache_build(void);
-
-/**
- * eeh_add_device_early
- * eeh_add_device_late
- *
- * Perform eeh initialization for devices added after boot.
- * Call eeh_add_device_early before doing any i/o to the
- * device (including config space i/o).  Call eeh_add_device_late
- * to finish the eeh setup for this device.
- */
+int eeh_dev_check_failure(struct eeh_dev *edev);
+void eeh_addr_cache_build(void);
+void eeh_add_device_early(struct device_node *);
 void eeh_add_device_tree_early(struct device_node *);
+void eeh_add_device_late(struct pci_dev *);
 void eeh_add_device_tree_late(struct pci_bus *);
-
-/**
- * eeh_remove_device_recursive - undo EEH for device & children.
- * @dev: pci device to be removed
- *
- * As above, this removes the device; it also removes child
- * pci devices as well.
- */
-void eeh_remove_bus_device(struct pci_dev *);
+void eeh_add_sysfs_files(struct pci_bus *);
+void eeh_remove_device(struct pci_dev *);
 
 /**
  * EEH_POSSIBLE_ERROR() -- test for possible MMIO failure.
@@ -77,7 +279,7 @@ void eeh_remove_bus_device(struct pci_dev *);
  * If this macro yields TRUE, the caller relays to eeh_check_failure()
  * which does further tests out of line.
  */
-#define EEH_POSSIBLE_ERROR(val, type)	((val) == (type)~0 && eeh_subsystem_enabled)
+#define EEH_POSSIBLE_ERROR(val, type)	((val) == (type)~0 && eeh_enabled())
 
 /*
  * Reads from a device which has been isolated by EEH will return
@@ -87,25 +289,47 @@ void eeh_remove_bus_device(struct pci_dev *);
 #define EEH_IO_ERROR_VALUE(size)	(~0U >> ((4 - (size)) * 8))
 
 #else /* !CONFIG_EEH */
-static inline void eeh_init(void) { }
 
-static inline unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val)
+static inline bool eeh_enabled(void)
 {
-	return val;
+        return false;
 }
 
-static inline int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
+static inline void eeh_set_enable(bool mode) { }
+
+static inline int eeh_init(void)
 {
 	return 0;
 }
 
-static inline void pci_addr_cache_build(void) { }
+static inline void *eeh_dev_init(struct device_node *dn, void *data)
+{
+	return NULL;
+}
+
+static inline void eeh_dev_phb_init_dynamic(struct pci_controller *phb) { }
+
+static inline unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val)
+{
+	return val;
+}
+
+#define eeh_dev_check_failure(x) (0)
+
+static inline void eeh_addr_cache_build(void) { }
+
+static inline void eeh_add_device_early(struct device_node *dn) { }
 
 static inline void eeh_add_device_tree_early(struct device_node *dn) { }
 
+static inline void eeh_add_device_late(struct pci_dev *dev) { }
+
 static inline void eeh_add_device_tree_late(struct pci_bus *bus) { }
 
-static inline void eeh_remove_bus_device(struct pci_dev *dev) { }
+static inline void eeh_add_sysfs_files(struct pci_bus *bus) { }
+
+static inline void eeh_remove_device(struct pci_dev *dev) { }
+
 #define EEH_POSSIBLE_ERROR(val, type) (0)
 #define EEH_IO_ERROR_VALUE(size) (-1UL)
 #endif /* CONFIG_EEH */
diff --git a/arch/powerpc/include/asm/eeh_event.h b/arch/powerpc/include/asm/eeh_event.h
index cc3cb04539a..1e551a2d6f8 100644
--- a/arch/powerpc/include/asm/eeh_event.h
+++ b/arch/powerpc/include/asm/eeh_event.h
@@ -1,6 +1,4 @@
 /*
- *	eeh_event.h
- *
  * 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
@@ -22,32 +20,21 @@
 #define ASM_POWERPC_EEH_EVENT_H
 #ifdef __KERNEL__
 
-/** EEH event -- structure holding pci controller data that describes
- *  a change in the isolation status of a PCI slot.  A pointer
- *  to this struct is passed as the data pointer in a notify callback.
+/*
+ * structure holding pci controller data that describes a
+ * change in the isolation status of a PCI slot.  A pointer
+ * to this struct is passed as the data pointer in a notify
+ * callback.
  */
 struct eeh_event {
-	struct list_head     list;
-	struct device_node 	*dn;   /* struct device node */
-	struct pci_dev       *dev;  /* affected device */
+	struct list_head	list;	/* to form event queue	*/
+	struct eeh_pe		*pe;	/* EEH PE		*/
 };
 
-/**
- * eeh_send_failure_event - generate a PCI error event
- * @dev pci device
- *
- * This routine builds a PCI error event which will be delivered
- * to all listeners on the eeh_notifier_chain.
- *
- * This routine can be called within an interrupt context;
- * the actual event will be delivered in a normal context
- * (from a workqueue).
- */
-int eeh_send_failure_event (struct device_node *dn,
-                            struct pci_dev *dev);
-
-/* Main recovery function */
-struct pci_dn * handle_eeh_events (struct eeh_event *);
+int eeh_event_init(void);
+int eeh_send_failure_event(struct eeh_pe *pe);
+void eeh_remove_event(struct eeh_pe *pe, bool force);
+void eeh_handle_event(struct eeh_pe *pe);
 
 #endif /* __KERNEL__ */
 #endif /* ASM_POWERPC_EEH_EVENT_H */
diff --git a/arch/powerpc/include/asm/ehv_pic.h b/arch/powerpc/include/asm/ehv_pic.h
new file mode 100644
index 00000000000..dc7d48e3ea9
--- /dev/null
+++ b/arch/powerpc/include/asm/ehv_pic.h
@@ -0,0 +1,40 @@
+/*
+ * EHV_PIC private definitions and structure.
+ *
+ * Copyright 2008-2010 Freescale Semiconductor, Inc.
+ *
+ * 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 __EHV_PIC_H__
+#define __EHV_PIC_H__
+
+#include <linux/irq.h>
+
+#define NR_EHV_PIC_INTS 1024
+
+#define EHV_PIC_INFO(name) EHV_PIC_##name
+
+#define EHV_PIC_VECPRI_POLARITY_NEGATIVE 0
+#define EHV_PIC_VECPRI_POLARITY_POSITIVE 1
+#define EHV_PIC_VECPRI_SENSE_EDGE 0
+#define EHV_PIC_VECPRI_SENSE_LEVEL 0x2
+#define EHV_PIC_VECPRI_POLARITY_MASK 0x1
+#define EHV_PIC_VECPRI_SENSE_MASK 0x2
+
+struct ehv_pic {
+	/* The remapper for this EHV_PIC */
+	struct irq_domain	*irqhost;
+
+	/* The "linux" controller struct */
+	struct irq_chip	hc_irq;
+
+	/* core int flag */
+	int coreint_flag;
+};
+
+void ehv_pic_init(void);
+unsigned int ehv_pic_get_irq(void);
+
+#endif /* __EHV_PIC_H__ */
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h