diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 8b133af..7af23c4 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -38,7 +38,6 @@
 obj-$(CONFIG_TAU)		+= tau_6xx.o
 obj32-$(CONFIG_SOFTWARE_SUSPEND) += swsusp_32.o
 obj32-$(CONFIG_MODULES)		+= module_32.o
-obj-$(CONFIG_E500)		+= perfmon_fsl_booke.o
 
 ifeq ($(CONFIG_PPC_MERGE),y)
 
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index 995fcef..93f21aa 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -182,7 +182,7 @@
 	prop = get_property(np, "linux,bootx-linebytes", NULL);
 	if (prop == NULL)
 		prop = get_property(np, "linebytes", NULL);
-	if (prop)
+	if (prop && *prop != 0xffffffffu)
 		pitch = *prop;
 	if (pitch == 1)
 		pitch = 0x1000;
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index f88a2a6..ba6b725 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -47,6 +47,17 @@
 static int novmerge = 1;
 #endif
 
+static inline unsigned long iommu_num_pages(unsigned long vaddr,
+					    unsigned long slen)
+{
+	unsigned long npages;
+
+	npages = IOMMU_PAGE_ALIGN(vaddr + slen) - (vaddr & IOMMU_PAGE_MASK);
+	npages >>= IOMMU_PAGE_SHIFT;
+
+	return npages;
+}
+
 static int __init setup_iommu(char *str)
 {
 	if (!strcmp(str, "novmerge"))
@@ -178,10 +189,10 @@
 	}
 
 	entry += tbl->it_offset;	/* Offset into real TCE table */
-	ret = entry << PAGE_SHIFT;	/* Set the return dma address */
+	ret = entry << IOMMU_PAGE_SHIFT;	/* Set the return dma address */
 
 	/* Put the TCEs in the HW table */
-	ppc_md.tce_build(tbl, entry, npages, (unsigned long)page & PAGE_MASK,
+	ppc_md.tce_build(tbl, entry, npages, (unsigned long)page & IOMMU_PAGE_MASK,
 			 direction);
 
 
@@ -203,7 +214,7 @@
 	unsigned long entry, free_entry;
 	unsigned long i;
 
-	entry = dma_addr >> PAGE_SHIFT;
+	entry = dma_addr >> IOMMU_PAGE_SHIFT;
 	free_entry = entry - tbl->it_offset;
 
 	if (((free_entry + npages) > tbl->it_size) ||
@@ -270,7 +281,7 @@
 	/* Init first segment length for backout at failure */
 	outs->dma_length = 0;
 
-	DBG("mapping %d elements:\n", nelems);
+	DBG("sg mapping %d elements:\n", nelems);
 
 	spin_lock_irqsave(&(tbl->it_lock), flags);
 
@@ -285,9 +296,8 @@
 		}
 		/* Allocate iommu entries for that segment */
 		vaddr = (unsigned long)page_address(s->page) + s->offset;
-		npages = PAGE_ALIGN(vaddr + slen) - (vaddr & PAGE_MASK);
-		npages >>= PAGE_SHIFT;
-		entry = iommu_range_alloc(tbl, npages, &handle, mask >> PAGE_SHIFT, 0);
+		npages = iommu_num_pages(vaddr, slen);
+		entry = iommu_range_alloc(tbl, npages, &handle, mask >> IOMMU_PAGE_SHIFT, 0);
 
 		DBG("  - vaddr: %lx, size: %lx\n", vaddr, slen);
 
@@ -301,14 +311,14 @@
 
 		/* Convert entry to a dma_addr_t */
 		entry += tbl->it_offset;
-		dma_addr = entry << PAGE_SHIFT;
-		dma_addr |= s->offset;
+		dma_addr = entry << IOMMU_PAGE_SHIFT;
+		dma_addr |= (s->offset & ~IOMMU_PAGE_MASK);
 
-		DBG("  - %lx pages, entry: %lx, dma_addr: %lx\n",
+		DBG("  - %lu pages, entry: %lx, dma_addr: %lx\n",
 			    npages, entry, dma_addr);
 
 		/* Insert into HW table */
-		ppc_md.tce_build(tbl, entry, npages, vaddr & PAGE_MASK, direction);
+		ppc_md.tce_build(tbl, entry, npages, vaddr & IOMMU_PAGE_MASK, direction);
 
 		/* If we are in an open segment, try merging */
 		if (segstart != s) {
@@ -323,7 +333,7 @@
 				DBG("    can't merge, new segment.\n");
 			} else {
 				outs->dma_length += s->length;
-				DBG("    merged, new len: %lx\n", outs->dma_length);
+				DBG("    merged, new len: %ux\n", outs->dma_length);
 			}
 		}
 
@@ -367,9 +377,8 @@
 		if (s->dma_length != 0) {
 			unsigned long vaddr, npages;
 
-			vaddr = s->dma_address & PAGE_MASK;
-			npages = (PAGE_ALIGN(s->dma_address + s->dma_length) - vaddr)
-				>> PAGE_SHIFT;
+			vaddr = s->dma_address & IOMMU_PAGE_MASK;
+			npages = iommu_num_pages(s->dma_address, s->dma_length);
 			__iommu_free(tbl, vaddr, npages);
 			s->dma_address = DMA_ERROR_CODE;
 			s->dma_length = 0;
@@ -398,8 +407,7 @@
 
 		if (sglist->dma_length == 0)
 			break;
-		npages = (PAGE_ALIGN(dma_handle + sglist->dma_length)
-			  - (dma_handle & PAGE_MASK)) >> PAGE_SHIFT;
+		npages = iommu_num_pages(dma_handle,sglist->dma_length);
 		__iommu_free(tbl, dma_handle, npages);
 		sglist++;
 	}
@@ -532,12 +540,11 @@
 	BUG_ON(direction == DMA_NONE);
 
 	uaddr = (unsigned long)vaddr;
-	npages = PAGE_ALIGN(uaddr + size) - (uaddr & PAGE_MASK);
-	npages >>= PAGE_SHIFT;
+	npages = iommu_num_pages(uaddr, size);
 
 	if (tbl) {
 		dma_handle = iommu_alloc(tbl, vaddr, npages, direction,
-					 mask >> PAGE_SHIFT, 0);
+					 mask >> IOMMU_PAGE_SHIFT, 0);
 		if (dma_handle == DMA_ERROR_CODE) {
 			if (printk_ratelimit())  {
 				printk(KERN_INFO "iommu_alloc failed, "
@@ -545,7 +552,7 @@
 						tbl, vaddr, npages);
 			}
 		} else
-			dma_handle |= (uaddr & ~PAGE_MASK);
+			dma_handle |= (uaddr & ~IOMMU_PAGE_MASK);
 	}
 
 	return dma_handle;
@@ -554,11 +561,14 @@
 void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle,
 		size_t size, enum dma_data_direction direction)
 {
+	unsigned int npages;
+
 	BUG_ON(direction == DMA_NONE);
 
-	if (tbl)
-		iommu_free(tbl, dma_handle, (PAGE_ALIGN(dma_handle + size) -
-					(dma_handle & PAGE_MASK)) >> PAGE_SHIFT);
+	if (tbl) {
+		npages = iommu_num_pages(dma_handle, size);
+		iommu_free(tbl, dma_handle, npages);
+	}
 }
 
 /* Allocates a contiguous real buffer and creates mappings over it.
@@ -570,11 +580,11 @@
 {
 	void *ret = NULL;
 	dma_addr_t mapping;
-	unsigned int npages, order;
+	unsigned int order;
+	unsigned int nio_pages, io_order;
 	struct page *page;
 
 	size = PAGE_ALIGN(size);
-	npages = size >> PAGE_SHIFT;
 	order = get_order(size);
 
  	/*
@@ -598,8 +608,10 @@
 	memset(ret, 0, size);
 
 	/* Set up tces to cover the allocated range */
-	mapping = iommu_alloc(tbl, ret, npages, DMA_BIDIRECTIONAL,
-			      mask >> PAGE_SHIFT, order);
+	nio_pages = size >> IOMMU_PAGE_SHIFT;
+	io_order = get_iommu_order(size);
+	mapping = iommu_alloc(tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
+			      mask >> IOMMU_PAGE_SHIFT, io_order);
 	if (mapping == DMA_ERROR_CODE) {
 		free_pages((unsigned long)ret, order);
 		return NULL;
@@ -611,12 +623,13 @@
 void iommu_free_coherent(struct iommu_table *tbl, size_t size,
 			 void *vaddr, dma_addr_t dma_handle)
 {
-	unsigned int npages;
-
 	if (tbl) {
+		unsigned int nio_pages;
+
 		size = PAGE_ALIGN(size);
-		npages = size >> PAGE_SHIFT;
-		iommu_free(tbl, dma_handle, npages);
+		nio_pages = size >> IOMMU_PAGE_SHIFT;
+		iommu_free(tbl, dma_handle, nio_pages);
+		size = PAGE_ALIGN(size);
 		free_pages((unsigned long)vaddr, get_order(size));
 	}
 }
diff --git a/arch/powerpc/kernel/perfmon_fsl_booke.c b/arch/powerpc/kernel/perfmon_fsl_booke.c
deleted file mode 100644
index e0dcf2b..0000000
--- a/arch/powerpc/kernel/perfmon_fsl_booke.c
+++ /dev/null
@@ -1,221 +0,0 @@
-/* arch/powerpc/kernel/perfmon_fsl_booke.c
- * Freescale Book-E Performance Monitor code
- *
- * Author: Andy Fleming
- * Copyright (c) 2004 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
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- */
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
-#include <linux/ptrace.h>
-#include <linux/slab.h>
-#include <linux/user.h>
-#include <linux/a.out.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/prctl.h>
-
-#include <asm/pgtable.h>
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <asm/io.h>
-#include <asm/reg.h>
-#include <asm/xmon.h>
-#include <asm/pmc.h>
-
-static inline u32 get_pmlca(int ctr);
-static inline void set_pmlca(int ctr, u32 pmlca);
-
-static inline u32 get_pmlca(int ctr)
-{
-	u32 pmlca;
-
-	switch (ctr) {
-		case 0:
-			pmlca = mfpmr(PMRN_PMLCA0);
-			break;
-		case 1:
-			pmlca = mfpmr(PMRN_PMLCA1);
-			break;
-		case 2:
-			pmlca = mfpmr(PMRN_PMLCA2);
-			break;
-		case 3:
-			pmlca = mfpmr(PMRN_PMLCA3);
-			break;
-		default:
-			panic("Bad ctr number\n");
-	}
-
-	return pmlca;
-}
-
-static inline void set_pmlca(int ctr, u32 pmlca)
-{
-	switch (ctr) {
-		case 0:
-			mtpmr(PMRN_PMLCA0, pmlca);
-			break;
-		case 1:
-			mtpmr(PMRN_PMLCA1, pmlca);
-			break;
-		case 2:
-			mtpmr(PMRN_PMLCA2, pmlca);
-			break;
-		case 3:
-			mtpmr(PMRN_PMLCA3, pmlca);
-			break;
-		default:
-			panic("Bad ctr number\n");
-	}
-}
-
-void init_pmc_stop(int ctr)
-{
-	u32 pmlca = (PMLCA_FC | PMLCA_FCS | PMLCA_FCU |
-			PMLCA_FCM1 | PMLCA_FCM0);
-	u32 pmlcb = 0;
-
-	switch (ctr) {
-		case 0:
-			mtpmr(PMRN_PMLCA0, pmlca);
-			mtpmr(PMRN_PMLCB0, pmlcb);
-			break;
-		case 1:
-			mtpmr(PMRN_PMLCA1, pmlca);
-			mtpmr(PMRN_PMLCB1, pmlcb);
-			break;
-		case 2:
-			mtpmr(PMRN_PMLCA2, pmlca);
-			mtpmr(PMRN_PMLCB2, pmlcb);
-			break;
-		case 3:
-			mtpmr(PMRN_PMLCA3, pmlca);
-			mtpmr(PMRN_PMLCB3, pmlcb);
-			break;
-		default:
-			panic("Bad ctr number!\n");
-	}
-}
-
-void set_pmc_event(int ctr, int event)
-{
-	u32 pmlca;
-
-	pmlca = get_pmlca(ctr);
-
-	pmlca = (pmlca & ~PMLCA_EVENT_MASK) |
-		((event << PMLCA_EVENT_SHIFT) &
-		 PMLCA_EVENT_MASK);
-
-	set_pmlca(ctr, pmlca);
-}
-
-void set_pmc_user_kernel(int ctr, int user, int kernel)
-{
-	u32 pmlca;
-
-	pmlca = get_pmlca(ctr);
-
-	if(user)
-		pmlca &= ~PMLCA_FCU;
-	else
-		pmlca |= PMLCA_FCU;
-
-	if(kernel)
-		pmlca &= ~PMLCA_FCS;
-	else
-		pmlca |= PMLCA_FCS;
-
-	set_pmlca(ctr, pmlca);
-}
-
-void set_pmc_marked(int ctr, int mark0, int mark1)
-{
-	u32 pmlca = get_pmlca(ctr);
-
-	if(mark0)
-		pmlca &= ~PMLCA_FCM0;
-	else
-		pmlca |= PMLCA_FCM0;
-
-	if(mark1)
-		pmlca &= ~PMLCA_FCM1;
-	else
-		pmlca |= PMLCA_FCM1;
-
-	set_pmlca(ctr, pmlca);
-}
-
-void pmc_start_ctr(int ctr, int enable)
-{
-	u32 pmlca = get_pmlca(ctr);
-
-	pmlca &= ~PMLCA_FC;
-
-	if (enable)
-		pmlca |= PMLCA_CE;
-	else
-		pmlca &= ~PMLCA_CE;
-
-	set_pmlca(ctr, pmlca);
-}
-
-void pmc_start_ctrs(int enable)
-{
-	u32 pmgc0 = mfpmr(PMRN_PMGC0);
-
-	pmgc0 &= ~PMGC0_FAC;
-	pmgc0 |= PMGC0_FCECE;
-
-	if (enable)
-		pmgc0 |= PMGC0_PMIE;
-	else
-		pmgc0 &= ~PMGC0_PMIE;
-
-	mtpmr(PMRN_PMGC0, pmgc0);
-}
-
-void pmc_stop_ctrs(void)
-{
-	u32 pmgc0 = mfpmr(PMRN_PMGC0);
-
-	pmgc0 |= PMGC0_FAC;
-
-	pmgc0 &= ~(PMGC0_PMIE | PMGC0_FCECE);
-
-	mtpmr(PMRN_PMGC0, pmgc0);
-}
-
-void dump_pmcs(void)
-{
-	printk("pmgc0: %x\n", mfpmr(PMRN_PMGC0));
-	printk("pmc\t\tpmlca\t\tpmlcb\n");
-	printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC0),
-			mfpmr(PMRN_PMLCA0), mfpmr(PMRN_PMLCB0));
-	printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC1),
-			mfpmr(PMRN_PMLCA1), mfpmr(PMRN_PMLCB1));
-	printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC2),
-			mfpmr(PMRN_PMLCA2), mfpmr(PMRN_PMLCB2));
-	printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC3),
-			mfpmr(PMRN_PMLCA3), mfpmr(PMRN_PMLCB3));
-}
-
-EXPORT_SYMBOL(init_pmc_stop);
-EXPORT_SYMBOL(set_pmc_event);
-EXPORT_SYMBOL(set_pmc_user_kernel);
-EXPORT_SYMBOL(set_pmc_marked);
-EXPORT_SYMBOL(pmc_start_ctr);
-EXPORT_SYMBOL(pmc_start_ctrs);
-EXPORT_SYMBOL(pmc_stop_ctrs);
-EXPORT_SYMBOL(dump_pmcs);
diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c
index a0a2efa..3d8f6f4 100644
--- a/arch/powerpc/kernel/pmc.c
+++ b/arch/powerpc/kernel/pmc.c
@@ -71,7 +71,7 @@
 	}
 
 	pmc_owner_caller = __builtin_return_address(0);
-	perf_irq = new_perf_irq ? : dummy_perf;
+	perf_irq = new_perf_irq ? new_perf_irq : dummy_perf;
 
  out:
 	spin_unlock(&pmc_owner_lock);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 5ed4c2c..c66b477 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -843,7 +843,7 @@
 
 void alignment_exception(struct pt_regs *regs)
 {
-	int fixed = 0;
+	int sig, code, fixed = 0;
 
 	/* we don't implement logging of alignment exceptions */
 	if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS))
@@ -857,14 +857,16 @@
 
 	/* Operand address was bad */
 	if (fixed == -EFAULT) {
-		if (user_mode(regs))
-			_exception(SIGSEGV, regs, SEGV_ACCERR, regs->dar);
-		else
-			/* Search exception table */
-			bad_page_fault(regs, regs->dar, SIGSEGV);
-		return;
+		sig = SIGSEGV;
+		code = SEGV_ACCERR;
+	} else {
+		sig = SIGBUS;
+		code = BUS_ADRALN;
 	}
-	_exception(SIGBUS, regs, BUS_ADRALN, regs->dar);
+	if (user_mode(regs))
+		_exception(sig, regs, code, regs->dar);
+	else
+		bad_page_fault(regs, regs->dar, sig);
 }
 
 void StackOverflow(struct pt_regs *regs)
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index cb87e71..ed00787 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -92,9 +92,9 @@
 				&tbl->it_index, &offset, &size);
 
 		/* TCE table size - measured in tce entries */
-		tbl->it_size = size >> PAGE_SHIFT;
+		tbl->it_size = size >> IOMMU_PAGE_SHIFT;
 		/* offset for VIO should always be 0 */
-		tbl->it_offset = offset >> PAGE_SHIFT;
+		tbl->it_offset = offset >> IOMMU_PAGE_SHIFT;
 		tbl->it_busno = 0;
 		tbl->it_type = TCE_VB;
 
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 9590ba7..7e8ded0 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -9,6 +9,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
+#include <linux/kprobes.h>
 #include <linux/ptrace.h>
 #include <asm/sstep.h>
 #include <asm/processor.h>
@@ -25,7 +26,7 @@
 /*
  * Determine whether a conditional branch instruction would branch.
  */
-static int branch_taken(unsigned int instr, struct pt_regs *regs)
+static int __kprobes branch_taken(unsigned int instr, struct pt_regs *regs)
 {
 	unsigned int bo = (instr >> 21) & 0x1f;
 	unsigned int bi;
@@ -51,7 +52,7 @@
  * or -1 if the instruction is one that should not be stepped,
  * such as an rfid, or a mtmsrd that would clear MSR_RI.
  */
-int emulate_step(struct pt_regs *regs, unsigned int instr)
+int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 {
 	unsigned int opcode, rd;
 	unsigned long int imm;
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 5615acc..fd68b74 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -480,9 +480,6 @@
 
 	mm->context.high_htlb_areas |= newareas;
 
-	/* update the paca copy of the context struct */
-	get_paca()->context = mm->context;
-
 	/* the context change must make it to memory before the flush,
 	 * so that further SLB misses do the right thing. */
 	mb();
diff --git a/arch/powerpc/oprofile/Makefile b/arch/powerpc/oprofile/Makefile
index 3145d61..0b5df9c 100644
--- a/arch/powerpc/oprofile/Makefile
+++ b/arch/powerpc/oprofile/Makefile
@@ -13,4 +13,4 @@
 oprofile-y := $(DRIVER_OBJS) common.o backtrace.o
 oprofile-$(CONFIG_PPC64) += op_model_rs64.o op_model_power4.o
 oprofile-$(CONFIG_FSL_BOOKE) += op_model_fsl_booke.o
-oprofile-$(CONFIG_PPC32) += op_model_7450.o
+oprofile-$(CONFIG_6xx) += op_model_7450.o
diff --git a/arch/powerpc/oprofile/common.c b/arch/powerpc/oprofile/common.c
index fd0bbbe..63bbef3 100644
--- a/arch/powerpc/oprofile/common.c
+++ b/arch/powerpc/oprofile/common.c
@@ -34,6 +34,11 @@
 	model->handle_interrupt(regs, ctr);
 }
 
+static void op_powerpc_cpu_setup(void *dummy)
+{
+	model->cpu_setup(ctr);
+}
+
 static int op_powerpc_setup(void)
 {
 	int err;
@@ -47,7 +52,7 @@
 	model->reg_setup(ctr, &sys, model->num_counters);
 
 	/* Configure the registers on all cpus.  */
-	on_each_cpu(model->cpu_setup, NULL, 0, 1);
+	on_each_cpu(op_powerpc_cpu_setup, NULL, 0, 1);
 
 	return 0;
 }
@@ -142,7 +147,8 @@
 		case PPC_OPROFILE_POWER4:
 			model = &op_model_power4;
 			break;
-#else
+#endif
+#ifdef CONFIG_6xx
 		case PPC_OPROFILE_G4:
 			model = &op_model_7450;
 			break;
diff --git a/arch/powerpc/oprofile/op_model_7450.c b/arch/powerpc/oprofile/op_model_7450.c
index d8ee3ae..f481c0e 100644
--- a/arch/powerpc/oprofile/op_model_7450.c
+++ b/arch/powerpc/oprofile/op_model_7450.c
@@ -81,7 +81,7 @@
 
 /* Configures the counters on this CPU based on the global
  * settings */
-static void fsl7450_cpu_setup(void *unused)
+static void fsl7450_cpu_setup(struct op_counter_config *ctr)
 {
 	/* freeze all counters */
 	pmc_stop_ctrs();
diff --git a/arch/powerpc/oprofile/op_model_fsl_booke.c b/arch/powerpc/oprofile/op_model_fsl_booke.c
index e29dede..0b3c31f 100644
--- a/arch/powerpc/oprofile/op_model_fsl_booke.c
+++ b/arch/powerpc/oprofile/op_model_fsl_booke.c
@@ -32,42 +32,152 @@
 static int num_counters;
 static int oprofile_running;
 
-static inline unsigned int ctr_read(unsigned int i)
+static void init_pmc_stop(int ctr)
 {
-	switch(i) {
+	u32 pmlca = (PMLCA_FC | PMLCA_FCS | PMLCA_FCU |
+			PMLCA_FCM1 | PMLCA_FCM0);
+	u32 pmlcb = 0;
+
+	switch (ctr) {
 		case 0:
-			return mfpmr(PMRN_PMC0);
+			mtpmr(PMRN_PMLCA0, pmlca);
+			mtpmr(PMRN_PMLCB0, pmlcb);
+			break;
 		case 1:
-			return mfpmr(PMRN_PMC1);
+			mtpmr(PMRN_PMLCA1, pmlca);
+			mtpmr(PMRN_PMLCB1, pmlcb);
+			break;
 		case 2:
-			return mfpmr(PMRN_PMC2);
+			mtpmr(PMRN_PMLCA2, pmlca);
+			mtpmr(PMRN_PMLCB2, pmlcb);
+			break;
 		case 3:
-			return mfpmr(PMRN_PMC3);
+			mtpmr(PMRN_PMLCA3, pmlca);
+			mtpmr(PMRN_PMLCB3, pmlcb);
+			break;
 		default:
-			return 0;
+			panic("Bad ctr number!\n");
 	}
 }
 
-static inline void ctr_write(unsigned int i, unsigned int val)
+static void set_pmc_event(int ctr, int event)
 {
-	switch(i) {
-		case 0:
-			mtpmr(PMRN_PMC0, val);
-			break;
-		case 1:
-			mtpmr(PMRN_PMC1, val);
-			break;
-		case 2:
-			mtpmr(PMRN_PMC2, val);
-			break;
-		case 3:
-			mtpmr(PMRN_PMC3, val);
-			break;
-		default:
-			break;
-	}
+	u32 pmlca;
+
+	pmlca = get_pmlca(ctr);
+
+	pmlca = (pmlca & ~PMLCA_EVENT_MASK) |
+		((event << PMLCA_EVENT_SHIFT) &
+		 PMLCA_EVENT_MASK);
+
+	set_pmlca(ctr, pmlca);
 }
 
+static void set_pmc_user_kernel(int ctr, int user, int kernel)
+{
+	u32 pmlca;
+
+	pmlca = get_pmlca(ctr);
+
+	if(user)
+		pmlca &= ~PMLCA_FCU;
+	else
+		pmlca |= PMLCA_FCU;
+
+	if(kernel)
+		pmlca &= ~PMLCA_FCS;
+	else
+		pmlca |= PMLCA_FCS;
+
+	set_pmlca(ctr, pmlca);
+}
+
+static void set_pmc_marked(int ctr, int mark0, int mark1)
+{
+	u32 pmlca = get_pmlca(ctr);
+
+	if(mark0)
+		pmlca &= ~PMLCA_FCM0;
+	else
+		pmlca |= PMLCA_FCM0;
+
+	if(mark1)
+		pmlca &= ~PMLCA_FCM1;
+	else
+		pmlca |= PMLCA_FCM1;
+
+	set_pmlca(ctr, pmlca);
+}
+
+static void pmc_start_ctr(int ctr, int enable)
+{
+	u32 pmlca = get_pmlca(ctr);
+
+	pmlca &= ~PMLCA_FC;
+
+	if (enable)
+		pmlca |= PMLCA_CE;
+	else
+		pmlca &= ~PMLCA_CE;
+
+	set_pmlca(ctr, pmlca);
+}
+
+static void pmc_start_ctrs(int enable)
+{
+	u32 pmgc0 = mfpmr(PMRN_PMGC0);
+
+	pmgc0 &= ~PMGC0_FAC;
+	pmgc0 |= PMGC0_FCECE;
+
+	if (enable)
+		pmgc0 |= PMGC0_PMIE;
+	else
+		pmgc0 &= ~PMGC0_PMIE;
+
+	mtpmr(PMRN_PMGC0, pmgc0);
+}
+
+static void pmc_stop_ctrs(void)
+{
+	u32 pmgc0 = mfpmr(PMRN_PMGC0);
+
+	pmgc0 |= PMGC0_FAC;
+
+	pmgc0 &= ~(PMGC0_PMIE | PMGC0_FCECE);
+
+	mtpmr(PMRN_PMGC0, pmgc0);
+}
+
+static void dump_pmcs(void)
+{
+	printk("pmgc0: %x\n", mfpmr(PMRN_PMGC0));
+	printk("pmc\t\tpmlca\t\tpmlcb\n");
+	printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC0),
+			mfpmr(PMRN_PMLCA0), mfpmr(PMRN_PMLCB0));
+	printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC1),
+			mfpmr(PMRN_PMLCA1), mfpmr(PMRN_PMLCB1));
+	printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC2),
+			mfpmr(PMRN_PMLCA2), mfpmr(PMRN_PMLCB2));
+	printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC3),
+			mfpmr(PMRN_PMLCA3), mfpmr(PMRN_PMLCB3));
+}
+
+static void fsl_booke_cpu_setup(struct op_counter_config *ctr)
+{
+	int i;
+
+	/* freeze all counters */
+	pmc_stop_ctrs();
+
+	for (i = 0;i < num_counters;i++) {
+		init_pmc_stop(i);
+
+		set_pmc_event(i, ctr[i].event);
+
+		set_pmc_user_kernel(i, ctr[i].user, ctr[i].kernel);
+	}
+}
 
 static void fsl_booke_reg_setup(struct op_counter_config *ctr,
 			     struct op_system_config *sys,
@@ -77,23 +187,14 @@
 
 	num_counters = num_ctrs;
 
-	/* freeze all counters */
-	pmc_stop_ctrs();
-
 	/* Our counters count up, and "count" refers to
 	 * how much before the next interrupt, and we interrupt
 	 * on overflow.  So we calculate the starting value
 	 * which will give us "count" until overflow.
 	 * Then we set the events on the enabled counters */
-	for (i = 0; i < num_counters; ++i) {
+	for (i = 0; i < num_counters; ++i)
 		reset_value[i] = 0x80000000UL - ctr[i].count;
 
-		init_pmc_stop(i);
-
-		set_pmc_event(i, ctr[i].event);
-
-		set_pmc_user_kernel(i, ctr[i].user, ctr[i].kernel);
-	}
 }
 
 static void fsl_booke_start(struct op_counter_config *ctr)
@@ -105,8 +206,8 @@
 	for (i = 0; i < num_counters; ++i) {
 		if (ctr[i].enabled) {
 			ctr_write(i, reset_value[i]);
-			/* Set Each enabled counterd to only
-			 * count when the Mark bit is not set */
+			/* Set each enabled counter to only
+			 * count when the Mark bit is *not* set */
 			set_pmc_marked(i, 1, 0);
 			pmc_start_ctr(i, 1);
 		} else {
@@ -177,6 +278,7 @@
 
 struct op_powerpc_model op_model_fsl_booke = {
 	.reg_setup		= fsl_booke_reg_setup,
+	.cpu_setup		= fsl_booke_cpu_setup,
 	.start			= fsl_booke_start,
 	.stop			= fsl_booke_stop,
 	.handle_interrupt	= fsl_booke_handle_interrupt,
diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c
index 6a927ef..356709d 100644
--- a/arch/powerpc/oprofile/op_model_power4.c
+++ b/arch/powerpc/oprofile/op_model_power4.c
@@ -82,7 +82,7 @@
 	return 0;
 }
 
-static void power4_cpu_setup(void *unused)
+static void power4_cpu_setup(struct op_counter_config *ctr)
 {
 	unsigned int mmcr0 = mmcr0_val;
 	unsigned long mmcra = mmcra_val;
diff --git a/arch/powerpc/oprofile/op_model_rs64.c b/arch/powerpc/oprofile/op_model_rs64.c
index 042f8f4..19c5ee0 100644
--- a/arch/powerpc/oprofile/op_model_rs64.c
+++ b/arch/powerpc/oprofile/op_model_rs64.c
@@ -102,7 +102,7 @@
 	/* XXX setup user and kernel profiling */
 }
 
-static void rs64_cpu_setup(void *unused)
+static void rs64_cpu_setup(struct op_counter_config *ctr)
 {
 	unsigned int mmcr0;
 
diff --git a/arch/powerpc/platforms/iseries/iommu.c b/arch/powerpc/platforms/iseries/iommu.c
index f4cbbcf..218817d 100644
--- a/arch/powerpc/platforms/iseries/iommu.c
+++ b/arch/powerpc/platforms/iseries/iommu.c
@@ -43,9 +43,6 @@
 	u64 rc;
 	u64 tce, rpn;
 
-	index <<= TCE_PAGE_FACTOR;
-	npages <<= TCE_PAGE_FACTOR;
-
 	while (npages--) {
 		rpn = virt_to_abs(uaddr) >> TCE_SHIFT;
 		tce = (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
@@ -75,9 +72,6 @@
 {
 	u64 rc;
 
-	npages <<= TCE_PAGE_FACTOR;
-	index <<= TCE_PAGE_FACTOR;
-
 	while (npages--) {
 		rc = HvCallXm_setTce((u64)tbl->it_index, (u64)index, 0);
 		if (rc)
@@ -136,10 +130,9 @@
 		panic("PCI_DMA: parms->size is zero, parms is 0x%p", parms);
 
 	/* itc_size is in pages worth of table, it_size is in # of entries */
-	tbl->it_size = ((parms->itc_size * TCE_PAGE_SIZE) /
-			TCE_ENTRY_SIZE) >> TCE_PAGE_FACTOR;
+	tbl->it_size = (parms->itc_size * TCE_PAGE_SIZE) / TCE_ENTRY_SIZE;
 	tbl->it_busno = parms->itc_busno;
-	tbl->it_offset = parms->itc_offset >> TCE_PAGE_FACTOR;
+	tbl->it_offset = parms->itc_offset;
 	tbl->it_index = parms->itc_index;
 	tbl->it_blocksize = 1;
 	tbl->it_type = virtbus ? TCE_VB : TCE_PCI;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index d24ba54..556c279 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -57,9 +57,6 @@
 	u64 *tcep;
 	u64 rpn;
 
-	index <<= TCE_PAGE_FACTOR;
-	npages <<= TCE_PAGE_FACTOR;
-
 	proto_tce = TCE_PCI_READ; // Read allowed
 
 	if (direction != DMA_TO_DEVICE)
@@ -82,9 +79,6 @@
 {
 	u64 *tcep;
 
-	npages <<= TCE_PAGE_FACTOR;
-	index <<= TCE_PAGE_FACTOR;
-
 	tcep = ((u64 *)tbl->it_base) + index;
 
 	while (npages--)
@@ -95,7 +89,6 @@
 {
 	u64 *tcep;
 
-	index <<= TCE_PAGE_FACTOR;
 	tcep = ((u64 *)tbl->it_base) + index;
 
 	return *tcep;
@@ -109,9 +102,6 @@
 	u64 proto_tce, tce;
 	u64 rpn;
 
-	tcenum <<= TCE_PAGE_FACTOR;
-	npages <<= TCE_PAGE_FACTOR;
-
 	rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT;
 	proto_tce = TCE_PCI_READ;
 	if (direction != DMA_TO_DEVICE)
@@ -146,7 +136,7 @@
 	u64 rpn;
 	long l, limit;
 
-	if (TCE_PAGE_FACTOR == 0 && npages == 1)
+	if (npages == 1)
 		return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
 					   direction);
 
@@ -164,9 +154,6 @@
 		__get_cpu_var(tce_page) = tcep;
 	}
 
-	tcenum <<= TCE_PAGE_FACTOR;
-	npages <<= TCE_PAGE_FACTOR;
-
 	rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT;
 	proto_tce = TCE_PCI_READ;
 	if (direction != DMA_TO_DEVICE)
@@ -207,9 +194,6 @@
 {
 	u64 rc;
 
-	tcenum <<= TCE_PAGE_FACTOR;
-	npages <<= TCE_PAGE_FACTOR;
-
 	while (npages--) {
 		rc = plpar_tce_put((u64)tbl->it_index, (u64)tcenum << 12, 0);
 
@@ -229,9 +213,6 @@
 {
 	u64 rc;
 
-	tcenum <<= TCE_PAGE_FACTOR;
-	npages <<= TCE_PAGE_FACTOR;
-
 	rc = plpar_tce_stuff((u64)tbl->it_index, (u64)tcenum << 12, 0, npages);
 
 	if (rc && printk_ratelimit()) {
@@ -248,7 +229,6 @@
 	u64 rc;
 	unsigned long tce_ret;
 
-	tcenum <<= TCE_PAGE_FACTOR;
 	rc = plpar_tce_get((u64)tbl->it_index, (u64)tcenum << 12, &tce_ret);
 
 	if (rc && printk_ratelimit()) {
@@ -289,7 +269,7 @@
 	tbl->it_busno = phb->bus->number;
 
 	/* Units of tce entries */
-	tbl->it_offset = phb->dma_window_base_cur >> PAGE_SHIFT;
+	tbl->it_offset = phb->dma_window_base_cur >> IOMMU_PAGE_SHIFT;
 
 	/* Test if we are going over 2GB of DMA space */
 	if (phb->dma_window_base_cur + phb->dma_window_size > 0x80000000ul) {
@@ -300,7 +280,7 @@
 	phb->dma_window_base_cur += phb->dma_window_size;
 
 	/* Set the tce table size - measured in entries */
-	tbl->it_size = phb->dma_window_size >> PAGE_SHIFT;
+	tbl->it_size = phb->dma_window_size >> IOMMU_PAGE_SHIFT;
 
 	tbl->it_index = 0;
 	tbl->it_blocksize = 16;
@@ -325,8 +305,8 @@
 	tbl->it_base   = 0;
 	tbl->it_blocksize  = 16;
 	tbl->it_type = TCE_PCI;
-	tbl->it_offset = offset >> PAGE_SHIFT;
-	tbl->it_size = size >> PAGE_SHIFT;
+	tbl->it_offset = offset >> IOMMU_PAGE_SHIFT;
+	tbl->it_size = size >> IOMMU_PAGE_SHIFT;
 }
 
 static void iommu_bus_setup_pSeries(struct pci_bus *bus)
@@ -522,8 +502,6 @@
 	const void *dma_window = NULL;
 	struct pci_dn *pci;
 
-	DBG("iommu_dev_setup_pSeriesLP, dev %p (%s)\n", dev, pci_name(dev));
-
 	/* dev setup for LPAR is a little tricky, since the device tree might
 	 * contain the dma-window properties per-device and not neccesarily
 	 * for the bus. So we need to search upwards in the tree until we
@@ -532,6 +510,9 @@
 	 */
 	dn = pci_device_to_OF_node(dev);
 
+	DBG("iommu_dev_setup_pSeriesLP, dev %p (%s) %s\n",
+	     dev, pci_name(dev), dn->full_name);
+
 	for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->iommu_table;
 	     pdn = pdn->parent) {
 		dma_window = get_property(pdn, "ibm,dma-window", NULL);
diff --git a/arch/powerpc/sysdev/dart.h b/arch/powerpc/sysdev/dart.h
index 1c8817c..ff202ed 100644
--- a/arch/powerpc/sysdev/dart.h
+++ b/arch/powerpc/sysdev/dart.h
@@ -72,7 +72,6 @@
 
 #define DART_PAGE_SHIFT		12
 #define DART_PAGE_SIZE		(1 << DART_PAGE_SHIFT)
-#define DART_PAGE_FACTOR	(PAGE_SHIFT - DART_PAGE_SHIFT)
 
 
 #endif /* _POWERPC_SYSDEV_DART_H */
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 03b4477..572b784 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -156,9 +156,6 @@
 
 	DBG("dart: build at: %lx, %lx, addr: %x\n", index, npages, uaddr);
 
-	index <<= DART_PAGE_FACTOR;
-	npages <<= DART_PAGE_FACTOR;
-
 	dp = ((unsigned int*)tbl->it_base) + index;
 
 	/* On U3, all memory is contigous, so we can move this
@@ -199,9 +196,6 @@
 
 	DBG("dart: free at: %lx, %lx\n", index, npages);
 
-	index <<= DART_PAGE_FACTOR;
-	npages <<= DART_PAGE_FACTOR;
-
 	dp  = ((unsigned int *)tbl->it_base) + index;
 
 	while (npages--)
@@ -281,7 +275,7 @@
 	iommu_table_dart.it_busno = 0;
 	iommu_table_dart.it_offset = 0;
 	/* it_size is in number of entries */
-	iommu_table_dart.it_size = (dart_tablesize / sizeof(u32)) >> DART_PAGE_FACTOR;
+	iommu_table_dart.it_size = dart_tablesize / sizeof(u32);
 
 	/* Initialize the common IOMMU code */
 	iommu_table_dart.it_base = (unsigned long)dart_vbase;
diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c
index 2bae632..e422322 100644
--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@@ -122,8 +122,7 @@
 				mcn_shift = QE_CR_MCN_NORMAL_SHIFT;
 		}
 
-		out_be32(&qe_immr->cp.cecdr,
-			 immrbar_virt_to_phys((void *)cmd_input));
+		out_be32(&qe_immr->cp.cecdr, cmd_input);
 		out_be32(&qe_immr->cp.cecr,
 			 (cmd | QE_CR_FLG | ((u32) device << dev_shift) | (u32)
 			  mcn_protocol << mcn_shift));
diff --git a/arch/ppc/kernel/traps.c b/arch/ppc/kernel/traps.c
index aafc8e8..9661a91 100644
--- a/arch/ppc/kernel/traps.c
+++ b/arch/ppc/kernel/traps.c
@@ -708,7 +708,7 @@
 
 void alignment_exception(struct pt_regs *regs)
 {
-	int fixed;
+	int sig, code, fixed = 0;
 
 	fixed = fix_alignment(regs);
 	if (fixed == 1) {
@@ -717,14 +717,16 @@
 		return;
 	}
 	if (fixed == -EFAULT) {
-		/* fixed == -EFAULT means the operand address was bad */
-		if (user_mode(regs))
-			_exception(SIGSEGV, regs, SEGV_ACCERR, regs->dar);
-		else
-			bad_page_fault(regs, regs->dar, SIGSEGV);
-		return;
+		sig = SIGSEGV;
+		code = SEGV_ACCERR;
+	} else {
+		sig = SIGBUS;
+		code = BUS_ADRALN;
 	}
-	_exception(SIGBUS, regs, BUS_ADRALN, regs->dar);
+	if (user_mode(regs))
+		_exception(sig, regs, code, regs->dar);
+	else
+		bad_page_fault(regs, regs->dar, sig);
 }
 
 void StackOverflow(struct pt_regs *regs)
diff --git a/drivers/video/offb.c b/drivers/video/offb.c
index bad0e98..9a40bbe 100644
--- a/drivers/video/offb.c
+++ b/drivers/video/offb.c
@@ -157,7 +157,7 @@
 		out_le32(par->cmap_adr + 0xb4, (red << 16 | green << 8 | blue));
 		break;
 	case cmap_gxt2000:
-		out_le32((unsigned __iomem *) par->cmap_adr + regno,
+		out_le32(((unsigned __iomem *) par->cmap_adr) + regno,
 			 (red << 16 | green << 8 | blue));
 		break;
 	}
@@ -213,7 +213,7 @@
 				out_le32(par->cmap_adr + 0xb4, 0);
 				break;
 			case cmap_gxt2000:
-				out_le32((unsigned __iomem *) par->cmap_adr + i,
+				out_le32(((unsigned __iomem *) par->cmap_adr) + i,
 					 0);
 				break;
 			}
@@ -226,13 +226,23 @@
 static void __iomem *offb_map_reg(struct device_node *np, int index,
 				  unsigned long offset, unsigned long size)
 {
-	struct resource r;
+	const u32 *addrp;
+	u64 asize, taddr;
+	unsigned int flags;
 
-	if (of_address_to_resource(np, index, &r))
-		return 0;
-	if ((r.start + offset + size) > r.end)
-		return 0;
-	return ioremap(r.start + offset, size);
+	addrp = of_get_pci_address(np, index, &asize, &flags);
+	if (addrp == NULL)
+		addrp = of_get_address(np, index, &asize, &flags);
+	if (addrp == NULL)
+		return NULL;
+	if ((flags & (IORESOURCE_IO | IORESOURCE_MEM)) == 0)
+		return NULL;
+	if ((offset + size) > asize)
+		return NULL;
+	taddr = of_translate_address(np, addrp);
+	if (taddr == OF_BAD_ADDR)
+		return NULL;
+	return ioremap(taddr + offset, size);
 }
 
 static void __init offb_init_fb(const char *name, const char *full_name,
@@ -289,7 +299,6 @@
 
 	par->cmap_type = cmap_unknown;
 	if (depth == 8) {
-		/* Palette hacks disabled for now */
 		if (dp && !strncmp(name, "ATY,Rage128", 11)) {
 			par->cmap_adr = offb_map_reg(dp, 2, 0, 0x1fff);
 			if (par->cmap_adr)
@@ -313,7 +322,8 @@
 			    ioremap(base + 0x7ff000, 0x1000) + 0xcc0;
 			par->cmap_data = par->cmap_adr + 1;
 			par->cmap_type = cmap_m64;
-		} else if (dp && device_is_compatible(dp, "pci1014,b7")) {
+		} else if (dp && (device_is_compatible(dp, "pci1014,b7") ||
+				  device_is_compatible(dp, "pci1014,21c"))) {
 			par->cmap_adr = offb_map_reg(dp, 0, 0x6000, 0x1000);
 			if (par->cmap_adr)
 				par->cmap_type = cmap_gxt2000;
@@ -433,7 +443,7 @@
 	pp = get_property(dp, "linux,bootx-linebytes", &len);
 	if (pp == NULL)
 		pp = get_property(dp, "linebytes", &len);
-	if (pp && len == sizeof(u32))
+	if (pp && len == sizeof(u32) && (*pp != 0xffffffffu))
 		pitch = *pp;
 	else
 		pitch = width * ((depth + 7) / 8);
@@ -496,7 +506,7 @@
 		offb_init_fb(no_real_node ? "bootx" : dp->name,
 			     no_real_node ? "display" : dp->full_name,
 			     width, height, depth, pitch, address,
-			     no_real_node ? dp : NULL);
+			     no_real_node ? NULL : dp);
 	}
 }
 
diff --git a/include/asm-powerpc/current.h b/include/asm-powerpc/current.h
index 1938d6ab..b8708ae 100644
--- a/include/asm-powerpc/current.h
+++ b/include/asm-powerpc/current.h
@@ -14,7 +14,17 @@
 #ifdef __powerpc64__
 #include <asm/paca.h>
 
-#define current		(get_paca()->__current)
+static inline struct task_struct *get_current(void)
+{
+	struct task_struct *task;
+
+	__asm__ __volatile__("ld %0,%1(13)"
+	: "=r" (task)
+	: "i" (offsetof(struct paca_struct, __current)));
+
+	return task;
+}
+#define current	get_current()
 
 #else
 
diff --git a/include/asm-powerpc/io.h b/include/asm-powerpc/io.h
index 3baff8b..c2c5f14 100644
--- a/include/asm-powerpc/io.h
+++ b/include/asm-powerpc/io.h
@@ -163,8 +163,11 @@
 
 static inline void mmiowb(void)
 {
-	__asm__ __volatile__ ("sync" : : : "memory");
-	get_paca()->io_sync = 0;
+	unsigned long tmp;
+
+	__asm__ __volatile__("sync; li %0,0; stb %0,%1(13)"
+	: "=&r" (tmp) : "i" (offsetof(struct paca_struct, io_sync))
+	: "memory");
 }
 
 /*
diff --git a/include/asm-powerpc/iommu.h b/include/asm-powerpc/iommu.h
index a5e9864..39fad68 100644
--- a/include/asm-powerpc/iommu.h
+++ b/include/asm-powerpc/iommu.h
@@ -22,17 +22,35 @@
 #define _ASM_IOMMU_H
 #ifdef __KERNEL__
 
-#include <asm/types.h>
+#include <linux/compiler.h>
 #include <linux/spinlock.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <asm/types.h>
+#include <asm/bitops.h>
+
+#define IOMMU_PAGE_SHIFT      12
+#define IOMMU_PAGE_SIZE       (ASM_CONST(1) << IOMMU_PAGE_SHIFT)
+#define IOMMU_PAGE_MASK       (~((1 << IOMMU_PAGE_SHIFT) - 1))
+#define IOMMU_PAGE_ALIGN(addr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE)
+
+#ifndef __ASSEMBLY__
+
+/* Pure 2^n version of get_order */
+static __inline__ __attribute_const__ int get_iommu_order(unsigned long size)
+{
+	return __ilog2((size - 1) >> IOMMU_PAGE_SHIFT) + 1;
+}
+
+#endif   /* __ASSEMBLY__ */
+
 
 /*
  * IOMAP_MAX_ORDER defines the largest contiguous block
  * of dma space we can get.  IOMAP_MAX_ORDER = 13
  * allows up to 2**12 pages (4096 * 4096) = 16 MB
  */
-#define IOMAP_MAX_ORDER 13
+#define IOMAP_MAX_ORDER		13
 
 struct iommu_table {
 	unsigned long  it_busno;     /* Bus number this table belongs to */
diff --git a/include/asm-powerpc/oprofile_impl.h b/include/asm-powerpc/oprofile_impl.h
index 5b33994..07a10e5 100644
--- a/include/asm-powerpc/oprofile_impl.h
+++ b/include/asm-powerpc/oprofile_impl.h
@@ -42,7 +42,7 @@
 	void (*reg_setup) (struct op_counter_config *,
 			   struct op_system_config *,
 			   int num_counters);
-	void (*cpu_setup) (void *);
+	void (*cpu_setup) (struct op_counter_config *);
 	void (*start) (struct op_counter_config *);
 	void (*stop) (void);
 	void (*handle_interrupt) (struct pt_regs *,
@@ -121,7 +121,90 @@
 		break;
 	}
 }
-#endif /* !CONFIG_FSL_BOOKE */
+#else /* CONFIG_FSL_BOOKE */
+static inline u32 get_pmlca(int ctr)
+{
+	u32 pmlca;
+
+	switch (ctr) {
+		case 0:
+			pmlca = mfpmr(PMRN_PMLCA0);
+			break;
+		case 1:
+			pmlca = mfpmr(PMRN_PMLCA1);
+			break;
+		case 2:
+			pmlca = mfpmr(PMRN_PMLCA2);
+			break;
+		case 3:
+			pmlca = mfpmr(PMRN_PMLCA3);
+			break;
+		default:
+			panic("Bad ctr number\n");
+	}
+
+	return pmlca;
+}
+
+static inline void set_pmlca(int ctr, u32 pmlca)
+{
+	switch (ctr) {
+		case 0:
+			mtpmr(PMRN_PMLCA0, pmlca);
+			break;
+		case 1:
+			mtpmr(PMRN_PMLCA1, pmlca);
+			break;
+		case 2:
+			mtpmr(PMRN_PMLCA2, pmlca);
+			break;
+		case 3:
+			mtpmr(PMRN_PMLCA3, pmlca);
+			break;
+		default:
+			panic("Bad ctr number\n");
+	}
+}
+
+static inline unsigned int ctr_read(unsigned int i)
+{
+	switch(i) {
+		case 0:
+			return mfpmr(PMRN_PMC0);
+		case 1:
+			return mfpmr(PMRN_PMC1);
+		case 2:
+			return mfpmr(PMRN_PMC2);
+		case 3:
+			return mfpmr(PMRN_PMC3);
+		default:
+			return 0;
+	}
+}
+
+static inline void ctr_write(unsigned int i, unsigned int val)
+{
+	switch(i) {
+		case 0:
+			mtpmr(PMRN_PMC0, val);
+			break;
+		case 1:
+			mtpmr(PMRN_PMC1, val);
+			break;
+		case 2:
+			mtpmr(PMRN_PMC2, val);
+			break;
+		case 3:
+			mtpmr(PMRN_PMC3, val);
+			break;
+		default:
+			break;
+	}
+}
+
+
+#endif /* CONFIG_FSL_BOOKE */
+
 
 extern void op_powerpc_backtrace(struct pt_regs * const regs, unsigned int depth);
 
diff --git a/include/asm-powerpc/pmc.h b/include/asm-powerpc/pmc.h
index 07d6a42..8588be6 100644
--- a/include/asm-powerpc/pmc.h
+++ b/include/asm-powerpc/pmc.h
@@ -32,18 +32,5 @@
 void power4_enable_pmcs(void);
 #endif
 
-#ifdef CONFIG_FSL_BOOKE
-void init_pmc_stop(int ctr);
-void set_pmc_event(int ctr, int event);
-void set_pmc_user_kernel(int ctr, int user, int kernel);
-void set_pmc_marked(int ctr, int mark0, int mark1);
-void pmc_start_ctr(int ctr, int enable);
-void pmc_start_ctrs(int enable);
-void pmc_stop_ctrs(void);
-void dump_pmcs(void);
-
-extern struct op_powerpc_model op_model_fsl_booke;
-#endif
-
 #endif /* __KERNEL__ */
 #endif /* _POWERPC_PMC_H */
diff --git a/include/asm-powerpc/system.h b/include/asm-powerpc/system.h
index 4362759..f7b1227 100644
--- a/include/asm-powerpc/system.h
+++ b/include/asm-powerpc/system.h
@@ -25,8 +25,8 @@
  *
  * We have to use the sync instructions for mb(), since lwsync doesn't
  * order loads with respect to previous stores.  Lwsync is fine for
- * rmb(), though.  Note that lwsync is interpreted as sync by
- * 32-bit and older 64-bit CPUs.
+ * rmb(), though. Note that rmb() actually uses a sync on 32-bit
+ * architectures.
  *
  * For wmb(), we use sync since wmb is used in drivers to order
  * stores to system memory with respect to writes to the device.
@@ -34,7 +34,7 @@
  * SMP since it is only used to order updates to system memory.
  */
 #define mb()   __asm__ __volatile__ ("sync" : : : "memory")
-#define rmb()  __asm__ __volatile__ ("lwsync" : : : "memory")
+#define rmb()  __asm__ __volatile__ (__stringify(LWSYNC) : : : "memory")
 #define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
 #define read_barrier_depends()  do { } while(0)
 
diff --git a/include/asm-powerpc/tce.h b/include/asm-powerpc/tce.h
index c9483ad..f663634 100644
--- a/include/asm-powerpc/tce.h
+++ b/include/asm-powerpc/tce.h
@@ -22,6 +22,8 @@
 #define _ASM_POWERPC_TCE_H
 #ifdef __KERNEL__
 
+#include <asm/iommu.h>
+
 /*
  * Tces come in two formats, one for the virtual bus and a different
  * format for PCI
@@ -33,7 +35,6 @@
 
 #define TCE_SHIFT	12
 #define TCE_PAGE_SIZE	(1 << TCE_SHIFT)
-#define TCE_PAGE_FACTOR	(PAGE_SHIFT - TCE_SHIFT)
 
 #define TCE_ENTRY_SIZE		8		/* each TCE is 64 bits */